{"meta":{"query_hash":"416db036aa93","filters":{"venue":"Proceedings of the VLDB Endowment"},"cohort_total":329,"direct_labels_cover":0,"predictions_cover":329,"exported":329,"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/416db036aa93","api":"https://metacan.xera.ac/api/v1/cohort?venue=Proceedings+of+the+VLDB+Endowment"},"results":[{"id":"W1509825211","doi":"10.14778/2733085.2733099","title":"Generating top-k packages via preference elicitation","year":2014,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Recommender system; Preference elicitation; Ranking (information retrieval); Function (biology); Preference; Rank (graph theory); Information retrieval; Variety (cybernetics); Learning to rank; Preference learning; Machine learning; Data mining; Artificial intelligence; Mathematics","score_opus":0.01761425993665048,"score_gpt":0.21582282076499093,"score_spread":0.19820856082834046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1509825211","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":[0.37002802,0.00010910108,0.584662,0.005352128,0.0012049833,0.0010487898,0.000004791469,0.0003506874,0.037239473],"genre_scores_gemma":[0.9520155,0.000012277429,0.04710476,0.00027208216,0.000096250085,0.000029058318,0.0000011624405,0.0000054516504,0.00046344858],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990539,0.000007792492,0.00019235096,0.00024768355,0.00031997258,0.00017832337],"domain_scores_gemma":[0.99946564,0.00002474553,0.0001838702,0.00019152704,0.000101437116,0.00003275026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037494028,0.00010171578,0.00010149542,0.000052541098,0.00014029496,0.0001758895,0.0010913879,0.000019478464,0.0000048026786],"category_scores_gemma":[0.000072811206,0.00006957213,0.00004411684,0.00023445,0.00002636134,0.0006074099,0.0005819283,0.00006306294,0.000011999358],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004898559,0.0001304972,0.0042936737,0.00016968256,0.000050484447,1.6970255e-7,0.0015225515,0.0001618568,0.16992375,0.3629229,0.0065423627,0.4542772],"study_design_scores_gemma":[0.00088331365,0.00027292164,0.009547294,0.00017882648,0.00004338956,0.000005368298,0.0002061054,0.41807413,0.5077993,0.04887432,0.013617068,0.00049795053],"about_ca_topic_score_codex":0.00001987496,"about_ca_topic_score_gemma":8.78188e-7,"teacher_disagreement_score":0.5819875,"about_ca_system_score_codex":0.000020617494,"about_ca_system_score_gemma":0.0000047349968,"threshold_uncertainty_score":0.28370693},"labels":[],"label_agreement":null},{"id":"W1539153042","doi":"10.14778/2831360.2831367","title":"S-Store","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":82,"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":"National Science Foundation","keywords":"Online transaction processing; Computer science; Stream processing; Transaction processing; Distributed transaction; Database; Database transaction; Correctness; Operating system; Programming language","score_opus":0.02531497744140868,"score_gpt":0.22789163883845423,"score_spread":0.20257666139704555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1539153042","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":[0.39133587,0.0034360837,0.29228917,0.020018857,0.008211268,0.0033532297,0.000071362716,0.0012306297,0.28005353],"genre_scores_gemma":[0.9228339,0.000010127453,0.075448774,0.00021771197,0.000110083085,0.000040999184,4.7037145e-7,0.000008847927,0.0013290712],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99920315,0.000003002099,0.00015934191,0.0001693263,0.0003173052,0.0001478801],"domain_scores_gemma":[0.9994241,0.000008303312,0.00013995433,0.00018520762,0.00017009805,0.000072362935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023096058,0.00008150924,0.00010924587,0.00002885352,0.000050576607,0.000022482749,0.0006017708,0.000017627674,0.0000017393049],"category_scores_gemma":[0.0000727645,0.000049637787,0.000045083292,0.00019880621,0.000042542466,0.0004595655,0.00053019205,0.0000552177,0.000012080257],"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":[0.0000062070417,0.000037761554,0.0017049497,0.00003639163,0.00001222764,4.2495958e-7,0.0013155242,0.000012838176,0.007404482,0.970444,0.016009105,0.0030160756],"study_design_scores_gemma":[0.00096733373,0.00019460043,0.0011739939,0.00017349666,0.000013219831,0.00006195305,0.001131418,0.0011998676,0.28426877,0.02385033,0.6866285,0.00033648693],"about_ca_topic_score_codex":0.000032776636,"about_ca_topic_score_gemma":0.0000013546219,"teacher_disagreement_score":0.9465937,"about_ca_system_score_codex":0.000048394417,"about_ca_system_score_gemma":0.000032551772,"threshold_uncertainty_score":0.20241702},"labels":[],"label_agreement":null},{"id":"W1545879303","doi":"10.14778/2732219.2732221","title":"More is simpler","year":2013,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":69,"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; Leverage (statistics); Similarity (geometry); Computation; Theoretical computer science; Cluster analysis; Similarity measure; Artificial intelligence; Algorithm","score_opus":0.007098670208723978,"score_gpt":0.2316398325702858,"score_spread":0.22454116236156182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1545879303","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":[0.93692887,0.000035060606,0.0001242212,0.0029503708,0.000044017703,0.0006032503,0.0000069916096,0.00006268462,0.059244543],"genre_scores_gemma":[0.997268,0.0000020745897,0.0010014186,0.00020669444,0.00012733464,0.00012011776,0.0000011810051,0.000012330995,0.0012608081],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992157,0.0000021089947,0.00021233407,0.00016464174,0.00020938503,0.00019583135],"domain_scores_gemma":[0.999478,0.000012122509,0.00017185639,0.00013784623,0.00015811327,0.000042051553],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000069883296,0.000121403464,0.000164659,0.000037383797,0.00007341194,0.000046519992,0.00038871844,0.000016317026,0.0017054535],"category_scores_gemma":[0.000002727996,0.00007966469,0.00017846319,0.00019902039,0.000050468087,0.000117554984,0.00024950216,0.00008957649,0.000034567995],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000072678877,0.00029825352,0.30801404,0.000045369572,0.00037801033,3.4737333e-8,0.001578787,0.000010267673,0.07429141,0.08161047,0.5007457,0.03302038],"study_design_scores_gemma":[0.00053110684,0.00006474459,0.027046619,0.00010464254,0.00018443943,0.0000010168591,0.0014915977,0.0018404042,0.72543323,0.19259273,0.050254602,0.00045487014],"about_ca_topic_score_codex":0.00040125017,"about_ca_topic_score_gemma":3.4821863e-7,"teacher_disagreement_score":0.6511418,"about_ca_system_score_codex":0.000020431378,"about_ca_system_score_gemma":0.0000075256403,"threshold_uncertainty_score":0.99920714},"labels":[],"label_agreement":null},{"id":"W1656389077","doi":"10.14778/2735479.2735485","title":"Rapid sampling for visualizations with ordering guarantees","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":102,"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":"National Institute of General Medical Sciences","keywords":"Computer science; Bar chart; Visualization; Focus (optics); Sampling (signal processing); Chart; Theoretical computer science; Property (philosophy); Algorithm; Data mining; Mathematics; Statistics; Computer vision","score_opus":0.07172555247471732,"score_gpt":0.31408397678660194,"score_spread":0.24235842431188462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1656389077","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":[0.008944848,0.000120233424,0.9858029,0.0015128406,0.00020855539,0.00055727793,0.000011149411,0.00013807246,0.0027041093],"genre_scores_gemma":[0.82699096,0.000048744645,0.1715887,0.00060775795,0.00009691161,0.00008523791,0.0000075583603,0.000026105798,0.0005479872],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918526,0.000002819071,0.00019005343,0.00018654151,0.0002775141,0.00015779384],"domain_scores_gemma":[0.9992229,0.000023112716,0.00016183457,0.00013025966,0.0004044468,0.000057492067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026222557,0.00009329687,0.00011655676,0.000067316716,0.00010635403,0.0001379919,0.00067925197,0.000018275323,0.0000022961588],"category_scores_gemma":[0.00012833712,0.00005999887,0.00004045055,0.00042715008,0.000035534787,0.00035357772,0.00022129857,0.000032700078,0.0000016336035],"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":[0.000028952405,0.0002120583,0.0024033627,0.0001689449,0.000085463646,1.2236166e-7,0.0030682608,0.0007315007,0.0051216017,0.97430307,0.0070352433,0.006841437],"study_design_scores_gemma":[0.0054413993,0.001120515,0.0006800156,0.000747427,0.00017637748,0.000045396548,0.0038682467,0.45422578,0.2367887,0.035179563,0.26070443,0.0010221543],"about_ca_topic_score_codex":0.0000067432675,"about_ca_topic_score_gemma":0.0000017713617,"teacher_disagreement_score":0.9391235,"about_ca_system_score_codex":0.000031194766,"about_ca_system_score_gemma":0.00005217185,"threshold_uncertainty_score":0.24466829},"labels":[],"label_agreement":null},{"id":"W1786535492","doi":"10.14778/2824032.2824111","title":"Gain control over your integration evaluations","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Semantic Web and Ontologies","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","funders":"","keywords":"Computer science; Data integration; Generality; Scalability; Information integration; Schema (genetic algorithms); System integration; Metadata; Reuse; Schema evolution; Data mining; Information retrieval; Database schema; Database; World Wide Web; Database design","score_opus":0.056228122232949214,"score_gpt":0.30801182340339606,"score_spread":0.25178370117044685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1786535492","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":[0.6659503,0.00092632655,0.2261869,0.037944995,0.0028207074,0.002394375,0.000008661082,0.00052643585,0.063241266],"genre_scores_gemma":[0.99325204,0.00000467191,0.0060453843,0.00036478767,0.000045677898,0.000038319595,2.094412e-7,0.0000034290879,0.0002454644],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990633,0.000010479803,0.00019098274,0.00016750039,0.00042108216,0.00014665915],"domain_scores_gemma":[0.9993159,0.000033637505,0.00015537413,0.00014711742,0.0003004488,0.00004749608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058083393,0.00008706969,0.00011985376,0.00005241963,0.00005839474,0.000081508595,0.0007167887,0.000030659397,0.0000045361426],"category_scores_gemma":[0.0003997622,0.000053096788,0.00006184859,0.00020032411,0.000040812054,0.00032439455,0.00016743719,0.00006965561,0.00001105069],"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":[0.000053005093,0.0003158306,0.021451253,0.000038135342,0.00010855327,6.6621243e-7,0.009570962,0.00029927128,0.07572036,0.809132,0.043990348,0.039319664],"study_design_scores_gemma":[0.0058654165,0.00061259564,0.059306465,0.00020348019,0.00015961105,0.00003947758,0.003830597,0.21147531,0.41096404,0.30146134,0.0054835025,0.0005981512],"about_ca_topic_score_codex":0.000054594206,"about_ca_topic_score_gemma":0.000004575882,"teacher_disagreement_score":0.5076706,"about_ca_system_score_codex":0.0000718287,"about_ca_system_score_gemma":0.00005628224,"threshold_uncertainty_score":0.21652241},"labels":[],"label_agreement":null},{"id":"W1828805609","doi":"10.14778/2733085.2733086","title":"Show me the money","year":2014,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":21,"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":"Computer science; Heuristics; Scalability; Profitability index; Revenue; Exploit; Maximization; Revenue model; Mathematical optimization; Database; Economics; Computer security","score_opus":0.012291976906149613,"score_gpt":0.2133033050567286,"score_spread":0.20101132815057898,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1828805609","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":[0.21074307,0.00089763635,0.16948712,0.14478213,0.0044097654,0.0048258663,0.000006188724,0.0017986549,0.4630496],"genre_scores_gemma":[0.9925765,0.000015699407,0.006243972,0.0005097343,0.00008115981,0.00007135856,5.3471346e-8,0.000007054861,0.0004944799],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99903476,0.000013340544,0.00021971851,0.00020908708,0.00032796306,0.0001951408],"domain_scores_gemma":[0.9993155,0.00004175715,0.00019819805,0.00030905078,0.00009738922,0.000038087386],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007191585,0.00011291549,0.00014217854,0.000034690685,0.00014315512,0.00013313629,0.0018561926,0.000032569988,0.000004435151],"category_scores_gemma":[0.00003764997,0.00005420928,0.000101263904,0.0001724182,0.000042272215,0.00020695887,0.000619037,0.00010738628,0.000008617345],"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":[0.0000031465622,0.000072211806,0.0036074873,0.000061547435,0.00004263168,8.213564e-8,0.0015143988,0.0000023299356,0.024808008,0.9011519,0.04224895,0.026487306],"study_design_scores_gemma":[0.00048061184,0.00024901357,0.005276378,0.00017097068,0.000027230562,0.000044916113,0.00025091475,0.012245134,0.68086404,0.119334884,0.1806956,0.00036030755],"about_ca_topic_score_codex":0.00006975286,"about_ca_topic_score_gemma":0.0000019806482,"teacher_disagreement_score":0.7818334,"about_ca_system_score_codex":0.000030072355,"about_ca_system_score_gemma":0.000009146096,"threshold_uncertainty_score":0.34492984},"labels":[],"label_agreement":null},{"id":"W1875516392","doi":"10.14778/2752939.2752950","title":"Viral marketing meets social advertising","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Optimization and Search Problems","field":"Computer Science","cited_by":62,"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":"Viral marketing; Leverage (statistics); Click-through rate; Computer science; Advertising; Online advertising; Regret; Context (archaeology); Host (biology); Social network (sociolinguistics); Social media; Display advertising; Business; World Wide Web; The Internet; Artificial intelligence","score_opus":0.025921147798563318,"score_gpt":0.25511025738176607,"score_spread":0.22918910958320277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1875516392","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":[0.30729544,0.000774723,0.060655292,0.08760607,0.0031998616,0.0033457219,0.0000084796975,0.001208893,0.53590554],"genre_scores_gemma":[0.9729325,0.000007718398,0.026052445,0.0002686141,0.000070780916,0.000015375625,2.0751449e-7,0.000008061623,0.000644298],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988138,0.000020139152,0.00021234243,0.00019721163,0.0005171964,0.00023929655],"domain_scores_gemma":[0.9994023,0.00002114957,0.000153683,0.00008414202,0.00025860436,0.00008014893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010091158,0.000091164584,0.00011385811,0.00005571134,0.00015294962,0.0001270083,0.0008413612,0.00003214479,0.00000606706],"category_scores_gemma":[0.00018544201,0.00006575007,0.000065328684,0.0002786363,0.00004796355,0.0004222389,0.0006255395,0.00009877778,0.0000069585644],"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":[0.00022269765,0.00066867005,0.0121728545,0.00043838026,0.0001918536,0.0000032595026,0.031960398,0.001167125,0.10475737,0.60758346,0.10050219,0.14033175],"study_design_scores_gemma":[0.010938481,0.0008171936,0.021005396,0.0009889329,0.000105981984,0.000112164154,0.004267505,0.3915859,0.35330355,0.0896806,0.124926336,0.002267994],"about_ca_topic_score_codex":0.000012717615,"about_ca_topic_score_gemma":4.684597e-7,"teacher_disagreement_score":0.6656371,"about_ca_system_score_codex":0.00008390748,"about_ca_system_score_gemma":0.000050049322,"threshold_uncertainty_score":0.26812103},"labels":[],"label_agreement":null},{"id":"W1967167578","doi":"10.14778/1453856.1453980","title":"Discovering data quality rules","year":2008,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":268,"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; Data quality; Consistency (knowledge bases); Context (archaeology); Quality (philosophy); Data mining; Data integrity; Set (abstract data type); Data consistency; Process (computing); Database; Artificial intelligence; Programming language; Engineering","score_opus":0.49777141101266814,"score_gpt":0.451736219472416,"score_spread":0.04603519154025215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967167578","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":[0.9511541,0.00012862953,0.00045843213,0.005143543,0.0004836817,0.00046454006,0.00031224947,0.00004861448,0.041806225],"genre_scores_gemma":[0.99422973,0.00008732842,0.0019098001,0.00033891847,0.00007437031,0.000012659445,0.000009695446,0.000007553263,0.003329965],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99658775,0.000030389752,0.00075386645,0.0005427183,0.0018482468,0.00023703698],"domain_scores_gemma":[0.9979997,0.00023210481,0.00051173725,0.0010212205,0.0001685729,0.00006665223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043975953,0.00013047698,0.0002713974,0.000084786334,0.00025556717,0.00014410127,0.0043056463,0.000028199831,0.000102604106],"category_scores_gemma":[0.0025366838,0.00007487221,0.00009972433,0.0003850528,0.00022391541,0.0010271574,0.0042868266,0.000101986094,0.00010806411],"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":[0.00017594465,0.0008405626,0.074812256,0.00021315133,0.00021673864,0.0000030715871,0.0062539536,0.00005269947,0.014850645,0.40627158,0.4563141,0.039995335],"study_design_scores_gemma":[0.0012760415,0.000097619464,0.19340204,0.00012766459,0.0000712369,0.000025424612,0.007961334,0.0005190978,0.03693907,0.11903248,0.6399669,0.000581099],"about_ca_topic_score_codex":0.00029214527,"about_ca_topic_score_gemma":0.00002114362,"teacher_disagreement_score":0.28723907,"about_ca_system_score_codex":0.000036563437,"about_ca_system_score_gemma":0.000028474376,"threshold_uncertainty_score":0.80010337},"labels":[],"label_agreement":null},{"id":"W1967348488","doi":"10.14778/1920841.1920978","title":"Identifying, attributing and describing spatial bursts","year":2010,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":43,"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":"Terabyte; Scalability; Computer science; Task (project management); Social media; Information retrieval; Scale (ratio); Data science; Data mining; World Wide Web; Database; Geography; Cartography","score_opus":0.02560125426761936,"score_gpt":0.2604515705919254,"score_spread":0.23485031632430606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967348488","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":[0.9953951,0.0001337295,0.00002791994,0.000722863,0.0003469228,0.00046648286,0.000026545245,0.00007111351,0.0028092891],"genre_scores_gemma":[0.9981066,0.000022431133,0.001350274,0.000126789,0.00017937493,0.00001942015,0.0000059156223,0.000019408792,0.00016979438],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9988023,0.000003946973,0.00027169863,0.00027296954,0.00037980248,0.00026925243],"domain_scores_gemma":[0.99925935,0.000027045651,0.0002135904,0.00016458998,0.0001988991,0.00013653691],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004011913,0.00014282341,0.00024418495,0.000060745107,0.000117914155,0.00004691757,0.00020702262,0.000051625953,0.000049222388],"category_scores_gemma":[0.00052376895,0.00010271234,0.00008702921,0.00014368689,0.00013419008,0.00012770646,0.00035221825,0.00026318783,0.000007993111],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000071259696,0.00008893235,0.4319229,0.00024496776,0.00006165592,0.000002125876,0.00031405734,1.4878927e-7,0.5555875,0.0012190281,0.0012163165,0.009271135],"study_design_scores_gemma":[0.002216688,0.00011521828,0.53886795,0.0006188931,0.00021908722,0.0001386382,0.00035492607,0.00024622914,0.45116684,0.0008454765,0.0049518733,0.00025820252],"about_ca_topic_score_codex":0.00013341222,"about_ca_topic_score_gemma":0.000022352353,"teacher_disagreement_score":0.106945,"about_ca_system_score_codex":0.00003790813,"about_ca_system_score_gemma":0.000033211258,"threshold_uncertainty_score":0.41884878},"labels":[],"label_agreement":null},{"id":"W1967654850","doi":"10.14778/1687627.1687642","title":"Measure-driven keyword-query expansion","year":2009,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":33,"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; Exploit; Pruning; Information retrieval; Query expansion; Web search query; Context (archaeology); Set (abstract data type); Process (computing); Domain (mathematical analysis); Measure (data warehouse); Focus (optics); Query optimization; Data mining; Word (group theory); Search engine; Mathematics","score_opus":0.012523221015441705,"score_gpt":0.21224724329768602,"score_spread":0.1997240222822443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967654850","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":[0.379091,0.0015743601,0.091732875,0.09179708,0.005961207,0.0062646675,0.00002768294,0.0024408484,0.42111027],"genre_scores_gemma":[0.9787016,0.000047868118,0.019623928,0.0006738421,0.000091438465,0.000014768483,8.436865e-7,0.0000065898694,0.0008391563],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986631,0.000005310395,0.00022438704,0.0003098115,0.0005431836,0.00025417228],"domain_scores_gemma":[0.9993754,0.000010340164,0.00016914059,0.00027867474,0.00011066001,0.00005576828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002935311,0.00013938549,0.0001494762,0.00008458587,0.000111996655,0.00014726708,0.001748166,0.000029317212,0.000006334734],"category_scores_gemma":[0.00003477958,0.00009365909,0.0000966987,0.0003897801,0.000030135054,0.0007735371,0.00054297876,0.00009895483,0.000018764424],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030941243,0.00059210946,0.0020950343,0.00009043943,0.000086635686,0.000003618088,0.0015525958,0.000048951606,0.11763148,0.40688083,0.056000836,0.41498655],"study_design_scores_gemma":[0.0038733108,0.0012303762,0.04921186,0.0010098192,0.0001691524,0.000043420718,0.0005796009,0.03699951,0.7104551,0.111288995,0.08345318,0.0016856694],"about_ca_topic_score_codex":0.000008529801,"about_ca_topic_score_gemma":4.4551524e-7,"teacher_disagreement_score":0.59961057,"about_ca_system_score_codex":0.000041307732,"about_ca_system_score_gemma":0.000014418463,"threshold_uncertainty_score":0.38193068},"labels":[],"label_agreement":null},{"id":"W1972924401","doi":"10.14778/1920841.1920947","title":"Building ranked mashups of unstructured sources with uncertain information","year":2010,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","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":"University of Waterloo","funders":"","keywords":"Mashup; Computer science; Ranking (information retrieval); Information retrieval; Rank (graph theory); Probabilistic logic; Information extraction; Semantics (computer science); Database; World Wide Web; Data mining; Web service; Artificial intelligence; Web modeling","score_opus":0.00427333096314046,"score_gpt":0.19202117821881115,"score_spread":0.1877478472556707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972924401","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":[0.9696986,0.00001918275,0.021152604,0.0015969527,0.00053821446,0.0007217533,0.0000101146725,0.000108694534,0.0061538615],"genre_scores_gemma":[0.9006141,0.0000038510634,0.099221386,0.000071256174,0.000027508739,0.000012874619,0.0000011910458,0.000003826257,0.00004403491],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990391,0.0000026121884,0.00024488277,0.00013691664,0.00041251926,0.00016395647],"domain_scores_gemma":[0.9992526,0.000014445918,0.0003580128,0.00019598169,0.00014655433,0.000032410917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027964904,0.000110978515,0.00013315963,0.000107592845,0.00007544364,0.00012562702,0.001261974,0.000027921542,0.000006379492],"category_scores_gemma":[0.000033359804,0.0000660921,0.00004452606,0.00037600537,0.000081799044,0.0013094232,0.00043681855,0.00011654724,0.000001447988],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000621849,0.00008510726,0.0072257947,0.00045912643,0.0001445296,3.4302906e-7,0.0033179729,0.00017614962,0.12516293,0.77569836,0.0016190178,0.08604848],"study_design_scores_gemma":[0.00246747,0.00026361644,0.010192231,0.00021664171,0.000084289146,0.000021852695,0.0007204661,0.016674226,0.9236752,0.0260879,0.019133717,0.00046240893],"about_ca_topic_score_codex":0.00004070364,"about_ca_topic_score_gemma":0.0000022963088,"teacher_disagreement_score":0.7985122,"about_ca_system_score_codex":0.000012318,"about_ca_system_score_gemma":0.000016822098,"threshold_uncertainty_score":0.26951575},"labels":[],"label_agreement":null},{"id":"W1980185632","doi":"10.14778/2350229.2350241","title":"Fundamentals of order dependencies","year":2012,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":53,"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":"Functional dependency; Lexicographical order; Axiom; Dependency theory (database theory); Tuple; Computer science; Inference; Dependency (UML); Set (abstract data type); Query optimization; Theoretical computer science; Mathematics; Data mining; Artificial intelligence; Discrete mathematics; Relational database; Programming language; Combinatorics","score_opus":0.015635755890120978,"score_gpt":0.22162146837522673,"score_spread":0.20598571248510575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980185632","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":[0.82814556,0.0017846138,0.017046688,0.004923457,0.00317745,0.0020185167,0.00003455075,0.00028712736,0.14258204],"genre_scores_gemma":[0.97913486,0.00003099132,0.019777272,0.000109480214,0.00004753213,0.000016364702,4.9142164e-7,0.0000050414183,0.00087797845],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99898946,0.000003619679,0.00021492058,0.00013810115,0.0004111539,0.00024275131],"domain_scores_gemma":[0.9994479,0.000015293637,0.00021234056,0.0001838829,0.00009612678,0.00004449002],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003904561,0.000095770396,0.00013007599,0.00006246886,0.000055202614,0.00004925135,0.0012357677,0.000018301416,0.000025191275],"category_scores_gemma":[0.000033960787,0.00006272663,0.000061294704,0.00035248187,0.00005517242,0.00095494214,0.0010970023,0.0000500688,0.000012188516],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014348312,0.0008212351,0.079185225,0.00038841166,0.00021364352,2.5815467e-7,0.003874838,0.000006572421,0.08988824,0.7600956,0.019957485,0.045554142],"study_design_scores_gemma":[0.0008333872,0.00014774803,0.025610078,0.00013766134,0.00006655538,0.000010800265,0.0011657674,0.000934089,0.9305962,0.007928,0.03221744,0.00035227608],"about_ca_topic_score_codex":0.000023795854,"about_ca_topic_score_gemma":4.3649774e-7,"teacher_disagreement_score":0.84070796,"about_ca_system_score_codex":0.000025184052,"about_ca_system_score_gemma":0.000009048292,"threshold_uncertainty_score":0.25579175},"labels":[],"label_agreement":null},{"id":"W1981001739","doi":"10.14778/1454159.1454200","title":"Semandaq","year":2008,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada)","funders":"","keywords":"Computer science; Relational database; SQL; Quality (philosophy); Database; Data mining; User interface; Interface (matter); Data quality; Programming language; Engineering; Operating system; Metric (unit)","score_opus":0.19753170774097992,"score_gpt":0.36462387965471404,"score_spread":0.16709217191373413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981001739","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":[0.80068356,0.000118321805,0.00017972747,0.008735856,0.00062021887,0.0005853546,0.000023982971,0.000056114586,0.18899688],"genre_scores_gemma":[0.98654854,0.000048459333,0.0005943238,0.00061057153,0.00005098256,0.000018157654,4.494238e-7,0.0000051787465,0.012123348],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99758977,0.000012106426,0.00046608812,0.0002824942,0.001462681,0.00018688786],"domain_scores_gemma":[0.9990459,0.000106558204,0.0003029659,0.00027634916,0.00021190692,0.000056326575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017533688,0.00009620295,0.00018751732,0.000098011194,0.00019713928,0.000065729495,0.0014223708,0.000025135536,0.00020311882],"category_scores_gemma":[0.00086513394,0.000052640884,0.00013033643,0.0004938522,0.00016242663,0.0003044075,0.000753782,0.000075279604,0.00016661463],"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":[0.00006856683,0.00036302433,0.023082986,0.000051659805,0.00007718274,0.0000022745867,0.0046289642,0.000022125005,0.010050088,0.19339785,0.7510016,0.017253686],"study_design_scores_gemma":[0.0008672022,0.0001264121,0.032872606,0.000052078558,0.00003461584,0.000035094992,0.003185166,0.0001226683,0.09423654,0.11127891,0.756931,0.00025773153],"about_ca_topic_score_codex":0.000039089464,"about_ca_topic_score_gemma":0.0000035280275,"teacher_disagreement_score":0.18586498,"about_ca_system_score_codex":0.000028662422,"about_ca_system_score_gemma":0.000017523329,"threshold_uncertainty_score":0.26431423},"labels":[],"label_agreement":null},{"id":"W1981578383","doi":"10.14778/2536336.2536345","title":"Discovering linkage points over web data","year":2013,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Toronto","funders":"","keywords":"Computer science; Schema matching; Schema (genetic algorithms); Data integration; Information retrieval; Data mining; Linked data; Linkage (software); Star schema; Database schema; Semi-structured model; Semantic Web; Database design","score_opus":0.1633565029719125,"score_gpt":0.3784563459656941,"score_spread":0.2150998429937816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981578383","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":[0.9129798,0.00011415341,0.00022802861,0.016537564,0.0009450997,0.0013378053,0.00024175725,0.00006987094,0.06754591],"genre_scores_gemma":[0.99342567,0.000044397417,0.0012500599,0.00085167494,0.000091476584,0.000033784854,0.000006921232,0.000010999965,0.004285006],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969058,0.000018836261,0.0006434542,0.000578454,0.0015704246,0.00028303842],"domain_scores_gemma":[0.99807376,0.00017455778,0.00043601185,0.0010589286,0.0001717631,0.00008495867],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0028414004,0.00014930883,0.00024101562,0.00011189501,0.00012964274,0.0005334381,0.0043639434,0.00003589757,0.0010719707],"category_scores_gemma":[0.0016988288,0.000083659,0.0000911408,0.000453439,0.00011373502,0.0018153233,0.0054029427,0.00013048263,0.00046066876],"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":[0.000027637863,0.00034791208,0.017461369,0.00012628308,0.00012641019,6.487209e-7,0.0012085491,0.000013935286,0.028694225,0.07321998,0.84908104,0.029692033],"study_design_scores_gemma":[0.0017917813,0.00013344384,0.08077819,0.0003077345,0.000113078524,0.0000070881465,0.0062133013,0.006896957,0.033514403,0.21411501,0.6554526,0.0006764249],"about_ca_topic_score_codex":0.0002499803,"about_ca_topic_score_gemma":0.000018090554,"teacher_disagreement_score":0.19362843,"about_ca_system_score_codex":0.00003873338,"about_ca_system_score_gemma":0.000021513402,"threshold_uncertainty_score":0.9998412},"labels":[],"label_agreement":null},{"id":"W1982177147","doi":"10.14778/2002974.2002976","title":"gStore","year":2011,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":263,"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":"SPARQL; RDF; Computer science; Information retrieval; Named graph; RDF Schema; Linked data; RDF query language; Scalability; RDF/XML; Pruning; Database; Semantic Web; Web search query; Web query classification; Search engine","score_opus":0.03354416418142819,"score_gpt":0.19815301334233806,"score_spread":0.16460884916090987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982177147","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":[0.6743295,0.0004640163,0.00353139,0.0031039817,0.0015004335,0.00059409766,0.0000010880682,0.00037904095,0.31609645],"genre_scores_gemma":[0.98174983,0.000011672171,0.017731292,0.00015436434,0.000021749895,0.000012631748,1.87641e-8,0.0000031928835,0.00031527228],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99934673,0.0000021601386,0.00013459065,0.00016141371,0.00019486078,0.00016024844],"domain_scores_gemma":[0.99961615,0.000010437947,0.00010882625,0.00015915094,0.00007678627,0.00002862939],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014435839,0.00007600151,0.00009837752,0.000034123474,0.0000550835,0.000023183224,0.001268918,0.000024977893,0.000012790261],"category_scores_gemma":[0.000042355165,0.000045043107,0.000065656095,0.00015739884,0.000055011507,0.00019735086,0.00044846477,0.00005672749,0.000013021169],"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":[0.000011234948,0.00015231427,0.032722227,0.00005737561,0.000040834282,0.0000010734827,0.006593833,3.7383558e-7,0.016664065,0.92401624,0.006840174,0.01290024],"study_design_scores_gemma":[0.00039847565,0.00015414663,0.08009625,0.00006930476,0.000020649282,0.000029664852,0.0005568363,0.00036258213,0.82067806,0.092568964,0.004855524,0.00020954416],"about_ca_topic_score_codex":0.000050670944,"about_ca_topic_score_gemma":0.0000013771727,"teacher_disagreement_score":0.8314473,"about_ca_system_score_codex":0.000018319892,"about_ca_system_score_gemma":0.000012993604,"threshold_uncertainty_score":0.23579866},"labels":[],"label_agreement":null},{"id":"W1986041862","doi":"10.14778/1920841.1920982","title":"An access cost-aware approach for object retrieval over multiple sources","year":2010,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","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 Toronto","funders":"","keywords":"Computer science; Overhead (engineering); Probabilistic logic; Object (grammar); Source code; Selection (genetic algorithm); Data mining; Information retrieval; Data source; Database; Artificial intelligence; Programming language","score_opus":0.024767759603829508,"score_gpt":0.279069790039691,"score_spread":0.2543020304358615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986041862","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":[0.8018389,0.00005656899,0.18005764,0.0015751431,0.0023067323,0.006093999,0.0001381389,0.0005717958,0.007361093],"genre_scores_gemma":[0.9644738,0.0000058117303,0.034681268,0.00018594254,0.00019602406,0.00011708327,0.000011099332,0.00001563344,0.00031334543],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99854624,0.0000047350404,0.00023061017,0.00046606798,0.00042885507,0.00032349338],"domain_scores_gemma":[0.99910796,0.00004101667,0.00023525467,0.00037474846,0.00015805088,0.00008299716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005437776,0.00017243047,0.00017610521,0.00009254317,0.00020796753,0.000563176,0.0035090633,0.000054836783,0.000007937582],"category_scores_gemma":[0.000093269584,0.00011796501,0.00010995419,0.0003525133,0.000073391224,0.0016927038,0.0010617637,0.00016808786,0.0000015920475],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000665523,0.004382917,0.18806846,0.0016814187,0.0007031418,0.0000021900673,0.0072604846,0.00051865866,0.37698635,0.20731589,0.05414492,0.15827003],"study_design_scores_gemma":[0.0031262864,0.00035182145,0.02122373,0.000051651867,0.00008861919,0.000008461264,0.0004661838,0.45658672,0.4877375,0.0051413933,0.02447739,0.0007402235],"about_ca_topic_score_codex":0.00003986216,"about_ca_topic_score_gemma":0.0000036846845,"teacher_disagreement_score":0.45606807,"about_ca_system_score_codex":0.000022338265,"about_ca_system_score_gemma":0.000020435977,"threshold_uncertainty_score":0.6520771},"labels":[],"label_agreement":null},{"id":"W1991635064","doi":"10.14778/2047485.2047492","title":"A data-based approach to social influence maximization","year":2011,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":426,"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":"Maximization; Submodular set function; Computer science; Scalability; Perspective (graphical); Set (abstract data type); Function (biology); Expectation–maximization algorithm; Social graph; Social network (sociolinguistics); Mathematical optimization; Theoretical computer science; Artificial intelligence; Social media; Mathematics; Maximum likelihood; World Wide Web; Statistics","score_opus":0.056720518850135716,"score_gpt":0.26189961063934397,"score_spread":0.20517909178920826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991635064","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":[0.74912,0.000020389363,0.06211278,0.00059285323,0.000079506994,0.0020141196,0.00017604673,0.00023726698,0.18564704],"genre_scores_gemma":[0.9810469,1.9981306e-7,0.018635739,0.00008277109,0.000078599835,0.000078779,0.000014371509,0.00001094837,0.00005167943],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99918824,0.0000051968454,0.00020682316,0.00023783698,0.0002049617,0.00015692355],"domain_scores_gemma":[0.9994437,0.0000059393838,0.00018271556,0.00019612568,0.00013637182,0.00003515072],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018976523,0.00010783131,0.00014790401,0.00005497216,0.00010261179,0.000026275402,0.0008376284,0.000016966625,0.00003992527],"category_scores_gemma":[0.000007701671,0.00008083672,0.000070374605,0.00033763866,0.000039483028,0.00012908899,0.00041742355,0.000071782495,0.0000035258686],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025969197,0.003268426,0.31139603,0.00023793227,0.000737233,1.195329e-7,0.0076476224,0.0014337575,0.039301097,0.5405243,0.058793392,0.03640039],"study_design_scores_gemma":[0.0027206317,0.00035439327,0.116854966,0.00032893676,0.001238319,0.0000017043022,0.002716396,0.059319235,0.66323596,0.120174974,0.031049574,0.0020048912],"about_ca_topic_score_codex":0.00017181116,"about_ca_topic_score_gemma":8.928153e-7,"teacher_disagreement_score":0.62393486,"about_ca_system_score_codex":0.00002244541,"about_ca_system_score_gemma":0.000018254026,"threshold_uncertainty_score":0.32964256},"labels":[],"label_agreement":null},{"id":"W2000482994","doi":"10.14778/1978665.1978666","title":"Similarity join size estimation using locality sensitive hashing","year":2011,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":37,"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":"Locality-sensitive hashing; Joins; Nearest neighbor search; Similarity (geometry); Join (topology); Computer science; Generalization; Data mining; Hash function; Range (aeronautics); Sampling (signal processing); Set (abstract data type); Pattern recognition (psychology); Algorithm; Artificial intelligence; Mathematics; Hash table","score_opus":0.05016504780970029,"score_gpt":0.27647349014964706,"score_spread":0.22630844233994676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000482994","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":[0.10295758,0.000032628795,0.8922403,0.00029328855,0.00012808303,0.00046930482,0.0000026301557,0.00021988651,0.0036563026],"genre_scores_gemma":[0.7017274,0.000007091325,0.29805863,0.00016154339,0.000014646317,0.000005130231,8.272999e-8,0.000005910269,0.000019577186],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988599,0.00001338373,0.0002827981,0.0002899039,0.00032790712,0.00022611143],"domain_scores_gemma":[0.99912316,0.00005413772,0.00030158553,0.0001843895,0.00028371398,0.000053000807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005044481,0.00014414615,0.00018156279,0.000043013028,0.00015677995,0.00006344918,0.0006155613,0.000050821596,0.000003983692],"category_scores_gemma":[0.00039806266,0.00010631476,0.00009343072,0.00035019402,0.000094366434,0.0010064009,0.0005686994,0.0001632413,0.0000016777918],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013869414,0.000665236,0.005298291,0.00041448392,0.00013665395,0.000009054312,0.012298182,0.00012783434,0.74390066,0.14023346,0.00073833414,0.09603911],"study_design_scores_gemma":[0.0001313104,0.00005314974,0.0019643772,0.00009504801,0.000015186567,0.000014508719,0.00008529372,0.02053291,0.93153393,0.045409326,0.00004312667,0.00012183422],"about_ca_topic_score_codex":0.00009585593,"about_ca_topic_score_gemma":7.5088985e-7,"teacher_disagreement_score":0.59876984,"about_ca_system_score_codex":0.00011851545,"about_ca_system_score_gemma":0.000029877618,"threshold_uncertainty_score":0.433539},"labels":[],"label_agreement":null},{"id":"W2000516574","doi":"10.14778/1920841.1920919","title":"Small domain randomization","year":2010,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":25,"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; Table (database); Partition (number theory); Randomization; Domain (mathematical analysis); Key (lock); Algorithm; Data mining; Theoretical computer science; Mathematics; Combinatorics","score_opus":0.01725406313730675,"score_gpt":0.22441536667375253,"score_spread":0.2071613035364458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000516574","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":[0.83625597,0.0000871551,0.05668096,0.08286729,0.0020875712,0.0014315958,0.000009458374,0.001097356,0.019482628],"genre_scores_gemma":[0.6307588,0.00001676637,0.36893332,0.00012568658,0.000040578077,0.000050459872,5.3733515e-7,0.000008399908,0.00006541033],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989244,0.0000056511694,0.00024151766,0.00030163978,0.0002966894,0.00023012863],"domain_scores_gemma":[0.9976994,0.000056512486,0.00023737688,0.0018373135,0.00013316533,0.00003622552],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0006550685,0.00012005928,0.00015088383,0.000084473395,0.00010594483,0.00010461769,0.02104012,0.00007983016,0.000009300281],"category_scores_gemma":[0.006470121,0.00008085882,0.00007176973,0.00040672184,0.00011035691,0.0003488751,0.037215516,0.0002618044,0.000008616575],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057042373,0.00018202903,0.0061349445,0.0000884747,0.000056613088,7.259899e-7,0.00037959157,0.0000032737512,0.5762413,0.30374077,0.09243409,0.020681119],"study_design_scores_gemma":[0.0013275149,0.00002817216,0.0008700642,0.00003171349,0.000007906015,0.000014040939,0.000029948656,0.0040377867,0.43131885,0.5585514,0.0036505598,0.00013206889],"about_ca_topic_score_codex":0.000016374246,"about_ca_topic_score_gemma":0.0000047647272,"teacher_disagreement_score":0.31225237,"about_ca_system_score_codex":0.00003057057,"about_ca_system_score_gemma":0.000022773425,"threshold_uncertainty_score":0.9842565},"labels":[],"label_agreement":null},{"id":"W2004580781","doi":"10.14778/1920841.1921038","title":"Peer coordination through distributed triggers","year":2010,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Peer-to-Peer Network Technologies","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; University of Ottawa","funders":"","keywords":"Computer science; Consistency (knowledge bases); Distributed computing; Distributed database; Peer-to-peer; Set (abstract data type); Distributed management; Semantics (computer science); Eventual consistency; Database; Data consistency; Programming language; Consistency model","score_opus":0.011311263184876547,"score_gpt":0.23842975324750668,"score_spread":0.22711849006263013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004580781","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":[0.6692074,0.00012786822,0.05649957,0.23238716,0.0039571477,0.0024193472,0.0000494913,0.0020738791,0.033278175],"genre_scores_gemma":[0.96089756,0.0000049589353,0.0378172,0.00021251386,0.000056046618,0.000075235235,0.0000014017213,0.000009222846,0.00092584634],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99835134,0.000003594605,0.00025845037,0.0003443053,0.0007136211,0.00032870905],"domain_scores_gemma":[0.99879795,0.000039193106,0.00020505428,0.00034731562,0.00055714085,0.000053336556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045793047,0.00016086201,0.00017645904,0.00006367295,0.00012827676,0.0001368705,0.0023089931,0.00009275512,0.0000046630153],"category_scores_gemma":[0.00057135185,0.00011295556,0.00009011338,0.0007468763,0.00009835423,0.00046493884,0.0009773175,0.0002908258,0.00001352179],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016675058,0.0001776133,0.0018005676,0.00003421216,0.000053894797,7.9765607e-7,0.0013006884,0.000056773675,0.16423799,0.58127576,0.22838788,0.02265712],"study_design_scores_gemma":[0.00059125456,0.00013193472,0.002982527,0.00004011631,0.000021491604,0.000020087347,0.00016660898,0.00225349,0.7214693,0.04834258,0.22366486,0.0003157622],"about_ca_topic_score_codex":0.000048637605,"about_ca_topic_score_gemma":0.0000051037914,"teacher_disagreement_score":0.5572313,"about_ca_system_score_codex":0.00007512622,"about_ca_system_score_gemma":0.000023526394,"threshold_uncertainty_score":0.46061942},"labels":[],"label_agreement":null},{"id":"W2005480575","doi":"10.14778/1920841.1920847","title":"Database replication","year":2010,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Branco Weiss Fellowship – Society in Science; Eidgenössische Technische Hochschule Zürich; McGill University","keywords":"Computer science; Scalability; Replication (statistics); Distributed computing; Eventual consistency; Database transaction; Consistency (knowledge bases); Fault tolerance; Overhead (engineering); Distributed database; Cloud computing; Database; Transaction processing; Data consistency; Weak consistency; Concurrency control; Strong consistency; Consistency model; Operating system; Artificial intelligence","score_opus":0.009657613492116489,"score_gpt":0.23346822183864122,"score_spread":0.22381060834652472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005480575","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":[0.89625865,0.00016090258,0.023791946,0.011953245,0.002896202,0.0015003909,0.00006310275,0.00037811618,0.06299744],"genre_scores_gemma":[0.9921904,0.000004319895,0.0072603566,0.000112355476,0.00005853337,0.000040599138,0.000001144497,0.000003789894,0.00032848434],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991353,0.0000020664345,0.00019356841,0.00027469377,0.0002575691,0.00013680889],"domain_scores_gemma":[0.99909407,0.000010532557,0.00018722733,0.00050940696,0.00015440528,0.000044338823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036841407,0.00007403183,0.00008892407,0.00002464716,0.000078786594,0.00007130908,0.0012147889,0.000028033077,0.0000053398585],"category_scores_gemma":[0.00008963555,0.000048836828,0.0000490164,0.00024914218,0.00003430751,0.0003265763,0.00032043146,0.00012614111,0.000012298986],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025242905,0.00006744034,0.0017932792,0.000035981975,0.000007845022,1.1299123e-7,0.00018206701,0.0000010108998,0.56899005,0.4119978,0.008593479,0.008328416],"study_design_scores_gemma":[0.0005003724,0.000043394626,0.010081649,0.00009178728,0.000011022573,0.000041156734,0.000055056116,0.0056377416,0.8418312,0.0067811683,0.13470244,0.00022302712],"about_ca_topic_score_codex":0.000033878514,"about_ca_topic_score_gemma":0.000002453319,"teacher_disagreement_score":0.40521663,"about_ca_system_score_codex":0.00001326218,"about_ca_system_score_gemma":0.000017152328,"threshold_uncertainty_score":0.22574002},"labels":[],"label_agreement":null},{"id":"W2005499394","doi":"10.14778/2168651.2168658","title":"Dense subgraph maintenance under streaming edge weight updates for real-time story identification","year":2012,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":172,"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; Enhanced Data Rates for GSM Evolution; Identification (biology); Social media; Globe; Scale (ratio); Point (geometry); Data science; Edge device; Range (aeronautics); Social network (sociolinguistics); World Wide Web; Artificial intelligence; Geography; Mathematics; Engineering","score_opus":0.013209024702018898,"score_gpt":0.23841514356549856,"score_spread":0.22520611886347966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005499394","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":[0.7876935,0.0008398109,0.18836561,0.01246155,0.0018182254,0.0033662606,0.00021854501,0.00060893677,0.0046275347],"genre_scores_gemma":[0.9329337,0.00009321036,0.06498047,0.00009990918,0.00016320363,0.00032919573,0.000011567745,0.000018684994,0.0013700759],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99891824,0.000006334805,0.00024696894,0.00028128084,0.00022494348,0.00032222198],"domain_scores_gemma":[0.9990567,0.00007127695,0.00029692787,0.0003005978,0.00019821983,0.000076308424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062210683,0.00012341753,0.00013127761,0.00007071628,0.00023877677,0.000095141484,0.00097094104,0.000036373902,0.0000037097977],"category_scores_gemma":[0.000042344993,0.000094084855,0.000087004024,0.00028709412,0.00006796048,0.0006674593,0.00027032127,0.00007253347,0.000019318],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012922139,0.00041721473,0.0021344253,0.00011582593,0.000091724665,5.4653196e-8,0.0018796637,0.000008658285,0.34711704,0.55318564,0.048699833,0.046337],"study_design_scores_gemma":[0.001516584,0.0001499862,0.07202521,0.00032760913,0.00020200337,0.000037022048,0.001259285,0.034459542,0.79720616,0.04403552,0.047816083,0.0009650009],"about_ca_topic_score_codex":0.000018345174,"about_ca_topic_score_gemma":6.2982417e-7,"teacher_disagreement_score":0.50915015,"about_ca_system_score_codex":0.000077047065,"about_ca_system_score_gemma":0.000021820086,"threshold_uncertainty_score":0.3836669},"labels":[],"label_agreement":null},{"id":"W2006568248","doi":"10.14778/1920841.1921043","title":"Transforming XML documents as schemas evolve","year":2010,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"DNA and Biological Computing","field":"Biochemistry, Genetics and Molecular Biology","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":"IBM (Canada); York University","funders":"","keywords":"XML Schema Editor; Computer science; Streaming XML; XML validation; Document Structure Description; Efficient XML Interchange; XML database; XML Schema (W3C); XSLT; Information retrieval; cXML; XML Encryption; RELAX NG; Programming language; Database; XML; World Wide Web","score_opus":0.006265382445630607,"score_gpt":0.23777636910250835,"score_spread":0.23151098665687775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006568248","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":[0.972853,0.00007057014,0.000017216922,0.00031926797,0.0002204337,0.00025449364,0.000002155591,0.000012819287,0.026250014],"genre_scores_gemma":[0.9977567,0.000026420905,0.0010894632,0.00021388568,0.00017144324,0.000017217993,0.0000031578554,0.000009297639,0.0007124104],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991788,0.0000030004724,0.00019008454,0.00024020956,0.00016259102,0.00022530237],"domain_scores_gemma":[0.99962974,0.0000056923222,0.00010950533,0.00010224275,0.000095402094,0.000057410685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002095124,0.000129423,0.000114595176,0.000017735676,0.000097391676,0.000020266682,0.00035024263,0.00010900528,0.000025495665],"category_scores_gemma":[0.00010457504,0.000079202306,0.00013296731,0.000077357174,0.00008317958,0.0000055794612,0.00021332563,0.00015374948,0.000008509527],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029417968,0.000048575235,0.00396922,0.000019050953,0.00002717036,1.0965937e-7,0.000035427955,5.700991e-7,0.9911987,0.002059731,0.00031607813,0.0022959085],"study_design_scores_gemma":[0.00030945346,0.00016649539,0.00059205084,0.0000199748,0.0000149878815,0.00001255202,0.0000678437,0.0000062323124,0.9552104,0.0007575551,0.0427355,0.00010695188],"about_ca_topic_score_codex":0.00001281019,"about_ca_topic_score_gemma":0.0000021638382,"teacher_disagreement_score":0.04241942,"about_ca_system_score_codex":0.0000073391184,"about_ca_system_score_gemma":0.00001880025,"threshold_uncertainty_score":0.32297763},"labels":[],"label_agreement":null},{"id":"W2014888296","doi":"10.14778/1920841.1921003","title":"TRAMP","year":2010,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":31,"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":"Provenance; Computer science; Schema (genetic algorithms); Transformation (genetics); Debugging; Tracing; Tramp; Suite; Information retrieval; Programming language; Database","score_opus":0.07102342555161244,"score_gpt":0.3438698995370234,"score_spread":0.27284647398541095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014888296","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":[0.9066228,0.000012220417,0.00008054212,0.0035909398,0.0027178465,0.00027173714,0.000007740257,0.0000437708,0.0866524],"genre_scores_gemma":[0.9903229,0.000001043329,0.001619519,0.00016505481,0.00009077456,0.000008170529,2.8684886e-7,0.0000047782705,0.0077874567],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99745244,0.000006225912,0.00044041674,0.00043973755,0.0014506106,0.00021055674],"domain_scores_gemma":[0.9986749,0.00015424157,0.00029524477,0.0005110643,0.00029405215,0.00007047343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038644255,0.00009445004,0.00014510284,0.00013699943,0.0001697291,0.00031576326,0.0021953697,0.000029177625,0.00039346243],"category_scores_gemma":[0.0020251677,0.000050517152,0.00012795215,0.0007446412,0.00014235903,0.00018791965,0.0008500804,0.0001617018,0.00014254816],"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":[0.000025639993,0.00027155128,0.027262358,0.000020153171,0.000032927335,4.2232645e-7,0.0010639763,0.000025121522,0.17062916,0.1453754,0.47786173,0.17743155],"study_design_scores_gemma":[0.0006440273,0.0000660258,0.05004142,0.00003479991,0.00003295152,0.000015064757,0.0013599801,0.002072644,0.14955658,0.13630393,0.6596014,0.00027119124],"about_ca_topic_score_codex":0.000024121387,"about_ca_topic_score_gemma":0.000009241057,"teacher_disagreement_score":0.18173964,"about_ca_system_score_codex":0.0000117051295,"about_ca_system_score_gemma":0.000017022332,"threshold_uncertainty_score":0.43081376},"labels":[],"label_agreement":null},{"id":"W2022740398","doi":"10.14778/1880172.1880173","title":"Generating efficient execution plans for vertically partitioned XML databases","year":2010,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":26,"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; Query plan; Scalability; Database; Query optimization; XML database; Sargable; Distributed database; XML; Online aggregation; Relational database; Distributed computing; Information retrieval; Web search query; Search engine; Operating system","score_opus":0.0174271781966315,"score_gpt":0.25235560063649676,"score_spread":0.23492842243986525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022740398","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":[0.312201,0.000037543137,0.68339896,0.0011785035,0.0012878455,0.0009178493,0.0001877612,0.00012185447,0.00066867715],"genre_scores_gemma":[0.784994,0.0000037298553,0.21446414,0.0001346182,0.00015258056,0.00017550788,0.000008562699,0.0000082305205,0.000058651774],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989457,0.0000039550923,0.0002782806,0.00027716928,0.00026446587,0.00023042255],"domain_scores_gemma":[0.9992994,0.00005563816,0.00017082418,0.00023074675,0.00018507785,0.000058326405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003160008,0.000113632006,0.00013214214,0.00003440803,0.00024658372,0.00004357004,0.0003866108,0.000023525841,0.000004766953],"category_scores_gemma":[0.00022137741,0.000076741635,0.00006810929,0.00013858081,0.000063189735,0.00031529227,0.00029693326,0.000092924296,0.0000029813104],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001098265,0.00005921365,0.00013625255,0.00005541117,0.000009006019,1.0929074e-7,0.00019954129,0.0002457767,0.48701692,0.5104063,0.00064501737,0.0012154717],"study_design_scores_gemma":[0.0006501855,0.00010183688,0.0005226831,0.00012200491,0.000022467773,0.000016490347,0.00016368064,0.085192226,0.88141394,0.0012112939,0.030348225,0.00023497574],"about_ca_topic_score_codex":0.000017834274,"about_ca_topic_score_gemma":0.000013943318,"teacher_disagreement_score":0.509195,"about_ca_system_score_codex":0.000021665675,"about_ca_system_score_gemma":0.000032420267,"threshold_uncertainty_score":0.3129433},"labels":[],"label_agreement":null},{"id":"W2033486966","doi":"10.14778/2095686.2095695","title":"Mining flipping correlations from large datasets with taxonomies","year":2011,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":28,"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 Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Abstraction; Computer science; Range (aeronautics); Correlation; Data mining; Abstraction layer; Pattern recognition (psychology); Algorithm; Artificial intelligence; Theoretical computer science; Mathematics; Programming language","score_opus":0.029882836731726446,"score_gpt":0.21506378199320536,"score_spread":0.1851809452614789,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033486966","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":[0.61757475,0.00035220303,0.33613077,0.0029001613,0.0008648675,0.001935575,0.0018677504,0.0005833824,0.037790515],"genre_scores_gemma":[0.66767305,0.000007705149,0.33193833,0.00011268758,0.000038803773,0.00009576897,0.000026363963,0.000008159477,0.000099112185],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991634,0.0000029467567,0.0001888617,0.00027856315,0.00017963226,0.00018663202],"domain_scores_gemma":[0.9993396,0.000033039214,0.00021358456,0.00030026448,0.00006446063,0.000049075454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014846135,0.00010580423,0.00011388073,0.00004388915,0.00020379266,0.000076776436,0.001091684,0.000022849004,0.00001759401],"category_scores_gemma":[0.000025198246,0.000070886446,0.00003169089,0.00025469984,0.00004917832,0.00052823755,0.0005648265,0.000077822886,0.00001079039],"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":[0.00005595723,0.0014404126,0.119315445,0.00010054048,0.00054343627,0.0000032485602,0.03410815,0.00003404407,0.01173665,0.66816187,0.08725122,0.07724899],"study_design_scores_gemma":[0.0064002154,0.00088913634,0.19831,0.0019088099,0.0005879712,0.00013477936,0.014354211,0.18360846,0.29067704,0.02751804,0.27284214,0.0027692094],"about_ca_topic_score_codex":0.00016390347,"about_ca_topic_score_gemma":0.000010235194,"teacher_disagreement_score":0.64064384,"about_ca_system_score_codex":0.000022697917,"about_ca_system_score_gemma":0.00002359841,"threshold_uncertainty_score":0.28906652},"labels":[],"label_agreement":null},{"id":"W2056191114","doi":"10.14778/1920841.1921016","title":"MEET DB2","year":2010,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","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":"IBM (Canada)","funders":"","keywords":"Computer science; Database; XML; Data migration; Source code; Executable; Process (computing); Software engineering; Operating system","score_opus":0.004885213329562108,"score_gpt":0.20289898918943194,"score_spread":0.19801377585986984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056191114","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":[0.7909763,0.00028922566,0.06152289,0.010531649,0.006275679,0.001719021,0.000045928176,0.0005929859,0.1280463],"genre_scores_gemma":[0.9255304,0.0000064863334,0.07364973,0.00014247159,0.00009565694,0.000033909928,2.2723547e-7,0.0000067590613,0.0005343948],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99917185,0.0000020351724,0.00018129568,0.00020432229,0.00026511808,0.000175355],"domain_scores_gemma":[0.99941367,0.000016260488,0.00015828841,0.00024860553,0.00011395736,0.00004921587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021576065,0.00009485729,0.00011647084,0.000033694043,0.000098761775,0.000032656753,0.0007621287,0.000027077336,0.000009794278],"category_scores_gemma":[0.00006919203,0.000058282087,0.00006074387,0.00019140095,0.00006343046,0.00045876423,0.000545493,0.00010966939,0.000008783582],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017361031,0.00002106378,0.0006496258,0.000021735697,0.0000062175204,1.4524322e-7,0.00023354596,9.04279e-7,0.17402548,0.8217029,0.0018040177,0.0015326157],"study_design_scores_gemma":[0.0003353493,0.0000535505,0.0015149605,0.00006029967,0.000007826334,0.000039534207,0.00012785893,0.0004827611,0.75651187,0.019543683,0.22112325,0.00019903987],"about_ca_topic_score_codex":0.000029742503,"about_ca_topic_score_gemma":0.0000097182365,"teacher_disagreement_score":0.80215925,"about_ca_system_score_codex":0.00001190885,"about_ca_system_score_gemma":0.00001853044,"threshold_uncertainty_score":0.23766744},"labels":[],"label_agreement":null},{"id":"W2058488627","doi":"10.14778/1687627.1687715","title":"Improved search for socially annotated data","year":2009,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":14,"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; Ranking (information retrieval); Scalability; Information retrieval; Annotation; Resource (disambiguation); Process (computing); Data mining; Similarity (geometry); Probabilistic logic; Cluster analysis; Machine learning; Database; Artificial intelligence","score_opus":0.045248350600693536,"score_gpt":0.2941844958611444,"score_spread":0.24893614526045088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058488627","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":[0.49842656,0.001136367,0.25336194,0.20692183,0.0018844407,0.0067352685,0.0011650041,0.0015748817,0.028793715],"genre_scores_gemma":[0.9471116,0.000018284205,0.051833406,0.00042310092,0.00009657431,0.000013061275,0.000016930579,0.0000066183993,0.00048042895],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988407,0.000004959543,0.00022272403,0.0003853114,0.0002820482,0.00026426857],"domain_scores_gemma":[0.999098,0.000032026895,0.0001433433,0.00045620595,0.0002197718,0.000050677318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066338276,0.00010348208,0.00016458644,0.00006256553,0.00015552044,0.00015270797,0.0032421402,0.000031813248,0.0000020617874],"category_scores_gemma":[0.000098287106,0.00007115716,0.0000808425,0.00041601527,0.00003428414,0.00048212515,0.0007623963,0.000082502316,0.0000021119126],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006753356,0.0005373074,0.00097158435,0.0001269123,0.00028444492,5.6145296e-7,0.0026159582,0.000023696579,0.5731775,0.12121306,0.053209472,0.24777192],"study_design_scores_gemma":[0.0024533814,0.0007948562,0.0040730257,0.00016676467,0.00021059171,0.00001130178,0.00066319323,0.34507123,0.6143347,0.017043976,0.014495116,0.0006818725],"about_ca_topic_score_codex":0.000033417313,"about_ca_topic_score_gemma":0.0000016417764,"teacher_disagreement_score":0.44868505,"about_ca_system_score_codex":0.000029400831,"about_ca_system_score_gemma":0.00007932559,"threshold_uncertainty_score":0.6024757},"labels":[],"label_agreement":null},{"id":"W2062482216","doi":"10.14778/1920841.1921029","title":"Efficient event processing through reconfigurable hardware for algorithmic trading","year":2010,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":68,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Complex event processing; Computer science; Field-programmable gate array; Event (particle physics); Reconfigurable computing; Latency (audio); Predicate (mathematical logic); Computer architecture; Embedded system; Programming language","score_opus":0.08710940498047279,"score_gpt":0.38037972187073804,"score_spread":0.2932703168902653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062482216","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":[0.8986805,0.00023937854,0.018759357,0.0034826596,0.004084335,0.0035866867,0.000050261195,0.00017499921,0.07094179],"genre_scores_gemma":[0.90486157,0.0000018887723,0.0926347,0.000109117434,0.00025458494,0.000265779,5.057509e-7,0.00003756405,0.0018343016],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99606675,0.00003215148,0.001047879,0.0007528258,0.0015274044,0.00057297177],"domain_scores_gemma":[0.99645275,0.0009868324,0.0010520144,0.00036440376,0.0010291763,0.00011483041],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006991785,0.00028665157,0.00048579814,0.0001823237,0.00053325243,0.00029574666,0.001740688,0.00012072948,0.00016132025],"category_scores_gemma":[0.008377729,0.00017775543,0.00038259197,0.0009107735,0.00018867884,0.00022669752,0.00021184985,0.00037963392,0.000009192263],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002470939,0.00036961035,0.0030532242,0.00028682864,0.00007476748,5.139414e-7,0.005903652,0.0004612123,0.32902378,0.009108699,0.015427347,0.6360433],"study_design_scores_gemma":[0.0019695112,0.0002890014,0.0024226361,0.00048028343,0.00013548032,0.0000873399,0.0030237036,0.12047252,0.6546086,0.14615798,0.069657944,0.00069500064],"about_ca_topic_score_codex":0.000025069558,"about_ca_topic_score_gemma":0.0000040254195,"teacher_disagreement_score":0.63534826,"about_ca_system_score_codex":0.00010052584,"about_ca_system_score_gemma":0.00011841158,"threshold_uncertainty_score":0.99997514},"labels":[],"label_agreement":null},{"id":"W2077780773","doi":"10.14778/1920841.1920948","title":"Computing closed skycubes","year":2010,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":31,"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":"Skyline; Linear subspace; Computer science; Representation (politics); Subspace topology; Computation; Theoretical computer science; Formal concept analysis; Closure (psychology); Space (punctuation); Algorithm; Data mining; Mathematics; Artificial intelligence","score_opus":0.006308341498846236,"score_gpt":0.20824132972052734,"score_spread":0.2019329882216811,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077780773","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":[0.8837771,0.00006155071,0.011448524,0.008201713,0.0037685558,0.0010743396,0.000007004164,0.0004758353,0.0911854],"genre_scores_gemma":[0.9592908,0.000004814833,0.039884705,0.00020998645,0.000122836,0.0000063667317,5.019893e-7,0.0000064408373,0.00047355006],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99897677,0.0000025402562,0.00019913651,0.00025585943,0.00033797746,0.00022774296],"domain_scores_gemma":[0.99944085,0.000021664408,0.0001621358,0.0002429743,0.00008789648,0.00004450471],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003694299,0.000110978785,0.00011764009,0.00006226274,0.00012960937,0.00018747772,0.0020092486,0.000026311218,0.000009850418],"category_scores_gemma":[0.000047081416,0.00007450462,0.00007364334,0.00030170925,0.000056873138,0.00047550767,0.0013005491,0.00016682009,0.000017476394],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000417916,0.0001831956,0.006009809,0.0000882738,0.00005394026,8.2488515e-7,0.0008306021,0.000005213068,0.13823707,0.72971624,0.011552989,0.113317646],"study_design_scores_gemma":[0.001812713,0.00018615946,0.036115523,0.00016616515,0.00006071124,0.000028264009,0.00034058312,0.062034525,0.75561196,0.04870328,0.09416545,0.00077468314],"about_ca_topic_score_codex":0.000018963792,"about_ca_topic_score_gemma":0.0000016069434,"teacher_disagreement_score":0.681013,"about_ca_system_score_codex":0.000011392027,"about_ca_system_score_gemma":0.000010807732,"threshold_uncertainty_score":0.37337172},"labels":[],"label_agreement":null},{"id":"W2077825087","doi":"10.14778/1920841.1921070","title":"Time for our field to grow up","year":2010,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Scientific Computing and Data 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":"University of Waterloo","funders":"","keywords":"Wonder; Pride; Population; Field (mathematics); Haven; Set (abstract data type); Computer science; Data science; Political