{"meta":{"query_hash":"0bc1e9e6864c","filters":{"venue":"Proceedings of the ACM on Management of Data"},"cohort_total":43,"direct_labels_cover":0,"predictions_cover":43,"exported":43,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/0bc1e9e6864c","api":"https://metacan.xera.ac/api/v1/cohort?venue=Proceedings+of+the+ACM+on+Management+of+Data"},"results":[{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.04636754490894221,"score_gpt":0.2778059725457491,"score_spread":0.23143842763680691,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380433188","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023332823,0.00033332102,0.96577823,0.00018436354,0.000042509982,0.0002542114,0.00079448003,0.0065883994,0.0026916915],"genre_scores_gemma":[0.41753024,0.00028528887,0.5763616,0.00017572912,0.000066574496,0.00035493466,0.0024134545,0.0009348546,0.001877265],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99792564,0.00044771604,0.0001201095,0.0003379941,0.0010142792,0.00015421805],"domain_scores_gemma":[0.99660563,0.0018154035,0.000288767,0.0005627452,0.00057880965,0.00014858728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021914253,0.0009194135,0.00071753317,0.0013389119,0.00036496896,0.0012182565,0.0015187019,0.0005092492,0.0025058899],"category_scores_gemma":[0.0072328323,0.00036098354,0.0006459228,0.0013095888,0.0005338353,0.0012826878,0.0010265767,0.000994251,0.000575365],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007843677,0.00036006232,0.010170035,0.0003150172,0.00016899778,0.00017621086,0.00018205839,0.3799504,0.022441281,0.023871839,0.018450364,0.54312944],"study_design_scores_gemma":[0.00005490303,0.00009687094,0.0009474748,0.000009824093,0.00002137434,0.00008734859,0.000030840692,0.9794613,0.007938948,0.007705579,0.0036251163,0.000020450423],"about_ca_topic_score_codex":0.0035831511,"about_ca_topic_score_gemma":0.0049920725,"teacher_disagreement_score":0.0035831511,"about_ca_system_score_codex":0.001070235,"about_ca_system_score_gemma":0.0019369086,"threshold_uncertainty_score":0.011589527},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.09927151819617334,"score_gpt":0.3177039142849232,"score_spread":0.21843239608874981,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380433238","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0054054754,0.00065944577,0.8065154,0.001115167,0.000179412,0.0007826047,0.00944581,0.16959305,0.0063035935],"genre_scores_gemma":[0.11557583,0.0008121913,0.8234657,0.0015597888,0.00013969121,0.00094891916,0.043438703,0.006509243,0.007549932],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997767,0.0005851346,0.00024322957,0.00078049506,0.00048313726,0.00014097523],"domain_scores_gemma":[0.99570614,0.0017400681,0.00023304255,0.0015358763,0.0005514247,0.00023346407],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029688056,0.0012600434,0.0010026973,0.0030214249,0.0011014758,0.002726241,0.0034335274,0.002045022,0.0174754],"category_scores_gemma":[0.013409506,0.000896132,0.002043104,0.0023792973,0.0012530128,0.008511955,0.006681971,0.0028463844,0.008386753],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008156921,0.0005498072,0.0024371282,0.0022748923,0.00024732857,0.0006966301,0.0020136503,0.031247452,0.02512683,0.14139357,0.21072686,0.58247024],"study_design_scores_gemma":[0.00017058048,0.00015227862,0.0012333704,0.00026921832,0.00011008952,0.00050387514,0.00044575735,0.40484232,0.02046156,0.28075486,0.29092717,0.00012882803],"about_ca_topic_score_codex":0.0067533297,"about_ca_topic_score_gemma":0.009189885,"teacher_disagreement_score":0.0174754,"about_ca_system_score_codex":0.0017054051,"about_ca_system_score_gemma":0.0020825577,"threshold_uncertainty_score":0.05846101},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Deutsche Forschungsgemeinschaft","keywords":"Blockchain; Computer science; Distributed computing; Data science; Computer security","score_opus":0.1258081962844258,"score_gpt":0.3060546250598179,"score_spread":0.1802464287753921,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380433250","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038299706,0.0014499616,0.9388972,0.0043233503,0.00007613708,0.00040009225,0.00048017208,0.004712659,0.01136072],"genre_scores_gemma":[0.3612569,0.0011108186,0.63012373,0.0004892088,0.000067707566,0.00020851262,0.00092650315,0.0004645197,0.005352175],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957467,0.0019038222,0.0003306338,0.0005648243,0.0011624659,0.0002916517],"domain_scores_gemma":[0.9932632,0.0025838243,0.0005235853,0.0019572035,0.0014683795,0.00020386031],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050835833,0.0010466494,0.0010413592,0.0015099015,0.00094838097,0.0032944696,0.0018191229,0.0012480654,0.0050774226],"category_scores_gemma":[0.01367918,0.0007324126,0.0007181841,0.0015865518,0.00067215256,0.00617802,0.001215058,0.0017598121,0.0021626665],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003276455,0.00030067816,0.010580395,0.00059152296,0.0003199822,0.00029010666,0.0006340408,0.2399277,0.011584877,0.04179916,0.022212984,0.67143095],"study_design_scores_gemma":[0.000034946584,0.000106032036,0.0010399825,0.00010218261,0.000066532215,0.00011741366,0.00027901263,0.94464564,0.0066521275,0.028634222,0.018274149,0.00004787011],"about_ca_topic_score_codex":0.0063334694,"about_ca_topic_score_gemma":0.014118849,"teacher_disagreement_score":0.0063334694,"about_ca_system_score_codex":0.0013245732,"about_ca_system_score_gemma":0.0018727669,"threshold_uncertainty_score":0.026884854},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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)","score_opus":0.1413222286035876,"score_gpt":0.37321535803998734,"score_spread":0.23189312943639975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381326963","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009280868,0.00022849467,0.97192895,0.00018847568,0.00006920367,0.00007132625,0.002085598,0.01445648,0.0016904972],"genre_scores_gemma":[0.13134165,0.00045360773,0.8590795,0.00014520797,0.00007433854,0.0003629488,0.0043518147,0.0021599664,0.0020309659],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996903,0.00006512357,0.00003524597,0.000060347098,0.000103693,0.000045259698],"domain_scores_gemma":[0.9993586,0.00026017972,0.00008371161,0.0001367713,0.00010875155,0.00005189639],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006623375,0.0012128518,0.0007739375,0.0017542421,0.0003527682,0.0020984984,0.0013551016,0.000602898,0.011229753],"category_scores_gemma":[0.0029888037,0.00044065248,0.0010913876,0.0016550518,0.00028657637,0.0023141638,0.0017109497,0.001051947,0.0017619855],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015510271,0.00022921151,0.0035862855,0.0010487715,0.00019775328,0.00049794314,0.0011589761,0.1192138,0.06841015,0.05356545,0.06439162,0.686149],"study_design_scores_gemma":[0.000096921285,0.00012831244,0.0013885439,0.00007594651,0.000047353475,0.00020955493,0.00017259477,0.8962713,0.0243526,0.029226163,0.047940277,0.00009042401],"about_ca_topic_score_codex":0.0027508172,"about_ca_topic_score_gemma":0.0038875348,"teacher_disagreement_score":0.011229753,"about_ca_system_score_codex":0.00047267755,"about_ca_system_score_gemma":0.00073199923,"threshold_uncertainty_score":0.037567258},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.06327816623333686,"score_gpt":0.3162685902262851,"score_spread":0.25299042399294824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381328483","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0806342,0.0013696111,0.90678763,0.003166252,0.00010438194,0.00024255461,0.0004934085,0.00065522606,0.006546792],"genre_scores_gemma":[0.81408274,0.001048494,0.17605685,0.00067517726,0.0002781812,0.0004011712,0.00071241794,0.00016118067,0.0065838327],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99844885,0.00060450175,0.00006425171,0.00033780865,0.00027574468,0.000268711],"domain_scores_gemma":[0.9917474,0.0063793967,0.0006748287,0.00034953826,0.0005263512,0.00032252897],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003613269,0.0013316403,0.0020643559,0.001111268,0.0009830291,0.0023793662,0.0030930452,0.0036672137,0.0030066404],"category_scores_gemma":[0.01378578,0.0005933263,0.001040002,0.0013485221,0.0013158702,0.0044415514,0.0015688302,0.0024064414,0.0005481372],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019049697,0.0001660049,0.0019560987,0.00019537206,0.00006113563,0.00017239487,0.00020565599,0.8893878,0.0014652906,0.06381093,0.0068453294,0.035543513],"study_design_scores_gemma":[0.000016927792,0.000015362404,0.000070900154,0.0000039117813,0.000006964724,0.000011833381,0.00001258587,0.99013877,0.00014193227,0.009149848,0.00042726225,0.0000038012868],"about_ca_topic_score_codex":0.012634974,"about_ca_topic_score_gemma":0.009763266,"teacher_disagreement_score":0.012634974,"about_ca_system_score_codex":0.0028876308,"about_ca_system_score_gemma":0.0019154459,"threshold_uncertainty_score":0.025122821},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.06453656104710064,"score_gpt":0.3010111735680607,"score_spread":0.23647461252096003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381329253","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17870839,0.0009691645,0.7968478,0.0011376198,0.00023965223,0.00039425743,0.0015758644,0.013153