{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":43,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":43,"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":"0bc1e9e6864c","filters":{"venue":"Proceedings of the ACM on Management of Data"}},"results":[{"id":"W4380433238","doi":"10.1145/3588911","title":"A Universal Question-Answering Platform for Knowledge Graphs","year":2023,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Topic Modeling","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"SPARQL; Computer science; Question answering; RDF; Information retrieval; Set (abstract data type); Named graph; Representation (politics); Query language; Artificial intelligence; Semantic Web; Programming language","authors":[{"name":"Reham Omar","is_ca":true},{"name":"Ishika Dhall","is_ca":true},{"name":"Panos Kalnis","is_ca":false},{"name":"E. M. E. Mansour","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09927151819617334,"gpt":0.3177039142849232,"spread":0.2184323960887498,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0006048317,0.00008515253,0.000111372,0.0001504991,0.00007119818,0.00003961353,0.007544034,0.00002244669,9.863819e-7],"category_scores_gemma":[0.0001350773,0.00006854083,0.00004609227,0.0005500299,0.00002738118,0.0007096175,0.007354468,0.00005244176,0.000005032432],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001838592,"about_ca_system_score_gemma":0.000009081826,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005856077,"about_ca_topic_score_gemma":8.384681e-7,"domain_scores_codex":[0.9990878,0.000001710891,0.0001863406,0.000331294,0.0002273092,0.0001656158],"domain_scores_gemma":[0.9984491,0.00005987484,0.000140423,0.001249256,0.00007871418,0.00002267008],"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":[0.00001378525,0.00004226855,0.0002860567,0.0005799173,0.00007305313,2.866145e-7,0.0003152814,0.00007311962,0.0004139628,0.9596515,0.00936765,0.02918312],"study_design_scores_gemma":[0.00168414,0.0002413216,0.003984808,0.001522074,0.0001528594,0.000001755122,0.001782757,0.5517629,0.007794406,0.4104829,0.0201283,0.0004617929],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7661267,0.0003603731,0.1600273,0.01874615,0.0028267,0.004794293,0.0002556251,0.001573241,0.04528968],"genre_scores_gemma":[0.7826145,0.0001440019,0.2159223,0.00004845789,0.0000466331,0.00002472181,0.00001512444,0.00001789115,0.001166429],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5516898,"threshold_uncertainty_score":0.9978256,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4380433250","doi":"10.1145/3588704","title":"How To Optimize My Blockchain? A Multi-Level Recommendation Approach","year":2023,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Blockchain Technology Applications and Security","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Deutsche Forschungsgemeinschaft","keywords":"Blockchain; Computer science; Distributed computing; Data science; Computer security","authors":[{"name":"Jeeta Ann Chacko","is_ca":false},{"name":"Ruben Mayer","is_ca":false},{"name":"Hans‐Arno Jacobsen","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1258081962844258,"gpt":0.3060546250598179,"spread":0.1802464287753921,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0008395089,0.0001255829,0.0001634282,0.0002295387,0.0001135582,0.00007026913,0.01077578,0.00005775071,0.000001525916],"category_scores_gemma":[0.0001950811,0.00009951457,0.00003919371,0.001502663,0.00005452628,0.0002233779,0.01348735,0.0001248038,0.000008796987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001768912,"about_ca_system_score_gemma":0.000005653841,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004393155,"about_ca_topic_score_gemma":4.942075e-7,"domain_scores_codex":[0.9987285,0.000006401373,0.0002214444,0.0005675533,0.0002695479,0.0002065667],"domain_scores_gemma":[0.997321,0.00003278373,0.0002282523,0.00227862,0.0001039971,0.00003535956],"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":[0.00003692567,0.001014844,0.0005035849,0.0007212822,0.0003313279,5.92867e-7,0.0008652809,0.0001857036,0.001843942,0.4919499,0.1479572,0.3545895],"study_design_scores_gemma":[0.00303016,0.0003681606,0.01438004,0.0004447779,0.0001951895,0.000007089463,0.005331575,0.8377447,0.02275477,0.05782834,0.05687067,0.001044541],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1140972,0.00004845676,0.541401,0.3297267,0.0004150323,0.00521391,0.00048569,0.001484885,0.007127084],"genre_scores_gemma":[0.2679747,0.00004111805,0.7308471,0.0002041792,0.0000142961,0.0001182508,0.00002866146,0.00001110877,0.0007605671],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.837559,"threshold_uncertainty_score":0.9945764,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4393212300","doi":"10.1145/3639311","title":"Fast Shapley Value Computation in Data Assemblage Tasks as Cooperative Simple Games","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":12,"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":"Shapley value; Simple (philosophy); Computation; Assemblage (archaeology); Value (mathematics); Computer science; Mathematical economics; Mathematics; Game theory; Algorithm; Geography; Machine learning; Archaeology","authors":[{"name":"Xuan Luo","is_ca":true},{"name":"Jian Pei","is_ca":false},{"name":"Cheng Xu","is_ca":false},{"name":"Wenjie Zhang","is_ca":false},{"name":"Jianliang Xu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06813038036782831,"gpt":0.3467607599894598,"spread":0.2786303796216315,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0008514842,0.0001590679,0.0002202775,0.0001396386,0.00006096109,0.0001418796,0.007396961,0.00002695137,0.000005494342],"category_scores_gemma":[0.0002490589,0.000115988,0.00002450493,0.0007176443,0.00006702937,0.003111049,0.01730037,0.0001310251,0.00001408769],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002717366,"about_ca_system_score_gemma":0.00002658915,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000725443,"about_ca_topic_score_gemma":0.0000123715,"domain_scores_codex":[0.9981644,0.00001646681,0.0003894526,0.0007413389,0.0005028596,0.0001854428],"domain_scores_gemma":[0.9972861,0.00009664791,0.000187576,0.002320606,0.00007974009,0.00002931813],"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":[0.00003710249,0.0001966733,0.0003171994,0.001821132,0.0002182464,0.00001529544,0.0009310828,0.0009278851,0.002453232,0.8545437,0.07050718,0.06803128],"study_design_scores_gemma":[0.001288273,0.0003994692,0.004176729,0.005130658,0.0001582981,0.00001874541,0.005617694,0.7638069,0.01381791,0.03225217,0.1724557,0.0008774431],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1890707,0.002451962,0.7502224,0.01840702,0.001863708,0.00551639,0.00770326,0.0008036772,0.02396086],"genre_scores_gemma":[0.7714996,0.0002777776,0.2267274,0.0002197143,0.00007009653,0.00002422481,0.0007282816,0.00002872336,0.0004241282],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8222915,"threshold_uncertainty_score":0.9979735,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4402426760","doi":"10.1145/3698820","title":"Memento Filter: A Fast, Dynamic, and Robust Range Filter","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Caching and Content Delivery","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Universitas Brawijaya","keywords":"Computer science; Range query (database); Filter (signal processing); Bloom filter; Key (lock); Range (aeronautics); Data mining; Information retrieval; Artificial intelligence; Algorithm; Computer vision; Search engine; Computer security; Web search query","authors":[{"name":"Navid Eslami","is_ca":false},{"name":"Niv Dayan","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05317012316491179,"gpt":0.2665536884634266,"spread":0.2133835652985148,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0004626812,0.0001268714,0.0001409349,0.0001144773,0.00005387934,0.0002183104,0.005352612,0.00002182537,0.000008685229],"category_scores_gemma":[0.00003500273,0.00009004776,0.00005174481,0.0002580696,0.0000462665,0.0008240303,0.00908743,0.0001009771,0.000007443359],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001716712,"about_ca_system_score_gemma":0.000004917244,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001464545,"about_ca_topic_score_gemma":0.000001346413,"domain_scores_codex":[0.9987699,0.000005404166,0.0002098782,0.0004772414,0.0003791621,0.0001584109],"domain_scores_gemma":[0.9985127,0.00003578567,0.00009074813,0.001290959,0.00003976185,0.00003000145],"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":[0.0001472681,0.000491929,0.002009017,0.007038311,0.001480587,0.00002691449,0.001522437,0.00008888067,0.008884511,0.1665637,0.4020627,0.4096837],"study_design_scores_gemma":[0.002502883,0.0006861474,0.01069634,0.007062045,0.0008135245,0.00003589156,0.001630458,0.8807132,0.002722015,0.02856022,0.0633632,0.001214143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7481349,0.009345307,0.04534461,0.1229169,0.003918058,0.004295986,0.001106762,0.001402466,0.06353503],"genre_scores_gemma":[0.9499611,0.0007493513,0.04323002,0.0005542551,0.00004728729,0.00002321958,0.00001956493,0.00002561277,0.005389536],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8806242,"threshold_uncertainty_score":0.9989269,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4399174291","doi":"10.1145/3654963","title":"OTClean: Data Cleaning for Conditional Independence Violations using Optimal Transport","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"Universitas Brawijaya","keywords":"Computer science; Scalability; Mathematical optimization; Independence (probability theory); Mathematics","authors":[{"name":"Alireza Pirhadi","is_ca":true},{"name":"Mohammad Hossein Moslemi","is_ca":true},{"name":"Alexander Cloninger","is_ca":false},{"name":"Mostafa Milani","is_ca":true},{"name":"Babak Salimi","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1243438065986618,"gpt":0.3641923593716973,"spread":0.2398485527730355,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001167637,0.0001375402,0.0001603445,0.0001084206,0.0001692001,0.000110118,0.0132617,0.00004329223,0.00001064247],"category_scores_gemma":[0.0002543516,0.0001161313,0.00005000392,0.0004773217,0.00007938879,0.002619752,0.008566443,0.0002184535,0.000002078208],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002918773,"about_ca_system_score_gemma":0.00003941914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007751763,"about_ca_topic_score_gemma":4.667616e-7,"domain_scores_codex":[0.9981532,0.000006811773,0.0003433266,0.0006852566,0.0006174715,0.0001939547],"domain_scores_gemma":[0.9975135,0.0001325283,0.0002205271,0.002004114,0.00009990761,0.00002938809],"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":[0.00009045592,0.0001823696,0.003155122,0.002264482,0.0006319392,0.000006737579,0.0005692481,0.04409605,0.001740423,0.9128144,0.008483176,0.02596556],"study_design_scores_gemma":[0.0002774451,0.00004344212,0.001948513,0.0005907605,0.0001625042,0.000005206388,0.0002626593,0.9804069,0.0003233357,0.0125913,0.003225197,0.0001627812],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0236423,0.00007945192,0.971218,0.002276841,0.0003814142,0.0006422068,0.0005595881,0.0001413885,0.001058778],"genre_scores_gemma":[0.5674987,0.00001115843,0.4321807,0.00003499403,0.00006175147,0.000004349426,0.0001419916,0.00001346612,0.00005284139],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9363108,"threshold_uncertainty_score":0.9994521,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4389609557","doi":"10.1145/3626761","title":"DProvDB: Differentially Private Query Processing with Multi-Analyst Provenance","year":2023,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Privacy-Preserving Technologies in Data","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":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Differential