science; Sociology; Mathematics; Epistemology; Law","score_opus":0.06868736015691174,"score_gpt":0.3657685805251993,"score_spread":0.29708122036828755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077825087","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":[0.91646606,0.000010238708,0.001135159,0.039248962,0.0077406503,0.0016531267,0.00004309174,0.0000897249,0.033613015],"genre_scores_gemma":[0.9679394,3.4080458e-7,0.0051704273,0.0008180286,0.00018402902,0.000045287517,6.6082754e-7,0.0000072220323,0.025834642],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979112,0.0000043957007,0.00039734182,0.00048642393,0.00095178414,0.0002488656],"domain_scores_gemma":[0.9986122,0.00023917637,0.00021254644,0.0004481263,0.00038911458,0.00009883845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033383123,0.000103826314,0.00016820672,0.00015851099,0.00017771115,0.00028579085,0.0019362883,0.000033820175,0.00008614716],"category_scores_gemma":[0.004353425,0.000060829323,0.00013943952,0.00053486146,0.000026852515,0.00014858453,0.0009176429,0.0000980985,0.00022600195],"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":[0.000036500576,0.00005125791,0.0007989774,0.000010675795,0.000012588371,5.3218425e-8,0.0004787382,0.000011879067,0.053139232,0.00903123,0.8967531,0.039675802],"study_design_scores_gemma":[0.00066751166,0.0002262924,0.0023910648,0.000047442878,0.000033763212,0.000004743465,0.0019269668,0.0028592176,0.21514027,0.033771522,0.7426676,0.0002635927],"about_ca_topic_score_codex":0.000018654362,"about_ca_topic_score_gemma":0.000006583209,"teacher_disagreement_score":0.16200104,"about_ca_system_score_codex":0.000013390833,"about_ca_system_score_gemma":0.000016544038,"threshold_uncertainty_score":0.52117705},"labels":[],"label_agreement":null},{"id":"W2080132606","doi":"10.14778/1938545.1938547","title":"Automatic wrappers for large scale web extraction","year":2011,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":135,"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; Noise (video); Scale (ratio); Noisy data; Extraction (chemistry); Data extraction; Data mining; Information extraction; Training set; Artificial intelligence; Machine learning; Information retrieval; Pattern recognition (psychology)","score_opus":0.024150020816393863,"score_gpt":0.24482076550129492,"score_spread":0.22067074468490105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080132606","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":[0.9398059,0.000117766554,0.033621512,0.0021358863,0.0008084552,0.0009767832,0.000041610594,0.00042050026,0.022071585],"genre_scores_gemma":[0.9490006,0.000009229226,0.05049328,0.000085047635,0.000029958534,0.000059392758,7.845499e-7,0.000006423864,0.00031527286],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991307,0.000003793631,0.00020485575,0.00023040806,0.00021518831,0.00021500592],"domain_scores_gemma":[0.9994513,0.000020024949,0.00019935456,0.00018631057,0.00009833239,0.000044726694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041219452,0.00009426787,0.00013477096,0.000080970654,0.000130293,0.0000503766,0.0008487081,0.000030293415,0.000025569047],"category_scores_gemma":[0.00004494737,0.0000645535,0.0001346095,0.00027448317,0.000021626764,0.00039808184,0.0002116503,0.00005681924,0.000011356515],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008868141,0.0029294358,0.0420534,0.0012621663,0.00089896575,0.0000015030014,0.039057735,0.000012177465,0.39986238,0.27338773,0.08925852,0.15118732],"study_design_scores_gemma":[0.0019720749,0.00039526506,0.0101086,0.00033352413,0.00029847582,0.000029137265,0.003211157,0.34435037,0.609665,0.012277534,0.016759338,0.00059956696],"about_ca_topic_score_codex":0.000017338372,"about_ca_topic_score_gemma":0.0000029112894,"teacher_disagreement_score":0.34433818,"about_ca_system_score_codex":0.000028943758,"about_ca_system_score_gemma":0.000021887554,"threshold_uncertainty_score":0.26324153},"labels":[],"label_agreement":null},{"id":"W2098095723","doi":"10.14778/2732977.2732979","title":"Accordion","year":2014,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":58,"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; Accordion; Partition (number theory); Heuristics; Bottleneck; Server; Distributed computing; Throughput; Distributed database; Database; Parallel computing; Operating system; Embedded system","score_opus":0.004902096397346088,"score_gpt":0.18554557464082128,"score_spread":0.18064347824347518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098095723","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":[0.50071096,0.0004651298,0.18169622,0.013136861,0.003989565,0.0016386438,0.000013279587,0.0006125223,0.2977368],"genre_scores_gemma":[0.9971385,0.0000045378406,0.0022658247,0.00015397358,0.00006377158,0.00001909656,1.4956503e-7,0.000003881318,0.00035025302],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991644,0.0000048927614,0.0001885269,0.00019116451,0.00028552653,0.00016549017],"domain_scores_gemma":[0.99948394,0.000014023885,0.0001627259,0.00018474089,0.00011469086,0.000039878163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003172962,0.00008410968,0.00012748178,0.000026054868,0.00007396817,0.00007566482,0.0010788158,0.000026558695,0.0000025077459],"category_scores_gemma":[0.000044945486,0.000053172014,0.00007586957,0.00023913155,0.000025306112,0.00023115703,0.0002963919,0.0000629722,0.000014834529],"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":[0.0000071575714,0.00010592337,0.0056121103,0.000108150976,0.000026945962,1.3674187e-7,0.0005112722,0.000033241908,0.04444461,0.88084936,0.016339617,0.051961467],"study_design_scores_gemma":[0.0020706651,0.00035821766,0.03465035,0.0005434484,0.00003405881,0.00006159868,0.00022207093,0.040167626,0.44563195,0.049288746,0.42624098,0.0007302884],"about_ca_topic_score_codex":0.000019242902,"about_ca_topic_score_gemma":4.504925e-7,"teacher_disagreement_score":0.8315606,"about_ca_system_score_codex":0.00002500387,"about_ca_system_score_gemma":0.000008758345,"threshold_uncertainty_score":0.21682918},"labels":[],"label_agreement":null},{"id":"W2100039551","doi":"10.14778/1687627.1687735","title":"Distribution based microdata anonymization","year":2009,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":11,"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":"Microdata (statistics); Computer science; Data anonymization; Closeness; Data mining; Aggregate (composite); Variety (cybernetics); Generalization; Information privacy; Artificial intelligence; Mathematics","score_opus":0.015626811778433624,"score_gpt":0.2368745563587915,"score_spread":0.2212477445803579,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100039551","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":[0.11603551,0.0003891682,0.54737806,0.32583088,0.0010795214,0.001796729,0.00022049973,0.0020361566,0.0052334312],"genre_scores_gemma":[0.9016946,0.000020319769,0.0978747,0.00032911843,0.00002044693,0.000011635662,0.000019060944,0.0000042525044,0.000025841915],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988794,0.0000056505046,0.00022489362,0.00032693785,0.0003369921,0.00022613985],"domain_scores_gemma":[0.99779254,0.000019182211,0.0002204376,0.0017944613,0.00014385229,0.000029543908],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00031611937,0.00011828913,0.00011626963,0.000055529228,0.00010786856,0.000103936785,0.016386358,0.000059343412,0.0000043211794],"category_scores_gemma":[0.0036888702,0.000087046246,0.000053217005,0.0005906645,0.000056187695,0.00056219177,0.013393894,0.00011839227,0.0000051962656],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002204924,0.00035698072,0.0031060872,0.00006791879,0.000022037884,7.4580373e-7,0.000057607696,0.000021821741,0.21389578,0.06580062,0.6724485,0.044199813],"study_design_scores_gemma":[0.00039911878,0.00010692954,0.006648937,0.00009299826,0.000011986524,0.0000060121565,0.000011658482,0.03901171,0.7958396,0.15203024,0.00567097,0.00016981312],"about_ca_topic_score_codex":0.000007648882,"about_ca_topic_score_gemma":2.7603065e-7,"teacher_disagreement_score":0.78565913,"about_ca_system_score_codex":0.00011154213,"about_ca_system_score_gemma":0.000028357294,"threshold_uncertainty_score":0.9945856},"labels":[],"label_agreement":null},{"id":"W2102679851","doi":"10.14778/2350229.2350249","title":"Efficient indexing and querying over syntactically annotated trees","year":2012,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Search engine indexing; Parsing; Coding (social sciences); Set (abstract data type); Natural language; Index (typography); Tree (set theory); Information retrieval; Artificial intelligence; Natural language processing; Mathematics","score_opus":0.010587261327778642,"score_gpt":0.2312921184450198,"score_spread":0.22070485711724114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102679851","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":[0.987073,0.00049553294,0.00827936,0.0007319494,0.00040673913,0.00030626124,0.0000035040996,0.00008972422,0.0026139135],"genre_scores_gemma":[0.98783183,0.000013801646,0.011938995,0.00010412638,0.00005436618,0.000011066503,2.1849753e-7,0.0000062982117,0.0000393116],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9989588,0.000006712473,0.00019444406,0.00020507441,0.00034693978,0.00028797722],"domain_scores_gemma":[0.99948496,0.000048816328,0.00015202301,0.00014607408,0.000069331094,0.00009878416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003400101,0.00011773375,0.00013070596,0.000057429672,0.00015029183,0.00010083412,0.0004941204,0.000034547615,0.0000051209076],"category_scores_gemma":[0.00006570981,0.000073797484,0.00004081841,0.00021362912,0.000046707188,0.00038318208,0.00094863435,0.00011121304,0.0000022630954],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000089112684,0.001229774,0.11621678,0.0003142767,0.00017539937,0.0000020905447,0.010959079,0.00033321115,0.42795873,0.35409015,0.004356822,0.08427459],"study_design_scores_gemma":[0.0023182814,0.00027803538,0.34775618,0.0009819949,0.00010344481,0.00014722273,0.00075397594,0.3043641,0.32575136,0.0043623806,0.012142879,0.0010401718],"about_ca_topic_score_codex":0.00003662682,"about_ca_topic_score_gemma":3.1551076e-7,"teacher_disagreement_score":0.34972778,"about_ca_system_score_codex":0.00003859493,"about_ca_system_score_gemma":0.000011828395,"threshold_uncertainty_score":0.3009374},"labels":[],"label_agreement":null},{"id":"W2103437490","doi":"10.14778/2733085.2733095","title":"ADDICT","year":2014,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Parallel Computing and Optimization Techniques","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":"University of Toronto","funders":"","keywords":"Computer science; Cache; Locality; Latency (audio); CAS latency; Database transaction; Transaction processing; Memory footprint; Parallel computing; Software; Operating system; Multi-core processor; Distributed computing; Embedded system; Database; Memory controller","score_opus":0.007883670614523518,"score_gpt":0.21113710324098256,"score_spread":0.20325343262645904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103437490","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":[0.025619077,0.000121534766,0.7666963,0.00549152,0.0005731408,0.00055791455,0.0000011399221,0.0010708973,0.19986852],"genre_scores_gemma":[0.89991593,0.000009393855,0.09933964,0.00030554528,0.00003514065,0.000011946571,9.781622e-8,0.0000043978375,0.00037787965],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993102,0.0000062748068,0.0001574276,0.00016830122,0.00022094116,0.00013683921],"domain_scores_gemma":[0.99952644,0.000024722653,0.00014483026,0.00015990832,0.00011076253,0.0000333092],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003091462,0.000076316646,0.000096641925,0.00004674288,0.00008295618,0.000055247183,0.0010864477,0.00002419624,0.0000037946038],"category_scores_gemma":[0.00007789163,0.00005076637,0.000059910475,0.00022886961,0.00003044579,0.00013297942,0.00040163234,0.000063966094,0.0000060216917],"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":[0.0000059260306,0.00012662396,0.0026038657,0.000054916523,0.000028455499,1.0903359e-7,0.0007901781,0.00062567415,0.00954284,0.90154576,0.040749397,0.04392623],"study_design_scores_gemma":[0.00075992674,0.00029381792,0.0043234196,0.00021126005,0.00001934589,0.00002846539,0.00003017492,0.26127774,0.5778818,0.08290684,0.071825385,0.00044181896],"about_ca_topic_score_codex":0.0000068054255,"about_ca_topic_score_gemma":1.07561e-7,"teacher_disagreement_score":0.8742969,"about_ca_system_score_codex":0.000019151843,"about_ca_system_score_gemma":0.000009527864,"threshold_uncertainty_score":0.20701927},"labels":[],"label_agreement":null},{"id":"W2103615139","doi":"10.14778/1453856.1453955","title":"Keyword query cleaning","year":2008,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":51,"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; Ontario Tech University","funders":"","keywords":"Computer science; Query optimization; Query expansion; Web query classification; Web search query; Sargable; Query language; Information retrieval; Online aggregation; View; Set (abstract data type); Context (archaeology); Database; Query by Example; Data mining; Search engine","score_opus":0.016461420648945766,"score_gpt":0.19089173340955867,"score_spread":0.1744303127606129,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103615139","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":[0.60831314,0.00057917554,0.029417112,0.013207592,0.0031492459,0.0018773159,0.000010949049,0.0010184579,0.34242702],"genre_scores_gemma":[0.96988904,0.00009433112,0.0265381,0.000390835,0.000099169716,0.000020613934,5.441161e-7,0.00000937941,0.0029579855],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99896103,0.0000031325603,0.00019207632,0.00024668654,0.00037375445,0.00022328919],"domain_scores_gemma":[0.99951816,0.00001365306,0.00014863415,0.00020839398,0.00006935916,0.000041814328],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021093339,0.000106922605,0.000118844495,0.00006666684,0.00017083708,0.00006966339,0.0015683782,0.000019186697,0.000008429159],"category_scores_gemma":[0.000029714281,0.00007393552,0.000077420795,0.00035447476,0.000059089576,0.00068336166,0.0010693619,0.00008772908,0.000024157225],"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":[0.000022854056,0.00045234628,0.024279408,0.00019837116,0.00017070577,0.000012605758,0.0043583424,0.000035954083,0.019002736,0.722929,0.13205719,0.09648048],"study_design_scores_gemma":[0.0039141644,0.00065245025,0.072624356,0.0006264704,0.00011797354,0.0002638663,0.00118348,0.0327918,0.5073615,0.05388988,0.32467648,0.0018975872],"about_ca_topic_score_codex":0.000023356679,"about_ca_topic_score_gemma":4.3471317e-7,"teacher_disagreement_score":0.66903913,"about_ca_system_score_codex":0.000029868654,"about_ca_system_score_gemma":0.000013174723,"threshold_uncertainty_score":0.3015003},"labels":[],"label_agreement":null},{"id":"W2104550444","doi":"10.14778/1453856.1453967","title":"Efficient skyline querying with variable user preferences on nominal attributes","year":2008,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":64,"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":"Chinese University of Hong Kong; National Natural Science Foundation of China","keywords":"Skyline; Computer science; Preference; Order (exchange); Tree (set theory); Variable (mathematics); Data mining; Mathematics; Statistics","score_opus":0.022724689187778764,"score_gpt":0.2061796146940327,"score_spread":0.18345492550625395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104550444","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":[0.942299,0.00011395638,0.03140335,0.0019219071,0.0005150641,0.0010894128,0.000021379245,0.00023321566,0.022402702],"genre_scores_gemma":[0.94786525,0.000017589153,0.050557565,0.00018497485,0.000069290196,0.000047246518,0.0000019409931,0.000009197517,0.0012469472],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99858,0.00000548491,0.00021331485,0.00036412786,0.0005465033,0.00029061723],"domain_scores_gemma":[0.9993514,0.00003183823,0.00019812351,0.000233198,0.00013192745,0.00005352268],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028065997,0.00016614275,0.00017830319,0.000086944136,0.00022396633,0.00010479479,0.0013093054,0.00002323703,0.000011351082],"category_scores_gemma":[0.000030704075,0.00009600473,0.000045265282,0.00046379335,0.00007910013,0.00026052786,0.0005990457,0.00011095652,0.0000131260485],"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":[0.00032274704,0.0029702298,0.045376793,0.00060126674,0.00043717914,0.000018824889,0.0038784917,0.011562833,0.02294219,0.86633044,0.03184597,0.013713015],"study_design_scores_gemma":[0.007962035,0.0041961223,0.06392181,0.0024644816,0.0002978971,0.00021944683,0.0009968836,0.22684716,0.62084156,0.0073655425,0.062273547,0.0026135482],"about_ca_topic_score_codex":0.000048741873,"about_ca_topic_score_gemma":7.442043e-7,"teacher_disagreement_score":0.8589649,"about_ca_system_score_codex":0.00004633295,"about_ca_system_score_gemma":0.000032022916,"threshold_uncertainty_score":0.39149594},"labels":[],"label_agreement":null},{"id":"W2106019582","doi":"10.14778/2168651.2168659","title":"ReStore","year":2012,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":110,"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":"Computer science; Workflow; Dataflow; Reuse; Compiler; Implementation; Distributed computing; Operating system; Database; Parallel computing; Programming language","score_opus":0.013537665615544914,"score_gpt":0.21423723860527902,"score_spread":0.2006995729897341,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106019582","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":[0.9262439,0.00042539305,0.0007928025,0.0041796416,0.0010079625,0.00032722641,3.3362133e-7,0.00017709257,0.066845655],"genre_scores_gemma":[0.99385566,0.0000027757678,0.0044812835,0.00021970783,0.0001489635,0.000010744688,2.8841237e-8,0.0000054765187,0.001275351],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99905515,0.0000049632886,0.00016077542,0.00015098703,0.00034117416,0.00028696822],"domain_scores_gemma":[0.99952465,0.00001724453,0.00013706143,0.00020161334,0.000053284617,0.00006611553],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039761452,0.00009276303,0.00009712346,0.000047050675,0.00011128998,0.000042146807,0.0011206586,0.000022099357,0.0000035794706],"category_scores_gemma":[0.000031209664,0.000057497342,0.000084285064,0.000273333,0.00003477031,0.000046145782,0.0010319632,0.000083665116,0.000015755362],"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":[0.000010251852,0.0005322625,0.061218604,0.00018328414,0.00010772331,4.186104e-7,0.0072438703,0.00021045054,0.01208643,0.82558686,0.04391252,0.048907313],"study_design_scores_gemma":[0.0020303626,0.00036211926,0.19024026,0.00057437294,0.0001257511,0.000097112315,0.0013992591,0.020193068,0.2969293,0.021232573,0.46558622,0.0012296259],"about_ca_topic_score_codex":0.000013921223,"about_ca_topic_score_gemma":1.2226836e-7,"teacher_disagreement_score":0.8043543,"about_ca_system_score_codex":0.0000470994,"about_ca_system_score_gemma":0.0000061619107,"threshold_uncertainty_score":0.23446734},"labels":[],"label_agreement":null},{"id":"W2107047397","doi":"10.14778/1687553.1687600","title":"SMDM","year":2009,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada)","funders":"","keywords":"Computer science; Ontology; Semantics (computer science); RDF; Business domain; IBM; Domain (mathematical analysis); Software engineering; Semantic Web; Business rule; Business process; Information retrieval; Programming language; Engineering","score_opus":0.009923090580914845,"score_gpt":0.21368471931580998,"score_spread":0.20376162873489514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107047397","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":[0.74015117,0.0008707627,0.005461815,0.054081433,0.0012215871,0.00082285155,0.000001101563,0.00057706254,0.19681221],"genre_scores_gemma":[0.98936236,0.000017232838,0.00965949,0.0006183233,0.00003241177,0.000004400631,2.6350463e-8,0.0000018141734,0.0003039189],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992835,0.0000020403866,0.00014195834,0.00016486726,0.00023491618,0.00017274659],"domain_scores_gemma":[0.9996376,0.000014343588,0.00009972717,0.00014974874,0.0000703877,0.000028206625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014880276,0.000078164405,0.00010693795,0.000035332756,0.0000613972,0.0000553159,0.0011525366,0.000023967137,0.0000034306377],"category_scores_gemma":[0.000053253287,0.000046895653,0.00006818728,0.00019937054,0.00003001604,0.00019854866,0.00019974975,0.000060557115,0.00000847609],"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":[0.000007882363,0.00014072002,0.0039727204,0.000023831128,0.000018660996,7.9776044e-7,0.0011445357,0.0000051927987,0.058598757,0.87188965,0.010650347,0.05354688],"study_design_scores_gemma":[0.00057188194,0.00028510316,0.07978327,0.00008808699,0.000018208946,0.000035942277,0.00022110142,0.001292125,0.7094968,0.1992545,0.008708642,0.00024434875],"about_ca_topic_score_codex":0.000008858319,"about_ca_topic_score_gemma":3.671084e-7,"teacher_disagreement_score":0.6726352,"about_ca_system_score_codex":0.000020666981,"about_ca_system_score_gemma":0.0000123837035,"threshold_uncertainty_score":0.21417189},"labels":[],"label_agreement":null},{"id":"W2107080109","doi":"10.14778/1454159.1454220","title":"A revival of integrity constraints for data cleaning","year":2008,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada)","funders":"Engineering and Physical Sciences Research Council","keywords":"Data integrity; Data quality; Computer science; Schema (genetic algorithms); Constraint (computer-aided design); Quality (philosophy); Risk analysis (engineering); Data science; Reliability engineering; Database; Information retrieval; Engineering; Operations management; Business; Mechanical engineering","score_opus":0.5397355688626213,"score_gpt":0.44987919658589165,"score_spread":0.08985637227672966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107080109","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":[0.8500509,0.00042490062,0.015139266,0.015039472,0.0016823104,0.005372691,0.0019499043,0.00011654823,0.11022396],"genre_scores_gemma":[0.9887461,0.00005381473,0.010149397,0.0002228591,0.000044572043,0.000017758673,0.0000071551717,0.0000061189994,0.0007522038],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976048,0.000018350816,0.0007493781,0.0003989694,0.0010432224,0.00018526842],"domain_scores_gemma":[0.99792594,0.00037583546,0.000643418,0.0005806316,0.0004252218,0.00004893055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048403526,0.000104420156,0.00031074267,0.00008824202,0.00013447949,0.00004258924,0.0028582267,0.000033695203,0.00007508502],"category_scores_gemma":[0.0055664913,0.00006296614,0.00011732032,0.00033269677,0.0004278637,0.0004206564,0.0016765116,0.00011009029,0.000009113499],"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":[0.00029208272,0.00060982816,0.013644658,0.00044162272,0.0002077467,9.020353e-7,0.0036846737,0.000005585712,0.014417396,0.33226407,0.51643145,0.11799998],"study_design_scores_gemma":[0.0051201885,0.0007756673,0.018781621,0.0009966926,0.0003461252,0.00007815339,0.025198024,0.0046057715,0.18076989,0.23142816,0.5310311,0.00086862466],"about_ca_topic_score_codex":0.000054789252,"about_ca_topic_score_gemma":0.0000049058367,"teacher_disagreement_score":0.1663525,"about_ca_system_score_codex":0.000023642877,"about_ca_system_score_gemma":0.000046541118,"threshold_uncertainty_score":0.6664012},"labels":[],"label_agreement":null},{"id":"W2110020044","doi":"10.14778/1453856.1453922","title":"A practical scalable distributed B-tree","year":2008,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":135,"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; Distributed computing; Scalability; Tree (set theory); Fault tolerance; Distributed transaction; Concurrency; Transaction processing; Database transaction; Operating system; Database","score_opus":0.026289657278363878,"score_gpt":0.2516244494746975,"score_spread":0.2253347921963336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110020044","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":[0.55609316,0.0008310526,0.27565634,0.048269875,0.0032626141,0.003596234,0.00021486617,0.0011655748,0.11091029],"genre_scores_gemma":[0.9893275,0.000021548927,0.009862182,0.00012931858,0.000054506287,0.000045533074,0.0000015346168,0.000007172541,0.00055074325],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984473,0.000008557899,0.00033875523,0.00032057593,0.00055458694,0.00033024352],"domain_scores_gemma":[0.9990719,0.000036039903,0.00025848136,0.00026647223,0.0002662021,0.00010092355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025765793,0.00014985877,0.00022481913,0.000035093828,0.00021126175,0.000073299365,0.0010027065,0.0000550194,0.000007378488],"category_scores_gemma":[0.00014461936,0.00009982893,0.00012292575,0.0005594726,0.00010709682,0.0004971574,0.0004543816,0.00015572096,0.000027860178],"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":[0.0000648429,0.001228532,0.027768876,0.0002313777,0.00017490066,0.000026071351,0.0014593208,0.000051344145,0.03679095,0.5540692,0.3743352,0.0037993747],"study_design_scores_gemma":[0.0053916196,0.0006968215,0.0888715,0.0007559718,0.00010505109,0.0023291477,0.00060047494,0.042496286,0.4776981,0.014927009,0.36446068,0.001667369],"about_ca_topic_score_codex":0.00003974651,"about_ca_topic_score_gemma":0.0000011608281,"teacher_disagreement_score":0.5391422,"about_ca_system_score_codex":0.0000741856,"about_ca_system_score_gemma":0.00007026755,"threshold_uncertainty_score":0.40709057},"labels":[],"label_agreement":null},{"id":"W2111227779","doi":"10.14778/1454159.1454189","title":"P2P logging and timestamping for reconciliation","year":2008,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Peer-to-Peer Network Technologies","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":"University of Waterloo","funders":"","keywords":"Computer science; Distributed hash table; Peer-to-peer; Hash function; Distributed computing; Consistency (knowledge bases); Hash table; Logging; Computer network; Computer security","score_opus":0.025745073631701223,"score_gpt":0.22740153810719047,"score_spread":0.20165646447548924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111227779","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":[0.91437715,0.000564041,0.055805214,0.02082683,0.00057353976,0.0018979567,0.0000052259356,0.00075752905,0.0051925248],"genre_scores_gemma":[0.8988047,0.000062966225,0.100351974,0.00026573372,0.00003806987,0.000093224924,1.8100945e-7,0.0000072968837,0.00037581316],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991657,0.0000019876645,0.00017696132,0.00025161073,0.00018864613,0.00021508064],"domain_scores_gemma":[0.9995276,0.000046996345,0.00013493611,0.00013864216,0.0001174423,0.000034421148],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027281212,0.00009582069,0.00012663688,0.000067882014,0.00015634828,0.000041653206,0.0006989679,0.00003800457,3.6439846e-7],"category_scores_gemma":[0.00016304766,0.00007293664,0.000041082414,0.00018027054,0.000050318755,0.00025079967,0.00051310775,0.0000655128,0.0000013665828],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009286942,0.00024022067,0.024745053,0.00059017923,0.0001897761,0.000002587148,0.012585212,0.00058359525,0.19543579,0.29220843,0.1442031,0.3291232],"study_design_scores_gemma":[0.0014863653,0.00054733997,0.011267107,0.00035251427,0.000035382967,0.00014764848,0.00035699847,0.03991204,0.821818,0.05558104,0.06780891,0.0006866307],"about_ca_topic_score_codex":0.000013140626,"about_ca_topic_score_gemma":7.9910444e-7,"teacher_disagreement_score":0.62638223,"about_ca_system_score_codex":0.00006657117,"about_ca_system_score_gemma":0.000017438117,"threshold_uncertainty_score":0.29742697},"labels":[],"label_agreement":null},{"id":"W2111607365","doi":"10.14778/1687627.1687727","title":"Distance-join","year":2009,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":207,"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; Reachability; Join (topology); Graph; Theoretical computer science; Query optimization; Shortest path problem; Data mining; Mathematics; Combinatorics","score_opus":0.006708040847259433,"score_gpt":0.20173282838343293,"score_spread":0.1950247875361735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111607365","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":[0.5986049,0.0014454274,0.10718113,0.039101478,0.0027340315,0.0021768238,0.000010968722,0.0009812367,0.24776398],"genre_scores_gemma":[0.9914644,0.000011976216,0.007607733,0.0004128946,0.000037236226,0.00000730535,7.754238e-8,0.0000028923212,0.00045551403],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99916536,0.0000041380795,0.00016758917,0.0002033222,0.00025977186,0.00019981344],"domain_scores_gemma":[0.9995786,0.000012441799,0.00012316788,0.00016776772,0.00007104229,0.00004697769],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023805257,0.000099689954,0.0001139967,0.00004226512,0.000102507205,0.00006288253,0.0011506444,0.000022353019,0.000005090124],"category_scores_gemma":[0.000023767769,0.000063898886,0.00009797885,0.00035160925,0.000044101747,0.00027688776,0.00015503821,0.00008518712,0.0000069998323],"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":[0.0000055839955,0.00008432592,0.0002975663,0.000009975845,0.000007881727,3.3853192e-7,0.0005244343,0.0000044277626,0.016565433,0.96046174,0.0010176725,0.021020636],"study_design_scores_gemma":[0.00045836464,0.00019047677,0.006579966,0.000086866494,0.000011245677,0.000016583928,0.000100645564,0.001393803,0.30702424,0.6775364,0.0063936226,0.00020773437],"about_ca_topic_score_codex":0.000001856344,"about_ca_topic_score_gemma":1.2209364e-7,"teacher_disagreement_score":0.39285943,"about_ca_system_score_codex":0.000022003263,"about_ca_system_score_gemma":0.00000958292,"threshold_uncertainty_score":0.26057208},"labels":[],"label_agreement":null},{"id":"W2111811740","doi":"10.14778/2021017.2021018","title":"On pruning for top-k ranking in uncertain databases","year":2011,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of Alberta","funders":"","keywords":"Tuple; Pruning; Ranking (information retrieval); Rank (graph theory); Computer science; Parameterized complexity; Key (lock); Range (aeronautics); Learning to rank; Semantics (computer science); Function (biology); Computation; Ranking SVM; Task (project management); Database; Information retrieval; Artificial intelligence; Data mining; Mathematics; Algorithm; Programming language; Combinatorics; Discrete mathematics","score_opus":0.06770205945613778,"score_gpt":0.2641757924783974,"score_spread":0.19647373302225962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111811740","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":[0.5855262,0.0004917268,0.2196287,0.006164803,0.003724011,0.008997007,0.000102482096,0.00069133873,0.17467369],"genre_scores_gemma":[0.9029351,0.000017123459,0.09624768,0.00031629106,0.00004031037,0.00012170543,0.0000025473178,0.000009812964,0.00030945096],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99910134,0.000003690255,0.00019013612,0.00026645095,0.00021585003,0.00022250396],"domain_scores_gemma":[0.99956614,0.00004259152,0.00013299464,0.00019210031,0.000042672065,0.000023520075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046120695,0.00010154695,0.00011642532,0.00011216949,0.00006827272,0.000051321094,0.0011641684,0.000012473918,0.000006410129],"category_scores_gemma":[0.00008515493,0.00007079518,0.00004917399,0.00027331762,0.000024096236,0.00054283784,0.0005742624,0.000062910134,0.0000025458744],"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":[0.000039508643,0.00020284436,0.0035784345,0.00013611406,0.000025965739,9.805547e-7,0.0017832603,0.000016704684,0.001867234,0.9585668,0.0027103147,0.03107188],"study_design_scores_gemma":[0.007208598,0.0011256022,0.015615649,0.002439603,0.000102068974,0.000010733275,0.002016525,0.07961056,0.60919136,0.24790746,0.033355225,0.0014166267],"about_ca_topic_score_codex":0.00008427108,"about_ca_topic_score_gemma":0.000003715605,"teacher_disagreement_score":0.71065927,"about_ca_system_score_codex":0.00003373865,"about_ca_system_score_gemma":0.000009701494,"threshold_uncertainty_score":0.28869435},"labels":[],"label_agreement":null},{"id":"W2111814513","doi":"10.14778/2535570.2488330","title":"Partitioning and ranking tagged data sources","year":2013,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","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 Toronto","funders":"","keywords":"Computer science; Ranking (information retrieval); Information retrieval; Categorization; Partition (number theory); Set (abstract data type); Rank (graph theory); Learning to rank; Focus (optics); Data mining; Social media; Data science; World Wide Web; Artificial intelligence; Mathematics","score_opus":0.016600964907052655,"score_gpt":0.23227638965751488,"score_spread":0.21567542475046222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111814513","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":[0.9902109,0.00011324747,0.00035964386,0.00060891657,0.000023923918,0.00032876394,0.0000060614448,0.000041771316,0.008306759],"genre_scores_gemma":[0.9978105,0.000005943015,0.001842751,0.00003201535,0.00011662299,0.00005012619,0.0000056794856,0.00000821709,0.00012818273],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993232,0.000004495772,0.00018516609,0.00019145885,0.00014794407,0.00014776392],"domain_scores_gemma":[0.9995285,0.000023539451,0.000176167,0.00017034162,0.000070653456,0.00003076946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018486894,0.000091497706,0.00013882828,0.000030443902,0.00013735952,0.00010141486,0.0004233802,0.000011345234,0.00020593191],"category_scores_gemma":[0.000008072168,0.000063947526,0.000043902877,0.00012076031,0.000057366524,0.00023909987,0.0006122765,0.0000783382,0.0000037746597],"study_design_candidate":"observational","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":[0.0000075612384,0.00013490782,0.8457416,0.000056195306,0.00032472503,3.3937354e-8,0.0008974551,0.00001886999,0.04420003,0.050766677,0.019358749,0.038493138],"study_design_scores_gemma":[0.001979,0.00013384869,0.12912174,0.0008836778,0.0007901069,0.0000054637735,0.004948171,0.02630422,0.4293917,0.37567985,0.02961612,0.001146113],"about_ca_topic_score_codex":0.00039649493,"about_ca_topic_score_gemma":0.0000020714606,"teacher_disagreement_score":0.7166199,"about_ca_system_score_codex":0.000008146572,"about_ca_system_score_gemma":0.000005246405,"threshold_uncertainty_score":0.26077044},"labels":[],"label_agreement":null},{"id":"W2112007194","doi":"10.14778/2536274.2536316","title":"IPS","year":2013,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","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 British Columbia","funders":"","keywords":"Flexibility (engineering); Computer science; Set (abstract data type); Task (project management); Point of interest; Human–computer interaction; Engineering; Artificial intelligence; Systems engineering","score_opus":0.0070832293950941465,"score_gpt":0.17799929477527485,"score_spread":0.1709160653801807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112007194","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":[0.39629704,0.00042943875,0.01863995,0.049979694,0.0034205546,0.00440059,0.000010426834,0.000916278,0.525906],"genre_scores_gemma":[0.9697813,0.00001704115,0.025442172,0.0005109809,0.00006896787,0.00007987505,4.212059e-7,0.0000068635077,0.0040924097],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992115,0.0000019021767,0.0001441847,0.00018626753,0.00027646398,0.00017967992],"domain_scores_gemma":[0.9995749,0.000008638027,0.00010589987,0.00018909613,0.00008413563,0.000037310016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014305618,0.00008152065,0.000082949744,0.000044452212,0.000064651,0.00018462469,0.0016311149,0.00001426695,0.000038168386],"category_scores_gemma":[0.000019537052,0.000050572533,0.000053258893,0.0002481553,0.000031035666,0.000868447,0.0010137294,0.000054949105,0.00011418137],"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":[0.0000018637287,0.00018353692,0.004513051,0.0000955266,0.0000662785,3.3842505e-7,0.00073989964,0.0000029612943,0.02246786,0.6650356,0.17672917,0.13016388],"study_design_scores_gemma":[0.0020976362,0.0003560065,0.070116386,0.00026939804,0.00007016772,0.000021762815,0.00086927006,0.028000873,0.46087056,0.25414503,0.18210751,0.0010753991],"about_ca_topic_score_codex":0.00003507383,"about_ca_topic_score_gemma":1.9688375e-7,"teacher_disagreement_score":0.57348424,"about_ca_system_score_codex":0.000017925096,"about_ca_system_score_gemma":0.0000053842614,"threshold_uncertainty_score":0.30310443},"labels":[],"label_agreement":null},{"id":"W2112485457","doi":"10.14778/1687553.1687567","title":"SQL/MapReduce","year":2009,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":127,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"ASTER","funders":"","keywords":"Computer science; SQL; User-defined function; Database; Schema (genetic algorithms); Scalability; NoSQL; Programming language; Query by Example; Information retrieval","score_opus":0.007158007447369725,"score_gpt":0.213177163393006,"score_spread":0.20601915594563627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112485457","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":[0.5029984,0.0027108418,0.2237486,0.04296666,0.003924058,0.0035277798,0.000052512587,0.0013390721,0.21873204],"genre_scores_gemma":[0.95441675,0.00002069933,0.04440263,0.00036877705,0.000072006,0.000014307388,2.881128e-7,0.00000426927,0.0007002581],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99910414,0.0000029773942,0.00020099866,0.00022066776,0.00027745808,0.00019375498],"domain_scores_gemma":[0.9994609,0.000010426868,0.00016095839,0.00021922882,0.00010132125,0.000047176272],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015849523,0.000103821214,0.00013086619,0.00003589507,0.00009432597,0.000031924814,0.00070322707,0.000020802752,0.0000036635506],"category_scores_gemma":[0.00004157975,0.00006595921,0.00006772858,0.00024631963,0.00003353394,0.00051576615,0.00024969265,0.00007139684,0.0000082502265],"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":[0.00000512731,0.00005884986,0.00017973223,0.000022989974,0.000008067452,3.353711e-7,0.0005211383,0.000009028319,0.08138123,0.8991455,0.00402295,0.0146450875],"study_design_scores_gemma":[0.0005473328,0.00023203864,0.004775483,0.00020832854,0.000012473395,0.000050180843,0.0002590401,0.0007015427,0.8459881,0.030510506,0.1164014,0.00031358964],"about_ca_topic_score_codex":0.000011385722,"about_ca_topic_score_gemma":3.770277e-7,"teacher_disagreement_score":0.86863494,"about_ca_system_score_codex":0.000031734755,"about_ca_system_score_gemma":0.000017379927,"threshold_uncertainty_score":0.26897386},"labels":[],"label_agreement":null},{"id":"W2112840274","doi":"10.14778/1920841.1920870","title":"Sampling the repairs of functional dependency violations under hard constraints","year":2010,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":127,"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; Dependency (UML); Class (philosophy); Functional dependency; Context (archaeology); Sampling (signal processing); Relation (database); Data integrity; Variety (cybernetics); Space (punctuation); Data mining; Metric (unit); Theoretical computer science; Relational database; Database; Artificial intelligence","score_opus":0.1812498346188758,"score_gpt":0.3696657815601582,"score_spread":0.18841594694128241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112840274","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":[0.92629546,0.000039803046,0.008185695,0.014130897,0.002090576,0.0010873767,0.00012208807,0.00005823748,0.047989838],"genre_scores_gemma":[0.99623656,0.0000070606734,0.00241368,0.00029666667,0.00006387834,0.000024664614,0.0000018669967,0.000005380852,0.000950246],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99753034,0.000019346113,0.00064790936,0.00029311297,0.0013378346,0.00017142981],"domain_scores_gemma":[0.9980634,0.000503447,0.0005448339,0.00036893235,0.00047173174,0.00004766303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036449814,0.00010588369,0.00017233849,0.00010136135,0.00025766712,0.00010931443,0.0011034026,0.000044866978,0.0007046714],"category_scores_gemma":[0.001882149,0.00005459006,0.00016978575,0.00041298583,0.00042693946,0.0002808494,0.0005194222,0.00021372054,0.000032872733],"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":[0.0000406563,0.00019969494,0.012779158,0.000028710534,0.000108756765,7.878107e-8,0.000861121,0.0001811694,0.08822781,0.8685724,0.014871586,0.014128816],"study_design_scores_gemma":[0.000885231,0.000087893015,0.22748715,0.0000849232,0.0001446285,0.000021484751,0.01379489,0.0007074735,0.035416216,0.68228227,0.03880276,0.00028507336],"about_ca_topic_score_codex":0.00004213702,"about_ca_topic_score_gemma":0.000041650997,"teacher_disagreement_score":0.21470799,"about_ca_system_score_codex":0.000020480677,"about_ca_system_score_gemma":0.000051850035,"threshold_uncertainty_score":0.77156574},"labels":[],"label_agreement":null},{"id":"W2113415503","doi":"10.14778/1687627.1687695","title":"Modeling and querying possible repairs in duplicate detection","year":2009,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":57,"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; Scalability; Data mining; Parameterized complexity; Cluster analysis; Identification (biology); Set (abstract data type); Database; Algorithm; Machine learning","score_opus":0.08693929288766766,"score_gpt":0.34729863073080464,"score_spread":0.260359337843137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113415503","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":[0.98984903,0.00009880213,0.0009361174,0.0031920713,0.00008745865,0.00035117197,0.0000019119432,0.000031364234,0.005452071],"genre_scores_gemma":[0.99872917,0.000051061652,0.0006796776,0.0002749681,0.000017679171,0.000012808088,1.6895997e-7,0.0000033024846,0.0002311365],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99837416,0.00001306557,0.00048557957,0.0003369924,0.0006125953,0.00017761232],"domain_scores_gemma":[0.9994571,0.000045437155,0.00017373641,0.00017864746,0.000104446466,0.00004060034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027393175,0.00009031103,0.00016443146,0.00013561318,0.00010704423,0.00015058336,0.00048287498,0.000031039086,0.0000061367723],"category_scores_gemma":[0.0005686248,0.000058522335,0.000055368604,0.00050589826,0.000032900443,0.00043352577,0.00026482166,0.00009461305,0.0000054743105],"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":[0.00033501125,0.0005314434,0.010654226,0.000138553,0.000049845905,0.0000018954241,0.0068016145,0.007408602,0.14498919,0.07114186,0.002017694,0.75593007],"study_design_scores_gemma":[0.0017237636,0.00036844655,0.030036906,0.00032865774,0.000054425847,0.00002011553,0.009990656,0.27121586,0.14676873,0.5345029,0.004465778,0.0005237359],"about_ca_topic_score_codex":0.00018582193,"about_ca_topic_score_gemma":0.000045618708,"teacher_disagreement_score":0.7554063,"about_ca_system_score_codex":0.000048131842,"about_ca_system_score_gemma":0.000006082922,"threshold_uncertainty_score":0.23864715},"labels":[],"label_agreement":null},{"id":"W2114206928","doi":"10.14778/2536206.2536214","title":"RACE","year":2013,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Algorithms and Data Compression","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":"Computer science; Speedup; Cache; Cloud computing; Parallel computing; Sequence (biology); Representation (politics); Multi-core processor; Contrast (vision); Scaling; Artificial intelligence; Operating system; Mathematics","score_opus":0.006947487662152172,"score_gpt":0.19577461303583504,"score_spread":0.18882712537368287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114206928","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":[0.756903,0.0012361578,0.07264776,0.037616394,0.0033356042,0.003812237,0.000012334755,0.0007929674,0.12364358],"genre_scores_gemma":[0.9512584,0.00002533878,0.047072764,0.00031585892,0.00006228636,0.00006029577,2.4874737e-7,0.0000062641175,0.0011985076],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99923503,0.000002520733,0.00014511478,0.00018280245,0.00027492642,0.00015957846],"domain_scores_gemma":[0.99949676,0.000014730991,0.00012041873,0.00019577092,0.00012462166,0.000047709553],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000110680885,0.00007911429,0.000091655194,0.000028741755,0.00008349166,0.000108447435,0.0012610446,0.000021734044,0.00003482133],"category_scores_gemma":[0.000024700155,0.000045504526,0.000049599636,0.00017799786,0.000028574528,0.0006187936,0.0009413285,0.0000696464,0.000058705802],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007013956,0.0003389601,0.005326307,0.00011429047,0.00005377529,4.6436472e-7,0.001745618,0.000021212387,0.2585592,0.32022998,0.23790045,0.17570272],"study_design_scores_gemma":[0.0011427408,0.00020901575,0.033985104,0.0002630177,0.000020197005,0.000038306574,0.00027853475,0.049332887,0.74552506,0.0898834,0.07878714,0.0005346172],"about_ca_topic_score_codex":0.000070750015,"about_ca_topic_score_gemma":1.4311335e-7,"teacher_disagreement_score":0.48696584,"about_ca_system_score_codex":0.000020190078,"about_ca_system_score_gemma":0.000010738056,"threshold_uncertainty_score":0.23433557},"labels":[],"label_agreement":null},{"id":"W2115215982","doi":"10.14778/1453856.1453883","title":"Hashed samples","year":2008,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":68,"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":"Similarity (geometry); Estimator; A priori and a posteriori; Computer science; Overhead (engineering); Set (abstract data type); Sampling (signal processing); Cosine similarity; Algorithm; Data mining; Pattern recognition (psychology); Mathematics; Artificial intelligence; Statistics","score_opus":0.2910039101624485,"score_gpt":0.3717421828373335,"score_spread":0.08073827267488504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115215982","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":[0.9066988,0.00011239092,0.00029726283,0.008024189,0.0005471967,0.00058889657,0.00003887616,0.00006138077,0.08363099],"genre_scores_gemma":[0.99176335,0.000049432107,0.0014904855,0.00058604486,0.0000533831,0.000022701443,8.843631e-7,0.0000060975512,0.006027601],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974399,0.000015017461,0.0005259413,0.00032169532,0.0014859284,0.00021151378],"domain_scores_gemma":[0.99886304,0.00017271173,0.00033943067,0.0003123499,0.00025066856,0.00006179988],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017999941,0.00011015458,0.00021698805,0.0001112632,0.00022911745,0.00008475884,0.001608782,0.000027633067,0.00023881749],"category_scores_gemma":[0.001475403,0.000061291445,0.00014360069,0.00051403855,0.00020424642,0.0003230026,0.0007911863,0.000077072356,0.0001401256],"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":[0.000083478175,0.00041628364,0.040988997,0.000052196898,0.000093921975,0.000001707678,0.0040231203,0.00002868511,0.018716447,0.2555075,0.6621273,0.017960351],"study_design_scores_gemma":[0.0008811202,0.00011983084,0.08030357,0.000049378672,0.000037110385,0.000025026126,0.0033977728,0.00008660491,0.11935536,0.13068919,0.6647803,0.0002747251],"about_ca_topic_score_codex":0.00008477276,"about_ca_topic_score_gemma":0.0000065381923,"teacher_disagreement_score":0.12481832,"about_ca_system_score_codex":0.000032165433,"about_ca_system_score_gemma":0.000021156167,"threshold_uncertainty_score":0.2989544},"labels":[],"label_agreement":null},{"id":"W2117538598","doi":"10.14778/1687627.1687659","title":"A scalable, predictable join operator for highly concurrent data warehouses","year":2009,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":87,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"ASTER","funders":"","keywords":"Computer science; Query plan; Scalability; Query optimization; Online aggregation; Data warehouse; Tuple; Throughput; Computation; Query language; Pipeline (software); Sargable; Database; Data mining; Distributed computing; Web search query; Search engine; Information retrieval; Algorithm; Programming language","score_opus":0.035230274181042985,"score_gpt":0.27187334763998267,"score_spread":0.23664307345893967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117538598","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":[0.0615283,0.0064493543,0.8841202,0.022799717,0.0050772345,0.009464697,0.0027102428,0.0013417017,0.0065084985],"genre_scores_gemma":[0.8585214,0.00013731155,0.13929592,0.0007249049,0.00028859067,0.00018286452,0.000027201942,0.000023034101,0.00079873804],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983907,0.0000058788737,0.00038242392,0.000503904,0.0003734522,0.00034365983],"domain_scores_gemma":[0.99879247,0.00003854173,0.00024784103,0.0005955508,0.00023754861,0.000088022105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039590764,0.00018198488,0.00026770183,0.000050405695,0.0001995488,0.00009984412,0.0018509738,0.000034404213,0.0000032829942],"category_scores_gemma":[0.00017082525,0.00011759239,0.000064350155,0.00027238386,0.00005536885,0.0013475947,0.0009288502,0.00008439428,0.000003663929],"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":[0.00004315786,0.00038808255,0.0007086476,0.0003567533,0.00007406635,7.166397e-7,0.000771516,0.000056824374,0.05403279,0.81659865,0.09806886,0.028899934],"study_design_scores_gemma":[0.0021027124,0.00070098205,0.00077238446,0.0006475923,0.000057869533,0.00003170143,0.00026284147,0.01667202,0.2977001,0.0037210968,0.67678374,0.0005469534],"about_ca_topic_score_codex":0.000024769344,"about_ca_topic_score_gemma":0.0000026290597,"teacher_disagreement_score":0.81287754,"about_ca_system_score_codex":0.000054175336,"about_ca_system_score_gemma":0.00007836897,"threshold_uncertainty_score":0.47952783},"labels":[],"label_agreement":null},{"id":"W2119323564","doi":"10.14778/2536206.2536208","title":"A data-adaptive and dynamic segmentation index for whole matching on time series","year":2013,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":99,"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":"Search engine indexing; Series (stratigraphy); Segmentation; Computer science; Matching (statistics); Index (typography); Time series; Similarity (geometry); Tree (set theory); Nearest neighbor search; Data mining; Algorithm; Pattern recognition (psychology); Mathematics; Artificial intelligence; Machine learning; Statistics; Image (mathematics)","score_opus":0.0158004004847677,"score_gpt":0.22996060156035852,"score_spread":0.21416020107559083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119323564","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":[0.9036361,0.0002207838,0.075984485,0.0116719315,0.00029713043,0.0033097211,0.00014024113,0.00020044026,0.0045391694],"genre_scores_gemma":[0.9465549,0.0000076204915,0.05213021,0.00012363147,0.000024307514,0.000076557226,0.0000062841086,0.0000098987975,0.0010665705],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991761,0.0000037393906,0.00018987118,0.00027916636,0.00019422323,0.00015691428],"domain_scores_gemma":[0.9994474,0.000030851752,0.00021620262,0.00016970173,0.00010288931,0.00003296685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002121915,0.0001054744,0.00014148575,0.000049109927,0.00016085315,0.00019364964,0.0006167976,0.000021755819,0.000007772007],"category_scores_gemma":[0.000023058306,0.000070660055,0.000040830048,0.00014063816,0.000038326747,0.0010286291,0.00057451404,0.00005450165,0.000007780195],"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":[0.0002274373,0.0004288633,0.0018759507,0.0005058567,0.0007940915,5.2577354e-7,0.01574961,0.0015437305,0.52550083,0.10214393,0.012577441,0.33865172],"study_design_scores_gemma":[0.000979509,0.0006762427,0.004820655,0.00022447377,0.00009588782,0.000016773163,0.0035349305,0.9080855,0.028784925,0.05064853,0.0017140722,0.0004184971],"about_ca_topic_score_codex":0.000048956746,"about_ca_topic_score_gemma":0.0000040184577,"teacher_disagreement_score":0.90654176,"about_ca_system_score_codex":0.00003358085,"about_ca_system_score_gemma":0.000009106037,"threshold_uncertainty_score":0.28814334},"labels":[],"label_agreement":null},{"id":"W2122028373","doi":"10.14778/1454159.1454213","title":"Capri/MR","year":2008,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","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 Ottawa; National Research Council Canada","funders":"","keywords":"Computer science; Protein structure database; Nearest neighbor search; Protein Data Bank; Data mining; Protein structure; Database; Biology; Gene; Sequence database","score_opus":0.0066496077312751325,"score_gpt":0.20217461489252136,"score_spread":0.19552500716124624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122028373","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":[0.98888886,0.00030914572,0.000039116647,0.00021702985,0.000109110086,0.00019647065,0.00000539815,0.000008300814,0.010226561],"genre_scores_gemma":[0.99734986,0.00013045328,0.0009755771,0.00020168394,0.00011477605,0.00001829296,0.0000028285388,0.000010200352,0.0011963588],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994246,0.000002150745,0.00012768389,0.00016077279,0.00014144741,0.00014334287],"domain_scores_gemma":[0.9996714,0.0000016403467,0.000092698625,0.000115540824,0.000084340856,0.000034394234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000057755195,0.00009389403,0.00008804619,0.00001545368,0.000081409446,0.000005040364,0.0002762096,0.0000618072,0.0000066085427],"category_scores_gemma":[0.000039457012,0.00006348539,0.000086420165,0.0000639402,0.00008920356,0.0000025841343,0.00018914469,0.000056856534,0.0000023158584],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027523547,0.000024406128,0.009861886,0.000019024195,0.000028894283,2.6075116e-7,0.00007688968,0.0000065469585,0.98478043,0.0013243594,0.0034610713,0.0003886986],"study_design_scores_gemma":[0.00028184275,0.00008796616,0.0044455617,0.000009559482,0.000011111828,0.000053942917,0.00003406815,0.000012920889,0.978581,0.0008412266,0.015546805,0.000093970746],"about_ca_topic_score_codex":0.00001503109,"about_ca_topic_score_gemma":0.000001738906,"teacher_disagreement_score":0.012085734,"about_ca_system_score_codex":0.000011092427,"about_ca_system_score_gemma":0.00002497549,"threshold_uncertainty_score":0.25888592},"labels":[],"label_agreement":null},{"id":"W2126547925","doi":"10.14778/1920841.1920906","title":"MRShare","year":2010,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":226,"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; Cloud computing; Batch processing; Context (archaeology); Distributed computing; Work (physics); Core (optical fiber); Database; Operating system","score_opus":0.00697231335455234,"score_gpt":0.1997996891760867,"score_spread":0.19282737582153436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126547925","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":[0.9452204,0.000030540323,0.00028517112,0.006609385,0.00091450947,0.0002850375,7.886839e-7,0.00016548856,0.04648865],"genre_scores_gemma":[0.9932321,9.2892014e-7,0.0052779214,0.00022438372,0.00009662097,0.000012775682,5.494284e-8,0.0000056329804,0.0011495829],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990791,0.000002451865,0.0001650133,0.00022931126,0.00032465122,0.0001994395],"domain_scores_gemma":[0.99945575,0.000017743854,0.00013829583,0.00024844968,0.000091190384,0.00004857686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025505826,0.0000976347,0.000098255216,0.000049207967,0.0001224923,0.00008758754,0.001674938,0.000029708768,0.000013051928],"category_scores_gemma":[0.000047315105,0.000061093844,0.000091733265,0.00026905304,0.000042109416,0.000026922524,0.0011536524,0.0001825974,0.0000162326],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009839376,0.00040790174,0.011096028,0.0002186367,0.00010423431,0.0000017315849,0.0031842834,0.00020910807,0.18638639,0.6587075,0.03838572,0.101288654],"study_design_scores_gemma":[0.0017176991,0.00027508,0.04126248,0.00031792518,0.000061639104,0.000082861385,0.00045869552,0.056166176,0.5817854,0.04708451,0.2698802,0.00090737164],"about_ca_topic_score_codex":0.000020881265,"about_ca_topic_score_gemma":0.0000019809274,"teacher_disagreement_score":0.611623,"about_ca_system_score_codex":0.0000144901405,"about_ca_system_score_gemma":0.000010022841,"threshold_uncertainty_score":0.31124794},"labels":[],"label_agreement":null},{"id":"W2128248866","doi":"10.14778/1687627.1687734","title":"k-automorphism","year":2009,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":407,"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":"Popularity; Computer science; Extension (predicate logic); Personally identifiable information; Automorphism; Computer security; Data mining; Theoretical computer science; Mathematics; Discrete mathematics; Programming language","score_opus":0.018531082140186377,"score_gpt":0.24089356765210648,"score_spread":0.22236248551192012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128248866","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":[0.25114912,0.0009786943,0.018465903,0.62907636,0.0017556207,0.0018545365,0.000019509549,0.0038239905,0.09287623],"genre_scores_gemma":[0.8742734,0.000038808015,0.1249027,0.0006267154,0.000026393727,0.000012704685,2.452746e-7,0.000005003081,0.000113994705],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99873894,0.0000034944705,0.00022923862,0.0003238241,0.00042183656,0.00028268862],"domain_scores_gemma":[0.99758226,0.00002279592,0.00019799705,0.002054665,0.000103533064,0.000038751114],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00030426978,0.000130169,0.00014901767,0.000084896994,0.000093593946,0.00008655194,0.02850315,0.00005899453,0.0000062904633],"category_scores_gemma":[0.003006293,0.000089201516,0.0000746543,0.00049993367,0.00007725148,0.00047396088,0.031161685,0.0001736706,0.000014516673],"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":[0.000007845016,0.00020731875,0.0011754701,0.000033456014,0.000030948784,0.0000017323594,0.00019378561,0.0000023009031,0.10061905,0.27122244,0.5662294,0.060276274],"study_design_scores_gemma":[0.00023404828,0.00009770848,0.003649854,0.000057881512,0.000006760562,0.000019212132,0.0000180252,0.004077854,0.32878983,0.65809244,0.004819984,0.00013640217],"about_ca_topic_score_codex":0.000008046096,"about_ca_topic_score_gemma":1.6921227e-7,"teacher_disagreement_score":0.6284497,"about_ca_system_score_codex":0.000072222785,"about_ca_system_score_gemma":0.00002003547,"threshold_uncertainty_score":0.9767531},"labels":[],"label_agreement":null},{"id":"W2128418848","doi":"10.14778/1453856.1453926","title":"Dynamic partitioning of the cache hierarchy in shared data centers","year":2008,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":24,"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; Cache; Database; Cache algorithms; Cache invalidation; Quality of service; Computer network; Operating system; Distributed computing; CPU cache","score_opus":0.028961392859703554,"score_gpt":0.23278076208879522,"score_spread":0.20381936922909166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128418848","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":[0.99365133,0.00012124219,0.0003746006,0.0033030037,0.00024144028,0.00035797068,0.000005663809,0.00003639408,0.0019083585],"genre_scores_gemma":[0.9974522,0.000013605352,0.0021548467,0.000106365325,0.000013232498,0.000009797963,7.5981836e-7,0.00000588483,0.00024332126],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871945,0.000016109501,0.00030818672,0.0003071829,0.0004228391,0.00022620667],"domain_scores_gemma":[0.9990987,0.000030369762,0.00025058593,0.0005385713,0.000052938212,0.000028794924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039490088,0.00010544505,0.00015006302,0.000070219314,0.00015232088,0.000030981773,0.0031151078,0.00002242663,0.0000024060407],"category_scores_gemma":[0.00006681892,0.00006337256,0.00007402581,0.00051048154,0.00011119526,0.000062670944,0.0032079187,0.00011351773,0.0000013516948],"study_design_candidate":"observational","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":[0.00014790679,0.0031241123,0.69642156,0.0015629053,0.0006691862,0.000019263629,0.05853932,0.034380022,0.08041113,0.053628717,0.027397431,0.04369844],"study_design_scores_gemma":[0.002262482,0.00014716388,0.35417548,0.0013683571,0.000053000924,0.00006609429,0.000941737,0.59919095,0.03290852,0.0037383277,0.004651378,0.00049649354],"about_ca_topic_score_codex":0.00013702876,"about_ca_topic_score_gemma":0.000010557589,"teacher_disagreement_score":0.56481093,"about_ca_system_score_codex":0.00007476493,"about_ca_system_score_gemma":0.000025745874,"threshold_uncertainty_score":0.5788697},"labels":[],"label_agreement":null},{"id":"W2128841495","doi":"10.14778/2021017.2021019","title":"PLP","year":2011,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":74,"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":"European Social Fund; National Science Foundation","keywords":"Computer science; Heap (data structure); Thread (computing); Parallel computing; Multi-core processor; Distributed computing; Operating system; Programming language","score_opus":0.026744184673494705,"score_gpt":0.21851641650143064,"score_spread":0.19177223182793593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128841495","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":[0.06933273,0.00027652807,0.38408816,0.0019861695,0.0008628227,0.0009628427,0.0000015403064,0.0015047342,0.54098445],"genre_scores_gemma":[0.82586116,0.000013854468,0.1735776,0.00015295338,0.000014751211,0.000012324723,3.945117e-8,0.000004064053,0.00036324473],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99936455,0.0000034711936,0.00015727594,0.00015996094,0.00017972845,0.00013503247],"domain_scores_gemma":[0.99955815,0.000007979255,0.0001412382,0.00014792358,0.000113146045,0.000031583037],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018697054,0.000074509335,0.00008527818,0.00004808853,0.00006868244,0.000028317749,0.0011514993,0.000024265988,0.000008298649],"category_scores_gemma":[0.000027458738,0.000049644914,0.000058008296,0.00023107271,0.000033825057,0.00016756315,0.00044017215,0.000060735605,0.000006103824],"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":[0.000013600292,0.00028484728,0.007944267,0.000059084818,0.000045798482,5.389159e-7,0.005714772,0.000050451155,0.008959356,0.94450206,0.018187206,0.014238011],"study_design_scores_gemma":[0.0003082726,0.00014396335,0.00544449,0.00008325943,0.000010794391,0.000016108634,0.000055217664,0.012080151,0.9155323,0.06267099,0.003427803,0.00022663485],"about_ca_topic_score_codex":0.000019592939,"about_ca_topic_score_gemma":1.3855889e-7,"teacher_disagreement_score":0.90657294,"about_ca_system_score_codex":0.000018631561,"about_ca_system_score_gemma":0.000012581571,"threshold_uncertainty_score":0.21397914},"labels":[],"label_agreement":null},{"id":"W2129889089","doi":"10.14778/1920841.1921055","title":"Just-in-time data integration in action","year":2010,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Semantic Web and Ontologies","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":"University of Toronto","funders":"","keywords":"Data integration; Computer science; Flexibility (engineering); Scalability; Process (computing); Information integration; Set (abstract data type); Ontology-based data integration; Enterprise information integration; System integration; Data virtualization; Database; Data science; Architecture","score_opus":0.054697867894580074,"score_gpt":0.29652098718718384,"score_spread":0.24182311929260375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129889089","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":[0.9916119,0.000023425271,0.00043214415,0.0032277948,0.0005320456,0.0002649999,0.0000010709726,0.000047705966,0.00385891],"genre_scores_gemma":[0.992647,0.000017449049,0.0070929695,0.00007047634,0.000032403193,0.0000112336165,7.699993e-7,0.0000027313638,0.00012500268],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992249,0.000004127684,0.0001859375,0.00023344981,0.00021284625,0.00013871917],"domain_scores_gemma":[0.99952316,0.000029837774,0.0001042955,0.00028499935,0.00004144459,0.000016232521],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048433573,0.00007167927,0.000103248705,0.00009311073,0.000025880812,0.00004912077,0.0017678794,0.000043268265,0.000006052318],"category_scores_gemma":[0.00018988915,0.000047401583,0.000019816021,0.00027664882,0.00003161665,0.000609891,0.0006545596,0.00018305468,0.000009098849],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025759611,0.00029550472,0.049113058,0.000053949894,0.000009532991,0.0000011073091,0.0018095188,0.0000064906335,0.79292655,0.07612143,0.003367491,0.07626961],"study_design_scores_gemma":[0.0010670939,0.00008968022,0.19470315,0.00020308957,0.000014146607,0.000027374423,0.0008229939,0.05703145,0.7206882,0.022618914,0.0024473292,0.0002865752],"about_ca_topic_score_codex":0.00016586123,"about_ca_topic_score_gemma":0.00018923786,"teacher_disagreement_score":0.1455901,"about_ca_system_score_codex":0.00003274931,"about_ca_system_score_gemma":0.00001820632,"threshold_uncertainty_score":0.32851893},"labels":[],"label_agreement":null},{"id":"W2130846554","doi":"10.14778/3402707.3402714","title":"RemusDB","year":2011,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":63,"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; University of Waterloo","funders":"","keywords":"Failover; Computer science; Downtime; Overhead (engineering); Database; Virtualization; High availability; Operating system; Virtual machine; Cloud computing","score_opus":0.02204543285509568,"score_gpt":0.19394199897665343,"score_spread":0.17189656612155774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130846554","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":[0.5940359,0.0001489651,0.0019915425,0.002074814,0.0010921662,0.00051945,5.370134e-7,0.0003166692,0.3998199],"genre_scores_gemma":[0.9878113,0.0000031371226,0.010538749,0.00022036508,0.000052834137,0.000010487596,2.3293559e-8,0.000005812572,0.0013572627],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99908155,0.0000042747592,0.00018858585,0.00023001869,0.00029180836,0.00020376376],"domain_scores_gemma":[0.99947697,0.000009544328,0.00015700125,0.00023323717,0.00007984654,0.000043399312],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027314734,0.000098144876,0.000105094194,0.000052906704,0.0000979747,0.000035448335,0.0015354628,0.000021980999,0.000008308242],"category_scores_gemma":[0.000020805508,0.00006134642,0.00008310732,0.0002701392,0.00004424982,0.000027776046,0.0010556664,0.00008080209,0.00001774015],"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":[0.000016890477,0.00041958483,0.006367983,0.00013542888,0.000114690956,0.0000020357436,0.00923467,0.000051519673,0.007941902,0.90346444,0.016440816,0.055810016],"study_design_scores_gemma":[0.002460879,0.0008357683,0.07069878,0.00061281933,0.000136482,0.00009910867,0.0015698664,0.03638502,0.6398753,0.13365477,0.112336084,0.0013351009],"about_ca_topic_score_codex":0.000046989964,"about_ca_topic_score_gemma":4.052533e-7,"teacher_disagreement_score":0.7698097,"about_ca_system_score_codex":0.000028421642,"about_ca_system_score_gemma":0.000008103347,"threshold_uncertainty_score":0.28532973},"labels":[],"label_agreement":null},{"id":"W2131027594","doi":"10.14778/2733004.2733021","title":"DGFIndex for smart grid","year":2014,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":25,"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; Search engine indexing; Grid file; Database; Grid; Big data; Data mining; Range query (database); Distributed computing; Grid computing; Information retrieval; Web search query; Sargable; Search