{"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29110137,0.00015809065,0.64753085,0.029620724,0.0022028203,0.00500111,0.008321313,0.002611316,0.013452396],"genre_scores_gemma":[0.8320891,0.00010546978,0.1619623,0.00021305731,0.00016063642,0.00008336881,0.0024087094,0.000038891798,0.0029384342],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99891835,0.000006029392,0.00021354793,0.00032264477,0.000388967,0.00015048056],"domain_scores_gemma":[0.99851954,0.000030498524,0.00023675081,0.0011123825,0.000079215475,0.000021626583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004808872,0.00009272507,0.00011754638,0.0000708477,0.00010263441,0.000026186142,0.0029498953,0.000021597287,0.000004363941],"category_scores_gemma":[0.00013197897,0.00006994965,0.000030792064,0.000824485,0.000039551942,0.0007406122,0.0028742908,0.000054809767,0.000034096724],"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":[0.00009440284,0.0002245666,0.002641084,0.0014006828,0.00017121891,0.0000016573797,0.00009632921,0.00041907126,0.012049106,0.5911238,0.36895984,0.022818193],"study_design_scores_gemma":[0.0025259154,0.0007186517,0.05291063,0.0030073775,0.00021886044,0.000007184514,0.00067663955,0.34964225,0.13707891,0.023298336,0.42881688,0.0010983705],"about_ca_topic_score_codex":0.000009335869,"about_ca_topic_score_gemma":4.3188996e-7,"teacher_disagreement_score":0.5678255,"about_ca_system_score_codex":0.00002557509,"about_ca_system_score_gemma":0.000009967477,"threshold_uncertainty_score":0.54816884},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7661267,0.0003603731,0.16002725,0.018746145,0.0028267002,0.0047942926,0.00025562508,0.0015732412,0.045289684],"genre_scores_gemma":[0.78261447,0.00014400185,0.21592225,0.000048457892,0.0000466331,0.000024721812,0.000015124445,0.000017891154,0.001166429],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908775,0.000001710891,0.00018634062,0.00033129402,0.00022730924,0.0001656158],"domain_scores_gemma":[0.9984491,0.00005987484,0.00014042298,0.0012492561,0.000078714176,0.000022670085],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0006048317,0.00008515253,0.00011137197,0.00015049914,0.00007119818,0.000039613526,0.007544034,0.000022446695,9.863819e-7],"category_scores_gemma":[0.00013507725,0.00006854083,0.000046092275,0.00055002986,0.000027381182,0.00070961745,0.0073544676,0.000052441756,0.0000050324325],"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":[0.00001378525,0.000042268548,0.0002860567,0.00057991734,0.00007305313,2.866145e-7,0.00031528136,0.00007311962,0.00041396276,0.95965147,0.00936765,0.02918312],"study_design_scores_gemma":[0.0016841396,0.00024132157,0.003984808,0.0015220743,0.00015285943,0.0000017551221,0.0017827571,0.55176294,0.0077944063,0.41048288,0.020128297,0.00046179292],"about_ca_topic_score_codex":0.0000058560768,"about_ca_topic_score_gemma":8.384681e-7,"teacher_disagreement_score":0.5516898,"about_ca_system_score_codex":0.000018385916,"about_ca_system_score_gemma":0.000009081826,"threshold_uncertainty_score":0.9978256},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.114097245,0.00004845676,0.541401,0.32972667,0.00041503232,0.00521391,0.00048569002,0.0014848848,0.007127084],"genre_scores_gemma":[0.26797473,0.000041118048,0.7308471,0.00020417919,0.000014296097,0.00011825083,0.000028661465,0.000011108771,0.0007605671],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987285,0.000006401373,0.00022144435,0.00056755333,0.00026954795,0.00020656666],"domain_scores_gemma":[0.997321,0.000032783733,0.00022825228,0.00227862,0.000103997096,0.00003535956],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0008395089,0.00012558291,0.00016342821,0.0002295387,0.000113558206,0.00007026913,0.0107757775,0.000057750705,0.0000015259162],"category_scores_gemma":[0.0001950811,0.00009951457,0.000039193714,0.0015026627,0.000054526277,0.00022337791,0.01348735,0.00012480385,0.000008796987],"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":[0.00003692567,0.001014844,0.0005035849,0.0007212822,0.00033132793,5.92867e-7,0.0008652809,0.00018570364,0.0018439422,0.4919499,0.14795716,0.35458946],"study_design_scores_gemma":[0.0030301602,0.0003681606,0.01438004,0.00044477792,0.00019518948,0.0000070894625,0.005331575,0.8377447,0.022754772,0.057828337,0.056870665,0.0010445412],"about_ca_topic_score_codex":0.000004393155,"about_ca_topic_score_gemma":4.9420754e-7,"teacher_disagreement_score":0.837559,"about_ca_system_score_codex":0.000017689115,"about_ca_system_score_gemma":0.000005653841,"threshold_uncertainty_score":0.9945764},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7976819,0.0001763762,0.17616053,0.009680131,0.0008348535,0.008864141,0.0015634524,0.0007117024,0.004326908],"genre_scores_gemma":[0.5778777,0.000061958825,0.4192698,0.000038165286,0.000049373455,0.00007896256,0.0004347041,0.000033292374,0.0021560458],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988141,0.000009606769,0.0003493549,0.00037871188,0.00031664898,0.00013155326],"domain_scores_gemma":[0.9979216,0.000051963805,0.00073583226,0.0009169249,0.00035417714,0.00001950993],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043752862,0.00010195432,0.0001962606,0.00014646741,0.000076934826,0.00006554772,0.003269394,0.00002327672,0.000006431816],"category_scores_gemma":[0.00044627397,0.000078751524,0.00005574996,0.000848534,0.00005746737,0.0017203345,0.003509484,0.000030987117,0.0000023495168],"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":[0.0019708064,0.0027768086,0.011224396,0.006752474,0.004375996,0.0000049704813,0.0159474,0.002052113,0.08315227,0.17757462,0.04776203,0.6464061],"study_design_scores_gemma":[0.0016324602,0.0009790356,0.023400873,0.0011654947,0.00042147867,0.0000021517947,0.006547365,0.84372175,0.10998636,0.010779471,0.00094939687,0.00041418825],"about_ca_topic_score_codex":0.00000990204,"about_ca_topic_score_gemma":0.0000015129333,"teacher_disagreement_score":0.8416696,"about_ca_system_score_codex":0.0000111953605,"about_ca_system_score_gemma":0.0000074895,"threshold_uncertainty_score":0.60754013},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.968526,0.0000044273506,0.00028015225,0.0021138962,0.00007272654,0.00029676556,0.00045686064,0.000027417136,0.028221762],"genre_scores_gemma":[0.99493176,0.000018338917,0.0041052564,0.00006333552,0.000033103686,0.000008468663,0.00007331492,0.000010583367,0.0007558696],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992564,0.0000028402103,0.00017801244,0.00020115986,0.00023331845,0.00012827819],"domain_scores_gemma":[0.9992232,0.000029731125,0.00018209148,0.0004850326,0.00006112591,0.00001885453],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001831086,0.000085242405,0.00011946183,0.000037899114,0.00009002283,0.000028021077,0.0017666447,0.000014606022,0.000016461987],"category_scores_gemma":[0.000013796304,0.000065491775,0.00004844461,0.00021903927,0.000063494204,0.00018338676,0.0035655692,0.000070247515,0.0000069232956],"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":[0.0000129120435,0.00011388121,0.011980298,0.00021615662,0.00016038063,7.144016e-8,0.00029192536,0.0008550979,0.0018950726,0.97457266,0.0061158175,0.0037857483],"study_design_scores_gemma":[0.0012614065,0.00008106435,0.04293729,0.001957451,0.00017253934,7.594236e-8,0.018077698,0.35625654,0.0028912257,0.57454187,0.0013423698,0.00048049985],"about_ca_topic_score_codex":0.000021243755,"about_ca_topic_score_gemma":2.8080956e-7,"teacher_disagreement_score":0.4000308,"about_ca_system_score_codex":0.0000070201013,"about_ca_system_score_gemma":0.000005728708,"threshold_uncertainty_score":0.4444227},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8170424,0.00028271877,0.15359813,0.009715632,0.0014454952,0.0026256014,0.0008552854,0.00042102445,0.014013714],"genre_scores_gemma":[0.9632377,0.000067352106,0.036224116,0.000067405985,0.000023529887,0.0000075829103,0.000014602921,0.0000092419805,0.00034849427],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9986205,0.000011842521,0.00033499688,0.00034900496,0.00050535094,0.00017829138],"domain_scores_gemma":[0.99720997,0.00016732793,0.00049816625,0.0019691703,0.00013751042,0.000017873612],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