privacy; Computer science; Privilege (computing); Private information retrieval; Computer security; Database; Data mining","authors":[{"name":"Shufan Zhang","is_ca":true},{"name":"Xi He","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08080241617828675,"gpt":0.3053888409634237,"spread":0.224586424785137,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0008214986,0.0002447723,0.0003143331,0.0002550271,0.0001389914,0.0001847346,0.1121326,0.00005989052,0.000001509673],"category_scores_gemma":[0.003805874,0.0001605587,0.00005023276,0.001975465,0.000203841,0.00171585,0.2895361,0.0002260115,0.000009425328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003448275,"about_ca_system_score_gemma":0.00002547655,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008429066,"about_ca_topic_score_gemma":0.000001881453,"domain_scores_codex":[0.997299,0.000009562658,0.0004382505,0.0009658078,0.0008835239,0.0004038254],"domain_scores_gemma":[0.9851438,0.00004429337,0.0007163389,0.0139097,0.0001504214,0.00003546114],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003324294,0.00181797,0.04533802,0.01388877,0.001944399,0.00003877956,0.0004030289,0.00007117314,0.03180781,0.08149703,0.4267505,0.3961101],"study_design_scores_gemma":[0.00409801,0.0007230832,0.1160266,0.008874075,0.0006622446,0.00001355473,0.000806903,0.4390196,0.1075009,0.3124638,0.007992337,0.001818841],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6555503,0.0004891714,0.1507843,0.1717355,0.0008676772,0.007140427,0.0006560421,0.006356523,0.006419953],"genre_scores_gemma":[0.421962,0.0001471763,0.5774327,0.0000678195,0.00001614527,0.00004822223,0.00002920575,0.00002957147,0.0002671766],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4389484,"threshold_uncertainty_score":0.8926712,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4389609606","doi":"10.1145/3626760","title":"Waffle: An Online Oblivious Datastore for Protecting Data Access Patterns","year":2023,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Cryptography and Data Security","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":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Universitas Brawijaya","keywords":"Computer science; Overhead (engineering); Benchmark (surveying); Adversary; Flexibility (engineering); Data access; Bandwidth (computing); Database; Distributed computing; Computer network; Operating system; Computer security","authors":[{"name":"Sujaya Maiyya","is_ca":true},{"name":"Sharath Chandra Vemula","is_ca":false},{"name":"Divyakant Agrawal","is_ca":false},{"name":"Amr El Abbadi","is_ca":false},{"name":"Florian Kerschbaum","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3094247226058124,"gpt":0.395503019242454,"spread":0.08607829663664163,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001696395,0.0001749463,0.000210991,0.0002097724,0.0001936319,0.0002694929,0.0461933,0.00003853066,0.0000033996],"category_scores_gemma":[0.0004945143,0.0001352398,0.0000424672,0.001164475,0.00005511833,0.004649607,0.06065496,0.0001685664,0.000001984416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009135771,"about_ca_system_score_gemma":0.0000132793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004839809,"about_ca_topic_score_gemma":0.00002372538,"domain_scores_codex":[0.9977684,0.00001258464,0.000366339,0.0009848602,0.000558951,0.0003088863],"domain_scores_gemma":[0.9918916,0.00009531283,0.0004102179,0.007441381,0.0001064388,0.00005504358],"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":[0.0002750595,0.002388853,0.02093963,0.009096486,0.0008014905,0.000007095789,0.0008389049,0.00003119596,0.001437251,0.1193393,0.281529,0.5633158],"study_design_scores_gemma":[0.007925739,0.002847778,0.2232691,0.006242944,0.0012042,0.00002203462,0.00782067,0.3587001,0.01255722,0.211375,0.1647696,0.003265605],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8084424,0.000124368,0.07918793,0.01381914,0.001446414,0.00780594,0.08732568,0.001243621,0.0006045459],"genre_scores_gemma":[0.683665,0.0003803383,0.2998813,0.0004059709,0.000299171,0.0001072191,0.01516485,0.00006116505,0.00003489106],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5600502,"threshold_uncertainty_score":0.9589673,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4381329253","doi":"10.1145/3589298","title":"Computing the Difference of Conjunctive Queries Efficiently","year":2023,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Advanced Database Systems and Queries","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":"Rewriting; Computer science; Query optimization; Heuristics; Operator (biology); Spatial query; Benchmark (surveying); Boolean conjunctive query; Set (abstract data type); Class (philosophy); Conjunctive query; SQL; Theoretical computer science; Algorithm; Sargable; Relational database; Search engine; Database; Information retrieval; Web search query","authors":[{"name":"Xiao Hu","is_ca":true},{"name":"Qichen Wang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06453656104710064,"gpt":0.3010111735680607,"spread":0.23647461252096,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0007263005,0.000120364,0.000210772,0.00007749945,0.0001244191,0.00002585767,0.006764605,0.00001656891,0.000001277877],"category_scores_gemma":[0.0003010224,0.00006775485,0.00004390653,0.0008355996,0.0002275442,0.0004132124,0.01417669,0.00008221818,0.000004143013],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008907376,"about_ca_system_score_gemma":0.00001013264,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002377506,"about_ca_topic_score_gemma":0.000001184099,"domain_scores_codex":[0.9986205,0.00001184252,0.0003349969,0.000349005,0.0005053509,0.0001782914],"domain_scores_gemma":[0.99721,0.0001673279,0.0004981662,0.00196917,0.0001375104,0.00001787361],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00003953294,0.00009681017,0.00284151,0.001075976,0.0001622806,8.51968e-7,0.001151381,0.0001325617,0.003717989,0.9608345,0.007160863,0.02278575],"study_design_scores_gemma":[0.004106314,0.001528385,0.441026,0.01123882,0.0004981742,0.00001556114,0.03662856,0.1257455,0.2332039,0.07698001,0.06712793,0.001900789],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8170424,0.0002827188,0.1535981,0.009715632,0.001445495,0.002625601,0.0008552854,0.0004210245,0.01401371],"genre_scores_gemma":[0.9632377,0.00006735211,0.03622412,0.00006740598,0.00002352989,0.00000758291,0.00001460292,0.00000924198,0.0003484943],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8838544,"threshold_uncertainty_score":0.9986092,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4381329270","doi":"10.1145/3589322","title":"Maestro: Automatic Generation of Comprehensive Benchmarks for Question Answering Over Knowledge Graphs","year":2023,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Advanced Graph Neural Networks","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":"Carleton University","funders":"","keywords":"Computer science; Benchmark (surveying); Question answering; Knowledge base; Vocabulary; Natural language; Information retrieval; Set (abstract data type); Natural language understanding; Knowledge graph; Usability; Artificial intelligence; Natural language processing; Programming language; Human–computer interaction; Linguistics","authors":[{"name":"Abdelghny Orogat","is_ca":true},{"name":"Ahmed El-Roby","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1019414078019133,"gpt":0.3440120252621289,"spread":0.2420706174602156,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003286015,0.0001266707,0.0001925608,0.0001814142,0.00006667955,0.00002875395,0.003945779,0.00003291727,0.000001435403],"category_scores_gemma":[0.00007565413,0.0001031526,0.00006636792,0.0008809985,0.00005939749,0.0007582035,0.003621084,0.00006639669,8.554737e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001340415,"about_ca_system_score_gemma":0.000005209152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002220491,"about_ca_topic_score_gemma":7.947879e-7,"domain_scores_codex":[0.9988128,0.00000867979,0.0003436856,0.0003690156,0.0002909776,0.0001748253],"domain_scores_gemma":[0.9981825,0.00008908675,0.0004037564,0.001139842,0.0001620451,0.00002277489],"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":[0.00005910853,0.0002930654,0.002184746,0.00435893,0.000354902,9.069694e-7,0.0004049941,0.003033863,0.04857857,0.7534453,0.07105367,0.116232],"study_design_scores_gemma":[0.0008526017,0.0003081538,0.02723791,0.001103665,0.0001105794,0.000001083867,0.0001801299,0.8777387,0.02010193,0.07105391,0.001047971,0.0002633825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9802012,0.0002187125,0.01508426,0.001200575,0.0007021718,0.001702162,0.00008309697,0.0001944579,0.0006133682],"genre_scores_gemma":[0.8480173,0.0002343549,0.1514501,0.00004335195,0.00003987854,0.00004132933,0.00008456816,0.00001594289,0.00007315879],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8747048,"threshold_uncertainty_score":0.7332304,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4407356147","doi":"10.1145/3709719","title":"Reliable Text-to-SQL with Adaptive Abstention","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Distributed and Parallel Computing Systems","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University; University of Toronto","funders":"","keywords":"Computer science; SQL; Programming language; Database","authors":[{"name":"Kaiwen Chen","is_ca":true},{"name":"Yueting Chen","is_ca":false},{"name":"Nick Koudas","is_ca":true},{"name":"Xiaohui Yu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03721397291859412,"gpt":0.2741668219245275,"spread":0.2369528490059334,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0004960598,0.0001083104,0.0001585676,0.0001072813,0.00007203928,0.0000819789,0.008341542,0.00002164034,0.000001294886],"category_scores_gemma":[0.00004974271,0.00007304428,0.00003100393,0.0008598426,0.00002872769,0.0003657976,0.006209785,0.00006846543,0.00001036481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000207606,"about_ca_system_score_gemma":0.00001339284,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001369832,"about_ca_topic_score_gemma":4.731428e-7,"domain_scores_codex":[0.9988154,0.000004866989,0.0002378821,0.0004100239,0.0003725998,0.0001592177],"domain_scores_gemma":[0.9979588,0.00002589425,0.0002235868,0.001624074,0.0001429893,0.00002468381],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001851634,0.0003920651,0.003737384,0.001412963,0.0005635452,0.000001731319,0.0002895336,0.001469888,0.0006248912,0.7292243,0.2361812,0.02591744],"study_design_scores_gemma":[0.009586477,0.004309912,0.1990767,0.03966447,0.001219126,0.00001859644,0.006592786,0.1678176,0.01924423,0.1537234,0.3959917,0.002755016],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1333856,0.0002984839,0.390639,0.02994033,0.001873072,0.004966131,0.0003803947,0.000633179,0.4378838],"genre_scores_gemma":[0.927381,0.000008973928,0.06936678,0.0001661547,0.00001443073,0.00001055705,0.000009666273,0.000005616913,0.00303685],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7939954,"threshold_uncertainty_score":0.9970238,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4380433188","doi":"10.1145/3588711","title":"dbET: Execution Time Distribution-based Plan Selection","year":2023,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Huawei Technologies (Canada); University of Toronto; York University","funders":"","keywords":"Computer science; Query plan; Plan (archaeology); Complement (music); Selection (genetic algorithm); Execution time; Overhead (engineering); Query optimization; Database; Sargable; Distributed computing; Programming language; Information retrieval; Web search query; Search engine; Artificial intelligence","authors":[{"name":"Yifan Li","is_ca":true},{"name":"Xiaohui Yu","is_ca":true},{"name":"Nick