engine","score_opus":0.009341681633792011,"score_gpt":0.2041474509423922,"score_spread":0.1948057693086002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131027594","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":[0.7357159,0.00020093496,0.11368806,0.030030841,0.0046194224,0.0029095432,0.000004914175,0.00073793717,0.11209241],"genre_scores_gemma":[0.9851859,0.0000016000178,0.012579352,0.0005072637,0.00022418897,0.000051626554,1.4935699e-7,0.000009317573,0.0014405764],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99895275,0.0000054511966,0.00021300804,0.00027992344,0.00029487727,0.0002540128],"domain_scores_gemma":[0.9993838,0.00005589483,0.00017816339,0.00022436964,0.00011016738,0.000047590704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057650387,0.00011639292,0.00014438666,0.000054687363,0.00015720283,0.00008319465,0.0013373544,0.00002697461,0.0000016009184],"category_scores_gemma":[0.000078819285,0.000075714706,0.000138369,0.0001976193,0.000036725232,0.000023684925,0.000736211,0.00006766901,0.000005661131],"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":[0.000027583272,0.0003128128,0.0045328755,0.00041233425,0.00012634687,1.5672929e-7,0.0016148161,0.0010853439,0.0075530396,0.79320294,0.061390214,0.12974152],"study_design_scores_gemma":[0.0023059035,0.0006314164,0.008741931,0.00029513572,0.000072345785,0.000014651715,0.00017323912,0.29522333,0.11386194,0.06554478,0.5125171,0.0006182447],"about_ca_topic_score_codex":0.000014966982,"about_ca_topic_score_gemma":5.5851854e-7,"teacher_disagreement_score":0.7276582,"about_ca_system_score_codex":0.00003439614,"about_ca_system_score_gemma":0.00000826364,"threshold_uncertainty_score":0.3087556},"labels":[],"label_agreement":null},{"id":"W2131164945","doi":"10.14778/2367502.2367512","title":"Solving big data challenges for enterprise application performance management","year":2012,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":232,"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; Scalability; Big data; Data science; Context (archaeology); Analytics; Instrumentation (computer programming); Data management; Enterprise system; System monitoring; Database; Data mining; Operating system","score_opus":0.050458643549431095,"score_gpt":0.2445988120777852,"score_spread":0.19414016852835408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131164945","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":[0.655544,0.0083906315,0.22292022,0.017744223,0.0053523,0.007983917,0.000016346576,0.0009174457,0.08113093],"genre_scores_gemma":[0.98453647,0.00021060152,0.014365145,0.00010836296,0.00028675102,0.0001456365,0.0000010483616,0.000011331422,0.0003346382],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986486,0.000004967377,0.00025236438,0.00037548973,0.00034731583,0.00037127943],"domain_scores_gemma":[0.9989534,0.000029610103,0.0002397541,0.00065390207,0.0000636092,0.000059709386],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008809931,0.00014288655,0.00013520557,0.00007748249,0.00018462937,0.000057550693,0.002611291,0.000026201637,4.464295e-7],"category_scores_gemma":[0.000015346905,0.00010121933,0.00006350873,0.00018030341,0.000029635703,0.00011133165,0.003052684,0.000066531094,0.000005970372],"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":[0.00001463677,0.00035827744,0.0026197792,0.0008979289,0.00011767201,4.8892307e-8,0.0019312069,0.00013149995,0.00087224995,0.05681726,0.0022707705,0.93396866],"study_design_scores_gemma":[0.0025080098,0.00031416837,0.039491046,0.0009266238,0.0002833625,0.000023327904,0.0019323125,0.47421503,0.03387995,0.0041663256,0.4411833,0.0010765292],"about_ca_topic_score_codex":0.0000043165373,"about_ca_topic_score_gemma":3.1608278e-7,"teacher_disagreement_score":0.93289214,"about_ca_system_score_codex":0.000057300927,"about_ca_system_score_gemma":0.0000048587526,"threshold_uncertainty_score":0.48524716},"labels":[],"label_agreement":null},{"id":"W2133246278","doi":"10.14778/1453856.1453895","title":"Efficient search for the top-k probable nearest neighbors in uncertain databases","year":2008,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":149,"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; Data mining; Query optimization; Online aggregation; k-nearest neighbors algorithm; Query language; Semantics (computer science); Information retrieval; Sargable; Object (grammar); Point (geometry); Database; Feature (linguistics); Web query classification; Web search query; Search engine; Artificial intelligence","score_opus":0.05346318793657699,"score_gpt":0.2715280562480217,"score_spread":0.21806486831144467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133246278","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":[0.8509537,0.0015126504,0.086007655,0.03346977,0.0020813877,0.012464797,0.0001696182,0.00037549614,0.012964948],"genre_scores_gemma":[0.9737758,0.00007928286,0.02437377,0.00032936386,0.00009826134,0.00029222222,0.000005310293,0.000014743215,0.0010312637],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985974,0.0000072163457,0.00023198513,0.00033261336,0.00046923594,0.00036157123],"domain_scores_gemma":[0.9993073,0.000115224175,0.00010003809,0.00033559575,0.0001031643,0.000038678783],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064528687,0.00012818976,0.00013612416,0.00008646279,0.00026629298,0.00009554292,0.0018695262,0.000015520287,0.000005675796],"category_scores_gemma":[0.00006846619,0.00007130609,0.000069953276,0.00061238057,0.000105564766,0.00026189876,0.0011306361,0.00010584273,0.0000052425244],"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":[0.00015794214,0.001646169,0.079070285,0.0006771564,0.00019514376,0.000008744637,0.006120609,0.024638068,0.0039788214,0.796243,0.04499962,0.042264413],"study_design_scores_gemma":[0.004220396,0.00039027887,0.047064595,0.0004220211,0.00006859218,0.000025807754,0.0015280664,0.7831204,0.0797512,0.0029186045,0.079629876,0.0008601595],"about_ca_topic_score_codex":0.00019713363,"about_ca_topic_score_gemma":0.0000070675205,"teacher_disagreement_score":0.7933244,"about_ca_system_score_codex":0.00006247049,"about_ca_system_score_gemma":0.000044956945,"threshold_uncertainty_score":0.3474076},"labels":[],"label_agreement":null},{"id":"W2133343243","doi":"10.14778/1920841.1921042","title":"QUICK","year":2010,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Semantic Web and Ontologies","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":"","keywords":"Numbering; Computer science; Schema (genetic algorithms); Information retrieval; Semantic Web; World Wide Web; Linked data; Programming language","score_opus":0.008614527310647397,"score_gpt":0.21608670940417116,"score_spread":0.20747218209352375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133343243","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":[0.9455228,0.00006457438,0.00074181246,0.008290952,0.0014919186,0.000267698,5.4746147e-7,0.00016316854,0.043456517],"genre_scores_gemma":[0.98394316,0.0000061536716,0.015443112,0.00020955365,0.00005318236,0.000011990068,2.671373e-8,0.0000032032758,0.00032958947],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99928886,0.0000015665549,0.00013854823,0.00016968651,0.0002302878,0.00017102594],"domain_scores_gemma":[0.9995577,0.000023818584,0.000107534805,0.00018928657,0.000088302244,0.000033376415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020013298,0.00007666295,0.00009868673,0.000033861732,0.00006924759,0.00006048465,0.0013731763,0.00003417208,0.0000101085525],"category_scores_gemma":[0.00009957433,0.000045543664,0.000064695,0.00016625383,0.00006677637,0.00019464693,0.00047176494,0.00013338089,0.000014589226],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035697815,0.0000706005,0.013330078,0.000031187286,0.000015764068,3.220559e-7,0.00076384644,6.8498736e-7,0.27068347,0.6991968,0.0051077274,0.010795915],"study_design_scores_gemma":[0.00036827783,0.00006970299,0.033610173,0.00002902934,0.000011747258,0.000034797078,0.00016426208,0.0008317136,0.8891436,0.05886644,0.016699592,0.00017068759],"about_ca_topic_score_codex":0.000032777723,"about_ca_topic_score_gemma":0.000006123437,"teacher_disagreement_score":0.6403304,"about_ca_system_score_codex":0.0000089272435,"about_ca_system_score_gemma":0.000018292709,"threshold_uncertainty_score":0.2551726},"labels":[],"label_agreement":null},{"id":"W2133623058","doi":"10.14778/1687627.1687729","title":"Creating competitive products","year":2009,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":62,"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":"Skyline; Dominance (genetics); Set (abstract data type); Computer science; Competitive advantage; Data mining; Business; Marketing","score_opus":0.011451827037985965,"score_gpt":0.21806801338273515,"score_spread":0.20661618634474918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133623058","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":[0.0867401,0.0004020935,0.0070993854,0.051812388,0.0013743496,0.0025361546,0.000012823213,0.0006803196,0.8493424],"genre_scores_gemma":[0.96070087,0.000018310699,0.03717291,0.0004861972,0.0001053931,0.000011153128,8.573751e-7,0.0000043009763,0.0015000242],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999026,0.0000034098975,0.00017259421,0.00027204995,0.0003251069,0.00020086336],"domain_scores_gemma":[0.9994711,0.000011241229,0.00016139884,0.00018852585,0.00013724144,0.000030451916],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024950027,0.00010425088,0.00011615428,0.000052560685,0.00012661799,0.00014150384,0.0012662322,0.000013669468,0.0000040257964],"category_scores_gemma":[0.000067928435,0.00007003898,0.00004455069,0.00040223324,0.0000314223,0.00061087083,0.00045613572,0.00007286852,0.0000099921745],"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":[0.0000037080583,0.00012890398,0.0004104213,0.000034790715,0.000019277337,5.602468e-7,0.00066260796,0.0000028430006,0.015575308,0.94460124,0.0043198233,0.0342405],"study_design_scores_gemma":[0.001422418,0.00062235224,0.03279612,0.00046533026,0.00006334319,0.000022001888,0.00080787245,0.006621058,0.8368195,0.06675237,0.052922327,0.00068528636],"about_ca_topic_score_codex":0.0000065727495,"about_ca_topic_score_gemma":1.5630096e-7,"teacher_disagreement_score":0.87784886,"about_ca_system_score_codex":0.000028885672,"about_ca_system_score_gemma":0.000011220066,"threshold_uncertainty_score":0.28561068},"labels":[],"label_agreement":null},{"id":"W2134489155","doi":"10.14778/2535570.2488332","title":"DAX","year":2013,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Cloud Computing and Resource Management","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":"University of Waterloo","funders":"","keywords":"Computer science; Eventual consistency; Scalability; Cloud computing; Consistency (knowledge bases); Exploit; Database; High availability; Weak consistency; Strong consistency; Distributed computing; Data consistency; Operating system; Consistency model; Computer security","score_opus":0.007384205337364365,"score_gpt":0.18660272779575862,"score_spread":0.17921852245839426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134489155","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":[0.9051675,0.00010380011,0.0011766552,0.0107811885,0.0004868162,0.00063818606,2.282624e-7,0.00019956891,0.08144606],"genre_scores_gemma":[0.99180716,0.0000023094526,0.005386706,0.00036592537,0.00005424538,0.00003232627,2.7565154e-8,0.000005307171,0.002345967],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990542,0.000003863509,0.0001841094,0.00021792472,0.00032474266,0.00021515125],"domain_scores_gemma":[0.99948275,0.000017266204,0.00013750224,0.00021297339,0.00010189271,0.00004763777],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017977462,0.000097502416,0.00010436421,0.000047870504,0.000103830986,0.00011965837,0.0014571133,0.000020385658,0.00001561826],"category_scores_gemma":[0.000023622848,0.00005896127,0.00008505517,0.00027428463,0.000037756774,0.000043549055,0.0011626726,0.00007966259,0.000059897568],"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":[0.0000056275044,0.0005279715,0.011150342,0.0002822157,0.00019033634,9.1235086e-7,0.0045965654,0.0008935212,0.04824752,0.5867401,0.1408057,0.20655921],"study_design_scores_gemma":[0.0028133814,0.00061212474,0.09641494,0.0006918737,0.00009410462,0.00007025065,0.0016259111,0.24228121,0.36644387,0.15242389,0.13501757,0.0015108833],"about_ca_topic_score_codex":0.00007277075,"about_ca_topic_score_gemma":2.0248655e-7,"teacher_disagreement_score":0.43431616,"about_ca_system_score_codex":0.000033144308,"about_ca_system_score_gemma":0.000007136895,"threshold_uncertainty_score":0.27077034},"labels":[],"label_agreement":null},{"id":"W2140944908","doi":"10.14778/1687627.1687722","title":"Improving the performance of list intersection","year":2009,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":45,"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; Intersection (aeronautics); Identifier; Overhead (engineering); Hash function; Sorting; Cache; Parallel computing; Hash table; Data structure; Algorithm; Theoretical computer science; Operating system; Programming language","score_opus":0.0073209096403227154,"score_gpt":0.2025471456109298,"score_spread":0.19522623597060706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140944908","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":[0.9896599,0.00010696723,0.005871165,0.0012561051,0.00042022235,0.00028858075,0.0000016094335,0.000045412104,0.0023500375],"genre_scores_gemma":[0.99581367,0.000018186865,0.003920101,0.00011052737,0.000045611036,0.0000054036295,1.5770617e-7,0.0000022697122,0.00008407359],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992772,0.0000035423705,0.00019048493,0.00014916428,0.00025747836,0.00012218136],"domain_scores_gemma":[0.99942565,0.00001307156,0.00024406948,0.00019179333,0.00010563311,0.000019780882],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025434513,0.00007576347,0.0000893066,0.000033290897,0.00011935916,0.000048351416,0.0010428762,0.000019749727,0.0000026095545],"category_scores_gemma":[0.00002340537,0.00003840383,0.000055688088,0.00020758173,0.000039038434,0.00041505916,0.00039129908,0.0000947562,9.9872e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004561078,0.0002133638,0.0025204783,0.00012642538,0.000023315573,1.480345e-7,0.0025236201,0.00008246111,0.64970684,0.03870257,0.0029585336,0.30309665],"study_design_scores_gemma":[0.00029482544,0.00038693903,0.010202835,0.00017579478,0.000012497981,0.000015023254,0.00016391465,0.112933174,0.87336427,0.0012446936,0.0010958471,0.00011018949],"about_ca_topic_score_codex":0.000050286628,"about_ca_topic_score_gemma":4.4382548e-7,"teacher_disagreement_score":0.30298647,"about_ca_system_score_codex":0.000030518004,"about_ca_system_score_gemma":0.000013238782,"threshold_uncertainty_score":0.19379407},"labels":[],"label_agreement":null},{"id":"W2146496747","doi":"10.14778/2732951.2732957","title":"Workload matters","year":2014,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":32,"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":"SPARQL; RDF; Workload; Computer science; RDF Schema; Simple Knowledge Organization System; Cwm; Set (abstract data type); Linked data; RDF query language; Semantic Web; Information retrieval; Database; Programming language; Operating system; Search engine; Web search query","score_opus":0.007596812784350849,"score_gpt":0.19535866088341539,"score_spread":0.18776184809906454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146496747","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":[0.7327305,0.00061322213,0.03569373,0.10795753,0.003003323,0.0010444571,0.0000011392334,0.000736966,0.1182191],"genre_scores_gemma":[0.9866909,0.000012015431,0.0114313075,0.0015564901,0.00004253438,0.000013568621,2.2741505e-8,0.000003998805,0.00024920475],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99921936,0.000004544055,0.00015388188,0.00018736022,0.00024277695,0.00019210817],"domain_scores_gemma":[0.99956995,0.00003761631,0.00012186388,0.00017992177,0.00005839658,0.000032261472],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025030784,0.00008847086,0.00012209598,0.00003855447,0.00006582998,0.00006938235,0.0012552396,0.000025078141,0.0000062666913],"category_scores_gemma":[0.000060499046,0.000054224474,0.00007071889,0.00017757653,0.000054435077,0.00017208894,0.00043940233,0.00006489455,0.000020866095],"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":[0.00001302869,0.00013147302,0.020820858,0.00013210683,0.000057349353,3.9220086e-7,0.0015163159,0.000020139041,0.046449266,0.81262594,0.038272623,0.07996048],"study_design_scores_gemma":[0.001333945,0.00026684286,0.059768945,0.00046329445,0.000048182214,0.000048115486,0.0004894985,0.006911357,0.7114866,0.14340246,0.07518445,0.0005963156],"about_ca_topic_score_codex":0.00002553347,"about_ca_topic_score_gemma":7.408146e-7,"teacher_disagreement_score":0.6692235,"about_ca_system_score_codex":0.000028580283,"about_ca_system_score_gemma":0.0000073589094,"threshold_uncertainty_score":0.23325685},"labels":[],"label_agreement":null},{"id":"W2147033904","doi":"10.14778/1687627.1687702","title":"Power-law based estimation of set similarity join size","year":2009,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":30,"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":"Hash function; Exploit; Computer science; Set (abstract data type); Similarity (geometry); Algorithm; Data mining; Signature (topology); Representation (politics); Nearest neighbor search; Mathematics; Theoretical computer science; Pattern recognition (psychology); Artificial intelligence; Law","score_opus":0.013244692484878601,"score_gpt":0.23772138781357566,"score_spread":0.22447669532869705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147033904","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":[0.50521785,0.0003095265,0.16400465,0.07835583,0.0022688874,0.005681021,0.00018784525,0.0010870283,0.24288738],"genre_scores_gemma":[0.95186794,0.0000029206983,0.047347084,0.0006768352,0.0000120641835,0.0000061032383,0.0000015429495,0.000003407336,0.00008207885],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988799,0.0000057961624,0.00026946183,0.00022750917,0.00044030845,0.00017704135],"domain_scores_gemma":[0.9993206,0.000034521243,0.00025971324,0.00024340507,0.00010372294,0.000038021688],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040692784,0.00011636167,0.00015944766,0.000048112463,0.00007168551,0.00008574753,0.00113078,0.000027506583,0.000013580965],"category_scores_gemma":[0.00008641793,0.00008492072,0.0000832758,0.0003195642,0.000048105634,0.0007320715,0.0002806361,0.00007289115,0.000003362216],"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":[0.000040116716,0.00073275086,0.00063613616,0.0002438461,0.000062686166,0.0000013006453,0.0010119908,0.00076761394,0.034989346,0.921275,0.013934904,0.02630431],"study_design_scores_gemma":[0.0019761736,0.00073618774,0.016511053,0.0002923399,0.00006574018,0.000003990584,0.00013212302,0.17396654,0.70694554,0.09411918,0.0047675455,0.00048358325],"about_ca_topic_score_codex":0.00001843906,"about_ca_topic_score_gemma":4.151098e-7,"teacher_disagreement_score":0.8271558,"about_ca_system_score_codex":0.000031768825,"about_ca_system_score_gemma":0.00001480871,"threshold_uncertainty_score":0.34629664},"labels":[],"label_agreement":null},{"id":"W2148524305","doi":"10.14778/1687627.1687771","title":"Framework for evaluating clustering algorithms in duplicate detection","year":2009,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":232,"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; Scalability; Cluster analysis; Data mining; Data deduplication; Process (computing); Algorithm; Machine learning; Database","score_opus":0.2418184006816228,"score_gpt":0.4629068859449667,"score_spread":0.2210884852633439,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148524305","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":[0.6674408,0.00016132377,0.30533537,0.016225928,0.0012386088,0.0041166223,0.00002894418,0.0001130461,0.005339356],"genre_scores_gemma":[0.9677308,0.000009590512,0.031421784,0.00048005677,0.000062763924,0.00009428709,4.5452225e-7,0.000005713973,0.00019453176],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978746,0.000017025968,0.000615692,0.0003701682,0.0008803767,0.00024213053],"domain_scores_gemma":[0.9988445,0.00029036397,0.0004058883,0.00022132986,0.00019980743,0.00003808988],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050753765,0.00010910629,0.0002029045,0.00011357587,0.00012783127,0.00015875141,0.00087569474,0.000049476246,0.0000142673825],"category_scores_gemma":[0.002896374,0.00007238074,0.00010822406,0.0005809948,0.000031867115,0.00029746705,0.00028571495,0.00011608299,0.000009187585],"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":[0.00014245746,0.00016941174,0.0004795575,0.000051535797,0.000017554423,1.2090392e-7,0.0015157416,0.00055106037,0.029401027,0.028678663,0.00073739997,0.9382555],"study_design_scores_gemma":[0.0009947035,0.00048885896,0.015678296,0.00022552047,0.00003471868,0.0000030283948,0.002768579,0.04831654,0.121707596,0.80476844,0.0047707963,0.00024289833],"about_ca_topic_score_codex":0.00002863098,"about_ca_topic_score_gemma":0.000012477404,"teacher_disagreement_score":0.9380126,"about_ca_system_score_codex":0.00008238278,"about_ca_system_score_gemma":0.000007840089,"threshold_uncertainty_score":0.34674394},"labels":[],"label_agreement":null},{"id":"W2151131744","doi":"10.14778/1687553.1687573","title":"Efficient index compression in DB2 LUW","year":2009,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":31,"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 Alberta; IBM (Canada)","funders":"","keywords":"Computer science; Index (typography); Workload; Unix; Database; Response time; Data compression; Memory footprint; Real-time computing; Operating system","score_opus":0.007764069645988815,"score_gpt":0.22779144631109907,"score_spread":0.22002737666511027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151131744","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":[0.9165519,0.0005327943,0.06289619,0.0035942595,0.0006916636,0.0011402003,0.000008426266,0.00017319672,0.014411372],"genre_scores_gemma":[0.99054056,0.000007921843,0.009156475,0.00015473837,0.000025710739,0.000014018364,2.4045315e-7,0.0000034121595,0.00009692401],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989137,0.0000059051436,0.00027020302,0.0002484433,0.0003441815,0.00021754041],"domain_scores_gemma":[0.99949527,0.000015246482,0.00017764817,0.00019715975,0.00007114759,0.000043539512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022551797,0.00011389749,0.00016307975,0.00008058458,0.00007209612,0.00002488386,0.00059199036,0.000028502875,0.0000024812205],"category_scores_gemma":[0.000033160235,0.0000723396,0.00005086929,0.00035378095,0.000033171425,0.00017445254,0.00033930485,0.00010868475,0.0000033731374],"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":[0.000049952374,0.0005025653,0.007991923,0.00010930864,0.000011541368,0.0000028412207,0.0026166965,0.00433651,0.12949935,0.82844305,0.0014402991,0.024995983],"study_design_scores_gemma":[0.004281908,0.00061220606,0.16645885,0.0024254357,0.000017892822,0.00008030532,0.0011179873,0.16956392,0.58410555,0.028336948,0.04186279,0.001136217],"about_ca_topic_score_codex":0.000033022985,"about_ca_topic_score_gemma":0.0000018667484,"teacher_disagreement_score":0.8001061,"about_ca_system_score_codex":0.000058270245,"about_ca_system_score_gemma":0.000015991413,"threshold_uncertainty_score":0.29499233},"labels":[],"label_agreement":null},{"id":"W2152102944","doi":"10.14778/2536354.2536355","title":"Hybrid storage management for database systems","year":2013,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Data Storage Technologies","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Database; Workload; Storage management; Data striping; Computer data storage; Flash (photography); Operating system; Distributed computing","score_opus":0.01574298037299049,"score_gpt":0.22913046462758513,"score_spread":0.21338748425459464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152102944","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":[0.07523427,0.0011059326,0.898228,0.004107407,0.0025489032,0.009450664,0.00017470661,0.0015089551,0.00764118],"genre_scores_gemma":[0.826055,0.000058848975,0.17140229,0.00012277681,0.000039807946,0.0013257551,0.0000041020244,0.000018128374,0.0009733048],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99861205,0.000003202095,0.00029309533,0.000408166,0.0003536451,0.00032983843],"domain_scores_gemma":[0.9988942,0.00003789157,0.0002710086,0.00057865283,0.00017157284,0.000046668134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024750008,0.00016778373,0.00018524713,0.000107861764,0.00012433442,0.00015176652,0.0025344265,0.00002442576,0.0000036485187],"category_scores_gemma":[0.000073939984,0.000115431234,0.00007021053,0.00021855623,0.0000761857,0.0010311749,0.00185766,0.00009019385,0.000022963433],"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":[0.000008479612,0.00014261523,0.000098146535,0.000676112,0.00008981577,0.0000018356325,0.00012072632,0.00012262672,0.03355996,0.8658372,0.08056906,0.018773401],"study_design_scores_gemma":[0.0032944516,0.0005451636,0.00072332396,0.0008933597,0.00013799552,0.00010987407,0.0021672917,0.08687318,0.6075168,0.16779839,0.12850915,0.0014309793],"about_ca_topic_score_codex":0.000029866484,"about_ca_topic_score_gemma":1.6162515e-7,"teacher_disagreement_score":0.7508207,"about_ca_system_score_codex":0.00011255758,"about_ca_system_score_gemma":0.000008906808,"threshold_uncertainty_score":0.47096375},"labels":[],"label_agreement":null},{"id":"W2153257312","doi":"10.14778/1687553.1687599","title":"Linkage Query Writer","year":2009,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":25,"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; SQL; Linkage (software); Interface (matter); Query language; Relational database; Linked data; Information retrieval; Process (computing); Programming language; Semantic Web","score_opus":0.1069606726619127,"score_gpt":0.37673219067138963,"score_spread":0.26977151800947696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153257312","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":[0.52583367,0.00033293842,0.0005984133,0.060149252,0.001165907,0.0013792233,0.000054156266,0.00014660775,0.4103398],"genre_scores_gemma":[0.987714,0.000028470464,0.0011292371,0.0030998958,0.00008960261,0.000010192375,8.515854e-7,0.000004637972,0.00792313],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974978,0.000016371505,0.0005678878,0.00034101374,0.0013441306,0.00023278913],"domain_scores_gemma":[0.998924,0.000103251616,0.0003309851,0.00035624963,0.00021935489,0.00006612787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002614618,0.000121788005,0.00021339851,0.00013023934,0.000113978145,0.00023526562,0.0016816239,0.000039460756,0.00017769769],"category_scores_gemma":[0.0008320099,0.000068434376,0.00015776599,0.00050039805,0.00007421353,0.00042646716,0.0004456585,0.00011386843,0.00014676094],"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":[0.000071081195,0.0004986149,0.0031908536,0.00004247603,0.00004835114,0.0000014295003,0.0020303852,0.000012882975,0.022937521,0.3614002,0.4590149,0.15075134],"study_design_scores_gemma":[0.0007251982,0.0002346121,0.035571966,0.000105847656,0.00004529116,0.0000064506507,0.002255354,0.00013275868,0.06783639,0.370855,0.52194834,0.00028280387],"about_ca_topic_score_codex":0.000016949567,"about_ca_topic_score_gemma":0.0000021430108,"teacher_disagreement_score":0.4618803,"about_ca_system_score_codex":0.00003447633,"about_ca_system_score_gemma":0.000012256058,"threshold_uncertainty_score":0.31249034},"labels":[],"label_agreement":null},{"id":"W2153974857","doi":"10.14778/3402707.3402754","title":"Efficient rank join with aggregation constraints","year":2011,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Join (topology); Computer science; Rank (graph theory); Probabilistic logic; Semantics (computer science); Theoretical computer science; Data mining; Artificial intelligence; Mathematics; Programming language","score_opus":0.01904745898815237,"score_gpt":0.1970963168557973,"score_spread":0.1780488578676449,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153974857","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":[0.60174406,0.00016285547,0.113404095,0.0028814964,0.0012823336,0.002991883,0.0000183265,0.0005226342,0.27699232],"genre_scores_gemma":[0.96600693,0.0000054811358,0.033579387,0.000099674704,0.000019677846,0.00002500987,4.5881185e-7,0.000005642871,0.00025772263],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99902564,0.00000387405,0.00017157457,0.00024487753,0.00036169853,0.00019233786],"domain_scores_gemma":[0.99947006,0.000007924704,0.00019218386,0.00018522344,0.0001030137,0.0000415713],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027603665,0.00011039282,0.00010745942,0.00006884943,0.00008116889,0.000069131376,0.000981235,0.00001712151,0.000023691991],"category_scores_gemma":[0.000016650622,0.000065974054,0.00004374979,0.00030637666,0.00012458814,0.00021788021,0.00040701675,0.00006237887,0.000014783052],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000070737166,0.00072849786,0.0068533295,0.00019784346,0.00019565817,0.0000052010814,0.006316897,0.00006390357,0.007089181,0.8023242,0.0038459194,0.17230868],"study_design_scores_gemma":[0.006278842,0.0011124474,0.037374686,0.0010143685,0.00021437342,0.0000978485,0.0017400839,0.06704925,0.85529274,0.023329943,0.005187639,0.0013077559],"about_ca_topic_score_codex":0.000017976505,"about_ca_topic_score_gemma":6.369735e-7,"teacher_disagreement_score":0.8482036,"about_ca_system_score_codex":0.000026271971,"about_ca_system_score_gemma":0.000014708351,"threshold_uncertainty_score":0.2690344},"labels":[],"label_agreement":null},{"id":"W2154764667","doi":"10.14778/1453856.1453953","title":"On efficiently searching trajectories and archival data for historical similarities","year":2008,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":24,"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 Alberta; IBM (Canada)","funders":"","keywords":"Computer science; False positive paradox; Series (stratigraphy); Computation; Similarity (geometry); Set (abstract data type); Data mining; Class (philosophy); Algorithm; Artificial intelligence","score_opus":0.05566045184704826,"score_gpt":0.2447184203810245,"score_spread":0.18905796853397625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154764667","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":[0.95474476,0.0006042215,0.03123226,0.0051400904,0.00065276545,0.00091868127,0.000061545645,0.0001525357,0.0064931684],"genre_scores_gemma":[0.9830872,0.00002789305,0.016338753,0.00006914459,0.0000725925,0.0000127867515,0.0000015756661,0.000007761469,0.00038231484],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988823,0.000005488724,0.0002098991,0.00033792848,0.00033917083,0.00022523952],"domain_scores_gemma":[0.9993481,0.00014613046,0.0001235527,0.00025591,0.00007349587,0.000052811018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034386292,0.00011013181,0.00018566362,0.000066137414,0.0004166428,0.00007162149,0.001111906,0.000016881066,9.939707e-7],"category_scores_gemma":[0.0002197885,0.00007383522,0.00007066757,0.0001717306,0.00009652716,0.00025992145,0.00082999223,0.00010313218,2.904041e-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":[0.00026844814,0.00061763887,0.0054865666,0.0005613739,0.0002834078,0.0000033921522,0.015291169,0.0005578502,0.017539594,0.87695223,0.028700568,0.053737782],"study_design_scores_gemma":[0.0049670795,0.0038033305,0.026470706,0.0008349237,0.00033883794,0.00035750854,0.002184874,0.68612486,0.09738377,0.090784736,0.08464552,0.0021038859],"about_ca_topic_score_codex":0.00005270056,"about_ca_topic_score_gemma":0.000001617955,"teacher_disagreement_score":0.7861675,"about_ca_system_score_codex":0.000065149005,"about_ca_system_score_gemma":0.000026243775,"threshold_uncertainty_score":0.32045215},"labels":[],"label_agreement":null},{"id":"W2154768509","doi":"10.14778/1453856.1453934","title":"Efficient network aware search in collaborative tagging sites","year":2008,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":112,"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":"Computer science; Popularity; Cluster analysis; Seekers; Context (archaeology); Upper and lower bounds; Heuristic; Space (punctuation); Information retrieval; Data mining; Machine learning; Artificial intelligence; Mathematics; Geography","score_opus":0.018816654655215464,"score_gpt":0.23477065336095104,"score_spread":0.2159539987057356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154768509","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":[0.9747671,0.00035982757,0.00432007,0.004400143,0.00048864394,0.001326805,0.000009366853,0.00015596596,0.014172111],"genre_scores_gemma":[0.9895294,0.000048593552,0.00972097,0.00018131685,0.000069703354,0.00003373873,0.0000011088049,0.0000070043347,0.0004082226],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986108,0.000011078361,0.00023007812,0.00031239146,0.0004804363,0.00035524115],"domain_scores_gemma":[0.999478,0.00003446865,0.00011743337,0.00017955517,0.00014571472,0.00004486928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004507724,0.00012700396,0.00016176351,0.00010441744,0.00020938404,0.00008293162,0.0012235133,0.000022817354,0.0000064809333],"category_scores_gemma":[0.000027871212,0.000091118745,0.000047503312,0.0013564816,0.00008518548,0.00023501576,0.0011413633,0.00012440185,0.000012018997],"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":[0.00013794436,0.0021178825,0.30759266,0.0006833361,0.00030709882,0.00007817216,0.038362216,0.07795362,0.016759776,0.40205416,0.12662037,0.027332757],"study_design_scores_gemma":[0.0035446377,0.00045877375,0.06893806,0.00077425846,0.000038441878,0.000036559373,0.0031868154,0.8175385,0.085904926,0.0046848003,0.013697199,0.0011970558],"about_ca_topic_score_codex":0.000024363851,"about_ca_topic_score_gemma":0.0000025083327,"teacher_disagreement_score":0.73958486,"about_ca_system_score_codex":0.00007358609,"about_ca_system_score_gemma":0.000035867382,"threshold_uncertainty_score":0.37157145},"labels":[],"label_agreement":null},{"id":"W2156972533","doi":"10.14778/1920841.1920874","title":"SECRET","year":2010,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":109,"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; Semantics (computer science); Key (lock); Variation (astronomy); Range (aeronautics); Window (computing); World Wide Web; Programming language; Computer security; Engineering","score_opus":0.004724064018066928,"score_gpt":0.20121431826377942,"score_spread":0.19649025424571248,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156972533","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":[0.84001786,0.00018914328,0.06407565,0.0069081103,0.004650925,0.0012967284,0.000035631132,0.00045974844,0.08236623],"genre_scores_gemma":[0.92730975,0.0000062181293,0.071846545,0.00013706723,0.00009145513,0.000029267343,3.2735093e-7,0.000006250909,0.0005731018],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99925953,0.000001738615,0.00016108358,0.00018324687,0.00023692833,0.0001574476],"domain_scores_gemma":[0.99946684,0.000014156902,0.00014293911,0.00022746752,0.00010345728,0.000045120043],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019094943,0.000084406944,0.00010256151,0.000029150833,0.00008796471,0.000028898348,0.0006923235,0.000025042607,0.0000115588955],"category_scores_gemma":[0.000060271203,0.000051671,0.00005470856,0.00017680172,0.00005752678,0.00041687625,0.0005016081,0.00013268665,0.000009644829],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017137397,0.0000179469,0.00094037864,0.000023773639,0.000005811545,1.4156481e-7,0.0002592755,7.534778e-7,0.211792,0.78322905,0.0014040106,0.0023251257],"study_design_scores_gemma":[0.00030817365,0.00004991636,0.0023133631,0.000054122163,0.000006324271,0.00004152394,0.00012678008,0.0005778935,0.72385365,0.012190359,0.26029432,0.00018356944],"about_ca_topic_score_codex":0.00002632655,"about_ca_topic_score_gemma":0.0000056044446,"teacher_disagreement_score":0.7710387,"about_ca_system_score_codex":0.000010012671,"about_ca_system_score_gemma":0.000017479135,"threshold_uncertainty_score":0.21070822},"labels":[],"label_agreement":null},{"id":"W2159157420","doi":"10.14778/1454159.1454222","title":"Scheduling continuous queries in data stream management systems","year":2008,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Database Systems and Queries","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":"University of Toronto","funders":"","keywords":"Computer science; Salient; Scheduling (production processes); Distributed computing; Operations research; Mathematical optimization; Artificial intelligence","score_opus":0.03159481624336894,"score_gpt":0.24339173839996645,"score_spread":0.2117969221565975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159157420","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":[0.7923319,0.006460499,0.15076892,0.002654699,0.0038091522,0.0053662257,0.00022873728,0.00069066085,0.037689243],"genre_scores_gemma":[0.93913877,0.00028827772,0.059666898,0.00004229101,0.00005971021,0.00008246927,0.0000049062855,0.00001217311,0.00070452713],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99839145,0.000009751829,0.00044494128,0.00044867065,0.0004177252,0.00028748444],"domain_scores_gemma":[0.99891967,0.00002427719,0.0002734864,0.00064577523,0.000089716996,0.000047057045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039422058,0.00016253669,0.00026929364,0.000096144344,0.00014061134,0.000045562938,0.0015846019,0.00002947938,0.0000013857345],"category_scores_gemma":[0.00004626315,0.00011436216,0.000038202,0.00037250097,0.000094955234,0.0010118962,0.0019932245,0.00010678152,0.000005029685],"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":[0.000027232538,0.00022889175,0.016808838,0.0006683237,0.00009477843,0.000026504807,0.0019015725,0.0005736235,0.0034774912,0.96983296,0.002690732,0.003669038],"study_design_scores_gemma":[0.011265027,0.0007517508,0.03881773,0.009506338,0.00019643587,0.0016245485,0.034170926,0.10581725,0.13397351,0.0077462466,0.6518935,0.004236733],"about_ca_topic_score_codex":0.00023110802,"about_ca_topic_score_gemma":0.000011634272,"teacher_disagreement_score":0.96208674,"about_ca_system_score_codex":0.000062664825,"about_ca_system_score_gemma":0.000025690124,"threshold_uncertainty_score":0.46635535},"labels":[],"label_agreement":null},{"id":"W2160152607","doi":"10.14778/1687627.1687754","title":"Efficient method for maximizing bichromatic reverse nearest neighbor","year":2009,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":129,"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":"Computer science; k-nearest neighbors algorithm; Point (geometry); Best bin first; Exponential function; Algorithm; Exponential growth; Theoretical computer science; Mathematics; Artificial intelligence","score_opus":0.014581193934234049,"score_gpt":0.25726412710710916,"score_spread":0.24268293317287512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160152607","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":[0.02502903,0.00025923093,0.9225783,0.029909458,0.0014680016,0.003988468,0.00002602421,0.0004478864,0.016293654],"genre_scores_gemma":[0.23784995,0.000010376794,0.760218,0.0010742566,0.00010261156,0.000066626446,0.0000015270398,0.0000115799785,0.00066507043],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99870026,0.000006684613,0.00028588108,0.0003376298,0.00036457035,0.0003049485],"domain_scores_gemma":[0.99927527,0.00004986282,0.00024026011,0.00027287612,0.00010518329,0.0000565302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066532433,0.00015014,0.00019244294,0.000094866045,0.00015238248,0.0001758173,0.0014844986,0.000026541322,0.000004913277],"category_scores_gemma":[0.00009940144,0.00010269854,0.00013011043,0.0004159688,0.000023536906,0.00023482196,0.00043015013,0.00006970707,0.0000069882067],"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":[0.000035042725,0.0005335892,0.000106609805,0.00037032375,0.000086717766,0.0000016353182,0.0014631114,0.00080195116,0.036367804,0.72198945,0.029689725,0.20855404],"study_design_scores_gemma":[0.0021429516,0.000513093,0.0032801377,0.00038131492,0.00013333779,0.000016350707,0.0003618814,0.8581399,0.08078135,0.029616717,0.02408257,0.0005503957],"about_ca_topic_score_codex":0.000014563547,"about_ca_topic_score_gemma":2.6863043e-7,"teacher_disagreement_score":0.85733795,"about_ca_system_score_codex":0.00005380619,"about_ca_system_score_gemma":0.000015660733,"threshold_uncertainty_score":0.4187925},"labels":[],"label_agreement":null},{"id":"W2162783807","doi":"10.14778/2021017.2021025","title":"Keyword search in graphs","year":2011,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":132,"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":"Substructure; Clique; Computer science; Graph; Combinatorics; Theoretical computer science; Time complexity; Mathematics; Algorithm","score_opus":0.036510813204070874,"score_gpt":0.2195111061961708,"score_spread":0.18300029299209994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162783807","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":[0.6515311,0.00023311931,0.0035395457,0.0030617833,0.0011405783,0.0016707658,0.0000066373755,0.00026579708,0.33855066],"genre_scores_gemma":[0.9822847,0.000039512935,0.016867494,0.00011877169,0.00001440654,0.000025542333,2.550495e-7,0.0000054437082,0.00064386055],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99903995,0.0000044733943,0.00017841053,0.00023361894,0.00030696095,0.00023657524],"domain_scores_gemma":[0.9996407,0.000007751302,0.000070842114,0.00019388298,0.000051583353,0.00003522365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040177046,0.00008809684,0.000101076876,0.0001424784,0.000042860283,0.000056693843,0.0017915879,0.00001831342,0.000016776954],"category_scores_gemma":[0.000013339024,0.000060204766,0.000053333162,0.0005919952,0.000046072717,0.000541179,0.0010697949,0.00009520025,0.000015416905],"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":[0.0000141689425,0.00032612952,0.039409887,0.00008708902,0.000034361397,0.0000025839072,0.0039617964,0.0000016882801,0.002874808,0.90280986,0.0032588637,0.047218792],"study_design_scores_gemma":[0.002839522,0.00051424874,0.24037719,0.00041102731,0.000041173687,0.000016320679,0.0015112209,0.010010333,0.45108527,0.2804068,0.011857077,0.00092981005],"about_ca_topic_score_codex":0.00012554941,"about_ca_topic_score_gemma":0.000003667571,"teacher_disagreement_score":0.622403,"about_ca_system_score_codex":0.000022814145,"about_ca_system_score_gemma":0.000009097477,"threshold_uncertainty_score":0.3329246},"labels":[],"label_agreement":null},{"id":"W2163438246","doi":"10.14778/1687553.1687556","title":"StatAdvisor","year":2009,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada); University of Waterloo","funders":"","keywords":"Computer science; IBM; Matching (statistics); SQL; Data mining; Oracle; Key (lock); Plan (archaeology); Construct (python library); Workload; Query plan; Information retrieval; Database; Statistics; Software engineering; Web search query; Mathematics; Sargable; Search engine; Programming language","score_opus":0.00712529554645085,"score_gpt":0.21475078658725172,"score_spread":0.20762549104080086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163438246","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":[0.3110972,0.0021420657,0.49768364,0.03613176,0.0028054875,0.0035635203,0.000089927955,0.001196905,0.14528947],"genre_scores_gemma":[0.924416,0.000029324068,0.074315324,0.00046362422,0.000055587,0.000014734784,4.5643256e-7,0.0000046034324,0.00070036994],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991847,0.0000025014126,0.00018743573,0.00019034542,0.00025856847,0.00017644964],"domain_scores_gemma":[0.9995141,0.000010085019,0.00014954267,0.00019461087,0.000090441084,0.000041197076],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014360667,0.000090722475,0.000117716765,0.000033572287,0.00008157266,0.00002825582,0.0006073239,0.000015436293,0.000003622939],"category_scores_gemma":[0.00003555743,0.000056136287,0.000055188844,0.00021862157,0.000028802295,0.0005249464,0.00022108211,0.000060428058,0.000006862375],"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":[0.000004979741,0.000047533475,0.0002154073,0.000020869633,0.000006545154,3.082437e-7,0.00040324224,0.0000065778154,0.036710158,0.94449466,0.0033230032,0.014766707],"study_design_scores_gemma":[0.00088065985,0.0004020905,0.008882077,0.00023711026,0.00001497516,0.00004771358,0.00038214625,0.00107291,0.6723152,0.05298606,0.26235396,0.00042512483],"about_ca_topic_score_codex":0.000010741815,"about_ca_topic_score_gemma":4.9572657e-7,"teacher_disagreement_score":0.89150864,"about_ca_system_score_codex":0.000026275979,"about_ca_system_score_gemma":0.000015163176,"threshold_uncertainty_score":0.22891712},"labels":[],"label_agreement":null},{"id":"W2168284908","doi":"10.14778/2757807.2757808","title":"ALID","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China; National Science Foundation","keywords":"Speedup; Scalability; Computer science; Parameterized complexity; Time complexity; Graph; Theoretical computer science; Algorithm; Parallel computing","score_opus":0.021096972285128485,"score_gpt":0.22558753531170597,"score_spread":0.20449056302657748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168284908","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":[0.9663441,0.00037554334,0.000020339061,0.0004813199,0.00013887922,0.00020166092,0.0000030936035,0.000006791138,0.03242823],"genre_scores_gemma":[0.99791723,0.000037216178,0.0008190228,0.0001364066,0.00007354117,0.000016714324,0.0000034372752,0.00000823587,0.0009881868],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994991,0.0000017040261,0.00015763547,0.00008924739,0.00013253956,0.00011976772],"domain_scores_gemma":[0.9996187,0.0000010875589,0.000109891975,0.00010579212,0.00012213859,0.000042362597],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016994732,0.00007941939,0.000078805875,0.0000140199945,0.000029450164,0.00001685574,0.000277248,0.00003891052,0.0000029620987],"category_scores_gemma":[0.000060705454,0.000050328286,0.00006492724,0.000059141916,0.000025847008,0.0000046660944,0.0002452173,0.000037180736,0.0000044502312],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000121636454,0.00014758503,0.011204921,0.0000959107,0.00012805506,5.6730205e-8,0.00071804906,0.000043257343,0.90807545,0.0053004427,0.071844615,0.0023200137],"study_design_scores_gemma":[0.0005975573,0.00018268127,0.00091245316,0.000015280495,0.000017656364,0.000013659714,0.0007720451,0.00007760332,0.93055034,0.0006459326,0.06611271,0.00010206286],"about_ca_topic_score_codex":0.000009019654,"about_ca_topic_score_gemma":4.6634253e-7,"teacher_disagreement_score":0.0315731,"about_ca_system_score_codex":0.000010668016,"about_ca_system_score_gemma":0.000024151923,"threshold_uncertainty_score":0.2052328},"labels":[],"label_agreement":null},{"id":"W2168773517","doi":"10.14778/2556549.2556568","title":"Expressiveness and complexity of order dependencies","year":2013,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada); York University; University of Toronto","funders":"","keywords":"Lexicographical order; Inference; Functional dependency; Tuple; Completeness (order theory); Computer science; Time complexity; SQL; Theoretical computer science; Dependency (UML); Class (philosophy); Rule of inference; Mathematics; Algorithm; Relational database; Discrete mathematics; Data mining; Artificial intelligence; Combinatorics; Programming language","score_opus":0.02515564258788441,"score_gpt":0.22424121724989018,"score_spread":0.19908557466200577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168773517","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":[0.9532568,0.00050288194,0.040075123,0.0011742834,0.00024680397,0.0008171437,0.000017861905,0.000059349415,0.0038497539],"genre_scores_gemma":[0.94398093,0.000021247693,0.055792622,0.000034411496,0.000012893121,0.000043895856,2.3716773e-7,0.0000037860082,0.0001099974],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99925846,0.0000049995706,0.00020443434,0.00017040578,0.00023089976,0.00013083013],"domain_scores_gemma":[0.99928015,0.000022855098,0.00022368913,0.00015613041,0.00028148483,0.00003567472],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011254465,0.00008854545,0.00016316636,0.00003043019,0.000071861294,0.000024786701,0.00041284531,0.000018672576,0.000011432151],"category_scores_gemma":[0.00005275162,0.000054814507,0.000029753688,0.00015412395,0.00019671298,0.00060606166,0.0006673933,0.00004632508,0.0000017303055],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005198078,0.000056209046,0.006440476,0.00028653757,0.000024150744,1.2860878e-7,0.0013331845,0.000007917286,0.23731883,0.75081736,0.0006258588,0.0030841455],"study_design_scores_gemma":[0.0005145108,0.00009020259,0.02592584,0.00028189315,0.000010924184,0.000025501404,0.001176789,0.0013012029,0.93200916,0.034840997,0.0036046738,0.00021831683],"about_ca_topic_score_codex":0.0002784749,"about_ca_topic_score_gemma":0.0000037989637,"teacher_disagreement_score":0.71597636,"about_ca_system_score_codex":0.000011061042,"about_ca_system_score_gemma":0.000014518514,"threshold_uncertainty_score":0.22352707},"labels":[],"label_agreement":null},{"id":"W2170712852","doi":"10.14778/2536258.2536262","title":"Discovering denial constraints","year":2013,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":252,"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; Rotation formalisms in three dimensions; Scalability; Inference; Data integrity; Set (abstract data type); Functional dependency; Constraint (computer-aided design); Theoretical computer science; Rank (graph theory); Semantics (computer science); Function (biology); Data mining; Artificial intelligence; Programming language; Database; Relational database","score_opus":0.08220481571088507,"score_gpt":0.3393964871060694,"score_spread":0.25719167139518434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170712852","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":[0.9038038,0.000025454941,0.00033549845,0.0057185395,0.00057440385,0.0007748185,0.000021429629,0.000032555618,0.08871349],"genre_scores_gemma":[0.99609274,0.0000069362504,0.0008359857,0.00035721285,0.000053452586,0.00004491731,4.5436397e-7,0.000005284103,0.0026030438],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997828,0.00001201534,0.00049279537,0.00028836506,0.0011550064,0.0002238247],"domain_scores_gemma":[0.9990573,0.00012386074,0.0003090717,0.0002336129,0.00020846954,0.00006767515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013059851,0.000107117456,0.00018252133,0.00008216985,0.00011224229,0.0003418665,0.0013534825,0.000025906991,0.000868397],"category_scores_gemma":[0.00093292526,0.000059682367,0.00011486481,0.00031202333,0.00024000049,0.0006437655,0.0009307045,0.00008061975,0.00035296645],"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":[0.00004327157,0.0003753887,0.024586255,0.00010308034,0.00014666413,7.799481e-7,0.0035542452,0.000041848674,0.07121547,0.41926512,0.27565965,0.20500822],"study_design_scores_gemma":[0.0021791435,0.00022566343,0.104418725,0.00024175047,0.000099229044,0.000023338467,0.023336178,0.00071541825,0.20724429,0.49402764,0.16674235,0.0007462656],"about_ca_topic_score_codex":0.0001441624,"about_ca_topic_score_gemma":0.0000064045,"teacher_disagreement_score":0.20426196,"about_ca_system_score_codex":0.000034927045,"about_ca_system_score_gemma":0.000015266527,"threshold_uncertainty_score":0.9508338},"labels":[],"label_agreement":null},{"id":"W2182859693","doi":"10.14778/3402707.3402711","title":"A Framework for supporting DBMS-like indexes in the cloud","year":2011,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Caching and Content Delivery","field":"Computer Science","cited_by":47,"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; Scalability; Cloud computing; Search engine indexing; Distributed computing; Database; Distributed database; Overhead (engineering); Node (physics); Hash table; High availability; Data mining; Hash function; Operating system; Information retrieval","score_opus":0.04723732750376692,"score_gpt":0.26008486779994716,"score_spread":0.21284754029618025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2182859693","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":[0.96807426,0.00021929106,0.019808583,0.0036762874,0.0012352014,0.001332649,0.0000042712795,0.000109441244,0.005539991],"genre_scores_gemma":[0.9900708,0.000008693403,0.008874674,0.000769817,0.00007820106,0.000111776906,1.37188e-7,0.0000068595973,0.00007901212],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988817,0.000010044774,0.00029006784,0.00024023537,0.00028829454,0.00028964778],"domain_scores_gemma":[0.99931175,0.0001122018,0.00024739452,0.00021387122,0.000086188054,0.000028615135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00091663736,0.00011631574,0.00014293352,0.000060687526,0.000121697034,0.00007936658,0.001662392,0.000048537924,0.0000032281362],"category_scores_gemma":[0.00017130666,0.000066442735,0.00013635072,0.00026770777,0.000041904168,0.00019959861,0.00032264856,0.00019639003,0.0000023524917],"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":[0.00006702128,0.0003055325,0.024421643,0.00010919608,0.000048166494,0.0000014750032,0.024752783,0.0000048400207,0.0048850845,0.93058896,0.002135095,0.012680201],"study_design_scores_gemma":[0.0022500409,0.00080669427,0.02228553,0.0009230469,0.000107100714,0.00008164313,0.008515564,0.0092908405,0.07816207,0.8715952,0.005123303,0.0008589637],"about_ca_topic_score_codex":0.00012348965,"about_ca_topic_score_gemma":0.0000046635323,"teacher_disagreement_score":0.07327698,"about_ca_system_score_codex":0.000030144975,"about_ca_system_score_gemma":0.000022222946,"threshold_uncertainty_score":0.30891657},"labels":[],"label_agreement":null},{"id":"W2189052568","doi":"10.14778/2850583.2850586","title":"The iBench integration metadata generator","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":59,"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":"Metadata; Computer science; Schema evolution; Data integration; Generality; Schema (genetic algorithms); Generator (circuit theory); Data mapping; Data element; Data science; Information retrieval; Data mining; Database; World Wide Web; Database schema","score_opus":0.2684436286050799,"score_gpt":0.39426327919983467,"score_spread":0.12581965059475475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2189052568","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":[0.56227,0.0032114782,0.012688137,0.14513184,0.010125631,0.0055021625,0.00031568826,0.00026482655,0.26049027],"genre_scores_gemma":[0.98278195,0.0000670096,0.0018297815,0.00080366945,0.00015287891,0.00007074004,0.000004070435,0.0000088888255,0.014280998],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971278,0.000040877665,0.00055919576,0.0002971171,0.0017786515,0.00019641424],"domain_scores_gemma":[0.9982618,0.00018957251,0.0004106837,0.00046310536,0.0005876063,0.00008720911],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0070192185,0.00011305642,0.00016360453,0.000065071916,0.00023543838,0.00075538893,0.0022563084,0.000027457436,0.0000224907],"category_scores_gemma":[0.0036645127,0.000047692887,0.000094306466,0.000526696,0.00013574363,0.0008420558,0.0010083524,0.000098844714,0.00007023685],"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":[0.000038690298,0.00007532341,0.00043589034,0.0000057694615,0.0000460658,1.2720135e-7,0.0010051575,0.000011203437,0.004470577,0.4131789,0.5342453,0.046486977],"study_design_scores_gemma":[0.00036845575,0.00007872825,0.0006366902,0.000017712851,0.000042707343,0.0000024377914,0.008432384,0.0005202109,0.07559018,0.13771304,0.7764785,0.00011892461],"about_ca_topic_score_codex":0.000089172674,"about_ca_topic_score_gemma":0.000051044895,"teacher_disagreement_score":0.420512,"about_ca_system_score_codex":0.00006292882,"about_ca_system_score_gemma":0.000045064586,"threshold_uncertainty_score":0.7284233},"labels":[],"label_agreement":null},{"id":"W2190899134","doi":"10.14778/2850578.2850579","title":"Messing up with BART","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":80,"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":"Scalability; Tuple; Computer science; Benchmarking; Completeness (order theory); Greedy algorithm; Process (computing); Benchmark (surveying); Property (philosophy); Scale (ratio); Control (management); Mathematical optimization; Algorithm; Database; Mathematics; Artificial intelligence; Programming language","score_opus":0.2772987549438379,"score_gpt":0.3926154589624858,"score_spread":0.11531670401864791,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2190899134","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":[0.5979908,0.00022995513,0.0013640509,0.022348074,0.0015784419,0.001216744,0.000026919257,0.00012045311,0.37512457],"genre_scores_gemma":[0.9887018,0.0000043793625,0.0019050792,0.00053653354,0.000050126506,0.000019953326,5.894613e-7,0.000007730512,0.008773807],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997272,0.000016838409,0.00038806433,0.00030152523,0.0018181411,0.00020340877],"domain_scores_gemma":[0.998772,0.00007504292,0.00033293464,0.00027549115,0.0004345559,0.000109954715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003346509,0.00011066196,0.00019715393,0.00009599598,0.00009975187,0.0002522856,0.0012115131,0.0000230524,0.000053414624],"category_scores_gemma":[0.0008722148,0.000054171618,0.000061510655,0.00052173494,0.00013228925,0.00050013873,0.00064812537,0.000078854784,0.0000786362],"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":[0.00031506005,0.00029908743,0.016755618,0.00006978135,0.00012665632,0.0000016025798,0.008404786,0.000090169684,0.004001799,0.21043591,0.7078582,0.05164132],"study_design_scores_gemma":[0.0022609094,0.00034659193,0.0050262087,0.00018449091,0.000094023235,0.000019369776,0.02731994,0.0003347774,0.07325927,0.1365034,0.7542753,0.00037569588],"about_ca_topic_score_codex":0.000050009403,"about_ca_topic_score_gemma":0.000008549571,"teacher_disagreement_score":0.390711,"about_ca_system_score_codex":0.000051422918,"about_ca_system_score_gemma":0.00004377445,"threshold_uncertainty_score":0.24327958},"labels":[],"label_agreement":null},{"id":"W2207847180","doi":"10.14778/2824032.2824049","title":"Fuzzy joins in MapReduce","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Joins; Skyline; Computer science; Point (geometry); Hamming distance; Fuzzy logic; Binary number; Algorithm; Data mining; Theoretical computer science; Artificial intelligence; Mathematics; Programming language; Arithmetic","score_opus":0.03116395072858845,"score_gpt":0.24520602154516505,"score_spread":0.2140420708165766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2207847180","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":[0.73181605,0.0006357042,0.00595455,0.031317372,0.0013084679,0.0017989166,0.00003634868,0.00037186008,0.22676072],"genre_scores_gemma":[0.9404029,0.000012981444,0.05876947,0.00016203888,0.000046769965,0.00008403352,6.187489e-7,0.000006055796,0.0005151261],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99921733,0.0000027015933,0.00017473257,0.00020242033,0.00024443778,0.00015840525],"domain_scores_gemma":[0.9995451,0.0000103544035,0.00009902136,0.00019245844,0.00008959329,0.0000634533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030273836,0.00007274306,0.00009338848,0.000054650736,0.000034168173,0.00006393428,0.0011323905,0.000020384114,9.230242e-7],"category_scores_gemma":[0.000050858882,0.000051220482,0.0000308689,0.00041460973,0.00003200295,0.00027873903,0.0005297822,0.00007756847,0.000015612213],"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":[0.0000103203465,0.000652384,0.007344702,0.000060583072,0.000029550421,0.0000010503861,0.0066056554,0.00006161057,0.026388656,0.78813714,0.08174744,0.08896091],"study_design_scores_gemma":[0.0041826414,0.00048296878,0.040900562,0.0005033286,0.00004381186,0.0001068697,0.0028360647,0.037390493,0.41059938,0.35446092,0.1473643,0.0011286619],"about_ca_topic_score_codex":0.00007825258,"about_ca_topic_score_gemma":0.0000024608607,"teacher_disagreement_score":0.4336762,"about_ca_system_score_codex":0.0000565259,"about_ca_system_score_gemma":0.000042343767,"threshold_uncertainty_score":0.21042821},"labels":[],"label_agreement":null},{"id":"W2212315060","doi":"10.14778/2856318.2856323","title":"Approximate closest community search in networks","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Caching and Content Delivery","field":"Computer Science","cited_by":217,"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":"Truss; Computer science; Approximation algorithm; Greedy algorithm; Set (abstract data type); Graph; Efficient algorithm; Theoretical computer science; Mathematical optimization; Mathematics; Combinatorics; Algorithm","score_opus":0.05422769107867213,"score_gpt":0.2469106196643252,"score_spread":0.19268292858565306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2212315060","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":[0.98646694,0.00018642399,0.00212052,0.0011731735,0.0002944132,0.0003084979,8.9527725e-7,0.00007872068,0.009370391],"genre_scores_gemma":[0.99884355,0.000015982761,0.000771196,0.00016970084,0.000030065352,0.000018457597,3.1534825e-7,0.000005782942,0.00014494765],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99899274,0.00003895423,0.0002087159,0.00015333293,0.00035146924,0.00025478858],"domain_scores_gemma":[0.9993865,0.000042178573,0.00008796383,0.00025193082,0.0001537572,0.00007765728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013461441,0.00010249407,0.00014844346,0.00007331387,0.00010233389,0.000093815914,0.0015317929,0.00003721478,6.6101035e-7],"category_scores_gemma":[0.00006138361,0.00007303118,0.00006101358,0.00038134758,0.000055984645,0.0002628202,0.001057972,0.00041459536,0.0000036636386],"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":[0.0003983334,0.0038952313,0.36171544,0.0005708845,0.0002297787,0.000012802464,0.046139665,0.018781038,0.038278054,0.4338373,0.022306388,0.07383508],"study_design_scores_gemma":[0.005202832,0.00080925535,0.02996845,0.00079080724,0.00003948416,0.00010362469,0.006622553,0.877474,0.044585016,0.03193763,0.0014937696,0.0009725695],"about_ca_topic_score_codex":0.0008669284,"about_ca_topic_score_gemma":0.000017755956,"teacher_disagreement_score":0.85869294,"about_ca_system_score_codex":0.00010306434,"about_ca_system_score_gemma":0.00003404179,"threshold_uncertainty_score":0.29781252},"labels":[],"label_agreement":null},{"id":"W2243935923","doi":"10.14778/2757807.2757810","title":"Compaction management in distributed key-value datastores","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Cache; Workload; Scalability; Server; Compaction; Distributed computing; Operating system","score_opus":0.02208657302277573,"score_gpt":0.2408768714961972,"score_spread":0.21879029847342146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2243935923","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":[0.9399338,0.00025388575,0.01112987,0.0074230996,0.001319248,0.001367873,0.000011464849,0.00030882322,0.038251944],"genre_scores_gemma":[0.9938556,0.000005557909,0.0056946916,0.00011639054,0.000042928557,0.000022550012,0.0000019043473,0.0000066955154,0.00025367245],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985707,0.000014180554,0.0002872269,0.00031426398,0.00054491503,0.00026875388],"domain_scores_gemma":[0.9993659,0.000014546332,0.00018731943,0.00027984253,0.00007174548,0.00008064071],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000591894,0.0001398288,0.00016019472,0.00012618677,0.00006929626,0.00009443506,0.0013376243,0.000025432297,0.0000011061256],"category_scores_gemma":[0.0000282981,0.00009844616,0.00006081567,0.0005871754,0.000043145064,0.000064324806,0.0013872172,0.00011456427,0.0000093386],"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":[0.00012597628,0.001499754,0.020888358,0.00045505608,0.00034721542,0.00001638234,0.007434492,0.0565934,0.0014147004,0.76360995,0.09386687,0.053747833],"study_design_scores_gemma":[0.008806355,0.00065787137,0.10592991,0.0011515333,0.00017627495,0.00007221828,0.0062240385,0.5487943,0.030357882,0.056354627,0.23997903,0.0014959202],"about_ca_topic_score_codex":0.00011502223,"about_ca_topic_score_gemma":0.0000025995168,"teacher_disagreement_score":0.7072553,"about_ca_system_score_codex":0.00022552369,"about_ca_system_score_gemma":0.000012180995,"threshold_uncertainty_score":0.40145177},"labels":[],"label_agreement":null},{"id":"W2244188037","doi":"10.14778/2824032.2824046","title":"A scalable distributed graph partitioner","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Interconnection Networks and Systems","field":"Computer Science","cited_by":76,"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":"Ministry of Economy, Trade and Industry","keywords":"Graph partition; Scalability; Partition (number theory); Computer science; Bounded function; Graph; Parallel computing; Space partitioning; Theoretical computer science; Algorithm; Combinatorics; Mathematics; Database","score_opus":0.024293433423822605,"score_gpt":0.2216525087113379,"score_spread":0.19735907528751528,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2244188037","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":[0.562266,0.001009178,0.2519546,0.026221799,0.0109243225,0.0029270458,0.000044636272,0.0010585547,0.1435939],"genre_scores_gemma":[0.9981429,0.0000037491611,0.0010209256,0.00014314966,0.00008459441,0.000047164664,6.425704e-7,0.000004391708,0.0005524893],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990664,0.000008179639,0.00022943852,0.000183941,0.00031979027,0.00019223333],"domain_scores_gemma":[0.999288,0.000011334511,0.00015579202,0.00014582246,0.0003131435,0.00008588656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040477957,0.0000876929,0.00012553338,0.00004068688,0.00008190871,0.00010447423,0.00062170136,0.000032656684,0.000005982477],"category_scores_gemma":[0.000045128723,0.0000555196,0.00008411182,0.0004100514,0.000035945563,0.00029328314,0.00024146472,0.00007179143,0.000017025608],"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":[0.000027898823,0.00024870576,0.007963274,0.000062939034,0.000087349064,8.5436164e-7,0.0018356752,0.0007738147,0.0057951855,0.69382894,0.28811887,0.001256478],"study_design_scores_gemma":[0.0047717094,0.00094538,0.0050995275,0.0007873184,0.00009126105,0.0002583454,0.002466784,0.111511976,0.31377363,0.27763748,0.28141448,0.0012421346],"about_ca_topic_score_codex":0.000049828705,"about_ca_topic_score_gemma":0.0000024604544,"teacher_disagreement_score":0.4358769,"about_ca_system_score_codex":0.00006105705,"about_ca_system_score_gemma":0.000022207492,"threshold_uncertainty_score":0.22640234},"labels":[],"label_agreement":null},{"id":"W2244331736","doi":"10.14778/2536222.2536255","title":"Toward scalable transaction processing","year":2013,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Scalability; Transaction processing system; Computer science; Transaction processing; Multi-core processor; Online transaction processing; Database transaction; Metadata; Distributed transaction; Distributed computing; Computer architecture; Embedded system; Parallel computing; Database; Operating system","score_opus":0.01483689700489075,"score_gpt":0.2104329737351254,"score_spread":0.19559607673023466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2244331736","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":[0.5702118,0.0016147485,0.29740322,0.023540141,0.0023633186,0.0042490778,0.000014737311,0.00088776136,0.099715166],"genre_scores_gemma":[0.9951335,0.000008227393,0.004052568,0.00010811009,0.000037161204,0.00009701479,1.9743572e-7,0.0000062205777,0.0005569688],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989096,0.000003852284,0.00025939336,0.00024028328,0.0003503049,0.00023655721],"domain_scores_gemma":[0.9993712,0.000006653544,0.00018735287,0.00012521388,0.00025210084,0.000057505134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017249398,0.00011445215,0.00014992186,0.000036563222,0.00011392385,0.00022287204,0.0008297125,0.00004028045,0.000016329828],"category_scores_gemma":[0.0000122931815,0.00007476407,0.00007795153,0.00036708612,0.00003520244,0.00089659996,0.00009336272,0.00009408954,0.000028255903],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023272729,0.0007013252,0.00489278,0.001644358,0.00011229727,9.517532e-7,0.008857253,0.00023842466,0.40818477,0.08125832,0.03135312,0.46273315],"study_design_scores_gemma":[0.0021056987,0.00027014365,0.017647756,0.001171491,0.00005137732,0.000111361085,0.0014267473,0.10843143,0.8074706,0.024663689,0.035718985,0.0009306829],"about_ca_topic_score_codex":0.00011402819,"about_ca_topic_score_gemma":4.937992e-7,"teacher_disagreement_score":0.46180245,"about_ca_system_score_codex":0.000052938063,"about_ca_system_score_gemma":0.00002527022,"threshold_uncertainty_score":0.30487907},"labels":[],"label_agreement":null},{"id":"W2256219868","doi":"10.14778/2752939.2752949","title":"Understanding