995,0.0069732442],"genre_scores_gemma":[0.47659075,0.0002503703,0.51562315,0.0005904895,0.00015879884,0.0001527021,0.00338564,0.0011777936,0.0020702162],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9888194,0.001160105,0.0010443678,0.0025585052,0.0053662155,0.0010513626],"domain_scores_gemma":[0.9839484,0.009363238,0.0008428504,0.0034914897,0.0020431061,0.00031091392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039043375,0.0014991137,0.0025491503,0.0018798314,0.0010742259,0.004431486,0.0048096133,0.0010956273,0.0063353786],"category_scores_gemma":[0.018756459,0.0012852565,0.002298489,0.0032072377,0.001956907,0.012546078,0.0042231954,0.0030028836,0.0017436433],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003098646,0.0011084514,0.01603581,0.0017017031,0.00081554835,0.0010970645,0.0014317619,0.13717954,0.0947395,0.12805423,0.020710148,0.5940276],"study_design_scores_gemma":[0.00028664386,0.0004769873,0.0022619653,0.000040863248,0.00023812412,0.0006232569,0.00046659753,0.7633927,0.05571991,0.16887096,0.0075191758,0.00010278566],"about_ca_topic_score_codex":0.0070763254,"about_ca_topic_score_gemma":0.00864323,"teacher_disagreement_score":0.0070763254,"about_ca_system_score_codex":0.002686167,"about_ca_system_score_gemma":0.002971568,"threshold_uncertainty_score":0.021193922},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.10194140780191328,"score_gpt":0.3440120252621289,"score_spread":0.24207061746021558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381329270","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08346705,0.002578621,0.49315286,0.0011522314,0.00081592955,0.0029271774,0.06082034,0.33548346,0.019602377],"genre_scores_gemma":[0.17867848,0.00070288085,0.58976233,0.00048684605,0.00010097405,0.0031378127,0.20767951,0.014482131,0.004969027],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99555737,0.0016310996,0.0004574482,0.0010287139,0.0010759896,0.00024946115],"domain_scores_gemma":[0.98413,0.009549213,0.0007482918,0.0019182493,0.003216448,0.0004378261],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040438254,0.0028687594,0.0009871292,0.005460505,0.000757851,0.0020091638,0.0032427867,0.0017104418,0.009022462],"category_scores_gemma":[0.03305459,0.000874062,0.0015403125,0.002840475,0.00079509773,0.003001204,0.0031630504,0.0017849598,0.004532638],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013310668,0.0010648484,0.009405471,0.0049609654,0.00041044893,0.0013453419,0.0025552996,0.05863292,0.04068023,0.021319382,0.30170867,0.5565853],"study_design_scores_gemma":[0.00073494343,0.00071829243,0.008176192,0.00048247838,0.00016745925,0.00071703584,0.0013844816,0.69310427,0.06720524,0.038458336,0.1886228,0.00022844566],"about_ca_topic_score_codex":0.004890708,"about_ca_topic_score_gemma":0.006124322,"teacher_disagreement_score":0.009022462,"about_ca_system_score_codex":0.0013600813,"about_ca_system_score_gemma":0.001837604,"threshold_uncertainty_score":0.030183196},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Lock (firearm); Robustness (evolution); Multi-core processor; Parallel computing; Byte; Distributed computing; Mutual exclusion; Operating system; Computer network","score_opus":0.10227693419833125,"score_gpt":0.3075132284456033,"score_spread":0.20523629424727205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388620459","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044992406,0.001222134,0.92449296,0.00027322443,0.00023533839,0.0002714456,0.00038688414,0.022686362,0.0054391893],"genre_scores_gemma":[0.6840305,0.0004903018,0.30489567,0.00043186435,0.00013507502,0.0003091201,0.0007108535,0.0015596211,0.0074370275],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99790156,0.00023738509,0.00018714326,0.00019839338,0.0011408881,0.00033464504],"domain_scores_gemma":[0.9968676,0.0008091504,0.00042835684,0.0011519708,0.0004989945,0.00024393399],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018673856,0.00050589663,0.0006107509,0.0007382544,0.0008424926,0.0019249923,0.0037163515,0.00050406874,0.0038301537],"category_scores_gemma":[0.0056267986,0.00055224466,0.0003916731,0.00085894275,0.0010675564,0.0026250416,0.002798971,0.0011948051,0.00105289],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032566378,0.0004863706,0.009904305,0.000789372,0.0002146327,0.0005273384,0.0007909556,0.14185327,0.16374774,0.083321184,0.031746782,0.5633614],"study_design_scores_gemma":[0.00053416507,0.0006915484,0.001310721,0.000058719306,0.00009649257,0.0005164099,0.00016453104,0.7604949,0.15644598,0.029659003,0.04984042,0.00018706037],"about_ca_topic_score_codex":0.002725313,"about_ca_topic_score_gemma":0.0039171004,"teacher_disagreement_score":0.0038301537,"about_ca_system_score_codex":0.0010558426,"about_ca_system_score_gemma":0.0023602871,"threshold_uncertainty_score":0.012813151},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.08080241617828675,"score_gpt":0.3053888409634237,"score_spread":0.22458642478513696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389609557","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0071597397,0.00037350747,0.9871787,0.0007026942,0.00006657071,0.00019954033,0.00039248398,0.0029650198,0.000961811],"genre_scores_gemma":[0.32529527,0.00044321423,0.6686343,0.00060679106,0.00016299966,0.0002993163,0.001391191,0.0005616874,0.0026052662],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9872313,0.0039051725,0.0010712927,0.0021123094,0.004831612,0.0008482149],"domain_scores_gemma":[0.9770702,0.008414316,0.0014463416,0.009903898,0.0024542639,0.0007108875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015725533,0.0009149397,0.0016547259,0.0014845076,0.0015635205,0.004498536,0.0043765856,0.0022181494,0.0024028919],"category_scores_gemma":[0.03274978,0.0008227591,0.0014008844,0.002460568,0.0027023235,0.00926779,0.009146815,0.0036949904,0.0008822423],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002408536,0.0005907496,0.0075709815,0.0006984157,0.0003044351,0.0005729696,0.0016128862,0.2273884,0.029339917,0.2948148,0.028506042,0.40619195],"study_design_scores_gemma":[0.00016822714,0.0002300862,0.00050856086,0.00004846725,0.00005097892,0.00038498768,0.00019383649,0.76263964,0.015613627,0.20563093,0.014469178,0.000061514955],"about_ca_topic_score_codex":0.0036700289,"about_ca_topic_score_gemma":0.0042353864,"teacher_disagreement_score":0.015725533,"about_ca_system_score_codex":0.0023096479,"about_ca_system_score_gemma":0.004570264,"threshold_uncertainty_score":0.083165586},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.3094247226058124,"score_gpt":0.395503019242454,"score_spread":0.08607829663664163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389609606","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1352917,0.0028376295,0.79538685,0.0017719049,0.00041278303,0.0008176987,0.0018435159,0.043655075,0.0179828],"genre_scores_gemma":[0.8468665,0.00073872885,0.13333403,0.0007397102,0.00014001253,0.0005870848,0.0015239472,0.0018431343,0.014226918],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972838,0.00046506638,0.00024885472,0.00045146505,0.0011151406,0.00043567785],"domain_scores_gemma":[0.98686326,0.001826457,0.0006704905,0.009627723,0.0007228612,0.00028926486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020993932,0.0010543258,0.00091313216,0.0012424546,0.0014133462,0.0021047867,0.0039399914,0.0013564102,0.0066295844],"category_scores_gemma":[0.008618623,0.0007704382,0.00082993833,0.0011220729,0.0030384012,0.009715975,0.007185211,0.002717954,0.002315535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032023743,0.0008259228,0.011315472,0.0014051773,0.0006476273,0.0012001165,0.0018628832,0.10181806,0.109029196,0.15012635,0.08296312,0.53560376],"study_design_scores_gemma":[0.00035780406,0.0008276007,0.0018822994,0.00021110832,0.00018006786,0.0014913429,0.00038270548,0.60420257,0.17013076,0.13624148,0.08384022,0.0002519934],"about_ca_topic_score_codex":0.0014460235,"about_ca_topic_score_gemma":0.0018561594,"teacher_disagreement_score":0.0066295844,"about_ca_system_score_codex":0.0013290744,"about_ca_system_score_gemma":0.0021212727,"threshold_uncertainty_score":0.022178173},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.07309228208787909,"score_gpt":0.28231069972847156,"score_spread":0.20921841764059246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389609976","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.066339046,0.0010818454,0.9232761,0.00024326077,0.000121231846,0.00014346463,0.00023172537,0.0024473818,0.0061160363],"genre_scores_gemma":[0.44770423,0.00036141076,0.54745275,0.00019851098,0.00007007952,0.00016336625,0.0008482967,0.00037224768,0.0028291338],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981171,0.00036461372,0.000121041034,0.0003030495,0.0008806339,0.00021368427],"domain_scores_gemma":[0.9972907,0.0009722587,0.00027316783,0.0008186423,0.0005108867,0.00013428973],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012974334,0.0008176316,0.00087891717,0.00074929436,0.0010156846,0.0012338326,0.0019856924,0.0005827884,0.0017143943],"category_scores_gemma":[0.005264302,0.00046874434,0.00044666053,0.0013559374,0.00071320584,0.0021768059,0.002157996,0.0007667255,0.0006394842],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012230957,0.00027783052,0.0042210124,0.00035092293,0.00010189194,0.00023581002,0.00042418