Koudas","is_ca":true},{"name":"Shu Lin","is_ca":true},{"name":"Calvin Sun","is_ca":true},{"name":"Chong Chen","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04636754490894221,"gpt":0.2778059725457491,"spread":0.2314384276368069,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004808872,0.00009272507,0.0001175464,0.0000708477,0.0001026344,0.00002618614,0.002949895,0.00002159729,0.000004363941],"category_scores_gemma":[0.000131979,0.00006994965,0.00003079206,0.000824485,0.00003955194,0.0007406122,0.002874291,0.00005480977,0.00003409672],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002557509,"about_ca_system_score_gemma":0.000009967477,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009335869,"about_ca_topic_score_gemma":4.3189e-7,"domain_scores_codex":[0.9989184,0.000006029392,0.0002135479,0.0003226448,0.000388967,0.0001504806],"domain_scores_gemma":[0.9985195,0.00003049852,0.0002367508,0.001112383,0.00007921548,0.00002162658],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009440284,0.0002245666,0.002641084,0.001400683,0.0001712189,0.00000165738,0.00009632921,0.0004190713,0.01204911,0.5911238,0.3689598,0.02281819],"study_design_scores_gemma":[0.002525915,0.0007186517,0.05291063,0.003007377,0.0002188604,0.000007184514,0.0006766396,0.3496422,0.1370789,0.02329834,0.4288169,0.001098371],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2911014,0.0001580907,0.6475309,0.02962072,0.00220282,0.00500111,0.008321313,0.002611316,0.0134524],"genre_scores_gemma":[0.8320891,0.0001054698,0.1619623,0.0002130573,0.0001606364,0.00008336881,0.002408709,0.0000388918,0.002938434],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5678255,"threshold_uncertainty_score":0.5481688,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4381326963","doi":"10.1145/3589290","title":"OM3: An Ordered Multi-level Min-Max Representation for Interactive Progressive Visualization of Time Series","year":2023,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; National Science Foundation","keywords":"Computer science; Zoom; Visualization; Representation (politics); Ranging; Latency (audio); Series (stratigraphy); Data mining; Computer graphics (images)","authors":[{"name":"Yunhai Wang","is_ca":false},{"name":"Y. L. Wang","is_ca":false},{"name":"Xin Chen","is_ca":false},{"name":"Yue Zhao","is_ca":false},{"name":"Fan Zhang","is_ca":false},{"name":"Eugene Wu","is_ca":false},{"name":"Chi‐Wing Fu","is_ca":false},{"name":"Xiaohui Yu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1413222286035876,"gpt":0.3732153580399873,"spread":0.2318931294363998,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004375286,0.0001019543,0.0001962606,0.0001464674,0.00007693483,0.00006554772,0.003269394,0.00002327672,0.000006431816],"category_scores_gemma":[0.000446274,0.00007875152,0.00005574996,0.000848534,0.00005746737,0.001720335,0.003509484,0.00003098712,0.000002349517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001119536,"about_ca_system_score_gemma":0.0000074895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000990204,"about_ca_topic_score_gemma":0.000001512933,"domain_scores_codex":[0.9988141,0.000009606769,0.0003493549,0.0003787119,0.000316649,0.0001315533],"domain_scores_gemma":[0.9979216,0.00005196381,0.0007358323,0.0009169249,0.0003541771,0.00001950993],"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":[0.001970806,0.002776809,0.0112244,0.006752474,0.004375996,0.000004970481,0.0159474,0.002052113,0.08315227,0.1775746,0.04776203,0.6464061],"study_design_scores_gemma":[0.00163246,0.0009790356,0.02340087,0.001165495,0.0004214787,0.000002151795,0.006547365,0.8437217,0.1099864,0.01077947,0.0009493969,0.0004141883],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7976819,0.0001763762,0.1761605,0.009680131,0.0008348535,0.008864141,0.001563452,0.0007117024,0.004326908],"genre_scores_gemma":[0.5778777,0.00006195882,0.4192698,0.00003816529,0.00004937346,0.00007896256,0.0004347041,0.00003329237,0.002156046],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8416696,"threshold_uncertainty_score":0.6075401,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4393183687","doi":"10.1145/3639279","title":"DTT: An Example-Driven Tabular Transformer for Joinability by Leveraging Large Language Models","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Topic Modeling","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Transformer; Computer science; Engineering; Electrical engineering; Voltage","authors":[{"name":"Arash Nobari","is_ca":true},{"name":"Davood Rafiei","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1034483500304466,"gpt":0.3135535429041299,"spread":0.2101051928736833,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.001020412,0.0001410283,0.0001770954,0.00007531972,0.00007403425,0.0001305876,0.006777298,0.00003344394,0.000005912318],"category_scores_gemma":[0.00003270242,0.0001083073,0.00006895718,0.0002364509,0.00002739451,0.001814663,0.002141988,0.0001039159,0.000001051985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000309453,"about_ca_system_score_gemma":0.00001259022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005040476,"about_ca_topic_score_gemma":0.000002233174,"domain_scores_codex":[0.998341,0.000006780432,0.0002984295,0.0006866871,0.0004056437,0.0002615245],"domain_scores_gemma":[0.9978883,0.00003836085,0.00008842078,0.00188624,0.00005954535,0.00003919055],"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":[0.00006730713,0.0006777084,0.0004567385,0.008183014,0.0005037949,0.000002951273,0.01043204,0.001083869,0.0191301,0.7719576,0.02803653,0.1594683],"study_design_scores_gemma":[0.0004619313,0.00009157027,0.00006154757,0.00037819,0.00008968128,8.198775e-7,0.001028081,0.9256535,0.008482542,0.05390392,0.009634013,0.0002142011],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1769517,0.0003968514,0.8154009,0.003943454,0.0002164728,0.00121592,0.0003027914,0.0001863628,0.001385517],"genre_scores_gemma":[0.8571216,0.00003576341,0.1424001,0.0001222814,0.00003108404,0.00002959426,0.00003553982,0.00001719983,0.0002067466],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9245696,"threshold_uncertainty_score":0.9985965,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4399174293","doi":"10.1145/3654921","title":"Reservoir Sampling over Joins","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":6,"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":"Joins; Tuple; Computer science; Join (topology); Graph; Theoretical computer science; Sampling (signal processing); Operator (biology); Data mining; Mathematics; Discrete mathematics","authors":[{"name":"Binyang Dai","is_ca":false},{"name":"Xiao Hu","is_ca":true},{"name":"Ke Yi","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.12639640691388,"gpt":0.35644566552144,"spread":0.23004925860756,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0007913063,0.0001225803,0.0001387795,0.0001549722,0.00004645425,0.00021136,0.01753785,0.000028986,0.000007797756],"category_scores_gemma":[0.0002213357,0.00008835139,0.00004654874,0.0006329475,0.00005640659,0.001413268,0.02627618,0.0001275121,0.000009249996],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002409232,"about_ca_system_score_gemma":0.00001135436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001236989,"about_ca_topic_score_gemma":4.109657e-7,"domain_scores_codex":[0.9984995,0.000004093562,0.0002636488,0.0005338515,0.0005225379,0.0001763938],"domain_scores_gemma":[0.9964963,0.00006712403,0.0001372459,0.003226153,0.0000478999,0.00002526079],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001225787,0.00010128,0.0006106788,0.001328099,0.0001790521,0.000002752041,0.0001522855,0.00000223844,0.002167499,0.5522776,0.3901671,0.05299922],"study_design_scores_gemma":[0.0006327116,0.0005233621,0.01679902,0.01016505,0.0003162784,0.00001255231,0.0003674848,0.02971886,0.06761117,0.4356281,0.4373125,0.0009129881],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5219773,0.00223277,0.1143882,0.08472753,0.003773032,0.005495519,0.002703296,0.006583806,0.2581185],"genre_scores_gemma":[0.25835,0.0002050345,0.7405537,0.0001528861,0.00005383756,0.00001547874,0.00002589906,0.00002379924,0.0006193818],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6261654,"threshold_uncertainty_score":0.9877777,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4396892532","doi":"10.1145/3651599","title":"Fast Matrix Multiplication for Query Processing","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Distributed and Parallel Computing Systems","field":"Computer Science","cited_by":6,"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; Matrix multiplication; Multiplication (music); Query optimization; Matrix (chemical analysis); Arithmetic; Information retrieval; Mathematics; Physics; Chemistry; Combinatorics","authors":[{"name":"Xiao Hu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0612702140294622,"gpt":0.3339377198722386,"spread":0.2726675058427764,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0006397471,0.000100074,0.0001250934,0.00007674519,0.00006897109,0.0002134123,0.006954094,0.00002596887,5.024006e-7],"category_scores_gemma":[0.00007286244,0.00007209273,0.0000510107,0.0004465298,0.00002587648,0.0006272839,0.003342333,0.0000578873,0.000004922032],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001724117,"about_ca_system_score_gemma":0.00001450509,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000302766,"about_ca_topic_score_gemma":9.123264e-8,"domain_scores_codex":[0.998865,0.000003572121,0.0002753411,0.0004196207,0.0002926524,0.0001437933],"domain_scores_gemma":[0.998528,0.00005096576,0.0001957663,0.00110377,0.0001020981,0.00001942123],"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":[0.00004590833,0.0002609143,0.0005977541,0.01548317,0.0002819637,8.581595e-7,0.0006807054,0.0004227698,0.00335974,0.4684806,0.1261558,0.3842298],"study_design_scores_gemma":[0.0006698997,0.00017112,0.002027971,0.005250718,0.0001521714,0.000006769897,0.0004070881,0.8515188,0.004497035,0.03049108,0.1044022,0.000405133],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03083707,0.001912696,0.9302827,0.01765155,0.00148777,0.003493401,0.0004712887,0.0008706589,0.0129929],"genre_scores_gemma":[0.8862575,0.00001919905,0.1128635,0.00003036093,0.00006922441,0.00002613004,0.00003003821,0.0000109605,0.0006930982],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8554204,"threshold_uncertainty_score":0.9984187,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4404130423","doi":"10.1145/3695835","title":"Computing A Well-Representative Summary of Conjunctive Query Results","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":6,"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":"Conjunctive query; Boolean conjunctive query; Computer science; Query optimization; Query expansion; Information retrieval; Theoretical computer science; Web search query; Sargable; Data mining; Search engine; Relational database","authors":[{"name":"Pankaj K. Agarwal","is_ca":false},{"name":"Aryan Esmailpour","is_ca":false},{"name":"Xiao Hu","is_ca":true},{"name":"Stavros Sintos","is_ca":false},{"name":"Jun