0007263005,0.00012036401,0.00021077196,0.00007749945,0.0001244191,0.000025857667,0.0067646047,0.000016568905,0.0000012778771],"category_scores_gemma":[0.00030102243,0.00006775485,0.00004390653,0.00083559955,0.00022754422,0.00041321243,0.014176695,0.000082218176,0.0000041430135],"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":[0.00003953294,0.00009681017,0.0028415099,0.0010759758,0.00016228063,8.5196797e-7,0.0011513807,0.00013256169,0.0037179892,0.9608345,0.007160863,0.022785755],"study_design_scores_gemma":[0.004106314,0.0015283847,0.44102597,0.011238818,0.0004981742,0.000015561141,0.036628563,0.12574555,0.23320392,0.07698001,0.06712793,0.0019007892],"about_ca_topic_score_codex":0.000023775056,"about_ca_topic_score_gemma":0.0000011840995,"teacher_disagreement_score":0.88385445,"about_ca_system_score_codex":0.000008907376,"about_ca_system_score_gemma":0.000010132642,"threshold_uncertainty_score":0.99860924},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9802012,0.00021871254,0.015084264,0.0012005747,0.0007021718,0.0017021617,0.00008309697,0.00019445793,0.00061336823],"genre_scores_gemma":[0.8480173,0.0002343549,0.15145014,0.00004335195,0.000039878538,0.00004132933,0.000084568164,0.000015942893,0.000073158786],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988128,0.00000867979,0.00034368562,0.00036901564,0.0002909776,0.00017482531],"domain_scores_gemma":[0.9981825,0.00008908675,0.00040375642,0.0011398421,0.0001620451,0.00002277489],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032860145,0.00012667074,0.00019256076,0.00018141419,0.000066679546,0.000028753946,0.0039457786,0.000032917265,0.0000014354029],"category_scores_gemma":[0.000075654134,0.000103152604,0.000066367924,0.0008809985,0.00005939749,0.0007582035,0.0036210844,0.00006639669,8.554737e-7],"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":[0.00005910853,0.00029306536,0.0021847463,0.0043589296,0.000354902,9.069694e-7,0.00040499406,0.003033863,0.048578568,0.75344527,0.07105367,0.116231985],"study_design_scores_gemma":[0.0008526017,0.00030815383,0.027237905,0.0011036649,0.000110579385,0.0000010838669,0.00018012988,0.8777387,0.020101933,0.07105391,0.0010479707,0.00026338248],"about_ca_topic_score_codex":0.0000022204908,"about_ca_topic_score_gemma":7.9478787e-7,"teacher_disagreement_score":0.87470484,"about_ca_system_score_codex":0.00001340415,"about_ca_system_score_gemma":0.000005209152,"threshold_uncertainty_score":0.7332304},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0816658,0.00085521914,0.8265824,0.03008797,0.0041977954,0.010613231,0.0021264395,0.0018902493,0.04198095],"genre_scores_gemma":[0.5243008,0.00012243274,0.47273642,0.00016579397,0.00010969408,0.00013821851,0.00008767308,0.000040886243,0.002298032],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99833304,0.0000054546476,0.00039081846,0.0005136287,0.00048233525,0.00027472884],"domain_scores_gemma":[0.99742824,0.000090761154,0.00039221643,0.0018971567,0.00015350398,0.000038145416],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0009883579,0.00015311695,0.0002703883,0.00011227769,0.00011361369,0.00012448031,0.010728033,0.0000401712,0.0000023797447],"category_scores_gemma":[0.00029134986,0.00011564949,0.00007904076,0.0007856054,0.000051639996,0.0006002194,0.0066412683,0.00007752754,0.0000061682176],"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":[0.000352623,0.0006211754,0.0009703023,0.008269079,0.0011512956,0.000009215238,0.0008133448,0.09670835,0.001968636,0.25616768,0.554125,0.0788433],"study_design_scores_gemma":[0.00452925,0.00030122566,0.0035355294,0.0033275126,0.00026617065,0.0000048960746,0.0013825806,0.9422029,0.005854471,0.017294,0.020493472,0.00080796273],"about_ca_topic_score_codex":0.000004858656,"about_ca_topic_score_gemma":1.1440891e-7,"teacher_disagreement_score":0.84549457,"about_ca_system_score_codex":0.000018789748,"about_ca_system_score_gemma":0.000010909913,"threshold_uncertainty_score":0.9946244},"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":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6555503,0.0004891714,0.15078434,0.17173554,0.0008676772,0.0071404274,0.0006560421,0.006356523,0.006419953],"genre_scores_gemma":[0.42196196,0.00014717627,0.5774327,0.0000678195,0.000016145274,0.00004822223,0.00002920575,0.00002957147,0.00026717657],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997299,0.000009562658,0.00043825054,0.0009658078,0.0008835239,0.00040382537],"domain_scores_gemma":[0.9851438,0.000044293374,0.00071633887,0.013909702,0.00015042137,0.000035461137],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0008214986,0.00024477232,0.00031433313,0.0002550271,0.00013899143,0.00018473457,0.11213258,0.00005989052,0.0000015096732],"category_scores_gemma":[0.0038058737,0.00016055875,0.000050232757,0.0019754653,0.00020384096,0.0017158499,0.28953612,0.00022601154,0.000009425328],"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":[0.00033242942,0.0018179704,0.045338016,0.013888766,0.0019443985,0.000038779563,0.00040302885,0.00007117314,0.031807806,0.08149703,0.42675054,0.3961101],"study_design_scores_gemma":[0.00409801,0.0007230832,0.116026625,0.0088740755,0.00066224457,0.000013554725,0.000806903,0.4390196,0.10750087,0.31246385,0.0079923365,0.0018188406],"about_ca_topic_score_codex":0.000008429066,"about_ca_topic_score_gemma":0.0000018814527,"teacher_disagreement_score":0.43894842,"about_ca_system_score_codex":0.00003448275,"about_ca_system_score_gemma":0.000025476553,"threshold_uncertainty_score":0.8926712},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80844235,0.00012436802,0.07918793,0.0138191385,0.0014464142,0.0078059398,0.087325685,0.0012436206,0.0006045459],"genre_scores_gemma":[0.68366504,0.00038033826,0.29988134,0.00040597087,0.000299171,0.000107219115,0.015164852,0.00006116505,0.00003489106],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977684,0.000012584644,0.00036633902,0.0009848602,0.000558951,0.00030888626],"domain_scores_gemma":[0.9918916,0.000095312826,0.00041021785,0.0074413815,0.00010643881,0.00005504358],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0016963949,0.00017494627,0.00021099103,0.00020977236,0.00019363195,0.00026949294,0.0461933,0.000038530663,0.0000033996005],"category_scores_gemma":[0.0004945143,0.00013523984,0.0000424672,0.0011644745,0.000055118326,0.0046496075,0.060654964,0.00016856643,0.0000019844165],"study_design_candidate":"design_other","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":[0.0002750595,0.0023888533,0.020939628,0.009096486,0.0008014905,0.000007095789,0.00083890493,0.000031195956,0.0014372506,0.119339265,0.28152898,0.5633158],"study_design_scores_gemma":[0.007925739,0.0028477784,0.22326912,0.0062429444,0.0012041996,0.000022034623,0.00782067,0.3587001,0.012557223,0.21137495,0.16476963,0.003265605],"about_ca_topic_score_codex":0.000048398088,"about_ca_topic_score_gemma":0.000023725377,"teacher_disagreement_score":0.5600502,"about_ca_system_score_codex":0.000009135771,"about_ca_system_score_gemma":0.0000132792975,"threshold_uncertainty_score":0.95896727},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9491505,0.00008183823,0.014559392,0.02004129,0.0011866183,0.00088202005,0.00014654898,0.0007019256,0.013249838],"genre_scores_gemma":[0.9893051,0.00004676115,0.009501261,0.00013280826,0.00002619646,0.000008042406,0.000030910916,0.000008350814,0.00094056554],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885863,0.000005031012,0.000221812,0.00032297536,0.0004296726,0.00016185179],"domain_scores_gemma":[0.9983845,0.000044286004,0.00019825612,0.0012666782,0.00008103316,0.000025270212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047245756,0.00008928548,0.00011289217,0.00008092167,0.00015041529,0.00011887671,0.005241433,0.000022080309,0.000005630865],"category_scores_gemma":[0.00011858956,0.000071629634,0.00005057053,0.0006103649,0.000045965924,0.0007350845,0.00652234,0.00009591504,0.00004899685],"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":[0.00011449742,0.00047170656,0.040321507,0.0013123853,0.0006849296,0.000012724432,0.0014353752,0.00886314,0.002605308,0.30147642,0.5747765,0.06792554],"study_design_scores_gemma":[0.000930194,0.