574,0.44984224,0.037658736,0.051930755,0.02080492,0.43292847],"study_design_scores_gemma":[0.000045102865,0.0001162957,0.0003421079,0.000014734428,0.000018331659,0.00020845175,0.00008381171,0.9606369,0.010244896,0.023132984,0.0051382985,0.000018120267],"about_ca_topic_score_codex":0.0020482838,"about_ca_topic_score_gemma":0.0040509966,"teacher_disagreement_score":0.0020482838,"about_ca_system_score_codex":0.0010741665,"about_ca_system_score_gemma":0.0020148472,"threshold_uncertainty_score":0.007793665},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.09719269435293139,"score_gpt":0.32207878026332337,"score_spread":0.224886085910392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389611627","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47205648,0.003075907,0.49925956,0.001585273,0.00015171827,0.00029664795,0.0006037639,0.013795867,0.009174848],"genre_scores_gemma":[0.7739594,0.0004374286,0.22189687,0.00036828892,0.00005826372,0.000087510496,0.0004923144,0.0008221208,0.0018777917],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977642,0.0005690016,0.00017117012,0.00037240825,0.0008748528,0.00024837628],"domain_scores_gemma":[0.9982565,0.0007570561,0.00014852075,0.000515947,0.00024173303,0.00008024688],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019031859,0.0010182671,0.0005647843,0.00044204967,0.00066654925,0.0020145138,0.0018861899,0.00068106106,0.00089212926],"category_scores_gemma":[0.00313869,0.0005935167,0.0007143142,0.0009996183,0.0011848017,0.0028456917,0.001481822,0.001609954,0.00028958765],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016031512,0.0005429073,0.016162524,0.0004601394,0.00034443167,0.0005720763,0.0013055234,0.4459093,0.15007564,0.024534255,0.0112626115,0.3472274],"study_design_scores_gemma":[0.00008435783,0.00028200168,0.0026702997,0.000018982495,0.00008517593,0.00017971915,0.0003435395,0.92751706,0.050522596,0.011530779,0.006723115,0.000042410422],"about_ca_topic_score_codex":0.0071837823,"about_ca_topic_score_gemma":0.009549847,"teacher_disagreement_score":0.0071837823,"about_ca_system_score_codex":0.0010943302,"about_ca_system_score_gemma":0.0016377532,"threshold_uncertainty_score":0.014283955},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.10344835003044657,"score_gpt":0.3135535429041299,"score_spread":0.21010519287368334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393183687","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014838665,0.00029568336,0.9390623,0.00038921632,0.00015148318,0.00017716984,0.0032145034,0.038470205,0.003400696],"genre_scores_gemma":[0.2596592,0.00047294633,0.70783186,0.00063300977,0.00012681946,0.00034707744,0.018027607,0.003564385,0.009337069],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990103,0.00018874303,0.00008800172,0.0002983102,0.0003332073,0.00008137789],"domain_scores_gemma":[0.9977513,0.0008313867,0.00015925051,0.0008287902,0.0003334803,0.000095785836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001350108,0.0010169699,0.00073226116,0.0014301519,0.0005445267,0.0017739859,0.002506195,0.0009190601,0.01073176],"category_scores_gemma":[0.006887335,0.00054995547,0.0017535323,0.0016715825,0.000907535,0.006842368,0.002464308,0.0024246697,0.005227981],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005623537,0.0004250442,0.0043151462,0.0004880039,0.00012025084,0.00039654126,0.00050036714,0.10527438,0.013235885,0.056524213,0.066849574,0.7513082],"study_design_scores_gemma":[0.000054082855,0.00008074307,0.00027980554,0.00003499546,0.000032562104,0.00016119111,0.00009108228,0.9183519,0.0131200515,0.048556384,0.01920556,0.000031634372],"about_ca_topic_score_codex":0.0064290254,"about_ca_topic_score_gemma":0.0109417755,"teacher_disagreement_score":0.01073176,"about_ca_system_score_codex":0.0011175158,"about_ca_system_score_gemma":0.0022653006,"threshold_uncertainty_score":0.035901308},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.06813038036782831,"score_gpt":0.34676075998945977,"score_spread":0.27863037962163145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393212300","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09026507,0.00011835322,0.90468854,0.00039236643,0.000043728767,0.00028785478,0.00021229008,0.00037881773,0.0036129963],"genre_scores_gemma":[0.6199874,0.00014667466,0.37516466,0.00018560699,0.000050501276,0.00040404737,0.00047561858,0.00018059883,0.0034048988],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99709046,0.0012300321,0.00015585049,0.0006239296,0.0005024816,0.00039725617],"domain_scores_gemma":[0.990493,0.007098612,0.0004899684,0.000984392,0.0004252312,0.00050884456],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004068304,0.001234872,0.0024423236,0.0010255831,0.0013008639,0.0034589448,0.0024684325,0.0014624957,0.006154745],"category_scores_gemma":[0.014121107,0.00081950444,0.0016164259,0.0016914392,0.0021123146,0.007486124,0.0032600733,0.0027620068,0.00064989267],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005371847,0.0002946581,0.0018496836,0.00039746103,0.0001610624,0.00028813092,0.00070389896,0.52611446,0.0041306964,0.38876852,0.0037057672,0.073048435],"study_design_scores_gemma":[0.00005681674,0.00004371314,0.00009468983,0.000011855371,0.000016178075,0.000029348093,0.000076885,0.69230145,0.0009437691,0.30560657,0.000806148,0.000012573643],"about_ca_topic_score_codex":0.002089321,"about_ca_topic_score_gemma":0.0028947336,"teacher_disagreement_score":0.006154745,"about_ca_system_score_codex":0.0022863378,"about_ca_system_score_gemma":0.0025816837,"threshold_uncertainty_score":0.021515489},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.06779863890756006,"score_gpt":0.30346095502099496,"score_spread":0.2356623161134349,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396892510","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032082815,0.00028106518,0.9633032,0.00025875831,0.00005443965,0.00006727056,0.000058320395,0.00034989367,0.0035441641],"genre_scores_gemma":[0.75051296,0.00058543665,0.24283662,0.00019140102,0.00017332801,0.00020372045,0.000249633,0.00022418336,0.0050227046],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964007,0.001010255,0.00013723968,0.00075773714,0.0013392692,0.00035479863],"domain_scores_gemma":[0.99270767,0.003934541,0.0008038918,0.0013640783,0.0009020229,0.000287856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030725,0.0007192231,0.0013825374,0.0006399719,0.0012878408,0.0026549743,0.0032399537,0.0011776519,0.0026125791],"category_scores_gemma":[0.011191178,0.00093762507,0.0008179936,0.0012798943,0.0015869847,0.0050460747,0.0025351075,0.001836185,0.0006369869],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019975482,0.000092815906,0.0005317449,0.00009463796,0.000048598926,0.000059748298,0.000092694536,0.87951976,0.003452198,0.08833679,0.0014388207,0.026132349],"study_design_scores_gemma":[0.000017870958,0.000048041064,0.00004509521,0.0000035462956,0.000009980741,0.00004107434,0.000017547462,0.9630043,0.0011507412,0.03477133,0.0008854434,0.0000050230947],"about_ca_topic_score_codex":0.0013185204,"about_ca_topic_score_gemma":0.0012787038,"teacher_disagreement_score":0.0032399537,"about_ca_system_score_codex":0.001559299,"about_ca_system_score_gemma":0.0015827037,"threshold_uncertainty_score":0.01624912},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Matrix multiplication; Multiplication (music); Query optimization; Matrix (chemical analysis); Arithmetic; Information retrieval; Mathematics; Physics; Chemistry; Combinatorics","score_opus":0.0612702140294622,"score_gpt":0.33393771987223864,"score_spread":0.27266750584277644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396892532","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007047295,0.0012335445,0.9819518,0.0005297004,0.00026629562,0.00013834721,0.00018269428,0.0035973918,0.005052878],"genre_scores_gemma":[0.17880824,0.0013903024,0.8097851,0.0005218305,0.00061680056,0.00043679125,0.0008355433,0.00115972,0.006445722],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99150145,0.0019330996,0.00054820295,0.0013085902,0.0037374094,0.0009713545],"domain_scores_gemma":[0.9858628,0.007652321,0.0005144928,0.0033690382,0.002337236,0.0002641127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043521607,0.0024444086,0.0018407255,0.0019076394,0.002124946,0.0042874548,0.002957052,0.0014912892,0.01304338],"category_scores_gemma":[0.017094681,0.0009869848,0.0014511634,0.004016181,0.0019660513,0.01215508,0.004060097,0.003769915,0.0063739596],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018369264,0.00033115357,0.00139671,0.0009424587,0.00016039661,0.0002718156,0.0006539543,0.06656437,0.032586828,0.32815263,0.042472146,0.52463067],"study_design_scores_gemma":[0.00020994784,0.0004593997,0.00035472837,0.00011585391,0.00009552384,0.0005269857,0.00019125157,0.5941912,0.035241634,0.31844634,0.05006021,0.000106945925],"about_ca_topic_score_codex":0.0031849623,"about_ca_topic_score_gemma":0.002792108,"teacher_disagreement_score":0.01304338,"about_ca_system_score_codex":0.0022215892,"about_ca_system_score_gemma":0.0020783106,"threshold_uncertainty_score":0.043634415},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science","score_opus":0.08898262796644435,"score_gpt":0.3509226316586121,"score_spread":0.26194000369216774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396892769","