Yang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05242105394825337,"gpt":0.3208429987592012,"spread":0.2684219448109479,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0008256802,0.0001406818,0.0002499656,0.0001227225,0.00005312201,0.00003632825,0.00440826,0.00002293215,0.000001912833],"category_scores_gemma":[0.0002457383,0.00009851893,0.00006151331,0.0005959872,0.0001507444,0.001239496,0.01165233,0.000115092,0.000004753233],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001891235,"about_ca_system_score_gemma":0.00001857197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005359937,"about_ca_topic_score_gemma":0.000001044064,"domain_scores_codex":[0.9982798,0.00001475004,0.0004924398,0.0005642483,0.0004875518,0.0001612146],"domain_scores_gemma":[0.9974471,0.0002120127,0.0004178621,0.001756399,0.0001403466,0.0000262334],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002018753,0.0001541204,0.0003507384,0.003249928,0.0005633752,0.0000082499,0.001544159,0.00007353749,0.002572304,0.8498114,0.1224486,0.01902164],"study_design_scores_gemma":[0.006696623,0.002053833,0.01630637,0.04686313,0.0009279915,0.0000408388,0.03274987,0.1321786,0.3007231,0.09916464,0.3598875,0.002407426],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1600652,0.005846035,0.4375251,0.02835225,0.006383163,0.008554295,0.008987875,0.00127542,0.3430107],"genre_scores_gemma":[0.6875433,0.000292335,0.3102241,0.0001125841,0.00009967228,0.00001191507,0.00008714744,0.00002741514,0.001601552],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7506468,"threshold_uncertainty_score":0.9963412,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4411403538","doi":"10.1145/3725325","title":"MIRAGE-ANNS: Mixed Approach Graph-based Indexing for Approximate Nearest Neighbor Search","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Search engine indexing; Computer science; Graph; Nearest neighbor search; k-nearest neighbors algorithm; Data mining; Search engine; Context (archaeology); Search algorithm; Theoretical computer science; Machine learning; Artificial intelligence; Algorithm; Information retrieval","authors":[{"name":"Sairaj Voruganti","is_ca":true},{"name":"M. TAMER ÖZSU","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08133916376663859,"gpt":0.3436731363883481,"spread":0.2623339726217095,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.001050344,0.0001891584,0.0002661807,0.0002745615,0.0001467608,0.0001362708,0.01145339,0.00005261897,8.80191e-7],"category_scores_gemma":[0.0003363953,0.0001433404,0.000103549,0.001225233,0.0001248497,0.0009386893,0.007456416,0.0001583971,5.374391e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003438451,"about_ca_system_score_gemma":0.00003183818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005631419,"about_ca_topic_score_gemma":1.267835e-7,"domain_scores_codex":[0.9981697,0.00001146122,0.0003745825,0.0006589313,0.0004774935,0.000307819],"domain_scores_gemma":[0.9970763,0.0001130467,0.0002591551,0.002287248,0.0002306505,0.00003356807],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004824206,0.0009930077,0.002179556,0.01060391,0.0005164978,0.000001595623,0.000162672,0.0001977213,0.007933303,0.7241876,0.04306589,0.2096758],"study_design_scores_gemma":[0.002932771,0.0005760807,0.003529876,0.002434548,0.0002557175,0.000001197517,0.0006180526,0.1622672,0.6098312,0.2015322,0.01529101,0.0007302313],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002484276,0.0001319106,0.9875416,0.001959308,0.00009591965,0.001730341,0.00007189691,0.000182574,0.005802239],"genre_scores_gemma":[0.1642654,0.00007255717,0.8348446,0.0003089953,0.0000168894,0.00009290465,0.00002790666,0.00001792389,0.00035286],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6018978,"threshold_uncertainty_score":0.9938951,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4399156413","doi":"10.1145/3654985","title":"Wii: Dynamic Budget Reallocation In Index Tuning","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":5,"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; Workload; Spurious relationship; Index (typography); Set (abstract data type); Process (computing); Mathematical optimization; Budget constraint; Resource allocation; Constraint (computer-aided design); Operations research; Operating system; Mathematics; Economics","authors":[{"name":"Xiaoying Wang","is_ca":true},{"name":"Wentao Wu","is_ca":false},{"name":"Chi Wang","is_ca":false},{"name":"Vivek Narasayya","is_ca":false},{"name":"Surajit Chaudhuri","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0325549985898155,"gpt":0.3031739514041989,"spread":0.2706189528143834,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005526692,0.00009026609,0.0001183053,0.0001482601,0.00003062159,0.00004720641,0.003889455,0.00001956135,0.000001484533],"category_scores_gemma":[0.00008517857,0.00006679924,0.000020759,0.0006179033,0.00003760923,0.001479947,0.005718832,0.00009284988,0.000003908148],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000319295,"about_ca_system_score_gemma":0.00001111094,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003115195,"about_ca_topic_score_gemma":0.00000677508,"domain_scores_codex":[0.998928,0.000004789542,0.0002595573,0.0003730128,0.0003096655,0.0001250347],"domain_scores_gemma":[0.9984084,0.00002942532,0.0001275949,0.001381488,0.00003776915,0.00001527289],"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":[0.00001870476,0.00007524338,0.00138869,0.002288703,0.00007550215,0.000003862039,0.0003874245,0.00009517273,0.002552785,0.9081269,0.006163977,0.07882304],"study_design_scores_gemma":[0.00134163,0.0003121003,0.04618535,0.01523278,0.0001182773,0.00001730208,0.003345717,0.6648142,0.005939333,0.1148196,0.146892,0.0009816528],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2309767,0.003067601,0.6843717,0.03232013,0.002704034,0.003762976,0.0005945985,0.000876513,0.04132574],"genre_scores_gemma":[0.907616,0.0001958607,0.09165423,0.00004835065,0.0000157965,0.00001384013,0.00002656498,0.0000104429,0.0004189021],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7933073,"threshold_uncertainty_score":0.722764,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4389609976","doi":"10.1145/3626739","title":"NOCAP: Near-Optimal Correlation-Aware Partitioning Joins","year":2023,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Caching and Content Delivery","field":"Computer Science","cited_by":4,"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":"Universitas Brawijaya","keywords":"Joins; Computer science; Join (topology); Skew; Exploit; Hash function; Key (lock); Relation (database); Parallel computing; Hash join; Theoretical computer science; Algorithm; Data mining; Mathematics","authors":[{"name":"Zichen Zhu","is_ca":false},{"name":"Xiao Hu","is_ca":true},{"name":"Manos Athanassoulis","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07309228208787909,"gpt":0.2823106997284716,"spread":0.2092184176405925,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004724576,0.00008928548,0.0001128922,0.00008092167,0.0001504153,0.0001188767,0.005241433,0.00002208031,0.000005630865],"category_scores_gemma":[0.0001185896,0.00007162963,0.00005057053,0.0006103649,0.00004596592,0.0007350845,0.00652234,0.00009591504,0.00004899685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001285272,"about_ca_system_score_gemma":0.000009442304,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001536262,"about_ca_topic_score_gemma":5.455581e-7,"domain_scores_codex":[0.9988586,0.000005031012,0.000221812,0.0003229754,0.0004296726,0.0001618518],"domain_scores_gemma":[0.9983845,0.000044286,0.0001982561,0.001266678,0.00008103316,0.00002527021],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001144974,0.0004717066,0.04032151,0.001312385,0.0006849296,0.00001272443,0.001435375,0.00886314,0.002605308,0.3014764,0.5747765,0.06792554],"study_design_scores_gemma":[0.000930194,0.000197662,0.05336503,0.001112562,0.000134596,0.00000429369,0.001043026,0.9243855,0.001190582,0.008671056,0.008586211,0.0003792139],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9491505,0.00008183823,0.01455939,0.02004129,0.001186618,0.00088202,0.000146549,0.0007019256,0.01324984],"genre_scores_gemma":[0.9893051,0.00004676115,0.009501261,0.0001328083,0.00002619646,0.000008042406,0.00003091092,0.000008350814,0.0009405655],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9155225,"threshold_uncertainty_score":0.9739974,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4399156410","doi":"10.1145/3654934","title":"Data Acquisition for Improving Model Confidence","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; York University","funders":"","keywords":"Computer science; Data acquisition; Machine learning; Context (archaeology); Knowledge acquisition; Range (aeronautics); Process (computing); Artificial intelligence; Data mining; Data quality; Data science; Engineering","authors":[{"name":"Yifan Li","is_ca":true},{"name":"Xiaohui Yu","is_ca":true},{"name":"Nick Koudas","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1126036958320424,"gpt":0.3468254042837654,"spread":0.234221708451723,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001149031,0.00009036245,0.00009823619,0.00007872344,0.00006875848,0.0001993884,0.01460913,0.00002355131,0.000001692036],"category_scores_gemma":[0.0002313609,0.00006692661,0.00002418117,0.000263363,0.00003464207,0.001913748,0.0117803,0.00008588455,0.000004472566],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001268386,"about_ca_system_score_gemma":0.00001840373,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007010779,"about_ca_topic_score_gemma":3.367759e-7,"domain_scores_codex":[0.9986843,0.000004231973,0.0002316189,0.0006214407,0.0003340466,0.0001243129],"domain_scores_gemma":[0.9960983,0.00007027651,0.0001817926,0.003559578,0.00007014562,0.00001987056],"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":[0.00002101077,0.00005815615,0.0000452954,0.002318568,0.00006015063,2.007479e-7,0.00007290684,0.0001060741,0.00430352,0.7822855,0.04631901,0.1644096],"study_design_scores_gemma":[0.0001098178,0.00003467237,0.0002208569,0.0002929323,0.00005664574,9.412082e-7,0.00004675375,0.967835,0.0008870623,0.02610713,0.00433099,0.00007721037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002718276,0.0003063394,0.974722,0.01593141,0.0003309291,0.0008520631,0.001275029,0.0002307827,0.003633127],"genre_scores_gemma":[0.6256407,0.00008017886,0.373152,0.0001203863,0.00005025498,0.00001835934,0.0003722272,0.00001295139,0.000552868],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9677289,"threshold_uncertainty_score":0.9962122,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4381328483","doi":"10.1145/3589320","title":"Mitigating Filter Bubbles Under a Competitive Diffusion Model","year":2023,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Opinion Dynamics and Social Influence","field":"Physics and Astronomy","cited_by":4,"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":"","keywords":"Heuristic; Computer science; Filter (signal processing); Viewpoints; Mathematical optimization; Maximization; Algorithm; Artificial intelligence; Mathematics","authors":[{"name":"Prithu Banerjee","is_ca":true},{"name":"Wei Chen","is_ca":false},{"name":"Laks V. S. Lakshmanan","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06327816623333686,"gpt":0.3162685902262851,"spread":0.2529904239929482,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001831086,0.00008524241,0.0001194618,0.00003789911,0.00009002283,0.00002802108,0.001766645,0.00001460602,0.00001646199],"category_scores_gemma":[0.0000137963,0.00006549177,0.00004844461,0.0002190393,0.0000634942,0.0001833868,0.003565569,0.00007024752,0.000006923296],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007020101,"about_ca_system_score_gemma":0.000005728708,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002124376,"about_ca_topic_score_gemma":2.808096e-7,"domain_scores_codex":[0.9992564,0.00000284021,0.0001780124,0.0002011599,0.0002333185,0.0001282782],"domain_scores_gemma":[0.9992232,0.00002973113,0.0001820915,0.0004850326,0.00006112591,0.00001885453],"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":[0.00001291204,0.0001138812,0.0119803,0.0002161566,0.0001603806,7.144016e-8,0.0002919254,0.0008550979,0.001895073,0.9745727,0.006115817,0.003785748],"study_design_scores_gemma":[0.001261406,0.00008106435,0.04293729,0.001957451,0.0001725393,7.594236e-8,0.0180777,0.3562565,0.002891226,0.5745419,0.00134237,0.0004804998],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.968526,0.000004427351,0.0002801522,0.002113896,0.00007272654,0.0002967656,0.0004568606,0.00002741714,0.02822176],"genre_scores_gemma":[0.9949318,0.00001833892,0.004105256,0.00006333552,0.00003310369,0.000008468663,0.00007331492,0.00001058337,0.0007558696],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4000308,"threshold_uncertainty_score":0.4444227,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4389611627","doi":"10.1145/3626750","title":"Rethink