00019766204,0.053365033,0.0011125617,0.00013459599,0.0000042936904,0.0010430262,0.92438555,0.0011905824,0.008671056,0.008586211,0.00037921392],"about_ca_topic_score_codex":0.00001536262,"about_ca_topic_score_gemma":5.455581e-7,"teacher_disagreement_score":0.91552246,"about_ca_system_score_codex":0.000012852719,"about_ca_system_score_gemma":0.000009442304,"threshold_uncertainty_score":0.9739974},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1463844,0.00089619774,0.74379265,0.047967296,0.0035240715,0.0070073786,0.003734073,0.001991202,0.044702746],"genre_scores_gemma":[0.04544917,0.0008376757,0.95240813,0.00017955685,0.00004733835,0.000032631484,0.00027499112,0.000022183487,0.0007483467],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871176,0.000008441777,0.00031115994,0.00040746943,0.0003983291,0.00016280933],"domain_scores_gemma":[0.99740183,0.000056160305,0.00025675548,0.0022080778,0.000057493122,0.000019697329],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00080965826,0.00010122134,0.00015495093,0.00016646617,0.00005021185,0.00002262217,0.0048261825,0.000017202645,0.000003567712],"category_scores_gemma":[0.00035752653,0.000075767144,0.00002277804,0.0010446664,0.00004928618,0.0018307419,0.0116351135,0.000077370954,0.000007187504],"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":[0.000044059467,0.00014778425,0.003261318,0.0016048243,0.000076297765,0.000006270806,0.00034811813,0.004942733,0.0007137644,0.91740906,0.05841587,0.013029911],"study_design_scores_gemma":[0.004786169,0.00050801795,0.04471492,0.012965981,0.00020817906,0.000015068638,0.007825891,0.6116262,0.03376877,0.047313053,0.23413967,0.002128056],"about_ca_topic_score_codex":0.000032219465,"about_ca_topic_score_gemma":0.0000030888746,"teacher_disagreement_score":0.87009597,"about_ca_system_score_codex":0.000015994472,"about_ca_system_score_gemma":0.000009730887,"threshold_uncertainty_score":0.9963586},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17695172,0.00039685136,0.8154009,0.0039434545,0.0002164728,0.0012159204,0.0003027914,0.00018636283,0.0013855168],"genre_scores_gemma":[0.85712165,0.000035763405,0.14240012,0.00012228136,0.000031084044,0.00002959426,0.000035539822,0.00001719983,0.00020674658],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99834096,0.0000067804317,0.00029842954,0.0006866871,0.00040564375,0.0002615245],"domain_scores_gemma":[0.99788827,0.000038360846,0.00008842078,0.0018862399,0.000059545346,0.000039190545],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0010204121,0.00014102834,0.00017709537,0.00007531972,0.00007403425,0.00013058756,0.0067772977,0.000033443936,0.000005912318],"category_scores_gemma":[0.00003270242,0.00010830729,0.000068957175,0.00023645088,0.000027394508,0.0018146628,0.0021419877,0.00010391595,0.000001051985],"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":[0.000067307126,0.00067770836,0.0004567385,0.008183014,0.0005037949,0.000002951273,0.010432036,0.0010838691,0.0191301,0.77195764,0.028036525,0.1594683],"study_design_scores_gemma":[0.00046193134,0.00009157027,0.000061547566,0.00037819,0.00008968128,8.198775e-7,0.0010280812,0.9256535,0.008482542,0.053903922,0.009634013,0.00021420109],"about_ca_topic_score_codex":0.000050404764,"about_ca_topic_score_gemma":0.0000022331742,"teacher_disagreement_score":0.9245696,"about_ca_system_score_codex":0.000030945303,"about_ca_system_score_gemma":0.00001259022,"threshold_uncertainty_score":0.9985965},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1890707,0.0024519623,0.75022244,0.018407017,0.0018637084,0.00551639,0.0077032596,0.0008036772,0.02396086],"genre_scores_gemma":[0.77149963,0.00027777755,0.22672741,0.0002197143,0.00007009653,0.000024224812,0.0007282816,0.000028723358,0.0004241282],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981644,0.000016466813,0.00038945256,0.00074133894,0.00050285965,0.00018544278],"domain_scores_gemma":[0.99728614,0.000096647906,0.00018757598,0.0023206056,0.00007974009,0.000029318126],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00085148425,0.00015906787,0.00022027746,0.00013963859,0.000060961094,0.00014187963,0.0073969606,0.000026951371,0.000005494342],"category_scores_gemma":[0.00024905885,0.000115987954,0.00002450493,0.00071764435,0.000067029374,0.003111049,0.01730037,0.00013102512,0.000014087694],"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":[0.000037102487,0.0001966733,0.00031719942,0.0018211325,0.0002182464,0.000015295436,0.0009310828,0.0009278851,0.0024532324,0.8545437,0.07050718,0.06803128],"study_design_scores_gemma":[0.0012882733,0.00039946922,0.004176729,0.005130658,0.00015829809,0.000018745413,0.0056176945,0.7638069,0.013817912,0.032252166,0.17245571,0.00087744306],"about_ca_topic_score_codex":0.0000725443,"about_ca_topic_score_gemma":0.000012371503,"teacher_disagreement_score":0.8222915,"about_ca_system_score_codex":0.000027173657,"about_ca_system_score_gemma":0.000026589147,"threshold_uncertainty_score":0.9979735},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.091715015,0.003027401,0.25083345,0.25230747,0.021189945,0.0050529274,0.0003828909,0.0019303255,0.37356058],"genre_scores_gemma":[0.9820414,0.00009557476,0.014756537,0.00019825056,0.00012984287,0.000011325105,0.000004184352,0.000009149996,0.0027537053],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99898756,0.0000057637976,0.0002443455,0.0003588547,0.00026544125,0.00013801253],"domain_scores_gemma":[0.9984293,0.000032610304,0.00010838901,0.0013575092,0.000052903302,0.000019279507],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00047920755,0.00008960267,0.0001308068,0.00007979763,0.000049119062,0.00010498369,0.007001912,0.000030617823,0.00001259059],"category_scores_gemma":[0.000024298202,0.000059134472,0.000056496294,0.00033059737,0.000039345854,0.0005341093,0.0057452363,0.000093094146,0.000018689021],"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":[0.0000078899175,0.00004551466,0.00016760173,0.0006059698,0.00015199198,0.0000018639988,0.00014734306,0.000024728624,0.000099780365,0.6998387,0.28604934,0.0128592905],"study_design_scores_gemma":[0.0009627086,0.0006279115,0.0037733929,0.0046958015,0.00022464052,0.00004544316,0.0019694986,0.30975923,0.0029308605,0.19842307,0.4758537,0.000733732],"about_ca_topic_score_codex":0.000009351381,"about_ca_topic_score_gemma":7.655476e-7,"teacher_disagreement_score":0.89032644,"about_ca_system_score_codex":0.0000146000075,"about_ca_system_score_gemma":0.000006297796,"threshold_uncertainty_score":0.9983707},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030837072,0.0019126959,0.93028265,0.017651554,0.0014877705,0.003493401,0.00047128872,0.0008706589,0.012992895],"genre_scores_gemma":[0.88625747,0.00001919905,0.1128635,0.000030360932,0.00006922441,0.000026130036,0.000030038205,0.000010960504,0.0006930982],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998865,0.0000035721214,0.00027534112,0.0004196207,0.0002926524,0.00014379331],"domain_scores_gemma":[0.998528,0.00005096576,0.00019576633,0.0011037703,0.00010209809,0.000019421226],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0006397471,0.000100074045,0.0001250934,0.00007674519,0.000068971094,0.00021341228,0.006954094,0.000025968873,5.024006e-7],"category_scores_gemma":[0.00007286244,0.00007209273,0.0000510107,0.00044652983,0.000025876478,0.00062728394,0.003342333,0.000057887297,0.000004922032],"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":[0.000045908328,0.00026091427,0.00059775414,0.015483167,0.00028196373,8.581595e-7,0.00068070536,0.0004227698,0.0033597397,0.46848056,0.12615584,0.38422984],"study_design_scores_gemma":[0.0006698997,0.00017112005,0.0020279712,0.0052507175,0.0001521714,0.000006769897,0.00040708805,0.8515188,0.0044970354,0.030491078,0.10440222,0.00040513303],"about_ca_topic_score_codex":0.0000030276603,"about_ca_topic_score_gemma":9.1232636e-8,"teacher_disagreement_score":0.8554204,"about_ca_system_score_codex":0.000017241166,"about_ca_system_score_gemma":0.00001450509,"threshold_uncertainty_score":0.99841875},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97934157,0.00011268691,0.0026072762,0.0063318983,0.00030494604,0.0012653444,0.000051194882,0.00019110837,0.009793964],"genre_scores_gemma":[0.98228,0.000049236616,0.01724398,0.000050419418,0.000009016332,0.00002116717,0.0000049948694,0.000013042466,0.00032815104],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99771136,0.0000137529,0.0006148742,0.0006668103,0.0007168595,0.00027635114],"domain_scores_gemma":[0.9971404,0.00009676366,0.0004688462,0.0021974335,0.00006305445,0.00003348528],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0024990786,0.00013496938,0.0001933129,0.00032387962,0.000059695012,0.00011601281,0.008567345,0.000027892576,0.0000045368383],"category_scores_gemma":[0.00073450175,0.000096232005,0.00006231999,0.0011741532,0.00006573793,0.0013041284,0.008387004,0.00026019532,0.0000048555185],"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":[0.00006203659,0.0002575031,0.031742632,0.0023035074,0.0001055475,0.00003263798,0.00018493416,0.00003503736,0.0011962745,0.93479335,0.003966375,0.025320133],"study_design_scores_gemma":[0.00036489664,0.00022392854,0.019307509,0.002907885,0.00002180671,0.0000057906796,0.00028163797,0.008997332,0.011457527,0.9554198,0.00076799956,0.00024393297],"about_ca_topic_score_codex":0.00001706558,"about_ca_topic_score_gemma":0.000002242875,"teacher_disagreement_score":0.0250762,"about_ca_system_score_codex":0.00003236486,"about_ca_system_score_gemma":0.000013795697,"threshold_uncertainty_score":0.99963295},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12539749,0.0027281593,0.36197993,0.28887004,0.007924831,0.0073489132,0.000722348,0.0021727388,0.20285554],"genre_scores_gemma":[0.46415532,0.000085417574,0.5248211,0.00049519783,0.00022756109,0.00002937693,0.00001907054,0.00003437268,0.01013256],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990421,0.000002946939,0.00016826313,0.00036826116,0.00028369186,0.00013474621],"domain_scores_gemma":[0.99862707,0.000054736873,0.00009046533,0.001167165,0.00004163506,0.000018915936],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0005499376,0.00008838597,0.000105353036,0.000077623095,0.000043453623,0.00013396035,0.007413268,0.000017124108,0.0000051657694],"category_scores_gemma":[0.00010893865,0.00005797269,0.000052616146,0.0002938019,0.000026260894,0.00048454278,0.0059605157,0.00008609196,0.000009448492],"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":[0.00002242446,0.000121926845,0.0004725463,0.002934276,0.000276796,0.0000013233945,0.0003405233,0.000028310842,0.0005532343,0.4557271,0.16309194,0.37642962],"study_design_scores_gemma":[0.00088769454,0.00051250367,0.002607276,0.002309021,0.00021874692,0.0000066188336,0.00028996024,0.42493284,0.005908987,0.101273306,0.46060336,0.00044969434],"about_ca_topic_score_codex":0.0000030439833,"about_ca_topic_score_gemma":6.870899e-8,"teacher_disagreement_score":0.42490453,"about_ca_system_score_codex":0.000006932418,"about_ca_system_score_gemma":0.0000059529602,"threshold_uncertainty_score":0.9979571},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8798825,0.00048765907,0.006920021,0.056849383,0.00077631377,0.0048385835,0.0040478883,0.0008603422,0.045337316],"genre_scores_gemma":[0.90175194,0.000059469196,0.09794006,0.00008403928,0.000014176896,0.000009790282,0.000052856103,0.0000121864205,0.00007548251],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998148,0.000015125662,0.0004044271,0.0006956123,0.0005619386,0.00017487121],"domain_scores_gemma":[0.99226856,0.0002861073,0.00025861926,0.007124062,0.00004588525,0.00001676761],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0026253483,0.00013456533,0.00018265705,0.00012930334,0.000034567856,0.000101114936,0.029189052,0.000028575741,0.0000044289804],"category_scores_gemma":[0.0010451544,0.000080701226,0.000033182892,0.0007276417,0.00010200427,0.0011629277,0.034585305,0.00017168227,0.0000023763187],"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":[0.00004121412,0.00042803577,0.0044825403,0.001800587,0.000161407,0.000002710067,0.00029648165,0.000002984104,0.0010582003,0.64369214,0.1972662,0.15076752],"study_design_scores_gemma":[0.0010955479,0.0010577545,0.022663807,0.016848193,0.0003354879,0.000006552034,0.0019194242,0.13824502,0.08233307,0.72136205,0.013180444,0.0009526787],"about_ca_topic_score_codex":0.000032698375,"about_ca_topic_score_gemma":0.0000035386352,"teacher_disagreement_score":0.18408576,"about_ca_system_score_codex":0.000028246108,"about_ca_system_score_gemma":0.000016790356,"threshold_uncertainty_score":0.9760635},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027182763,0.0003063394,0.974722,0.015931413,0.0003309291,0.0008520631,0.0012750288,0.00023078268,0.0036331268],"genre_scores_gemma":[0.62564075,0.000080178856,0.37315205,0.000120386336,0.000050254985,0.000018359338,0.00037222716,0.000012951394,0.000552868],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99868435,0.0000042319725,0.00023161886,0.0006214407,0.00033404658,0.0001243129],"domain_scores_gemma":[0.99609834,0.00007027651,0.00018179264,0.0035595775,0.000070145616,0.000019870557],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0011490313,0.00009036245,0.00009823619,0.00007872344,0.00006875848,0.00019938836,0.014609128,0.000023551314,0.000001692036],"category_scores_gemma":[0.0002313609,0.00006692661,0.000024181172,0.00026336298,0.000034642075,0.0019137475,0.011780305,0.000085884545,0.000004472566],"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":[0.000021010768,0.000058156147,0.000045295405,0.0023185683,0.000060150633,2.0074788e-7,0.00007290684,0.000106074105,0.0043035196,0.7822855,0.04631901,0.1644096],"study_design_scores_gemma":[0.00010981779,0.000034672372,0.00022085689,0.00029293227,0.000056645742,9.412082e-7,0.00004675375,0.967835,0.0008870623,0.026107129,0.00433099,0.00007721037],"about_ca_topic_score_codex":0.000007010779,"about_ca_topic_score_gemma":3.367759e-7,"teacher_disagreement_score":0.9677289,"about_ca_system_score_codex":0.000012683863,"about_ca_system_score_gemma":0.000018403727,"threshold_uncertainty_score":0.99621224},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2309767,0.0030676015,0.6843717,0.032320127,0.0027040339,0.003762976,0.0005945985,0.000876513,0.041325737],"genre_scores_gemma":[0.907616,0.00019586073,0.09165423,0.00004835065,0.0000157965,0.000013840127,0.000026564981,0.000010442902,0.0004189021],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99892795,0.0000047895423,0.0002595573,0.00037301282,0.00030966545,0.00012503465],"domain_scores_gemma":[0.99840844,0.000029425322,0.00012759493,0.0013814878,0.000037769154,0.000015272886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005526692,0.00009026609,0.00011830535,0.00014826011,0.000030621588,0.00004720641,0.0038894552,0.000019561354,0.0000014845332],"category_scores_gemma":[0.00008517857,0.000066799235,0.000020759,0.0006179033,0.00003760923,0.0014799472,0.0057188324,0.000092849885,0.0000039081483],"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":[0.000018704755,0.000075243384,0.0013886895,0.002288703,0.000075502154,0.000003862039,0.00038742452,0.00009517273,0.0025527852,0.9081269,0.0061639766,0.078823045],"study_design_scores_gemma":[0.0013416301,0.00031210028,0.046185352,0.015232775,0.00011827728,0.00001730208,0.0033457165,0.66481423,0.0059393332,0.11481959,0.14689203,0.0009816528],"about_ca_topic_score_codex":0.00003115195,"about_ca_topic_score_gemma":0.0000067750802,"teacher_disagreement_score":0.7933073,"about_ca_system_score_codex":0.000031929503,"about_ca_system_score_gemma":0.000011110944,"threshold_uncertainty_score":0.722764},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023642302,0.00007945192,0.97121805,0.0022768413,0.00038141417,0.0006422068,0.0005595881,0.00014138852,0.0010587777],"genre_scores_gemma":[0.5674987,0.000011158427,0.43218073,0.00003499403,0.00006175147,0.0000043494265,0.00014199158,0.000013466122,0.00005284139],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99815315,0.0000068117733,0.0003433266,0.0006852566,0.0006174715,0.00019395474],"domain_scores_gemma":[0.99751353,0.0001325283,0.00022052713,0.002004114,0.00009990761,0.000029388091],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0011676371,0.00013754024,0.0001603445,0.000108420565,0.00016920011,0.00011011799,0.013261697,0.00004329223,0.000010642475],"category