the causes of consistency anomalies in Apache Cassandra","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":20,"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":"Garbage collection; Computer science; Consistency (knowledge bases); Garbage; Workload; Java; Server; Throughput; Operating system; Database; Real-time computing; Programming language; Artificial intelligence","score_opus":0.13004382623379485,"score_gpt":0.2601769927376143,"score_spread":0.13013316650381945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2256219868","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":[0.8653115,0.003044976,0.019166606,0.011774501,0.0017947934,0.002054431,0.000047399495,0.00014213842,0.096663654],"genre_scores_gemma":[0.9993048,0.000012662087,0.0004775117,0.00005554218,0.000017560737,0.00001985673,1.514533e-7,0.000004251075,0.000107716754],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988748,0.000014553171,0.00034615077,0.00017498662,0.00039593448,0.00019362074],"domain_scores_gemma":[0.9992649,0.00005274781,0.00028711025,0.00019217886,0.00016083363,0.00004220811],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066032895,0.00010784038,0.00021014606,0.000053302243,0.00006912688,0.00006481237,0.0008749725,0.00003420985,0.0000011048649],"category_scores_gemma":[0.000114740804,0.00005948293,0.00006552324,0.0004451088,0.00015497458,0.0002416839,0.00028798514,0.00009277092,0.0000011466794],"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":[0.000030431616,0.00018648447,0.056550216,0.00021306882,0.000075760865,0.0000022856973,0.016343338,0.00020418473,0.008386954,0.91182774,0.005701622,0.00047790396],"study_design_scores_gemma":[0.013280998,0.0015838705,0.0772793,0.004579651,0.00025712012,0.0005222766,0.15836132,0.04074893,0.341222,0.33482084,0.024872161,0.0024715618],"about_ca_topic_score_codex":0.00016733493,"about_ca_topic_score_gemma":0.00002747058,"teacher_disagreement_score":0.57700694,"about_ca_system_score_codex":0.00013674996,"about_ca_system_score_gemma":0.00006999453,"threshold_uncertainty_score":0.24256435},"labels":[],"label_agreement":null},{"id":"W2260484439","doi":"10.14778/2824032.2824036","title":"SEMA-JOIN","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":31,"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; Joins; Join (topology); Hash join; Table (database); Theoretical computer science; Data mining; Database; Programming language; Mathematics","score_opus":0.2932342444414948,"score_gpt":0.4016846612147633,"score_spread":0.1084504167732685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2260484439","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":[0.43994513,0.00027912902,0.0005336356,0.030319914,0.001955734,0.0012935428,0.000052827963,0.000118911725,0.5255012],"genre_scores_gemma":[0.9859812,0.000009056158,0.0013921544,0.00085359847,0.000077642915,0.000024651386,7.039278e-7,0.0000071393297,0.011653826],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971752,0.000019333223,0.0004998872,0.00029988968,0.0018020106,0.00020364292],"domain_scores_gemma":[0.9987275,0.00009267046,0.00034512812,0.00031042256,0.0004077383,0.00011655031],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004506487,0.000104631836,0.00019964241,0.00010627566,0.000071584924,0.00017336388,0.0016081008,0.00002890498,0.00009238273],"category_scores_gemma":[0.0021712196,0.000057614587,0.000105742736,0.0005442548,0.00009932725,0.00037151197,0.0010611337,0.000078993304,0.00026981288],"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":[0.000047495738,0.00018033956,0.004232143,0.00002544698,0.000036928286,4.7956195e-7,0.002107809,0.00002234002,0.0024244182,0.19565849,0.77837974,0.016884403],"study_design_scores_gemma":[0.0007256248,0.00011260732,0.00270726,0.0000387251,0.000029683872,0.000005298719,0.007430501,0.0001606574,0.03601578,0.26492023,0.68769,0.00016360579],"about_ca_topic_score_codex":0.00006553871,"about_ca_topic_score_gemma":0.000007710871,"teacher_disagreement_score":0.5460361,"about_ca_system_score_codex":0.00005517833,"about_ca_system_score_gemma":0.000031029544,"threshold_uncertainty_score":0.3467989},"labels":[],"label_agreement":null},{"id":"W2262592273","doi":"10.14778/2824032.2824109","title":"KATARA","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":45,"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; Table (database); Crowdsourcing; Ambiguity; Tuple; Information retrieval; Annotation; Task (project management); Semantics (computer science); Reliability (semiconductor); Data mining; World Wide Web; Programming language; Artificial intelligence","score_opus":0.34404765762554373,"score_gpt":0.4117242000185209,"score_spread":0.06767654239297716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2262592273","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":[0.4788121,0.00027195603,0.00041791852,0.02637879,0.0019338108,0.0011111654,0.00005469319,0.000101510384,0.49091807],"genre_scores_gemma":[0.9904682,0.000007201678,0.0010645605,0.00070658646,0.00006562925,0.000019416075,7.5012537e-7,0.000005446402,0.007662233],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973964,0.000014970492,0.00044493604,0.00027100352,0.0016916761,0.00018101264],"domain_scores_gemma":[0.99885494,0.0000811193,0.00030329896,0.00027498003,0.00038114854,0.00010450634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038696777,0.000091712696,0.00017262471,0.00009248174,0.00006401042,0.00015642121,0.001688209,0.000024278228,0.00008126148],"category_scores_gemma":[0.0019589872,0.00004972197,0.00009150177,0.0004905285,0.000099061384,0.0003781865,0.0010013727,0.000070292015,0.00025454286],"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":[0.000051583163,0.00016946271,0.005958328,0.00002003826,0.00003560149,3.9031346e-7,0.0019413386,0.000023848972,0.0014267978,0.23066008,0.74037254,0.019339977],"study_design_scores_gemma":[0.00063827843,0.00009866243,0.0031026935,0.000027972552,0.000026041062,0.000003994799,0.0062122,0.00012786972,0.031369224,0.24951574,0.7087362,0.0001411328],"about_ca_topic_score_codex":0.00006843983,"about_ca_topic_score_gemma":0.0000044513918,"teacher_disagreement_score":0.5116561,"about_ca_system_score_codex":0.00004662251,"about_ca_system_score_gemma":0.000027515853,"threshold_uncertainty_score":0.32717186},"labels":[],"label_agreement":null},{"id":"W2262876226","doi":"10.14778/2824032.2824069","title":"Towards scalable real-time analytics","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Systems, Applications & Products in Data Processing (Canada)","funders":"","keywords":"Computer science; Analytics; Scalability; Timestamp; Online transaction processing; Database; Asynchronous communication; Online analytical processing; Distributed computing; Distributed transaction; Distributed database; Snapshot (computer storage); Transaction processing; Real-time computing; Database transaction; Data warehouse; Computer network","score_opus":0.021671129085309535,"score_gpt":0.2320368607474169,"score_spread":0.21036573166210737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2262876226","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":[0.6355346,0.000120247874,0.0016504044,0.008674496,0.00066992454,0.0005843219,0.000001500224,0.0004066962,0.35235783],"genre_scores_gemma":[0.97504276,0.000009619946,0.017032927,0.00020517659,0.00012407423,0.000012011445,1.814284e-7,0.000012958648,0.007560286],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985016,0.000008445411,0.00026318926,0.00029404392,0.0006399036,0.00029279353],"domain_scores_gemma":[0.99912745,0.000015800992,0.00020196172,0.0002951575,0.00023290505,0.00012672546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069583644,0.00014071177,0.00019040315,0.000082533166,0.00009246294,0.00012405035,0.0016043844,0.00003494667,0.0000046088203],"category_scores_gemma":[0.00007204556,0.00009209258,0.00010779724,0.00055383734,0.000055605433,0.000042587617,0.0014976764,0.00009212472,0.000040945688],"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":[0.00008618694,0.0014786076,0.010516953,0.0004803023,0.0006375198,0.000010528054,0.012547927,0.018721415,0.028849645,0.46238372,0.36470369,0.0995835],"study_design_scores_gemma":[0.0031116582,0.00081384444,0.0058191284,0.00047155502,0.00018981055,0.00006216728,0.0011156979,0.71238685,0.13956833,0.05929105,0.076045744,0.0011241863],"about_ca_topic_score_codex":0.00011990584,"about_ca_topic_score_gemma":4.008229e-7,"teacher_disagreement_score":0.69366544,"about_ca_system_score_codex":0.00012300724,"about_ca_system_score_gemma":0.000048939524,"threshold_uncertainty_score":0.37554264},"labels":[],"label_agreement":null},{"id":"W2263157912","doi":"10.14778/2777598.2777604","title":"Giraph unchained","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":145,"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":"Asynchronous communication; Computer science; Scalability; Computation; Synchronization (alternating current); Distributed computing; Bulk synchronous parallel; Graph; Parallel computing; Model of computation; Theoretical computer science; Algorithm; Computer network; Operating system","score_opus":0.01784287209176177,"score_gpt":0.2045423580511298,"score_spread":0.18669948595936803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2263157912","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":[0.782061,0.00088793505,0.029292163,0.016403556,0.00435679,0.0017244632,0.000009095242,0.0008121827,0.16445282],"genre_scores_gemma":[0.99002445,0.0000040409936,0.00901067,0.0002543683,0.000050227412,0.000018863573,1.0705394e-7,0.000005529686,0.00063175923],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99905723,0.0000071876366,0.00017110538,0.00020340644,0.00035938306,0.00020165698],"domain_scores_gemma":[0.99939,0.000016322278,0.00013217864,0.00018034816,0.00018320176,0.00009794727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005284773,0.00010494823,0.000120482284,0.00006554927,0.00006842081,0.000057898946,0.0012945564,0.00002751794,0.0000035929856],"category_scores_gemma":[0.00006864707,0.000066444074,0.00008978057,0.00044708466,0.00006702289,0.00027584442,0.00046472927,0.00008348611,0.000012215428],"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":[0.000013105319,0.000109908055,0.001106457,0.00002251225,0.000030219144,6.090736e-7,0.0022528814,0.000025057376,0.010060721,0.9759554,0.004424277,0.0059988378],"study_design_scores_gemma":[0.0013123702,0.00028311697,0.00089011935,0.00007830159,0.000021077658,0.00003574569,0.0006269273,0.0051900353,0.31245232,0.6690939,0.009709193,0.0003068535],"about_ca_topic_score_codex":0.0000075723387,"about_ca_topic_score_gemma":1.9534805e-7,"teacher_disagreement_score":0.3068615,"about_ca_system_score_codex":0.000028638226,"about_ca_system_score_gemma":0.000027523747,"threshold_uncertainty_score":0.27095106},"labels":[],"label_agreement":null},{"id":"W2264475115","doi":"10.14778/2809974.2809977","title":"Worker skill estimation in team-based tasks","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Nautical Research Society","funders":"Army Research Office; National Science Foundation","keywords":"Task (project management); Computer science; Scalability; Outcome (game theory); Estimation; Machine learning; Artificial intelligence; Knowledge management; Mathematics; Engineering","score_opus":0.015130512596530404,"score_gpt":0.23288734720550677,"score_spread":0.21775683460897638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2264475115","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":[0.94043535,0.0001752509,0.03502602,0.003638536,0.0006818429,0.0007269947,0.0000011277822,0.00021187238,0.019103017],"genre_scores_gemma":[0.97312963,8.9572353e-7,0.026485702,0.0001935896,0.000021123433,0.000023401002,2.72831e-7,0.0000075694447,0.00013778954],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988914,0.000009941719,0.00024867637,0.00024111413,0.00038317588,0.00022565702],"domain_scores_gemma":[0.99938387,0.000030516474,0.00016877662,0.00019929485,0.00014384084,0.000073722826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063835434,0.00011654095,0.00014203614,0.00010372374,0.0000532469,0.000099049576,0.00061335874,0.000043380773,0.0000015029901],"category_scores_gemma":[0.00018343181,0.00008352593,0.000055967088,0.0004545556,0.000045004494,0.00023527241,0.00020388157,0.0001236134,0.000008957428],"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":[0.00028385987,0.0027360865,0.14965677,0.0005695273,0.0001249368,0.000012815565,0.044645168,0.2037523,0.07087663,0.13672142,0.07518087,0.3154396],"study_design_scores_gemma":[0.0023697019,0.00017907622,0.008053805,0.000682365,0.000020840202,0.000023456678,0.0006577434,0.71006435,0.25788403,0.017014917,0.0026321982,0.00041749724],"about_ca_topic_score_codex":0.00006578122,"about_ca_topic_score_gemma":0.000003476578,"teacher_disagreement_score":0.5063121,"about_ca_system_score_codex":0.00012862249,"about_ca_system_score_gemma":0.00006508552,"threshold_uncertainty_score":0.34060884},"labels":[],"label_agreement":null},{"id":"W2266577329","doi":"10.14778/2904483.2904488","title":"A general-purpose query-centric framework for querying big graphs","year":2016,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":45,"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; Scalability; Graph database; Workload; Theoretical computer science; Graph; Analytics; Big data; Computation; Vertex (graph theory); Database; Data mining; Programming language; Operating system","score_opus":0.016580142920986043,"score_gpt":0.2329751982869722,"score_spread":0.21639505536598613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2266577329","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":[0.34963214,0.00079576485,0.6331053,0.008730476,0.0031750614,0.0023042422,0.000029954574,0.0004067703,0.0018203382],"genre_scores_gemma":[0.90761656,0.00010774913,0.09089976,0.00044509437,0.0001818642,0.00021556947,1.9575852e-7,0.000020489259,0.0005127399],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984252,0.000012931019,0.00032733718,0.00043085625,0.00034687537,0.00045680697],"domain_scores_gemma":[0.9989212,0.00018226393,0.000293419,0.0002955759,0.00020450399,0.00010302433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005411391,0.0002048414,0.0002284467,0.00017343392,0.0002193481,0.000095611744,0.0015276691,0.00007951395,0.000005463524],"category_scores_gemma":[0.00021598376,0.00011126787,0.00027783492,0.0006635526,0.00010011114,0.00032339976,0.00043382501,0.000106020976,0.0000062864715],"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":[0.000018304208,0.00008463498,0.0009963693,0.00004429554,0.000036072917,2.9659878e-7,0.0003173446,0.0000014725252,0.034433812,0.9042671,0.0003815838,0.059418734],"study_design_scores_gemma":[0.00059635786,0.00010812207,0.00036009715,0.00023105882,0.000020245436,0.000010371752,0.000036568636,0.00028851652,0.2323498,0.7627926,0.003009588,0.00019666793],"about_ca_topic_score_codex":0.0000073260444,"about_ca_topic_score_gemma":3.4906088e-7,"teacher_disagreement_score":0.5579844,"about_ca_system_score_codex":0.000052964144,"about_ca_system_score_gemma":0.00003205448,"threshold_uncertainty_score":0.45373723},"labels":[],"label_agreement":null},{"id":"W2268506948","doi":"10.14778/2824032.2824128","title":"S+EPPs","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":19,"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":"SPARQL; Computer science; Component (thermodynamics); Graph; Theoretical computer science; Information retrieval; RDF; Semantic Web","score_opus":0.0193053903847535,"score_gpt":0.20903259207919872,"score_spread":0.18972720169444524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2268506948","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":[0.7289942,0.00083128235,0.021608507,0.015232095,0.0039899084,0.0013618338,0.0000066563834,0.0006412276,0.22733432],"genre_scores_gemma":[0.9897546,0.000003915908,0.009400987,0.00021033693,0.00004669523,0.000014937402,6.478766e-8,0.000004478742,0.0005639916],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99918914,0.0000053871504,0.00014425565,0.00017313511,0.00031582222,0.00017223893],"domain_scores_gemma":[0.999488,0.000012906769,0.00011000348,0.00015616653,0.00014866605,0.0000842545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044140624,0.00008550421,0.00009932996,0.00004534445,0.00005797815,0.00005600574,0.0012229076,0.000022659538,0.0000029617981],"category_scores_gemma":[0.00005638969,0.00005365784,0.00007159053,0.00032060943,0.00005462693,0.00028650145,0.0004654459,0.0000754636,0.000018560157],"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":[0.0000078039,0.00009238796,0.0013397904,0.000018065688,0.000020846757,4.57407e-7,0.001877356,0.000012880943,0.0076179206,0.9761877,0.0047945147,0.008030276],"study_design_scores_gemma":[0.0008791683,0.00019561374,0.0011998207,0.00006480868,0.00001610537,0.00003912973,0.0004969937,0.002624215,0.37220138,0.60743314,0.014607201,0.00024245618],"about_ca_topic_score_codex":0.000006373683,"about_ca_topic_score_gemma":1.4419844e-7,"teacher_disagreement_score":0.3687546,"about_ca_system_score_codex":0.000025549838,"about_ca_system_score_gemma":0.000023216835,"threshold_uncertainty_score":0.2272487},"labels":[],"label_agreement":null},{"id":"W2281494333","doi":"10.14778/2732977.2732980","title":"An experimental comparison of pregel-like graph processing systems","year":2014,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":194,"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; PageRank; Graph; Global Positioning System; Theoretical computer science; Operating system","score_opus":0.014468431683686635,"score_gpt":0.2619565896032245,"score_spread":0.24748815791953785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2281494333","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":[0.9746047,0.0010036724,0.019689692,0.00009614123,0.0007305464,0.0006141273,0.0000023964783,0.00014280285,0.0031159187],"genre_scores_gemma":[0.9953004,0.000002031,0.0045354897,0.000028429447,0.000044438573,0.000042085758,3.5116784e-7,0.000010077922,0.000036669855],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985229,0.000025963396,0.00042139913,0.00031843412,0.00046880174,0.00024250934],"domain_scores_gemma":[0.9990125,0.000023452838,0.00046599552,0.0002550271,0.00016292225,0.00008010418],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054045673,0.00016613302,0.00029487783,0.00010396065,0.00015907388,0.00011374676,0.0014886064,0.000046019388,0.0000018747517],"category_scores_gemma":[0.000014245865,0.00011540042,0.000104330684,0.000378179,0.00013562465,0.00053775316,0.0002542168,0.00010479143,0.0000012906137],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038786915,0.001202476,0.009021328,0.00048138437,0.00004875325,1.468379e-7,0.011263991,0.00048601534,0.5828564,0.38394213,0.00028638917,0.010372172],"study_design_scores_gemma":[0.00050985464,0.0004999023,0.00060721923,0.00027450858,0.000019006893,0.000009795583,0.0019054175,0.06426916,0.9246236,0.0067856084,0.00028669523,0.00020920251],"about_ca_topic_score_codex":0.000017060764,"about_ca_topic_score_gemma":2.42743e-7,"teacher_disagreement_score":0.37715653,"about_ca_system_score_codex":0.000023219203,"about_ca_system_score_gemma":0.000016256396,"threshold_uncertainty_score":0.47058925},"labels":[],"label_agreement":null},{"id":"W2291620117","doi":"10.14778/2850469.2850471","title":"K-core decomposition of large networks on a single PC","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":214,"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 Victoria","funders":"","keywords":"Computer science; Decomposition; Implementation; Core (optical fiber); Metric (unit); Graph; Multi-core processor; Vertex (graph theory); Theoretical computer science; Parallel computing; Algorithm","score_opus":0.03872705365176489,"score_gpt":0.26743815820515754,"score_spread":0.22871110455339266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2291620117","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":[0.9472895,0.00023702887,0.033182878,0.0011546283,0.0010514866,0.00061568833,0.0000071263125,0.00012917057,0.016332446],"genre_scores_gemma":[0.99581593,0.000003565747,0.0038843877,0.000171841,0.000048739574,0.0000119162705,4.9317805e-7,0.000005771841,0.00005734892],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999089,0.000008435948,0.00020712036,0.00018820592,0.0003082777,0.000198966],"domain_scores_gemma":[0.9993529,0.000027160462,0.00021952347,0.00016027859,0.00017224732,0.00006793695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048543222,0.00010431635,0.00014762967,0.00006495639,0.00006162973,0.00003066371,0.0007489573,0.00003748217,0.00000230686],"category_scores_gemma":[0.000032537115,0.00007150745,0.00009612005,0.00032565187,0.000044765507,0.00019161007,0.00029174864,0.00009273659,0.0000030846863],"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":[0.00009773434,0.001020113,0.0019155865,0.000058924372,0.00006399117,0.0000010284303,0.0026835252,0.0009016492,0.039658867,0.9423572,0.0027537255,0.008487668],"study_design_scores_gemma":[0.0021253896,0.0014751757,0.0015594936,0.00043795773,0.00004336684,0.000030175348,0.0004968683,0.05340236,0.72513217,0.21349053,0.0014474926,0.00035901656],"about_ca_topic_score_codex":0.0000040216364,"about_ca_topic_score_gemma":3.4152757e-7,"teacher_disagreement_score":0.72886664,"about_ca_system_score_codex":0.000037422942,"about_ca_system_score_gemma":0.000012286922,"threshold_uncertainty_score":0.29159892},"labels":[],"label_agreement":null},{"id":"W2292011317","doi":"10.14778/2735461.2735463","title":"Top-k nearest neighbor search in uncertain data series","year":2014,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":59,"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":"Series (stratigraphy); Computer science; Nearest neighbor search; k-nearest neighbors algorithm; Metric (unit); Data mining; Independence (probability theory); Time series; Uncertain data; Variety (cybernetics); Synthetic data; Algorithm; Artificial intelligence; Machine learning; Mathematics; Statistics","score_opus":0.03384988583387695,"score_gpt":0.25089819564159177,"score_spread":0.21704830980771483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2292011317","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":[0.88545465,0.0005714949,0.011167424,0.03152989,0.000881585,0.0014322741,0.00003630683,0.00028984863,0.06863655],"genre_scores_gemma":[0.98641336,0.00002048511,0.01292011,0.00010629685,0.000069559224,0.0000090543535,0.0000018553801,0.000007655134,0.00045165056],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864185,0.000013283972,0.0002873168,0.0003814179,0.00037911875,0.00029698436],"domain_scores_gemma":[0.9991732,0.000039490867,0.00013572743,0.0004939408,0.00010502079,0.00005259359],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008554975,0.00011881112,0.00019745511,0.00008200165,0.00011238982,0.00017259763,0.0025290155,0.0000314706,0.000016234722],"category_scores_gemma":[0.00015338848,0.00007980731,0.00005360056,0.0006264593,0.00007180639,0.00072713627,0.0021185714,0.00013417599,0.000006734542],"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":[0.00008074103,0.0003480575,0.106390946,0.00037316195,0.00013152302,0.0000028148056,0.005846408,0.0016307351,0.02844865,0.68146825,0.005084925,0.17019382],"study_design_scores_gemma":[0.0015954772,0.00057694584,0.040112376,0.00051068753,0.00006441691,0.000053201038,0.002243335,0.76397437,0.10634771,0.019390913,0.06424116,0.0008894327],"about_ca_topic_score_codex":0.00034665733,"about_ca_topic_score_gemma":0.000038804617,"teacher_disagreement_score":0.7623436,"about_ca_system_score_codex":0.00003930357,"about_ca_system_score_gemma":0.000029926574,"threshold_uncertainty_score":0.46995822},"labels":[],"label_agreement":null},{"id":"W2293393493","doi":"10.14778/2732967.2732970","title":"ConfluxDB","year":2014,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":20,"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; Scalability; Replication (statistics); Distributed computing; Snapshot (computer storage); Database transaction; Database; Transaction processing; Operating system; Parallel computing","score_opus":0.005146339465848849,"score_gpt":0.18617502323385682,"score_spread":0.18102868376800796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2293393493","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":[0.39358214,0.0005977657,0.105470434,0.01625444,0.004042369,0.0019498118,0.000031421634,0.00069155137,0.47738007],"genre_scores_gemma":[0.9970141,0.000003400866,0.0020877253,0.00024217482,0.000054551674,0.000020090862,2.0333833e-7,0.000004155981,0.0005736062],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99910986,0.000005035731,0.00020820857,0.00019998886,0.00029521008,0.00018170298],"domain_scores_gemma":[0.99943274,0.000017513383,0.00017047462,0.00019262185,0.00013858668,0.00004804056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032216855,0.000090956615,0.00014067983,0.000024739033,0.00007528951,0.00008007339,0.0011417078,0.00002811797,0.0000042869688],"category_scores_gemma":[0.000049456572,0.000058012032,0.00007456373,0.00021246349,0.00003827459,0.00018955077,0.00027654832,0.000067272755,0.00001902585],"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":[0.0000034857817,0.00006306741,0.002331287,0.000068272144,0.0000194934,1.0122881e-7,0.00042296553,0.000014523986,0.02573156,0.94629186,0.012127362,0.012926041],"study_design_scores_gemma":[0.0015149168,0.00022381188,0.0144500295,0.00032605918,0.000022488966,0.00003966877,0.00013481657,0.023443405,0.3328744,0.029658213,0.5968274,0.0004848332],"about_ca_topic_score_codex":0.000020451296,"about_ca_topic_score_gemma":4.6227726e-7,"teacher_disagreement_score":0.9166336,"about_ca_system_score_codex":0.000022004037,"about_ca_system_score_gemma":0.000010834772,"threshold_uncertainty_score":0.2365662},"labels":[],"label_agreement":null},{"id":"W2293703278","doi":"10.14778/3402707.3402744","title":"Publishing set-valued data via differential privacy","year":2011,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":221,"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":"Differential privacy; Computer science; Data publishing; Data mining; Scalability; Context (archaeology); Data anonymization; Set (abstract data type); Information privacy; Information retrieval; Theoretical computer science; Publishing; Database; Computer security","score_opus":0.09995646936477759,"score_gpt":0.2744083175834562,"score_spread":0.1744518482186786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2293703278","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":[0.56784207,0.00065752125,0.28587046,0.08721219,0.0065385,0.004067027,0.00032834985,0.005286196,0.042197667],"genre_scores_gemma":[0.79826784,0.000024026427,0.20142338,0.0001243139,0.00006184972,0.000028874556,0.000008562542,0.000017791019,0.000043378648],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99740887,0.000015402937,0.00045380223,0.000827536,0.00078508887,0.0005093186],"domain_scores_gemma":[0.9915843,0.00004407513,0.0004808494,0.007611141,0.00019321695,0.00008640517],"candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0007836958,0.0002447771,0.00026235174,0.00015459441,0.00017837636,0.0005190451,0.10310147,0.00012585157,0.000040123818],"category_scores_gemma":[0.010895777,0.00017284676,0.00007911601,0.0006397457,0.00017042446,0.004645349,0.2920184,0.0004204892,0.000013601742],"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":[0.00006733322,0.00074287265,0.014304189,0.00032927553,0.0003607973,0.000005118408,0.0029594037,3.5441556e-7,0.060766134,0.09714977,0.7552817,0.068033054],"study_design_scores_gemma":[0.001096923,0.00014346525,0.009421084,0.00022423598,0.000075169766,0.000049232425,0.00017092383,0.052375328,0.36270386,0.5688383,0.0042990264,0.0006024253],"about_ca_topic_score_codex":0.00018663303,"about_ca_topic_score_gemma":0.0000023004163,"teacher_disagreement_score":0.7509827,"about_ca_system_score_codex":0.000090294685,"about_ca_system_score_gemma":0.000045594035,"threshold_uncertainty_score":0.99743587},"labels":[],"label_agreement":null},{"id":"W2294111665","doi":"10.14778/2732951.2732960","title":"Scalable logging through emerging non-volatile memory","year":2014,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":206,"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":"Commit; Scalability; Computer science; Logging; Dram; Bottleneck; Embedded system; Overhead (engineering); Cache; Operating system; Computer hardware; Database; Forestry","score_opus":0.009201764651845435,"score_gpt":0.2140710501752543,"score_spread":0.20486928552340886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2294111665","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":[0.93868697,0.00017060743,0.0029936065,0.00016682343,0.00066026096,0.00029328512,0.0000010982696,0.00027859045,0.056748763],"genre_scores_gemma":[0.9965774,0.000023531016,0.0027802605,0.00009665233,0.00017426004,0.000015871929,3.5789773e-7,0.00003306024,0.00029863088],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990234,0.0000033004628,0.00026340704,0.00018547502,0.00020221664,0.00032224128],"domain_scores_gemma":[0.9996544,0.000041771935,0.000095654534,0.00011935652,0.000046263198,0.000042524945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001940666,0.00017410413,0.00020763825,0.00003844881,0.00015506144,0.000022632346,0.00031835583,0.000038797836,0.000019970512],"category_scores_gemma":[0.00004329647,0.00013455709,0.00008979337,0.00018769012,0.000038390892,0.00027723875,0.00015832955,0.00019821149,0.000010447451],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014485829,0.000030463498,0.00091348856,0.0006078284,0.00004886808,3.573366e-7,0.0014106685,0.050189327,0.93157315,0.0017589668,0.0026234898,0.010828932],"study_design_scores_gemma":[0.00032718136,0.000030218405,0.00024181975,0.00019594416,0.00002127989,0.0000074566774,0.00022397116,0.043345474,0.9474207,0.0033793969,0.004614752,0.00019177303],"about_ca_topic_score_codex":0.0000062430413,"about_ca_topic_score_gemma":3.6681053e-7,"teacher_disagreement_score":0.05789041,"about_ca_system_score_codex":0.0000529348,"about_ca_system_score_gemma":0.0000041957805,"threshold_uncertainty_score":0.5487079},"labels":[],"label_agreement":null},{"id":"W2295333720","doi":"10.14778/2856318.2856331","title":"CLAMShell","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":49,"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":"Crowds; Computer science; Latency (audio); Speedup; Data science; Computer security; Operating system; Telecommunications","score_opus":0.020412257649798923,"score_gpt":0.20830406149783764,"score_spread":0.18789180384803872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2295333720","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":[0.8262311,0.00040866356,0.006498457,0.00630544,0.0017005039,0.00062953285,0.0000014939382,0.00039414334,0.15783064],"genre_scores_gemma":[0.99118066,0.000003256044,0.007616778,0.0002082496,0.0000650924,0.000008926,8.1452114e-8,0.000006904274,0.0009100611],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989984,0.0000053552503,0.00018592429,0.00021602493,0.0003822793,0.00021202613],"domain_scores_gemma":[0.9993323,0.000015392645,0.00014099236,0.00021495952,0.0001988977,0.00009744889],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042795393,0.00010098659,0.0001229801,0.000044004468,0.000071569026,0.00010021334,0.0009290282,0.00003202793,0.0000018590206],"category_scores_gemma":[0.000083288454,0.00006687511,0.00007377498,0.00028034096,0.000050913528,0.00021089485,0.00047398385,0.00009788693,0.000019407462],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050616152,0.000540233,0.016412312,0.00021930493,0.00012423619,0.000004446753,0.015555159,0.0005165673,0.17414682,0.5860891,0.1397205,0.06662072],"study_design_scores_gemma":[0.0013891684,0.00023682386,0.0015306255,0.0002000244,0.000030458037,0.00010127933,0.0009489834,0.010633801,0.8909265,0.03914884,0.05444123,0.00041225503],"about_ca_topic_score_codex":0.000027747801,"about_ca_topic_score_gemma":6.030181e-7,"teacher_disagreement_score":0.7167797,"about_ca_system_score_codex":0.00005865012,"about_ca_system_score_gemma":0.00004125707,"threshold_uncertainty_score":0.27270877},"labels":[],"label_agreement":null},{"id":"W2295468252","doi":"10.14778/2856318.2856325","title":"Combining quantitative and logical data cleaning","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":104,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University; McMaster University; University of Toronto","funders":"","keywords":"Computer science; Metric (unit); Inference; Functional dependency; Set (abstract data type); Distortion (music); Statistical inference; Data mining; Algorithm; Theoretical computer science; Dependency (UML); Quality (philosophy); Data quality; Artificial intelligence; Relational database; Mathematics","score_opus":0.6149975953066957,"score_gpt":0.46831911800896336,"score_spread":0.14667847729773237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2295468252","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":[0.8576558,0.000619131,0.0020347037,0.01634783,0.00095049787,0.0010692904,0.00014263696,0.00009417782,0.121085934],"genre_scores_gemma":[0.99297893,0.000018739227,0.0060202754,0.000415054,0.000023338138,0.000006020169,0.0000035215762,0.000005000513,0.0005291247],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977972,0.000031881475,0.00043404335,0.00041970517,0.0011464946,0.00017070991],"domain_scores_gemma":[0.9986349,0.0003081137,0.00033326904,0.00037710302,0.00024603843,0.00010061237],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0059782444,0.00009779505,0.00021289579,0.000073743955,0.00010760045,0.0002372084,0.0018597412,0.000026016503,0.000018939967],"category_scores_gemma":[0.0047378363,0.00005502174,0.00003024039,0.0003319944,0.00018943092,0.0006538076,0.00362099,0.00010046949,0.000030717252],"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":[0.00012732235,0.00018007187,0.01047531,0.000032786473,0.00006513477,0.0000010813916,0.0058014565,0.000017464672,0.0013909802,0.8257729,0.1355931,0.020542407],"study_design_scores_gemma":[0.0026813566,0.0007681448,0.014293695,0.00020923157,0.00012735295,0.000021913154,0.10939527,0.00860213,0.0059854877,0.5873224,0.2700839,0.00050907466],"about_ca_topic_score_codex":0.000057334182,"about_ca_topic_score_gemma":0.000007735977,"teacher_disagreement_score":0.23845045,"about_ca_system_score_codex":0.000021559514,"about_ca_system_score_gemma":0.000018833302,"threshold_uncertainty_score":0.5671975},"labels":[],"label_agreement":null},{"id":"W2295513305","doi":"10.14778/3402755.3402776","title":"Debugging data exchange with vagabond","year":2011,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Semantic Web and Ontologies","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","funders":"","keywords":"Debugging; Computer science; Process (computing); Programming language; Background debug mode interface; Algorithmic program debugging; Data exchange; World Wide Web","score_opus":0.08127179066559559,"score_gpt":0.22769392641453015,"score_spread":0.14642213574893456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2295513305","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":[0.60448337,0.0033630345,0.0392726,0.009529696,0.0020123187,0.002580052,0.00002299461,0.0014366899,0.33729923],"genre_scores_gemma":[0.9408769,0.000030048945,0.058658488,0.00017574414,0.000031599804,0.000015770178,3.263931e-7,0.0000067951505,0.00020429942],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99904,0.0000034029351,0.00014397236,0.00031249734,0.0002741013,0.00022601997],"domain_scores_gemma":[0.99922293,0.000018365165,0.00015053058,0.0004892487,0.00008103313,0.00003786062],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026332735,0.00011025405,0.0001323353,0.00004772451,0.00007987058,0.000048912538,0.002821053,0.000023843224,0.000012653657],"category_scores_gemma":[0.000039419923,0.00006096907,0.000026014008,0.00022559844,0.00007194042,0.0005281902,0.0015518977,0.00007252308,0.000006094811],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019075486,0.0010400609,0.19403554,0.0009324094,0.0005725549,0.000022813096,0.03925276,0.0000034062848,0.02655946,0.50862783,0.041385245,0.18737715],"study_design_scores_gemma":[0.002815668,0.00096300116,0.13695996,0.00080555206,0.00026677837,0.00031487778,0.0025056368,0.009731671,0.7487727,0.07026994,0.025296519,0.0012977341],"about_ca_topic_score_codex":0.0001361938,"about_ca_topic_score_gemma":0.000019099853,"teacher_disagreement_score":0.7222132,"about_ca_system_score_codex":0.000016032933,"about_ca_system_score_gemma":0.00002373958,"threshold_uncertainty_score":0.5242265},"labels":[],"label_agreement":null},{"id":"W2296703446","doi":"10.14778/2733004.2733009","title":"TPC-DI","year":2014,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":69,"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; Master data; Data warehouse; Variety (cybernetics); Data integration; Enterprise data management; Data management; Context (archaeology); Data science; Analytics; Business intelligence; Database; Enterprise information system","score_opus":0.006928866262876887,"score_gpt":0.2013198379173866,"score_spread":0.19439097165450972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2296703446","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":[0.17036842,0.0005470241,0.68495053,0.008240313,0.0027955992,0.0014357596,0.000019355068,0.0005991098,0.1310439],"genre_scores_gemma":[0.9619393,0.000011231326,0.036953047,0.00021185112,0.00009502512,0.000031955587,2.994009e-7,0.0000073228757,0.0007500128],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99917585,0.000004529989,0.00018339272,0.00020524168,0.00025669867,0.00017431674],"domain_scores_gemma":[0.999445,0.000022350092,0.00016367168,0.00022561877,0.00009992623,0.00004340333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000254247,0.000093794086,0.00012932316,0.000031142477,0.000093863164,0.00002892226,0.0006632908,0.000019386465,0.0000034837408],"category_scores_gemma":[0.00007985511,0.000058040892,0.00006063383,0.00018068755,0.000047541464,0.00037805893,0.0005160126,0.00006235753,0.000012287691],"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":[0.0000023587384,0.000022990585,0.00096213433,0.00004811667,0.000007917121,6.395507e-8,0.0002826719,0.000008410064,0.020031683,0.9698065,0.0019571495,0.0068700262],"study_design_scores_gemma":[0.00063621614,0.00016522827,0.003931986,0.00021994776,0.000013109904,0.000029360182,0.00017178764,0.0044397656,0.4836682,0.019820027,0.4865787,0.0003256516],"about_ca_topic_score_codex":0.00002085497,"about_ca_topic_score_gemma":0.0000011686384,"teacher_disagreement_score":0.94998646,"about_ca_system_score_codex":0.000022395623,"about_ca_system_score_gemma":0.000010062474,"threshold_uncertainty_score":0.23668389},"labels":[],"label_agreement":null},{"id":"W2301743601","doi":"10.14778/2904483.2904486","title":"Leopard","year":2016,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"VLSI and FPGA Design Techniques","field":"Engineering","cited_by":93,"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":"Graph partition; Computer science; Graph; Space partitioning; Vertex (graph theory); Algorithm; Theoretical computer science","score_opus":0.0057559873206896065,"score_gpt":0.165789516692164,"score_spread":0.1600335293714744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2301743601","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":[0.789663,0.00064914045,0.0029961888,0.0017218998,0.0006808917,0.00094638066,0.000017766692,0.0016489439,0.20167577],"genre_scores_gemma":[0.99851036,0.00010758085,0.00077722315,0.000025017376,0.000045950135,0.000039230905,4.5040657e-8,0.000015685002,0.0004789241],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995028,9.398415e-7,0.00013429836,0.00007969975,0.00013604791,0.00014625488],"domain_scores_gemma":[0.99981534,0.000011471581,0.000032470496,0.000072596515,0.00003951891,0.000028589533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009377203,0.00008634578,0.00009610636,0.000034306126,0.000021735346,0.000009290191,0.00024886854,0.000032229458,0.00003227071],"category_scores_gemma":[0.000018069877,0.000043574903,0.00005997138,0.00008095094,0.00003220766,0.00009079252,0.00005384014,0.000041507577,0.000015666252],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033924628,0.000012228031,0.0018368239,0.000050289,0.000022553566,9.198606e-8,0.00008398108,0.0000019066997,0.95410043,0.005848942,0.020100024,0.017939309],"study_design_scores_gemma":[0.00014037227,0.000023901446,0.0008005056,0.00008881865,0.000009032894,0.000003433562,0.000015158841,0.000028412027,0.9833267,0.004602714,0.010882595,0.00007836067],"about_ca_topic_score_codex":0.0000022798317,"about_ca_topic_score_gemma":2.1931349e-7,"teacher_disagreement_score":0.20884733,"about_ca_system_score_codex":0.000046246583,"about_ca_system_score_gemma":0.0000029958708,"threshold_uncertainty_score":0.17769329},"labels":[],"label_agreement":null},{"id":"W2396123608","doi":"10.14778/3402707.3402730","title":"Business policy modeling and enforcement in databases","year":2011,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Service-Oriented Architecture and Web Services","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":"","keywords":"Computer science; Database; Business rule; Business process; Workflow; Business process modeling; Enforcement; Database design; Business logic; Business; Work in process","score_opus":0.03058924432200034,"score_gpt":0.23099414169690724,"score_spread":0.2004048973749069,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2396123608","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":[0.96345913,0.00033017452,0.0068128044,0.0018234891,0.0002112144,0.000553638,0.0000044158915,0.00008282935,0.026722275],"genre_scores_gemma":[0.9902955,0.00007337051,0.009020548,0.0005266653,0.00003753004,0.00002352971,4.696728e-7,0.0000059851545,0.000016382664],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99904394,0.0000042604156,0.00022865669,0.00026363457,0.00023112948,0.0002283477],"domain_scores_gemma":[0.9995408,0.000011452375,0.0001065729,0.00018408192,0.00010855762,0.000048552814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017614492,0.00012572331,0.00013246773,0.00017346418,0.00006448862,0.00003350969,0.0008139336,0.00001876859,0.0000056205035],"category_scores_gemma":[0.000012871977,0.00008377364,0.000026544432,0.0006446153,0.000025720692,0.0003963285,0.00094941113,0.000076842865,0.0000012467472],"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":[0.000050117713,0.0002491051,0.015803697,0.00041393327,0.00004137888,0.0000013658902,0.023451136,0.00054619234,0.010519799,0.93682784,0.00003292982,0.012062502],"study_design_scores_gemma":[0.004791801,0.00039043516,0.045058765,0.0020502275,0.000103345556,0.00012241844,0.0061354614,0.30818233,0.45304018,0.17288786,0.005640248,0.0015969309],"about_ca_topic_score_codex":0.0040277606,"about_ca_topic_score_gemma":0.000087555556,"teacher_disagreement_score":0.76394,"about_ca_system_score_codex":0.00002705491,"about_ca_system_score_gemma":0.000034940524,"threshold_uncertainty_score":0.60887957},"labels":[],"label_agreement":null},{"id":"W2401646429","doi":"10.14778/2831360.2831363","title":"Finding Pareto optimal groups","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":80,"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":"Air Force Office of Scientific Research; Science and Technology Planning Project of Guangdong Province; Natural Science Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Skyline; Computer science; Pruning; Pareto optimal; Scalability; Computation; Point (geometry); Heuristic; Set (abstract data type); Pareto principle; Group (periodic table); Data mining; Algorithm; Theoretical computer science; Mathematics; Mathematical optimization; Artificial intelligence; Database","score_opus":0.036021360278773625,"score_gpt":0.24106280418211742,"score_spread":0.2050414439033438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2401646429","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":[0.7089795,0.00065942126,0.07446523,0.018097717,0.0053601377,0.0025915573,0.000026315513,0.0009629025,0.18885721],"genre_scores_gemma":[0.9623431,0.000011854415,0.03624926,0.0002009993,0.00011147584,0.00003106839,0.0000011572713,0.000008837936,0.0010422594],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988187,0.00000391319,0.00019191476,0.00026104023,0.00047506578,0.00024936773],"domain_scores_gemma":[0.99943733,0.0000113143315,0.0001546911,0.00020776263,0.000103265826,0.00008562455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047612665,0.00011651102,0.00012494589,0.00006957579,0.000075484706,0.00019192022,0.0018031009,0.000022084583,0.0000040668197],"category_scores_gemma":[0.000057193924,0.00007945555,0.00006306719,0.00035341317,0.000038939914,0.00083729555,0.0014597153,0.000080849706,0.000025883435],"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":[0.000027260496,0.00031976608,0.011576944,0.0001331596,0.00013717725,0.0000046173486,0.0043280288,0.00015265618,0.0045431335,0.81665975,0.11962101,0.042496514],"study_design_scores_gemma":[0.0084434245,0.0015880336,0.016628746,0.00076534884,0.0002575864,0.000112594746,0.006869012,0.15252732,0.38453764,0.12861781,0.29696703,0.0026854638],"about_ca_topic_score_codex":0.000014881933,"about_ca_topic_score_gemma":4.294083e-7,"teacher_disagreement_score":0.6880419,"about_ca_system_score_codex":0.000057840807,"about_ca_system_score_gemma":0.000017765855,"threshold_uncertainty_score":0.33506402},"labels":[],"label_agreement":null},{"id":"W2402668406","doi":"10.14778/2735461.2735467","title":"Interpretable and informative explanations of outcomes","year":2014,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":82,"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":"Automatic summarization; Heuristics; Computer science; Construct (python library); Set (abstract data type); Dimension (graph theory); Data mining; Binary classification; Binary number; Machine learning; Sample (material); Artificial intelligence; Mathematics","score_opus":0.0047771768864128625,"score_gpt":0.19223746017089116,"score_spread":0.1874602832844783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2402668406","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":[0.45528734,0.00015102426,0.15896405,0.0130461715,0.0012718292,0.0019579008,0.00004436052,0.00026758338,0.36900973],"genre_scores_gemma":[0.98783374,0.000011405014,0.011607975,0.00013078439,0.0000059568533,0.0000120943805,4.563159e-7,0.0000018475821,0.0003957321],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99947417,0.000002349574,0.00016998197,0.000089268324,0.00017672309,0.00008751735],"domain_scores_gemma":[0.99961185,0.000029341969,0.00016594767,0.00010701339,0.00006608724,0.00001977716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002280105,0.00006099158,0.000108646185,0.00006518534,0.00004201112,0.00005296666,0.0006283052,0.000009992699,0.0000031566074],"category_scores_gemma":[0.000057073343,0.00003788334,0.00003031873,0.0001404005,0.000040062525,0.0007448601,0.00066264276,0.00003435502,0.0000014786871],"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":[0.0000038044534,0.00007656019,0.019864246,0.00014102823,0.000084108746,2.8059977e-8,0.004175443,0.000008451794,0.0012270682,0.9315855,0.0043026395,0.038531125],"study_design_scores_gemma":[0.004728019,0.0009302537,0.1921794,0.00082860957,0.00020600781,0.000013993035,0.004756938,0.21948856,0.33279675,0.17661004,0.066288784,0.0011726365],"about_ca_topic_score_codex":0.000015588615,"about_ca_topic_score_gemma":6.588807e-7,"teacher_disagreement_score":0.75497544,"about_ca_system_score_codex":0.0000082638135,"about_ca_system_score_gemma":0.0000037004836,"threshold_uncertainty_score":0.15448378},"labels":[],"label_agreement":null},{"id":"W2405215503","doi":"10.14778/3402707.3402722","title":"Data coordination","year":2011,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Semantic Web and Ontologies","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":"University of British Columbia","funders":"","keywords":"Computer science; Base (topology); Data source; Distributed computing; Data mining; Mathematics","score_opus":0.09979098660822669,"score_gpt":0.25600075673108735,"score_spread":0.15620977012286066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2405215503","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":[0.51025456,0.0010093132,0.041354768,0.026649984,0.003875251,0.0020269633,0.00002881839,0.0009578753,0.4138425],"genre_scores_gemma":[0.9809693,0.000010006021,0.018638374,0.00013185134,0.000020440679,0.0000072098806,3.48686e-7,0.000002750008,0.00021972331],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99932843,0.0000027729616,0.00013774663,0.00020802364,0.00019692695,0.0001261117],"domain_scores_gemma":[0.9994039,0.000013903211,0.00012595461,0.00034932967,0.00008620895,0.000020682217],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026517472,0.00006419757,0.00008283482,0.000033925542,0.00005398197,0.000031821735,0.002623609,0.000021151274,0.00000809543],"category_scores_gemma":[0.000092518254,0.000039838164,0.000026474603,0.00016903169,0.00004338786,0.00047172944,0.0012991403,0.000047650054,0.000008614927],"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":[0.000013061281,0.00023193035,0.025694484,0.00007716987,0.000056942703,7.7460663e-7,0.0031430149,4.624303e-7,0.016244307,0.8878413,0.035612404,0.03108415],"study_design_scores_gemma":[0.0009889174,0.00023645694,0.12738712,0.00014413046,0.00006427924,0.000046813093,0.0009129046,0.010938042,0.6851572,0.151358,0.02233369,0.00043247247],"about_ca_topic_score_codex":0.000051606807,"about_ca_topic_score_gemma":0.0000029018377,"teacher_disagreement_score":0.7364833,"about_ca_system_score_codex":0.00001405122,"about_ca_system_score_gemma":0.000013748479,"threshold_uncertainty_score":0.48753622},"labels":[],"label_agreement":null},{"id":"W2406955896","doi":"10.14778/2732219.2732227","title":"Multi-core, main-memory joins","year":2013,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Data Storage Technologies","field":"Computer Science","cited_by":247,"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":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Computer science; Hash join; Joins; Merge sort; Parallel computing; Join (topology); sort; Merge (version control); Hash function; Merge algorithm; SIMD; Theoretical computer science; Sorting algorithm; Database; Programming language; Mathematics","score_opus":0.025084745881657163,"score_gpt":0.23972005889048253,"score_spread":0.21463531300882538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2406955896","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":[0.8213486,0.0009483462,0.13314387,0.015207855,0.0020279726,0.0050245067,0.000040970746,0.0032463418,0.019011538],"genre_scores_gemma":[0.7174404,0.00003140084,0.2813375,0.00027594803,0.000022863938,0.00014803898,3.528418e-7,0.000012247413,0.0007312035],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986787,0.0000025456607,0.00026379075,0.00036623367,0.00034696877,0.00034175487],"domain_scores_gemma":[0.9990351,0.00002954086,0.00024601497,0.00048375258,0.00015195974,0.000053631356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015331377,0.0001712422,0.00017982107,0.00010089971,0.00011487442,0.00008625915,0.002377629,0.00005808849,0.00001778731],"category_scores_gemma":[0.00020367735,0.000114008966,0.00008094415,0.00040837718,0.00016046836,0.0009050202,0.0019709168,0.00018189696,0.00008834002],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005622714,0.00037227696,0.0024753208,0.00013199996,0.00006200668,0.00000252169,0.0010935223,0.000048989543,0.73581636,0.16327415,0.034097325,0.06261987],"study_design_scores_gemma":[0.0012631797,0.00017609917,0.013307141,0.00014629545,0.000019301426,0.00006153323,0.000941706,0.010638284,0.87452143,0.09271867,0.005639162,0.0005671781],"about_ca_topic_score_codex":0.000056718487,"about_ca_topic_score_gemma":0.0000018366054,"teacher_disagreement_score":0.14819363,"about_ca_system_score_codex":0.00010706523,"about_ca_system_score_gemma":0.000021492471,"threshold_uncertainty_score":0.4649151},"labels":[],"label_agreement":null},{"id":"W2492590231","doi":"10.14778/2983200.2983203","title":"Distributed data deduplication","year":2016,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":80,"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":"Data deduplication; Tuple; Computer science; Blocking (statistics); Block (permutation group theory); Relation (database); Backup; Locality; Process (computing); Theoretical computer science; Data mining; Database; Mathematics","score_opus":0.27015668142943616,"score_gpt":0.4095847037039765,"score_spread":0.13942802227454032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2492590231","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":[0.53420186,0.00044796744,0.06260016,0.31239685,0.002539681,0.004448726,0.006065222,0.0003774347,0.07692211],"genre_scores_gemma":[0.9969729,0.000034896664,0.0007136844,0.00032922538,0.000048093018,0.000023461926,0.000013878963,0.000004956632,0.0018588923],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978591,0.000014057066,0.00046756526,0.00042803856,0.0010639259,0.00016730075],"domain_scores_gemma":[0.9981716,0.0002162236,0.00040090503,0.00091236766,0.0002468247,0.000052059524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028330449,0.00008521082,0.00013965889,0.00006043705,0.00009177444,0.000107490894,0.0036101257,0.000024283818,0.00013077073],"category_scores_gemma":[0.0027982353,0.000036720947,0.000050297233,0.0004182962,0.00011102656,0.0006597339,0.0023385265,0.00003541284,0.00015625088],"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":[0.000041050534,0.00017856839,0.0076983077,0.00002086533,0.000045253637,9.9132635e-8,0.00014281253,0.0000010380242,0.033738043,0.18160972,0.6230755,0.15344873],"study_design_scores_gemma":[0.00055827317,0.00003815815,0.022558033,0.00006807549,0.0000369814,0.0000021759029,0.0005607348,0.00011306024,0.056911714,0.1197099,0.7993017,0.0001411777],"about_ca_topic_score_codex":0.000025190955,"about_ca_topic_score_gemma":0.0000059905256,"teacher_disagreement_score":0.46277106,"about_ca_system_score_codex":0.000042893793,"about_ca_system_score_gemma":0.00001607763,"threshold_uncertainty_score":0.6708572},"labels":[],"label_agreement":null},{"id":"W2512595308","doi":"10.14778/3067421.3067422","title":"Effective and complete discovery of order dependencies via set-based axiomatization","year":2017,"lang":"en","type":"preprint","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","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 Windsor; University of Waterloo; York University; Ontario Tech University","funders":"","keywords":"Computer science; Tuple; Completeness (order theory); Inference; Axiom; Rule of inference; Functional dependency; Set (abstract data type); Data mining; Theoretical computer science; Algorithm; Mathematics; Artificial intelligence; Relational database; Discrete mathematics","score_opus":0.10627989270277285,"score_gpt":0.36554846528466095,"score_spread":0.25926857258188807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2512595308","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":[0.92862576,0.0005723568,0.044241324,0.0048176064,0.0018971969,0.00620824,0.0012669788,0.00007313653,0.012297385],"genre_scores_gemma":[0.9976421,0.00004405493,0.0016117803,0.000101327976,0.000037904534,0.00012380512,0.000017444943,0.000013441772,0.00040815343],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99652123,0.000064020365,0.00081908697,0.00064141577,0.0017498058,0.00020444182],"domain_scores_gemma":[0.9958264,0.00045310255,0.0022152902,0.0006880905,0.00076772046,0.000049363105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033594456,0.00027509505,0.0006356508,0.00025058165,0.00022286916,0.0005649687,0.0020778584,0.00011836934,0.000019704748],"category_scores_gemma":[0.002580051,0.00017196836,0.00018238943,0.00021983782,0.00041099906,0.0005211645,0.003889347,0.00020965181,0.0000060249936],"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":[0.0023546412,0.003064084,0.08989029,0.023661176,0.0037959192,0.0000075752273,0.030185876,0.007448188,0.24226977,0.26579016,0.05540025,0.27613208],"study_design_scores_gemma":[0.003221047,0.00052344747,0.1476767,0.003035057,0.00080556545,0.000007890549,0.0041645863,0.019071246,0.25606704,0.5560165,0.0080988165,0.0013120841],"about_ca_topic_score_codex":0.0004662753,"about_ca_topic_score_gemma":0.000050521336,"teacher_disagreement_score":0.29022634,"about_ca_system_score_codex":0.00007165452,"about_ca_system_score_gemma":0.00006601547,"threshold_uncertainty_score":0.70126665},"labels":[],"label_agreement":null},{"id":"W2544486974","doi":"10.14778/2994509.2994518","title":"Detecting data errors","year":2016,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":237,"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":"University of California Berkeley","keywords":"Computer science; Raw data; Outlier; Data mining; Set (abstract data type); Variety (cybernetics); Data quality; Ground truth; Anomaly detection; Quality (philosophy); Big data; Data science; Machine learning; Artificial intelligence; Engineering","score_opus":0.30976099780462824,"score_gpt":0.41262294928917714,"score_spread":0.10286195148454891,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2544486974","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":[0.8245145,0.00020489054,0.003952549,0.058244314,0.0024263745,0.0016782933,0.000400624,0.00019917605,0.108379275],"genre_scores_gemma":[0.99439347,0.00001976695,0.0012644703,0.00030697422,0.0000648686,0.000011581206,6.5930794e-7,0.0000073253163,0.003930863],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973492,0.000019714142,0.0005474916,0.0004984864,0.001347826,0.00023725697],"domain_scores_gemma":[0.9980723,0.0003440704,0.000466794,0.00086386176,0.00019223653,0.000060700644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00496573,0.00010763893,0.00018001643,0.000102775724,0.00013860654,0.00012181615,0.0041889576,0.000027374881,0.00018562136],"category_scores_gemma":[0.00501184,0.000046149242,0.000071275084,0.00042631655,0.00012405789,0.00078664353,0.0036942144,0.00005910585,0.00015150444],"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":[0.00007913954,0.00019482571,0.013919795,0.00005613091,0.00010709281,6.834094e-7,0.0009899496,0.0000023793123,0.086810105,0.07285151,0.2312869,0.5937015],"study_design_scores_gemma":[0.001125774,0.00011145139,0.009615254,0.00023926575,0.000070922404,0.00000861578,0.004676851,0.0001844982,0.18276016,0.13835426,0.6625121,0.00034083013],"about_ca_topic_score_codex":0.000045145218,"about_ca_topic_score_gemma":0.000018741684,"teacher_disagreement_score":0.59336066,"about_ca_system_score_codex":0.000038518217,"about_ca_system_score_gemma":0.000016787368,"threshold_uncertainty_score":0.77841955},"labels":[],"label_agreement":null},{"id":"W2546973305","doi":"10.14778/3007263.3007267","title":"GraphJet","year":2016,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":76,"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; Graph; Exploit; Theoretical computer science; Clique-width; Line graph; Voltage graph","score_opus":0.006945037593673362,"score_gpt":0.19420157507786545,"score_spread":0.18725653748419208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2546973305","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":[0.7553497,0.00109715,0.12309057,0.06280648,0.0042061163,0.002636927,0.000014381383,0.0013109469,0.04948776],"genre_scores_gemma":[0.9898244,0.00006108803,0.00931329,0.00026523307,0.000042148335,0.000025590756,2.2415202e-8,0.0000072895946,0.00046091407],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99900234,0.0000036860688,0.00018449422,0.00025888477,0.00030026282,0.00025031768],"domain_scores_gemma":[0.99940956,0.000044188593,0.0001711645,0.00021760612,0.00010201606,0.000055470657],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012707924,0.00011171973,0.00011490628,0.000057398294,0.00007183212,0.000026576838,0.0013751762,0.000027891345,0.0000055932137],"category_scores_gemma":[0.000041042942,0.000052800227,0.0001070718,0.00041530002,0.00008620361,0.00042965563,0.00053687685,0.00006220458,0.000009251295],"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":[0.000013329016,0.0000679858,0.008830296,0.000021522503,0.000030339877,5.88333e-7,0.00018880851,0.000007053108,0.2449301,0.6714856,0.008027935,0.06639641],"study_design_scores_gemma":[0.0008428018,0.00014835905,0.0087744165,0.00020951417,0.000012232948,0.000027301494,0.000020314848,0.00026681146,0.6893929,0.28645137,0.0135690905,0.00028488695],"about_ca_topic_score_codex":0.000002165058,"about_ca_topic_score_gemma":4.5766782e-7,"teacher_disagreement_score":0.4444628,"about_ca_system_score_codex":0.00002751165,"about_ca_system_score_gemma":0.000007783081,"threshold_uncertainty_score":0.25554425},"labels":[],"label_agreement":null},{"id":"W2547436379","doi":"10.14778/3007263.3007293","title":"Collaborative crowdsourcing with crowd4U","year":2016,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Nautical Research Society","funders":"Army Research Office; Microsoft Research; Ministry of Education, Culture, Sports, Science and Technology; Agence Nationale de la Recherche; National Science Foundation","keywords":"Crowdsourcing; Software deployment; Computer science; Task (project management); Set (abstract data type); Data science; Crowdsourcing software development; Human–computer interaction; Knowledge management; Quality (philosophy); World Wide Web; Software engineering; Engineering; Software; Software development","score_opus":0.0036326253293779993,"score_gpt":0.18044141811212303,"score_spread":0.17680879278274503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2547436379","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":[0.94343644,0.00018548507,0.024285197,0.00815062,0.0003917234,0.00076477363,0.000005446428,0.00030941493,0.022470882],"genre_scores_gemma":[0.98857987,0.000011878916,0.010152071,0.00015291301,0.000058765705,0.000033760403,4.8916718e-8,0.000016695752,0.0009940187],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99845266,0.00001244044,0.00027018794,0.00041019046,0.00048782423,0.00036666813],"domain_scores_gemma":[0.99877,0.00008371988,0.00031113194,0.00032118443,0.00042343326,0.000090546644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000361743,0.00020236382,0.00022410118,0.000084671155,0.0002281613,0.00015020609,0.0009963802,0.000046379577,0.000008209874],"category_scores_gemma":[0.000093871146,0.00009486901,0.00007787195,0.0006529661,0.00017093252,0.00044761988,0.0003975918,0.00009616911,0.000010723746],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009718099,0.00019757131,0.015687928,0.00011570986,0.00016235936,0.000004716306,0.005119101,0.00006839459,0.80044353,0.13324694,0.0057667354,0.039089814],"study_design_scores_gemma":[0.0011903205,0.0002231174,0.002958793,0.0006635433,0.000027202583,0.000058111647,0.00043308505,0.00026989888,0.9847465,0.0029343215,0.0061807656,0.00031432416],"about_ca_topic_score_codex":0.000016256208,"about_ca_topic_score_gemma":0.0000031325967,"teacher_disagreement_score":0.18430297,"about_ca_system_score_codex":0.0000982649,"about_ca_system_score_gemma":0.00007635457,"threshold_uncertainty_score":0.38686457},"labels":[],"label_agreement":null},{"id":"W2548122763","doi":"10.14778/2994509.2994514","title":"ActiveClean","year":2016,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":244,"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":"MNIST database; Computer science; Context (archaeology); Support vector machine; Data mining; Convergence (economics); Process (computing); Class (philosophy); Iterative and incremental development; Machine learning; Artificial intelligence; Deep learning","score_opus":0.009115700324434017,"score_gpt":0.2121947867126384,"score_spread":0.20307908638820438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2548122763","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":[0.35625824,0.00024428862,0.27719334,0.15244272,0.0018138462,0.0013919857,0.000014805551,0.0009568534,0.20968392],"genre_scores_gemma":[0.98823136,0.000015588701,0.01057301,0.00009126191,0.000027976917,0.000012272708,9.592381e-8,0.000003741714,0.0010447019],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999399,0.000006654332,0.00011725924,0.00018284912,0.00017663343,0.0001175978],"domain_scores_gemma":[0.9995267,0.000035164914,0.0001479358,0.00018745528,0.00007123804,0.000031500836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024550143,0.00006172685,0.00006522557,0.000034179924,0.00006358518,0.000034275752,0.00091081834,0.000017557079,0.0000105892395],"category_scores_gemma":[0.00012363808,0.00002905918,0.0000414636,0.00014897944,0.000036198537,0.0003022806,0.00032721367,0.000047177637,0.000026465435],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000050923313,0.00004358792,0.005162852,0.000012705832,0.000010724554,3.3015958e-8,0.00024853944,2.9720874e-7,0.34996387,0.3406787,0.0026924536,0.30118114],"study_design_scores_gemma":[0.00063869683,0.00010652409,0.076522864,0.00012768761,0.000011149107,0.000010785298,0.00007034253,0.00087337213,0.8030983,0.023660831,0.09468397,0.0001954392],"about_ca_topic_score_codex":0.000009090244,"about_ca_topic_score_gemma":2.7925827e-7,"teacher_disagreement_score":0.6319731,"about_ca_system_score_codex":0.000033861215,"about_ca_system_score_gemma":0.0000116041465,"threshold_uncertainty_score":0.16925423},"labels":[],"label_agreement":null},{"id":"W2548429475","doi":"10.14778/3007263.3007289","title":"Sapphire","year":2016,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"SPARQL; Computer science; RDF; Information retrieval; Linked data; RDF Schema; Cloud computing; Vocabulary; Database; Semantic Web","score_opus":0.010229025287030399,"score_gpt":0.19948959821345455,"score_spread":0.18926057292642415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2548429475","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":[0.8444193,0.00049998314,0.012061124,0.0629525,0.0015437847,0.0007139052,0.0000028746836,0.00048522328,0.077321276],"genre_scores_gemma":[0.99446684,0.000028500734,0.0045065316,0.00016960247,0.000034562545,0.000013164943,9.096623e-9,0.0000031750149,0.00077760656],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99927807,0.0000024154926,0.00013853297,0.00017736742,0.00022971092,0.00017392192],"domain_scores_gemma":[0.9995897,0.000036141937,0.000104227634,0.00016316013,0.00007783576,0.000028973946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015349936,0.0000767219,0.00010121269,0.000032089676,0.00005381616,0.00003102657,0.0011668098,0.000024119905,0.000007999537],"category_scores_gemma":[0.00008835635,0.00003337328,0.00006720408,0.00014116964,0.00006422758,0.00023210446,0.00047013356,0.000031180836,0.000019990955],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008102873,0.00006936025,0.017827475,0.00003684961,0.000031642317,5.666241e-7,0.00059159426,2.917962e-7,0.2066006,0.68236095,0.010430043,0.08204249],"study_design_scores_gemma":[0.00055269024,0.00008419057,0.02434375,0.00014958995,0.00001052681,0.00002088197,0.00010493861,0.000086437554,0.8878292,0.074476875,0.012182308,0.00015865524],"about_ca_topic_score_codex":0.000009683239,"about_ca_topic_score_gemma":8.044335e-7,"teacher_disagreement_score":0.6812286,"about_ca_system_score_codex":0.000027624117,"about_ca_system_score_gemma":0.000014565369,"threshold_uncertainty_score":0.21682423},"labels":[],"label_agreement":null},{"id":"W2549035799","doi":"10.14778/3007263.3007320","title":"Qualitative