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21445453,0.0038429408,0.7467605,0.0033235403,0.0004151045,0.00054769916,0.010209891,0.012878201,0.0075675966],"genre_scores_gemma":[0.74037284,0.0012731705,0.24477397,0.0006585868,0.00027267236,0.00030445674,0.008913123,0.0005866873,0.002844581],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99019486,0.0017508547,0.0012612303,0.0020679757,0.004112924,0.00061220344],"domain_scores_gemma":[0.9394614,0.029790048,0.0085572945,0.015029036,0.0057014637,0.0014607199],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00434885,0.0012604654,0.0016662992,0.004998861,0.001511091,0.0033563888,0.0025188697,0.002103411,0.0024967538],"category_scores_gemma":[0.07849787,0.0007972623,0.00078257994,0.010401985,0.0014520218,0.011592067,0.004709005,0.0018531987,0.0013123138],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021123243,0.00044796808,0.06291169,0.001382423,0.00036235063,0.0014072751,0.002773007,0.29368642,0.019845873,0.070450656,0.03765471,0.5069654],"study_design_scores_gemma":[0.00012399576,0.00034006368,0.0076572797,0.00011303173,0.00012266156,0.0020371408,0.0013143014,0.80155796,0.01030641,0.15741551,0.018901577,0.00011006443],"about_ca_topic_score_codex":0.008415269,"about_ca_topic_score_gemma":0.008173718,"teacher_disagreement_score":0.008415269,"about_ca_system_score_codex":0.001575254,"about_ca_system_score_gemma":0.0017218416,"threshold_uncertainty_score":0.022999167},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Universitas Brawijaya","keywords":"Computer science","score_opus":0.05590839665298635,"score_gpt":0.3236092414076727,"score_spread":0.26770084475468636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396892922","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04686186,0.00091565796,0.9237599,0.0026678215,0.00026293486,0.0003441986,0.00073303544,0.018365234,0.0060893386],"genre_scores_gemma":[0.25405577,0.00029658576,0.7367905,0.0011770603,0.00015796606,0.00055620755,0.0011789096,0.0010007727,0.0047861747],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9906036,0.0022529073,0.00062711077,0.0026931632,0.0025984272,0.0012247815],"domain_scores_gemma":[0.97547185,0.010808306,0.0012328924,0.010648844,0.0012883602,0.0005498411],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00475499,0.001817694,0.002363025,0.0011474699,0.0014953421,0.0038133236,0.0044709877,0.0032283848,0.008695833],"category_scores_gemma":[0.023411658,0.0011835361,0.0043669613,0.0015417513,0.002535764,0.010689813,0.004179268,0.0055577178,0.003308073],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033999984,0.0009794749,0.005673829,0.0014450473,0.0004606624,0.00038046684,0.0011152376,0.13995911,0.05690054,0.26307,0.026730059,0.49988565],"study_design_scores_gemma":[0.00034191582,0.00037551174,0.00074358704,0.00014500218,0.00022951946,0.00048782607,0.00020503068,0.76277417,0.02536229,0.18817267,0.021041544,0.00012095715],"about_ca_topic_score_codex":0.005625187,"about_ca_topic_score_gemma":0.0058719874,"teacher_disagreement_score":0.008695833,"about_ca_system_score_codex":0.0040725237,"about_ca_system_score_gemma":0.005823125,"threshold_uncertainty_score":0.029548347},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Universitas Brawijaya","keywords":"STREAMS; Forgetting; Computer science; Psychology; Cognitive psychology; Computer network","score_opus":0.17013563614582022,"score_gpt":0.36502365305304313,"score_spread":0.1948880169072229,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396893056","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.091165274,0.0018866396,0.883114,0.009870627,0.00032885477,0.00019716352,0.00077457156,0.00070673664,0.011956082],"genre_scores_gemma":[0.8604854,0.0016936383,0.1286929,0.0013836604,0.00083545694,0.0002903069,0.00093090744,0.00032818902,0.0053594727],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98675644,0.005640956,0.0008933102,0.003025953,0.0025246341,0.0011587368],"domain_scores_gemma":[0.66303045,0.30073148,0.009230653,0.016108304,0.007624387,0.00327485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018989332,0.0013389228,0.0022518558,0.0016940839,0.0026281795,0.0058435528,0.004297584,0.00426761,0.0062490953],"category_scores_gemma":[0.1990873,0.0014536171,0.002192589,0.0023210172,0.006900932,0.01920074,0.006686232,0.007770666,0.0007319573],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015288874,0.0001826485,0.007595639,0.0004861897,0.0001243824,0.00086902454,0.0012359612,0.23661041,0.0018200664,0.694072,0.004920815,0.050553918],"study_design_scores_gemma":[0.00007572677,0.00008957333,0.00045469266,0.00008619647,0.000028454739,0.0002484314,0.00015985008,0.54343957,0.0010248529,0.45256215,0.0017870002,0.000043591357],"about_ca_topic_score_codex":0.0053036804,"about_ca_topic_score_gemma":0.0032968319,"teacher_disagreement_score":0.018989332,"about_ca_system_score_codex":0.002334645,"about_ca_system_score_gemma":0.0032757916,"threshold_uncertainty_score":0.100426435},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.11260369583204238,"score_gpt":0.3468254042837654,"score_spread":0.23422170845172302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399156410","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046888392,0.0008294734,0.94590425,0.0007758488,0.00007480355,0.0002772324,0.0006579277,0.0031959997,0.0013960685],"genre_scores_gemma":[0.41808838,0.00045600248,0.5730137,0.0008035888,0.00016732111,0.00067930826,0.004735751,0.0007837301,0.0012722177],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9912096,0.0027722684,0.0009594766,0.0019634832,0.002614927,0.00048021684],"domain_scores_gemma":[0.9360967,0.03444773,0.004057187,0.015179763,0.009325502,0.00089303794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013758249,0.0021959506,0.0028936437,0.0032929152,0.0012760692,0.0030683181,0.0041530915,0.0023348948,0.003508053],"category_scores_gemma":[0.09475756,0.0012489841,0.0017610899,0.0028219754,0.0017298417,0.008389064,0.0066670114,0.0054065106,0.0019219934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016116498,0.0012650847,0.027632434,0.0008276705,0.0004181537,0.0003846941,0.0012371646,0.17302561,0.018951697,0.020353466,0.0146879805,0.73960453],"study_design_scores_gemma":[0.00010746165,0.00035806067,0.0027218305,0.00009817799,0.00007984424,0.00024774976,0.00028271766,0.94820035,0.015221208,0.026830697,0.0057942695,0.00005767327],"about_ca_topic_score_codex":0.0034630334,"about_ca_topic_score_gemma":0.0052741743,"teacher_disagreement_score":0.013758249,"about_ca_system_score_codex":0.0011821003,"about_ca_system_score_gemma":0.0040551797,"threshold_uncertainty_score":0.07276142},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; 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","score_opus":0.032554998589815504,"score_gpt":0.30317395140419895,"score_spread":0.2706189528143834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399156413","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030578515,0.0016963229,0.9256335,0.0006408496,0.0002107261,0.000445145,0.00046217357,0.032693755,0.007639083],"genre_scores_gemma":[0.37965587,0.0006171966,0.6092455,0.0005121783,0.0001631668,0.0007158569,0.0011588976,0.0032408552,0.0046904953],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960472,0.00086237397,0.00028865255,0.00079378625,0.0012955721,0.00071245426],"domain_scores_gemma":[0.9949787,0.0020004185,0.0005429355,0.0018059241,0.0003574446,0.0003145262],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038337323,0.0020559153,0.0015979656,0.0017442793,0.0013437849,0.003018651,0.0057807695,0.0017499136,0.006150592],"category_scores_gemma":[0.013945741,0.0012133747,0.00072020944,0.0021307515,0.001431858,0.0054889806,0.0048302836,0.0027702134,0.0025098633],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013669684,0.000721878,0.0058592753,0.00065804203,0.00018256044,0.0002672613,0.0007492848,0.2060806,0.047629155,0.03774072,0.04254052,0.65620375],"study_design_scores_gemma":[0.00016299548,0.0001813528,0.00097318937,0.00006143509,0.000053686323,0.0001660452,0.00011220842,0.9469015,0.01715155,0.020879844,0.013272435,0.00008381068],"about_ca_topic_score_codex":0.0041381004,"about_ca_topic_score_gemma":0.0050067957,"teacher_disagreement_score":0.006150592,"about_ca_system_score_codex":0.0017644488,"about_ca_system_score_gemma":0.0034433948,"threshold_uncertainty_score":0.020575821},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Universitas Brawijaya","keywords":"Computer science; Scalability; Mathematical optimization; Independence (probability