_scores_gemma":[0.00025435162,0.0001161313,0.000050003917,0.0004773217,0.00007938879,0.0026197517,0.008566443,0.0002184535,0.000002078208],"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":[0.00009045592,0.0001823696,0.003155122,0.0022644815,0.00063193915,0.0000067375786,0.0005692481,0.04409605,0.0017404235,0.91281444,0.008483176,0.02596556],"study_design_scores_gemma":[0.00027744507,0.000043442116,0.001948513,0.0005907605,0.0001625042,0.0000052063883,0.00026265928,0.9804069,0.00032333567,0.012591301,0.0032251966,0.0001627812],"about_ca_topic_score_codex":0.000007751763,"about_ca_topic_score_gemma":4.667616e-7,"teacher_disagreement_score":0.9363108,"about_ca_system_score_codex":0.000029187726,"about_ca_system_score_gemma":0.00003941914,"threshold_uncertainty_score":0.9994521},"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":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5219773,0.0022327702,0.11438821,0.084727526,0.003773032,0.005495519,0.0027032956,0.0065838057,0.25811854],"genre_scores_gemma":[0.25835,0.00020503449,0.7405537,0.00015288609,0.00005383756,0.00001547874,0.000025899064,0.000023799237,0.0006193818],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99849945,0.000004093562,0.0002636488,0.0005338515,0.00052253786,0.00017639376],"domain_scores_gemma":[0.9964963,0.000067124034,0.00013724588,0.0032261529,0.000047899895,0.000025260786],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0007913063,0.00012258034,0.00013877952,0.00015497221,0.00004645425,0.00021136002,0.01753785,0.000028986,0.000007797756],"category_scores_gemma":[0.00022133572,0.00008835139,0.000046548736,0.0006329475,0.000056406592,0.0014132684,0.026276184,0.00012751209,0.000009249996],"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":[0.000012257867,0.000101280035,0.0006106788,0.0013280986,0.00017905208,0.000002752041,0.00015228555,0.0000022384397,0.0021674987,0.55227757,0.39016706,0.052999217],"study_design_scores_gemma":[0.0006327116,0.00052336213,0.016799023,0.010165046,0.00031627843,0.00001255231,0.00036748475,0.02971886,0.06761117,0.43562806,0.43731245,0.0009129881],"about_ca_topic_score_codex":0.000012369894,"about_ca_topic_score_gemma":4.1096573e-7,"teacher_disagreement_score":0.62616545,"about_ca_system_score_codex":0.00002409232,"about_ca_system_score_gemma":0.000011354361,"threshold_uncertainty_score":0.9877777},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.083660975,0.0033809193,0.8359582,0.058401514,0.0037422532,0.0043937666,0.0049141063,0.0006420108,0.0049062953],"genre_scores_gemma":[0.2687187,0.00036692145,0.73018855,0.0000838699,0.0001161075,0.000005722396,0.00027068952,0.000015240867,0.00023424732],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984418,0.0000031199463,0.00023458243,0.0008566557,0.00033795965,0.00012588307],"domain_scores_gemma":[0.9941567,0.000058104077,0.00013692028,0.0055835275,0.000041829015,0.000022917444],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00094381865,0.00010116671,0.00011711129,0.000075489435,0.00006279305,0.00017949314,0.017144196,0.000031040072,0.0000027910107],"category_scores_gemma":[0.00024075339,0.000073553776,0.000013436783,0.00022205838,0.00003341998,0.0024827672,0.038225748,0.00008721198,9.929338e-7],"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":[0.00003592201,0.000058844787,0.00011021383,0.0031001735,0.00019286606,0.0000012198079,0.000108556786,0.000010752835,0.0056300103,0.15374252,0.080830276,0.7561786],"study_design_scores_gemma":[0.0003451138,0.000044616405,0.00044381912,0.00078392477,0.00015147384,0.000007694895,0.00015154424,0.8964323,0.0028336558,0.03247177,0.06617129,0.00016279984],"about_ca_topic_score_codex":0.000006028885,"about_ca_topic_score_gemma":8.390851e-7,"teacher_disagreement_score":0.89642155,"about_ca_system_score_codex":0.000009587436,"about_ca_system_score_gemma":0.000011541543,"threshold_uncertainty_score":0.98817354},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74813485,0.009345307,0.045344606,0.12291692,0.0039180582,0.004295986,0.0011067619,0.0014024662,0.063535035],"genre_scores_gemma":[0.9499611,0.0007493513,0.04323002,0.0005542551,0.00004728729,0.000023219582,0.000019564932,0.000025612768,0.0053895363],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987699,0.0000054041657,0.00020987823,0.00047724144,0.00037916214,0.00015841088],"domain_scores_gemma":[0.99851274,0.000035785673,0.00009074813,0.0012909588,0.00003976185,0.000030001445],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00046268123,0.00012687143,0.00014093492,0.00011447726,0.000053879343,0.00021831036,0.0053526117,0.000021825368,0.000008685229],"category_scores_gemma":[0.000035002733,0.00009004776,0.000051744813,0.00025806963,0.000046266505,0.0008240303,0.00908743,0.00010097709,0.000007443359],"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":[0.00014726809,0.000491929,0.0020090167,0.007038311,0.0014805873,0.000026914486,0.0015224371,0.00008888067,0.008884511,0.16656373,0.4020627,0.4096837],"study_design_scores_gemma":[0.0025028833,0.0006861474,0.010696338,0.007062045,0.00081352453,0.000035891564,0.0016304577,0.88071316,0.0027220154,0.02856022,0.0633632,0.0012141428],"about_ca_topic_score_codex":0.000014645447,"about_ca_topic_score_gemma":0.0000013464132,"teacher_disagreement_score":0.88062423,"about_ca_system_score_codex":0.000017167116,"about_ca_system_score_gemma":0.0000049172445,"threshold_uncertainty_score":0.9989269},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16006525,0.0058460347,0.43752506,0.028352248,0.0063831634,0.008554295,0.008987875,0.00127542,0.34301066],"genre_scores_gemma":[0.6875433,0.000292335,0.31022412,0.000112584064,0.00009967228,0.000011915071,0.00008714744,0.000027415137,0.0016015518],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982798,0.000014750035,0.0004924398,0.0005642483,0.00048755176,0.00016121464],"domain_scores_gemma":[0.99744713,0.00021201273,0.00041786215,0.0017563992,0.0001403466,0.000026233398],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0008256802,0.00014068185,0.00024996555,0.00012272249,0.000053122014,0.000036328245,0.0044082603,0.000022932152,0.0000019128329],"category_scores_gemma":[0.00024573834,0.000098518925,0.00006151331,0.0005959872,0.00015074435,0.0012394963,0.011652334,0.00011509197,0.0000047532326],"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":[0.00020187527,0.0001541204,0.00035073835,0.0032499284,0.00056337524,0.0000082499,0.0015441594,0.000073537485,0.002572304,0.84981143,0.122448616,0.01902164],"study_design_scores_gemma":[0.006696623,0.0020538326,0.016306374,0.046863127,0.0009279915,0.0000408388,0.032749873,0.13217863,0.30072308,0.09916464,0.35988754,0.0024074262],"about_ca_topic_score_codex":0.000053599375,"about_ca_topic_score_gemma":0.0000010440639,"teacher_disagreement_score":0.7506468,"about_ca_system_score_codex":0.000018912346,"about_ca_system_score_gemma":0.000018571971,"threshold_uncertainty_score":0.9963412},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7480225,0.001214944,0.19482292,0.0103624435,0.0019515227,0.009477723,0.00031211294,0.00031204737,0.03352378],"genre_scores_gemma":[0.9166248,0.00011862492,0.0825082,0.00017720007,0.00004682014,0.00006750586,0.000071199036,0.000010067586,0.00037559328],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861544,0.00001655567,0.00027017575,0.0005896713,0.00035006143,0.00015807107],"domain_scores_gemma":[0.9976025,0.00007593901,0.00024186925,0.0018919362,0.00016249227,0.000025239358],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0005202746,0.00014714371,0.00019321915,0.00013631806,0.000089130204,0.00007747607,0.0061539537,0.00003867613,0.000003137227],"category_scores_gemma":[0.00014662015,0.000104349965,0.000038389007,0.00075300207,0.000055391847,0.0006152577,0.005792634,0.000110029076,0.0000021678209],"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":[0.0002796657,0.0006514191,0.0063497354,0.00065819867,0.0011088044,0.000001631308,0.000673467,0.00021245402,0.015465212,0.7900328,0.04309121,0.14147541],"study_design_scores_gemma":[0.0078112427,0.00095887855,0.086640865,0.0051833224,0.0012004428,0.0000017563788,0.0007614331,0.43840316,0.23281536,0.20373124,0.021196404,0.0012959087],"about