Query Optimization in HTAP Databases","year":2023,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Computer science; Online analytical processing; Online transaction processing; Database; Schedule; Isolation (microbiology); Parallel computing; Database transaction; Transaction processing; Data warehouse; Operating system","authors":[{"name":"Haoze Song","is_ca":false},{"name":"Wenchao Zhou","is_ca":false},{"name":"Feifei Li","is_ca":false},{"name":"X. Peng","is_ca":false},{"name":"Heming Cui","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09719269435293139,"gpt":0.3220787802633234,"spread":0.224886085910392,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0008096583,0.0001012213,0.0001549509,0.0001664662,0.00005021185,0.00002262217,0.004826182,0.00001720264,0.000003567712],"category_scores_gemma":[0.0003575265,0.00007576714,0.00002277804,0.001044666,0.00004928618,0.001830742,0.01163511,0.00007737095,0.000007187504],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001599447,"about_ca_system_score_gemma":0.000009730887,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003221946,"about_ca_topic_score_gemma":0.000003088875,"domain_scores_codex":[0.9987118,0.000008441777,0.0003111599,0.0004074694,0.0003983291,0.0001628093],"domain_scores_gemma":[0.9974018,0.0000561603,0.0002567555,0.002208078,0.00005749312,0.00001969733],"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":[0.00004405947,0.0001477842,0.003261318,0.001604824,0.00007629777,0.000006270806,0.0003481181,0.004942733,0.0007137644,0.9174091,0.05841587,0.01302991],"study_design_scores_gemma":[0.004786169,0.000508018,0.04471492,0.01296598,0.0002081791,0.00001506864,0.007825891,0.6116262,0.03376877,0.04731305,0.2341397,0.002128056],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1463844,0.0008961977,0.7437927,0.0479673,0.003524072,0.007007379,0.003734073,0.001991202,0.04470275],"genre_scores_gemma":[0.04544917,0.0008376757,0.9524081,0.0001795569,0.00004733835,0.00003263148,0.0002749911,0.00002218349,0.0007483467],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.870096,"threshold_uncertainty_score":0.9963586,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4396893056","doi":"10.1145/3651603","title":"On the Feasibility of Forgetting in Data Streams","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Universitas Brawijaya","keywords":"STREAMS; Forgetting; Computer science; Psychology; Cognitive psychology; Computer network","authors":[{"name":"A. Pavan","is_ca":false},{"name":"Sourav Chakraborty","is_ca":false},{"name":"N. V. Vinodchandran","is_ca":false},{"name":"Kuldeep S. Meel","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1701356361458202,"gpt":0.3650236530530431,"spread":0.1948880169072229,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.002625348,0.0001345653,0.0001826571,0.0001293033,0.00003456786,0.0001011149,0.02918905,0.00002857574,0.00000442898],"category_scores_gemma":[0.001045154,0.00008070123,0.00003318289,0.0007276417,0.0001020043,0.001162928,0.0345853,0.0001716823,0.000002376319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002824611,"about_ca_system_score_gemma":0.00001679036,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003269838,"about_ca_topic_score_gemma":0.000003538635,"domain_scores_codex":[0.998148,0.00001512566,0.0004044271,0.0006956123,0.0005619386,0.0001748712],"domain_scores_gemma":[0.9922686,0.0002861073,0.0002586193,0.007124062,0.00004588525,0.00001676761],"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":[0.00004121412,0.0004280358,0.00448254,0.001800587,0.000161407,0.000002710067,0.0002964817,0.000002984104,0.0010582,0.6436921,0.1972662,0.1507675],"study_design_scores_gemma":[0.001095548,0.001057755,0.02266381,0.01684819,0.0003354879,0.000006552034,0.001919424,0.138245,0.08233307,0.7213621,0.01318044,0.0009526787],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8798825,0.0004876591,0.006920021,0.05684938,0.0007763138,0.004838584,0.004047888,0.0008603422,0.04533732],"genre_scores_gemma":[0.9017519,0.0000594692,0.09794006,0.00008403928,0.0000141769,0.000009790282,0.0000528561,0.00001218642,0.00007548251],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1840858,"threshold_uncertainty_score":0.9760635,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4396892922","doi":"10.1145/3651613","title":"A faster FPRAS for #NFA","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Universitas Brawijaya","keywords":"Computer science","authors":[{"name":"Kuldeep S. Meel","is_ca":true},{"name":"Sourav Chakraborty","is_ca":false},{"name":"Umang Mathur","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05590839665298635,"gpt":0.3236092414076727,"spread":0.2677008447546864,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0005499376,0.00008838597,0.000105353,0.0000776231,0.00004345362,0.0001339603,0.007413268,0.00001712411,0.000005165769],"category_scores_gemma":[0.0001089386,0.00005797269,0.00005261615,0.0002938019,0.00002626089,0.0004845428,0.005960516,0.00008609196,0.000009448492],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006932418,"about_ca_system_score_gemma":0.00000595296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003043983,"about_ca_topic_score_gemma":6.870899e-8,"domain_scores_codex":[0.9990421,0.000002946939,0.0001682631,0.0003682612,0.0002836919,0.0001347462],"domain_scores_gemma":[0.9986271,0.00005473687,0.00009046533,0.001167165,0.00004163506,0.00001891594],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002242446,0.0001219268,0.0004725463,0.002934276,0.000276796,0.000001323394,0.0003405233,0.00002831084,0.0005532343,0.4557271,0.1630919,0.3764296],"study_design_scores_gemma":[0.0008876945,0.0005125037,0.002607276,0.002309021,0.0002187469,0.000006618834,0.0002899602,0.4249328,0.005908987,0.1012733,0.4606034,0.0004496943],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1253975,0.002728159,0.3619799,0.28887,0.007924831,0.007348913,0.000722348,0.002172739,0.2028555],"genre_scores_gemma":[0.4641553,0.00008541757,0.5248211,0.0004951978,0.0002275611,0.00002937693,0.00001907054,0.00003437268,0.01013256],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4249045,"threshold_uncertainty_score":0.9979571,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4411141691","doi":"10.1145/3725235","title":"Fast Matrix Multiplication meets the Submodular Width","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Complexity and Algorithms in Graphs","field":"Computer Science","cited_by":3,"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":"Universitas Brawijaya","keywords":"Matrix multiplication; Submodular set function; Multiplication (music); Matrix (chemical analysis); Computer science; Mathematics; Arithmetic; Combinatorics; Physics; Materials science","authors":[{"name":"Mahmoud Abo Khamis","is_ca":false},{"name":"Dan Suciu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0438812084694511,"gpt":0.3106361800602223,"spread":0.2667549715907712,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0006626774,0.0001054071,0.0001228742,0.00009608772,0.0001502213,0.00008920414,0.01576854,0.000022346,0.000002416177],"category_scores_gemma":[0.0001203214,0.00006607023,0.00005603896,0.000735602,0.0001068504,0.0004588128,0.01257077,0.00009710631,0.000003678051],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001375524,"about_ca_system_score_gemma":0.000007475083,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001205716,"about_ca_topic_score_gemma":6.688711e-7,"domain_scores_codex":[0.9988296,0.000008414263,0.0002450394,0.0003830919,0.0003905112,0.0001433199],"domain_scores_gemma":[0.9967936,0.00006056133,0.0002215639,0.00281411,0.00009519276,0.0000149553],"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":[0.00001275584,0.0001410992,0.0007500685,0.0002935517,0.0001238765,1.490082e-7,0.0000911336,0.00002285658,0.0007240184,0.8840756,0.0147442,0.09902068],"study_design_scores_gemma":[0.001355178,0.0001348166,0.07100637,0.001210324,0.0002532637,0.000002487371,0.000631618,0.1209216,0.0249745,0.6913294,0.08774407,0.0004363966],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.1684631,0.002437698,0.2310883,0.4591266,0.003652572,0.009621059,0.0004678165,0.001025337,0.1241175],"genre_scores_gemma":[0.7685112,0.0002226654,0.2296169,0.0004228016,0.00003521052,0.00003205478,0.00001072027,0.000008927376,0.001139467],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6000481,"threshold_uncertainty_score":0.9954154,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4417070120","doi":"10.1145/3769829","title":"ST-Raptor: LLM-Powered Semi-Structured Table Question Answering","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"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":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Table (database); Correctness; Tree (set theory); Set (abstract data type); Benchmark (surveying); Pipeline (software); Question answering","authors":[{"name":"Boyu Niu","is_ca":false},{"name":"Xuanhe Zhou","is_ca":false},{"name":"Wei Zhou","is_ca":false},{"name":"J. Wang","is_ca":true},{"name":"Guoliang Li","is_ca":false},{"name":"Xinyi Zhang","is_ca":false},{"name":"Fan Wu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1373690653317707,"gpt":0.4113977177010211,"spread":0.2740286523692504,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.004589377,0.0001902699,0.0003469302,0.0003353163,0.0001466706,0.0002305001,0.01354192,0.00005505337,0.0001036157],"category_scores_gemma":[0.002736851,0.0001319879,0.00007724066,0.00141199,0.0001371963,0.001187272,0.01392516,0.0001364371,0.00001738261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004017593,"about_ca_system_score_gemma":0.00001743541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003939051,"about_ca_topic_score_gemma":0.000008334242,"domain_scores_codex":[0.996578,0.00002592972,0.0008279958,0.0007839422,0.00152624,0.0002578941],"domain_scores_gemma":[0.9951386,0.0001805702,0.0006581854,0.003723342,0.0002570845,0.00004218798],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002094153,0.0002834424,0.002763894,0.0007572036,0.0003440762,7.503498e-7,0.0001046866,0.00006004163,0.002227288,0.3225597,0.6057335,0.064956],"study_design_scores_gemma":[0.001309752,0.000152241,0.01995722,0.001184405,0.0003417159,6.492049e-7,0.004922315,0.001181659,0.01221279,0.4279818,0.5303765,0.0003789175],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4741293,0.001232714,0.01066175,0.0632491,0.00700108,0.007664409,0.005984611,0.0005818234,0.4294952],"genre_scores_gemma":[0.953068,0.0003909626,0.02908194,0.0009074103,0.00006657454,0.00003000252,0.0001662103,0.00002413148,0.01626475],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4789387,"threshold_uncertainty_score":0.99405,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4411403532","doi":"10.1145/3725397","title":"Computing Inconsistency Measures Under Differential Privacy","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":2,"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":"Universitas Brawijaya","keywords":"Differential privacy; Computer science; Tuple; Graph; Data mining; Data quality; Information sensitivity; Theoretical computer science; Mathematics; Computer security","authors":[{"name":"Shubhankar Mohapatra","is_ca":true},{"name":"Amir Gilad","is_ca":false},{"name":"Xi He","is_ca":true},{"name":"Benny