theory); Mathematics","score_opus":0.12434380659866183,"score_gpt":0.3641923593716973,"score_spread":0.23984855277303546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399174291","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017414105,0.0000663337,0.997221,0.00013580089,0.000020327156,0.00003859871,0.00005106481,0.000540071,0.00018541292],"genre_scores_gemma":[0.15939814,0.00029452328,0.83517224,0.00043574275,0.00012316962,0.00042025957,0.0009657904,0.000968841,0.002221215],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99364626,0.0023119836,0.0004228577,0.0012506263,0.001959227,0.0004090894],"domain_scores_gemma":[0.9832876,0.008246134,0.0016192176,0.0044114874,0.002053997,0.00038160058],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009386571,0.0016054147,0.0020952506,0.0019304189,0.0017679493,0.002945765,0.0038068949,0.0026074317,0.0028277982],"category_scores_gemma":[0.032097597,0.0010656045,0.0026681519,0.0025633627,0.0036322847,0.0059973216,0.007385392,0.005768319,0.0011272002],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036128197,0.00016224975,0.0026036573,0.00047874133,0.00022787377,0.00032823943,0.00059674546,0.6314083,0.012559094,0.09293812,0.009314306,0.2490214],"study_design_scores_gemma":[0.000023740322,0.000082329934,0.00029405562,0.00003725482,0.000020751471,0.00012427621,0.00011455949,0.9252272,0.00764299,0.06267842,0.0037222607,0.000031997806],"about_ca_topic_score_codex":0.0051218187,"about_ca_topic_score_gemma":0.004157647,"teacher_disagreement_score":0.009386571,"about_ca_system_score_codex":0.001953521,"about_ca_system_score_gemma":0.00621663,"threshold_uncertainty_score":0.04964149},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.12639640691388002,"score_gpt":0.35644566552143997,"score_spread":0.23004925860755995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399174293","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022335097,0.00038367294,0.9739688,0.00023402381,0.00006270807,0.00010625283,0.0002479372,0.0013492324,0.0013123271],"genre_scores_gemma":[0.46804598,0.0005295398,0.52527195,0.0003548824,0.00021096821,0.0002923068,0.0015457108,0.00040163487,0.0033470292],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973459,0.0005581336,0.00018167094,0.00070905656,0.0009259118,0.00027930204],"domain_scores_gemma":[0.99328244,0.0034484512,0.0004660331,0.0016376526,0.0008532012,0.00031213593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030159557,0.00077691977,0.0017835059,0.00096540543,0.0012657401,0.0023815676,0.0026434525,0.0010855757,0.002230403],"category_scores_gemma":[0.013358836,0.000574609,0.0010516034,0.0021653767,0.0013788306,0.00556631,0.00282901,0.0016834321,0.0005774895],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010434801,0.00031304586,0.009125411,0.00041552933,0.00020328246,0.000449977,0.000558938,0.52582574,0.023966579,0.124949776,0.012204978,0.3009433],"study_design_scores_gemma":[0.000026751406,0.00007723278,0.0002910621,0.00001032443,0.000019690948,0.000107124375,0.00005669325,0.9583165,0.00559247,0.03265283,0.002834606,0.0000146663215],"about_ca_topic_score_codex":0.0041956166,"about_ca_topic_score_gemma":0.0048497254,"teacher_disagreement_score":0.0041956166,"about_ca_system_score_codex":0.0010620913,"about_ca_system_score_gemma":0.002047708,"threshold_uncertainty_score":0.015950084},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Information retrieval; Schema (genetic algorithms); Component (thermodynamics); Data mining; Table (database)","score_opus":0.13553878951404624,"score_gpt":0.3611646660040275,"score_spread":0.22562587648998128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399174990","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005283117,0.0010136061,0.97902346,0.00042911866,0.00009096947,0.00027918836,0.0038240163,0.008567123,0.0014894741],"genre_scores_gemma":[0.04773195,0.0006501893,0.9341906,0.00028891323,0.000049265567,0.0002496573,0.0151884165,0.0004975746,0.001153388],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99507093,0.0010032109,0.00054775045,0.0011237198,0.0020647733,0.00018965312],"domain_scores_gemma":[0.98945016,0.0033476572,0.00068684353,0.004246322,0.0020654334,0.00020354305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048620133,0.0015933871,0.001557241,0.0061145136,0.0010770715,0.002766668,0.0025415837,0.001382983,0.0041517504],"category_scores_gemma":[0.018212255,0.00083058147,0.0027428796,0.0076521495,0.0011606152,0.007479253,0.004695519,0.0027574361,0.0036031613],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004036581,0.00027856618,0.0057885326,0.0015374925,0.00034487678,0.0008471529,0.0011083203,0.045446634,0.029075319,0.05368097,0.035161097,0.8263273],"study_design_scores_gemma":[0.00008141572,0.00022921874,0.0024565202,0.00029590103,0.00019051133,0.0014471185,0.00090682425,0.62741417,0.08410067,0.14040375,0.14231431,0.00015960379],"about_ca_topic_score_codex":0.0035258203,"about_ca_topic_score_gemma":0.005729317,"teacher_disagreement_score":0.0061145136,"about_ca_system_score_codex":0.0015541754,"about_ca_system_score_gemma":0.0026816295,"threshold_uncertainty_score":0.025713086},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.053170123164911785,"score_gpt":0.2665536884634266,"score_spread":0.2133835652985148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402426760","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05009426,0.0030037414,0.8588315,0.00072507624,0.00031673306,0.00039551026,0.0035548618,0.07214289,0.010935448],"genre_scores_gemma":[0.41744038,0.0008783995,0.55792433,0.001238479,0.00021554937,0.000620263,0.0065526417,0.002553058,0.01257689],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997474,0.00018717961,0.00023821389,0.0004365246,0.0014115518,0.0002525423],"domain_scores_gemma":[0.99441296,0.0016789889,0.0005318301,0.0017377377,0.0014458103,0.00019274087],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018310681,0.0009973404,0.0012399158,0.0024944902,0.001046283,0.0025774979,0.0030301851,0.0014319126,0.005982],"category_scores_gemma":[0.011472814,0.00069404586,0.0006838584,0.0022930577,0.0009327604,0.0059981747,0.00279922,0.0010574491,0.0036618935],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002314446,0.00028472094,0.010185171,0.0005392072,0.00014822479,0.00046092013,0.00052010285,0.018097362,0.05744437,0.026969958,0.07530449,0.80773103],"study_design_scores_gemma":[0.00042661556,0.0009205572,0.004141358,0.00018818009,0.00014113002,0.0016560914,0.00049059594,0.6293814,0.1950389,0.04762153,0.11963395,0.00035967462],"about_ca_topic_score_codex":0.0047856444,"about_ca_topic_score_gemma":0.0056317337,"teacher_disagreement_score":0.005982,"about_ca_system_score_codex":0.0011756434,"about_ca_system_score_gemma":0.0018756979,"threshold_uncertainty_score":0.020011842},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.052421053948253374,"score_gpt":0.32084299875920125,"score_spread":0.2684219448109479,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404130423","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12023291,0.001285593,0.8692543,0.0008227641,0.00009340795,0.0002964107,0.0020094144,0.0045837783,0.0014213934],"genre_scores_gemma":[0.40213993,0.0005813177,0.58961916,0.00020750533,0.00016875486,0.00023631615,0.0054775877,0.0003584222,0.0012109805],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99651766,0.0004423555,0.0005561039,0.0009240954,0.0012649632,0.00029484864],"domain_scores_gemma":[0.9915677,0.003514435,0.0011407828,0.0017974216,0.0016127464,0.00036696135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025030738,0.0015338259,0.0028599603,0.002158416,0.0008257327,0.0036531007,0.0023298287,0.001562423,0.0020033838],"category_scores_gemma":[0.017379662,0.0007958171,0.0011603119,0.0035117636,0.00083130674,0.0063770353,0.0018423541,0.0013802095,0.0011630506],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022342494,0.00051512435,0.013603477,0.0016048938,0.0005805501,0.00082893367,0.0017321219,0.34882572,0.06622405,0.025096007,0.015311513,0.52344334],"study_design_scores_gemma":[0.000059565544,0.00032946415,0.0022847063,0.000037220714,0.00013523051,0.00038636907,0.00045458396,0.94372463,0.023980442,0.024680609,0.003879738,0.00004740794],"about_ca_topic_score_codex":0.0021994978,"about_ca_topic_score_gemma":0.003327274,"teacher_disagreement_score":0.0036531007,"about_ca_system_score_codex":0.0012439626,"about_ca_system_score_gemma":0.0016549132,"threshold_uncertainty_score":0.013237655},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Benchmark (surveying); Computer science; Artificial intelligence; Information retrieval; Geography","score_opus":0.05128988014828679,"score_gpt":0.2954122021952202,"score_spread":0.2441223220469334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407355838","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0931278,0.0006280868,0.78108895,0.0005263693,0.00021434792,0.000959839,0.0027669207,0.114560336,0.0061272713],"genre_scores_gemma":[0.52473414,0.00016546823,0.45116344,0.0002994257,0.00006845826,0.0011054464,0.014242655,0.004989411,0.0032315583],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99592835,0.002090082,0.00024693293,0.0007815512,0.00073061796,0.00022245581],"domain_scores_gemma":[0.98882747,0.0067569925,0.00040366568,0.0020180522,0.0016901554,0.00030379437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003410154,0.0020921822,0.0012396389,0.0022651465,0.0007089255,0.0017398016,0.00282885,0.0011607552,0.00489074],"category_scores_gemma":[0.022113223,0.00065274374,0.00089632807,0.0011675162,0.00075791276,0.0027543015,0.0032713104,0.0013647428,0.0023988765],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018693177,0.00083767535,0.004778986,0.0011651808,0.00020971383,0.000816551,0.0014383157,0.23298718,0.039030798,0.009083797,0.044714082,0.66306835],"study_design_scores_gemma":[0.00016480048,0.00024966258,0.0007474704,0.00002982591,0.000059350416,0.000092291506,0.00031863645,0.9578103,0.022603178,0.009819552,0.008062644,0.000042190757],"about_ca_topic_score_codex":0.0045393924,"about_ca_topic_score_gemma":0.006106475,"teacher_disagreement_score":0.00489074,"about_ca_system_score_codex":0.0011495715,"about_ca_system_score_gemma":0.0014695527,"threshold_uncertainty_score":0.018034875},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Toronto","funders":"","keywords":"Computer