_ca_topic_score_codex":0.000028122555,"about_ca_topic_score_gemma":0.00000605031,"teacher_disagreement_score":0.58630157,"about_ca_system_score_codex":0.000044019776,"about_ca_system_score_gemma":0.000017394996,"threshold_uncertainty_score":0.99922323},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13338555,0.00029848388,0.39063904,0.029940331,0.0018730719,0.004966131,0.00038039466,0.00063317904,0.4378838],"genre_scores_gemma":[0.927381,0.000008973928,0.069366775,0.00016615468,0.000014430728,0.000010557053,0.000009666273,0.000005616913,0.0030368504],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988154,0.0000048669885,0.00023788208,0.0004100239,0.00037259975,0.00015921766],"domain_scores_gemma":[0.9979588,0.000025894245,0.00022358682,0.0016240736,0.0001429893,0.000024683808],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00049605983,0.0001083104,0.00015856762,0.000107281325,0.00007203928,0.0000819789,0.008341542,0.000021640342,0.0000012948861],"category_scores_gemma":[0.000049742706,0.00007304428,0.000031003932,0.00085984264,0.000028727685,0.0003657976,0.0062097847,0.00006846543,0.000010364814],"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":[0.0001851634,0.00039206512,0.003737384,0.0014129633,0.00056354515,0.0000017313187,0.00028953364,0.0014698876,0.0006248912,0.72922426,0.23618115,0.02591744],"study_design_scores_gemma":[0.009586477,0.004309912,0.19907673,0.039664473,0.0012191256,0.000018596444,0.006592786,0.16781756,0.019244226,0.15372336,0.39599174,0.002755016],"about_ca_topic_score_codex":0.000013698322,"about_ca_topic_score_gemma":4.7314285e-7,"teacher_disagreement_score":0.79399544,"about_ca_system_score_codex":0.000020760599,"about_ca_system_score_gemma":0.000013392838,"threshold_uncertainty_score":0.9970238},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53120035,0.0006416736,0.026517393,0.07384835,0.007591261,0.007773333,0.0025272812,0.000273683,0.34962663],"genre_scores_gemma":[0.96664,0.000031439893,0.020601215,0.00025618306,0.00002631226,0.000035045476,0.000023127497,0.0000092726505,0.012377426],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973082,0.00001299552,0.00061613444,0.0008661555,0.0009970447,0.0001994476],"domain_scores_gemma":[0.9938637,0.00088578067,0.0005678313,0.0041648317,0.0004896962,0.000028172388],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.004422387,0.00014419624,0.00028763028,0.00030094202,0.00018855806,0.00023683866,0.013344548,0.000025928759,0.000032609434],"category_scores_gemma":[0.007132439,0.00008988958,0.00008953086,0.0011524493,0.00028820283,0.0003662034,0.01367251,0.000057994945,0.000010724509],"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":[0.00022940034,0.00021631955,0.0036126403,0.00052213896,0.0002557702,2.3262962e-7,0.00010397244,0.000043886972,0.00018292961,0.3735617,0.55144364,0.06982733],"study_design_scores_gemma":[0.0015475354,0.000233266,0.026352573,0.0017306041,0.00053357676,7.051335e-7,0.01440855,0.0035357669,0.008596565,0.55910057,0.38356802,0.00039229143],"about_ca_topic_score_codex":0.000010778389,"about_ca_topic_score_gemma":0.0000033572173,"teacher_disagreement_score":0.4354396,"about_ca_system_score_codex":0.000017688879,"about_ca_system_score_gemma":0.00002026314,"threshold_uncertainty_score":0.9943047},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16581629,0.00037294888,0.6077154,0.20983483,0.0011651771,0.003155156,0.00028594348,0.0009888747,0.010665328],"genre_scores_gemma":[0.14608423,0.00006393252,0.8531748,0.00016756011,0.00001756221,0.00004010918,0.000029146302,0.000010460214,0.0004121964],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983718,0.000005276459,0.00036533113,0.00062284985,0.00038327623,0.00025148314],"domain_scores_gemma":[0.9892777,0.00012704598,0.00038299928,0.01007353,0.000121197074,0.00001749785],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0007960676,0.00016123679,0.00020701755,0.00022725263,0.00012655088,0.00014325912,0.09012894,0.00006403822,0.0000013837931],"category_scores_gemma":[0.008152371,0.00012808914,0.00005548649,0.00071216613,0.00011914147,0.001280113,0.25028405,0.00012065504,0.0000013086351],"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":[0.00012561883,0.00028770693,0.0019308855,0.0016492298,0.00044851413,6.2336056e-7,0.00009728827,0.00004028924,0.007074493,0.2021202,0.6811937,0.105031416],"study_design_scores_gemma":[0.00093603414,0.00021614943,0.004611975,0.001068561,0.00013518085,9.3713527e-7,0.00016397273,0.27936715,0.041812636,0.6534608,0.0179381,0.000288479],"about_ca_topic_score_codex":0.0000031009758,"about_ca_topic_score_gemma":2.6058683e-7,"teacher_disagreement_score":0.66325563,"about_ca_system_score_codex":0.00004450688,"about_ca_system_score_gemma":0.000014101261,"threshold_uncertainty_score":0.97597384},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010694007,0.0006272769,0.9563394,0.015405596,0.0013236995,0.0024197174,0.0010316807,0.0002283842,0.011930201],"genre_scores_gemma":[0.014498009,0.00013977374,0.98089814,0.00021640127,0.00004150148,0.000061777166,0.00003024368,0.0000119625365,0.0041021877],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99867904,0.0000042793495,0.00034588075,0.00047055527,0.00029609405,0.00020414116],"domain_scores_gemma":[0.9973451,0.000056256482,0.0003223393,0.0021066994,0.00014671164,0.00002288911],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0005031657,0.00014636092,0.00023362334,0.0001032868,0.00011783708,0.00004983129,0.0061934586,0.000026534279,0.000001254303],"category_scores_gemma":[0.0002293947,0.00010468768,0.00006367197,0.00038350752,0.000099492194,0.001154112,0.0098961815,0.00006358676,0.000001781936],"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":[0.000049129263,0.00007954855,0.00017440986,0.0012800017,0.00016592955,4.0217932e-7,0.00008749847,0.000017388678,0.00040539532,0.8967305,0.04467313,0.056336705],"study_design_scores_gemma":[0.0017822033,0.00033883285,0.0021252397,0.0027774943,0.00019162668,0.0000027359408,0.0014716577,0.014965381,0.051233996,0.04273557,0.8818519,0.0005233643],"about_ca_topic_score_codex":0.000009419884,"about_ca_topic_score_gemma":7.2572385e-7,"teacher_disagreement_score":0.8539949,"about_ca_system_score_codex":0.000016562299,"about_ca_system_score_gemma":0.000016547145,"threshold_uncertainty_score":0.99918354},"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":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53776973,0.00008739156,0.45908058,0.00086113194,0.0002846462,0.0015050303,0.0001434365,0.00008437539,0.00018368567],"genre_scores_gemma":[0.3287501,0.000022331864,0.67105305,0.000054706434,0.000010568498,0.00002431887,0.000019900623,0.000008405094,0.000056617933],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876344,0.000009455179,0.00034011094,0.0004896052,0.00019269326,0.00020471116],"domain_scores_gemma":[0.99824077,0.00003714663,0.0003021492,0.0012905331,0.000110438996,0.000018937282],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0008975607,0.00013231157,0.00017039351,0.00026121392,0.00011094439,0.00009817941,0.006430416,0.000036908332,3.5357525e-7],"category_scores_gemma":[0.000050261457,0.00011138623,0.00005432051,0.0007132099,0.000056785582,0.00095731206,0.002658565,0.000077661796,1.8191824e-7],"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":[0.00006242179,0.00051091495,0.001961292,0.0009786066,0.00017833083,3.7045817e-7,0.00022249717,0.00032919878,0.072176084,0.21869428,0.00014600586,0.70474],"study_design_scores_gemma":[0.00055442995,0.000045954537,0.0038466083,0.0002131641,0.000038455386,3.960674e-7,0.00025467802,0.9209152,0.0042991666,0.069676794,0.000045374436,0.0001097767],"about_ca_topic_score_codex":0.000017591778,"about_ca_topic_score_gemma":0.0000017562027,"teacher_disagreement_score":0.920586,"about_ca_system_score_codex":0.000027296963,"about_ca_system_score_gemma":0.000011506348,"threshold_uncertainty_score":0.9989453},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16846313,0.0024376984,0.23108827,0.45912662,0.0036525724,0.009621059,0.00046781646,0.0010253368,0.12411751],"genre_scores_gemma":[0.76851124,0.00022266542,0.2296169,0.0004228016,0.00003521052,0.00003205478,0.000010720269,0.000008927376,0