Kimelfeld","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.075174269373825,"gpt":0.3138096824857975,"spread":0.2386354131119726,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0006702516,0.0001812729,0.0002550269,0.0002242598,0.0001314004,0.0001272356,0.1433659,0.00006312096,0.000003159057],"category_scores_gemma":[0.007522821,0.0001370166,0.00006213125,0.0008779236,0.0001702776,0.000742671,0.508442,0.0002120807,0.00000291669],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004277708,"about_ca_system_score_gemma":0.00002277746,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001034611,"about_ca_topic_score_gemma":5.381802e-7,"domain_scores_codex":[0.9979943,0.00001319094,0.0004382556,0.0006752007,0.0006151527,0.0002638708],"domain_scores_gemma":[0.9831027,0.0001254758,0.0004127856,0.0161962,0.0001401665,0.00002264366],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003819583,0.0004326229,0.006318192,0.00131141,0.0006531897,0.000001142971,0.00005493309,0.000007746912,0.003641536,0.4080743,0.4515916,0.127875],"study_design_scores_gemma":[0.0008129012,0.00006804231,0.02770217,0.001571699,0.00015054,0.000001475218,0.0002395011,0.02105974,0.02177789,0.9235966,0.002723866,0.0002955617],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3644495,0.0006429094,0.284761,0.2995751,0.002494391,0.002831312,0.0002076265,0.001854903,0.04318325],"genre_scores_gemma":[0.7247604,0.00007476093,0.2748934,0.0001536885,0.00001197141,0.000004112657,0.000006735146,0.000007469993,0.00008746525],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5155223,"threshold_uncertainty_score":0.9006063,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4388620459","doi":"10.1145/3617336","title":"OptiQL: Robust Optimistic Locking for Memory-Optimized Indexes","year":2023,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":2,"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; Lock (firearm); Robustness (evolution); Multi-core processor; Parallel computing; Byte; Distributed computing; Mutual exclusion; Operating system; Computer network","authors":[{"name":"Ge Shi","is_ca":true},{"name":"Ziyi Yan","is_ca":true},{"name":"Tianzheng Wang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1022769341983313,"gpt":0.3075132284456033,"spread":0.205236294247272,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0009883579,0.000153117,0.0002703883,0.0001122777,0.0001136137,0.0001244803,0.01072803,0.0000401712,0.000002379745],"category_scores_gemma":[0.0002913499,0.0001156495,0.00007904076,0.0007856054,0.00005164,0.0006002194,0.006641268,0.00007752754,0.000006168218],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001878975,"about_ca_system_score_gemma":0.00001090991,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004858656,"about_ca_topic_score_gemma":1.144089e-7,"domain_scores_codex":[0.998333,0.000005454648,0.0003908185,0.0005136287,0.0004823353,0.0002747288],"domain_scores_gemma":[0.9974282,0.00009076115,0.0003922164,0.001897157,0.000153504,0.00003814542],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000352623,0.0006211754,0.0009703023,0.008269079,0.001151296,0.000009215238,0.0008133448,0.09670835,0.001968636,0.2561677,0.554125,0.0788433],"study_design_scores_gemma":[0.00452925,0.0003012257,0.003535529,0.003327513,0.0002661707,0.000004896075,0.001382581,0.9422029,0.005854471,0.017294,0.02049347,0.0008079627],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0816658,0.0008552191,0.8265824,0.03008797,0.004197795,0.01061323,0.002126439,0.001890249,0.04198095],"genre_scores_gemma":[0.5243008,0.0001224327,0.4727364,0.000165794,0.0001096941,0.0001382185,0.00008767308,0.00004088624,0.002298032],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8454946,"threshold_uncertainty_score":0.9946244,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4414427902","doi":"10.1145/3749156","title":"A Comprehensive Benchmark on Spectral GNNs: The Impact on Efficiency, Memory, and Effectiveness","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Nanyang Technological University; Ministry of Education - Singapore","keywords":"Benchmarking; Graph; Computation; Benchmark (surveying); Power graph analysis","authors":[{"name":"Ningyi Liao","is_ca":false},{"name":"Haoyu Liu","is_ca":false},{"name":"Zulun Zhu","is_ca":false},{"name":"Siqiang Luo","is_ca":false},{"name":"Laks V. S. Lakshmanan","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02864368781006588,"gpt":0.3161488555937306,"spread":0.2875051677836648,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0004599447,0.000218388,0.0002471708,0.0001368278,0.0001592317,0.00008182732,0.007680561,0.00003094919,0.000001355184],"category_scores_gemma":[0.0001119866,0.0001171523,0.00007879357,0.0008402602,0.0001815619,0.0003028534,0.006171436,0.0002181367,0.000001542658],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003480812,"about_ca_system_score_gemma":0.000008091544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008027797,"about_ca_topic_score_gemma":2.225997e-7,"domain_scores_codex":[0.9984842,0.00002988405,0.0002148003,0.0005953319,0.0004218946,0.0002538949],"domain_scores_gemma":[0.9972139,0.0004770817,0.0002246573,0.001981979,0.00007241427,0.0000299439],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.001978127,0.001360811,0.007890954,0.002607798,0.001331047,0.00001200959,0.0004850666,0.01487588,0.00643112,0.790327,0.04010503,0.1325951],"study_design_scores_gemma":[0.003433119,0.002992969,0.6694353,0.005150671,0.0002647027,0.000009011481,0.0005894523,0.05677215,0.04245939,0.2169412,0.001161829,0.0007902493],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9807904,0.0002424016,0.00165582,0.004483038,0.0003702723,0.001787442,0.00003682751,0.00007670745,0.01055711],"genre_scores_gemma":[0.9970779,0.0001024921,0.002417025,0.0003128274,0.0000179368,0.00001406105,0.000002620826,0.000007508685,0.00004765945],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6615443,"threshold_uncertainty_score":0.9976884,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4411141435","doi":"10.1145/3725240","title":"Optimal Bounds for Private Minimum Spanning Trees via Input Perturbation","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":1,"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":"Spanning tree; Minimum spanning tree; Minimum degree spanning tree; Combinatorics; Perturbation (astronomy); Mathematics; Physics","authors":[{"name":"Rasmus Pagh","is_ca":false},{"name":"Lukas Retschmeier","is_ca":false},{"name":"Hao Wu","is_ca":true},{"name":"H. H. Zhang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05061472259112793,"gpt":0.3086069096880938,"spread":0.2579921870969659,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0007960676,0.0001612368,0.0002070176,0.0002272526,0.0001265509,0.0001432591,0.09012894,0.00006403822,0.000001383793],"category_scores_gemma":[0.008152371,0.0001280891,0.00005548649,0.0007121661,0.0001191415,0.001280113,0.250284,0.000120655,0.000001308635],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004450688,"about_ca_system_score_gemma":0.00001410126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003100976,"about_ca_topic_score_gemma":2.605868e-7,"domain_scores_codex":[0.9983718,0.000005276459,0.0003653311,0.0006228499,0.0003832762,0.0002514831],"domain_scores_gemma":[0.9892777,0.000127046,0.0003829993,0.01007353,0.0001211971,0.00001749785],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001256188,0.0002877069,0.001930885,0.00164923,0.0004485141,6.233606e-7,0.00009728827,0.00004028924,0.007074493,0.2021202,0.6811937,0.1050314],"study_design_scores_gemma":[0.0009360341,0.0002161494,0.004611975,0.001068561,0.0001351808,9.371353e-7,0.0001639727,0.2793671,0.04181264,0.6534608,0.0179381,0.000288479],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1658163,0.0003729489,0.6077154,0.2098348,0.001165177,0.003155156,0.0002859435,0.0009888747,0.01066533],"genre_scores_gemma":[0.1460842,0.00006393252,0.8531748,0.0001675601,0.00001756221,0.00004010918,0.0000291463,0.00001046021,0.0004121964],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6632556,"threshold_uncertainty_score":0.9759738,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4411141774","doi":"10.1145/3725254","title":"Towards Update-Dependent Analysis of Query Maintenance","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":1,"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":"Universitas Brawijaya","keywords":"Computer science; Query optimization; Information retrieval","authors":[{"name":"Qichen Wang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02913723348163801,"gpt":0.2919665382818373,"spread":0.2628293048001993,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0008020885,0.0001232574,0.000370778,0.0002460098,0.00003895916,0.00005012133,0.0119081,0.00003259323,0.000004454307],"category_scores_gemma":[0.0001228452,0.00008796943,0.0001195358,0.001971162,0.00006312152,0.0004577063,0.007895271,0.00007494777,0.00000159329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002607539,"about_ca_system_score_gemma":0.00001778269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004200175,"about_ca_topic_score_gemma":0.000001955237,"domain_scores_codex":[0.9983438,0.000007981167,0.0004932259,0.0004503286,0.0005329125,0.0001718019],"domain_scores_gemma":[0.9966889,0.00002165964,0.0004865181,0.002569031,0.0002118127,0.00002207908],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00006987168,0.0004465888,0.01267568,0.001614135,0.003660234,0.0000019933,0.0001282063,0.0004746463,0.0009921243,0.8658156,0.06880877,0.04531214],"study_design_scores_gemma":[0.00484371,0.0004157328,0.5287294,0.008989298,0.007098665,0.000003023392,0.00321097,0.1815981,0.05839938,0.09280138,0.1123215,0.001588793],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3197254,0.00208199,0.3955477,0.04614657,0.002722356,0.003865871,0.003154065,0.000419571,0.2263365],"genre_scores_gemma":[0.9833844,0.0001088379,0.01557978,0.0001539084,0.000006444912,0.0000086253,0.00001581773,0.000004058122,0.0007381392],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7730142,"threshold_uncertainty_score":0.9934379,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4399174990","doi":"10.1145/3654984","title":"Unstructured Data Fusion for Schema and Data Extraction","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Information retrieval; Schema (genetic algorithms); Component (thermodynamics); Data mining; Table (database)","authors":[{"name":"Kaiwen Chen","is_ca":true},{"name":"Nick Koudas","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1355387895140462,"gpt":0.3611646660040275,"spread":0.2256258764899813,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0009438187,0.0001011667,0.0001171113,0.00007548944,0.00006279305,0.0001794931,0.0171442,0.00003104007,0.000002791011],"category_scores_gemma":[0.0002407534,0.00007355378,0.00001343678,0.0002220584,0.00003341998,0.002482767,0.03822575,0.00008721198,9.929338e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009587436,"about_ca_system_score_gemma":0.00001154154,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006028885,"about_ca_topic_score_gemma":8.390851e-7,"domain_scores_codex":[0.9984418,0.000003119946,0.0002345824,0.0008566557,0.0003379596,0.0001258831],"domain_scores_gemma":[0.9941567,0.00005810408,0.0001369203,0.005583527,0.00004182901,0.00002291744],"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":[0.00003592201,0.00005884479,0.0001102138,0.003100174,0.0001928661,0.000001219808,0.0001085568,0.00001075283,0.00563001,0.1537425,0.08083028,0.7561786],"study_design_scores_gemma":[0.0003451138,0.0000446164,0.0004438191,0.0007839248,0.0001514738,0.000007694895,0.0001515442,0.8964323,0.002833656,0.03247177,0.06617129,0.0001627998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08366098,0.003380919,0.8359582,0.05840151,0.003742253,0.004393767,0.004914106,0.0006420108,0.004906295],"genre_scores_gemma":[0.2687187,0.0003669214,0.7301885,0.0000838699,0.0001161075,0.000005722396,0.0002706895,0.00001524087,0.0002342473],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8964216,"threshold_uncertainty_score":0.9881735,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4411141791","doi":"10.1145/3725253","title":"Towards