science; SQL; Programming language; Database","score_opus":0.03721397291859412,"score_gpt":0.2741668219245275,"score_spread":0.23695284900593339,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407356147","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03966335,0.00015182767,0.91798526,0.00048083568,0.000041850275,0.00018096284,0.00027296576,0.039872985,0.0013499975],"genre_scores_gemma":[0.6025104,0.00011849279,0.38929725,0.0005299482,0.000074924064,0.00030051998,0.000950656,0.0031834897,0.0030343223],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99174225,0.0032965087,0.0005446021,0.0013866773,0.002748844,0.00028125162],"domain_scores_gemma":[0.9718204,0.014438236,0.0014418991,0.009617512,0.0022271166,0.00045486377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007771262,0.0012653947,0.0009940852,0.0007792821,0.00055810745,0.002339134,0.0042097913,0.0017349182,0.0034019288],"category_scores_gemma":[0.041461475,0.0007673644,0.0009996502,0.00066182925,0.0019019564,0.0063083204,0.0052610096,0.002695811,0.0017795713],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00268958,0.0008219838,0.010602772,0.00053173624,0.00018870538,0.0007908033,0.0019687118,0.3637539,0.06737945,0.058828242,0.019639302,0.47280487],"study_design_scores_gemma":[0.00005226412,0.00011286305,0.00023602291,0.00000934358,0.0000149288335,0.00008006486,0.000042257296,0.95847964,0.01169343,0.026531378,0.002721254,0.000026502135],"about_ca_topic_score_codex":0.0022129556,"about_ca_topic_score_gemma":0.002502219,"teacher_disagreement_score":0.007771262,"about_ca_system_score_codex":0.0009060062,"about_ca_system_score_gemma":0.001545325,"threshold_uncertainty_score":0.041098893},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Universitas Brawijaya","keywords":"Conjunctive query; Computer science; Information retrieval; Relational database","score_opus":0.23177775578713952,"score_gpt":0.42148744517481745,"score_spread":0.18970968938767793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411141319","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2338613,0.0010300613,0.74449867,0.003600675,0.00013139193,0.00081211666,0.0048771002,0.003692457,0.0074961716],"genre_scores_gemma":[0.590995,0.00034459558,0.39720622,0.00056039635,0.00014723299,0.00041154484,0.0064140204,0.0005747877,0.0033461696],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9950676,0.00091774086,0.0006559367,0.0014703823,0.0014715634,0.00041669546],"domain_scores_gemma":[0.98198396,0.012090206,0.0013137783,0.0030408895,0.0010162515,0.0005548978],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040204306,0.00085956213,0.0013670238,0.00088867417,0.0010819446,0.0031879249,0.0021676354,0.001437684,0.007455106],"category_scores_gemma":[0.024834706,0.0007734019,0.001584535,0.0014915776,0.0015207669,0.010712854,0.004040366,0.002093174,0.00081875623],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0043270355,0.00088087865,0.01579568,0.003210411,0.000586007,0.0011747524,0.003803917,0.12598379,0.06883511,0.35669804,0.024920242,0.39378414],"study_design_scores_gemma":[0.00040193586,0.00046832356,0.0020084053,0.00015191898,0.00019966345,0.00097204227,0.0013995213,0.50793356,0.046567332,0.42456093,0.015247686,0.00008871698],"about_ca_topic_score_codex":0.0009988025,"about_ca_topic_score_gemma":0.0014930882,"teacher_disagreement_score":0.007455106,"about_ca_system_score_codex":0.0012150586,"about_ca_system_score_gemma":0.0014687267,"threshold_uncertainty_score":0.024939835},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Spanning tree; Minimum spanning tree; Minimum degree spanning tree; Combinatorics; Perturbation (astronomy); Mathematics; Physics","score_opus":0.05061472259112793,"score_gpt":0.3086069096880938,"score_spread":0.25799218709696586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411141435","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056881096,0.0022926633,0.915876,0.0063771484,0.0002698445,0.0003100783,0.0012563261,0.0024542573,0.014282569],"genre_scores_gemma":[0.8011921,0.0016246402,0.18666926,0.0015868717,0.00046056893,0.00058862404,0.0013498586,0.0010057305,0.0055223517],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9903246,0.003533841,0.00044983803,0.0019328262,0.0025870646,0.0011718622],"domain_scores_gemma":[0.93494457,0.049056966,0.0024416223,0.010209826,0.0020288324,0.0013182296],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00877942,0.0028096894,0.0033886866,0.0013060239,0.001947948,0.005432856,0.0056064944,0.0039412472,0.0063274163],"category_scores_gemma":[0.07445807,0.0013860388,0.0020584145,0.0031608664,0.0042061526,0.018542593,0.008033188,0.0088679055,0.002103406],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023284366,0.00042983852,0.0021963532,0.00087067334,0.00022183364,0.00044723338,0.00080150506,0.60753685,0.010069198,0.28777424,0.012070339,0.07525355],"study_design_scores_gemma":[0.00007106192,0.00011102093,0.00020386149,0.000070481285,0.000050868555,0.00018685916,0.00008207118,0.7460705,0.0033207275,0.24787644,0.0019279118,0.000028219802],"about_ca_topic_score_codex":0.00089711626,"about_ca_topic_score_gemma":0.0010300733,"teacher_disagreement_score":0.00877942,"about_ca_system_score_codex":0.0052189077,"about_ca_system_score_gemma":0.0028510075,"threshold_uncertainty_score":0.046430588},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Join (topology); Aggregate (composite); Computer science; Algorithm; Theoretical computer science; Mathematics; Combinatorics","score_opus":0.06301675797609008,"score_gpt":0.3193127812564128,"score_spread":0.25629602328032275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411141648","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041534714,0.001066912,0.93523663,0.0005878003,0.00011483612,0.00022550346,0.0010930034,0.009313324,0.010827305],"genre_scores_gemma":[0.36144364,0.0007742166,0.62116784,0.00065856404,0.00032640764,0.00054139184,0.004926794,0.0023089703,0.007852244],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.991699,0.0012270834,0.0009802621,0.0017777069,0.0030433189,0.0012725779],"domain_scores_gemma":[0.99010324,0.004178574,0.0006068093,0.0035609733,0.0012300235,0.00032042403],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036039967,0.001711749,0.0017805877,0.0014837867,0.0013460873,0.0052784965,0.003008788,0.0016681484,0.009325603],"category_scores_gemma":[0.013654062,0.00088356814,0.0019805583,0.0033567331,0.0014831864,0.010811654,0.005173522,0.0027885444,0.0039592623],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004086814,0.0009916375,0.004244715,0.001530201,0.00026203305,0.00022671255,0.0016036232,0.119201705,0.04411084,0.27541992,0.033173125,0.51514876],"study_design_scores_gemma":[0.0003238949,0.00036362396,0.000888912,0.000088224384,0.00013434868,0.00034258552,0.00040748564,0.58417636,0.032464966,0.36375436,0.016971154,0.000084069885],"about_ca_topic_score_codex":0.0018048545,"about_ca_topic_score_gemma":0.0021819635,"teacher_disagreement_score":0.009325603,"about_ca_system_score_codex":0.0024971934,"about_ca_system_score_gemma":0.0022923911,"threshold_uncertainty_score":0.03119719},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.024970418219312337,"score_gpt":0.32197904203225824,"score_spread":0.2970086238129459,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411141667","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019299842,0.00033189633,0.9684415,0.00039210616,0.00013104259,0.0002229926,0.00052142143,0.0052712075,0.005387903],"genre_scores_gemma":[0.13585854,0.00015178154,0.8552765,0.00023783586,0.00010976144,0.00039118194,0.001612988,0.00062449416,0.0057368926],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99785006,0.00031818205,0.0001513171,0.0006304374,0.0007290445,0.0003209251],"domain_scores_gemma":[0.99647444,0.0010182154,0.00029868766,0.0013398348,0.0006638947,0.00020497144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010415919,0.0016559496,0.0016167706,0.0026663179,0.0012780591,0.0025373467,0.003604642,0.0013275968,0.012030361],"category_scores_gemma":[0.006146848,0.0008749006,0.0012913259,0.0038299721,0.0009519055,0.006178799,0.0034489988,0.0017395514,0.0042522866],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00074000226,0.0003360304,0.0020272795,0.0004003229,0.00013257592,0.00026907437,0.00058533635,0.13954385,0.02373864,0.08544931,0.02562875,0.72114885],"study_design_scores_gemma":[0.00013627757,0.00014630811,0.00037742197,0.000028667262,0.000029315417,0.00017913262,0.00009432121,0.8876814,0.005403137,0.096789904,0.009089132,0.000045027173],"about_ca_topic_score_codex":0.009977807,"about_ca_topic_score_gemma":0.013613483,"teacher_disagreement_score":0.012030361,"about_ca_system_score_codex":0.0019007871,"about_ca_system_score_gemma":0.0026337425,"threshold_uncertainty_score":0.040245593},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.0438812084694511,"score_gpt":0.3106361800602223,"score_spread":0.2667549715907712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411141691","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.079799905,0.002171641,0.8