.0011394675],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988296,0.000008414263,0.00024503944,0.00038309186,0.0003905112,0.00014331994],"domain_scores_gemma":[0.9967936,0.00006056133,0.00022156387,0.0028141101,0.00009519276,0.000014955302],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0006626774,0.000105407074,0.00012287422,0.00009608772,0.00015022125,0.000089204135,0.01576854,0.000022346005,0.0000024161768],"category_scores_gemma":[0.00012032136,0.00006607023,0.000056038964,0.000735602,0.00010685036,0.0004588128,0.012570774,0.00009710631,0.0000036780507],"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":[0.000012755842,0.00014109924,0.0007500685,0.0002935517,0.00012387645,1.4900819e-7,0.0000911336,0.000022856575,0.0007240184,0.8840756,0.014744199,0.09902068],"study_design_scores_gemma":[0.0013551782,0.00013481661,0.07100637,0.0012103238,0.00025326372,0.000002487371,0.000631618,0.120921634,0.024974499,0.69132936,0.08774407,0.0004363966],"about_ca_topic_score_codex":0.000012057156,"about_ca_topic_score_gemma":6.6887105e-7,"teacher_disagreement_score":0.6000481,"about_ca_system_score_codex":0.000013755241,"about_ca_system_score_gemma":0.000007475083,"threshold_uncertainty_score":0.9954154},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3197254,0.0020819895,0.3955477,0.046146568,0.0027223555,0.0038658709,0.003154065,0.00041957098,0.22633648],"genre_scores_gemma":[0.9833844,0.00010883787,0.015579778,0.0001539084,0.0000064449123,0.0000086253,0.000015817732,0.000004058122,0.0007381392],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99834377,0.000007981167,0.0004932259,0.00045032863,0.0005329125,0.00017180189],"domain_scores_gemma":[0.9966889,0.000021659642,0.00048651805,0.0025690312,0.00021181266,0.000022079084],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0008020885,0.00012325744,0.00037077797,0.00024600985,0.000038959155,0.000050121333,0.011908105,0.000032593234,0.000004454307],"category_scores_gemma":[0.00012284525,0.000087969434,0.00011953585,0.0019711622,0.00006312152,0.00045770625,0.007895271,0.00007494777,0.0000015932902],"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":[0.00006987168,0.00044658882,0.012675679,0.0016141352,0.0036602342,0.0000019933002,0.00012820626,0.00047464634,0.0009921243,0.8658156,0.06880877,0.045312144],"study_design_scores_gemma":[0.0048437105,0.0004157328,0.5287294,0.008989298,0.007098665,0.0000030233919,0.00321097,0.18159813,0.058399383,0.092801385,0.112321526,0.0015887925],"about_ca_topic_score_codex":0.000042001746,"about_ca_topic_score_gemma":0.0000019552367,"teacher_disagreement_score":0.77301425,"about_ca_system_score_codex":0.000026075386,"about_ca_system_score_gemma":0.000017782691,"threshold_uncertainty_score":0.99343795},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16193967,0.00042803897,0.04646963,0.37070012,0.0025785083,0.009395396,0.0026101267,0.00014082917,0.4057377],"genre_scores_gemma":[0.9390636,0.00012404908,0.056339905,0.0012260502,0.0000311521,0.00006338455,0.000020771708,0.000013042477,0.003118062],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99662274,0.000036736452,0.0008861673,0.0005740526,0.0016592909,0.00022101335],"domain_scores_gemma":[0.99388444,0.0013351043,0.00096621463,0.0033381649,0.00044775227,0.000028320248],"candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0099159945,0.00014000782,0.00030806998,0.00016820767,0.00014106078,0.00014316633,0.013026213,0.000038482372,0.000050767292],"category_scores_gemma":[0.01685998,0.00007696724,0.00011556368,0.00085259747,0.0002342756,0.0010248135,0.01601715,0.00012584077,0.000007758214],"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":[0.00020518246,0.0002606869,0.00068431103,0.00047227863,0.0002531939,3.197928e-7,0.00022443001,0.0000052381074,0.0002669767,0.6632769,0.29642883,0.03792165],"study_design_scores_gemma":[0.0013810998,0.00030970157,0.012049801,0.0010430168,0.0006123891,0.0000012796462,0.04163684,0.0008499566,0.015342247,0.58777887,0.33870068,0.00029413385],"about_ca_topic_score_codex":0.000020225616,"about_ca_topic_score_gemma":0.0000034683087,"teacher_disagreement_score":0.7771239,"about_ca_system_score_codex":0.000017675475,"about_ca_system_score_gemma":0.00003292517,"threshold_uncertainty_score":0.9923138},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.096945755,0.0004623742,0.82325524,0.05856487,0.0022583094,0.0027949226,0.00029942763,0.00039109506,0.015028015],"genre_scores_gemma":[0.96299124,0.0000732037,0.034544118,0.00040042782,0.000027671764,0.000023269064,0.000009769591,0.000011791529,0.0019185258],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983535,0.000008158059,0.00040866708,0.0005649548,0.0004299913,0.00023472252],"domain_scores_gemma":[0.9976196,0.000035943754,0.00032407706,0.0018393607,0.00014326943,0.00003770901],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00050944556,0.00018034191,0.00025284203,0.00012808674,0.000095016236,0.00013553043,0.008679803,0.0000592386,0.00000951819],"category_scores_gemma":[0.00012746618,0.00012901933,0.000069013724,0.00062171655,0.000041186657,0.0010122329,0.002697233,0.00016180618,0.000002446287],"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":[0.0015208987,0.0032133416,0.00887787,0.023824217,0.0037892552,0.00002191597,0.007870779,0.0016398174,0.03264361,0.1794755,0.3062414,0.4308814],"study_design_scores_gemma":[0.011086256,0.0023948052,0.017329589,0.07438261,0.0019239751,0.000033778393,0.016933832,0.41205817,0.23491332,0.0790498,0.14589098,0.004002865],"about_ca_topic_score_codex":0.00009950792,"about_ca_topic_score_gemma":0.000012834901,"teacher_disagreement_score":0.8660455,"about_ca_system_score_codex":0.00004496994,"about_ca_system_score_gemma":0.000021526888,"threshold_uncertainty_score":0.9966837},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7299008,0.0006025948,0.04887603,0.015094695,0.0013596884,0.0033122082,0.0002076615,0.00050557556,0.20014076],"genre_scores_gemma":[0.88680714,0.000069749476,0.11245104,0.00014206137,0.000018620629,0.0000147043675,0.000013578938,0.0000116016645,0.00047149337],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981715,0.00002336859,0.0003632919,0.0006190351,0.00052381353,0.00029897233],"domain_scores_gemma":[0.9969978,0.000054866337,0.000227081,0.00257591,0.00010439822,0.00003997439],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0012703056,0.00018275049,0.00025746008,0.00027827633,0.00017061026,0.0001435047,0.016377635,0.000043905493,0.0000030067747],"category_scores_gemma":[0.00006740235,0.00014034,0.00010003165,0.0014771885,0.0001731702,0.00079805555,0.01247853,0.00021632922,0.000003073251],"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":[0.000072799674,0.0005887379,0.0017502472,0.001496193,0.0003808226,0.0000013040601,0.00044878694,0.000041734933,0.0040218094,0.85875565,0.006022935,0.12641898],"study_design_scores_gemma":[0.0023354464,0.0003140251,0.03427992,0.003220172,0.00033248146,0.000008514791,0.003702649,0.027663006,0.09845387,0.82605106,0.0028030626,0.00083578],"about_ca_topic_score_codex":0.000006833125,"about_ca_topic_score_gemma":2.0421385e-7,"teacher_disagreement_score":0.19966927,"about_ca_system_score_codex":0.000015867687,"about_ca_system_score_gemma":0.00001458262,"threshold_uncertainty_score":0.9955084},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36444947,0.00064290944,0.284761,0.29957512,0.0024943913,0.0028313117,0.00020762646,0.0018549034,0.043183252],"genre_scores_gemma":[0.72476035,0.00007476093,0.27489343,0.0001536885,0.000011971406,0.0000041126573,0.0000067351457,0.0000074699933,0.00008746525],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979943,0.000013190945,0.0004382556,0.00067520066,0.0006151527,0.00026387084],"domain_scores_gemma":[0.98310274,0.00012547578,0.00041278562,0.016196202,0.00014016652,0.000022643657],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00067025155,0.00018127293,0.00025502685,0.00022425983,0.00013140045,0.00012723563,0.14336589,0.00006312096,0.000003159057],"category_scores_gemma":[0.007522821,0.00013701657,0.00006213125,0.0008779236,0.00017027756,0.000742671,0.50844204,0.00021208073,0.00000291669],"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":[0.