data cleaning","year":2016,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":40,"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; Scripting language; Data quality; Data science; Analytics; Big data; Data mining; Qualitative property; Taxonomy (biology); Human error; Data analysis; Machine learning; Engineering; Reliability engineering","score_opus":0.49719438527572407,"score_gpt":0.5118316654115125,"score_spread":0.01463728013578841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2549035799","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":[0.5305543,0.00037204282,0.012773984,0.14685042,0.0029572733,0.0028874537,0.0015612461,0.000282114,0.30176115],"genre_scores_gemma":[0.9906567,0.000029674975,0.0020621761,0.00046064003,0.00006355929,0.0000140252905,0.0000019123615,0.000008211407,0.0067030974],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99707395,0.000054203138,0.0006099861,0.00051712495,0.0015164987,0.00022823692],"domain_scores_gemma":[0.9975797,0.00075669464,0.000523128,0.0007999892,0.00027780829,0.00006266577],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007971959,0.00011361256,0.00021056649,0.000098657794,0.00012307406,0.00012943112,0.0039916974,0.000025975121,0.00022627517],"category_scores_gemma":[0.0053848857,0.000048753016,0.00007263375,0.0004165528,0.00019017141,0.0009519894,0.0033566512,0.00005801426,0.00020923244],"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":[0.000074246906,0.00015256497,0.0012404068,0.000032946264,0.00009278326,3.3275384e-7,0.010124757,7.2548795e-7,0.019982668,0.44760528,0.38279852,0.13789476],"study_design_scores_gemma":[0.0011057628,0.00012199723,0.0027024832,0.00023299074,0.000056074652,0.0000031928748,0.046988912,0.00007014482,0.044552885,0.39121953,0.5126522,0.00029379534],"about_ca_topic_score_codex":0.00004059124,"about_ca_topic_score_gemma":0.000009891659,"teacher_disagreement_score":0.4601024,"about_ca_system_score_codex":0.000041729014,"about_ca_system_score_gemma":0.000019799001,"threshold_uncertainty_score":0.74176335},"labels":[],"label_agreement":null},{"id":"W2560800565","doi":"10.14778/3137628.3137635","title":"Revenue maximization in incentivized social advertising","year":2017,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Optimization and Search Problems","field":"Computer Science","cited_by":61,"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":"Submodular set function; Incentive; Revenue; Online advertising; Viral marketing; Monetization; Budget constraint; Knapsack problem; Microeconomics; Computer science; Social graph; Bidding; Advertising; Maximization; Social media; Business; Economics; The Internet; Mathematical optimization; Mathematics","score_opus":0.019394091572590408,"score_gpt":0.2669975460336904,"score_spread":0.2476034544611,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560800565","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":[0.66265184,0.0002641554,0.13751875,0.07603337,0.0027123932,0.004773823,0.000022146158,0.0003499083,0.115673624],"genre_scores_gemma":[0.9914254,0.000034400266,0.007953942,0.0000845894,0.000027520251,0.000018024926,2.5170812e-7,0.000005037895,0.00045086778],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9991935,0.000009403002,0.00018771373,0.00017101468,0.000270102,0.00016830255],"domain_scores_gemma":[0.9994309,0.000007977458,0.0002714816,0.00015002092,0.000115426265,0.000024201647],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036659016,0.000068438465,0.000108231274,0.000058178095,0.00034055708,0.00021542788,0.0011166184,0.00003170611,0.000004966547],"category_scores_gemma":[0.000107616914,0.000053721575,0.000045623485,0.00013964553,0.000059620994,0.00062085007,0.0005785368,0.00009026477,0.0000028866932],"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":[0.00013078656,0.00092045264,0.1824477,0.0005495064,0.00008984622,0.000004032888,0.022343744,0.00080987596,0.122035705,0.47190395,0.010810833,0.18795358],"study_design_scores_gemma":[0.009131769,0.00018160287,0.37994733,0.0011369439,0.000034188273,0.0000149982625,0.0003599478,0.2585043,0.22514269,0.114919946,0.009638741,0.000987561],"about_ca_topic_score_codex":0.000050769395,"about_ca_topic_score_gemma":0.000007684617,"teacher_disagreement_score":0.356984,"about_ca_system_score_codex":0.000065230706,"about_ca_system_score_gemma":0.000026839962,"threshold_uncertainty_score":0.2619324},"labels":[],"label_agreement":null},{"id":"W2571118757","doi":"10.14778/3015274.3015276","title":"Mostly-optimistic concurrency control for highly contended dynamic workloads on a thousand cores","year":2016,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":113,"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; Concurrency control; Server; Parallel computing; Concurrency; Cache; Distributed computing; Cache coherence; Lock (firearm); Deadlock; Out-of-order execution; Serialization; Operating system; CPU cache; Database transaction; Cache algorithms; Database","score_opus":0.010182189561394737,"score_gpt":0.23399981616808416,"score_spread":0.2238176266066894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2571118757","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":[0.20233181,0.001689224,0.72948194,0.03651856,0.005851727,0.009331218,0.001171501,0.0008308275,0.0127932085],"genre_scores_gemma":[0.9975842,0.000016408529,0.0011596283,0.00021572433,0.00004757536,0.00027765188,7.779945e-7,0.000013415753,0.0006845674],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983288,0.00001097251,0.00043175175,0.00043769856,0.00039121488,0.0003995704],"domain_scores_gemma":[0.99865997,0.00021087931,0.0004082284,0.00027062235,0.0003541246,0.00009616707],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034535863,0.00022914725,0.00036107254,0.000054674532,0.00013870845,0.00010269337,0.0011903711,0.000064897125,0.0000040731225],"category_scores_gemma":[0.00017508176,0.00012070175,0.00017936804,0.00019094943,0.00011022103,0.000213188,0.00012757434,0.00007953036,0.000006892104],"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":[0.00036627313,0.0003741017,0.0015734758,0.0002322303,0.00020226571,0.0000014994145,0.00039364307,0.000047234204,0.098462045,0.8396074,0.009755659,0.04898416],"study_design_scores_gemma":[0.08865922,0.010681211,0.02884931,0.011101881,0.00075039564,0.0001987048,0.0007438637,0.17689422,0.3712588,0.1887504,0.11678544,0.0053265747],"about_ca_topic_score_codex":0.000006334392,"about_ca_topic_score_gemma":0.0000013369787,"teacher_disagreement_score":0.79525244,"about_ca_system_score_codex":0.000115007235,"about_ca_system_score_gemma":0.00004643147,"threshold_uncertainty_score":0.49220744},"labels":[],"label_agreement":null},{"id":"W2572152291","doi":"10.14778/3021924.3021930","title":"Efficient computation of feedback arc set at web-scale","year":2016,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":37,"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 Victoria","funders":"","keywords":"Computer science; Scalability; Feedback arc set; Set (abstract data type); Randomized algorithm; Greedy algorithm; Theoretical computer science; Probabilistic logic; Algorithm; Graph; Artificial intelligence","score_opus":0.01020956528438349,"score_gpt":0.23808216134682195,"score_spread":0.22787259606243845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2572152291","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":[0.99084955,0.000020733585,0.0008916839,0.0004887902,0.00004138934,0.00028335667,0.000022137754,0.000028758077,0.007373577],"genre_scores_gemma":[0.9985845,0.000002334486,0.00094639533,0.000010018593,0.00006235813,0.000026283036,0.0000016186623,0.000010868642,0.000355637],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990632,0.0000066289103,0.0003086739,0.00018097233,0.00027231246,0.00016821531],"domain_scores_gemma":[0.99929297,0.000028203713,0.0003669871,0.000106192805,0.00016907028,0.00003654674],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017738031,0.000118614174,0.00021351298,0.000054585893,0.00006180518,0.000009267527,0.00026241108,0.000017536042,0.00010393607],"category_scores_gemma":[0.0000041114845,0.00006813695,0.00017981017,0.00019383272,0.00007662822,0.000027230755,0.00029548683,0.00004165491,0.000009118343],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008191881,0.0004271388,0.17870066,0.000088977285,0.0002546486,4.1099828e-8,0.0007813481,0.0006028238,0.76619935,0.015514538,0.016333425,0.021015132],"study_design_scores_gemma":[0.0010540284,0.00010146275,0.01217468,0.00037845905,0.00014237723,9.439622e-7,0.0003003916,0.0062639075,0.96433413,0.013279682,0.0017353556,0.00023456984],"about_ca_topic_score_codex":0.000039518072,"about_ca_topic_score_gemma":0.0000018742925,"teacher_disagreement_score":0.19813478,"about_ca_system_score_codex":0.000068660265,"about_ca_system_score_gemma":0.000012400784,"threshold_uncertainty_score":0.2778544},"labels":[],"label_agreement":null},{"id":"W2574861468","doi":"10.14778/3025111.3025123","title":"Skipping-oriented partitioning for columnar layouts","year":2016,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Data Storage Technologies","field":"Computer Science","cited_by":50,"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; Flexibility (engineering); Workload; Column (typography); Big data; Analytics; Database; Data access; Distributed computing; Tuple; Data science; Data mining; Mathematics","score_opus":0.01434291533108535,"score_gpt":0.23476807476105574,"score_spread":0.2204251594299704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2574861468","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":[0.11725757,0.00019034992,0.8644633,0.012862764,0.000805689,0.0016032393,0.000063818836,0.0010286086,0.0017246163],"genre_scores_gemma":[0.89365506,0.000022688997,0.10550037,0.00012394342,0.00003544641,0.0002452632,5.232312e-7,0.000010727757,0.0004059721],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99891526,0.0000025113204,0.00023067441,0.00031657808,0.0002465552,0.00028840252],"domain_scores_gemma":[0.99914396,0.00007436513,0.00025237608,0.00028304875,0.00021134291,0.000034919198],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020751003,0.00011681113,0.0001429627,0.00006379831,0.00015128404,0.00003933007,0.0012148201,0.0000423013,0.0000036040608],"category_scores_gemma":[0.00045207326,0.000068390524,0.00007458227,0.00028216143,0.00012035885,0.0006330317,0.0007509695,0.000051977673,0.0000067881774],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024381512,0.00009930131,0.0029571836,0.00007087794,0.000042924246,3.314782e-7,0.00038364908,0.000011560366,0.1741098,0.7808163,0.0075515946,0.03393211],"study_design_scores_gemma":[0.0010390027,0.00020857065,0.0010894346,0.00027359748,0.000015310983,0.000010339279,0.00015946254,0.00044938462,0.857893,0.097135395,0.041492693,0.00023380577],"about_ca_topic_score_codex":0.0000034211646,"about_ca_topic_score_gemma":0.0000013059796,"teacher_disagreement_score":0.77639747,"about_ca_system_score_codex":0.00010462975,"about_ca_system_score_gemma":0.000019042704,"threshold_uncertainty_score":0.27888846},"labels":[],"label_agreement":null},{"id":"W2579368542","doi":"10.14778/3025111.3025122","title":"Persistent hybrid transactional memory for databases","year":2016,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":32,"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":"Transactional memory; Computer science; Scalability; Software transactional memory; Synchronization (alternating current); Concurrency; Implementation; Transactional leadership; Database transaction; Concurrency control; Embedded system; Operating system; Parallel computing; Database; Software engineering; Computer network","score_opus":0.023698588738854606,"score_gpt":0.2329220493524717,"score_spread":0.2092234606136171,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2579368542","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":[0.15057367,0.0012912116,0.7977292,0.029700516,0.003656313,0.0033104182,0.0012091738,0.0003608616,0.012168616],"genre_scores_gemma":[0.9943507,0.000014855571,0.004203239,0.000110252935,0.00007436444,0.0001191191,0.0000010792475,0.0000062154318,0.0011202102],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989791,0.0000033077158,0.0002248218,0.00026990127,0.00031383068,0.00020907093],"domain_scores_gemma":[0.99939555,0.000047750516,0.00015129616,0.0001679085,0.00018342973,0.000054065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024131288,0.00010661881,0.00013963837,0.00003131873,0.00010922325,0.00003612321,0.0007537318,0.000013408455,0.00001031529],"category_scores_gemma":[0.00003529374,0.00005627878,0.00020286284,0.00009472694,0.000049142178,0.00037770075,0.0000956777,0.00003302552,0.0000050592753],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016962683,0.00069292105,0.001151408,0.0006251415,0.00040053052,0.0000012569974,0.00084906945,0.0000613037,0.39546382,0.30755365,0.086603634,0.20642762],"study_design_scores_gemma":[0.0029422648,0.00027535637,0.001032585,0.00062925916,0.0000672767,0.000102050275,0.00021649437,0.003491095,0.7889556,0.004159562,0.19766821,0.00046020217],"about_ca_topic_score_codex":0.000009918944,"about_ca_topic_score_gemma":6.5016644e-7,"teacher_disagreement_score":0.843777,"about_ca_system_score_codex":0.00006505225,"about_ca_system_score_gemma":0.000030310357,"threshold_uncertainty_score":0.2294982},"labels":[],"label_agreement":null},{"id":"W2591700809","doi":"10.14778/3137628.3137631","title":"HoloClean","year":2017,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":454,"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; Defense Advanced Research Projects Agency","keywords":"Leverage (statistics); Computer science; Probabilistic logic; Inference; Tuple; Data mining; Statistical model; Machine learning; Artificial intelligence; Mathematics","score_opus":0.22842113719041443,"score_gpt":0.4286142488382545,"score_spread":0.20019311164784007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2591700809","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":[0.581025,0.00004108088,0.000087839646,0.024449741,0.0010436918,0.00057143305,0.000028283312,0.000039192495,0.39271373],"genre_scores_gemma":[0.9901442,0.000014291614,0.0004617177,0.0003847261,0.000059751605,0.000012974079,2.2077373e-7,0.000005049163,0.008917073],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979413,0.000008699308,0.00038580198,0.00029643648,0.0011827187,0.00018502654],"domain_scores_gemma":[0.99826056,0.000067055895,0.0006783588,0.00073050876,0.00020838475,0.000055133634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028892548,0.00009153604,0.00017483621,0.00006363964,0.00048777726,0.00057495205,0.0038197737,0.000025606552,0.00013652032],"category_scores_gemma":[0.0026008012,0.00005030314,0.00012403652,0.0001049913,0.00022738478,0.0005424615,0.0018964281,0.00007774967,0.00016891785],"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":[0.000058013004,0.00023263598,0.03047157,0.000045969504,0.000069661015,9.3672304e-7,0.0012200383,0.000004676824,0.008127528,0.49477202,0.33836237,0.12663458],"study_design_scores_gemma":[0.0007907638,0.00009693258,0.1417979,0.00007219232,0.000042830896,0.000004126095,0.0026405826,0.000100045116,0.08212352,0.28274205,0.48936182,0.00022724316],"about_ca_topic_score_codex":0.000084885505,"about_ca_topic_score_gemma":0.000009997489,"teacher_disagreement_score":0.4091192,"about_ca_system_score_codex":0.000022835353,"about_ca_system_score_gemma":0.000010587316,"threshold_uncertainty_score":0.7098153},"labels":[],"label_agreement":null},{"id":"W2616147950","doi":"10.14778/3115404.3115409","title":"Auto-join","year":2017,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":66,"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":"Joins; Join (topology); Computer science; Transformation (genetics); Domain (mathematical analysis); String (physics); Database; Data mining; Theoretical computer science; Programming language; Mathematics","score_opus":0.19962649177423786,"score_gpt":0.4134582450415684,"score_spread":0.21383175326733056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2616147950","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":[0.3593015,0.0000888122,0.00025488046,0.04407267,0.0019231034,0.0010338206,0.000057418318,0.00007551115,0.5931923],"genre_scores_gemma":[0.9845093,0.000016093094,0.0007370529,0.00042024293,0.00006947974,0.00002097857,3.231767e-7,0.0000058122955,0.014220709],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976644,0.0000105407835,0.00045332251,0.00032973324,0.0013317786,0.0002102305],"domain_scores_gemma":[0.9981151,0.000082763654,0.00075638824,0.000758498,0.00022520404,0.000062045314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032645203,0.000105961655,0.00020365432,0.00007488864,0.00050972303,0.0006620825,0.0037798367,0.000030618357,0.00019230042],"category_scores_gemma":[0.002977339,0.000058914313,0.00014040794,0.00012143654,0.0002163719,0.0006064652,0.0020014464,0.00008723116,0.00019545775],"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":[0.00004967026,0.00023604221,0.01742536,0.0000561211,0.00007307003,8.7720787e-7,0.0011789707,0.0000049124883,0.012397085,0.49123296,0.384108,0.09323694],"study_design_scores_gemma":[0.00066539604,0.000072268034,0.08386739,0.0000710882,0.00003837509,0.0000032514204,0.0015339248,0.00022891264,0.05437285,0.24218534,0.61676323,0.00019797371],"about_ca_topic_score_codex":0.000115769944,"about_ca_topic_score_gemma":0.000013101016,"teacher_disagreement_score":0.6252078,"about_ca_system_score_codex":0.000031349173,"about_ca_system_score_gemma":0.000016739512,"threshold_uncertainty_score":0.702394},"labels":[],"label_agreement":null},{"id":"W2619906413","doi":"10.14778/3099622.3099623","title":"Revisiting the stop-and-stare algorithms for influence maximization","year":2017,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":132,"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; Ministry of Education, India","keywords":"Maximization; Scalability; Computer science; Set (abstract data type); Scaling; Order (exchange); Approximation algorithm; Mathematical optimization; Algorithm; Mathematics; Economics","score_opus":0.0194310404711445,"score_gpt":0.28423438600650436,"score_spread":0.26480334553535984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2619906413","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":[0.97348404,0.00024102491,0.0074142017,0.0076604267,0.0001011298,0.001970093,0.000037649585,0.000075424316,0.009016015],"genre_scores_gemma":[0.9959675,0.000010389929,0.0034641004,0.000035087407,0.000245358,0.00011112218,0.0000016204194,0.000009367188,0.00015542873],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993892,0.0000033926444,0.00018118128,0.00015412855,0.0001335819,0.00013852544],"domain_scores_gemma":[0.99913615,0.000033653905,0.00042752837,0.00019433264,0.00018754762,0.000020785348],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026058158,0.000096095355,0.00013628039,0.000017629676,0.00061037997,0.00016102676,0.0005178602,0.000013646282,0.000009800626],"category_scores_gemma":[0.000041870582,0.00005684004,0.00009772077,0.00004711254,0.00008218846,0.00015412166,0.00031023225,0.000071508766,3.785159e-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":[0.000042794007,0.000067476125,0.33397397,0.00019991821,0.00036417626,5.7698458e-8,0.001663497,0.00026312887,0.015564481,0.3004269,0.0023583893,0.34507522],"study_design_scores_gemma":[0.002577603,0.00019644908,0.19529936,0.0015280356,0.0011321829,0.000004924774,0.003998016,0.061999425,0.30472842,0.37843302,0.048917588,0.0011849753],"about_ca_topic_score_codex":0.00011759481,"about_ca_topic_score_gemma":5.2011745e-7,"teacher_disagreement_score":0.34389025,"about_ca_system_score_codex":0.000016262975,"about_ca_system_score_gemma":0.000007866463,"threshold_uncertainty_score":0.46946108},"labels":[],"label_agreement":null},{"id":"W2621145626","doi":"10.14778/3099622.3099626","title":"Attribute-driven community search","year":2017,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":241,"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":"Computer science; Node (physics); Theoretical computer science; Relevance (law); Graph; Community structure; Cohesion (chemistry); Data mining; Mathematics; Combinatorics","score_opus":0.04102465157361466,"score_gpt":0.3032241378313941,"score_spread":0.26219948625777945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2621145626","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":[0.9562356,0.000010333797,0.0001491237,0.0007569417,0.00004505531,0.00028885237,0.000014649196,0.000035339937,0.042464107],"genre_scores_gemma":[0.99872714,0.000003187533,0.0006295879,0.000017231561,0.00012295775,0.0000324204,0.0000025955276,0.000010949738,0.00045393335],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99921113,0.000015190502,0.0001915436,0.00012258146,0.0002438831,0.00021567244],"domain_scores_gemma":[0.99899507,0.000029205037,0.00027971066,0.00046367102,0.00018536563,0.000046988513],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039921215,0.0001178787,0.00020420001,0.00003298868,0.00092147826,0.00012836391,0.0014906954,0.000019985535,0.00010458909],"category_scores_gemma":[0.000016034175,0.00008449266,0.00018497126,0.00007309437,0.00015759614,0.0001373857,0.001180349,0.0003128576,0.0000075026314],"study_design_candidate":"observational","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":[0.000012271674,0.00027326506,0.91299534,0.00003240821,0.0002106703,5.4893988e-8,0.000570152,0.000019044226,0.02006343,0.051418554,0.007716234,0.006688601],"study_design_scores_gemma":[0.0010300203,0.00015017219,0.2870824,0.00027590376,0.00023448002,0.0000013829736,0.0016671309,0.0015627277,0.6484465,0.050857868,0.008218663,0.00047274382],"about_ca_topic_score_codex":0.0014134153,"about_ca_topic_score_gemma":0.000009821865,"teacher_disagreement_score":0.62838304,"about_ca_system_score_codex":0.000036202156,"about_ca_system_score_gemma":0.000015002552,"threshold_uncertainty_score":0.7087359},"labels":[],"label_agreement":null},{"id":"W2750991217","doi":"10.14778/3137765.3137788","title":"Interactive navigation of open data linkages","year":2017,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":24,"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; Scalability; Cloud computing; The Internet; Big data; Interface (matter); Data mining; Linkage (software); Millisecond; Information retrieval; World Wide Web; Database; Operating system","score_opus":0.07352448097533695,"score_gpt":0.3467404140371007,"score_spread":0.2732159330617637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2750991217","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":[0.48272163,0.00036898974,0.031643257,0.052422773,0.006481676,0.00820128,0.00054312707,0.0003067002,0.41731057],"genre_scores_gemma":[0.9792583,0.000025233547,0.019955995,0.000046115416,0.000040815205,0.000013305531,0.000007778519,0.0000044361054,0.00064800703],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991727,0.0000035952316,0.00018765673,0.00027875887,0.00025139295,0.00010593549],"domain_scores_gemma":[0.99829566,0.00001673016,0.0005904602,0.0009603945,0.00011481937,0.000021901882],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0004890842,0.00007657579,0.00012795923,0.000031153922,0.00016594466,0.0006306551,0.013280481,0.000014848073,0.0000044371955],"category_scores_gemma":[0.00011926006,0.000051985196,0.000027841865,0.00007442619,0.000069915994,0.004080686,0.017588599,0.00006786437,0.000004390636],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044339165,0.0007352378,0.01787056,0.00048335668,0.00042779473,0.0000022979493,0.003151432,0.0000061083238,0.042440247,0.36466163,0.05461492,0.51556206],"study_design_scores_gemma":[0.0024688984,0.00031604109,0.07515684,0.001497129,0.00013521075,0.0000091551365,0.0008584633,0.04004428,0.7634811,0.06349241,0.051957164,0.0005833007],"about_ca_topic_score_codex":0.00019393158,"about_ca_topic_score_gemma":0.0000016536487,"teacher_disagreement_score":0.72104084,"about_ca_system_score_codex":0.000015621637,"about_ca_system_score_gemma":0.000013371451,"threshold_uncertainty_score":0.99205816},"labels":[],"label_agreement":null},{"id":"W2751694342","doi":"10.14778/3137628.3137630","title":"Trajectory similarity join in spatial networks","year":2017,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":179,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Beijing Nova Program; King Abdullah University of Science and Technology; National Natural Science Foundation of China; Innovationsfonden","keywords":"Join (topology); Computer science; Pruning; Similarity (geometry); Trajectory; Nearest neighbor search; Heuristic; Matching (statistics); Data mining; Scheduling (production processes); Algorithm; Theoretical computer science; Artificial intelligence; Mathematics; Mathematical optimization","score_opus":0.017957525548891625,"score_gpt":0.2326463657509419,"score_spread":0.21468884020205029,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2751694342","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":[0.61113197,0.00068999483,0.12078937,0.034044098,0.009884554,0.005164852,0.00003494446,0.0006155878,0.21764465],"genre_scores_gemma":[0.9957062,0.000034477915,0.0036973408,0.00013590323,0.00010679132,0.000020282738,4.767567e-7,0.000005522338,0.00029297575],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99897367,0.000005084467,0.00020604536,0.00027764752,0.00028817652,0.00024939867],"domain_scores_gemma":[0.99923086,0.00001206393,0.00025904135,0.00041569507,0.000043804364,0.000038550115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047627816,0.000114710565,0.00014758695,0.000057797843,0.00020435259,0.0003233687,0.0027833115,0.000034773304,0.0000067041615],"category_scores_gemma":[0.00006288499,0.000083354986,0.00006796947,0.00009639008,0.00007470499,0.0008001223,0.0015572353,0.00014951445,0.0000033723093],"study_design_candidate":"observational","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":[0.00008183008,0.0012035789,0.24829292,0.00039802957,0.0001467031,0.00001722348,0.0021305052,0.00063407986,0.0059012426,0.23371635,0.033703383,0.47377414],"study_design_scores_gemma":[0.002774164,0.00019681864,0.7102966,0.00032208135,0.000042472344,0.000006086137,0.00012286418,0.22558244,0.03072217,0.018450417,0.010794926,0.00068900123],"about_ca_topic_score_codex":0.00029543447,"about_ca_topic_score_gemma":0.000052325548,"teacher_disagreement_score":0.47308514,"about_ca_system_score_codex":0.000041239076,"about_ca_system_score_gemma":0.000012204574,"threshold_uncertainty_score":0.51721317},"labels":[],"label_agreement":null},{"id":"W2752921427","doi":"10.14778/3137765.3137771","title":"Query-able Kafka","year":2017,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada)","funders":"","keywords":"SPARK (programming language); Computer science; Analytics; Downstream (manufacturing); Overhead (engineering); Pipeline (software); Upstream (networking); Big data; Order (exchange); Computer network; Data science; Data mining; Operating system; Engineering","score_opus":0.016787425411015303,"score_gpt":0.25097056548130364,"score_spread":0.23418314007028834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2752921427","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":[0.32951903,0.0002911954,0.016434796,0.038941722,0.0026282223,0.0025797521,0.000051849704,0.0020021729,0.6075513],"genre_scores_gemma":[0.9241966,0.000020286821,0.07465646,0.00012555438,0.000045236487,0.000044552875,2.536987e-7,0.000008941056,0.00090210617],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99892265,0.0000030665722,0.00019382751,0.00029442608,0.000342515,0.00024354822],"domain_scores_gemma":[0.99858457,0.000014917343,0.00040345796,0.00082094956,0.00012489442,0.000051229148],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037763658,0.00012453599,0.00015472024,0.000048156875,0.00033902703,0.00039899637,0.004901499,0.00003938869,0.000006808636],"category_scores_gemma":[0.00021045136,0.000085451895,0.000077596225,0.0000807505,0.0001497657,0.0008899518,0.0024373948,0.000106466345,0.000014056127],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012986693,0.00020468765,0.016778937,0.0001018939,0.0000611402,0.0000018138173,0.00082001864,9.66727e-7,0.054229774,0.7796585,0.101776786,0.046352528],"study_design_scores_gemma":[0.00035004306,0.00011437516,0.008372648,0.00019695825,0.00001639019,0.000019832587,0.000035781875,0.0007561648,0.89816004,0.061925266,0.029822657,0.00022985232],"about_ca_topic_score_codex":0.00017956451,"about_ca_topic_score_gemma":0.0000025149338,"teacher_disagreement_score":0.84393024,"about_ca_system_score_codex":0.00004853107,"about_ca_system_score_gemma":0.000027132095,"threshold_uncertainty_score":0.91082865},"labels":[],"label_agreement":null},{"id":"W2753088425","doi":"10.14778/3137628.3137637","title":"I've seen \"enough\"","year":2017,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":69,"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; Visualization; Usability; Sampling (signal processing); Interactivity; Data mining; Context (archaeology); Speedup; Creative visualization; Data visualization; Sample (material); Machine learning; Data science; Human–computer interaction; World Wide Web; Computer vision; Parallel computing","score_opus":0.026778950403935492,"score_gpt":0.29047185050860946,"score_spread":0.26369290010467394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2753088425","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":[0.18039562,0.0003471076,0.06532205,0.06977273,0.0047640875,0.0023406052,0.00008136377,0.0008040913,0.6761723],"genre_scores_gemma":[0.991994,0.000028443792,0.0050943242,0.00035711727,0.00005813189,0.0000061842143,5.0416355e-7,0.000005602105,0.0024556909],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992126,0.000002223446,0.00015636106,0.0001837368,0.00029599539,0.00014904427],"domain_scores_gemma":[0.9991261,0.000007695338,0.00029640953,0.00038947747,0.00013267114,0.000047695285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002094565,0.00008106488,0.00010423144,0.000032362885,0.00030003896,0.00035258944,0.0024872632,0.000022509928,0.000010301957],"category_scores_gemma":[0.00012115489,0.000053990963,0.00006220066,0.00008571981,0.00006633272,0.0005471233,0.0010721808,0.000055440778,0.000022770784],"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":[0.0000037515763,0.00012776059,0.0073667862,0.000062404506,0.000046805384,5.4839114e-7,0.0012650423,0.000005474488,0.009728499,0.9462515,0.026004026,0.009137377],"study_design_scores_gemma":[0.0023728367,0.00026147414,0.03783859,0.00042309592,0.00010198526,0.000032993896,0.0006533157,0.048884388,0.6312818,0.064882815,0.21237074,0.00089596043],"about_ca_topic_score_codex":0.000017570876,"about_ca_topic_score_gemma":9.168307e-7,"teacher_disagreement_score":0.8813687,"about_ca_system_score_codex":0.000022321172,"about_ca_system_score_gemma":0.000019916859,"threshold_uncertainty_score":0.46219954},"labels":[],"label_agreement":null},{"id":"W2765782779","doi":"10.14778/3151106.3151107","title":"Scalable replay-based replication for fast databases","year":2017,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":28,"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":"Backup; Computer science; Scalability; Bottleneck; Transaction log; Backup software; Replication (statistics); Database; Fault tolerance; Computer network; Database transaction; Bandwidth (computing); High availability; Throughput; Distributed computing; Operating system; Embedded system","score_opus":0.038431743002288236,"score_gpt":0.292418312224537,"score_spread":0.25398656922224877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2765782779","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":[0.24467807,0.0005918057,0.656847,0.03753402,0.0035163735,0.0076933056,0.0007960179,0.00065125787,0.047692128],"genre_scores_gemma":[0.9834422,0.0000041086214,0.015488738,0.00012962907,0.00006320594,0.00021035486,0.00000457793,0.0000072212197,0.00064995233],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988692,0.0000027278822,0.0002519469,0.0004162361,0.0002592013,0.00020070445],"domain_scores_gemma":[0.99800247,0.000025491587,0.00055560534,0.001094027,0.00027564765,0.000046762838],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005181615,0.00010504189,0.00015428792,0.000025888745,0.00046122295,0.00025295065,0.0018628689,0.000024390789,0.0000017959794],"category_scores_gemma":[0.00029503735,0.00007337558,0.00009099236,0.000080008715,0.000061344785,0.0005290757,0.00032579157,0.000049706654,0.0000039769748],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011905559,0.0004735369,0.02515779,0.00091532496,0.00009456426,5.87232e-7,0.0005217963,0.000124895,0.15986037,0.6541004,0.10076403,0.057867657],"study_design_scores_gemma":[0.001622547,0.00013684676,0.011423581,0.00049502746,0.000029405315,0.000008906101,0.000070427166,0.053854417,0.76596445,0.0033082247,0.1627605,0.0003256461],"about_ca_topic_score_codex":0.00008411734,"about_ca_topic_score_gemma":0.0000028813247,"teacher_disagreement_score":0.73876417,"about_ca_system_score_codex":0.000039899707,"about_ca_system_score_gemma":0.00003668753,"threshold_uncertainty_score":0.35474008},"labels":[],"label_agreement":null},{"id":"W2765816511","doi":"10.14778/3151106.3151111","title":"Efficient mining of regional movement patterns in semantic trajectories","year":2017,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Trajectory; Computer science; Focus (optics); Data mining; Movement (music); Scheme (mathematics); Semantics (computer science); Space (punctuation); Key (lock); Artificial intelligence; Mathematics","score_opus":0.023246962939578505,"score_gpt":0.242734101600947,"score_spread":0.21948713866136849,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2765816511","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":[0.99427193,0.000037474285,0.0012779103,0.0017810205,0.0003438253,0.00033244837,0.0000051970574,0.000018658895,0.0019315606],"genre_scores_gemma":[0.9958568,0.000013570392,0.003828165,0.0000677956,0.000030564166,0.000021614147,4.33814e-7,0.0000049456617,0.00017607815],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99877894,0.0000038720577,0.0002895356,0.0002547335,0.00046444795,0.0002084896],"domain_scores_gemma":[0.999101,0.000016870366,0.00042405093,0.00035988438,0.00007014482,0.000028043352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038973708,0.00011375884,0.00017333038,0.00009333963,0.00012330971,0.00012897934,0.0020039787,0.000019024363,0.0000038330973],"category_scores_gemma":[0.00004274173,0.00008144228,0.00007138026,0.000113043505,0.000074522985,0.00024678087,0.0011461632,0.00005874729,0.0000010370734],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055516328,0.0013932863,0.59383374,0.0011885181,0.00022141686,0.00000770191,0.01128236,0.0006467534,0.034364786,0.31047603,0.0030341714,0.04349568],"study_design_scores_gemma":[0.0024131376,0.00027102363,0.76624763,0.0013611863,0.00005170375,0.000004229427,0.0017373621,0.054835662,0.16468422,0.006889146,0.0009875228,0.00051717914],"about_ca_topic_score_codex":0.00017394153,"about_ca_topic_score_gemma":0.00001076283,"teacher_disagreement_score":0.3035869,"about_ca_system_score_codex":0.00003814222,"about_ca_system_score_gemma":0.000013945787,"threshold_uncertainty_score":0.37239242},"labels":[],"label_agreement":null},{"id":"W2786851308","doi":"10.14778/3199517.3199520","title":"Distributed evaluation of subgraph queries using worst-case optimal low-memory dataflows","year":2018,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":19,"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":"Dataflow; Computer science; Computation; Memory footprint; Joins; Massively parallel; Graph; Parallel computing; Theoretical computer science; Distributed computing; Algorithm","score_opus":0.03065908720145722,"score_gpt":0.27186278200001407,"score_spread":0.24120369479855686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2786851308","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":[0.98613364,0.00008773525,0.012356245,0.000111252804,0.00039636865,0.00045277833,0.000035123343,0.000042837142,0.00038399763],"genre_scores_gemma":[0.98560834,0.000003871512,0.014248506,0.000026869846,0.00007127653,0.000019624753,0.0000024565963,0.000007867031,0.00001118666],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983817,0.000035348367,0.00036556873,0.0003188536,0.0006482508,0.000250301],"domain_scores_gemma":[0.998414,0.00003438453,0.00038440115,0.0003204366,0.00078540726,0.000061384664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015750446,0.00016035767,0.0001999588,0.00012113631,0.00022023726,0.000068327536,0.00092900306,0.000045620254,0.000020900527],"category_scores_gemma":[0.00014801974,0.00011771552,0.000118366515,0.0007308742,0.00033408141,0.00062423415,0.0005400721,0.000092781665,0.0000021552642],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046898215,0.0020768119,0.006718559,0.00089523976,0.00079708116,0.000026470825,0.02174058,0.0044213226,0.6214676,0.2684966,0.0018572331,0.07103355],"study_design_scores_gemma":[0.0010403418,0.00021481366,0.0007748189,0.00023167336,0.0001559275,0.00021844373,0.0010272999,0.20445865,0.77310735,0.018426128,0.00007391285,0.00027063125],"about_ca_topic_score_codex":0.00004552956,"about_ca_topic_score_gemma":0.0000027716414,"teacher_disagreement_score":0.25007048,"about_ca_system_score_codex":0.00005499443,"about_ca_system_score_gemma":0.00006536766,"threshold_uncertainty_score":0.48002994},"labels":[],"label_agreement":null},{"id":"W2798664493","doi":"10.14778/3192965.3192973","title":"Table union search on open data","year":2018,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":193,"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":"Table (database); Computer science; Benchmark (surveying); Data mining; Set (abstract data type); Semantic search; Domain (mathematical analysis); Ontology; Decision table; Probabilistic logic; Information retrieval; Search engine; Artificial intelligence; Mathematics; Programming language","score_opus":0.48054255452095584,"score_gpt":0.4884253644300699,"score_spread":0.007882809909114052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2798664493","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":[0.14392589,0.000053706885,0.0005731527,0.06921851,0.0016684515,0.002985392,0.0004888851,0.000073652496,0.78101236],"genre_scores_gemma":[0.9754143,0.00002897564,0.0017305071,0.003336686,0.00013562753,0.000023069544,0.00001300143,0.000011988765,0.019305864],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969523,0.000043248896,0.0004378641,0.000614234,0.0016927511,0.00025959374],"domain_scores_gemma":[0.9979764,0.00015689502,0.0002506188,0.0011581137,0.00038716942,0.00007080311],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.010258411,0.000108462635,0.00019549599,0.00011024985,0.00026476663,0.0006400906,0.010241611,0.000025533533,0.0004610213],"category_scores_gemma":[0.0013318779,0.00006089952,0.000033590495,0.0007900212,0.00020266307,0.0010107273,0.012952176,0.00010497614,0.00044534542],"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":[0.000075199125,0.00020598088,0.0009332173,0.000012908748,0.000028405233,1.5634785e-7,0.00040697042,0.0000033356066,0.0023794074,0.10444706,0.8579091,0.033598304],"study_design_scores_gemma":[0.000430178,0.00023024277,0.0018608792,0.00006300217,0.000013084304,0.0000011404599,0.0017424794,0.00041701316,0.048950367,0.023500832,0.92268395,0.00010681401],"about_ca_topic_score_codex":0.0004345713,"about_ca_topic_score_gemma":0.00004147274,"teacher_disagreement_score":0.8314884,"about_ca_system_score_codex":0.000034097906,"about_ca_system_score_gemma":0.000040924526,"threshold_uncertainty_score":0.99511343},"labels":[],"label_agreement":null},{"id":"W2808068568","doi":"10.14778/3213880.3213884","title":"Morton filters","year":2018,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Caching and Content Delivery","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Advanced Micro Devices (Canada)","funders":"","keywords":"Bloom filter; Computer science; Hash function; Filter (signal processing); Parallel computing; Set (abstract data type); Cache; Metadata; Data structure; Computer hardware; Algorithm; Operating system; Programming language","score_opus":0.010008721895973577,"score_gpt":0.20012860783806471,"score_spread":0.19011988594209114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2808068568","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":[0.95801896,0.00007770697,0.001561543,0.003208141,0.00094269594,0.00023708558,0.0000014878932,0.0001398304,0.035812564],"genre_scores_gemma":[0.99728537,0.000007276546,0.0012850566,0.00042959704,0.00009697863,0.0000097194625,6.960008e-8,0.000004358458,0.0008815897],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99920964,0.0000030357528,0.00014306522,0.00019862092,0.00027373264,0.00017189],"domain_scores_gemma":[0.9995279,0.000011551668,0.00010922273,0.00017327006,0.00013878293,0.000039302722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001797334,0.00008346685,0.00009061399,0.000044609224,0.00010712949,0.00006684242,0.0010351121,0.000020516756,0.000008296882],"category_scores_gemma":[0.000029978797,0.000055088705,0.00008409826,0.0001951277,0.00007233072,0.00021749924,0.0004460116,0.0000676652,0.000023743656],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005027951,0.00027190085,0.014028618,0.00009096422,0.00013796883,0.0000014309344,0.0041082352,0.0000121762,0.63336444,0.24075134,0.07091645,0.036266215],"study_design_scores_gemma":[0.0009502899,0.0005167682,0.008445333,0.00023468313,0.000040515195,0.000047645717,0.0002902196,0.015616619,0.9419585,0.013819995,0.017651519,0.00042794808],"about_ca_topic_score_codex":0.000058868336,"about_ca_topic_score_gemma":0.0000012628575,"teacher_disagreement_score":0.30859405,"about_ca_system_score_codex":0.00003330027,"about_ca_system_score_gemma":0.000013571821,"threshold_uncertainty_score":0.22464523},"labels":[],"label_agreement":null},{"id":"W2809683060","doi":"10.14778/3231751.3231764","title":"Experimental analysis of distributed graph systems","year":2018,"lang":"en","type":"preprint","venue":"Proceedings of the VLDB Endowment","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"PageRank; Computer science; Scalability; Heuristics; Graph; Usability; SPARK (programming language); Distributed computing; Power graph analysis; Theoretical computer science; Database; Human–computer interaction; Operating system","score_opus":0.014885829664977758,"score_gpt":0.24282909842498754,"score_spread":0.22794326876000978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2809683060","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":[0.9565686,0.0017117566,0.034013223,0.00023904386,0.0029190998,0.0014662282,0.00040287236,0.00019145805,0.002487735],"genre_scores_gemma":[0.99772805,0.00001914695,0.0019949204,0.000016594833,0.000060039303,0.0001058357,0.000013055375,0.000010951805,0.000051415107],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99767405,0.000027621209,0.0006973741,0.00061063736,0.0006958036,0.00029450498],"domain_scores_gemma":[0.99774426,0.000039373488,0.0011014165,0.0006117761,0.0004182372,0.000084918094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006656767,0.00031629286,0.0007323844,0.0004651828,0.00010859247,0.00013845837,0.00307182,0.00014743416,0.000010440048],"category_scores_gemma":[0.00003487631,0.00022270196,0.0007460807,0.0015334983,0.00025331418,0.00015331325,0.0029665425,0.00024017291,0.0000017280812],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001464017,0.0025333976,0.013433425,0.001937929,0.017008852,0.0000033723368,0.011383017,0.007049278,0.15051423,0.79046935,0.004559375,0.00096140837],"study_design_scores_gemma":[0.00066342345,0.00029703983,0.004588625,0.00073431944,0.0017676094,0.000008480704,0.0010800234,0.05232437,0.9011002,0.036410734,0.00027485474,0.0007502815],"about_ca_topic_score_codex":0.000089875226,"about_ca_topic_score_gemma":3.820164e-7,"teacher_disagreement_score":0.7540586,"about_ca_system_score_codex":0.00008163501,"about_ca_system_score_gemma":0.00004052169,"threshold_uncertainty_score":0.9081522},"labels":[],"label_agreement":null},{"id":"W2810219908","doi":"10.14778/3358701.3358704","title":"Online density bursting subgraph detection from temporal graphs","year":2019,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Caching and Content Delivery","field":"Computer Science","cited_by":38,"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; Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Scalability; Duration (music); Bounded function; Indecomposable module; Set (abstract data type); Burstiness; Combinatorics; Mathematics; Network packet; Computer network","score_opus":0.010226559624712495,"score_gpt":0.19241496182112253,"score_spread":0.18218840219641003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810219908","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":[0.997369,0.00008845425,0.00080362847,0.000374414,0.00063973444,0.00023008337,0.0000041639396,0.00011429957,0.0003762163],"genre_scores_gemma":[0.9982903,0.000010546849,0.0013664194,0.000149574,0.000047676815,0.000005499247,0.0000011185956,0.000007011452,0.00012186106],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99888223,0.000008418522,0.00022439178,0.0003282619,0.00036069695,0.00019599553],"domain_scores_gemma":[0.9993261,0.0000359556,0.00022783989,0.00021330986,0.00014953974,0.000047261598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022337901,0.0001303002,0.00016743357,0.00008845774,0.00011013787,0.00008209521,0.00077158853,0.00004316368,0.0000036096117],"category_scores_gemma":[0.00003662103,0.00009522572,0.00016156067,0.00032945708,0.000028739487,0.00030140564,0.00038971397,0.00017325356,0.000009598071],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040641466,0.00022464083,0.2457244,0.000045662335,0.000084678075,8.1638865e-7,0.0006699429,0.00003243377,0.7312617,0.006319476,0.00020042143,0.015395215],"study_design_scores_gemma":[0.0019960627,0.00040593895,0.18064456,0.0004446336,0.0000953033,0.0000366073,0.0007341505,0.043396164,0.735818,0.035118077,0.00060571684,0.0007047262],"about_ca_topic_score_codex":0.0013065414,"about_ca_topic_score_gemma":0.000040169663,"teacher_disagreement_score":0.06507984,"about_ca_system_score_codex":0.000045631634,"about_ca_system_score_gemma":0.000013646482,"threshold_uncertainty_score":0.3883192},"labels":[],"label_agreement":null},{"id":"W2888965704","doi":"10.14778/3236187.3236194","title":"AIDA","year":2018,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Relational database management system; Software portability; Python (programming language); Relational database; Relational algebra; Programming language; Database; Interpreter","score_opus":0.00852893521103026,"score_gpt":0.21841857042476365,"score_spread":0.20988963521373338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2888965704","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":[0.40965956,0.0007420248,0.32926363,0.010149733,0.0053633307,0.0021051436,0.000039847462,0.00077390426,0.24190281],"genre_scores_gemma":[0.94054335,0.000008846162,0.05809994,0.00023023537,0.00017563558,0.000023158884,1.6368548e-7,0.000006101219,0.00091254036],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99924445,0.0000024568137,0.00016331895,0.00018942129,0.00023517605,0.00016516853],"domain_scores_gemma":[0.9994459,0.000010206528,0.00013932545,0.00020165695,0.00016635183,0.00003656006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016053741,0.00008116871,0.00009990864,0.000029825032,0.00011615262,0.000025161513,0.0006357742,0.000016839238,0.000010112851],"category_scores_gemma":[0.000042140433,0.00004948987,0.0000471814,0.00022830749,0.00010137826,0.00041837993,0.0005610943,0.00004676553,0.000026714315],"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":[0.00000497326,0.00002819921,0.0009440452,0.000033872682,0.000012499582,1.5212036e-7,0.0007194151,5.972677e-7,0.044242404,0.9426572,0.0056752414,0.0056814365],"study_design_scores_gemma":[0.00028898544,0.00015224186,0.0013759928,0.00011269284,0.000006134966,0.000021284219,0.0001681592,0.00047938345,0.7318061,0.009399347,0.2560306,0.0001591166],"about_ca_topic_score_codex":0.000027246697,"about_ca_topic_score_gemma":0.0000024600802,"teacher_disagreement_score":0.9332578,"about_ca_system_score_codex":0.000023794077,"about_ca_system_score_gemma":0.000015357962,"threshold_uncertainty_score":0.20181383},"labels":[],"label_agreement":null},{"id":"W2889269664","doi":"10.14778/3229863.3236259","title":"MustaCHE","year":2018,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Visualization and Analytics","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":"University of Alberta","funders":"","keywords":"Cluster analysis; Computer science; Set (abstract data type); Context (archaeology); Visualization; Hierarchical clustering; Range (aeronautics); Artificial intelligence; Data mining","score_opus":0.020014877002886716,"score_gpt":0.27329417948981405,"score_spread":0.2532793024869273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889269664","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":[0.209643,0.0002608574,0.21481214,0.030370777,0.0039568907,0.001777663,0.000032245163,0.0010144968,0.5381319],"genre_scores_gemma":[0.99090636,0.000009119599,0.0068256743,0.00073893875,0.00008870707,0.000004112209,3.242609e-7,0.00000435234,0.0014224375],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993461,0.00000238026,0.00013805379,0.00014684454,0.00024190213,0.00012474916],"domain_scores_gemma":[0.9995082,0.000007000518,0.00010985813,0.00014904591,0.00018959504,0.000036313413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017415047,0.000061237915,0.000068710775,0.00004006576,0.00008067404,0.00007836564,0.0010195385,0.000017110406,0.000022442822],"category_scores_gemma":[0.000056441222,0.00003919653,0.000041009047,0.00035457299,0.0000711658,0.0002394026,0.00048067275,0.00003691528,0.00003285873],"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":[0.0000028222037,0.000099067074,0.002191163,0.000030905474,0.000023649052,1.128633e-7,0.0011662593,0.0000010490119,0.016648356,0.9297303,0.043906875,0.0061994493],"study_design_scores_gemma":[0.0006322693,0.00021759403,0.0027056772,0.00009315515,0.000028219929,0.000012602052,0.00031601716,0.028770538,0.7474197,0.023917371,0.19560702,0.0002798147],"about_ca_topic_score_codex":0.000006304939,"about_ca_topic_score_gemma":6.648143e-7,"teacher_disagreement_score":0.9058129,"about_ca_system_score_codex":0.000019557927,"about_ca_system_score_gemma":0.000016395483,"threshold_uncertainty_score":0.18945731},"labels":[],"label_agreement":null},{"id":"W2889272789","doi":"10.14778/3229863.3236248","title":"Tooling framework for instantiating natural language querying system","year":2018,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Semantic Web and Ontologies","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":"Université de Montréal","funders":"","keywords":"Computer science; Schema (genetic algorithms); Natural language; Natural language user interface; Query language; Programming language; Database schema; Information retrieval; Database; Software engineering; Database design; Natural language processing","score_opus":0.014094250275580228,"score_gpt":0.26261730427254903,"score_spread":0.2485230539969688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889272789","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":[0.8949727,0.00088155834,0.09366,0.0011547903,0.0025186255,0.0008480165,0.0000031475113,0.00042943124,0.0055317343],"genre_scores_gemma":[0.8545078,0.000002130637,0.14507481,0.00012969717,0.00021941644,0.000025795614,1.1196106e-7,0.0000069100597,0.00003330205],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99897915,0.000004571879,0.00024612262,0.0002464323,0.00024244125,0.0002812585],"domain_scores_gemma":[0.9992392,0.000121366975,0.00025142235,0.00017192539,0.00018952729,0.000026545156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036929225,0.00011688953,0.00017361228,0.000052391923,0.00023273056,0.00013032698,0.0010134057,0.000048887196,7.938517e-7],"category_scores_gemma":[0.00038988536,0.00007637766,0.000098113465,0.00023894351,0.000057897414,0.00026777803,0.00040405904,0.000110328154,0.0000027650824],"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":[0.000017832172,0.000021957687,0.0021925943,0.00035144348,0.00004345412,5.0593707e-7,0.00637959,0.000001465433,0.03419819,0.9429475,0.0002498435,0.013595637],"study_design_scores_gemma":[0.0006538945,0.00019268302,0.0019187359,0.0015569773,0.00004473972,0.000043725286,0.01098217,0.03887284,0.9257198,0.019084718,0.00055275834,0.0003769488],"about_ca_topic_score_codex":0.00004096782,"about_ca_topic_score_gemma":0.0000038502,"teacher_disagreement_score":0.92386276,"about_ca_system_score_codex":0.00006698011,"about_ca_system_score_gemma":0.00002122404,"threshold_uncertainty_score":0.31145906},"labels":[],"label_agreement":null},{"id":"W2889537237","doi":"10.14778/3229863.3236267","title":"ConTPL","year":2018,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Institute of General Medical Sciences","keywords":"Differential privacy; Computer science; Bounding overwatch; Data stream mining; The Internet; Information privacy; Visualization; Data mining; Computer security; Artificial intelligence; World Wide Web","score_opus":0.0235639165118382,"score_gpt":0.25419733674221073,"score_spread":0.23063342023037253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889537237","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":[0.50498587,0.00056491425,0.030836765,0.27160323,0.0041977507,0.0021491603,0.000030063651,0.0033893967,0.18224289],"genre_scores_gemma":[0.88793236,0.000016981705,0.1114932,0.00030418334,0.00006662788,0.000023542301,1.3954693e-7,0.0000071187487,0.00015583144],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988566,0.0000036224249,0.00020377032,0.0003127404,0.00035705947,0.00026622802],"domain_scores_gemma":[0.99746007,0.000030183592,0.00018723054,0.002078993,0.00020901262,0.000034519027],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0003398894,0.00011183287,0.00012868507,0.0000665616,0.00011684232,0.00008182285,0.028671412,0.000052448453,0.000013540141],"category_scores_gemma":[0.004765936,0.0000744327,0.000056325815,0.00043141664,0.00025097202,0.00041443243,0.069867596,0.00012234681,0.000038973078],"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":[0.000011218126,0.00010605214,0.004273599,0.000048529168,0.000051485014,5.0050284e-7,0.0003067931,1.2507779e-7,0.08399903,0.17053759,0.71955115,0.021113962],"study_design_scores_gemma":[0.00023445698,0.00010883991,0.0012463157,0.00005642942,0.0000062660624,0.000010674302,0.00003928942,0.0028015806,0.64621454,0.33488,0.014284846,0.0001167839],"about_ca_topic_score_codex":0.000022035245,"about_ca_topic_score_gemma":0.0000012830451,"teacher_disagreement_score":0.7052663,"about_ca_system_score_codex":0.000058601832,"about_ca_system_score_gemma":0.000021207872,"threshold_uncertainty_score":0.97658396},"labels":[],"label_agreement":null},{"id":"W2909564896","doi":"10.14778/3352063.3352120","title":"Guided automated learning for query workload re-optimization","year":2019,"lang":"en","type":"preprint","venue":"Proceedings of the VLDB Endowment","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":"York University; IBM (Canada); Ontario Tech University","funders":"","keywords":"Computer science; Query optimization; Sargable; Web query classification; Query expansion; Web search query; Query language; SQL; Query plan; Query by Example; Knowledge base; View; SPARQL; Online aggregation; Spatial query; Database; Information retrieval; RDF query language; Data mining; RDF; World Wide Web; Semantic Web; Search engine; Database design","score_opus":0.025071032492887956,"score_gpt":0.2745905191098624,"score_spread":0.24951948661697443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2909564896","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":[0.0039266595,0.0006850238,0.98346007,0.0013723712,0.0024762852,0.003163055,0.000036229034,0.0010600307,0.0038202798],"genre_scores_gemma":[0.27169842,0.00034465853,0.7234798,0.00022269902,0.0003265735,0.00087052153,0.000046628036,0.00008110121,0.0029295986],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979,0.000017431435,0.0006280646,0.00066862546,0.00044464003,0.00034123557],"domain_scores_gemma":[0.99771035,0.00007546852,0.0011486477,0.0004675306,0.0005422369,0.000055787525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005967803,0.000318986,0.00046787402,0.00012701012,0.00017927852,0.00013552392,0.0012036517,0.0001720579,0.000005153577],"category_scores_gemma":[0.0003151286,0.00023707378,0.00023184673,0.00025191918,0.00004890588,0.0004291637,0.002485057,0.0003439212,0.000004930471],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004822862,0.00010151036,0.0010279425,0.0024443124,0.00019593224,4.324511e-7,0.0017446401,0.918273,0.0045501986,0.050351772,0.01812813,0.0031339363],"study_design_scores_gemma":[0.0006730152,0.0000973591,0.00012019116,0.0023468402,0.000053779826,0.000008039998,0.00023781766,0.9520628,0.023828607,0.0018497453,0.018206935,0.0005149057],"about_ca_topic_score_codex":0.000060346832,"about_ca_topic_score_gemma":0.0000014001266,"teacher_disagreement_score":0.26777178,"about_ca_system_score_codex":0.00016779933,"about_ca_system_score_gemma":0.00011926781,"threshold_uncertainty_score":0.9667588},"labels":[],"label_agreement":null},{"id":"W2912891501","doi":"10.14778/3291264.3291270","title":"PS-tree-based efficient boolean expression matching for high-dimensional and dense workloads","year":2018,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Network Packet Processing and Optimization","field":"Computer Science","cited_by":20,"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; Disjoint sets; Matching (statistics); Predicate (mathematical logic); Memory footprint; Tree (set theory); Theoretical computer science; Algorithm; Parallel computing; Mathematics","score_opus":0.008289532133585992,"score_gpt":0.21845650172001987,"score_spread":0.21016696958643388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912891501","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":[0.6591832,0.00024844642,0.33610868,0.0024012967,0.0006627058,0.0006770421,0.0000033511749,0.00015956457,0.0005556694],"genre_scores_gemma":[0.87046283,0.0000029457708,0.1289369,0.00031676964,0.00012266547,0.000033601853,9.779619e-7,0.000011544241,0.00011177719],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988123,0.000008069666,0.00023210225,0.000359062,0.0003344691,0.00025394934],"domain_scores_gemma":[0.9992129,0.00005328469,0.00024192098,0.00015052575,0.00027141132,0.000069908994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004094632,0.0001487528,0.0001475235,0.000072326795,0.00036144294,0.00014314901,0.0004694834,0.00004968543,0.0000025196093],"category_scores_gemma":[0.00004410829,0.00010166779,0.00005001475,0.00023987374,0.00010627544,0.00016581282,0.0003080567,0.000075843105,0.0000014041906],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012446111,0.0015241303,0.0050800955,0.0012492469,0.0001269869,0.0000020193586,0.007968274,0.064768896,0.6060919,0.0846747,0.040217888,0.18705124],"study_design_scores_gemma":[0.0015110222,0.00028103605,0.00083327206,0.0008653288,0.000033612374,0.0000069535554,0.000051032697,0.37054193,0.6110886,0.014170776,0.00032894005,0.0002875057],"about_ca_topic_score_codex":0.0000056324634,"about_ca_topic_score_gemma":8.8533926e-7,"teacher_disagreement_score":0.30577302,"about_ca_system_score_codex":0.000039963168,"about_ca_system_score_gemma":0.000037024365,"threshold_uncertainty_score":0.41458923},"labels":[],"label_agreement":null},{"id":"W2915016908","doi":"10.14778/3291264.3291274","title":"Shrinkwrap","year":2018,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Cryptography and Data Security","field":"Computer Science","cited_by":91,"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; Differential privacy; SQL; Padding; Set (abstract data type); Cardinality (data modeling); Query optimization; Operator (biology); Sargable; Database; Web search query; Information retrieval; Data mining; Computer security; Search engine","score_opus":0.00835529035135328,"score_gpt":0.21258179589086773,"score_spread":0.20422650553951446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2915016908","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":[0.75451183,0.00073153834,0.022488616,0.008864042,0.0030235134,0.001333294,0.000027491657,0.00062808004,0.2083916],"genre_scores_gemma":[0.984395,0.000013897258,0.015170202,0.00027192803,0.00010613642,0.00001110032,1.7274368e-7,0.0000035403837,0.00002800481],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991575,0.0000028300801,0.00015213763,0.00022249842,0.00027719545,0.00018786646],"domain_scores_gemma":[0.9994425,0.0000126185405,0.000110515066,0.00023666375,0.00014938884,0.00004831002],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016531638,0.000086816646,0.00009195426,0.000056648714,0.00012661956,0.00007293649,0.0014435889,0.000026516975,0.000019853873],"category_scores_gemma":[0.000030182578,0.000056833363,0.000087750566,0.00045230673,0.00013709461,0.00034876485,0.00071863085,0.00007202637,0.00002033605],"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":[0.000007355646,0.00008117831,0.0026106327,0.000021449327,0.00001791259,1.0477616e-7,0.0012552453,8.587849e-8,0.016582156,0.965081,0.009414755,0.0049281707],"study_design_scores_gemma":[0.0005931985,0.00030126813,0.011721106,0.00008362894,0.000019148718,0.000020651598,0.0002080869,0.000725446,0.7085136,0.20112479,0.07641447,0.0002745895],"about_ca_topic_score_codex":0.000021237694,"about_ca_topic_score_gemma":0.0000022737497,"teacher_disagreement_score":0.7639562,"about_ca_system_score_codex":0.000013388009,"about_ca_system_score_gemma":0.00001303417,"threshold_uncertainty_score":0.26825714},"labels":[],"label_agreement":null},{"id":"W2915915402","doi":"10.14778/3297753.3297758","title":"Cleaning crowdsourced labels using oracles for statistical classification","year":2018,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":36,"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; Oracle; Crowdsourcing; Margin (machine learning); Ground truth; Artificial intelligence; Test data; Data mining; Machine learning; Estimator; Mathematics; Statistics","score_opus":0.04114410296757267,"score_gpt":0.28516068795633887,"score_spread":0.2440165849887662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2915915402","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":[0.65262103,0.000032711443,0.34343427,0.0007782058,0.0004587849,0.0006373984,0.000007686798,0.0001542774,0.001875631],"genre_scores_gemma":[0.87514096,0.0000015028904,0.12444888,0.00012623025,0.00016346513,0.000019347413,5.074137e-7,0.000015719432,0.000083378334],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986499,0.000011144968,0.0003319565,0.00036726633,0.0003137995,0.00032593144],"domain_scores_gemma":[0.9988934,0.000104104736,0.00029785186,0.00022761078,0.0004086574,0.00006838983],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055510545,0.00014614631,0.0001811678,0.00007237247,0.00040207614,0.00019294665,0.0006990641,0.000054865817,0.0000049512623],"category_scores_gemma":[0.00024116597,0.00011049845,0.000076841105,0.00029565234,0.00019632909,0.00023924702,0.00026983218,0.00009176676,0.0000038427115],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003740715,0.00009045936,0.0011076056,0.00011498662,0.00003950071,1.8231607e-7,0.0019615248,0.000038717484,0.7455593,0.22190188,0.0017678904,0.027380602],"study_design_scores_gemma":[0.0009097046,0.00027615487,0.0030316547,0.00029230752,0.000066216286,0.000031229953,0.0007326252,0.23885702,0.73517406,0.01568951,0.004593271,0.0003462305],"about_ca_topic_score_codex":0.00002536165,"about_ca_topic_score_gemma":0.0000015133587,"teacher_disagreement_score":0.2388183,"about_ca_system_score_codex":0.0000893534,"about_ca_system_score_gemma":0.000043772714,"threshold_uncertainty_score":0.4505996},"labels":[],"label_agreement":null},{"id":"W2917106292","doi":"10.14778/3303753.3303756","title":"Correlation constraint shortest path over large multi-relation graphs","year":2019,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":14,"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":"Relation (database); Theoretical computer science; Computer science; Reachability; Vertex (graph theory); Tree traversal; Enhanced Data Rates for GSM Evolution; Shortest path problem; Longest path problem; Mathematics; Discrete mathematics; Graph; Algorithm; Data mining; Artificial intelligence","score_opus":0.010235153334248006,"score_gpt":0.2181015650240609,"score_spread":0.20786641168981287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2917106292","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":[0.7148809,0.0002322647,0.22136419,0.0019833685,0.0041352655,0.00424825,0.00007326063,0.00054032693,0.052542202],"genre_scores_gemma":[0.9913014,0.000015017662,0.007853547,0.00013347255,0.000019150842,0.000016629368,0.0000063680604,0.0000070834717,0.0006473093],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998851,0.000005533761,0.00024357444,0.00029605674,0.00038432344,0.00021951854],"domain_scores_gemma":[0.99940866,0.000020880108,0.00023334788,0.00020974693,0.000089063826,0.00003828408],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037835518,0.0001259545,0.00012502396,0.00008863161,0.00008184447,0.00011864792,0.0007432235,0.00003869066,0.000034728106],"category_scores_gemma":[0.000025965068,0.00009112277,0.0000853626,0.0003279725,0.000031891315,0.0008753407,0.0005072589,0.000110571404,0.000045778208],"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":[0.000006531156,0.00026803697,0.17189485,0.00004293268,0.000056242432,4.235593e-7,0.0005922656,0.00008882503,0.005448272,0.8096076,0.0021127919,0.009881196],"study_design_scores_gemma":[0.0030047554,0.00019954379,0.31461275,0.0002777655,0.00006413156,0.000007211438,0.00044090493,0.6583411,0.006341008,0.00939721,0.0067964876,0.00051712187],"about_ca_topic_score_codex":0.000018368497,"about_ca_topic_score_gemma":0.0000014551802,"teacher_disagreement_score":0.8002104,"about_ca_system_score_codex":0.000057331443,"about_ca_system_score_gemma":0.000012298431,"threshold_uncertainty_score":0.37158787},"labels":[],"label_agreement":null},{"id":"W2925810066","doi":"10.14778/3342263.3342643","title":"Optimizing subgraph queries by combining binary and worst-case optimal joins","year":2019,"lang":"en","type":"preprint","venue":"Proceedings of the VLDB Endowment","topic":"Graph Theory 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 Waterloo","funders":"","keywords":"Joins; Computer science; Intersection (aeronautics); Binary number; Partition (number theory); Query plan; Vertex (graph theory); Query optimization; Matching (statistics); Theoretical computer science; Graph; Mathematics; Data mining; Sargable; Combinatorics; Search engine; Information retrieval","score_opus":0.011492111412630185,"score_gpt":0.21651894232646995,"score_spread":0.20502683091383977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2925810066","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":[0.9834711,0.0024016553,0.006830541,0.0016375632,0.001575357,0.0013188454,0.000051765543,0.00025221618,0.0024609605],"genre_scores_gemma":[0.96212727,0.00028545846,0.03700558,0.00015636603,0.00004461871,0.000095072646,0.0000033816823,0.000031872933,0.00025035528],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99767417,0.000031166834,0.0005163832,0.00085356936,0.0004496153,0.00047511488],"domain_scores_gemma":[0.9984549,0.000093012204,0.0006557339,0.00047966352,0.00018041012,0.00013623605],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007779043,0.00047391368,0.0005642964,0.00023248629,0.00032325578,0.0004354776,0.0017136894,0.00020201359,0.000006743285],"category_scores_gemma":[0.000045624267,0.00036551637,0.000270276,0.00035520433,0.00028160785,0.00047737136,0.0051540188,0.00073219475,0.0000026613923],"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":[0.00038933603,0.0019980457,0.011430016,0.0064245,0.0021495826,0.00026550944,0.06972934,0.010456414,0.056378324,0.8012309,0.021862507,0.017685492],"study_design_scores_gemma":[0.008116392,0.0027119482,0.0015898729,0.009220527,0.0009893159,0.004677493,0.01501081,0.33752123,0.36821243,0.2376984,0.007119782,0.007131791],"about_ca_topic_score_codex":0.000055634035,"about_ca_topic_score_gemma":5.2952413e-7,"teacher_disagreement_score":0.56353253,"about_ca_system_score_codex":0.00005459553,"about_ca_system_score_gemma":0.000057932753,"threshold_uncertainty_score":0.99987966},"labels":[],"label_agreement":null},{"id":"W2963174348","doi":"10.14778/2994509.2994534","title":"LSH