963785,0.007230886,0.00022262683,0.00034133784,0.0015845204,0.0020073594,0.010263243],"genre_scores_gemma":[0.6055515,0.0016240686,0.38183513,0.0021885277,0.0010559871,0.00070901896,0.0014201353,0.00067393115,0.0049417205],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9912349,0.001926647,0.000701551,0.002892561,0.002035923,0.0012083545],"domain_scores_gemma":[0.96171135,0.02605462,0.0020887894,0.0074821715,0.0017563405,0.00090666825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055986997,0.002120182,0.0031925652,0.001435435,0.0015560677,0.007350797,0.0033150245,0.0028490233,0.006124865],"category_scores_gemma":[0.03382564,0.0012754186,0.0029335357,0.003613947,0.0036336381,0.027274953,0.004628514,0.006633448,0.0017730101],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002000887,0.00058162864,0.0037989216,0.001423446,0.00027351294,0.00032379612,0.0010600699,0.11677308,0.022326613,0.5965684,0.022496352,0.2323732],"study_design_scores_gemma":[0.00009803737,0.00020118515,0.0004680363,0.000050899303,0.000059199614,0.0003810377,0.00016408981,0.20460333,0.0063030478,0.78322875,0.0043984717,0.000043842596],"about_ca_topic_score_codex":0.0024352667,"about_ca_topic_score_gemma":0.001981932,"teacher_disagreement_score":0.007350797,"about_ca_system_score_codex":0.0027352897,"about_ca_system_score_gemma":0.003355478,"threshold_uncertainty_score":0.029609084},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Universitas Brawijaya","keywords":"Computer science; Query optimization; Information retrieval","score_opus":0.029137233481638006,"score_gpt":0.2919665382818373,"score_spread":0.2628293048001993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411141774","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.122953,0.0020859074,0.8560124,0.003981926,0.00015786814,0.00021953801,0.0008090761,0.0014393831,0.012340914],"genre_scores_gemma":[0.84872425,0.0012788809,0.1407419,0.001129284,0.0008809345,0.00039045105,0.0011366117,0.0007428442,0.0049747936],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9911203,0.0019161791,0.00040775244,0.0015510949,0.0038489886,0.0011557492],"domain_scores_gemma":[0.9401087,0.045937303,0.0034013393,0.006764219,0.0028622025,0.00092630746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005349948,0.0014242465,0.0015455202,0.0022675043,0.0015355379,0.004319074,0.0053273137,0.0019236011,0.0047589336],"category_scores_gemma":[0.045319147,0.0012867048,0.0016630912,0.0024717248,0.0033117128,0.016197408,0.0045888275,0.0061288457,0.00066707894],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015852092,0.00056471885,0.007568233,0.0008807058,0.00019266694,0.00041118215,0.0014617739,0.43509486,0.023360467,0.41159043,0.011687318,0.10560236],"study_design_scores_gemma":[0.000039274775,0.00008705042,0.0006790821,0.000022096001,0.000046906876,0.00011041144,0.00008859996,0.8484834,0.0030879972,0.14508142,0.0022519047,0.000021876012],"about_ca_topic_score_codex":0.0025036607,"about_ca_topic_score_gemma":0.0015463406,"teacher_disagreement_score":0.005349948,"about_ca_system_score_codex":0.0044779484,"about_ca_system_score_gemma":0.0022790115,"threshold_uncertainty_score":0.032489955},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Power (physics); Physics; Thermodynamics","score_opus":0.3512875317024356,"score_gpt":0.4853916397535502,"score_spread":0.1341041080511146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411141791","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026570925,0.00043647786,0.95760036,0.001382251,0.00007257985,0.00024057632,0.00025032254,0.0100359805,0.003410481],"genre_scores_gemma":[0.23455168,0.0003020953,0.7591935,0.0007360288,0.00012444258,0.00033326994,0.00061633927,0.0008630748,0.0032796308],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98931575,0.0034018399,0.0008179074,0.002321109,0.0030241096,0.0011192975],"domain_scores_gemma":[0.9381166,0.03765275,0.0031706544,0.016504332,0.0036855254,0.00087008387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0076191407,0.0018040496,0.0021235207,0.0019464114,0.0015433759,0.0040607317,0.0049127336,0.002449607,0.005085383],"category_scores_gemma":[0.034828827,0.0014146798,0.003339996,0.0022316107,0.0038487858,0.012280659,0.004895981,0.005551391,0.0024395601],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011749472,0.0005070941,0.0064784354,0.00089874497,0.0002158488,0.0002841472,0.000770773,0.13623938,0.020528832,0.1559456,0.017653495,0.65930265],"study_design_scores_gemma":[0.00009375368,0.00015197885,0.00038278304,0.00010595313,0.00007005306,0.0002331257,0.00011957294,0.82470614,0.011158048,0.15550104,0.0074143703,0.00006310589],"about_ca_topic_score_codex":0.007882884,"about_ca_topic_score_gemma":0.01059101,"teacher_disagreement_score":0.007882884,"about_ca_system_score_codex":0.004026576,"about_ca_system_score_gemma":0.0066928673,"threshold_uncertainty_score":0.04029435},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.051498392685557864,"score_gpt":0.28534842485965994,"score_spread":0.23385003217410208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411403262","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40520212,0.0164054,0.5485639,0.0054100296,0.0012553709,0.00020463242,0.00021205071,0.010377885,0.012368538],"genre_scores_gemma":[0.92426133,0.0018115778,0.06920459,0.00090700295,0.00021600009,0.00004700834,0.000113173744,0.0004905087,0.0029489002],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99771667,0.0003672025,0.00014650608,0.00030715187,0.0011248313,0.00033763936],"domain_scores_gemma":[0.99441445,0.0017597744,0.00072672294,0.001672153,0.00089389,0.0005330122],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031605733,0.0004478312,0.0004877634,0.00033998193,0.00072141184,0.0027826724,0.0022609313,0.00073440664,0.0011591199],"category_scores_gemma":[0.009897531,0.00044273853,0.00026720905,0.0005724852,0.0008800514,0.0033432757,0.0010741118,0.0018243723,0.0006112628],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034512808,0.000825295,0.046577234,0.00086082844,0.00024258802,0.00089840346,0.0024568916,0.026641041,0.12288985,0.0583507,0.0246965,0.7121093],"study_design_scores_gemma":[0.00063767063,0.0024885137,0.019849613,0.00049054663,0.0005121358,0.0032477607,0.0022347316,0.4783119,0.25097984,0.07648045,0.16443327,0.00033358287],"about_ca_topic_score_codex":0.002805056,"about_ca_topic_score_gemma":0.004081802,"teacher_disagreement_score":0.0031605733,"about_ca_system_score_codex":0.00076318864,"about_ca_system_score_gemma":0.0015819812,"threshold_uncertainty_score":0.01671487},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Backtracking; Computer science; Benchmark (surveying); Redundancy (engineering); Graph; Computation; Theoretical computer science; Algorithm","score_opus":0.05965004820938316,"score_gpt":0.2988278835663659,"score_spread":0.23917783535698275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411403412","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02847587,0.00052159274,0.9637913,0.0004461709,0.000047734422,0.00033511565,0.00033085738,0.0036543172,0.0023971095],"genre_scores_gemma":[0.15925963,0.00024112882,0.8357441,0.00024805786,0.000055133674,0.00027044502,0.0015203968,0.00050613115,0.0021550008],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971667,0.0007294914,0.00016255838,0.0006636289,0.0009005046,0.00037716277],"domain_scores_gemma":[0.99399537,0.002968369,0.0005198902,0.0016609917,0.00061481143,0.00024052127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002120654,0.0015707241,0.0019573597,0.0035475094,0.0013790808,0.0016705755,0.004199226,0.0021680787,0.0032560101],"category_scores_gemma":[0.010186351,0.0010042053,0.0021187004,0.0040586977,0.0016645081,0.0039102854,0.0033354373,0.001960062,0.0012997808],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00096120464,0.0008866323,0.004590924,0.0008047934,0.00036287008,0.00076384534,0.0010293091,0.4489129,0.03341317,0.049242273,0.017605608,0.4414265],"study_design_scores_gemma":[0.00011269762,0.00014650862,0.00049024145,0.000047448128,0.00008621269,0.0002889663,0.00014965933,0.95206064,0.006815512,0.036477033,0.0032935247,0.000031516094],"about_ca_topic_score_codex":0.0075197527,"about_ca_topic_score_gemma":0.0145814195,"teacher_disagreement_score":0.0075197527,"about_ca_system_score_codex":0.0015901959,"about_ca_system_score_gemma":0.0038750798,"threshold_uncertainty_score":0.014951944},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.075174269373825,"score_gpt":0.31380968248579755,"score_spread":0.23863541311197256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411403532","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.113485746,0.0007033829,0.8818488,0.0010153545,0.000042909556,0.000097381344,0.00079033064,0.0007338881,0.0012821532],"genre_scores_gemma":[0.77530164,0.00041688088,0.22147135,0.00032807313,0.0001247116,0.00021360833,0.0014645421,0.00017792871,0.0005011652],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98686683,0.004698911,0.0011960252,0.0029662861,0.003534422,0.00073755276],"domain_scores_gemma":[0.89761204,0.07356503,0.009071289,0.013562599,0.0049208063,0.0012683733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011246082,0.0010894664,0.0017272226,0.0038101368,0.00097247673,0.0034985112,0.002840875,0.0017807091,0.0012357645],"category_scores_gemma":[0.10538367,0.00