000038195827,0.00043262285,0.0063181925,0.0013114099,0.00065318967,0.0000011429713,0.000054933087,0.000007746912,0.003641536,0.40807435,0.45159164,0.12787504],"study_design_scores_gemma":[0.00081290124,0.00006804231,0.02770217,0.001571699,0.00015054004,0.0000014752179,0.00023950114,0.021059742,0.021777892,0.9235966,0.0027238664,0.0002955617],"about_ca_topic_score_codex":0.000010346113,"about_ca_topic_score_gemma":5.381802e-7,"teacher_disagreement_score":0.5155223,"about_ca_system_score_codex":0.000042777076,"about_ca_system_score_gemma":0.000022777456,"threshold_uncertainty_score":0.9006063},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024842764,0.00013191058,0.98754156,0.001959308,0.00009591965,0.0017303413,0.00007189691,0.00018257402,0.0058022393],"genre_scores_gemma":[0.16426538,0.00007255717,0.8348446,0.00030899525,0.000016889402,0.00009290465,0.000027906657,0.000017923885,0.00035285996],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9981697,0.000011461223,0.00037458245,0.0006589313,0.0004774935,0.00030781896],"domain_scores_gemma":[0.99707633,0.00011304667,0.00025915506,0.0022872477,0.00023065049,0.000033568067],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0010503442,0.0001891584,0.0002661807,0.00027456152,0.00014676084,0.0001362708,0.01145339,0.000052618972,8.80191e-7],"category_scores_gemma":[0.00033639534,0.00014334042,0.000103548955,0.0012252327,0.0001248497,0.0009386893,0.0074564163,0.0001583971,5.374391e-7],"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":[0.00048242055,0.0009930077,0.0021795563,0.010603911,0.00051649776,0.0000015956231,0.00016267205,0.00019772128,0.007933303,0.7241876,0.043065887,0.20967585],"study_design_scores_gemma":[0.002932771,0.0005760807,0.0035298758,0.0024345485,0.00025571755,0.0000011975173,0.0006180526,0.16226718,0.60983115,0.20153217,0.015291015,0.0007302313],"about_ca_topic_score_codex":0.0000056314193,"about_ca_topic_score_gemma":1.2678346e-7,"teacher_disagreement_score":0.60189784,"about_ca_system_score_codex":0.00003438451,"about_ca_system_score_gemma":0.000031838183,"threshold_uncertainty_score":0.9938951},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9807904,0.00024240158,0.00165582,0.004483038,0.00037027226,0.0017874415,0.00003682751,0.00007670745,0.010557108],"genre_scores_gemma":[0.9970779,0.00010249211,0.002417025,0.00031282744,0.000017936802,0.000014061051,0.000002620826,0.0000075086846,0.000047659454],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9984842,0.000029884053,0.0002148003,0.0005953319,0.00042189457,0.00025389486],"domain_scores_gemma":[0.9972139,0.00047708166,0.00022465727,0.0019819788,0.000072414274,0.000029943902],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00045994465,0.00021838803,0.00024717083,0.00013682779,0.00015923174,0.00008182732,0.007680561,0.000030949188,0.0000013551839],"category_scores_gemma":[0.00011198661,0.00011715234,0.00007879357,0.00084026024,0.00018156187,0.0003028534,0.006171436,0.00021813672,0.0000015426584],"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":[0.0019781266,0.0013608112,0.007890954,0.0026077975,0.0013310472,0.0000120095865,0.0004850666,0.014875876,0.0064311195,0.790327,0.040105034,0.13259514],"study_design_scores_gemma":[0.0034331193,0.002992969,0.66943526,0.0051506707,0.0002647027,0.000009011481,0.0005894523,0.05677215,0.042459387,0.21694118,0.0011618285,0.00079024927],"about_ca_topic_score_codex":0.000008027797,"about_ca_topic_score_gemma":2.2259967e-7,"teacher_disagreement_score":0.6615443,"about_ca_system_score_codex":0.000034808123,"about_ca_system_score_gemma":0.000008091544,"threshold_uncertainty_score":0.99768835},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4741293,0.0012327136,0.010661748,0.0632491,0.0070010796,0.0076644095,0.005984611,0.0005818234,0.42949522],"genre_scores_gemma":[0.953068,0.00039096255,0.029081939,0.00090741034,0.00006657454,0.000030002517,0.00016621033,0.00002413148,0.016264753],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.996578,0.000025929723,0.00082799577,0.0007839422,0.0015262396,0.00025789413],"domain_scores_gemma":[0.99513865,0.00018057018,0.0006581854,0.0037233424,0.00025708447,0.000042187985],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0045893774,0.00019026989,0.00034693017,0.00033531626,0.0001466706,0.00023050007,0.013541919,0.000055053366,0.00010361574],"category_scores_gemma":[0.002736851,0.00013198791,0.000077240664,0.0014119896,0.00013719634,0.0011872721,0.0139251575,0.0001364371,0.000017382607],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002094153,0.00028344244,0.0027638937,0.0007572036,0.00034407622,7.503498e-7,0.00010468664,0.00006004163,0.0022272882,0.32255965,0.6057335,0.064956],"study_design_scores_gemma":[0.001309752,0.00015224097,0.019957216,0.0011844047,0.0003417159,6.4920494e-7,0.004922315,0.0011816588,0.012212787,0.42798182,0.5303765,0.00037891752],"about_ca_topic_score_codex":0.000039390507,"about_ca_topic_score_gemma":0.000008334242,"teacher_disagreement_score":0.47893873,"about_ca_system_score_codex":0.000040175928,"about_ca_system_score_gemma":0.000017435414,"threshold_uncertainty_score":0.99405},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029771065,0.00037489142,0.71232307,0.058202118,0.0013170706,0.005550721,0.0009575433,0.000996175,0.19050732],"genre_scores_gemma":[0.6375569,0.0010502848,0.33072367,0.0036652284,0.000109197936,0.00010952417,0.0018302874,0.00007139159,0.024883496],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902546,0.000006329768,0.000291778,0.00023297538,0.0003459248,0.000097526514],"domain_scores_gemma":[0.9985188,0.000013757867,0.00023854543,0.0010275088,0.00018580997,0.000015557765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000291861,0.00008721089,0.00011686262,0.00013523138,0.000075258635,0.00008137524,0.0049718097,0.000021441905,0.000009908508],"category_scores_gemma":[0.00013000658,0.000065448876,0.000027579117,0.0010083795,0.00005437928,0.0015575404,0.0028584388,0.000034363115,0.0000062253303],"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":[0.000014700993,0.00012308438,0.00023253744,0.00047057535,0.00008837985,1.1420854e-7,0.00015980986,0.0000073280034,0.00020776127,0.9688689,0.02416655,0.0056602187],"study_design_scores_gemma":[0.004386214,0.0006381386,0.009459635,0.0062697274,0.0007944943,0.000004516797,0.0031302576,0.39501077,0.15605439,0.119338185,0.30380583,0.0011078137],"about_ca_topic_score_codex":7.562608e-7,"about_ca_topic_score_gemma":9.173595e-8,"teacher_disagreement_score":0.84953076,"about_ca_system_score_codex":0.000011834423,"about_ca_system_score_gemma":0.000013660311,"threshold_uncertainty_score":0.9238942},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033629403,0.002558785,0.5411043,0.011579382,0.001153788,0.005233359,0.00097421353,0.0011179242,0.4026488],"genre_scores_gemma":[0.6308535,0.00003201599,0.36739698,0.00012229363,0.00004041929,0.000039624116,0.00001563269,0.000015351132,0.0014842073],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99850625,0.000009041668,0.00036384194,0.00051187834,0.00042110492,0.00018789891],"domain_scores_gemma":[0.99721706,0.000037798913,0.0004134936,0.0021773719,0.00013003896,0.000024214716],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0005333616,0.00014879114,0.0002371773,0.00012569045,0.00013262493,0.0000524682,0.0069377827,0.000027703976,6.1954114e-7],"category_scores_gemma":[0.00010864658,0.00010401763,0.000041938227,0.0007043432,0.000081682134,0.0010579152,0.011569202,0.00009365237,0.0000020865514],"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":[0.000045088105,0.000083182196,0.0002271033,0.0028266576,0.00010997419,0.0000012855601,0.0001347401,0.000013551869,0.00030084376,0.93261075,0.0131063005,0.050540525],"study_design_scores_gemma":[0.005628211,0.0010182384,0.010470549,0.06306552,0.001003803,0.00002996742,0.04677004,0.08464871,0.078421496,0.03661512,0.67014194,0.002186418],"about_ca_topic_score_codex":0.000012098216,"about_ca_topic_score_gemma":6.675352e-7,"teacher_disagreement_score":0.8959956,"about_ca_system_score_codex":0.000042034688,"about_ca_system_score_gemma":0.000021922819,"threshold_uncertainty_score":0.99843514},"labels":[],"label_agreement":null}]}