ensemble","year":2016,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":136,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Jaccard index; Computer science; Data mining; Domain (mathematical analysis); Locality-sensitive hashing; Data structure; Data set; Set (abstract data type); Hash function; Mathematics; Cluster analysis; Hash table; Artificial intelligence","score_opus":0.011317738621502458,"score_gpt":0.23601808838573757,"score_spread":0.2247003497642351,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963174348","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":[0.04250883,0.00044962417,0.88309455,0.01294032,0.0005182425,0.00095625786,0.0000042918964,0.00074522535,0.05878263],"genre_scores_gemma":[0.9593542,0.00012551785,0.038513463,0.0002420546,0.000038890572,0.00002536894,2.2089313e-8,0.000007568619,0.0016928882],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991205,0.0000030870124,0.0001775863,0.00022092754,0.0002731289,0.00020479602],"domain_scores_gemma":[0.99941796,0.00003544148,0.00014816405,0.00020227823,0.00015292712,0.000043226366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018533497,0.000098585486,0.00011518255,0.000044655608,0.00006265881,0.000034126006,0.0010770373,0.000027414659,0.000007321221],"category_scores_gemma":[0.00011395042,0.00004764201,0.00008073931,0.00024732196,0.0000565943,0.0005505309,0.0005385869,0.00004971574,0.000014441157],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000071254076,0.000040814786,0.00086848286,0.000018160299,0.000010257009,3.2892754e-7,0.00011350731,6.117543e-8,0.678563,0.15629025,0.004964155,0.15912385],"study_design_scores_gemma":[0.00016544692,0.000064680746,0.00043278869,0.00007612592,0.0000032325504,0.0000071408995,0.000007675085,0.000011651627,0.9174836,0.065804206,0.015867881,0.00007553816],"about_ca_topic_score_codex":0.0000037066704,"about_ca_topic_score_gemma":1.579966e-7,"teacher_disagreement_score":0.9168454,"about_ca_system_score_codex":0.00005022846,"about_ca_system_score_gemma":0.000015605869,"threshold_uncertainty_score":0.20014212},"labels":[],"label_agreement":null},{"id":"W2965684979","doi":"10.14778/3339490.3339492","title":"Finding theme communities from database networks","year":2019,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Mining Algorithms and Applications","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":"Theme (computing); Computer science; Scalability; Database; Tree (set theory); World Wide Web; Mathematics","score_opus":0.0209118966385737,"score_gpt":0.2322965180983817,"score_spread":0.211384621459808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2965684979","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":[0.9317533,0.00043213626,0.043221254,0.003025964,0.0009804774,0.0010629157,0.00017728159,0.00026773335,0.019078981],"genre_scores_gemma":[0.96115625,0.000047329995,0.038152076,0.00022480263,0.000057560334,0.0000413943,0.000014467912,0.000008224468,0.0002978861],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992383,0.0000051032057,0.00017833931,0.0001783644,0.00022066121,0.0001792019],"domain_scores_gemma":[0.99919885,0.00008066827,0.00016400042,0.0004572907,0.0000630789,0.00003613176],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021762903,0.0001016773,0.00012477707,0.00003345599,0.00013664759,0.00013606207,0.001977144,0.00002496541,0.000029411116],"category_scores_gemma":[0.000010111687,0.0000708892,0.000050430954,0.00022484463,0.00004162768,0.00041139856,0.0012999184,0.0001455137,0.00002572513],"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":[0.000023089664,0.00061613723,0.050980475,0.00014233857,0.00027789516,5.8004144e-7,0.012137772,0.000525456,0.052680418,0.76145136,0.035212945,0.08595155],"study_design_scores_gemma":[0.0017119561,0.00018369478,0.014930639,0.0009238634,0.0000799188,0.000016129228,0.005691132,0.82039756,0.09220814,0.018329399,0.04464206,0.00088550925],"about_ca_topic_score_codex":0.0003550345,"about_ca_topic_score_gemma":0.0000038505887,"teacher_disagreement_score":0.8198721,"about_ca_system_score_codex":0.00002584581,"about_ca_system_score_gemma":0.000012884684,"threshold_uncertainty_score":0.36740583},"labels":[],"label_agreement":null},{"id":"W2966581343","doi":"10.14778/3339490.3339501","title":"Ontology-based entity matching in attributed graphs","year":2019,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Subgraph isomorphism problem; Computer science; Matching (statistics); Theoretical computer science; Graph; Node (physics); Ontology; Ontology alignment; Factor-critical graph; Induced subgraph isomorphism problem; Semantic Web; Line graph; Mathematics; Artificial intelligence; Voltage graph; Process ontology","score_opus":0.07418500935219877,"score_gpt":0.34623299728772483,"score_spread":0.2720479879355261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2966581343","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":[0.98475546,0.000033870314,0.00015314102,0.0034702083,0.00046629945,0.00067367504,0.000025715577,0.00002720511,0.010394404],"genre_scores_gemma":[0.9976239,0.0000056124086,0.0008196006,0.00068469,0.000007864894,0.000024880035,0.0000025636862,0.0000056471868,0.0008252035],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974928,0.00004000347,0.0006309997,0.0004183921,0.0011375081,0.00028028898],"domain_scores_gemma":[0.99881697,0.00021766378,0.00040446437,0.00034165813,0.00017174552,0.00004748088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004184755,0.00013012227,0.00031638573,0.00028027146,0.000066725406,0.00012778424,0.0015108541,0.000051136096,0.000250012],"category_scores_gemma":[0.0005835287,0.00008234577,0.00015047236,0.00085262844,0.000077742014,0.00036156047,0.0005871282,0.00015359814,0.0001539824],"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":[0.00023374766,0.00085560465,0.51670027,0.00024159494,0.00008698645,0.0000016849737,0.0017937744,0.00047849593,0.027812595,0.41533756,0.026402518,0.010055174],"study_design_scores_gemma":[0.0035719716,0.00021557864,0.30878088,0.00027340982,0.000053733373,0.0000033144022,0.00486704,0.0010644203,0.04916881,0.56806576,0.06345311,0.0004819681],"about_ca_topic_score_codex":0.00039071255,"about_ca_topic_score_gemma":0.00016100743,"teacher_disagreement_score":0.2079194,"about_ca_system_score_codex":0.00007171022,"about_ca_system_score_gemma":0.000026213926,"threshold_uncertainty_score":0.3357963},"labels":[],"label_agreement":null},{"id":"W2970397632","doi":"10.14778/3352063.3352102","title":"Making an RDBMS data scientist friendly","year":2019,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Database Systems and Queries","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":"McGill University","funders":"","keywords":"Computer science; Python (programming language); Relational database management system; Database; Implementation; Relational database; Programming language","score_opus":0.04182728214053458,"score_gpt":0.2994120196958087,"score_spread":0.2575847375552741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970397632","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":[0.75171787,0.00082411786,0.17091905,0.002535334,0.0075852396,0.003299675,0.0003865153,0.00067142805,0.062060796],"genre_scores_gemma":[0.910773,0.0000059719764,0.08838612,0.00011957611,0.000073226234,0.000012921228,0.0000059001713,0.000010790441,0.00061253045],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99841154,0.000006624878,0.00025845875,0.0005579578,0.0004909601,0.0002744508],"domain_scores_gemma":[0.99854815,0.000016273158,0.00026375422,0.0009934909,0.0001234971,0.000054822343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005192709,0.00013185714,0.00017040569,0.000060796177,0.0001518843,0.000120929035,0.0027352106,0.000024617913,0.000016327489],"category_scores_gemma":[0.000049727852,0.00008821317,0.00003951248,0.00036661097,0.000073441,0.0022772537,0.0027206033,0.00009434558,0.000031823667],"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":[0.000010470026,0.000101490485,0.00465114,0.00015512822,0.000023078495,7.8271864e-7,0.0007564136,0.00002192056,0.06998489,0.91178334,0.0032021934,0.009309152],"study_design_scores_gemma":[0.0017364477,0.00058327307,0.0100350985,0.0010406689,0.00004572979,0.00015745484,0.0020991191,0.036561385,0.15963826,0.009006774,0.7779661,0.001129727],"about_ca_topic_score_codex":0.00004447783,"about_ca_topic_score_gemma":0.0000063613375,"teacher_disagreement_score":0.90277654,"about_ca_system_score_codex":0.000037531918,"about_ca_system_score_gemma":0.000036994625,"threshold_uncertainty_score":0.50827473},"labels":[],"label_agreement":null},{"id":"W2970408474","doi":"10.14778/3342263.3342274","title":"PrivateSQL","year":2019,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":108,"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; Differential privacy; SQL; Relational database; Schema (genetic algorithms); Conjunctive query; Information retrieval; Workload; View; Relation (database); Database; Data mining; Database design","score_opus":0.014256454438070635,"score_gpt":0.2277791953859026,"score_spread":0.21352274094783197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970408474","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":[0.8757601,0.00023308536,0.0021193912,0.0722217,0.0013360684,0.0013208734,0.000008229378,0.001089553,0.045911007],"genre_scores_gemma":[0.9072232,0.000025249008,0.09218266,0.00019678473,0.00001738778,0.000024599598,2.745681e-7,0.000009083087,0.00032073053],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99871206,0.0000035170917,0.0002201496,0.00036041133,0.00042393393,0.00027995475],"domain_scores_gemma":[0.9970193,0.000037693513,0.00020918065,0.0025999537,0.00010259733,0.000031254585],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00032276646,0.00012642957,0.00015475889,0.00007572629,0.000052886615,0.00008255759,0.03186454,0.000058225178,0.00002008319],"category_scores_gemma":[0.0025393898,0.00008459246,0.000072317205,0.00046934426,0.00006399529,0.0005183493,0.082974136,0.0001712531,0.000081411315],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001494774,0.00021456553,0.056894142,0.0002606339,0.000092958886,7.541e-7,0.00031179233,0.0000056197086,0.2883253,0.31009686,0.32623586,0.01754658],"study_design_scores_gemma":[0.00036202048,0.00008518571,0.0039182235,0.00010601036,0.000006606029,0.000011749446,0.000044477285,0.00546892,0.6329242,0.3464052,0.010483029,0.00018440653],"about_ca_topic_score_codex":0.000012515972,"about_ca_topic_score_gemma":1.8999822e-7,"teacher_disagreement_score":0.34459886,"about_ca_system_score_codex":0.000071639624,"about_ca_system_score_gemma":0.000021218235,"threshold_uncertainty_score":0.97337353},"labels":[],"label_agreement":null},{"id":"W2970546348","doi":"10.14778/3342263.33422629","title":"DimmStore","year":2019,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Testbed; Server; Exploit; Locality; Power (physics); Memory management; Embedded system; Power consumption; Operating system; Computer network; Semiconductor memory","score_opus":0.005575699143324562,"score_gpt":0.18550559531025376,"score_spread":0.1799298961669292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970546348","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":[0.9380495,0.00008152104,0.0002299447,0.002469163,0.0005989055,0.00034285488,2.3492278e-7,0.00010543001,0.05812244],"genre_scores_gemma":[0.99376434,0.000002050881,0.0020366744,0.0002352501,0.000042453812,0.000007571573,3.513742e-8,0.000005675925,0.0039059308],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990334,0.0000036015042,0.0001647602,0.00024354455,0.0003587094,0.0001960154],"domain_scores_gemma":[0.99949527,0.000016888433,0.00014393694,0.00024546217,0.000064042346,0.000034395212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023133743,0.00009707034,0.0001189258,0.000048370795,0.00006508474,0.00005874638,0.0014097191,0.000021967375,0.00000771905],"category_scores_gemma":[0.000013740094,0.00006027769,0.000100369405,0.0002731321,0.00002396775,0.000027406304,0.0011165312,0.000085819134,0.000052261497],"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":[0.000019977006,0.00040638557,0.050132304,0.0004372382,0.00017852463,0.0000011178604,0.004712468,0.0018425136,0.041833322,0.8185715,0.022990594,0.058874052],"study_design_scores_gemma":[0.004542072,0.0010284935,0.09470952,0.0011853449,0.00011022069,0.00007492841,0.0017261399,0.1671365,0.34074795,0.047590204,0.33942172,0.0017268952],"about_ca_topic_score_codex":0.000014636812,"about_ca_topic_score_gemma":1.5078298e-7,"teacher_disagreement_score":0.7709813,"about_ca_system_score_codex":0.000043316824,"about_ca_system_score_gemma":0.00000906704,"threshold_uncertainty_score":0.26196325},"labels":[],"label_agreement":null},{"id":"W2970613315","doi":"10.14778/3352063.3352096","title":"ApproxML","year":2019,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Bayesian Modeling and Causal Inference","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 Toronto","funders":"","keywords":"Computer science; Pipeline (software); Reuse; Machine learning; Artificial intelligence; Variety (cybernetics); Mixture model; Process (computing); Gaussian process; Gaussian","score_opus":0.007709354976284009,"score_gpt":0.19244915397182222,"score_spread":0.18473979899553822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970613315","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":[0.83522993,0.0002181093,0.037599396,0.00459052,0.0011184493,0.00084976136,0.0000018500374,0.0002749829,0.120117],"genre_scores_gemma":[0.9885133,0.000008291541,0.010111623,0.00022560495,0.000021874175,0.0000133489475,6.419139e-8,0.0000047894036,0.0011011148],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99914545,0.0000029174018,0.00015917637,0.00022788413,0.00028380734,0.00018077275],"domain_scores_gemma":[0.9995293,0.000012220459,0.000113735296,0.00019745542,0.00010728529,0.00004002488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020603108,0.000089949885,0.00011354273,0.000034124547,0.00004150929,0.00006540808,0.0012017176,0.000031278316,0.000012397198],"category_scores_gemma":[0.000015981,0.00005795437,0.00006907061,0.00022281596,0.000024919995,0.00022492946,0.00041458503,0.00010132595,0.0000632006],"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":[0.000005399769,0.000076131335,0.004613321,0.000077006196,0.000019803461,9.9049444e-8,0.0006200061,0.00005017033,0.06813677,0.91556954,0.0014948908,0.009336878],"study_design_scores_gemma":[0.0011596075,0.00035513617,0.0055123656,0.000358846,0.000027398291,0.000038233633,0.000212153,0.08386054,0.7188461,0.17796129,0.011032087,0.00063623494],"about_ca_topic_score_codex":0.0000100508305,"about_ca_topic_score_gemma":1.1345994e-7,"teacher_disagreement_score":0.73760825,"about_ca_system_score_codex":0.000024152652,"about_ca_system_score_gemma":0.000023509368,"threshold_uncertainty_score":0.23633106},"labels":[],"label_agreement":null},{"id":"W2970675344","doi":"10.14778/3352063.3352117","title":"Combating fake news","year":2019,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Disinformation; Fake news; Crowdsourcing; Social media; Popularity; Internet privacy; Misinformation; Computer science; News media; Political science; Journalism; Public relations; Data science; World Wide Web; Sociology; Media studies; Computer security","score_opus":0.01544656451373473,"score_gpt":0.2722623878711316,"score_spread":0.2568158233573969,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970675344","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":[0.5593018,0.000010915431,0.0000013823203,0.00279239,0.0001903826,0.00027376693,8.3997327e-7,0.000023993987,0.4374045],"genre_scores_gemma":[0.9937443,0.00002614091,0.00023186463,0.0006376263,0.00005278235,0.0000018910034,2.049206e-7,0.0000038501507,0.0053013097],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99914926,0.000005762069,0.0001738802,0.000069149246,0.000417152,0.00018479684],"domain_scores_gemma":[0.99956405,0.000024422669,0.00019085471,0.00005419411,0.00010611031,0.000060364047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004560047,0.00005674142,0.00008932942,0.000032229524,0.00016407686,0.0000665053,0.00030338287,0.000031982494,0.00034980822],"category_scores_gemma":[0.00023311173,0.00003802374,0.000055474746,0.00019270016,0.000054076518,0.00029992568,0.00007333643,0.00006706523,0.000091410344],"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":[0.000026317264,0.00010516183,0.04878106,0.00014630791,0.000041417454,3.8382378e-8,0.17052162,0.000013982666,0.016510364,0.6975129,0.04193233,0.024408493],"study_design_scores_gemma":[0.0019587476,0.00019363537,0.024922622,0.0003730014,0.000041054987,0.00000272593,0.21756075,0.00031985177,0.07410217,0.012558174,0.6674601,0.0005071997],"about_ca_topic_score_codex":0.0003075203,"about_ca_topic_score_gemma":0.000022257333,"teacher_disagreement_score":0.68495476,"about_ca_system_score_codex":0.000058817972,"about_ca_system_score_gemma":0.000042811527,"threshold_uncertainty_score":0.38301548},"labels":[],"label_agreement":null},{"id":"W2970727798","doi":"10.14778/3342263.3342638","title":"Distributed implementations of dependency discovery algorithms","year":2019,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":27,"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; Implementation; Pruning; Dependency (UML); Focus (optics); Space (punctuation); Computation; Distributed computing; Big data; Theoretical computer science; Distributed algorithm; Algorithm; Parallel computing; Data mining; Artificial intelligence; Programming language","score_opus":0.07908823019991898,"score_gpt":0.3774095362212648,"score_spread":0.29832130602134577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970727798","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":[0.9667907,0.0000726735,0.0033724345,0.003610219,0.00085716223,0.0015522186,0.0012258309,0.00003067185,0.022488091],"genre_scores_gemma":[0.9968333,0.000018676517,0.0009405906,0.00010579873,0.000020206731,0.000026400936,0.00001295579,0.0000058572555,0.0020361624],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996812,0.000018787943,0.00077431847,0.00031919454,0.0018687225,0.0002069648],"domain_scores_gemma":[0.9983375,0.00019277105,0.0006506442,0.00034793498,0.00042828542,0.0000428547],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002252459,0.00011455639,0.00025915678,0.0001185201,0.00007360909,0.00013234159,0.0013754949,0.000026259968,0.00032719996],"category_scores_gemma":[0.0006641033,0.00006889862,0.00016789186,0.0006234606,0.000080383536,0.0007502263,0.0008783225,0.00007308929,0.00005789742],"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":[0.00014170432,0.0010027615,0.16609113,0.0003129117,0.0003544421,5.417889e-7,0.0027569423,0.00015256002,0.054206166,0.64535916,0.094592266,0.035029385],"study_design_scores_gemma":[0.003519723,0.0005813181,0.17173222,0.00024021845,0.0002450055,0.000008155084,0.036157276,0.0007551209,0.34045133,0.34142417,0.10423032,0.0006551354],"about_ca_topic_score_codex":0.00015827289,"about_ca_topic_score_gemma":0.000017339196,"teacher_disagreement_score":0.30393502,"about_ca_system_score_codex":0.00006158742,"about_ca_system_score_gemma":0.000037736067,"threshold_uncertainty_score":0.35826102},"labels":[],"label_agreement":null},{"id":"W2970828623","doi":"10.14778/3342263.3342645","title":"Efficient algorithms for densest subgraph discovery","year":2019,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":115,"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":"Induced subgraph isomorphism problem; Intuition; Computer science; Subgraph isomorphism problem; Graph; Algorithm; Color-coding; Efficient algorithm; Theoretical computer science; Artificial intelligence; Line graph","score_opus":0.013070494118829084,"score_gpt":0.23755038924642918,"score_spread":0.2244798951276001,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970828623","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":[0.8442253,0.0002037985,0.14223969,0.0041658515,0.001301415,0.002864289,0.00012969748,0.000196548,0.0046734493],"genre_scores_gemma":[0.89763343,0.000010207881,0.100622945,0.00017065865,0.000067402456,0.0002434801,0.0000027237243,0.000013924841,0.0012352272],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988986,0.0000020641403,0.00021825757,0.00035187957,0.00028725114,0.0002418988],"domain_scores_gemma":[0.9992806,0.000054706565,0.00018057783,0.00030130002,0.0001376661,0.000045186025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025585078,0.00012018037,0.00014648329,0.000057965866,0.000110698245,0.00016386058,0.0012661234,0.000028531555,0.0000024703484],"category_scores_gemma":[0.000027147285,0.000080985934,0.00012650063,0.00034598244,0.00004304125,0.00019577617,0.00043721878,0.00006559136,0.000014707158],"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":[0.00002552519,0.00078304723,0.0048751594,0.0002989809,0.00012693963,2.2793668e-7,0.0015499904,0.000533874,0.0851652,0.8348223,0.010426831,0.06139191],"study_design_scores_gemma":[0.002906623,0.00064082956,0.014247085,0.0003904539,0.000102783524,0.000044341406,0.00077524333,0.5267554,0.3926595,0.01994577,0.040547334,0.0009846651],"about_ca_topic_score_codex":0.000021657046,"about_ca_topic_score_gemma":4.30241e-7,"teacher_disagreement_score":0.81487656,"about_ca_system_score_codex":0.000036720663,"about_ca_system_score_gemma":0.000028802728,"threshold_uncertainty_score":0.33025107},"labels":[],"label_agreement":null},{"id":"W2970882829","doi":"10.14778/3352063.3352146","title":"PNUTS to Sherpa","year":2019,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Distributed systems and fault tolerance","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":"University of Toronto","funders":"","keywords":"Cloud computing; Computer science; Operating system","score_opus":0.0041628378496365685,"score_gpt":0.19134434637664263,"score_spread":0.18718150852700607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970882829","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":[0.88689107,0.0001657234,0.0047544846,0.0068647466,0.0018607783,0.0015435073,0.000011847213,0.00017110574,0.09773674],"genre_scores_gemma":[0.9949233,0.0000023834114,0.0025548765,0.00038716616,0.000036776593,0.00003113554,1.4361933e-7,0.000005573039,0.0020586255],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989311,0.0000029412627,0.00021023398,0.00026767407,0.00036472094,0.00022330505],"domain_scores_gemma":[0.99942124,0.000010762766,0.000119633594,0.00024095125,0.0001365907,0.00007082805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021488089,0.00010372165,0.00015842692,0.00003777588,0.000044165015,0.0000900356,0.001339107,0.000028268909,0.000012777512],"category_scores_gemma":[0.000019485553,0.00006836665,0.00007728317,0.000381958,0.000012384014,0.00023216405,0.00045742164,0.000067958135,0.00015455727],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032243388,0.00027657708,0.028263656,0.0003302663,0.00008371922,9.42801e-7,0.0034463909,0.00020838174,0.27475414,0.60883945,0.059591945,0.024172263],"study_design_scores_gemma":[0.0019809487,0.0005614014,0.04001458,0.0008979381,0.000022360035,0.000044899538,0.00051154516,0.007158541,0.4832112,0.009037692,0.4556716,0.00088731793],"about_ca_topic_score_codex":0.00002759643,"about_ca_topic_score_gemma":6.343724e-7,"teacher_disagreement_score":0.5998018,"about_ca_system_score_codex":0.000047565125,"about_ca_system_score_gemma":0.000017262573,"threshold_uncertainty_score":0.2787911},"labels":[],"label_agreement":null},{"id":"W2970956651","doi":"10.14778/3342263.3342627","title":"Ocean vista","year":2019,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":24,"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; Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Computer science; Computer network; Distributed computing; Gossip; Latency (audio); Concurrency control; Distributed transaction; Serializability; Transaction processing; Replication (statistics); Asynchronous communication; Database transaction; Database; Telecommunications","score_opus":0.004017234516262306,"score_gpt":0.1842977793246883,"score_spread":0.18028054480842598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970956651","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":[0.9005635,0.0002414818,0.0017336773,0.0030905595,0.0014345988,0.00096144853,0.0000134196,0.00017944547,0.091781914],"genre_scores_gemma":[0.9970585,0.0000043666296,0.0007876948,0.00014710483,0.000030805175,0.0000033650056,2.682273e-7,0.0000053275953,0.001962574],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989882,0.0000031907798,0.00021680494,0.00024200573,0.00034787218,0.00020194321],"domain_scores_gemma":[0.9993966,0.000011371941,0.00018166754,0.00023752329,0.00012830303,0.000044509412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022060613,0.00010147729,0.00015202115,0.000029593986,0.00005070336,0.00009668509,0.0012930895,0.000028971124,0.000010896719],"category_scores_gemma":[0.00001550226,0.00006572293,0.00008881922,0.00027956403,0.000023034348,0.00027131432,0.00036865188,0.000079088,0.000054660068],"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":[0.000016593374,0.00021634257,0.037235066,0.00031122973,0.00006929421,6.999347e-7,0.0014338058,0.00007890212,0.06313338,0.85302246,0.039503165,0.0049790614],"study_design_scores_gemma":[0.0039430447,0.00061087916,0.04235111,0.001093614,0.00004579095,0.000103757695,0.0009123377,0.031204296,0.43653375,0.02554924,0.45633855,0.001313642],"about_ca_topic_score_codex":0.000018721064,"about_ca_topic_score_gemma":1.6979106e-7,"teacher_disagreement_score":0.8274732,"about_ca_system_score_codex":0.000039887887,"about_ca_system_score_gemma":0.000018633233,"threshold_uncertainty_score":0.26801035},"labels":[],"label_agreement":null},{"id":"W2970992672","doi":"10.14778/3352063.3352116","title":"Data lake management","year":2019,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":236,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"TD Bank Group; University of Toronto","funders":"","keywords":"Metadata; Data management; Metadata management; Data science; Data management plan; Computer science; Data integration; Software versioning; Data mapping; Data extraction; Data element; Research data; Data virtualization; Data curation; Database; World Wide Web; Software","score_opus":0.19096554616353498,"score_gpt":0.3896089267691528,"score_spread":0.19864338060561784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970992672","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":[0.21318969,0.00013218504,0.00026199353,0.012052642,0.0021087513,0.0025781002,0.0005677844,0.000097855685,0.769011],"genre_scores_gemma":[0.94992584,0.00007182606,0.0026983237,0.0012261103,0.00006681453,0.000030666233,0.00002150233,0.00001461448,0.045944292],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99663407,0.000016608958,0.00058983057,0.000625041,0.0018801609,0.00025427833],"domain_scores_gemma":[0.9979554,0.00010453135,0.00039833755,0.0013374187,0.00014767765,0.000056676807],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0039867936,0.00013409548,0.00023356757,0.00013503643,0.0000818218,0.000221756,0.0055228253,0.000027945136,0.0008325573],"category_scores_gemma":[0.00029328867,0.00007762691,0.00008796646,0.00058597256,0.000071151895,0.0006484029,0.0057442994,0.00009131345,0.000896293],"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":[0.00006041762,0.0002915908,0.014538794,0.00019110406,0.00017358296,8.7280773e-7,0.00038638516,0.000021883334,0.0011219103,0.37607518,0.5550478,0.052090466],"study_design_scores_gemma":[0.00046774835,0.000037125898,0.01089679,0.00005279854,0.00004019351,0.0000016245751,0.001976713,0.00022190128,0.0016090437,0.032707166,0.9518612,0.00012771656],"about_ca_topic_score_codex":0.000013332878,"about_ca_topic_score_gemma":0.000025716168,"teacher_disagreement_score":0.7367362,"about_ca_system_score_codex":0.000024845214,"about_ca_system_score_gemma":0.00000963265,"threshold_uncertainty_score":0.9998816},"labels":[],"label_agreement":null},{"id":"W2971000368","doi":"10.14778/3352063.3352080","title":"VISE","year":2019,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Image and Video Retrieval Techniques","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; Pipeline (software); Interface (matter); Convolutional neural network; Nearest neighbor search; Scalability; Feature (linguistics); Image retrieval; Artificial intelligence; Frame (networking); Search engine; Computer vision; Information retrieval; Image (mathematics); Database","score_opus":0.005005524439825163,"score_gpt":0.21708860347009692,"score_spread":0.21208307903027176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2971000368","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":[0.571269,0.0011420272,0.16233233,0.008188185,0.0017167411,0.0038572655,0.000005872852,0.0014595184,0.2500291],"genre_scores_gemma":[0.96983624,0.000045617628,0.028317561,0.00029804758,0.000021973594,0.000015196658,6.140412e-8,0.0000066557504,0.0014586777],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992056,0.0000022196175,0.00015461248,0.00020427389,0.00026827704,0.00016505313],"domain_scores_gemma":[0.9994925,0.000016758493,0.00013526728,0.00020418063,0.00011906218,0.00003218862],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015678514,0.000088570494,0.000116696734,0.00004284029,0.000037792634,0.000045110457,0.0010844993,0.000024260764,0.000013513369],"category_scores_gemma":[0.000037562644,0.00005642055,0.00007858957,0.00029688413,0.000026550093,0.0004795687,0.00054834277,0.00008570979,0.00003314406],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002105681,0.0001423019,0.009712984,0.00014136922,0.000030249019,5.209541e-7,0.0006219401,0.0000037888933,0.54164034,0.37614608,0.0058786524,0.065660685],"study_design_scores_gemma":[0.00016862934,0.00009203671,0.0011746681,0.000051792904,0.0000034012576,0.000005635633,0.000022691494,0.00025592506,0.95896405,0.024904193,0.014268374,0.00008861961],"about_ca_topic_score_codex":0.0000044177523,"about_ca_topic_score_gemma":5.083884e-8,"teacher_disagreement_score":0.41732368,"about_ca_system_score_codex":0.000034603578,"about_ca_system_score_gemma":0.000013187899,"threshold_uncertainty_score":0.23007633},"labels":[],"label_agreement":null},{"id":"W2971120804","doi":"10.14778/3352063.3352064","title":"GALO","year":2019,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Database Systems and Queries","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":"York University; IBM (Canada)","funders":"","keywords":"Computer science; SPARQL; Knowledge base; SQL; Query optimization; Process (computing); Query plan; Plan (archaeology); Information retrieval; Base (topology); RDF; Web query classification; Sargable; Database; Data mining; Web search query; World Wide Web; Search engine; Semantic Web; Programming language","score_opus":0.00448911751621578,"score_gpt":0.1879691187956926,"score_spread":0.18348000127947683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2971120804","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":[0.790643,0.0006672369,0.03792579,0.004586798,0.0032058212,0.002140955,0.00002351572,0.00039348085,0.1604134],"genre_scores_gemma":[0.97267497,0.00001203102,0.02501776,0.00015515744,0.000038657265,0.000020777248,2.5156626e-7,0.0000061927994,0.0020742242],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992317,0.0000022906145,0.00015992098,0.00019468907,0.00025575663,0.00015562128],"domain_scores_gemma":[0.9995089,0.000013148125,0.00014252399,0.00021988952,0.000084688305,0.00003083019],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014927969,0.00008163986,0.000118469026,0.000029204257,0.00004519318,0.000022873372,0.0006022268,0.000017043536,0.000015074452],"category_scores_gemma":[0.000020683174,0.000049999875,0.00005848602,0.00018431025,0.000024669895,0.0004454415,0.00049622665,0.000058909758,0.000052821702],"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":[0.0000039013694,0.000026335196,0.004848587,0.00007756338,0.000011724414,1.2539253e-7,0.00036671793,0.0000086869595,0.0638581,0.9268997,0.00190935,0.001989212],"study_design_scores_gemma":[0.00083645753,0.0001776493,0.0065123723,0.0003000527,0.000010447131,0.00003765729,0.00042122678,0.0014387503,0.65702146,0.010725998,0.32215685,0.0003610974],"about_ca_topic_score_codex":0.000019591354,"about_ca_topic_score_gemma":5.734331e-7,"teacher_disagreement_score":0.9161737,"about_ca_system_score_codex":0.000025675734,"about_ca_system_score_gemma":0.000014549085,"threshold_uncertainty_score":0.20389357},"labels":[],"label_agreement":null},{"id":"W2971290973","doi":"10.14778/3342263.3342633","title":"An intermediate representation for optimizing machine learning pipelines","year":2019,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":48,"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":"Berlin Center for Machine Learning; Banting and Best Diabetes Centre, University of Toronto; York University","keywords":"Computer science; Preprocessor; Pipeline transport; Domain (mathematical analysis); External Data Representation; Representation (politics); Semantics (computer science); Data pre-processing; Feature (linguistics); Programming language; Feature engineering; Artificial intelligence; Theoretical computer science; Machine learning; Deep learning","score_opus":0.08481634541627903,"score_gpt":0.37581740113264334,"score_spread":0.2910010557163643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2971290973","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":[0.9877953,0.00004826567,0.004278206,0.0010042647,0.0017216165,0.0009229115,0.000015349648,0.00007066769,0.004143419],"genre_scores_gemma":[0.99001527,0.0000061262253,0.0057410784,0.00008536051,0.00008941763,0.000023176352,0.000007208806,0.000009809999,0.0040225666],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977226,0.000021330216,0.00054124004,0.0005845365,0.0009160785,0.00021419927],"domain_scores_gemma":[0.99835145,0.0002851158,0.0005112295,0.00038190704,0.00041484073,0.000055449287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036566402,0.00011197171,0.00020199454,0.00019322244,0.0001646316,0.0003722907,0.0013205295,0.000023948644,0.00007444027],"category_scores_gemma":[0.0016821229,0.00006789742,0.00012992485,0.0005110878,0.00004772451,0.00044443438,0.00054611283,0.000091047696,0.000039597613],"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":[0.00058819697,0.0005940286,0.35132962,0.0002440423,0.00014433132,5.2510336e-7,0.009255592,0.039714452,0.20424487,0.015489102,0.051079687,0.32731554],"study_design_scores_gemma":[0.002221947,0.0005329134,0.016040811,0.00018791932,0.0000736933,0.0000059614185,0.010837451,0.800462,0.10141424,0.021786993,0.046004232,0.00043185105],"about_ca_topic_score_codex":0.00003893317,"about_ca_topic_score_gemma":0.0000031930292,"teacher_disagreement_score":0.76074755,"about_ca_system_score_codex":0.000030031139,"about_ca_system_score_gemma":0.000011537506,"threshold_uncertainty_score":0.3590008},"labels":[],"label_agreement":null},{"id":"W2982295803","doi":"10.14778/3364324.3364330","title":"LINC","year":2019,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":56,"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":"Computer science; Cluster analysis; Theoretical computer science; Graph; Algorithm; Data mining; Artificial intelligence","score_opus":0.003710575606360767,"score_gpt":0.20465746596577183,"score_spread":0.20094689035941107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2982295803","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":[0.8479055,0.00002689722,0.000058995338,0.00029790576,0.000074674084,0.00033072414,0.0000027225587,0.000038705708,0.15126385],"genre_scores_gemma":[0.9971005,0.0000016208218,0.0007130739,0.00003469065,0.00010772226,0.000023579189,8.923303e-7,0.0000092118735,0.0020087194],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99936783,0.0000022097915,0.00016987903,0.00014207196,0.0001753966,0.00014259017],"domain_scores_gemma":[0.9996026,0.000012635572,0.0001578935,0.0001224572,0.00008020697,0.00002418735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000116350995,0.0000901637,0.00014985859,0.00003251598,0.000037077923,0.000021495915,0.0003482012,0.000012970871,0.00052129716],"category_scores_gemma":[0.0000020267296,0.000060486138,0.00015562444,0.00017493693,0.000022686321,0.000061161234,0.00021433606,0.00008468955,0.000036277608],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015039342,0.0001829142,0.5947813,0.00003887872,0.00020091249,2.0793323e-8,0.00027614352,0.000027689024,0.07425597,0.3061601,0.013627154,0.01043392],"study_design_scores_gemma":[0.00081793533,0.000126612,0.018909736,0.00019453438,0.00017063195,9.725087e-7,0.0006294047,0.0015569674,0.7830499,0.1303304,0.063783996,0.00042895178],"about_ca_topic_score_codex":0.000068080975,"about_ca_topic_score_gemma":3.3207024e-7,"teacher_disagreement_score":0.7087939,"about_ca_system_score_codex":0.000018843157,"about_ca_system_score_gemma":0.000008512082,"threshold_uncertainty_score":0.5707838},"labels":[],"label_agreement":null},{"id":"W2982581272","doi":"10.14778/3364324.3364332","title":"Secure multi-party functional dependency discovery","year":2019,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Cryptography and Data Security","field":"Computer Science","cited_by":22,"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; Profiling (computer programming); Computation; Secure two-party computation; Cryptography; Dependency (UML); Functional dependency; Access control; Distributed computing; Secure multi-party computation; Cryptographic protocol; Semantics (computer science); Data anonymization; Theoretical computer science; Computer security; Data mining; Information privacy; Algorithm; Relational database; Programming language; Artificial intelligence","score_opus":0.011561321195034262,"score_gpt":0.2036494168363956,"score_spread":0.19208809564136134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2982581272","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":[0.9462669,0.00070696254,0.0323743,0.0019234956,0.0027486633,0.0013259329,0.000074724696,0.00023415798,0.014344852],"genre_scores_gemma":[0.99162585,0.000021556858,0.007922166,0.00017439114,0.00004970656,0.000021643944,0.0000019358788,0.0000060513735,0.00017669832],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985757,0.000005622492,0.0002147404,0.00036658364,0.0006025831,0.00023475658],"domain_scores_gemma":[0.99930865,0.000026955155,0.00016989568,0.00028356613,0.00015644316,0.000054480326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023205073,0.00014106485,0.00014683144,0.00006909713,0.0000985036,0.00014233073,0.0010779978,0.000049105372,0.000041857165],"category_scores_gemma":[0.00003647935,0.00009349541,0.0001701739,0.00036442876,0.000045545854,0.0012161209,0.00073642255,0.00016853584,0.000035891953],"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":[0.000035043948,0.00039911212,0.04581522,0.0001313767,0.000067424895,4.1899366e-7,0.0010683502,0.000019186853,0.038305793,0.9073943,0.0055686072,0.0011951939],"study_design_scores_gemma":[0.0068962476,0.0006783251,0.24380673,0.00051928614,0.00013342647,0.00013761464,0.0018640017,0.012834312,0.45563507,0.23080285,0.04493492,0.0017572122],"about_ca_topic_score_codex":0.000027193893,"about_ca_topic_score_gemma":0.000005476553,"teacher_disagreement_score":0.67659146,"about_ca_system_score_codex":0.00004106265,"about_ca_system_score_gemma":0.000041869713,"threshold_uncertainty_score":0.3812632},"labels":[],"label_agreement":null},{"id":"W3000259868","doi":"10.14778/3372716.3372728","title":"Evaluating persistent memory range indexes","year":2019,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":94,"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; Benchmarking; Index (typography); Dram; Range (aeronautics); Tree (set theory); Key (lock); Data structure; Focus (optics); Persistent data structure; Database; Operating system; Computer hardware; Programming language","score_opus":0.03028429458173998,"score_gpt":0.2794155407627558,"score_spread":0.24913124618101584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3000259868","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":[0.9432056,0.0004350843,0.009034029,0.002227383,0.0006686972,0.0012210986,0.0000011297042,0.0005109197,0.042696062],"genre_scores_gemma":[0.9390992,0.000013335327,0.059463408,0.00022202427,0.00002788967,0.00002240793,1.485438e-7,0.000007409551,0.0011442042],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99881095,0.000012138024,0.00023628458,0.0002743096,0.00047082608,0.00019550086],"domain_scores_gemma":[0.99926144,0.000034578807,0.00024236625,0.00021906642,0.00020489203,0.000037680613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062808767,0.00011565216,0.0001554544,0.00007573659,0.000095629635,0.00007921404,0.0011515063,0.000037616588,0.000014419749],"category_scores_gemma":[0.000062548104,0.00008094182,0.00014781568,0.0002757289,0.000029063209,0.000220792,0.0005968669,0.00010771523,0.000015710935],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018444717,0.0013497014,0.13213705,0.0016162097,0.0007245926,0.0000016234399,0.031649023,0.053953152,0.3542597,0.24044444,0.028669862,0.15501021],"study_design_scores_gemma":[0.0023475988,0.00097631256,0.006835184,0.00065647933,0.00007178848,0.000043051085,0.00059881766,0.5122238,0.46441534,0.0094032595,0.0016300791,0.00079832715],"about_ca_topic_score_codex":0.000014628991,"about_ca_topic_score_gemma":1.2359116e-7,"teacher_disagreement_score":0.4582706,"about_ca_system_score_codex":0.00006310275,"about_ca_system_score_gemma":0.000029760473,"threshold_uncertainty_score":0.33007118},"labels":[],"label_agreement":null},{"id":"W3011592252","doi":"10.14778/3236187.3236199","title":"Efficient construction of approximate ad-hoc ML models through materialization and reuse","year":2018,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Online analytical processing; Reuse; Dimension (graph theory); Cluster analysis; Variety (cybernetics); Data warehouse; Data mining; Construct (python library); Mixture model; Machine learning; Artificial intelligence; Mathematics; Programming language","score_opus":0.0167162247919843,"score_gpt":0.22005666246918465,"score_spread":0.20334043767720034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011592252","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":[0.8782429,0.0001761049,0.11153561,0.0012548182,0.0011440531,0.0009492957,0.000020523074,0.00014041924,0.0065362365],"genre_scores_gemma":[0.857347,0.00012030771,0.14233345,0.000053859596,0.000046469795,0.00001767999,0.0000014892881,0.000008131737,0.00007159434],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990968,0.0000052533956,0.00024215007,0.00024535749,0.0002692093,0.00014120842],"domain_scores_gemma":[0.99929297,0.0000054379566,0.0002692447,0.00024777793,0.00016338463,0.000021155745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023166873,0.00009892955,0.00013054845,0.000053211403,0.000087751745,0.00009616457,0.00074541685,0.000024670964,0.000004329851],"category_scores_gemma":[0.000021527581,0.00007025754,0.0000279853,0.00025121451,0.00017364838,0.00044867917,0.0010269454,0.000027420587,0.0000014436985],"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":[0.00006234717,0.00019497969,0.00020988885,0.0004396009,0.00007376381,1.9723541e-7,0.0067503527,0.00017533051,0.06799204,0.90664,0.0017095257,0.015752012],"study_design_scores_gemma":[0.0010513441,0.00029108985,0.00022954712,0.00024001939,0.000055432443,0.000013376674,0.0005180683,0.3404569,0.5452298,0.10984698,0.0018106686,0.000256773],"about_ca_topic_score_codex":0.000010669031,"about_ca_topic_score_gemma":2.0500302e-7,"teacher_disagreement_score":0.796793,"about_ca_system_score_codex":0.00001998862,"about_ca_system_score_gemma":0.000007353367,"threshold_uncertainty_score":0.28650194},"labels":[],"label_agreement":null},{"id":"W3012550338","doi":"10.14778/3389133.3389134","title":"Dash","year":2020,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Data Storage Technologies","field":"Computer Science","cited_by":135,"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":"Hash function; Scalability; Emulation; Hash table; Factor (programming language); Double hashing; Table (database)","score_opus":0.021384455536146138,"score_gpt":0.22421011762339768,"score_spread":0.20282566208725156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012550338","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":[0.25722143,0.001645049,0.3888936,0.26322767,0.0016848856,0.0034011577,0.000055809964,0.006458937,0.07741145],"genre_scores_gemma":[0.92402464,0.000021269649,0.07505194,0.0007989347,0.000027453438,0.000019137018,1.6031734e-7,0.000005905706,0.0000505319],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99916226,0.0000015138392,0.00015379219,0.00025300193,0.00026258788,0.00016682479],"domain_scores_gemma":[0.99952847,0.000014356758,0.0001436229,0.00020397823,0.00006704888,0.000042511725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007203795,0.0000934175,0.00011556132,0.000026441305,0.000056751618,0.000041245286,0.0023199013,0.000027529288,0.000004226365],"category_scores_gemma":[0.00020508877,0.00006256819,0.0000497191,0.00042252173,0.00007289151,0.00043965803,0.0017972084,0.00011530189,0.000018790372],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009833822,0.00005757588,0.0015006555,0.00009057555,0.00002969021,0.0000015097414,0.0012782875,0.00003327442,0.17655663,0.7617239,0.022596227,0.036121838],"study_design_scores_gemma":[0.0003344827,0.00013594607,0.00051428966,0.00003400526,0.000008792299,0.000008631237,0.00023818138,0.0024467586,0.91997427,0.042872075,0.03324641,0.00018616366],"about_ca_topic_score_codex":0.0000026108858,"about_ca_topic_score_gemma":1.1646844e-7,"teacher_disagreement_score":0.7434176,"about_ca_system_score_codex":0.000030033836,"about_ca_system_score_gemma":0.00001177812,"threshold_uncertainty_score":0.43109924},"labels":[],"label_agreement":null},{"id":"W3012623189","doi":"10.14778/3407790.3407814","title":"Efficient oblivious database joins","year":2020,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Cryptography and Data Security","field":"Computer Science","cited_by":38,"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; Cloud computing; Encryption; Sorting; Join (topology); Logarithm; Data structure; Computational complexity theory","score_opus":0.018108163619771928,"score_gpt":0.21146538441976953,"score_spread":0.1933572207999976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012623189","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":[0.87630403,0.0018999901,0.052926395,0.037392586,0.001502849,0.0025127556,0.00030603286,0.0009421207,0.026213221],"genre_scores_gemma":[0.98523706,0.000020952997,0.013631336,0.0010056688,0.00007690041,0.000016642929,0.0000015225152,0.0000061169285,0.0000037695481],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987121,0.000005685035,0.00022907105,0.00036294252,0.0004515557,0.00023864432],"domain_scores_gemma":[0.99932647,0.000023267046,0.00015758397,0.00025835377,0.000095517265,0.00013881734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015926598,0.00013206522,0.00014922538,0.00005084594,0.00011889574,0.000094481446,0.0016184011,0.00002575462,0.000013089121],"category_scores_gemma":[0.00009399932,0.00009102941,0.0001259619,0.00071475154,0.000067986985,0.0001794327,0.0013247725,0.00014446386,0.0000170787],"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":[0.000039832896,0.00049525127,0.0022440092,0.00026117655,0.00006296401,0.0000029111795,0.007021662,0.00010565055,0.088558435,0.87391037,0.022689942,0.0046077757],"study_design_scores_gemma":[0.003615983,0.0008608748,0.0075136167,0.0003936267,0.00014810938,0.00006566576,0.0016246196,0.12884152,0.757386,0.020047856,0.07814152,0.0013605917],"about_ca_topic_score_codex":0.000023482695,"about_ca_topic_score_gemma":8.417359e-7,"teacher_disagreement_score":0.8538625,"about_ca_system_score_codex":0.000018319797,"about_ca_system_score_gemma":0.000025217676,"threshold_uncertainty_score":0.37120715},"labels":[],"label_agreement":null},{"id":"W3025940890","doi":"10.14778/3401960.3401966","title":"Approximate denial constraints","year":2020,"lang":"en","type":"preprint","venue":"Proceedings of the VLDB Endowment","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":"Overfitting; Computer science; Feature (linguistics); Focus (optics); Axiom; Mathematical optimization; Theoretical computer science; Algorithm; Mathematics; Artificial intelligence","score_opus":0.024586798940756546,"score_gpt":0.24463647034998354,"score_spread":0.220049671409227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3025940890","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":[0.039188817,0.0013956144,0.86743206,0.02017019,0.009223286,0.0069777104,0.00080099935,0.0013823141,0.05342901],"genre_scores_gemma":[0.7881625,0.000079015816,0.21059102,0.00034285887,0.00034919564,0.00023751194,0.000008089317,0.000032980253,0.00019680447],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9979242,0.000010260104,0.00050793175,0.00067595684,0.0005724337,0.0003091853],"domain_scores_gemma":[0.9985228,0.000024437519,0.0006989788,0.00043101428,0.00020997404,0.00011277604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002568294,0.0003178144,0.0004591874,0.00005879194,0.00011121855,0.00010925247,0.0019014293,0.00011220133,0.000010334445],"category_scores_gemma":[0.000118112745,0.00022207276,0.00022326631,0.00019855234,0.00022383215,0.00027527465,0.005981031,0.00045307365,0.000011766715],"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":[0.000021514148,0.00007864928,0.00033392143,0.0013307725,0.00013626249,0.0000038266594,0.0018653291,0.0000526406,0.022878129,0.9612013,0.0044086627,0.007689011],"study_design_scores_gemma":[0.0024306918,0.00030459143,0.0009789225,0.003786323,0.00021827247,0.00020874728,0.0010919714,0.017110368,0.6843369,0.2057581,0.08136823,0.002406877],"about_ca_topic_score_codex":0.00003351815,"about_ca_topic_score_gemma":0.0000010917934,"teacher_disagreement_score":0.7554432,"about_ca_system_score_codex":0.000081095386,"about_ca_system_score_gemma":0.00012471496,"threshold_uncertainty_score":0.9055864},"labels":[],"label_agreement":null},{"id":"W3038067601","doi":"10.14778/3397230.3397239","title":"Scalable, near-zero loss disaster recovery for distributed data stores","year":2020,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Distributed systems and fault tolerance","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":"","keywords":"Backup; Computer science; Failover; Data loss; Scalability; Distributed computing; Replication (statistics); Fault tolerance; Backup software; Eventual consistency; Computer network; Disaster recovery; Data integrity; Data recovery; Asynchronous communication; Data consistency; Database; Consistency model; Operating system","score_opus":0.036865755455791,"score_gpt":0.2497641672253746,"score_spread":0.21289841176958357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3038067601","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":[0.1030829,0.000952254,0.8432946,0.038668554,0.0021526245,0.0036845298,0.0051508583,0.00045178458,0.0025618814],"genre_scores_gemma":[0.9873709,0.000016565133,0.011559863,0.0006270666,0.000116860974,0.0000795079,0.000057573972,0.000016701257,0.00015492745],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982187,0.000007837443,0.00041303213,0.0005910806,0.0004179991,0.00035135465],"domain_scores_gemma":[0.9987673,0.000054228225,0.0003165043,0.00050835323,0.00021750678,0.00013611563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031902775,0.00019347729,0.00029766042,0.000016367381,0.00018013935,0.00032925358,0.003231648,0.00005620358,0.000004975122],"category_scores_gemma":[0.00022714538,0.00013404392,0.00011847201,0.00042507655,0.00008869632,0.0008268354,0.0014606233,0.000114551105,0.000010491246],"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":[0.0005133031,0.0006616146,0.012949405,0.0018854141,0.0005164725,0.000004527071,0.0038485462,0.0009054827,0.017452039,0.08340915,0.83825266,0.03960135],"study_design_scores_gemma":[0.004387758,0.00078644906,0.0045539793,0.0006815166,0.00014369699,0.000035293586,0.00044611804,0.27306998,0.031229625,0.01031868,0.67319393,0.0011529578],"about_ca_topic_score_codex":0.000026173442,"about_ca_topic_score_gemma":0.000001377912,"teacher_disagreement_score":0.884288,"about_ca_system_score_codex":0.00005099909,"about_ca_system_score_gemma":0.000053514585,"threshold_uncertainty_score":0.600526},"labels":[],"label_agreement":null},{"id":"W3082162291","doi":"10.14778/3407790.3407810","title":"<i>Pytheas</i>","year":2020,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Information retrieval; Metadata; Table (database); File format; Data extraction; Data mining; World Wide Web; Database","score_opus":0.014954288133886124,"score_gpt":0.18961740079404488,"score_spread":0.17466311266015874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3082162291","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":[0.4625249,0.0010568252,0.038144115,0.32840836,0.0011753975,0.0013009517,0.00005337429,0.0012841234,0.16605197],"genre_scores_gemma":[0.9899863,0.000013076613,0.008126179,0.0016468503,0.00006397918,0.0000074240706,2.9052853e-7,0.000004719711,0.00015118661],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991593,0.0000034163554,0.00016677065,0.00023240931,0.00029024057,0.00014790343],"domain_scores_gemma":[0.9995685,0.000013174198,0.00012603102,0.00014624861,0.00006894396,0.00007707654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013785309,0.000083438616,0.00012883371,0.00002394711,0.00006702668,0.00007479577,0.0014319876,0.0000177434,0.000008399292],"category_scores_gemma":[0.00007352225,0.000053449574,0.00010158331,0.00046211423,0.000030372343,0.00023829279,0.0006164167,0.00007740207,0.000025192969],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003139592,0.00029542597,0.017496489,0.00029126025,0.00032381047,0.0000026861387,0.009434387,0.00009699093,0.37427163,0.37418905,0.17416836,0.049398508],"study_design_scores_gemma":[0.0010443601,0.00028324977,0.0020628124,0.00013963736,0.000121968005,0.000017779877,0.0006596342,0.0320426,0.8367914,0.007445361,0.118871875,0.0005193205],"about_ca_topic_score_codex":0.000012789074,"about_ca_topic_score_gemma":1.7645762e-7,"teacher_disagreement_score":0.5274614,"about_ca_system_score_codex":0.000011742894,"about_ca_system_score_gemma":0.000016363956,"threshold_uncertainty_score":0.26610133},"labels":[],"label_agreement":null},{"id":"W3084763998","doi":"10.14778/3407790.3407854","title":"SAQE","year":2020,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":53,"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; Differential privacy; Query optimization; Query expansion; Query plan; Overhead (engineering); Data mining; Private information retrieval; Information privacy; Leverage (statistics); Information retrieval; Sargable; Web search query; Computer security; Search engine","score_opus":0.033158732127586174,"score_gpt":0.23953265542545057,"score_spread":0.20637392329786441,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3084763998","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":[0.10939742,0.00047338704,0.017745748,0.8357466,0.00077306887,0.001076397,0.000019452918,0.0020912043,0.032676704],"genre_scores_gemma":[0.8689418,0.000033438544,0.12975425,0.0011648312,0.000043654793,0.000022308921,2.2816339e-7,0.000008251227,0.000031275526],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99886113,0.0000033389288,0.00020246916,0.0003325341,0.00037528662,0.00022525774],"domain_scores_gemma":[0.9983419,0.00002614826,0.00016691373,0.0013225692,0.00008468018,0.000057777244],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00017340896,0.000112388036,0.00013723213,0.000034518,0.00006906894,0.00007712365,0.030127784,0.000044626948,0.000009196309],"category_scores_gemma":[0.0062766476,0.00007727979,0.00006795893,0.0005255071,0.000078502744,0.000396207,0.08179853,0.00016988562,0.000024438947],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011732094,0.00007637417,0.0039566173,0.00013604735,0.00005160914,0.0000012796687,0.0005726086,0.000003156925,0.09997336,0.09124094,0.7863541,0.017622173],"study_design_scores_gemma":[0.00036924693,0.00012433926,0.00096676603,0.000060277638,0.00001178693,0.000008618211,0.000100662764,0.016351797,0.7296154,0.23259471,0.019590065,0.000206322],"about_ca_topic_score_codex":0.0000082972265,"about_ca_topic_score_gemma":1.5844554e-7,"teacher_disagreement_score":0.8345818,"about_ca_system_score_codex":0.000039182283,"about_ca_system_score_gemma":0.00001946529,"threshold_uncertainty_score":0.9751197},"labels":[],"label_agreement":null},{"id":"W3085364681","doi":"10.14778/3415478.3415562","title":"Data collection and quality challenges for deep learning","year":2020,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":145,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Feature engineering; Deep learning; Data collection; Big data; Data science; Software; Data mining","score_opus":0.12845824892835148,"score_gpt":0.3110977474383105,"score_spread":0.182639498509959,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3085364681","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":[0.038945284,0.001535561,0.8831534,0.06631579,0.00012736954,0.0021987313,0.000014846895,0.00067745853,0.0070315828],"genre_scores_gemma":[0.9614473,0.00042233357,0.037741568,0.00015732815,0.000039222483,0.00010763241,6.8974833e-7,0.000004764426,0.00007916247],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999429,0.000004350586,0.00013658358,0.00024973066,0.000102142505,0.00007821957],"domain_scores_gemma":[0.99960136,0.000030645457,0.00013961899,0.00011841736,0.00007515113,0.000034799104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024573467,0.000054332108,0.000082374514,0.000015867787,0.00016029565,0.000039649574,0.00058924255,0.000022265722,9.3283114e-7],"category_scores_gemma":[0.00009299544,0.00004134062,0.000025023679,0.00014894363,0.000023223844,0.00018352339,0.0005234082,0.0000624755,4.671265e-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":[0.000047985137,0.00011978023,0.001822355,0.0005275249,0.000067034794,2.937659e-8,0.0042955074,0.0000143875795,0.07864595,0.62925315,0.0025350556,0.2826712],"study_design_scores_gemma":[0.0013275876,0.0009906711,0.013023881,0.00007684271,0.00006673175,0.000012986558,0.002236707,0.2485432,0.42419934,0.031442072,0.27752557,0.00055440573],"about_ca_topic_score_codex":0.0000089119185,"about_ca_topic_score_gemma":0.0000017197472,"teacher_disagreement_score":0.92250204,"about_ca_system_score_codex":0.000012818247,"about_ca_system_score_gemma":0.000006592554,"threshold_uncertainty_score":0.16858216},"labels":[],"label_agreement":null},{"id":"W3085986371","doi":"10.14778/3407790.3407845","title":"Do the best cloud configurations grow on trees?","year":2020,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Cloud computing; Bayesian optimization; Computer science; Black box; Optimization problem; Mathematical optimization; Data mining; Algorithm; Machine learning; Artificial intelligence; Mathematics; Operating system","score_opus":0.025114293130988532,"score_gpt":0.22797825888268863,"score_spread":0.2028639657517001,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3085986371","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":[0.6030521,0.0002747268,0.002653852,0.25040352,0.0012605947,0.0015981952,0.000005227505,0.00036005408,0.14039172],"genre_scores_gemma":[0.9964392,0.0000070135616,0.0004582914,0.0023390928,0.00026139905,0.00002574331,1.2720184e-7,0.000008002499,0.00046111122],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987362,0.000013203822,0.00023895729,0.00031707168,0.00047620526,0.00021835632],"domain_scores_gemma":[0.9993207,0.00006457216,0.00019994647,0.000255551,0.00008714739,0.000072074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002482458,0.00014374105,0.000135756,0.000031492105,0.0003005844,0.00019672235,0.0018285388,0.00002596904,0.000007693105],"category_scores_gemma":[0.000080784055,0.00007594473,0.00012918853,0.00043154974,0.000073795105,0.000027095322,0.00070749153,0.00017722699,0.000045708966],"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":[0.00003032028,0.00033701316,0.0006826694,0.00008837185,0.00015074246,0.0000017584186,0.010083234,0.0043302393,0.010834987,0.8953238,0.047217034,0.03091984],"study_design_scores_gemma":[0.004425322,0.0031309966,0.009696194,0.0009678652,0.00033658132,0.000051245526,0.0107848635,0.26585,0.19733083,0.031002026,0.47471237,0.0017117071],"about_ca_topic_score_codex":0.000016888403,"about_ca_topic_score_gemma":6.0790416e-7,"teacher_disagreement_score":0.86432177,"about_ca_system_score_codex":0.000033776676,"about_ca_system_score_gemma":0.0000147524,"threshold_uncertainty_score":0.33979106},"labels":[],"label_agreement":null},{"id":"W3086093300","doi":"10.14778/3415478.3415483","title":"PiBench online","year":2020,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Data Storage Technologies","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":"Simon Fraser University","funders":"","keywords":"Computer science; Benchmarking; Upload; Emulation; Key (lock); Implementation; Operating system; Dram; Interface (matter); Spec#; Embedded system; Software engineering; Computer hardware","score_opus":0.025558968550096615,"score_gpt":0.23712624469475133,"score_spread":0.2115672761446547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3086093300","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":[0.5202621,0.00166486,0.20393234,0.24619077,0.0013277765,0.0027534822,0.00013636572,0.0047536925,0.01897858],"genre_scores_gemma":[0.8768339,0.000035615765,0.12206458,0.0009534634,0.00004026387,0.0000139013655,6.363261e-7,0.0000069534917,0.0000506738],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990522,0.0000017522218,0.00018717637,0.00028253096,0.00029148403,0.00018485749],"domain_scores_gemma":[0.9994633,0.000016545067,0.00016493481,0.00021961608,0.000087567365,0.000048036938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006560101,0.00010884063,0.00013564374,0.000032660195,0.00005706886,0.000036187426,0.002339904,0.000032193584,0.000004927004],"category_scores_gemma":[0.00021558066,0.00007284462,0.00005491452,0.00049446686,0.00007687367,0.0004233381,0.0017614434,0.00014597557,0.000010899602],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002019426,0.00025342006,0.0025885024,0.00018199135,0.000058332782,0.0000033712042,0.002060109,0.00009722237,0.2538564,0.646611,0.025146415,0.06912308],"study_design_scores_gemma":[0.00067317113,0.00032310895,0.0017880033,0.0000754947,0.000018376068,0.000017799926,0.0005933079,0.00822041,0.89762735,0.057648245,0.032658506,0.0003561975],"about_ca_topic_score_codex":0.0000044254275,"about_ca_topic_score_gemma":3.7419542e-7,"teacher_disagreement_score":0.643771,"about_ca_system_score_codex":0.00003545845,"about_ca_system_score_gemma":0.00001536423,"threshold_uncertainty_score":0.4348163},"labels":[],"label_agreement":null},{"id":"W3086099593","doi":"10.14778/3407790.3407856","title":"Sentinel","year":2020,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Software System Performance and Reliability","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":"University of Waterloo","funders":"","keywords":"Debugging; Computer science; Variety (cybernetics); Server; Distributed computing; Web application; Operating system; Database; Embedded system; Artificial intelligence","score_opus":0.013665081243024367,"score_gpt":0.20227277804738522,"score_spread":0.18860769680436085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3086099593","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":[0.945706,0.00018020908,0.0033058946,0.031996988,0.00066019146,0.00068860495,0.0000015904619,0.00037527148,0.017085252],"genre_scores_gemma":[0.9970093,0.000008723503,0.0020091992,0.0007967401,0.000077754485,0.000014464946,5.981876e-8,0.00000401066,0.000079788864],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991226,0.0000032047105,0.00020829478,0.0002149659,0.00029817017,0.00015273708],"domain_scores_gemma":[0.9995416,0.000012802289,0.00013406677,0.00013491657,0.00011314564,0.000063515494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017199776,0.000084837964,0.00012507774,0.000016295628,0.00006792759,0.00004200329,0.0010112736,0.00002653765,0.00000617559],"category_scores_gemma":[0.00007001482,0.000050098195,0.00009418442,0.0003329955,0.000035209614,0.00023804221,0.0005036266,0.00008104108,0.000028455996],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006989229,0.00044376336,0.569014,0.002120252,0.00020018885,0.0000017565194,0.017522365,0.00011565774,0.1784233,0.12668376,0.08076434,0.024640745],"study_design_scores_gemma":[0.0018993114,0.00028468043,0.07463063,0.00026482262,0.00004835024,0.00003454602,0.00050308026,0.027235925,0.8416666,0.007930712,0.044846542,0.0006548392],"about_ca_topic_score_codex":0.0000067268866,"about_ca_topic_score_gemma":4.948282e-8,"teacher_disagreement_score":0.66324323,"about_ca_system_score_codex":0.000019935278,"about_ca_system_score_gemma":0.00002028679,"threshold_uncertainty_score":0.20429452},"labels":[],"label_agreement":null},{"id":"W3086212533","doi":"10.14778/3407790.3407861","title":"Suffix rank","year":2020,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Algorithms and Data Compression","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 Victoria; University of Toronto","funders":"","keywords":"Substring; Suffix array; Suffix; Generalized suffix tree; Computer science; Suffix tree; Compressed suffix array; Scalability; Rank (graph theory); Extension (predicate logic); Liveness; Algorithm; Context (archaeology); Parallelizable manifold; Auxiliary memory; Theoretical computer science; Data structure; Mathematics; Combinatorics; Database","score_opus":0.01641272735555164,"score_gpt":0.20674939338029258,"score_spread":0.19033666602474095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3086212533","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":[0.39472064,0.0026384469,0.25931868,0.2120973,0.004138572,0.0042767455,0.00007334357,0.0018504238,0.12088584],"genre_scores_gemma":[0.9743349,0.000029493069,0.024165077,0.0012222988,0.00011831928,0.0000141071405,4.3230608e-7,0.0000067663377,0.00010859697],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99912035,0.0000031619763,0.00016569854,0.00023562709,0.0003218358,0.00015332602],"domain_scores_gemma":[0.99956286,0.000013881014,0.00012207487,0.00014074263,0.00007996375,0.00008049859],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010890627,0.000089794754,0.00011676552,0.000018139039,0.00008014175,0.000070768816,0.0014069949,0.000022277256,0.000013735927],"category_scores_gemma":[0.00004759439,0.00005511328,0.00006737249,0.0002631085,0.000028380939,0.00033807816,0.0010603406,0.00009060231,0.000019343279],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007525189,0.00034722048,0.0057842545,0.00031831005,0.00010100898,0.000003184765,0.0073113097,0.000074169126,0.28302062,0.45094278,0.16298349,0.089038394],"study_design_scores_gemma":[0.001870915,0.00041238673,0.005575307,0.00018546265,0.000034317687,0.000021121316,0.00026912658,0.07575242,0.73661625,0.013868397,0.16487789,0.0005164161],"about_ca_topic_score_codex":0.000012641496,"about_ca_topic_score_gemma":8.949419e-8,"teacher_disagreement_score":0.5796143,"about_ca_system_score_codex":0.0000147099345,"about_ca_system_score_gemma":0.000016193915,"threshold_uncertainty_score":0.261457},"labels":[],"label_agreement":null},{"id":"W3086284023","doi":"10.14778/3415478.3415500","title":"ActiveDeeper","year":2020,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Web