Practical FPRAS for #NFA: Exploiting the Power of Dependence","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Data Quality and Management","field":"Decision Sciences","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":"Computer science; Power (physics); Physics; Thermodynamics","authors":[{"name":"Kuldeep S. Meel","is_ca":true},{"name":"Alexis de Colnet","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3512875317024356,"gpt":0.4853916397535502,"spread":0.1341041080511146,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.009915994,0.0001400078,0.00030807,0.0001682077,0.0001410608,0.0001431663,0.01302621,0.00003848237,0.00005076729],"category_scores_gemma":[0.01685998,0.00007696724,0.0001155637,0.0008525975,0.0002342756,0.001024814,0.01601715,0.0001258408,0.000007758214],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001767547,"about_ca_system_score_gemma":0.00003292517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002022562,"about_ca_topic_score_gemma":0.000003468309,"domain_scores_codex":[0.9966227,0.00003673645,0.0008861673,0.0005740526,0.001659291,0.0002210134],"domain_scores_gemma":[0.9938844,0.001335104,0.0009662146,0.003338165,0.0004477523,0.00002832025],"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":[0.0002051825,0.0002606869,0.000684311,0.0004722786,0.0002531939,3.197928e-7,0.00022443,0.000005238107,0.0002669767,0.6632769,0.2964288,0.03792165],"study_design_scores_gemma":[0.0013811,0.0003097016,0.0120498,0.001043017,0.0006123891,0.000001279646,0.04163684,0.0008499566,0.01534225,0.5877789,0.3387007,0.0002941338],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1619397,0.000428039,0.04646963,0.3707001,0.002578508,0.009395396,0.002610127,0.0001408292,0.4057377],"genre_scores_gemma":[0.9390636,0.0001240491,0.0563399,0.00122605,0.0000311521,0.00006338455,0.00002077171,0.00001304248,0.003118062],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7771239,"threshold_uncertainty_score":0.9923138,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4396892769","doi":"10.1145/3651144","title":"On Reporting Durable Patterns in Temporal Proximity Graphs","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Advanced Graph Theory Research","field":"Computer Science","cited_by":1,"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","authors":[{"name":"Pankaj K. Agarwal","is_ca":false},{"name":"Xiao Hu","is_ca":true},{"name":"Stavros Sintos","is_ca":false},{"name":"Jun Yang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08898262796644435,"gpt":0.3509226316586121,"spread":0.2619400036921677,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.002499079,0.0001349694,0.0001933129,0.0003238796,0.00005969501,0.0001160128,0.008567345,0.00002789258,0.000004536838],"category_scores_gemma":[0.0007345018,0.000096232,0.00006231999,0.001174153,0.00006573793,0.001304128,0.008387004,0.0002601953,0.000004855518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003236486,"about_ca_system_score_gemma":0.0000137957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001706558,"about_ca_topic_score_gemma":0.000002242875,"domain_scores_codex":[0.9977114,0.0000137529,0.0006148742,0.0006668103,0.0007168595,0.0002763511],"domain_scores_gemma":[0.9971404,0.00009676366,0.0004688462,0.002197433,0.00006305445,0.00003348528],"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":[0.00006203659,0.0002575031,0.03174263,0.002303507,0.0001055475,0.00003263798,0.0001849342,0.00003503736,0.001196275,0.9347934,0.003966375,0.02532013],"study_design_scores_gemma":[0.0003648966,0.0002239285,0.01930751,0.002907885,0.00002180671,0.00000579068,0.000281638,0.008997332,0.01145753,0.9554198,0.0007679996,0.000243933],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9793416,0.0001126869,0.002607276,0.006331898,0.000304946,0.001265344,0.00005119488,0.0001911084,0.009793964],"genre_scores_gemma":[0.98228,0.00004923662,0.01724398,0.00005041942,0.000009016332,0.00002116717,0.000004994869,0.00001304247,0.000328151],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0250762,"threshold_uncertainty_score":0.999633,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4411141667","doi":"10.1145/3725228","title":"An Improved Fully Dynamic Algorithm for Counting 4-Cycles in General Graphs Using Fast Matrix Multiplication","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":1,"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":"Universitas Brawijaya","keywords":"Matrix multiplication; Multiplication (music); Algorithm; Computer science; Matrix (chemical analysis); Multiplication algorithm; Arithmetic; Mathematics; Parallel computing; Combinatorics; Physics; Materials science","authors":[{"name":"Sepehr Assadi","is_ca":true},{"name":"Vihan Shah","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02497041821931234,"gpt":0.3219790420322582,"spread":0.2970086238129459,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0008975607,0.0001323116,0.0001703935,0.0002612139,0.0001109444,0.00009817941,0.006430416,0.00003690833,3.535752e-7],"category_scores_gemma":[0.00005026146,0.0001113862,0.00005432051,0.0007132099,0.00005678558,0.0009573121,0.002658565,0.0000776618,1.819182e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002729696,"about_ca_system_score_gemma":0.00001150635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001759178,"about_ca_topic_score_gemma":0.000001756203,"domain_scores_codex":[0.9987634,0.000009455179,0.0003401109,0.0004896052,0.0001926933,0.0002047112],"domain_scores_gemma":[0.9982408,0.00003714663,0.0003021492,0.001290533,0.000110439,0.00001893728],"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":[0.00006242179,0.0005109149,0.001961292,0.0009786066,0.0001783308,3.704582e-7,0.0002224972,0.0003291988,0.07217608,0.2186943,0.0001460059,0.70474],"study_design_scores_gemma":[0.0005544299,0.00004595454,0.003846608,0.0002131641,0.00003845539,3.960674e-7,0.000254678,0.9209152,0.004299167,0.06967679,0.00004537444,0.0001097767],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5377697,0.00008739156,0.4590806,0.0008611319,0.0002846462,0.00150503,0.0001434365,0.00008437539,0.0001836857],"genre_scores_gemma":[0.3287501,0.00002233186,0.6710531,0.00005470643,0.0000105685,0.00002431887,0.00001990062,0.000008405094,0.00005661793],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.920586,"threshold_uncertainty_score":0.9989453,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4411141648","doi":"10.1145/3725241","title":"Output-Optimal Algorithms for Join-Aggregate Queries","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":1,"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":"Join (topology); Aggregate (composite); Computer science; Algorithm; Theoretical computer science; Mathematics; Combinatorics","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.06301675797609008,"gpt":0.3193127812564128,"spread":0.2562960232803227,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0005031657,0.0001463609,0.0002336233,0.0001032868,0.0001178371,0.00004983129,0.006193459,0.00002653428,0.000001254303],"category_scores_gemma":[0.0002293947,0.0001046877,0.00006367197,0.0003835075,0.00009949219,0.001154112,0.009896182,0.00006358676,0.000001781936],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000165623,"about_ca_system_score_gemma":0.00001654714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009419884,"about_ca_topic_score_gemma":7.257239e-7,"domain_scores_codex":[0.998679,0.000004279349,0.0003458807,0.0004705553,0.000296094,0.0002041412],"domain_scores_gemma":[0.9973451,0.00005625648,0.0003223393,0.002106699,0.0001467116,0.00002288911],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004912926,0.00007954855,0.0001744099,0.001280002,0.0001659296,4.021793e-7,0.00008749847,0.00001738868,0.0004053953,0.8967305,0.04467313,0.0563367],"study_design_scores_gemma":[0.001782203,0.0003388328,0.00212524,0.002777494,0.0001916267,0.000002735941,0.001471658,0.01496538,0.051234,0.04273557,0.8818519,0.0005233643],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01069401,0.0006272769,0.9563394,0.0154056,0.001323699,0.002419717,0.001031681,0.0002283842,0.0119302],"genre_scores_gemma":[0.01449801,0.0001397737,0.9808981,0.0002164013,0.00004150148,0.00006177717,0.00003024368,0.00001196254,0.004102188],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8539949,"threshold_uncertainty_score":0.9991835,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4411141319","doi":"10.1145/3725250","title":"Smallest Synthetic Witnesses for Conjunctive Queries","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":1,"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":"Universitas Brawijaya","keywords":"Conjunctive query; Computer science; Information retrieval; Relational database","authors":[{"name":"Aryan Esmailpour","is_ca":false},{"name":"Boris Glavic","is_ca":false},{"name":"Stavros Sintos","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2317777557871395,"gpt":0.4214874451748175,"spread":0.1897096893876779,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.004422387,0.0001441962,0.0002876303,0.000300942,0.0001885581,0.0002368387,0.01334455,0.00002592876,0.00003260943],"category_scores_gemma":[0.007132439,0.00008988958,0.00008953086,0.001152449,0.0002882028,0.0003662034,0.01367251,0.00005799494,0.00001072451],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001768888,"about_ca_system_score_gemma":0.00002026314,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001077839,"about_ca_topic_score_gemma":0.000003357217,"domain_scores_codex":[0.9973082,0.00001299552,0.0006161344,0.0008661555,0.0009970447,0.0001994476],"domain_scores_gemma":[0.9938637,0.0008857807,0.0005678313,0.004164832,0.0004896962,0.00002817239],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002294003,0.0002163195,0.00361264,0.000522139,0.0002557702,2.326296e-7,0.0001039724,0.00004388697,0.0001829296,0.3735617,0.5514436,0.06982733],"study_design_scores_gemma":[0.001547535,0.000233266,0.02635257,0.001730604,0.0005335768,7.051335e-7,0.01440855,0.003535767,0.008596565,0.5591006,0.383568,0.0003922914],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5312003,0.0006416736,0.02651739,0.07384835,0.007591261,0.007773333,0.002527281,0.000273683,0.3496266],"genre_scores_gemma":[0.96664,0.00003143989,0.02060121,0.0002561831,0.00002631226,0.00003504548,0.0000231275,0.00000927265,0.01237743],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4354396,"threshold_uncertainty_score":0.9943047,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4396892510","doi":"10.1145/3651598","title":"Topology-aware Parallel Joins","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Interconnection Networks and Systems","field":"Computer Science","cited_by":0,"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":"Joins; Join (topology); Skew; Cartesian product; Network topology; Computer science; Topology (electrical circuits); Extension topology; Product topology; Computation; Logical topology; Theoretical computer science; Algorithm; Mathematics; Discrete mathematics; General topology; Combinatorics; Computer network; Topological space","authors":[{"name":"Xiao Hu","is_ca":true},{"name":"Paraschos