080853887,0.0014076995,0.0045649437,0.0028367755,0.009065102,0.0046078158,0.003442042,0.00021978022],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006920431,0.00022522354,0.03729807,0.00046787143,0.0004514067,0.000451241,0.0007690486,0.6322364,0.005047184,0.17481554,0.0035716956,0.14397427],"study_design_scores_gemma":[0.000031287767,0.00010579601,0.0026425645,0.000038700215,0.000041092415,0.00023441402,0.00015929765,0.7395459,0.0026531653,0.25358075,0.0009357052,0.00003127989],"about_ca_topic_score_codex":0.0018808712,"about_ca_topic_score_gemma":0.0013799828,"teacher_disagreement_score":0.011246082,"about_ca_system_score_codex":0.0029272411,"about_ca_system_score_gemma":0.0017764771,"threshold_uncertainty_score":0.05947572},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.08133916376663859,"score_gpt":0.34367313638834807,"score_spread":0.2623339726217095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411403538","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029914945,0.0032801158,0.93178856,0.00045527628,0.00037246733,0.00053064723,0.0028189775,0.021975297,0.008863769],"genre_scores_gemma":[0.14146195,0.00095157436,0.84173846,0.00032772947,0.00017274264,0.00036596268,0.008109569,0.00082150544,0.00605058],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980995,0.00037277417,0.000170405,0.00032241445,0.0009103546,0.00012463765],"domain_scores_gemma":[0.9975682,0.0006891334,0.00015969409,0.0009910166,0.0004862581,0.00010565829],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009713725,0.0011776345,0.0019586522,0.0033838057,0.0010748273,0.0018421841,0.0029517862,0.0013805743,0.0055590514],"category_scores_gemma":[0.0072082966,0.0005282782,0.0010691498,0.0049633165,0.000690302,0.004272624,0.003054677,0.0013124126,0.0034087286],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007046199,0.00051447685,0.0028210706,0.00054192584,0.00021307722,0.00019486663,0.00027124694,0.08542538,0.01225173,0.025907075,0.056263402,0.8148911],"study_design_scores_gemma":[0.00009499804,0.00026475612,0.0005505135,0.00003105924,0.000044863416,0.00028000915,0.00010591492,0.9449919,0.0069768326,0.02442574,0.022177054,0.00005634715],"about_ca_topic_score_codex":0.011624373,"about_ca_topic_score_gemma":0.024882462,"teacher_disagreement_score":0.011624373,"about_ca_system_score_codex":0.0011662246,"about_ca_system_score_gemma":0.0019046011,"threshold_uncertainty_score":0.02311343},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.028643687810065883,"score_gpt":0.3161488555937306,"score_spread":0.28750516778366475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414427902","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45228127,0.0070202127,0.48932168,0.0024427436,0.0009083007,0.00044166003,0.0028078696,0.013937554,0.030838685],"genre_scores_gemma":[0.79652655,0.0017975618,0.19302718,0.0006968562,0.00008587243,0.00023229622,0.0037485901,0.00089701265,0.0029881366],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865294,0.0003347236,0.00010005021,0.00032916796,0.00036752413,0.00021562673],"domain_scores_gemma":[0.99500895,0.0026618678,0.00020336288,0.0010402646,0.0008963341,0.00018928103],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022635348,0.001547973,0.0009944419,0.0013298,0.00079212955,0.001511725,0.0018737465,0.0016956822,0.0033911867],"category_scores_gemma":[0.013572955,0.00033197703,0.00081921206,0.0012606027,0.0010759989,0.0037612338,0.0013392575,0.0015108738,0.0010774477],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008076993,0.00042196282,0.0047416165,0.001107908,0.0002222813,0.00017531673,0.00015894229,0.729959,0.00834077,0.02648868,0.014267781,0.21330804],"study_design_scores_gemma":[0.00006093071,0.00025602683,0.0007742235,0.000084399384,0.00005349481,0.00014101669,0.00014219698,0.96453166,0.010765629,0.018727886,0.0044343364,0.00002818169],"about_ca_topic_score_codex":0.009189421,"about_ca_topic_score_gemma":0.011574575,"teacher_disagreement_score":0.009189421,"about_ca_system_score_codex":0.0018499865,"about_ca_system_score_gemma":0.0018397497,"threshold_uncertainty_score":0.018271863},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.13736906533177068,"score_gpt":0.41139771770102107,"score_spread":0.2740286523692504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417070120","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005129872,0.00013125273,0.93378687,0.00047949055,0.00008264359,0.00052328134,0.0016995209,0.055211026,0.0029559266],"genre_scores_gemma":[0.09696149,0.00014422945,0.8896387,0.000618017,0.00007187905,0.0007174174,0.005927822,0.002885153,0.003035236],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9913845,0.003823354,0.0005900752,0.0014294168,0.0023502158,0.0004224913],"domain_scores_gemma":[0.9803193,0.011658198,0.0006564366,0.0042458647,0.002703304,0.00041698443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007122713,0.0017083603,0.0012093979,0.002025845,0.0009965374,0.003233228,0.0049992334,0.0025711847,0.018189942],"category_scores_gemma":[0.036045633,0.0011824083,0.0025987593,0.0012706327,0.0022425468,0.008227798,0.0070294533,0.0032784736,0.010599013],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013155829,0.0005915498,0.004868027,0.0022853522,0.00020060148,0.0010362555,0.005028586,0.04882607,0.049198322,0.14773639,0.11733877,0.6215744],"study_design_scores_gemma":[0.00014345092,0.00021854679,0.00065769977,0.0001336518,0.00005046182,0.0004660384,0.00048506976,0.8496262,0.031208577,0.06915355,0.047736388,0.00012046911],"about_ca_topic_score_codex":0.005198085,"about_ca_topic_score_gemma":0.006700838,"teacher_disagreement_score":0.018189942,"about_ca_system_score_codex":0.001343792,"about_ca_system_score_gemma":0.0043568206,"threshold_uncertainty_score":0.060851395},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Transformation (genetics); Computation; Visualization; Data visualization; Multivariate statistics; Data transformation; Time series; Data manipulation language","score_opus":0.0252930631897247,"score_gpt":0.31984117046811056,"score_spread":0.2945481072783859,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7109087591","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009393284,0.00015609556,0.974853,0.00013762462,0.000057819125,0.00005072405,0.00041506835,0.013909077,0.0010272542],"genre_scores_gemma":[0.35501885,0.0005482093,0.6348733,0.00017345884,0.00013675021,0.00026516293,0.0026327423,0.002976996,0.0033745284],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991565,0.0001513692,0.000062223415,0.0002177626,0.00035488492,0.000057242974],"domain_scores_gemma":[0.9974407,0.0008889734,0.0001673503,0.0008273431,0.0005402891,0.0001353641],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000878109,0.0010304188,0.0008060341,0.0010862869,0.00036985415,0.0017515495,0.0016231633,0.0005662288,0.0050417744],"category_scores_gemma":[0.0071399966,0.00044752532,0.0008872088,0.001396234,0.0006402779,0.0021650232,0.0025866688,0.0014132519,0.0019708804],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001026503,0.00023216821,0.0047635348,0.0006184254,0.00020356051,0.0005756604,0.0011570224,0.2009265,0.17155106,0.05201286,0.037199352,0.5297334],"study_design_scores_gemma":[0.00006871174,0.00009562179,0.0008909188,0.000017201643,0.000025356008,0.00022337126,0.00011747746,0.89861107,0.054661922,0.029174974,0.016064888,0.000048495007],"about_ca_topic_score_codex":0.0022278386,"about_ca_topic_score_gemma":0.0025568025,"teacher_disagreement_score":0.0050417744,"about_ca_system_score_codex":0.00038633126,"about_ca_system_score_gemma":0.0008041564,"threshold_uncertainty_score":0.016866446},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.04016599984991381,"score_gpt":0.2851652727165403,"score_spread":0.24499927286662648,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7109234313","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15901548,0.0029681362,0.6372416,0.0008712966,0.0010364422,0.0013617548,0.0048879576,0.1549608,0.037656486],"genre_scores_gemma":[0.55822974,0.0017159504,0.39401466,0.0018437959,0.00029138455,0.000789406,0.013376077,0.0021225605,0.027616378],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994066,0.00006310135,0.00007282425,0.00016331478,0.00020781737,0.00008643699],"domain_scores_gemma":[0.99925345,0.00012658782,0.00004956985,0.00022217468,0.0002260452,0.000122119],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076643267,0.00077401305,0.00072972686,0.0006554783,0.00043531114,0.0013254497,0.0022992678,0.00045972795,0.005636983],"category_scores_gemma":[0.002095441,0.00047219006,0.00035451917,0.0007648136,0.00031964213,0.0020742153,0.0019439962,0.0012730701,0.0020235423],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0059674974,0.0013586523,0.013496904,0.0007785579,0.00039809884,0.0012566103,0.00057847524,0.040858362,0.16677803,0.019065615,0.17896205,0.57050115],"study_design_scores_gemma":[0.0012017295,0.001188355,0.0076957024,0.000101035446,0.00030008276,0.0010137429,0.0001854237,0.75293,0.079643734,0.010506722,0.14499003,0.00024348372],"about_ca_topic_score_codex":0.002021376,"about_ca_topic_score_gemma":0.0023582892,"teacher_disagreement_score":0.005636983,"about_ca_system_score_codex":0.0007095376,"about_ca_system_score_gemma":0.0014190922,"threshold_uncertainty_score":0.018857598},"labels":[],"label_agreement":null}]}