Data Mining and Analysis","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":"Simon Fraser University","funders":"","keywords":"Deep Web; Computer science; World Wide Web; State (computer science); Database; The Internet; Programming language","score_opus":0.017852573838847422,"score_gpt":0.1999878516851466,"score_spread":0.18213527784629918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3086284023","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":[0.7190417,0.00038449836,0.029923724,0.15283167,0.0006267063,0.0007840962,0.000025399537,0.00064708217,0.09573512],"genre_scores_gemma":[0.99133116,0.000008363268,0.0075931028,0.00085842545,0.000051258798,0.0000069626567,2.0583838e-7,0.000003816912,0.00014671052],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99926704,0.0000030531535,0.0001296591,0.00021801847,0.00025388232,0.00012833705],"domain_scores_gemma":[0.99962586,0.000012546252,0.00010977031,0.00011920507,0.00006949347,0.00006314052],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000102330356,0.00007502735,0.00011357278,0.000023737804,0.00006281082,0.000067037254,0.0012049533,0.000016930193,0.000012025849],"category_scores_gemma":[0.00007488997,0.00004771483,0.00008882336,0.00037257368,0.00002747088,0.0002783713,0.0005759422,0.0000752608,0.000020886015],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035748522,0.0002821683,0.016553577,0.00019551754,0.00040245074,0.0000019583706,0.014409091,0.00008201562,0.5945716,0.23713374,0.07132722,0.06500491],"study_design_scores_gemma":[0.00067537226,0.00019249992,0.004281387,0.000075557335,0.000081204555,0.0000075473845,0.0008154758,0.021323796,0.92533946,0.0037554265,0.043103017,0.0003492458],"about_ca_topic_score_codex":0.0000110887495,"about_ca_topic_score_gemma":1.5607867e-7,"teacher_disagreement_score":0.33076787,"about_ca_system_score_codex":0.000014675363,"about_ca_system_score_gemma":0.000013976991,"threshold_uncertainty_score":0.22391231},"labels":[],"label_agreement":null},{"id":"W3086973390","doi":"10.14778/3407790.3407858","title":"ATHENA++","year":2020,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada)","funders":"","keywords":"Computer science; Benchmark (surveying); SQL; Query language; Set (abstract data type); Ontology; Nesting (process); Information retrieval; Programming language; Database","score_opus":0.02196695787347267,"score_gpt":0.2013119211773401,"score_spread":0.17934496330386743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3086973390","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":[0.7002492,0.0009199088,0.014618284,0.17549935,0.0011577631,0.0011367764,0.0000030819858,0.0008205306,0.10559513],"genre_scores_gemma":[0.99016094,0.000014786858,0.008392509,0.0012806354,0.000050916165,0.000008805714,2.9315208e-8,0.0000034676764,0.000087885535],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99928653,0.0000023911164,0.0001414853,0.00018630839,0.00023364696,0.00014960667],"domain_scores_gemma":[0.9996657,0.000018353072,0.000101171114,0.000104459155,0.00006230857,0.000048011138],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009559963,0.00007745857,0.00011388701,0.000015830858,0.00005175779,0.0000487947,0.0012801461,0.000020733978,0.0000061668643],"category_scores_gemma":[0.00009978203,0.000046496938,0.00007338549,0.00021976704,0.000039732462,0.00016956628,0.00056876073,0.00006709908,0.000018290855],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020001755,0.00010310149,0.014219382,0.00016383699,0.00006544538,0.0000015745072,0.008324417,0.000014264227,0.11385434,0.82015973,0.023505563,0.019568317],"study_design_scores_gemma":[0.0007839324,0.00027742033,0.0119349,0.00007565153,0.000028622913,0.000018637782,0.0006988395,0.007215099,0.90772325,0.03988873,0.031046838,0.00030807592],"about_ca_topic_score_codex":0.000009286717,"about_ca_topic_score_gemma":2.3927433e-7,"teacher_disagreement_score":0.7938689,"about_ca_system_score_codex":0.000012677645,"about_ca_system_score_gemma":0.000014111875,"threshold_uncertainty_score":0.23788512},"labels":[],"label_agreement":null},{"id":"W3094958164","doi":"10.14778/3424573.3424575","title":"An analysis of concurrency control protocols for in-memory databases with CCBench","year":2020,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nautilus Environmental","funders":"","keywords":"Computer science; Workload; Garbage collection; Parallel computing; Thread (computing); Scalability; Cache; Concurrency control; Concurrency; Distributed computing; Cache coherence; Transaction processing; Database transaction; Operating system; CPU cache; Database; Programming language; Garbage; Cache algorithms","score_opus":0.029335185320784087,"score_gpt":0.29091004507903095,"score_spread":0.26157485975824685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094958164","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":[0.53519475,0.00029626337,0.39698502,0.004818989,0.0002100763,0.058642242,0.0014972369,0.00020365152,0.0021517866],"genre_scores_gemma":[0.9938208,0.0000011184061,0.003013824,0.0001337078,0.000021148897,0.0029939816,0.000004578199,0.000004851145,0.0000059758077],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873674,0.00000958649,0.00040298828,0.0003348114,0.0003275088,0.00018834275],"domain_scores_gemma":[0.9989888,0.000040369738,0.00040632623,0.00021585562,0.00027508684,0.00007357791],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029321603,0.00012520843,0.00041829204,0.00008116704,0.0000380895,0.000042973057,0.0009991409,0.000020382495,0.0000033207468],"category_scores_gemma":[0.00006103514,0.000079374164,0.000106215884,0.00097164215,0.000051589363,0.00038232483,0.00008829139,0.00006305654,2.838569e-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":[0.0012784016,0.0028099034,0.446074,0.0036528956,0.0022768783,0.0000041757503,0.012904868,0.009489482,0.24458598,0.25129613,0.0032803894,0.02234687],"study_design_scores_gemma":[0.012206458,0.0029470504,0.060233228,0.0010924971,0.0007917311,0.000005627863,0.001683421,0.65723807,0.25668922,0.0004587746,0.005798484,0.00085545547],"about_ca_topic_score_codex":0.00006654613,"about_ca_topic_score_gemma":0.00001030129,"teacher_disagreement_score":0.6477486,"about_ca_system_score_codex":0.000023912124,"about_ca_system_score_gemma":0.000051139043,"threshold_uncertainty_score":0.32367846},"labels":[],"label_agreement":null},{"id":"W3095172747","doi":"10.14778/3424573.3424578","title":"MorphoSys","year":2020,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":20,"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; Replication (statistics); Distributed computing; Workload; Distributed database; Operating system","score_opus":0.01438667055517795,"score_gpt":0.19289990444754224,"score_spread":0.1785132338923643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095172747","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":[0.8452984,0.0002687311,0.0062193084,0.083495505,0.0006001004,0.000760207,0.0000013360321,0.00049274653,0.06286363],"genre_scores_gemma":[0.99372804,0.000002781925,0.0044262926,0.0014478524,0.000088961264,0.0000080363225,3.4045804e-8,0.0000057297166,0.00029228756],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990369,0.0000039128413,0.00018234513,0.00025078177,0.0003453319,0.00018072482],"domain_scores_gemma":[0.999575,0.000013141843,0.0001384648,0.0001389966,0.000060934683,0.00007343396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014690871,0.000098265074,0.0001190857,0.000024981357,0.0000877907,0.0000671549,0.0015018742,0.000018327735,0.0000053630724],"category_scores_gemma":[0.000039780083,0.000063216714,0.000098610755,0.00037290077,0.000029858067,0.000026489317,0.0012776717,0.00009207338,0.000020346963],"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":[0.00004164646,0.00042662333,0.008395015,0.0006601382,0.00028740242,0.000006060058,0.015579747,0.003981596,0.083184876,0.64812124,0.1364066,0.10290906],"study_design_scores_gemma":[0.0023375018,0.00068939995,0.009921397,0.0003292303,0.00009050763,0.00003222471,0.0010602351,0.314719,0.45056012,0.014323701,0.20498756,0.0009491081],"about_ca_topic_score_codex":0.00000954946,"about_ca_topic_score_gemma":7.046183e-8,"teacher_disagreement_score":0.6337975,"about_ca_system_score_codex":0.000023072153,"about_ca_system_score_gemma":0.00000909739,"threshold_uncertainty_score":0.2790881},"labels":[],"label_agreement":null},{"id":"W3096891463","doi":"10.14778/3430915.3430932","title":"CoroBase","year":2020,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":25,"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; Pointer (user interface); Database transaction; Asynchronous communication; Database; Transaction processing system; Software; Operating system; Transaction processing; Online transaction processing; Distributed computing; Computer network; Computer hardware","score_opus":0.014720176867610645,"score_gpt":0.19351069959949013,"score_spread":0.17879052273187948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3096891463","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":[0.52674955,0.0017861458,0.093542024,0.15635428,0.0033091386,0.0037143049,0.00009422595,0.0013191297,0.2131312],"genre_scores_gemma":[0.99663997,0.0000056811746,0.0022213976,0.00093902386,0.00005573336,0.000015433436,2.0277547e-7,0.000004066959,0.0001185126],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991526,0.0000029773473,0.00019695461,0.00021023334,0.00028236213,0.00015484357],"domain_scores_gemma":[0.9995367,0.000008621962,0.00014960943,0.00011426645,0.00010742606,0.000083381645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010827522,0.000086789034,0.0001298423,0.000011832146,0.000058812595,0.000066337045,0.0011029061,0.000021499329,0.0000060385505],"category_scores_gemma":[0.00004551254,0.0000568854,0.00007715941,0.00032075692,0.000027472914,0.00020678712,0.00034770934,0.000073924806,0.000021151283],"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":[0.000033670913,0.00020451784,0.011123498,0.0003745813,0.00007969673,0.0000032521684,0.0041294633,0.00010258592,0.11786035,0.7482157,0.09986975,0.01800296],"study_design_scores_gemma":[0.0027996323,0.0005353163,0.011660825,0.00039968317,0.000045680423,0.00005084011,0.0005476307,0.053686135,0.6175923,0.008398377,0.30344492,0.00083864346],"about_ca_topic_score_codex":0.000011683012,"about_ca_topic_score_gemma":1.9631604e-7,"teacher_disagreement_score":0.7398173,"about_ca_system_score_codex":0.00001964322,"about_ca_system_score_gemma":0.00001739129,"threshold_uncertainty_score":0.23197193},"labels":[],"label_agreement":null},{"id":"W3111141572","doi":"10.14778/3461535.3461552","title":"Are we ready for learned cardinality estimation?","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":94,"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":"Cardinality (data modeling); Inference; Focus (optics); Ask price; Domain (mathematical analysis); Workload; Data modeling","score_opus":0.07254020723674541,"score_gpt":0.3182425928154698,"score_spread":0.24570238557872437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111141572","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":[0.03581718,0.0016343446,0.9190651,0.032550536,0.0015613487,0.0018495268,0.00020818209,0.00031656053,0.0069971997],"genre_scores_gemma":[0.6461959,0.000090101654,0.35057035,0.0003490755,0.00013767446,0.00028006246,0.0000072317566,0.000018385217,0.002351191],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99907386,0.0000068919903,0.00022608234,0.00027685726,0.0002479769,0.00016831793],"domain_scores_gemma":[0.9989714,0.00004187137,0.00032798277,0.00024464465,0.00037426865,0.000039829076],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025911038,0.000098469995,0.00018563331,0.000021399741,0.00014273918,0.000046186724,0.0003480255,0.000024538538,0.0000028020536],"category_scores_gemma":[0.00023383842,0.00006954681,0.00009262721,0.00020534465,0.000035075704,0.00038591787,0.00035587052,0.000057577625,0.000002549301],"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":[0.0000165635,0.00008967053,0.001611922,0.00051854615,0.000058557274,0.0000012719577,0.00069167797,0.00022171637,0.015134723,0.96336216,0.008120652,0.010172537],"study_design_scores_gemma":[0.001145771,0.00009789975,0.0031264147,0.00058612344,0.00005536728,0.000067407585,0.0016634879,0.0104529075,0.61151433,0.059330247,0.31153727,0.0004228036],"about_ca_topic_score_codex":0.000015139584,"about_ca_topic_score_gemma":0.0000033824444,"teacher_disagreement_score":0.90403193,"about_ca_system_score_codex":0.0000470658,"about_ca_system_score_gemma":0.00003588518,"threshold_uncertainty_score":0.28360367},"labels":[],"label_agreement":null},{"id":"W3112994038","doi":"10.14778/3436905.3436920","title":"Maximizing social welfare in a competitive diffusion model","year":2020,"lang":"en","type":"preprint","venue":"Proceedings of the VLDB Endowment","topic":"Mobile Crowdsensing and Crowdsourcing","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":"Competition (biology); Viral marketing; Computer science; Incentive; Maximization; Quality (philosophy); Social Welfare; Microeconomics; Focus (optics); Competitive equilibrium; Social network (sociolinguistics); Utility maximization; Utility maximization problem; Mathematical economics; Economics; Social media","score_opus":0.02382788169935284,"score_gpt":0.23324999598651466,"score_spread":0.20942211428716181,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3112994038","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":[0.84638715,0.00030233094,0.021170339,0.086299606,0.0016845338,0.003131159,0.000053105978,0.00063427055,0.040337514],"genre_scores_gemma":[0.98649395,0.000017768118,0.012978235,0.0002568088,0.00009638403,0.000068079586,0.0000014899088,0.00002560695,0.00006169189],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976949,0.00001956041,0.00051444926,0.0007629852,0.00062349206,0.00038458878],"domain_scores_gemma":[0.99890214,0.00002661851,0.00054744945,0.0002539635,0.00019279073,0.00007705649],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034167667,0.00034721347,0.00052538456,0.00014478425,0.00024922134,0.00023848459,0.0018566536,0.00019256456,0.0000027535668],"category_scores_gemma":[0.00008871257,0.00028102513,0.00028065918,0.00034127384,0.00008954394,0.00013758206,0.0055034836,0.0008540002,0.000001990237],"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":[0.00011871519,0.00066569046,0.0023209841,0.002452681,0.00017890325,0.000014542562,0.053469718,0.011193184,0.07917639,0.8307878,0.0018788915,0.017742546],"study_design_scores_gemma":[0.0016793971,0.00008377089,0.004054505,0.0018969048,0.00008286863,0.000018630179,0.002492832,0.85237515,0.04623341,0.089060985,0.000965306,0.0010562603],"about_ca_topic_score_codex":0.000088560846,"about_ca_topic_score_gemma":0.0000067486594,"teacher_disagreement_score":0.84118193,"about_ca_system_score_codex":0.0002534759,"about_ca_system_score_gemma":0.00009056122,"threshold_uncertainty_score":0.9999642},"labels":[],"label_agreement":null},{"id":"W3116457585","doi":"10.14778/3184470.3184473","title":"Distributed evaluation of subgraph queries using worst-case optimal low-memory dataflows","year":2018,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":70,"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":"Dataflow; Computer science; Computation; Memory footprint; Joins; Massively parallel; Graph; Parallel computing; Theoretical computer science; Distributed computing; Algorithm","score_opus":0.03065908720145722,"score_gpt":0.27186278200001407,"score_spread":0.24120369479855686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3116457585","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":[0.98613364,0.00008773525,0.012356245,0.000111252804,0.00039636865,0.00045277833,0.000035123343,0.000042837142,0.00038399763],"genre_scores_gemma":[0.98560834,0.000003871512,0.014248506,0.000026869846,0.00007127653,0.000019624753,0.0000024565963,0.000007867031,0.00001118666],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983817,0.000035348367,0.00036556873,0.0003188536,0.0006482508,0.000250301],"domain_scores_gemma":[0.998414,0.00003438453,0.00038440115,0.0003204366,0.00078540726,0.000061384664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015750446,0.00016035767,0.0001999588,0.00012113631,0.00022023726,0.000068327536,0.00092900306,0.000045620254,0.000020900527],"category_scores_gemma":[0.00014801974,0.00011771552,0.000118366515,0.0007308742,0.00033408141,0.00062423415,0.0005400721,0.000092781665,0.0000021552642],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046898215,0.0020768119,0.006718559,0.00089523976,0.00079708116,0.000026470825,0.02174058,0.0044213226,0.6214676,0.2684966,0.0018572331,0.07103355],"study_design_scores_gemma":[0.0010403418,0.00021481366,0.0007748189,0.00023167336,0.0001559275,0.00021844373,0.0010272999,0.20445865,0.77310735,0.018426128,0.00007391285,0.00027063125],"about_ca_topic_score_codex":0.00004552956,"about_ca_topic_score_gemma":0.0000027716414,"teacher_disagreement_score":0.25007048,"about_ca_system_score_codex":0.00005499443,"about_ca_system_score_gemma":0.00006536766,"threshold_uncertainty_score":0.48002994},"labels":[],"label_agreement":null},{"id":"W3129744650","doi":"10.14778/3436905.3436907","title":"Astrid","year":2020,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Substring; Computer science; Suffix; String (physics); Embedding; String searching algorithm; Suffix tree; Prefix; Theoretical computer science; Artificial intelligence; Algorithm; Pattern matching; Data structure; Mathematics","score_opus":0.23727257312021974,"score_gpt":0.3685803821593431,"score_spread":0.13130780903912334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3129744650","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":[0.43085164,0.00024410128,0.0015449723,0.23463301,0.0012367474,0.0018680387,0.00013247674,0.0001911545,0.32929784],"genre_scores_gemma":[0.99463326,0.000011536804,0.00085147464,0.003094351,0.00008625298,0.000012896247,5.447293e-7,0.000005221107,0.0013044851],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978124,0.000011695125,0.000443128,0.00029951116,0.0012725078,0.0001607695],"domain_scores_gemma":[0.99917275,0.00009041185,0.00029648736,0.00017408904,0.0001738307,0.00009240432],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013217991,0.000088944296,0.0001762848,0.000044756034,0.000079841324,0.00014072865,0.0016350687,0.00002013584,0.00025656924],"category_scores_gemma":[0.0017892872,0.000049946695,0.000118964046,0.0005834355,0.000075054166,0.00026496765,0.0009852855,0.000083488616,0.00022311318],"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":[0.000085641164,0.00013679477,0.0049301153,0.00006872585,0.000061068466,5.706894e-7,0.0026777708,0.000030874984,0.019813828,0.19976592,0.72573215,0.046696533],"study_design_scores_gemma":[0.00055762246,0.00014776093,0.0040365746,0.000026576838,0.000032281147,0.0000015618142,0.0038704344,0.0003229242,0.09918325,0.042425442,0.84923977,0.00015579663],"about_ca_topic_score_codex":0.000013649885,"about_ca_topic_score_gemma":9.058845e-7,"teacher_disagreement_score":0.56378156,"about_ca_system_score_codex":0.000017586028,"about_ca_system_score_gemma":0.000013401373,"threshold_uncertainty_score":0.30383915},"labels":[],"label_agreement":null},{"id":"W3133302368","doi":"10.14778/3436905.3436916","title":"Scalable mining of maximal quasi-cliques","year":2020,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":28,"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; Scalability; Clique; Load balancing (electrical power); Speedup; Vertex (graph theory); Graph; Theoretical computer science; Parallel computing; Combinatorics; Mathematics; Database","score_opus":0.02458840115704153,"score_gpt":0.23857404697814444,"score_spread":0.2139856458211029,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3133302368","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":[0.838084,0.0005889855,0.064703874,0.05366145,0.00042061394,0.0014685529,0.000091558024,0.0005106172,0.040470365],"genre_scores_gemma":[0.8645822,0.000017900727,0.13491927,0.0003034072,0.000045169072,0.00002960682,6.562806e-7,0.000006717899,0.000095068805],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991196,0.0000029521643,0.0002468928,0.00022930832,0.00025373464,0.00014750999],"domain_scores_gemma":[0.99943054,0.00002338798,0.00021637754,0.00014672648,0.00012119171,0.00006180488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016608651,0.000085478365,0.00015005335,0.000026013542,0.0000619162,0.000049493097,0.0011860491,0.000022360124,0.0000068860786],"category_scores_gemma":[0.000066035165,0.00006184247,0.000062301115,0.0003678818,0.00005480744,0.00025651252,0.0005986982,0.00006337939,0.00000532019],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029044208,0.000827283,0.012678753,0.0006134823,0.00015975627,8.8659743e-7,0.014803257,0.000031424646,0.2912116,0.40322495,0.046570268,0.22984932],"study_design_scores_gemma":[0.000681178,0.0005609812,0.0041714613,0.00022427073,0.0000421252,0.000010831112,0.0009878761,0.07152831,0.89771265,0.0045671924,0.019189823,0.00032329818],"about_ca_topic_score_codex":0.000026902802,"about_ca_topic_score_gemma":2.2447796e-7,"teacher_disagreement_score":0.60650104,"about_ca_system_score_codex":0.000013760361,"about_ca_system_score_gemma":0.00002550283,"threshold_uncertainty_score":0.25218627},"labels":[],"label_agreement":null},{"id":"W3138240437","doi":"10.14778/3407790.3407806","title":"Knowledge translation","year":2020,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Semantic Web and Ontologies","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":"University of Toronto","funders":"","keywords":"Computer science; Heuristics; SPARQL; Set (abstract data type); Ranking (information retrieval); Information retrieval; Translation (biology); Rank (graph theory); Semantic mapping; Natural language processing; Artificial intelligence; Data mining; Semantic Web; RDF; Programming language; Mathematics","score_opus":0.08498789382318941,"score_gpt":0.2627009697317941,"score_spread":0.17771307590860466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138240437","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":[0.49101648,0.0044311294,0.058806453,0.16562808,0.0018371359,0.0020619964,0.0000044846006,0.001152321,0.27506194],"genre_scores_gemma":[0.99101156,0.00001614763,0.00856821,0.00029948592,0.000046910463,0.0000083939685,5.5697132e-8,0.0000029641662,0.000046248464],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99943197,0.0000030956119,0.00013784971,0.00016062637,0.00015105575,0.00011541297],"domain_scores_gemma":[0.9997293,0.000026499041,0.0000745946,0.00007108568,0.00006170494,0.00003686962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009419574,0.000068062414,0.00009712015,0.000018712573,0.000047451707,0.000038765134,0.0007918405,0.000021948757,0.000004147763],"category_scores_gemma":[0.000053866,0.000043517444,0.00006411762,0.00024464724,0.00002938554,0.00019096483,0.00017770035,0.00005719724,0.000014031193],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003632313,0.0002137757,0.008261106,0.0003951079,0.00008272687,7.4841927e-7,0.03454797,0.000025837357,0.2274045,0.5295998,0.014911184,0.1845209],"study_design_scores_gemma":[0.0010422128,0.00025762265,0.008925303,0.000088372275,0.00003659886,0.000009497584,0.0007331523,0.027213762,0.9068916,0.020455522,0.03404786,0.00029852858],"about_ca_topic_score_codex":0.000004520957,"about_ca_topic_score_gemma":6.374464e-7,"teacher_disagreement_score":0.67948705,"about_ca_system_score_codex":0.000011192641,"about_ca_system_score_gemma":0.000015043131,"threshold_uncertainty_score":0.17745899},"labels":[],"label_agreement":null},{"id":"W3142663085","doi":"10.14778/3447689.3447695","title":"On the string matching with <i>k</i> differences in DNA databases","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Algorithms and Data Compression","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 Winnipeg","funders":"","keywords":"Substring; Suffix tree; String (physics); String searching algorithm; Combinatorics; Pattern matching; Trie; Bounded function; Speedup; Sequence (biology); Tree (set theory); Computer science; Alphabet; Matching (statistics); Time complexity; Mathematics; Algorithm; Data structure; Artificial intelligence; Parallel computing; Biology","score_opus":0.024683335890819752,"score_gpt":0.22047070030775745,"score_spread":0.1957873644169377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3142663085","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":[0.98898023,0.00011579279,0.005643086,0.0028676793,0.00014116148,0.00021221914,0.000009052142,0.000033502885,0.0019972513],"genre_scores_gemma":[0.99356633,0.00003165136,0.0060198735,0.00026795556,0.000021447473,0.000020509593,7.479634e-7,0.000004473598,0.000067020985],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99900717,0.00001092691,0.00015349693,0.00026412067,0.00039173407,0.00017255539],"domain_scores_gemma":[0.99941444,0.00012675555,0.00011894208,0.0002559141,0.000057187324,0.00002673627],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020715961,0.000106078296,0.00012342719,0.000031351323,0.00013021866,0.00012367564,0.00092454656,0.000011923561,0.000007891535],"category_scores_gemma":[0.000045605077,0.000047999467,0.00002947785,0.00031231588,0.000033993238,0.00033007108,0.0008947942,0.000143876,0.0000017556042],"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":[0.00003536715,0.00036875118,0.013821284,0.0000956593,0.000042087162,0.00000960576,0.0020853607,0.00007842822,0.04198414,0.9297407,0.0018799346,0.0098586725],"study_design_scores_gemma":[0.0013334011,0.00023103174,0.035562817,0.002769536,0.000026882808,0.00006431035,0.002456913,0.008515589,0.89671326,0.049749915,0.0020413075,0.00053502707],"about_ca_topic_score_codex":0.0000723674,"about_ca_topic_score_gemma":0.000011594631,"teacher_disagreement_score":0.8799908,"about_ca_system_score_codex":0.000024755931,"about_ca_system_score_gemma":0.000032156273,"threshold_uncertainty_score":0.19573614},"labels":[],"label_agreement":null},{"id":"W3145740377","doi":"10.14778/3447689.3447700","title":"Dealer","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":82,"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":"Sensitivity (control systems); Computer science; Revenue; Function (biology); Differential privacy; Value (mathematics); Set (abstract data type); Artificial intelligence; Machine learning; Algorithm; Economics","score_opus":0.02334067523738829,"score_gpt":0.2458582682426131,"score_spread":0.2225175930052248,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3145740377","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":[0.3983595,0.002211594,0.022583565,0.44697264,0.002904201,0.0011731624,0.000031291624,0.002296425,0.12346761],"genre_scores_gemma":[0.73456985,0.000095345495,0.2643981,0.00045679824,0.000033299173,0.000031885385,5.7324326e-7,0.000009679732,0.00040447825],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99884236,0.0000051560473,0.00019743163,0.00033626563,0.00037616128,0.0002426046],"domain_scores_gemma":[0.99744624,0.00003642539,0.0001407056,0.0021455123,0.00019757215,0.000033560267],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00024483431,0.00010362028,0.00012924905,0.00004507489,0.00008152426,0.00009307819,0.019368498,0.000051152834,0.00001682845],"category_scores_gemma":[0.005576262,0.00007407057,0.0000735337,0.0005515668,0.00007073227,0.00035496082,0.08382558,0.00015303341,0.000015408994],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000049679807,0.00020520625,0.008174485,0.00012920755,0.00008151966,0.000005918305,0.00022100635,0.0000024218045,0.1586717,0.20351249,0.6021311,0.02685996],"study_design_scores_gemma":[0.00017196199,0.000017989003,0.0016633614,0.000056275923,0.0000067799983,0.000029878249,0.00004982042,0.0016243694,0.7067502,0.2792879,0.010239441,0.00010197991],"about_ca_topic_score_codex":0.000009155411,"about_ca_topic_score_gemma":9.919974e-7,"teacher_disagreement_score":0.59189165,"about_ca_system_score_codex":0.00006112171,"about_ca_system_score_gemma":0.000044587978,"threshold_uncertainty_score":0.9859372},"labels":[],"label_agreement":null},{"id":"W3151791879","doi":"10.14778/3447689.3447713","title":"FREDE","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Optech (Canada)","funders":"","keywords":"Computer science","score_opus":0.007135979711530603,"score_gpt":0.22110637753027845,"score_spread":0.21397039781874785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3151791879","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":[0.98165417,0.0012366697,0.00005222753,0.0003941248,0.0001367233,0.000087046355,0.0000040496197,0.0000037990317,0.01643118],"genre_scores_gemma":[0.9969527,0.00025899993,0.0010129069,0.0000862952,0.00009744795,0.000009574878,0.0000051893926,0.000008070748,0.0015688165],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999506,0.000003864516,0.00012039322,0.00014973887,0.00012026689,0.00009972723],"domain_scores_gemma":[0.99963975,0.000002780051,0.00007484828,0.00009961267,0.00015651737,0.000026484031],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000094412324,0.000062468236,0.000063895706,0.000009670089,0.000041530526,0.000013257062,0.00013238181,0.00004406875,0.00001566676],"category_scores_gemma":[0.00008647285,0.000046468558,0.00007396725,0.000071754366,0.000027519009,0.0000014819548,0.00016381415,0.0000346277,0.0000019216516],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005909965,0.00003200573,0.0062702238,0.000014343063,0.000018782423,1.0292719e-7,0.000028232918,0.000008634661,0.9911825,0.0008348494,0.00062242214,0.0009819835],"study_design_scores_gemma":[0.00016640143,0.000038789156,0.0035254927,0.000009608531,0.000011525564,0.0000026493308,0.00005221244,0.0000067405354,0.97040683,0.0011984173,0.024527285,0.000054029773],"about_ca_topic_score_codex":0.0000042916554,"about_ca_topic_score_gemma":0.0000024795556,"teacher_disagreement_score":0.023904864,"about_ca_system_score_codex":0.000007437804,"about_ca_system_score_gemma":0.000026512027,"threshold_uncertainty_score":0.18949328},"labels":[],"label_agreement":null},{"id":"W3161742868","doi":"10.14778/3529337.3529339","title":"Accurate summary-based cardinality estimation through the lens of cardinality estimation graphs","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":19,"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":"Estimator; Cardinality (data modeling); Graph; Mathematics; Computer science; Joins; Statistics; Mathematical optimization; Theoretical computer science; Data mining","score_opus":0.026187567913794885,"score_gpt":0.2648038244692834,"score_spread":0.23861625655548852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3161742868","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":[0.18143903,0.00071999227,0.80042106,0.007915283,0.0013669381,0.0027482035,0.00044610634,0.00024149622,0.0047019226],"genre_scores_gemma":[0.96529347,0.0000099486615,0.0343011,0.00013153933,0.000016034519,0.00019598211,0.0000101212745,0.000008275033,0.00003355623],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99808776,0.000068511334,0.0004946308,0.00032802226,0.00079803116,0.00022305691],"domain_scores_gemma":[0.9984455,0.000099321114,0.0007158389,0.00046831055,0.0002446408,0.000026370639],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010711838,0.00016995796,0.000288403,0.00004898074,0.00051505456,0.00003801413,0.000892233,0.000023142706,0.0000062093013],"category_scores_gemma":[0.0001352125,0.00010842681,0.00020466332,0.0006465326,0.00015071424,0.0008298625,0.0007333257,0.00017891942,8.179958e-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":[0.000081458085,0.00018109482,0.0021688442,0.00050361996,0.000116064,6.1697295e-7,0.003263824,0.08446805,0.008137811,0.8946987,0.0025409972,0.0038389657],"study_design_scores_gemma":[0.0029605443,0.00088684884,0.018867863,0.00062088744,0.00037864246,0.00007344085,0.004741607,0.45860603,0.3121204,0.14939964,0.05008564,0.0012584259],"about_ca_topic_score_codex":0.000629028,"about_ca_topic_score_gemma":0.0000043904047,"teacher_disagreement_score":0.7838544,"about_ca_system_score_codex":0.00013517903,"about_ca_system_score_gemma":0.000080137725,"threshold_uncertainty_score":0.4421517},"labels":[],"label_agreement":null},{"id":"W3164690045","doi":"10.14778/3457390.3457398","title":"CBench","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Topic Modeling","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Question answering; Benchmark (surveying); Benchmarking; Suite; Set (abstract data type); Vocabulary; Information retrieval; Syntax; Graph; Artificial intelligence; Task (project management); Natural language processing; Theoretical computer science; Programming language","score_opus":0.01596362296791629,"score_gpt":0.2186539506523365,"score_spread":0.20269032768442022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164690045","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":[0.75457007,0.0011547001,0.058939986,0.027196297,0.0022635008,0.0006213855,0.0000025624104,0.00031870746,0.15493278],"genre_scores_gemma":[0.9619998,0.000016257269,0.036558054,0.00032200277,0.00004904496,0.000010957895,7.134994e-8,0.00000396651,0.0010398967],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991588,0.0000032863743,0.00016270323,0.000225817,0.00029204946,0.00015732025],"domain_scores_gemma":[0.99949545,0.000013807881,0.0000852946,0.00020559426,0.00016482269,0.00003500634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001529272,0.00006907214,0.000093591865,0.000022735967,0.00005942242,0.00006378667,0.00081843877,0.000022546657,0.0000138682135],"category_scores_gemma":[0.00006304325,0.000049005088,0.00006871177,0.0002452701,0.00001739739,0.00018203243,0.0006900905,0.00007648387,0.000007355087],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002173103,0.00011431626,0.0046632974,0.000086841246,0.00003529016,0.0000022157615,0.0015862242,0.000083198065,0.16363892,0.80180866,0.0030024908,0.024976382],"study_design_scores_gemma":[0.00032694335,0.000024447225,0.0018903445,0.000083026585,0.00001121015,0.000043355907,0.00017193986,0.011714133,0.93195933,0.044555016,0.0090687,0.00015155114],"about_ca_topic_score_codex":0.000010253595,"about_ca_topic_score_gemma":7.709086e-7,"teacher_disagreement_score":0.76832044,"about_ca_system_score_codex":0.00003456443,"about_ca_system_score_gemma":0.000040816067,"threshold_uncertainty_score":0.19983694},"labels":[],"label_agreement":null},{"id":"W3168854329","doi":"10.14778/3467861.3467872","title":"Data acquisition for improving machine learning models","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":37,"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":"Data acquisition; Process (computing); Data modeling; Online machine learning; Knowledge acquisition; Training set; Annotation; Data integration; Supervised learning","score_opus":0.28485107715764413,"score_gpt":0.3865902747486838,"score_spread":0.10173919759103967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3168854329","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":[0.34090647,0.0057663396,0.42422983,0.08517427,0.0057165683,0.008959401,0.006814382,0.00065220817,0.12178054],"genre_scores_gemma":[0.9832612,0.000044959266,0.01113982,0.0006037925,0.00009906612,0.000044733228,0.00009258271,0.000013597734,0.0047002416],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997707,0.000024167575,0.0005174584,0.0005506269,0.0009839372,0.00021679357],"domain_scores_gemma":[0.99829924,0.00023395833,0.00042211078,0.00053675455,0.0004596683,0.00004828629],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003924377,0.00011057221,0.00020817966,0.00007268613,0.00023440333,0.0002969926,0.0018212791,0.000032396198,0.00006977861],"category_scores_gemma":[0.0020432211,0.000072175,0.000098573946,0.00036925025,0.000045768316,0.0009666055,0.0027392702,0.00010470805,0.000010632699],"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":[0.00027277885,0.0006811334,0.0018762513,0.0006955244,0.0002340544,0.0000021070473,0.0024178128,0.002590723,0.12323816,0.51967067,0.08047108,0.26784968],"study_design_scores_gemma":[0.001653374,0.00015896161,0.00046786,0.0001174401,0.00018600131,0.000012674619,0.006433871,0.34921727,0.09174051,0.3349099,0.21471637,0.00038579613],"about_ca_topic_score_codex":0.00004646267,"about_ca_topic_score_gemma":0.000017219705,"teacher_disagreement_score":0.6423547,"about_ca_system_score_codex":0.000037372865,"about_ca_system_score_gemma":0.000034403554,"threshold_uncertainty_score":0.34143046},"labels":[],"label_agreement":null},{"id":"W3176539131","doi":"10.14778/3467861.3467876","title":"Kamino","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":20,"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; Differential privacy; Tuple; Data mining; Schema (genetic algorithms); Publication; Data integrity; Data structure; Probabilistic logic; Database; Information retrieval; Artificial intelligence","score_opus":0.022339782567990962,"score_gpt":0.24248893966061258,"score_spread":0.22014915709262162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176539131","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":[0.43674234,0.0023225048,0.019918049,0.40723386,0.0032661706,0.0012125276,0.0000362396,0.0024617864,0.12680653],"genre_scores_gemma":[0.7731489,0.000090144385,0.22586387,0.00037615167,0.000034634028,0.00003058393,6.403772e-7,0.000009428869,0.0004456341],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987947,0.0000049765686,0.00020564518,0.00035254637,0.00039427535,0.0002478934],"domain_scores_gemma":[0.9972964,0.00003763902,0.00015019196,0.0022867208,0.00019552643,0.00003351479],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00023804406,0.00010870805,0.00013626169,0.000047889032,0.00008409929,0.00010105869,0.020970901,0.00005240036,0.000014466364],"category_scores_gemma":[0.006290858,0.000078442805,0.00007628239,0.00057608524,0.00007763833,0.00037658314,0.08977445,0.00015697085,0.0000151634],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000048467778,0.00023345841,0.006955541,0.00014479375,0.000082729995,0.0000068014306,0.00025241458,0.0000018821733,0.21897338,0.22226237,0.51972353,0.031358242],"study_design_scores_gemma":[0.00016065993,0.000019938543,0.0014086881,0.000053559124,0.0000066148077,0.000029731471,0.000057234753,0.0015667899,0.7386775,0.25000262,0.007919598,0.00009703304],"about_ca_topic_score_codex":0.000008956824,"about_ca_topic_score_gemma":7.8518485e-7,"teacher_disagreement_score":0.51970416,"about_ca_system_score_codex":0.00006461734,"about_ca_system_score_gemma":0.00004457947,"threshold_uncertainty_score":0.9843261},"labels":[],"label_agreement":null},{"id":"W3184011463","doi":"10.14778/3476249.3476263","title":"LES <sup>3</sup>","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management 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; York University","funders":"","keywords":"Search engine indexing; Computer science; Set (abstract data type); Pruning; Similarity (geometry); Bitmap; Nearest neighbor search; Representation (politics); Data mining; Encoding (memory); Theoretical computer science; Artificial intelligence","score_opus":0.01984668302522739,"score_gpt":0.22997774859488967,"score_spread":0.2101310655696623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3184011463","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":[0.34659728,0.0020105797,0.03541348,0.045955215,0.0020503171,0.0019012189,0.000046191602,0.00096238375,0.56506336],"genre_scores_gemma":[0.94843084,0.00010246688,0.043038886,0.0005595953,0.00013872118,0.000036563895,0.0000027973247,0.000013516567,0.0076766056],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99894786,0.000004928912,0.00018116944,0.00029035614,0.0003673373,0.0002083744],"domain_scores_gemma":[0.99945295,0.000016022357,0.00010180446,0.0002522951,0.00013601128,0.000040902294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020417517,0.00010676496,0.000121298144,0.0000437259,0.00011113545,0.00019065813,0.0013533733,0.000022704799,0.0000346441],"category_scores_gemma":[0.00004950829,0.00007519621,0.000088331086,0.00040427956,0.00003617477,0.00048015616,0.0014690756,0.00008473796,0.000020600184],"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":[0.0000049259834,0.0002914217,0.0039258767,0.00017901765,0.0001239182,0.000006568027,0.001500877,0.00008233967,0.00863394,0.7888961,0.035746675,0.16060835],"study_design_scores_gemma":[0.0017072883,0.00015627303,0.0068930225,0.00031996964,0.000100060424,0.00005638725,0.0017209504,0.049378242,0.5445997,0.044723555,0.3495947,0.0007498518],"about_ca_topic_score_codex":0.000023651035,"about_ca_topic_score_gemma":6.1175916e-7,"teacher_disagreement_score":0.7441725,"about_ca_system_score_codex":0.000031404317,"about_ca_system_score_gemma":0.000017344935,"threshold_uncertainty_score":0.30664122},"labels":[],"label_agreement":null},{"id":"W3193493045","doi":"10.14778/3510397.3510400","title":"Making RDBMSs efficient on graph workloads through predefined joins","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","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":"Joins; Computer science; Relational database management system; Hash function; Tuple; Graph; Theoretical computer science; Database; Relational database; Parallel computing; Data mining; Programming language","score_opus":0.03152427770464434,"score_gpt":0.2577984677144628,"score_spread":0.22627419000981847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3193493045","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":[0.62613016,0.0026580144,0.21189597,0.014520136,0.008615957,0.006298223,0.0003087243,0.0014116226,0.12816119],"genre_scores_gemma":[0.9791439,0.000012153151,0.01970851,0.0004622788,0.000052410374,0.00023724207,0.0000011688462,0.000015183979,0.00036710646],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99810785,0.000017284192,0.00033677692,0.00043362848,0.0007684211,0.00033605806],"domain_scores_gemma":[0.9991365,0.000039882925,0.0003499764,0.00036042623,0.00007702898,0.000036201855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036409707,0.00018439937,0.00021560803,0.00008399521,0.00055375963,0.000048037095,0.0010405282,0.000019775967,0.00003463975],"category_scores_gemma":[0.000044430155,0.00013143769,0.0001434302,0.0006957361,0.000062393425,0.00021089878,0.0016756979,0.00021547012,0.000006557785],"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":[0.000045446144,0.00024119149,0.00039330978,0.000071743976,0.000036735182,0.0000018149368,0.0028360095,0.005117445,0.007910102,0.97815347,0.0032654973,0.0019272632],"study_design_scores_gemma":[0.004692939,0.002467755,0.0043585375,0.0016496216,0.00011670852,0.0002891181,0.0077518835,0.017933708,0.3229144,0.048298176,0.5872843,0.0022428741],"about_ca_topic_score_codex":0.000026301277,"about_ca_topic_score_gemma":9.923156e-7,"teacher_disagreement_score":0.9298553,"about_ca_system_score_codex":0.00014257309,"about_ca_system_score_gemma":0.000032529275,"threshold_uncertainty_score":0.5359874},"labels":[],"label_agreement":null},{"id":"W3196580506","doi":"10.14778/3476249.3476297","title":"Columnar storage and list-based processing for graph database management systems","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":25,"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; Joins; Scalability; Column (typography); Query optimization; Graph; Block (permutation group theory); Parallel computing; Online aggregation; Database; Relational database management system; Theoretical computer science; Sargable; Relational database; Information retrieval; Web search query; Programming language; Search engine","score_opus":0.013402134967230724,"score_gpt":0.2220701710286801,"score_spread":0.20866803606144937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196580506","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":[0.30107942,0.008278761,0.6648469,0.005392474,0.00289085,0.0065645333,0.000193229,0.0006107772,0.010143074],"genre_scores_gemma":[0.9573745,0.00003433738,0.041664388,0.00018869119,0.000040286955,0.00023281283,0.0000031790228,0.000013296497,0.00044850408],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987713,0.000012391002,0.00025003363,0.0004086676,0.00030729818,0.0002502993],"domain_scores_gemma":[0.99924403,0.000039445356,0.00019843991,0.0002208664,0.00022544364,0.00007174418],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054798473,0.00014659438,0.00018335921,0.000085254855,0.00026111686,0.0002699175,0.00064266345,0.000028740133,0.0000015299933],"category_scores_gemma":[0.000028862167,0.0001138115,0.00008518967,0.00046294695,0.00007518876,0.00032870655,0.00040144735,0.000074008945,4.3878745e-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":[0.00007730276,0.00066099793,0.0012396101,0.006229311,0.00019693412,0.000014244972,0.0012897067,0.00033107813,0.05124158,0.9146512,0.0026312515,0.021436743],"study_design_scores_gemma":[0.008384937,0.00064266054,0.0019689878,0.0043749367,0.0004950598,0.00017439011,0.005358085,0.29811662,0.566676,0.08850939,0.023574155,0.0017247736],"about_ca_topic_score_codex":0.0000063030034,"about_ca_topic_score_gemma":8.755884e-7,"teacher_disagreement_score":0.82614183,"about_ca_system_score_codex":0.000029245404,"about_ca_system_score_gemma":0.000032076077,"threshold_uncertainty_score":0.46410984},"labels":[],"label_agreement":null},{"id":"W3196792859","doi":"10.14778/3476311.3476335","title":"Demonstration of dealer","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":16,"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":"Revenue; Variety (cybernetics); Quality (philosophy); Computer science; Business; Artificial intelligence; Finance","score_opus":0.023331209508722677,"score_gpt":0.24659098665221155,"score_spread":0.22325977714348888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196792859","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":[0.77274275,0.0010837342,0.039844442,0.11768635,0.0011498012,0.00089637295,0.000027836568,0.0006993766,0.06586934],"genre_scores_gemma":[0.83591765,0.00004948858,0.1638717,0.00006289394,0.000010541444,0.000011485001,4.9983186e-7,0.000003825736,0.00007192547],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990401,0.0000052825535,0.00024177536,0.00023096004,0.00033313816,0.00014869538],"domain_scores_gemma":[0.998134,0.000034776385,0.00022158254,0.001343713,0.00024583322,0.000020068563],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00023816136,0.000078394216,0.00012458842,0.00004615669,0.000035862384,0.000036558213,0.009823031,0.000047827703,0.000006304731],"category_scores_gemma":[0.0030085605,0.00005843032,0.0000602257,0.0004605957,0.00007985611,0.0003268236,0.028563092,0.0000998556,0.0000024073292],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000068665695,0.0002219117,0.016600532,0.00019885201,0.00007288542,0.0000015358885,0.00022323043,0.0000061626974,0.61665875,0.23381782,0.106566384,0.025625061],"study_design_scores_gemma":[0.00012604237,0.000021775566,0.001965832,0.00006039324,0.0000070198676,0.000012175119,0.00005294907,0.002040293,0.86076885,0.13434109,0.0005470718,0.00005647978],"about_ca_topic_score_codex":0.0000102501945,"about_ca_topic_score_gemma":0.0000014740185,"teacher_disagreement_score":0.2441101,"about_ca_system_score_codex":0.000036745783,"about_ca_system_score_gemma":0.000049137456,"threshold_uncertainty_score":0.9955343},"labels":[],"label_agreement":null},{"id":"W3196867679","doi":"10.14778/3476311.3476364","title":"RONIN","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University; University of Toronto","funders":"","keywords":"Computer science; Information retrieval; Set (abstract data type); Data mining; Focus (optics); Nearest neighbor search; Data set; Artificial intelligence","score_opus":0.1406382432299656,"score_gpt":0.3809184801512673,"score_spread":0.24028023692130168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196867679","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":[0.4804395,0.00058951386,0.00048333433,0.04221652,0.0016395466,0.00068538205,0.00006042078,0.00007851747,0.47380725],"genre_scores_gemma":[0.9762882,0.000035285226,0.0014249325,0.0010451176,0.000056120527,0.00001783146,0.0000011813275,0.0000058426594,0.021125503],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99779195,0.000018119796,0.0004320659,0.0003129895,0.0012682908,0.00017660054],"domain_scores_gemma":[0.99891376,0.00011885011,0.00024745948,0.0003046986,0.0003657482,0.00004950802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019107901,0.00008340477,0.00017131149,0.00005737561,0.000101211415,0.00018480327,0.0011014874,0.000024018727,0.00047268005],"category_scores_gemma":[0.0016489527,0.000048975202,0.0001284088,0.00059782196,0.00007221659,0.00024800588,0.0011062807,0.000075980824,0.00013896008],"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":[0.000024271416,0.00030152552,0.0062036165,0.000052082636,0.00007166926,0.0000021839644,0.0012425383,0.000020623087,0.02952056,0.55710566,0.35787448,0.047580805],"study_design_scores_gemma":[0.00037321,0.000032629538,0.0074127265,0.000041000363,0.00002726179,0.000007480076,0.0040583415,0.000064022934,0.26923838,0.13959633,0.5790274,0.00012121171],"about_ca_topic_score_codex":0.000020487536,"about_ca_topic_score_gemma":0.000009381887,"teacher_disagreement_score":0.4958487,"about_ca_system_score_codex":0.00003358756,"about_ca_system_score_gemma":0.000031696378,"threshold_uncertainty_score":0.5175515},"labels":[],"label_agreement":null},{"id":"W3196877232","doi":"10.14778/3476311.3476317","title":"A demonstration of KGLac","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":21,"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":"Computer science; SPARQL; Metadata; Data science; Knowledge graph; Knowledge extraction; Data discovery; Information retrieval; Pipeline (software); Annotation; RDF; Graph; World Wide Web; Data mining; Semantic Web; Artificial intelligence; Theoretical computer science","score_opus":0.12604269999402856,"score_gpt":0.37172051449046417,"score_spread":0.2456778144964356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196877232","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":[0.752775,0.00025877618,0.0010402,0.013215906,0.0006407837,0.0005654376,0.000053638738,0.00002856534,0.23142166],"genre_scores_gemma":[0.9949608,0.000025744577,0.0015046119,0.00021119443,0.00002210992,0.000009580924,0.0000011715498,0.0000029822577,0.0032617946],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980476,0.000018376948,0.0005238903,0.0002214717,0.0010781497,0.00011051998],"domain_scores_gemma":[0.9987438,0.00011703688,0.00039328376,0.0002242978,0.00049047504,0.00003111715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017312103,0.0000661122,0.0001712227,0.00006345713,0.000043499804,0.00007060956,0.00065499276,0.000023855804,0.00012968972],"category_scores_gemma":[0.0010943022,0.000040826413,0.000111771624,0.0005520632,0.00008383944,0.0002395424,0.0004812306,0.00005070557,0.000018175544],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045631707,0.00042810192,0.013169458,0.00012618996,0.00008606206,8.153006e-7,0.0015818576,0.000027108743,0.16656572,0.6959935,0.075051084,0.04692447],"study_design_scores_gemma":[0.0004344225,0.000060633625,0.01036923,0.00007540858,0.000045366036,0.000005692648,0.0055575883,0.00013184437,0.8172494,0.1126685,0.05329797,0.00010390501],"about_ca_topic_score_codex":0.00002185203,"about_ca_topic_score_gemma":0.000011768813,"teacher_disagreement_score":0.6506837,"about_ca_system_score_codex":0.0000187178,"about_ca_system_score_gemma":0.000035934336,"threshold_uncertainty_score":0.16648528},"labels":[],"label_agreement":null},{"id":"W3197016261","doi":"10.14778/3476311.3476326","title":"CBench","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Topic Modeling","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":"Carleton University","funders":"","keywords":"Computer science; Benchmarking; Suite; Benchmark (surveying); Question answering; Set (abstract data type); Task (project management); Quality (philosophy); Artificial intelligence; Information retrieval; Natural language processing; Programming language; Systems engineering","score_opus":0.01596362296791629,"score_gpt":0.2186539506523365,"score_spread":0.20269032768442022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197016261","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":[0.75457007,0.0011547001,0.058939986,0.027196297,0.0022635008,0.0006213855,0.0000025624104,0.00031870746,0.15493278],"genre_scores_gemma":[0.9619998,0.000016257269,0.036558054,0.00032200277,0.00004904496,0.000010957895,7.134994e-8,0.00000396651,0.0010398967],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991588,0.0000032863743,0.00016270323,0.000225817,0.00029204946,0.00015732025],"domain_scores_gemma":[0.99949545,0.000013807881,0.0000852946,0.00020559426,0.00016482269,0.00003500634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001529272,0.00006907214,0.000093591865,0.000022735967,0.00005942242,0.00006378667,0.00081843877,0.000022546657,0.0000138682135],"category_scores_gemma":[0.00006304325,0.000049005088,0.00006871177,0.0002452701,0.00001739739,0.00018203243,0.0006900905,0.00007648387,0.000007355087],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002173103,0.00011431626,0.0046632974,0.000086841246,0.00003529016,0.0000022157615,0.0015862242,0.000083198065,0.16363892,0.80180866,0.0030024908,0.024976382],"study_design_scores_gemma":[0.00032694335,0.000024447225,0.0018903445,0.000083026585,0.00001121015,0.000043355907,0.00017193986,0.011714133,0.93195933,0.044555016,0.0090687,0.00015155114],"about_ca_topic_score_codex":0.000010253595,"about_ca_topic_score_gemma":7.709086e-7,"teacher_disagreement_score":0.76832044,"about_ca_system_score_codex":0.00003456443,"about_ca_system_score_gemma":0.000040816067,"threshold_uncertainty_score":0.19983694},"labels":[],"label_agreement":null},{"id":"W3197536806","doi":"10.14778/3476311.3476394","title":"The future of data(base) education","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","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 British Columbia","funders":"","keywords":"Popularity; Field (mathematics); Computer science; Mathematics education; Position (finance); Base (topology); Core (optical fiber); Data science; Psychology; Mathematics","score_opus":0.05319081169306056,"score_gpt":0.2876094141118519,"score_spread":0.23441860241879137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197536806","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":[0.6964943,0.019886,0.00019868056,0.09681054,0.012775706,0.0021011145,0.00013118554,0.00018393736,0.17141853],"genre_scores_gemma":[0.9954842,0.00046399355,0.0004266008,0.00078993844,0.0016278622,0.000020579764,0.000044154043,0.000014564881,0.0011281096],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99906594,0.0000016109567,0.00025716316,0.00021320565,0.00031957508,0.00014251046],"domain_scores_gemma":[0.9986303,0.000020641432,0.00035399434,0.00037123123,0.00061799394,0.0000058686237],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003179219,0.00010067014,0.00011568275,0.000037527127,0.00017690062,0.00014766064,0.0011227452,0.000032689393,0.00008041129],"category_scores_gemma":[0.00013855514,0.00005620828,0.00005089343,0.0005147562,0.00008264737,0.0008827821,0.0009896638,0.00008837738,0.000016015358],"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":[0.000058791113,0.000499194,0.015873836,0.0011628785,0.000088486784,3.6231643e-7,0.0000955167,0.00000321667,0.036190126,0.4312833,0.22335672,0.29138756],"study_design_scores_gemma":[0.00013732126,0.0000037120788,0.0050028367,0.00020768677,0.00009663418,0.000005806194,0.0020892327,0.00020356129,0.04898689,0.011482052,0.9316545,0.0001297328],"about_ca_topic_score_codex":0.00010666433,"about_ca_topic_score_gemma":0.000034344663,"teacher_disagreement_score":0.7082978,"about_ca_system_score_codex":0.000014100526,"about_ca_system_score_gemma":0.000068695095,"threshold_uncertainty_score":0.22921072},"labels":[],"label_agreement":null},{"id":"W3198515637","doi":"10.14778/3476249.3476283","title":"SlimChain","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Blockchain Technology Applications and Security","field":"Computer Science","cited_by":143,"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; Blockchain; Scalability; Distributed computing; Database transaction; Computer network; Robustness (evolution); Distributed data store; Node (physics); Computer security; Database","score_opus":0.007848441708610996,"score_gpt":0.20753097551931157,"score_spread":0.19968253381070059,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3198515637","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":[0.8050135,0.0016333768,0.0297914,0.093431175,0.0007254562,0.00095120823,0.0000070364777,0.0007373251,0.06770957],"genre_scores_gemma":[0.9825384,0.00003128308,0.016678011,0.00030715653,0.000015931759,0.000044771827,1.341835e-7,0.0000032553214,0.00038102453],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993379,0.000003078526,0.00014217329,0.00021385195,0.00016329768,0.00013970872],"domain_scores_gemma":[0.99944717,0.000014887696,0.00009312364,0.00025752847,0.00016199518,0.000025326266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016279379,0.00006597559,0.00009182382,0.00003088128,0.00009842859,0.000030182458,0.0009497809,0.00004653624,0.000008127463],"category_scores_gemma":[0.000043509244,0.000047849604,0.00006192339,0.00046602834,0.000054508066,0.00007211336,0.00068401906,0.000108761626,0.0000067280694],"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":[5.0575426e-7,0.00007241115,0.00067257014,0.000012723174,0.000010834795,2.9861937e-7,0.0002218188,9.3073265e-7,0.035157885,0.95569056,0.0015278172,0.0066316514],"study_design_scores_gemma":[0.00017838718,0.000017983286,0.0012114798,0.000019320722,0.0000065534523,0.000030025218,0.00012711863,0.0013192861,0.83414876,0.1458716,0.016982842,0.00008663263],"about_ca_topic_score_codex":0.0000051345273,"about_ca_topic_score_gemma":0.0000012777843,"teacher_disagreement_score":0.809819,"about_ca_system_score_codex":0.000023711471,"about_ca_system_score_gemma":0.000027789556,"threshold_uncertainty_score":0.19512503},"labels":[],"label_agreement":null},{"id":"W3198645887","doi":"10.14778/3476249.3476304","title":"Explaining inference queries with bayesian optimization","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Inference; Python (programming language); Bayesian inference; Query optimization; Predicate (mathematical logic); Bayesian probability; Data mining; Information retrieval; Theoretical computer science; Artificial intelligence; Programming language","score_opus":0.010849102484855025,"score_gpt":0.230534737405498,"score_spread":0.219685634920643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3198645887","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":[0.018158924,0.00010999857,0.9489129,0.008225379,0.00017292488,0.00022891702,0.0000025909967,0.00018301408,0.02400531],"genre_scores_gemma":[0.86676115,0.000025763002,0.1328185,0.00010743906,0.000018055447,0.000020438607,0.0000030121548,0.000005056619,0.00024057478],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921966,0.000010206338,0.00014933074,0.00023543503,0.0002607639,0.00012459555],"domain_scores_gemma":[0.99934465,0.000033063938,0.00017946758,0.0001932817,0.00021562216,0.000033923057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016262077,0.00008466735,0.00009384204,0.000035456647,0.00012845875,0.00014424132,0.00048126688,0.000022227552,0.00001270003],"category_scores_gemma":[0.00017639263,0.00005594676,0.000024587966,0.00037709414,0.000036193553,0.00043552092,0.00025621633,0.00009546215,0.0000016413103],"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":[0.000032864595,0.0002041107,0.061489403,0.00019923106,0.00006567672,0.0000023600667,0.0062238458,0.019589946,0.020793522,0.8592628,0.00085768267,0.03127851],"study_design_scores_gemma":[0.0014919383,0.00037834127,0.026113223,0.00073975633,0.00006319653,0.00011481956,0.0030301565,0.61113423,0.3404017,0.0054568923,0.010341077,0.0007346419],"about_ca_topic_score_codex":0.000016841266,"about_ca_topic_score_gemma":0.0000031902534,"teacher_disagreement_score":0.85380596,"about_ca_system_score_codex":0.00002555895,"about_ca_system_score_gemma":0.00006039668,"threshold_uncertainty_score":0.22814426},"labels":[],"label_agreement":null},{"id":"W3198782179","doi":"10.14778/3476311.3476363","title":"Catch a blowfish alive","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Privacy-Preserving Technologies in Data","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":"Computer science; Differential privacy; Domain (mathematical analysis); Bounded function; Information privacy; Privacy policy; Computer security; Data mining","score_opus":0.020958974059684658,"score_gpt":0.24404106155515926,"score_spread":0.2230820874954746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3198782179","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":[0.46516135,0.0014128569,0.008385319,0.4600379,0.0023213057,0.001252777,0.00005306863,0.0019374674,0.059437964],"genre_scores_gemma":[0.7928564,0.00013644612,0.20559348,0.00079610606,0.000048357655,0.00006266,0.0000012867483,0.000014531387,0.00049074227],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985235,0.000007341048,0.00024653538,0.0004461603,0.00046918265,0.00030729876],"domain_scores_gemma":[0.99700606,0.0000471596,0.00019047852,0.0024294793,0.0002817738,0.00004503604],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00028327756,0.00013826771,0.00017652317,0.000054699052,0.00010257443,0.00012945202,0.02109172,0.00006746051,0.00001614737],"category_scores_gemma":[0.0060790908,0.00010343336,0.000095883566,0.00069851027,0.00009671245,0.00040458192,0.08475925,0.00019787141,0.000014259442],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000071980967,0.0002980166,0.006645828,0.00015824698,0.0001342381,0.000011006101,0.00065153395,0.0000022354438,0.12121726,0.068229206,0.78949195,0.013153279],"study_design_scores_gemma":[0.0002595632,0.00003277928,0.0010162339,0.00009451634,0.000014659776,0.00005010362,0.0001389372,0.0020292425,0.7683044,0.21804132,0.009863267,0.00015498295],"about_ca_topic_score_codex":0.000031512067,"about_ca_topic_score_gemma":0.0000031824725,"teacher_disagreement_score":0.7796287,"about_ca_system_score_codex":0.0000916807,"about_ca_system_score_gemma":0.00006724824,"threshold_uncertainty_score":0.98420465},"labels":[],"label_agreement":null},{"id":"W3200211247","doi":"10.14778/3485450.3485462","title":"Accelerating recommendation system training by leveraging popular choices","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":50,"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":"Computer science; Embedding; Recommender system; Categorical variable; Popularity; Parallel computing; Feature (linguistics); Representation (politics); Machine learning; Artificial intelligence","score_opus":0.04706617408481114,"score_gpt":0.2487423492667841,"score_spread":0.20167617518197295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200211247","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":[0.45524335,0.0028225817,0.27091077,0.036990352,0.0070218453,0.0038684763,0.00004657478,0.0031920772,0.21990396],"genre_scores_gemma":[0.9739036,0.00001782071,0.02546209,0.00020116044,0.00007656005,0.00006692087,0.0000033053814,0.000012836308,0.0002556922],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985837,0.000026909056,0.00044672107,0.0003824806,0.00029840064,0.00026183738],"domain_scores_gemma":[0.9991394,0.000027896976,0.0004062193,0.00018329924,0.00019047037,0.000052664163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006726156,0.00015743497,0.00024258174,0.000055523466,0.00024720596,0.00034053467,0.00075581175,0.00004907969,0.000007969791],"category_scores_gemma":[0.00004223103,0.00012048206,0.00010420159,0.0003474764,0.000012647343,0.00063513994,0.00045962833,0.00014465506,0.0000014463916],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000070387177,0.00024152367,0.012014093,0.0012534388,0.00026667875,0.0000039580605,0.012866509,0.000011500875,0.41082028,0.2821753,0.032334365,0.24800532],"study_design_scores_gemma":[0.0005604162,0.00006551785,0.0003677594,0.00086607266,0.000026095502,0.0001381244,0.004564815,0.010553251,0.92606723,0.0018202917,0.054568045,0.00040237806],"about_ca_topic_score_codex":0.00009116113,"about_ca_topic_score_gemma":0.0000022096112,"teacher_disagreement_score":0.51866025,"about_ca_system_score_codex":0.00014263422,"about_ca_system_score_gemma":0.000033478715,"threshold_uncertainty_score":0.49131158},"labels":[],"label_agreement":null},{"id":"W3210479060","doi":"10.14778/3461535.3461546","title":"Comprehensible counterfactual explanation on Kolmogorov-Smirnov test","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Explainable Artificial Intelligence (XAI)","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":"McMaster University; Simon Fraser University","funders":"","keywords":"Counterfactual thinking; Benchmark (surveying); Scalability; Test (biology); Set (abstract data type); Test set; Computer science; Exponential function; Algorithm; Artificial intelligence; Mathematics; Machine learning; Psychology; Database","score_opus":0.019585693011753096,"score_gpt":0.23513753534632073,"score_spread":0.21555184233456764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210479060","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":[0.85226566,0.00039707668,0.016659427,0.018279618,0.002341863,0.0014393972,0.00002651317,0.0005125679,0.10807788],"genre_scores_gemma":[0.9948555,0.000033170065,0.0033953164,0.0006765409,0.00006242902,0.00003247577,0.0000010960182,0.000011983593,0.0009314618],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99826247,0.000010999039,0.00034875036,0.00042378507,0.0006320177,0.00032195565],"domain_scores_gemma":[0.9986642,0.00018850957,0.00022207508,0.00031090016,0.00054562045,0.00006866712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026512778,0.00017411426,0.00019143042,0.00008735147,0.00018724735,0.00019640531,0.0010296226,0.00005125859,0.00004109648],"category_scores_gemma":[0.00030350254,0.00013508718,0.00009409036,0.00058358756,0.0000675595,0.0005097957,0.00048090704,0.00016494957,0.000095479554],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034066354,0.0009856039,0.0035717292,0.00013247822,0.00006927861,0.000010007233,0.0039964537,0.00073765405,0.56101054,0.40172893,0.014625415,0.0130978245],"study_design_scores_gemma":[0.00015414032,0.0001557787,0.0007016729,0.00010110527,0.000008346779,0.000020380518,0.0006379215,0.0064215437,0.97733104,0.0080773365,0.0062378375,0.00015287066],"about_ca_topic_score_codex":0.000044442815,"about_ca_topic_score_gemma":0.000010035669,"teacher_disagreement_score":0.4163205,"about_ca_system_score_codex":0.00014935253,"about_ca_system_score_gemma":0.000076169374,"threshold_uncertainty_score":0.5508695},"labels":[],"label_agreement":null},{"id":"W3211025647","doi":"10.14778/3484224.3484231","title":"Quantifying identifiability to choose and audit ϵ in differentially private deep learning","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Differential privacy; Identifiability; Computer science; Adversary; Bounding overwatch; Upper and lower bounds; Inference; Bayesian inference; Audit; Information privacy; Obfuscation; Data mining; Machine learning; Computer security; Bayesian probability; Artificial