Koutris","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06779863890756006,"gpt":0.303460955020995,"spread":0.2356623161134349,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0004792075,0.00008960267,0.0001308068,0.00007979763,0.00004911906,0.0001049837,0.007001912,0.00003061782,0.00001259059],"category_scores_gemma":[0.0000242982,0.00005913447,0.00005649629,0.0003305974,0.00003934585,0.0005341093,0.005745236,0.00009309415,0.00001868902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001460001,"about_ca_system_score_gemma":0.000006297796,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009351381,"about_ca_topic_score_gemma":7.655476e-7,"domain_scores_codex":[0.9989876,0.000005763798,0.0002443455,0.0003588547,0.0002654413,0.0001380125],"domain_scores_gemma":[0.9984293,0.0000326103,0.000108389,0.001357509,0.0000529033,0.00001927951],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000007889917,0.00004551466,0.0001676017,0.0006059698,0.000151992,0.000001863999,0.0001473431,0.00002472862,0.00009978037,0.6998387,0.2860493,0.01285929],"study_design_scores_gemma":[0.0009627086,0.0006279115,0.003773393,0.004695802,0.0002246405,0.00004544316,0.001969499,0.3097592,0.002930861,0.1984231,0.4758537,0.000733732],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.09171502,0.003027401,0.2508335,0.2523075,0.02118994,0.005052927,0.0003828909,0.001930326,0.3735606],"genre_scores_gemma":[0.9820414,0.00009557476,0.01475654,0.0001982506,0.0001298429,0.00001132511,0.000004184352,0.000009149996,0.002753705],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8903264,"threshold_uncertainty_score":0.9983707,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W7109087591","doi":"10.1145/3769841","title":"Visualization-Oriented Progressive Time Series Transformation","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Transformation (genetics); Computation; Visualization; Data visualization; Multivariate statistics; Data transformation; Time series; Data manipulation language","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.0252930631897247,"gpt":0.3198411704681106,"spread":0.2945481072783859,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000291861,0.00008721089,0.0001168626,0.0001352314,0.00007525863,0.00008137524,0.00497181,0.00002144191,0.000009908508],"category_scores_gemma":[0.0001300066,0.00006544888,0.00002757912,0.00100838,0.00005437928,0.00155754,0.002858439,0.00003436311,0.00000622533],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001183442,"about_ca_system_score_gemma":0.00001366031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.562608e-7,"about_ca_topic_score_gemma":9.173595e-8,"domain_scores_codex":[0.9990255,0.000006329768,0.000291778,0.0002329754,0.0003459248,0.00009752651],"domain_scores_gemma":[0.9985188,0.00001375787,0.0002385454,0.001027509,0.00018581,0.00001555777],"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":[0.00001470099,0.0001230844,0.0002325374,0.0004705754,0.00008837985,1.142085e-7,0.0001598099,0.000007328003,0.0002077613,0.9688689,0.02416655,0.005660219],"study_design_scores_gemma":[0.004386214,0.0006381386,0.009459635,0.006269727,0.0007944943,0.000004516797,0.003130258,0.3950108,0.1560544,0.1193382,0.3038058,0.001107814],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02977107,0.0003748914,0.7123231,0.05820212,0.001317071,0.005550721,0.0009575433,0.000996175,0.1905073],"genre_scores_gemma":[0.6375569,0.001050285,0.3307237,0.003665228,0.0001091979,0.0001095242,0.001830287,0.00007139159,0.0248835],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8495308,"threshold_uncertainty_score":0.9238942,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4411403412","doi":"10.1145/3725404","title":"Fast Maximum Common Subgraph Search: A Redundancy-Reduced Backtracking Approach","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":0,"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":"","keywords":"Backtracking; Computer science; Benchmark (surveying); Redundancy (engineering); Graph; Computation; Theoretical computer science; Algorithm","authors":[{"name":"Kaiqiang Yu","is_ca":false},{"name":"Kaixin Wang","is_ca":false},{"name":"Cheng Long","is_ca":false},{"name":"Laks V. S. Lakshmanan","is_ca":true},{"name":"Reynold Cheng","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05965004820938316,"gpt":0.2988278835663659,"spread":0.2391778353569828,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001270306,0.0001827505,0.0002574601,0.0002782763,0.0001706103,0.0001435047,0.01637764,0.00004390549,0.000003006775],"category_scores_gemma":[0.00006740235,0.00014034,0.0001000316,0.001477189,0.0001731702,0.0007980556,0.01247853,0.0002163292,0.000003073251],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001586769,"about_ca_system_score_gemma":0.00001458262,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006833125,"about_ca_topic_score_gemma":2.042138e-7,"domain_scores_codex":[0.9981715,0.00002336859,0.0003632919,0.0006190351,0.0005238135,0.0002989723],"domain_scores_gemma":[0.9969978,0.00005486634,0.000227081,0.00257591,0.0001043982,0.00003997439],"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":[0.00007279967,0.0005887379,0.001750247,0.001496193,0.0003808226,0.00000130406,0.0004487869,0.00004173493,0.004021809,0.8587556,0.006022935,0.126419],"study_design_scores_gemma":[0.002335446,0.0003140251,0.03427992,0.003220172,0.0003324815,0.000008514791,0.003702649,0.02766301,0.09845387,0.8260511,0.002803063,0.00083578],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7299008,0.0006025948,0.04887603,0.01509469,0.001359688,0.003312208,0.0002076615,0.0005055756,0.2001408],"genre_scores_gemma":[0.8868071,0.00006974948,0.112451,0.0001420614,0.00001862063,0.00001470437,0.00001357894,0.00001160166,0.0004714934],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1996693,"threshold_uncertainty_score":0.9955084,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4411403262","doi":"10.1145/3725319","title":"Low-Latency Transaction Scheduling via Userspace Interrupts: Why Wait or Yield When You Can Preempt?","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":0,"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":"Universitas Brawijaya","keywords":"Computer science; Preemption; Context switch; Scheduling (production processes); Database transaction; Latency (audio); Operating system; Parallel computing; Embedded system; Distributed computing; Database","authors":[{"name":"Kaisong Huang","is_ca":true},{"name":"Zhuoyue Zhao","is_ca":false},{"name":"Dong Xie","is_ca":false},{"name":"Tianzheng Wang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05149839268555786,"gpt":0.2853484248596599,"spread":0.2338500321741021,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0005094456,0.0001803419,0.000252842,0.0001280867,0.00009501624,0.0001355304,0.008679803,0.0000592386,0.00000951819],"category_scores_gemma":[0.0001274662,0.0001290193,0.00006901372,0.0006217166,0.00004118666,0.001012233,0.002697233,0.0001618062,0.000002446287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004496994,"about_ca_system_score_gemma":0.00002152689,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009950792,"about_ca_topic_score_gemma":0.0000128349,"domain_scores_codex":[0.9983535,0.000008158059,0.0004086671,0.0005649548,0.0004299913,0.0002347225],"domain_scores_gemma":[0.9976196,0.00003594375,0.0003240771,0.001839361,0.0001432694,0.00003770901],"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":[0.001520899,0.003213342,0.00887787,0.02382422,0.003789255,0.00002191597,0.007870779,0.001639817,0.03264361,0.1794755,0.3062414,0.4308814],"study_design_scores_gemma":[0.01108626,0.002394805,0.01732959,0.07438261,0.001923975,0.00003377839,0.01693383,0.4120582,0.2349133,0.0790498,0.145891,0.004002865],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09694576,0.0004623742,0.8232552,0.05856487,0.002258309,0.002794923,0.0002994276,0.0003910951,0.01502801],"genre_scores_gemma":[0.9629912,0.0000732037,0.03454412,0.0004004278,0.00002767176,0.00002326906,0.000009769591,0.00001179153,0.001918526],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8660455,"threshold_uncertainty_score":0.9966837,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W7109234313","doi":"10.1145/3769790","title":"Enjima: A Resource-Adaptive Stream Processing System","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":0,"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":"Latency (audio); Stream processing; Dataflow; Pipeline (software); Workload; Throughput; Scheduling (production processes); Memory management; Response time","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.04016599984991381,"gpt":0.2851652727165403,"spread":0.2449992728666265,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0005333616,0.0001487911,0.0002371773,0.0001256905,0.0001326249,0.0000524682,0.006937783,0.00002770398,6.195411e-7],"category_scores_gemma":[0.0001086466,0.0001040176,0.00004193823,0.0007043432,0.00008168213,0.001057915,0.0115692,0.00009365237,0.000002086551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004203469,"about_ca_system_score_gemma":0.00002192282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001209822,"about_ca_topic_score_gemma":6.675352e-7,"domain_scores_codex":[0.9985062,0.000009041668,0.0003638419,0.0005118783,0.0004211049,0.0001878989],"domain_scores_gemma":[0.9972171,0.00003779891,0.0004134936,0.002177372,0.000130039,0.00002421472],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004508811,0.0000831822,0.0002271033,0.002826658,0.0001099742,0.00000128556,0.0001347401,0.00001355187,0.0003008438,0.9326108,0.0131063,0.05054053],"study_design_scores_gemma":[0.005628211,0.001018238,0.01047055,0.06306552,0.001003803,0.00002996742,0.04677004,0.08464871,0.0784215,0.03661512,0.6701419,0.002186418],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0336294,0.002558785,0.5411043,0.01157938,0.001153788,0.005233359,0.0009742135,0.001117924,0.4026488],"genre_scores_gemma":[0.6308535,0.00003201599,0.367397,0.0001222936,0.00004041929,0.00003962412,0.00001563269,0.00001535113,0.001484207],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8959956,"threshold_uncertainty_score":0.9984351,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4407355838","doi":"10.1145/3709681","title":"Dialogue Benchmark Generation from Knowledge Graphs with Cost-Effective Retrieval-Augmented LLMs","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Benchmark (surveying); Computer science; Artificial intelligence; Information retrieval; Geography","authors":[{"name":"Reham Omar","is_ca":true},{"name":"Omij Mangukiya","is_ca":true},{"name":"E. M. E. Mansour","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05128988014828679,"gpt":0.2954122021952202,"spread":0.2441223220469334,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0005202746,0.0001471437,0.0001932192,0.0001363181,0.0000891302,0.00007747607,0.006153954,0.00003867613,0.000003137227],"category_scores_gemma":[0.0001466202,0.00010435,0.00003838901,0.0007530021,0.00005539185,0.0006152577,0.005792634,0.0001100291,0.000002167821],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004401978,"about_ca_system_score_gemma":0.000017395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002812255,"about_ca_topic_score_gemma":0.00000605031,"domain_scores_codex":[0.9986154,0.00001655567,0.0002701757,0.0005896713,0.0003500614,0.0001580711],"domain_scores_gemma":[0.9976025,0.00007593901,0.0002418692,0.001891936,0.0001624923,0.00002523936],"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":[0.0002796657,0.0006514191,0.006349735,0.0006581987,0.001108804,0.000001631308,0.000673467,0.000212454,0.01546521,0.7900328,0.04309121,0.1414754],"study_design_scores_gemma":[0.007811243,0.0009588785,0.08664086,0.005183322,0.001200443,0.000001756379,0.0007614331,0.4384032,0.2328154,0.2037312,0.0211964,0.001295909],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7480225,0.001214944,0.1948229,0.01036244,0.001951523,0.009477723,0.0003121129,0.0003120474,0.03352378],"genre_scores_gemma":[0.9166248,0.0001186249,0.0825082,0.0001772001,0.00004682014,0.00006750586,0.00007119904,0.00001006759,0.0003755933],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5863016,"threshold_uncertainty_score":0.9992232,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}