intelligence; Mathematics","score_opus":0.029575709233698576,"score_gpt":0.2709407707795119,"score_spread":0.24136506154581333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211025647","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":[0.9810587,0.00019151912,0.005117183,0.012598553,0.00025568396,0.0003374139,0.0000017696942,0.00018617895,0.00025295847],"genre_scores_gemma":[0.92968345,0.000084621526,0.0700534,0.00007249318,0.000013380731,0.00003853909,6.3214884e-7,0.000009592961,0.000043887478],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9981795,0.00002575769,0.00037598584,0.0006482577,0.00041319657,0.00035728334],"domain_scores_gemma":[0.9980598,0.00008857985,0.00019350061,0.0014510802,0.00014200306,0.00006505027],"candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00070706836,0.00016534979,0.00024629396,0.0001304674,0.00012811682,0.00025248842,0.008749944,0.000067715606,0.000007812998],"category_scores_gemma":[0.0143897245,0.00013455465,0.00005728964,0.00078776997,0.00007625908,0.00048691107,0.07084211,0.0003334438,0.000004755624],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032682045,0.0003679192,0.35630482,0.0006150403,0.00008222062,0.000011451433,0.001868121,0.00006454159,0.5079831,0.02960072,0.002674117,0.10039529],"study_design_scores_gemma":[0.00064178347,0.00006375385,0.27181935,0.00041315577,0.00001703526,0.000023667782,0.00031046974,0.015724557,0.5766465,0.13297997,0.0010058776,0.00035386987],"about_ca_topic_score_codex":0.00004590962,"about_ca_topic_score_gemma":0.000036116533,"teacher_disagreement_score":0.10337926,"about_ca_system_score_codex":0.00012085337,"about_ca_system_score_gemma":0.000026893034,"threshold_uncertainty_score":0.9966132},"labels":[],"label_agreement":null},{"id":"W3211229017","doi":"10.14778/3551793.3551804","title":"A scalable AutoML approach based on graph neural networks","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Scalability; Scripting language; Metadata; Pipeline (software); Artificial intelligence; Machine learning; Graph; Pipeline transport; Theoretical computer science; Database; Programming language; World Wide Web","score_opus":0.012770768817358303,"score_gpt":0.21496839349981606,"score_spread":0.20219762468245775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211229017","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":[0.16984214,0.00091908086,0.48526505,0.081706524,0.005062535,0.006236517,0.00007373475,0.0030000778,0.24789436],"genre_scores_gemma":[0.99109983,0.0000020377447,0.0074948114,0.0009179666,0.000034033987,0.00015997852,0.00000587282,0.000009044433,0.00027640068],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986434,0.000028766097,0.00019797633,0.0003581157,0.00054267794,0.00022908194],"domain_scores_gemma":[0.9993181,0.000034188542,0.00022163267,0.000310207,0.00006639535,0.000049430768],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061705365,0.00011886866,0.00012172312,0.00010369971,0.00038572343,0.00009674426,0.0014575786,0.00002077916,0.000016349464],"category_scores_gemma":[0.000053680164,0.000086346336,0.00009150135,0.00070227904,0.000033950477,0.00014523316,0.0006012432,0.0003255756,0.0000015755095],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012838113,0.0014606979,0.016204458,0.00015123459,0.000051885614,9.5124807e-7,0.0009407894,0.6324161,0.0032570483,0.24861503,0.03973371,0.057039715],"study_design_scores_gemma":[0.00029984192,0.0001360351,0.0030244654,0.000007322508,0.000007282446,0.0000053255044,0.000054025037,0.99106103,0.000464435,0.000547872,0.0042958753,0.000096466145],"about_ca_topic_score_codex":0.00003393227,"about_ca_topic_score_gemma":1.4447184e-7,"teacher_disagreement_score":0.8212577,"about_ca_system_score_codex":0.000068635316,"about_ca_system_score_gemma":0.000021174548,"threshold_uncertainty_score":0.35211012},"labels":[],"label_agreement":null},{"id":"W4206548428","doi":"10.14778/3494124.3494141","title":"APEX","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Liquid Crystal Research Advancements","field":"Materials Science","cited_by":53,"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":"Apex (geometry); Medicine; Anatomy","score_opus":0.019380075659541512,"score_gpt":0.2763615835010787,"score_spread":0.25698150784153717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206548428","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":[0.972504,0.00019731783,0.000018764385,0.0012388226,0.00027631712,0.00024355989,0.000010534654,0.000031938675,0.025478706],"genre_scores_gemma":[0.99405134,0.0000372699,0.0020513334,0.00016817288,0.000049653372,0.00004230494,5.1307063e-7,0.000010390925,0.0035890136],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986249,0.000007358493,0.0001985267,0.00022449708,0.0006483787,0.00029634548],"domain_scores_gemma":[0.9993488,0.000024255723,0.00011033458,0.00013960221,0.00030551333,0.00007147854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029652327,0.00008746023,0.00012267541,0.000022586039,0.00008780896,0.000059568145,0.00046682308,0.000019832489,0.00062772096],"category_scores_gemma":[0.00036745373,0.000058504967,0.00006339436,0.00021043027,0.00008627783,0.00020636486,0.00065003714,0.000072258015,0.00007431133],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001725364,0.000070102324,0.0005657099,0.000058332498,0.000006682896,9.619215e-7,0.00009626321,0.000003162981,0.99162066,0.0055635767,0.0016139412,0.0003833322],"study_design_scores_gemma":[0.00025928835,0.00003811814,0.0004352967,0.000049688006,0.000006520778,0.000007593179,0.00019391245,0.000009933228,0.9834203,0.0042892895,0.011228998,0.00006105852],"about_ca_topic_score_codex":0.000010990987,"about_ca_topic_score_gemma":0.0000014281612,"teacher_disagreement_score":0.021889692,"about_ca_system_score_codex":0.00008798976,"about_ca_system_score_gemma":0.00006146135,"threshold_uncertainty_score":0.68731046},"labels":[],"label_agreement":null},{"id":"W4210797700","doi":"10.14778/3489496.3489504","title":"LargeEA","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":29,"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; Scalability; Benchmark (surveying); Exploit; Process (computing); Channel (broadcasting); Partition (number theory); Competitor analysis; Feature (linguistics); Data mining; Artificial intelligence; Database; Programming language","score_opus":0.007208047789126523,"score_gpt":0.2039609482731143,"score_spread":0.1967529004839878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210797700","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":[0.7001984,0.006081498,0.074952126,0.05669829,0.006572707,0.0021463132,0.000014283928,0.0012749392,0.15206142],"genre_scores_gemma":[0.96857095,0.00006409425,0.029670145,0.0007024539,0.000057009234,0.000018530509,2.0033906e-7,0.000008141623,0.0009084475],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990408,0.0000045671427,0.00017162146,0.00026229976,0.00029697875,0.00022372491],"domain_scores_gemma":[0.9994027,0.00002552372,0.0001267309,0.00021310017,0.00018362625,0.000048330807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010343153,0.00009638671,0.00011962219,0.00002710934,0.00008373565,0.0000525752,0.0009073472,0.00002777057,0.000008543218],"category_scores_gemma":[0.000055103195,0.0000671169,0.00010271695,0.00056103966,0.00003701969,0.00028907717,0.0007651329,0.00012112785,0.00000646813],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000755201,0.00017758775,0.0058248206,0.00006630682,0.00005163523,0.000006228023,0.00053692196,0.00015931147,0.17577301,0.787488,0.010192885,0.019715738],"study_design_scores_gemma":[0.00039717698,0.000041052295,0.0029313955,0.00007699507,0.0000116321,0.000059356957,0.00006508303,0.0021859335,0.8963573,0.07911799,0.018572854,0.0001832127],"about_ca_topic_score_codex":0.0000017473697,"about_ca_topic_score_gemma":8.0405096e-7,"teacher_disagreement_score":0.7205843,"about_ca_system_score_codex":0.000025347721,"about_ca_system_score_gemma":0.000020538953,"threshold_uncertainty_score":0.27369478},"labels":[],"label_agreement":null},{"id":"W4226196214","doi":"10.14778/3503585.3503597","title":"COMET","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Lossy compression; Computer science; Speedup; Overhead (engineering); Convolutional neural network; Compression ratio; Bandwidth (computing); Process (computing); Computer engineering; Artificial neural network; Compression (physics); Bounded function; Data compression; Algorithm; Parallel computing; Artificial intelligence; Telecommunications","score_opus":0.0152569447225827,"score_gpt":0.24091374650963057,"score_spread":0.22565680178704786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226196214","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":[0.47190452,0.0027802293,0.17560425,0.13743098,0.0034428397,0.0029521321,0.000020235753,0.0012463516,0.20461845],"genre_scores_gemma":[0.9385456,0.00004757461,0.05972239,0.00061027665,0.00005749932,0.000051917355,2.908566e-7,0.000006250638,0.0009582337],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99926805,0.0000030018755,0.00014898919,0.00021274322,0.00021874357,0.00014845155],"domain_scores_gemma":[0.99943423,0.000030855594,0.000113514725,0.00022163421,0.0001614546,0.000038308848],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000724316,0.00007008555,0.00009179431,0.000020310377,0.00008794058,0.00003873004,0.00084603997,0.00001647306,0.000007668394],"category_scores_gemma":[0.000038849852,0.00005039876,0.000060795748,0.00059479085,0.000034025496,0.0001806629,0.0006610377,0.000078154895,0.000011010392],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001988579,0.00011137374,0.0016733636,0.000026209576,0.00001977483,6.793973e-7,0.00022095174,0.00009895884,0.16498858,0.81213385,0.008713459,0.012010807],"study_design_scores_gemma":[0.00023997674,0.000021904943,0.0031805988,0.000032900807,0.000009205817,0.00003697409,0.000045848526,0.0018894122,0.88763875,0.07006523,0.03671422,0.0001249891],"about_ca_topic_score_codex":0.0000013062825,"about_ca_topic_score_gemma":4.682423e-7,"teacher_disagreement_score":0.74206865,"about_ca_system_score_codex":0.00002987925,"about_ca_system_score_gemma":0.000018928256,"threshold_uncertainty_score":0.20552018},"labels":[],"label_agreement":null},{"id":"W4240133548","doi":"10.1145/3186728.3164137","title":"Query fresh","year":2017,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":23,"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; Backup; Overhead (engineering); Operating system; Database; Computer network; Replication (statistics)","score_opus":0.013816238538806296,"score_gpt":0.2359611939109308,"score_spread":0.2221449553721245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240133548","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":[0.6260232,0.00072342716,0.010066876,0.020488463,0.0046637533,0.0015030081,0.00004520342,0.00033950948,0.33614656],"genre_scores_gemma":[0.9971766,0.000011277769,0.0017279338,0.00009820669,0.00007256407,0.00002410429,1.2269605e-7,0.0000045495376,0.0008846442],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99905866,0.000002558724,0.000198715,0.00022353829,0.00031713012,0.00019941901],"domain_scores_gemma":[0.99895513,0.000008551289,0.00037031423,0.00047453077,0.00014109998,0.00005036345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025997596,0.000098681,0.00014647924,0.000020875632,0.00034736225,0.0003283055,0.0026964615,0.000033729295,0.000004692379],"category_scores_gemma":[0.000080091675,0.00006398971,0.00009330434,0.00006586633,0.00007378044,0.0005007933,0.00072832033,0.00008320481,0.000014640412],"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":[0.000012834736,0.00020006785,0.03225876,0.00018169089,0.000077298515,0.000002275655,0.0010331582,0.000010417579,0.05285279,0.8273743,0.06282776,0.023168653],"study_design_scores_gemma":[0.0024081762,0.00021092322,0.18318936,0.0009568191,0.00004174661,0.00007211641,0.0003586124,0.0071238233,0.54443085,0.046432216,0.21389253,0.0008828112],"about_ca_topic_score_codex":0.00010820428,"about_ca_topic_score_gemma":0.0000037571765,"teacher_disagreement_score":0.7809421,"about_ca_system_score_codex":0.000030413392,"about_ca_system_score_gemma":0.000019882795,"threshold_uncertainty_score":0.5010741},"labels":[],"label_agreement":null},{"id":"W4245107420","doi":"10.14778/3236187.3269462","title":"Efficient construction of approximate ad-hoc ML models through materialization and reuse","year":2018,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","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":"University of Toronto","funders":"","keywords":"Computer science; Online analytical processing; Reuse; Dimension (graph theory); Cluster analysis; Data mining; Variety (cybernetics); Construct (python library); Data warehouse; Mixture model; Machine learning; Artificial intelligence; Mathematics","score_opus":0.0167162247919843,"score_gpt":0.22005666246918465,"score_spread":0.20334043767720034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245107420","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":[0.8782429,0.0001761049,0.11153561,0.0012548182,0.0011440531,0.0009492957,0.000020523074,0.00014041924,0.0065362365],"genre_scores_gemma":[0.857347,0.00012030771,0.14233345,0.000053859596,0.000046469795,0.00001767999,0.0000014892881,0.000008131737,0.00007159434],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990968,0.0000052533956,0.00024215007,0.00024535749,0.0002692093,0.00014120842],"domain_scores_gemma":[0.99929297,0.0000054379566,0.0002692447,0.00024777793,0.00016338463,0.000021155745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023166873,0.00009892955,0.00013054845,0.000053211403,0.000087751745,0.00009616457,0.00074541685,0.000024670964,0.000004329851],"category_scores_gemma":[0.000021527581,0.00007025754,0.0000279853,0.00025121451,0.00017364838,0.00044867917,0.0010269454,0.000027420587,0.0000014436985],"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":[0.00006234717,0.00019497969,0.00020988885,0.0004396009,0.00007376381,1.9723541e-7,0.0067503527,0.00017533051,0.06799204,0.90664,0.0017095257,0.015752012],"study_design_scores_gemma":[0.0010513441,0.00029108985,0.00022954712,0.00024001939,0.000055432443,0.000013376674,0.0005180683,0.3404569,0.5452298,0.10984698,0.0018106686,0.000256773],"about_ca_topic_score_codex":0.000010669031,"about_ca_topic_score_gemma":2.0500302e-7,"teacher_disagreement_score":0.796793,"about_ca_system_score_codex":0.00001998862,"about_ca_system_score_gemma":0.000007353367,"threshold_uncertainty_score":0.28650194},"labels":[],"label_agreement":null},{"id":"W4246281707","doi":"10.1145/3187009.3164147","title":"Bztree","year":2018,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Data Storage Technologies","field":"Computer Science","cited_by":91,"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; Throughput; Block (permutation group theory); Non-volatile memory; Embedded system; Computer hardware; Tree (set theory); Code (set theory); Parallel computing; Operating system; Programming language","score_opus":0.01413647543843038,"score_gpt":0.23617268233670108,"score_spread":0.2220362068982707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246281707","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":[0.5111469,0.000836374,0.25280896,0.031061577,0.0038424272,0.0025387446,0.00003087176,0.004373182,0.19336092],"genre_scores_gemma":[0.90750587,0.000011869613,0.0919593,0.00016950653,0.00005144404,0.000020318696,9.228312e-8,0.000005695705,0.00027590196],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99911964,0.0000015838795,0.00015454313,0.00024831083,0.00026775664,0.00020817833],"domain_scores_gemma":[0.9992897,0.000015487916,0.00015651788,0.00035755814,0.00015541441,0.000025338439],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013682774,0.000097531825,0.0001038119,0.00006071629,0.00010299351,0.000042465606,0.0023589425,0.000033509958,0.0000070833507],"category_scores_gemma":[0.00014873414,0.00006302792,0.000044542052,0.00041112877,0.00023184763,0.0004679766,0.0016546318,0.000085013606,0.000034863453],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007385755,0.00006998602,0.001388867,0.00002693118,0.000022797749,5.0601227e-7,0.0005411999,0.0000014072349,0.104651086,0.8233912,0.016877748,0.053020913],"study_design_scores_gemma":[0.00019337347,0.00013603958,0.0009159349,0.000035268913,0.0000052787805,0.000012605525,0.00009483996,0.0004750034,0.8715439,0.10502451,0.021443095,0.00012015496],"about_ca_topic_score_codex":0.0000076012657,"about_ca_topic_score_gemma":0.0000014090231,"teacher_disagreement_score":0.7668928,"about_ca_system_score_codex":0.000049853174,"about_ca_system_score_gemma":0.000012908025,"threshold_uncertainty_score":0.43835413},"labels":[],"label_agreement":null},{"id":"W4255889623","doi":"10.1145/3186728.3164139","title":"The ubiquity of large graphs and surprising challenges of graph processing","year":2017,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":145,"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; Suite; Scalability; Visualization; Graph; Software; Data science; Theoretical computer science; World Wide Web; Data mining; Programming language; Database","score_opus":0.03165215848905461,"score_gpt":0.305877498930536,"score_spread":0.2742253404414814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255889623","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":[0.9529137,0.007738642,0.006533025,0.010939031,0.0005543471,0.0009844365,0.00003565786,0.00011266666,0.020188492],"genre_scores_gemma":[0.9978432,0.0012031455,0.00087847805,0.000024760504,0.000007285321,0.0000030242907,1.3508314e-7,0.000004299002,0.000035663452],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99908924,0.0000071133745,0.0002628044,0.00016793047,0.00032059662,0.00015233086],"domain_scores_gemma":[0.998675,0.00002990881,0.00071509834,0.00028590407,0.00026181832,0.00003225958],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007855187,0.00008632643,0.00016136603,0.00005110719,0.0004098463,0.0001434559,0.0013143467,0.000025910542,4.5393205e-7],"category_scores_gemma":[0.00016295596,0.000049952338,0.000060141978,0.00011976994,0.00021860497,0.00040133944,0.0008019978,0.000057699766,1.0948424e-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":[0.0000084984595,0.00012533937,0.008416948,0.00044228576,0.00004221077,9.78765e-8,0.0024625405,9.151604e-7,0.008176235,0.9540617,0.00021869251,0.026044562],"study_design_scores_gemma":[0.0019692439,0.000305938,0.09130651,0.0016058898,0.00013939007,0.000015429207,0.004136856,0.012937432,0.6419738,0.2406629,0.0044353297,0.00051129085],"about_ca_topic_score_codex":0.00002105556,"about_ca_topic_score_gemma":0.0000108046615,"teacher_disagreement_score":0.71339875,"about_ca_system_score_codex":0.0000064206993,"about_ca_system_score_gemma":0.000021782223,"threshold_uncertainty_score":0.3152248},"labels":[],"label_agreement":null},{"id":"W4284974261","doi":"10.14778/3551793.3551848","title":"Are updatable learned indexes ready?","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":56,"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; Concurrency; Robustness (evolution); Software deployment; Space (punctuation); Data science; Software engineering; Distributed computing; Operating system","score_opus":0.026758491041296073,"score_gpt":0.24009395904235964,"score_spread":0.21333546800106357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4284974261","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":[0.80070585,0.0047924626,0.026004432,0.05250406,0.00991946,0.006011425,0.00071622455,0.0021057315,0.097240366],"genre_scores_gemma":[0.987028,0.000030529736,0.010235769,0.00067980523,0.00006971382,0.00012495676,0.0000046074865,0.000013252894,0.0018133613],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99869895,0.000010233714,0.00019094301,0.00030666514,0.00057452585,0.00021868279],"domain_scores_gemma":[0.9991949,0.00001727809,0.00036199085,0.00030075587,0.00007834909,0.00004672578],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003427073,0.00010459943,0.00013917858,0.00005941566,0.00039919332,0.00009004104,0.0019647714,0.000017193417,0.00005707698],"category_scores_gemma":[0.000035297744,0.00007306912,0.000053953605,0.00036559775,0.000031078795,0.00044241312,0.0036688459,0.0001944643,0.000007658596],"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":[0.00012806007,0.0012430145,0.030123476,0.0002852328,0.00015060112,0.000009969118,0.0028658283,0.00088377064,0.07552483,0.49902862,0.3328007,0.056955904],"study_design_scores_gemma":[0.0021625776,0.00046383266,0.015985832,0.00023587016,0.000049644586,0.00013103451,0.0022092252,0.024698097,0.18171312,0.06189088,0.7095927,0.00086719124],"about_ca_topic_score_codex":0.00006755797,"about_ca_topic_score_gemma":7.06538e-7,"teacher_disagreement_score":0.43713775,"about_ca_system_score_codex":0.000067916866,"about_ca_system_score_gemma":0.000024668157,"threshold_uncertainty_score":0.4572954},"labels":[],"label_agreement":null},{"id":"W4285335450","doi":"10.14778/3494124.3494149","title":"Ember","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":15,"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; Joins; Schema (genetic algorithms); Context (archaeology); Code (set theory); Information retrieval; Theoretical computer science; Artificial intelligence; Programming language","score_opus":0.14569448175843022,"score_gpt":0.38625044455308555,"score_spread":0.24055596279465533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285335450","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":[0.40125245,0.00031275986,0.00026590438,0.028313095,0.0013686477,0.0005097799,0.000044472054,0.000057740494,0.56787515],"genre_scores_gemma":[0.9674962,0.000029763456,0.0013860769,0.0013606643,0.00006237678,0.000018442566,0.0000011414002,0.0000063186676,0.029638993],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977883,0.000016972948,0.0004301266,0.0003109235,0.0012832199,0.00017046872],"domain_scores_gemma":[0.9988625,0.000120243756,0.00023858955,0.00031222502,0.00041631577,0.000050094055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017498882,0.00008337014,0.00017010682,0.00005396444,0.000096120886,0.00018215316,0.001006377,0.000024441402,0.00066612894],"category_scores_gemma":[0.0015655471,0.000048218102,0.00013489154,0.0006024831,0.000071193106,0.00025271895,0.0011002491,0.00007328689,0.00017525165],"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":[0.000022604734,0.00029209678,0.0067584496,0.00005124116,0.00007451925,0.000002271176,0.0011799654,0.000013204485,0.022831721,0.44697928,0.4881496,0.033645038],"study_design_scores_gemma":[0.00033984127,0.000023287874,0.007295904,0.000036280824,0.000028410883,0.000008421216,0.0034987936,0.000047074947,0.19152468,0.14425294,0.65282774,0.00011665757],"about_ca_topic_score_codex":0.000016777569,"about_ca_topic_score_gemma":0.000008547709,"teacher_disagreement_score":0.56624377,"about_ca_system_score_codex":0.000026989946,"about_ca_system_score_gemma":0.000026741482,"threshold_uncertainty_score":0.7293645},"labels":[],"label_agreement":null},{"id":"W4285337687","doi":"10.14778/3494124.3494125","title":"Enabling SQL-based training data debugging for federated learning","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Privacy-Preserving Technologies in Data","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":"Simon Fraser University","funders":"","keywords":"Debugging; Computer science; SQL; SQL injection; Protocol (science); Machine learning; Federated learning; Database; Software engineering; Artificial intelligence; Data mining; Query by Example; Programming language; World Wide Web; Search engine","score_opus":0.09386716120745424,"score_gpt":0.2972390531859824,"score_spread":0.20337189197852817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285337687","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":[0.092358634,0.0020237544,0.7468655,0.145719,0.0017974285,0.0022303364,0.000118994234,0.0039200727,0.0049662795],"genre_scores_gemma":[0.6459005,0.000023640616,0.35360548,0.00025854987,0.000046674617,0.00005452234,0.000021547785,0.00002094414,0.00006811181],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978906,0.000016571434,0.0003814528,0.0007777176,0.00043834726,0.00049529143],"domain_scores_gemma":[0.9965925,0.0002801063,0.00034377628,0.0023806351,0.00034918642,0.000053787317],"candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0011070502,0.00019591958,0.0002634108,0.00010678088,0.00045423786,0.0004174115,0.020600203,0.00008537467,0.0000060922657],"category_scores_gemma":[0.02836267,0.00016085446,0.00008561833,0.00074358156,0.000070954135,0.0008041558,0.052701075,0.00032982358,0.0000017866693],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000077726094,0.0004111237,0.004491067,0.0010933151,0.00045701914,0.000014584535,0.0016190605,0.00084204157,0.5571414,0.020713173,0.118438154,0.2947013],"study_design_scores_gemma":[0.0007098358,0.000051461717,0.000066784974,0.0003091116,0.000031366686,0.000017715174,0.0005501723,0.50710136,0.4548428,0.026495857,0.009583449,0.00024011132],"about_ca_topic_score_codex":0.000013105246,"about_ca_topic_score_gemma":0.0000033826764,"teacher_disagreement_score":0.5535419,"about_ca_system_score_codex":0.000097292024,"about_ca_system_score_gemma":0.00021942335,"threshold_uncertainty_score":0.98469883},"labels":[],"label_agreement":null},{"id":"W4288080130","doi":"10.14778/3407790.3407823","title":"Hypergraph motifs","year":2020,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"National Supercomputing Center, Korea Institute of Science and Technology Information; Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Korea Advanced Institute of Science and Technology; Iran Telecommunication Research Center; National Research Foundation of Korea","keywords":"Hypergraph; Computer science; Theoretical computer science; Motif (music); Combinatorics; Mathematics","score_opus":0.010777552812729326,"score_gpt":0.20393807135097922,"score_spread":0.1931605185382499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288080130","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":[0.8878644,0.00010554649,0.0008976586,0.0063366555,0.00007421095,0.0005780227,0.000013230708,0.00015995927,0.103970304],"genre_scores_gemma":[0.9983946,0.0000028871318,0.0010799345,0.00017335484,0.00019085241,0.000027061424,0.0000010473848,0.000011000612,0.000119245145],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992916,0.0000029614966,0.00019458044,0.00017100041,0.0001904111,0.00014945336],"domain_scores_gemma":[0.9996204,0.000009924761,0.00015131671,0.00008065535,0.00007899123,0.00005870767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006799145,0.000108442124,0.00016959078,0.000024318271,0.00006278013,0.00002517776,0.00040414164,0.000012605679,0.00018670342],"category_scores_gemma":[0.000006009543,0.000075434575,0.00020052791,0.00032046207,0.000040931747,0.000061326464,0.000228174,0.000098680444,0.000008315842],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000419236,0.0003035304,0.38780767,0.00008652248,0.0005510876,1.5846135e-7,0.0015872724,0.00009722258,0.18430103,0.33059654,0.0722881,0.022338936],"study_design_scores_gemma":[0.00079326465,0.00016969931,0.008224536,0.000101056,0.0003100349,8.531273e-7,0.0009829891,0.0039666956,0.85703236,0.075957656,0.051977605,0.0004832352],"about_ca_topic_score_codex":0.00004778497,"about_ca_topic_score_gemma":2.2147206e-7,"teacher_disagreement_score":0.67273134,"about_ca_system_score_codex":0.000010640118,"about_ca_system_score_gemma":0.000007875927,"threshold_uncertainty_score":0.30761325},"labels":[],"label_agreement":null},{"id":"W4289550979","doi":"10.14778/3551793.3551862","title":"Optimizing differentially-maintained recursive queries on dynamic graphs","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Graph Theory and Algorithms","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":"","keywords":"Computer science; Scalability; Dataflow; Computation; Overhead (engineering); Graph; Probabilistic logic; Parallel computing; Differential (mechanical device); Theoretical computer science; Algorithm; Programming language","score_opus":0.006113840765845322,"score_gpt":0.20260877880646236,"score_spread":0.19649493804061705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289550979","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":[0.9658409,0.00034214742,0.011849522,0.0069612847,0.0028258073,0.001564766,0.000037219826,0.00041065476,0.010167737],"genre_scores_gemma":[0.9928987,0.000019731833,0.0063519324,0.0002899293,0.000013760697,0.00013825901,0.0000011770927,0.000012477692,0.0002740563],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99851805,0.000031477437,0.0002454755,0.00036986143,0.0005266669,0.0003084652],"domain_scores_gemma":[0.9993058,0.00005301824,0.00026220997,0.00023862858,0.00008299636,0.00005736512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003942887,0.00018097548,0.00019597613,0.00016546501,0.00056314387,0.00008260253,0.0016688367,0.000022488754,0.000031299078],"category_scores_gemma":[0.000036048594,0.00013448304,0.00019547663,0.00056310993,0.000097867895,0.0002027025,0.0011642721,0.00026250075,0.0000022133015],"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":[0.000060684146,0.00019508998,0.00010811023,0.00002504269,0.000060589446,0.0000015985897,0.0031512321,0.0003384273,0.013182394,0.97910315,0.00023913698,0.003534534],"study_design_scores_gemma":[0.0012954794,0.0011764426,0.0011035145,0.00012017661,0.000051926174,0.000045259294,0.0033767382,0.008446545,0.10028046,0.88192356,0.0016310125,0.00054888515],"about_ca_topic_score_codex":0.000007841678,"about_ca_topic_score_gemma":6.541462e-7,"teacher_disagreement_score":0.0971796,"about_ca_system_score_codex":0.00010933765,"about_ca_system_score_gemma":0.000023187833,"threshold_uncertainty_score":0.54840595},"labels":[],"label_agreement":null},{"id":"W4289785654","doi":"10.14778/3551793.3551829","title":"On shapley value in data assemblage under independent utility","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Privacy-Preserving Technologies in Data","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":"Simon Fraser University","funders":"","keywords":"Shapley value; Computer science; Benchmark (surveying); Revenue; Computation; Value (mathematics); Assemblage (archaeology); Mathematical economics; Game theory; Economics; Algorithm; Machine learning; Finance","score_opus":0.06382497208843492,"score_gpt":0.2859229840051806,"score_spread":0.22209801191674572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289785654","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":[0.88316464,0.00029256757,0.0053735054,0.0959756,0.0013239804,0.0019487306,0.00026420478,0.0008121187,0.0108446535],"genre_scores_gemma":[0.98778796,0.000016709837,0.011602625,0.00044188896,0.000011595744,0.00008151191,0.000006344296,0.000011840088,0.000039495622],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99721074,0.00003845803,0.00038509202,0.00084603106,0.0011268784,0.00039279897],"domain_scores_gemma":[0.99381995,0.00013699212,0.00028045566,0.0056706746,0.000048603106,0.000043314998],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0019367702,0.00018320893,0.0002170632,0.00019000092,0.0002036542,0.00009900478,0.05981081,0.000055672324,0.000042218828],"category_scores_gemma":[0.004459235,0.00014675429,0.000054605727,0.00086468004,0.0000787149,0.0006115855,0.27411762,0.00063224207,0.000005876472],"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":[0.000105273335,0.0017809157,0.012147615,0.00015636595,0.00011662434,0.000011832433,0.0005314163,0.0006051011,0.018663935,0.61452186,0.34007645,0.011282611],"study_design_scores_gemma":[0.0008020112,0.00015554085,0.010841207,0.000070278984,0.000012142991,0.00002129848,0.00039674318,0.13973208,0.033591583,0.8109443,0.0031284275,0.00030435692],"about_ca_topic_score_codex":0.00022035089,"about_ca_topic_score_gemma":0.000010728185,"teacher_disagreement_score":0.336948,"about_ca_system_score_codex":0.00047676841,"about_ca_system_score_gemma":0.00007379382,"threshold_uncertainty_score":0.9452761},"labels":[],"label_agreement":null},{"id":"W4294903937","doi":"10.14778/3547305.3547324","title":"Misinformation mitigation under differential propagation rates and temporal penalties","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Misinformation and Its Impacts","field":"Social Sciences","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":"University of British Columbia","funders":"","keywords":"Submodular set function; Bounding overwatch; Computer science; Misinformation; Mathematical optimization; Reachability; Theoretical computer science; Algorithm; Mathematics; Artificial intelligence","score_opus":0.01896916786759804,"score_gpt":0.2716387004994955,"score_spread":0.25266953263189745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294903937","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":[0.9805265,0.000024082772,0.00003965287,0.00483484,0.00018381159,0.00050268427,0.0000058348473,0.000031572294,0.01385103],"genre_scores_gemma":[0.9984636,0.00002421086,0.00007202462,0.00018690815,0.000042291813,0.000016578006,0.000006863789,0.0000035688297,0.0011839845],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9989895,0.000018683633,0.00022467715,0.00006677973,0.0005676774,0.00013267956],"domain_scores_gemma":[0.9995007,0.000016838625,0.00028761468,0.000033248354,0.00011542927,0.000046181798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046634531,0.0000654062,0.00007586478,0.00007105262,0.0008190518,0.00011451517,0.00014714008,0.000020980355,0.00020803727],"category_scores_gemma":[0.00008774341,0.000049193823,0.000033788714,0.0001883795,0.000107002874,0.00065128563,0.00010178899,0.000081168066,0.0000020427342],"study_design_candidate":"qualitative","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":[0.00021963617,0.0002537292,0.017227354,0.00036438458,0.000090714435,7.359339e-8,0.3816765,0.0002174816,0.029832514,0.5264729,0.026332736,0.017311955],"study_design_scores_gemma":[0.0038101354,0.0005473285,0.14180398,0.00018415238,0.00014211317,0.000018737868,0.5963381,0.0065305834,0.15373953,0.043390773,0.05264724,0.0008473279],"about_ca_topic_score_codex":0.0002307779,"about_ca_topic_score_gemma":0.00001773732,"teacher_disagreement_score":0.48308218,"about_ca_system_score_codex":0.00012391126,"about_ca_system_score_gemma":0.00006174772,"threshold_uncertainty_score":0.6299567},"labels":[],"label_agreement":null},{"id":"W4294904134","doi":"10.14778/3547305.3547321","title":"Improving matrix-vector multiplication via lossless grammar-compressed matrices","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Algorithms and Data Compression","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":"Dalhousie University","funders":"","keywords":"Lossless compression; Computer science; Matrix (chemical analysis); Algorithm; Matrix multiplication; Linear algebra; Data compression ratio; Data compression; Theoretical computer science; Mathematics; Image compression; Artificial intelligence; Image processing","score_opus":0.008123292950760374,"score_gpt":0.222613248707195,"score_spread":0.21448995575643465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294904134","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":[0.47993773,0.003160778,0.49554124,0.0076634134,0.004341841,0.0053642835,0.00018172924,0.0012901768,0.0025188026],"genre_scores_gemma":[0.9692787,0.000017151373,0.030090375,0.00008755281,0.00008250033,0.00023353864,0.000003842222,0.000015377878,0.00019099672],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981784,0.000017959615,0.00034718643,0.00045544523,0.0007106414,0.00029032637],"domain_scores_gemma":[0.99884295,0.00004930998,0.0005127885,0.0003858281,0.00014079097,0.000068321046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038993263,0.00017036907,0.00018708294,0.000105772786,0.0005141458,0.00015183966,0.0024394253,0.000029889283,0.000024270927],"category_scores_gemma":[0.000027417267,0.00012600957,0.00011118611,0.0005493456,0.000037006528,0.0005447305,0.003000215,0.00021323397,0.000005513974],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008645638,0.0006213713,0.0031540703,0.0003371648,0.00007190499,0.0000020528066,0.0015141878,0.0008478217,0.8288828,0.043166947,0.0052168104,0.11609842],"study_design_scores_gemma":[0.0018594998,0.00031344942,0.0068022925,0.0000814505,0.00006313472,0.00007735246,0.00036994324,0.60135645,0.3591512,0.008561823,0.020667313,0.00069606997],"about_ca_topic_score_codex":0.00026907204,"about_ca_topic_score_gemma":7.2347393e-7,"teacher_disagreement_score":0.60050863,"about_ca_system_score_codex":0.00013474045,"about_ca_system_score_gemma":0.00003206297,"threshold_uncertainty_score":0.5138522},"labels":[],"label_agreement":null},{"id":"W4312277017","doi":"10.14778/3551793.3551808","title":"Evaluating persistent memory range indexes","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Memory and Neural Computing","field":"Engineering","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":"Simon Fraser University","funders":"","keywords":"Dram; Computer science; Scalability; Latency (audio); CAS latency; Range (aeronautics); Embedded system; Memory controller; Computer hardware; Operating system; Semiconductor memory; Telecommunications; Engineering","score_opus":0.037182770645599446,"score_gpt":0.2610079709039207,"score_spread":0.22382520025832126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312277017","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":[0.99365234,0.00054442254,0.000009838289,0.00013155353,0.00045817636,0.00032310243,0.0000038620287,0.00013220552,0.0047444897],"genre_scores_gemma":[0.9989965,0.000010102584,0.00045335296,0.00007728098,0.00006790605,0.00007674939,4.2108474e-7,0.000021496664,0.00029620618],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99903667,0.000007652807,0.00020982754,0.00014816991,0.00038506225,0.00021262318],"domain_scores_gemma":[0.9997278,0.00003138414,0.000086527,0.000081092265,0.000039324168,0.000033908193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033906783,0.00011959898,0.00013912308,0.00004895924,0.0002806662,0.00001189565,0.0003367384,0.0000144093565,0.00006691214],"category_scores_gemma":[0.00003740043,0.00009748541,0.00013910198,0.00020320126,0.000024839692,0.00008534559,0.00034357628,0.00024685453,0.0000018436946],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044318833,0.00005245265,0.0010408337,0.0002698059,0.00008680905,8.475202e-7,0.0026527753,0.23299457,0.7479743,0.00047661382,0.0008624084,0.01354426],"study_design_scores_gemma":[0.0014113858,0.00039790725,0.0009299769,0.00011949559,0.0001226063,0.00008199381,0.0050098337,0.036085255,0.9514213,0.0013803996,0.0025705185,0.00046930398],"about_ca_topic_score_codex":0.0000023892285,"about_ca_topic_score_gemma":1.5248257e-7,"teacher_disagreement_score":0.20344703,"about_ca_system_score_codex":0.00014664744,"about_ca_system_score_gemma":0.000007100522,"threshold_uncertainty_score":0.39753398},"labels":[],"label_agreement":null},{"id":"W4312312306","doi":"10.14778/3554821.3554894","title":"Modern techniques for querying graph-structured relations","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","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":"Computer science; Graph; Graph database; Theoretical computer science; Query optimization; Distributed computing; Information retrieval","score_opus":0.012329831228488347,"score_gpt":0.23290806312094914,"score_spread":0.22057823189246079,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312312306","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":[0.015531275,0.0003844102,0.9743632,0.002892468,0.0006536959,0.0020885903,0.00015151876,0.00039127265,0.0035435453],"genre_scores_gemma":[0.75325537,0.0000061697033,0.2452721,0.00013627206,0.0000399596,0.0007859298,0.0000032680425,0.00001231065,0.0004886409],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990763,0.0000061714754,0.0002279446,0.00023849105,0.0002803347,0.00017075127],"domain_scores_gemma":[0.99941176,0.000029341609,0.00023703025,0.00018948702,0.00010504978,0.000027356073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025992654,0.000097971555,0.00012763884,0.000079829355,0.0004959202,0.00002457217,0.000609687,0.000016432145,0.0000050540484],"category_scores_gemma":[0.00004213373,0.00007301742,0.00010088165,0.00028864326,0.000033994176,0.00036861328,0.0007007031,0.000106656116,2.359005e-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":[0.0000135352375,0.00003470186,0.00046747405,0.000059485046,0.000024213476,1.3240867e-7,0.0013922406,0.00021378273,0.0721375,0.9138495,0.003362744,0.008444733],"study_design_scores_gemma":[0.00064260064,0.0002640939,0.000373389,0.000096516385,0.00003325975,0.00005967248,0.00089749176,0.011104225,0.43248463,0.34040317,0.21319938,0.00044157787],"about_ca_topic_score_codex":0.000023338906,"about_ca_topic_score_gemma":0.000002101803,"teacher_disagreement_score":0.73772407,"about_ca_system_score_codex":0.000076470846,"about_ca_system_score_gemma":0.000026771337,"threshold_uncertainty_score":0.38142675},"labels":[],"label_agreement":null},{"id":"W4312535937","doi":"10.14778/3551793.3551805","title":"Don't be a tattle-tale","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Privacy-Preserving Technologies in Data","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":"University of Waterloo","funders":"","keywords":"Computer science; Inference; Computation; Data mining; Information sensitivity; Information retrieval; Computer security; Algorithm; Artificial intelligence","score_opus":0.02477296912415364,"score_gpt":0.24534879267563733,"score_spread":0.2205758235514837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312535937","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":[0.49887007,0.000987985,0.005484641,0.4459524,0.003112917,0.0023612708,0.00017966915,0.0026114096,0.040439658],"genre_scores_gemma":[0.9315504,0.000025573028,0.067032896,0.0007086676,0.000025856509,0.00024352678,0.0000014403249,0.000014635224,0.00039700267],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982948,0.000010227711,0.00024333711,0.0004109499,0.0007179431,0.0003227467],"domain_scores_gemma":[0.9974478,0.000048218408,0.0002490851,0.0021398268,0.00007702256,0.000038042854],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00053415843,0.00013582848,0.00015642204,0.000110918045,0.00031299578,0.000080425656,0.034147177,0.000029946734,0.00006661129],"category_scores_gemma":[0.0025148217,0.00010544111,0.00009221444,0.00074740115,0.000117852614,0.00037261134,0.16487686,0.0003067496,0.0000047999956],"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":[0.000014814307,0.00025512313,0.003066552,0.00006855744,0.00005879078,0.0000026489797,0.0005771691,0.000019658499,0.04066259,0.06722664,0.88015133,0.007896137],"study_design_scores_gemma":[0.00093609886,0.00034889535,0.0011647689,0.000052819618,0.000027508248,0.00011999151,0.001011039,0.014145351,0.34899956,0.49883232,0.1338817,0.00047995846],"about_ca_topic_score_codex":0.00004462379,"about_ca_topic_score_gemma":7.9265e-7,"teacher_disagreement_score":0.74626964,"about_ca_system_score_codex":0.00017521561,"about_ca_system_score_gemma":0.000037931284,"threshold_uncertainty_score":0.9710786},"labels":[],"label_agreement":null},{"id":"W4312578340","doi":"10.14778/3554821.3554897","title":"The past, present and future of indexing on persistent memory","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Memory and Neural Computing","field":"Engineering","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":"Search engine indexing; Computer science; Hash function; Contrast (vision); Data science; Information retrieval; Artificial intelligence; Computer security","score_opus":0.009660911960263854,"score_gpt":0.19781378855625145,"score_spread":0.1881528765959876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312578340","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":[0.99078846,0.0014869809,0.0000029369744,0.001601184,0.00047646384,0.00033383255,0.000003656926,0.000044197608,0.005262297],"genre_scores_gemma":[0.9993522,0.00008820771,0.000050229002,0.00003588161,0.00026705547,0.000030408712,1.7006666e-7,0.000012662006,0.00016316147],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99930644,0.000006070665,0.0001675037,0.00010905308,0.00025902854,0.00015189688],"domain_scores_gemma":[0.9997271,0.000050515533,0.00008921058,0.00007976659,0.000027133106,0.000026301945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017900678,0.0000963272,0.00010772223,0.000028219221,0.00028811055,0.000010244846,0.00024525877,0.000013323823,0.0000053049403],"category_scores_gemma":[0.0000051249467,0.000059784128,0.00007858503,0.000115344694,0.00004007674,0.00003999524,0.00027554465,0.00021144535,1.5554815e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050509727,0.00026299318,0.0022548458,0.0014687354,0.0005517503,0.0000030135461,0.012799822,0.26682597,0.50301313,0.01510985,0.013079726,0.1841251],"study_design_scores_gemma":[0.0014579374,0.00077672396,0.0024563784,0.00017870106,0.00011996151,0.00007397039,0.02207575,0.012619456,0.828133,0.0022268554,0.1294027,0.0004785609],"about_ca_topic_score_codex":0.00000123215,"about_ca_topic_score_gemma":7.2333634e-8,"teacher_disagreement_score":0.3251199,"about_ca_system_score_codex":0.000053392905,"about_ca_system_score_gemma":0.0000034001312,"threshold_uncertainty_score":0.24379261},"labels":[],"label_agreement":null},{"id":"W4312611216","doi":"10.14778/3551793.3551865","title":"Spatial and temporal constrained ranked retrieval over videos","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":14,"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; Graph; Matching (statistics); Artificial intelligence; Construct (python library); Pattern recognition (psychology); Window (computing); Data mining; Theoretical computer science; Mathematics","score_opus":0.011406514400310977,"score_gpt":0.24518063879892166,"score_spread":0.23377412439861067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312611216","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":[0.79627603,0.0015783171,0.16865802,0.012074014,0.0015198481,0.0047287904,0.0000885289,0.0012640044,0.013812448],"genre_scores_gemma":[0.9864942,0.000026987345,0.01283868,0.0003602674,0.000036960326,0.00003203005,6.282576e-7,0.000009830607,0.0002004563],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986065,0.000014542182,0.00028189822,0.00032791207,0.0005402102,0.00022895719],"domain_scores_gemma":[0.99936897,0.000042866443,0.00025545925,0.0001731361,0.00009919063,0.000060382456],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043995655,0.00014478847,0.00019782937,0.00008043825,0.0002706698,0.00006887213,0.0008405775,0.00002614082,0.000036488917],"category_scores_gemma":[0.000102598904,0.0001101706,0.000086493936,0.0004048276,0.00013131132,0.0003677526,0.0014063489,0.00021967932,6.0793946e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00079901255,0.0005745352,0.034515943,0.000272509,0.00022948622,0.000016705588,0.0038106507,0.000008376018,0.6486601,0.22023675,0.009655171,0.08122074],"study_design_scores_gemma":[0.0019719698,0.0007975674,0.0044848635,0.000053732092,0.000034949735,0.00011525644,0.00026266833,0.002858666,0.9148391,0.057333503,0.016833114,0.00041464507],"about_ca_topic_score_codex":0.000051447554,"about_ca_topic_score_gemma":6.680081e-7,"teacher_disagreement_score":0.26617894,"about_ca_system_score_codex":0.00008082372,"about_ca_system_score_gemma":0.00005390598,"threshold_uncertainty_score":0.44926268},"labels":[],"label_agreement":null},{"id":"W4312621027","doi":"10.14778/3561261.3561270","title":"TreeLine","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Data Storage Technologies","field":"Computer Science","cited_by":33,"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; Merge (version control); Associative array; Workload; Key (lock); Point (geometry); Parallel computing; Operating system; Artificial intelligence","score_opus":0.012707166413659191,"score_gpt":0.22132474582873737,"score_spread":0.2086175794150782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312621027","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":[0.63402855,0.0037781864,0.16330159,0.10949912,0.005870527,0.005213883,0.00023423834,0.006622392,0.07145149],"genre_scores_gemma":[0.9547662,0.000013051824,0.044367928,0.0002532956,0.000015936932,0.00011700463,5.140949e-7,0.000006635584,0.00045944637],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99901867,0.000003504854,0.0001670489,0.00023459502,0.0003992679,0.00017689755],"domain_scores_gemma":[0.9994396,0.000017833447,0.000175697,0.00029668905,0.000051051502,0.000019148018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020482029,0.000085163156,0.000104460836,0.00007288146,0.0001990535,0.000023811172,0.0026517485,0.000012684304,0.000017928862],"category_scores_gemma":[0.000078726676,0.000061476334,0.000054565422,0.0005296486,0.000056459292,0.00027529226,0.0040010866,0.00016528319,0.0000034321868],"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":[0.000014112118,0.00019948688,0.0009912945,0.000029992223,0.00002819435,0.00000204191,0.00063003146,0.00032450896,0.08813933,0.83184135,0.023780683,0.054018956],"study_design_scores_gemma":[0.0009324502,0.00043375287,0.0008431661,0.00002384356,0.000018913088,0.00010020887,0.0012989898,0.005709714,0.5899306,0.20204169,0.19826096,0.0004057033],"about_ca_topic_score_codex":0.000008282491,"about_ca_topic_score_gemma":3.6612022e-7,"teacher_disagreement_score":0.62979966,"about_ca_system_score_codex":0.00010768436,"about_ca_system_score_gemma":0.000015911528,"threshold_uncertainty_score":0.4987068},"labels":[],"label_agreement":null},{"id":"W4312691443","doi":"10.14778/3554821.3554869","title":"SmartBench","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Topic Modeling","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":"Carleton University","funders":"","keywords":"Benchmark (surveying); Computer science; Question answering; Usability; Cover (algebra); Task (project management); Software deployment; Natural language; Information retrieval; Quality (philosophy); Natural language processing; Artificial intelligence; Software engineering; Human–computer interaction; Systems engineering; Engineering","score_opus":0.014372961389645013,"score_gpt":0.20559853763416233,"score_spread":0.19122557624451733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312691443","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":[0.8732742,0.00045162064,0.016131897,0.0190174,0.0026494246,0.001127141,0.0000060521756,0.00034392643,0.08699835],"genre_scores_gemma":[0.9899225,0.0000028214624,0.008913582,0.00033912968,0.000031189247,0.00006525459,8.0068865e-8,0.000004368705,0.00072102743],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99900335,0.0000054225984,0.00016464424,0.00021102403,0.00044935982,0.00016620426],"domain_scores_gemma":[0.99960464,0.00001246391,0.00011885644,0.00018528878,0.00004962919,0.000029107809],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003158916,0.00006761811,0.00008442576,0.00004501127,0.0002024335,0.00003581343,0.0015263545,0.000009437035,0.00003639613],"category_scores_gemma":[0.00002051232,0.00005075029,0.0000653261,0.0002716388,0.000016662882,0.00014059359,0.0017489269,0.0001261654,0.0000030049218],"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":[0.000008051571,0.00018715333,0.007434713,0.000057352525,0.00003687705,9.4584016e-7,0.003747841,0.0011534098,0.044770483,0.91003656,0.009307684,0.02325891],"study_design_scores_gemma":[0.0023239027,0.0005978493,0.007704653,0.00008927898,0.000056867793,0.00020583403,0.0020785343,0.17570825,0.38518944,0.23584056,0.18919604,0.0010087929],"about_ca_topic_score_codex":0.000027643839,"about_ca_topic_score_gemma":3.0251456e-7,"teacher_disagreement_score":0.674196,"about_ca_system_score_codex":0.00007914117,"about_ca_system_score_gemma":0.000025424724,"threshold_uncertainty_score":0.28363717},"labels":[],"label_agreement":null},{"id":"W4312701113","doi":"10.14778/3551793.3551847","title":"ConnectorX","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":11,"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; Overhead (engineering); Bridge (graph theory); Database; Process (computing); Interface (matter); Distributed computing; Operating system","score_opus":0.007993055508866007,"score_gpt":0.19490780951306425,"score_spread":0.18691475400419824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312701113","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":[0.7458826,0.002752974,0.10068063,0.0221336,0.008822625,0.004206023,0.00026949396,0.0011287649,0.11412332],"genre_scores_gemma":[0.9870508,0.0000055930623,0.011830204,0.0002459637,0.00003438326,0.00011866357,5.318936e-7,0.0000058965934,0.00070798735],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99914026,0.000006278125,0.00016254684,0.00018826217,0.00035293135,0.0001496986],"domain_scores_gemma":[0.999557,0.000018309682,0.00016218204,0.0001773182,0.000056119432,0.000029066352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023300976,0.000073417854,0.00010425366,0.0000351295,0.0002530426,0.00001650047,0.00076665974,0.0000069172866,0.000032771397],"category_scores_gemma":[0.000029672337,0.00005113397,0.000058586334,0.00027194733,0.000030397576,0.00024854258,0.0014445221,0.00009169454,0.0000031897878],"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":[0.000005068178,0.000041124793,0.00069238554,0.000025452146,0.000011792147,4.0809516e-7,0.0006236226,0.00004679266,0.029578049,0.9625613,0.005011687,0.0014023262],"study_design_scores_gemma":[0.00061512267,0.00021280389,0.0009796411,0.000037238304,0.000010158989,0.00007973623,0.0012475075,0.0013091181,0.22696058,0.011485464,0.7567901,0.00027250723],"about_ca_topic_score_codex":0.000031615906,"about_ca_topic_score_gemma":6.731587e-7,"teacher_disagreement_score":0.95107585,"about_ca_system_score_codex":0.00005963777,"about_ca_system_score_gemma":0.00002159342,"threshold_uncertainty_score":0.20851828},"labels":[],"label_agreement":null},{"id":"W4312844330","doi":"10.14778/3551793.3551821","title":"MIDE","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Privacy-Preserving Technologies in Data","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":"","keywords":"False positive paradox; Computer science; False positives and false negatives; Bounded function; Context (archaeology); Data mining; True positive rate; Machine learning; Artificial intelligence; Mathematics","score_opus":0.020862250324350327,"score_gpt":0.2353562044626464,"score_spread":0.21449395413829608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312844330","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":[0.5110213,0.001165021,0.0068433476,0.40655068,0.0036353187,0.0022362452,0.00008148085,0.0028368195,0.06562974],"genre_scores_gemma":[0.92283124,0.000017080887,0.076354705,0.00039568482,0.00001847249,0.00014050255,4.944039e-7,0.00000894226,0.00023289681],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986694,0.00000749714,0.00019840957,0.00031118817,0.00056755263,0.00024598703],"domain_scores_gemma":[0.9977479,0.00003359108,0.00019727336,0.0019375992,0.000057062407,0.000026602114],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00046466038,0.000098822115,0.000115886316,0.00008589042,0.0002504757,0.000053983822,0.037356425,0.000020507505,0.00003219649],"category_scores_gemma":[0.002458711,0.00007492487,0.00007029873,0.0006067944,0.000066362634,0.000281399,0.18635795,0.00024107486,0.000005705048],"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":[0.000010871681,0.0001863726,0.0040859575,0.000052314394,0.000047339974,0.0000017013552,0.0003259534,0.000020165913,0.052415803,0.12816636,0.80174094,0.012946191],"study_design_scores_gemma":[0.0003868552,0.00013954498,0.0012248926,0.000024995823,0.000011182772,0.000049734554,0.00026997185,0.008893512,0.2968087,0.638643,0.053326838,0.00022077287],"about_ca_topic_score_codex":0.00002543884,"about_ca_topic_score_gemma":3.2909315e-7,"teacher_disagreement_score":0.7484141,"about_ca_system_score_codex":0.00014334357,"about_ca_system_score_gemma":0.000026733109,"threshold_uncertainty_score":0.96785194},"labels":[],"label_agreement":null},{"id":"W4312887229","doi":"10.14778/3551793.3551857","title":"Tiresias","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Cloud Computing and Resource Management","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":"University of Waterloo","funders":"","keywords":"Computer science; Latency (audio); Search engine indexing; Adaptation (eye); Row; Parallel computing; Artificial intelligence; Database","score_opus":0.009267484417925695,"score_gpt":0.19480690833967898,"score_spread":0.1855394239217533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312887229","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":[0.90553933,0.000254455,0.00066594227,0.015281037,0.001042623,0.00061374507,0.0000017078797,0.00027748392,0.07632365],"genre_scores_gemma":[0.9950537,0.0000015104193,0.0019025767,0.0004166769,0.000037890877,0.00004420383,6.040225e-8,0.0000057102707,0.0025376824],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988766,0.0000094517445,0.00016852128,0.00022776796,0.000525398,0.00019230893],"domain_scores_gemma":[0.9995528,0.000022963219,0.00015398949,0.00020112132,0.00003733232,0.000031780455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037589407,0.00008353868,0.00009561672,0.00006255477,0.00034654746,0.000048258822,0.001846067,0.000008411911,0.000018116789],"category_scores_gemma":[0.000019214469,0.000059161,0.00009630411,0.00042305313,0.000026736496,0.000015706859,0.0032870653,0.00012436589,0.0000045900756],"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":[0.000026032449,0.000697724,0.00572013,0.00018179046,0.00015638476,0.000004422975,0.0072546806,0.010323007,0.012495588,0.79060256,0.11726051,0.055277154],"study_design_scores_gemma":[0.0028276779,0.0010938852,0.01978599,0.00017841355,0.0000950201,0.00018274158,0.0032884139,0.14832342,0.09244895,0.058749057,0.6718451,0.0011813645],"about_ca_topic_score_codex":0.000023116103,"about_ca_topic_score_gemma":2.2781205e-7,"teacher_disagreement_score":0.73185354,"about_ca_system_score_codex":0.00008160265,"about_ca_system_score_gemma":0.000017180526,"threshold_uncertainty_score":0.40970916},"labels":[],"label_agreement":null},{"id":"W4312987091","doi":"10.14778/3565816.3565818","title":"Online schema evolution is (almost) free for snapshot databases","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Distributed systems and fault tolerance","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":"Simon Fraser University","funders":"","keywords":"Computer science; Schema evolution; Schema migration; Database schema; Schema (genetic algorithms); Snapshot (computer storage); Database; Information retrieval; Semi-structured model; Database design","score_opus":0.02804371284440938,"score_gpt":0.25714350070823433,"score_spread":0.22909978786382496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312987091","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":[0.73476917,0.0051922956,0.16741663,0.049876064,0.006757501,0.008816028,0.012966943,0.00068376405,0.0135216],"genre_scores_gemma":[0.984235,0.00000767776,0.014364483,0.00043495267,0.00010320108,0.00032276465,0.000038365062,0.000010877537,0.00048267673],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99852526,0.0000067744095,0.00031356854,0.00036092085,0.00052969635,0.00026379264],"domain_scores_gemma":[0.99905175,0.000030757787,0.0002903456,0.0003860047,0.00019193496,0.000049219878],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037852017,0.00013296741,0.00018452776,0.000054373875,0.0003391559,0.0000497334,0.0018707587,0.000017039996,0.00003530133],"category_scores_gemma":[0.000091794565,0.000102873,0.00012976896,0.00043713296,0.00003474025,0.0003306294,0.0014289621,0.00011986656,0.0000012422772],"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":[0.00007482882,0.0011514825,0.0031648828,0.0003739139,0.00011549989,8.124632e-7,0.0012675419,0.00015263693,0.05419257,0.5234749,0.4124197,0.0036112664],"study_design_scores_gemma":[0.00425622,0.00073128636,0.004584511,0.00029499375,0.00008674161,0.000107276355,0.002232638,0.066686705,0.16999047,0.024809372,0.72537136,0.00084841746],"about_ca_topic_score_codex":0.00009140312,"about_ca_topic_score_gemma":0.0000029877492,"teacher_disagreement_score":0.49866548,"about_ca_system_score_codex":0.00016255544,"about_ca_system_score_gemma":0.000053467465,"threshold_uncertainty_score":0.4195039},"labels":[],"label_agreement":null},{"id":"W4312989454","doi":"10.14778/3554821.3554864","title":"CERTEM","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and 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 Toronto","funders":"","keywords":"Counterfactual thinking; Computer science; Debugging; Order (exchange); Matching (statistics); State (computer science); Artificial intelligence; Programming language; Epistemology; Mathematics; Philosophy","score_opus":0.15111650697305168,"score_gpt":0.36334862928504613,"score_spread":0.21223212231199445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312989454","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":[0.53809255,0.0002681255,0.00020710441,0.045273386,0.0028318563,0.0017611758,0.00020573886,0.00012971419,0.41123036],"genre_scores_gemma":[0.98736215,0.000005397933,0.00023851325,0.0009930928,0.00003097232,0.00008245711,9.2624504e-7,0.000005511134,0.01128096],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970824,0.000027909195,0.00043657777,0.0002919813,0.0019832933,0.00017785195],"domain_scores_gemma":[0.99910545,0.00011003951,0.0003467173,0.00027720293,0.00011902891,0.000041532097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033835822,0.000080759426,0.0001556302,0.00011181532,0.00033136888,0.00010189803,0.0021313764,0.00001009337,0.00083877996],"category_scores_gemma":[0.00048715516,0.00004940535,0.00012511532,0.0006803476,0.00006181779,0.00019040935,0.002684553,0.00011771538,0.000055046767],"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":[0.000058427693,0.00034138578,0.0037109056,0.000025704463,0.00004996509,6.4963194e-7,0.0019254583,0.00010779127,0.0065438417,0.30644527,0.65225214,0.028538445],"study_design_scores_gemma":[0.00033387492,0.000091145674,0.0034412453,0.0000060549437,0.000017886538,0.0000054992192,0.007972308,0.00017091559,0.008237335,0.09827807,0.8813429,0.00010279608],"about_ca_topic_score_codex":0.00004756431,"about_ca_topic_score_gemma":0.0000022901604,"teacher_disagreement_score":0.44926962,"about_ca_system_score_codex":0.00007334291,"about_ca_system_score_gemma":0.000016999908,"threshold_uncertainty_score":0.91840523},"labels":[],"label_agreement":null},{"id":"W4312990730","doi":"10.14778/3554821.3554858","title":"POEM","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Neural Network Applications","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":"","keywords":"Computer science; Artificial intelligence; Poetry; Image (mathematics); Convolutional neural network; Inference; Modular design; Bedroom; Deep learning; Pattern recognition (psychology); Machine learning; Art; Geography","score_opus":0.012971825591411225,"score_gpt":0.22596645889845804,"score_spread":0.21299463330704682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312990730","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":[0.6240905,0.00149683,0.06292016,0.114053525,0.0035016348,0.0062897764,0.000041929416,0.0017339077,0.18587172],"genre_scores_gemma":[0.986137,0.000007770871,0.012153956,0.00052129506,0.00002865602,0.0002450434,1.8929632e-7,0.000006085034,0.0009000435],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991697,0.000004042843,0.0001409162,0.0002029101,0.000326633,0.00015577985],"domain_scores_gemma":[0.99956447,0.000021252608,0.00014811286,0.0001893544,0.000046374877,0.000030430787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012451805,0.00006671644,0.00007329701,0.000032142598,0.00028380615,0.000020856576,0.0015475412,0.000007002151,0.000017620405],"category_scores_gemma":[0.000011375244,0.000050597086,0.00005613212,0.00053542847,0.000026527263,0.00014531171,0.0015696728,0.00012323803,0.000004760373],"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":[0.0000060454636,0.00012863877,0.0009461279,0.000012454342,0.000014132651,2.554929e-7,0.000555896,0.0011586484,0.057644315,0.90927905,0.017226523,0.013027898],"study_design_scores_gemma":[0.0008953139,0.0002904406,0.0041278475,0.00002312884,0.000025277377,0.000115915565,0.000419084,0.018265372,0.3320203,0.28672063,0.3566057,0.0004909401],"about_ca_topic_score_codex":0.000003549028,"about_ca_topic_score_gemma":1.4490983e-7,"teacher_disagreement_score":0.6225584,"about_ca_system_score_codex":0.00007228728,"about_ca_system_score_gemma":0.000012752453,"threshold_uncertainty_score":0.28757423},"labels":[],"label_agreement":null},{"id":"W4313065965","doi":"10.14778/3551793.3551853","title":"Spooky","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Data Storage Technologies","field":"Computer Science","cited_by":50,"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":"Merge (version control); Computer science; Granularity; Associative array; Data structure; Parallel computing; Operating system; Programming language","score_opus":0.01181195605712601,"score_gpt":0.21574701719651604,"score_spread":0.20393506113939003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313065965","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":[0.6994852,0.004030131,0.07107375,0.07065836,0.006296491,0.005331377,0.00017595115,0.006597687,0.13635105],"genre_scores_gemma":[0.9700024,0.000015046574,0.02909995,0.00020416013,0.000011425601,0.000113893526,2.3624067e-7,0.000006437783,0.0005464444],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990152,0.0000032939115,0.0001488963,0.00023612546,0.0004123539,0.0001841278],"domain_scores_gemma":[0.99944913,0.000017046601,0.00017015259,0.00030167444,0.000042721225,0.000019259778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017359323,0.00008467878,0.000099378194,0.000070830865,0.00021389812,0.000027999122,0.0027647177,0.000012949984,0.0000314626],"category_scores_gemma":[0.00006500297,0.000062693776,0.00005383142,0.00048773727,0.00006093732,0.0002997795,0.0042267833,0.00017067014,0.0000065009945],"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":[0.000006709241,0.00015118167,0.0010438033,0.000029224695,0.00002361626,0.000002089613,0.0007865943,0.00014891243,0.044917148,0.8988926,0.021766154,0.03223196],"study_design_scores_gemma":[0.000829141,0.00040808856,0.0010242441,0.00002966553,0.000019595755,0.00013536982,0.001463115,0.005643093,0.53638,0.23221758,0.22136521,0.0004848736],"about_ca_topic_score_codex":0.0000061712303,"about_ca_topic_score_gemma":1.2999537e-7,"teacher_disagreement_score":0.66667503,"about_ca_system_score_codex":0.00011521271,"about_ca_system_score_gemma":0.000009302494,"threshold_uncertainty_score":0.5268383},"labels":[],"label_agreement":null},{"id":"W4313152108","doi":"10.14778/3561261.3561263","title":"The case for distributed shared-memory databases with RDMA-enabled memory disaggregation","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Data Storage Technologies","field":"Computer Science","cited_by":33,"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":"Remote direct memory access; Scalability; Computer science; Shared memory; Database; Distributed memory; Scaling; Memory management; Operating system; Semiconductor memory","score_opus":0.01966093503013673,"score_gpt":0.2441219501968502,"score_spread":0.22446101516671346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313152108","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":[0.44393736,0.0030101857,0.49184886,0.035985302,0.0021170175,0.012583489,0.0059748497,0.0029098177,0.0016331221],"genre_scores_gemma":[0.9633692,0.000026984822,0.034480687,0.00013235652,0.000037059093,0.0015931432,0.00005164679,0.000022356915,0.00028658423],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985098,0.000012434827,0.00027187905,0.00043289948,0.00042629652,0.00034667877],"domain_scores_gemma":[0.99850005,0.00022685688,0.000443779,0.0006142683,0.00017619932,0.00003883311],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052005285,0.00017990745,0.00016413853,0.000060779887,0.0012232185,0.0001271685,0.002133181,0.000017896755,0.0000058622563],"category_scores_gemma":[0.00039415184,0.000103260354,0.00006668813,0.0005869945,0.00018262248,0.00081211136,0.0025694193,0.00020169471,8.5037124e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010588729,0.0011409628,0.0011634274,0.00078671495,0.00056232716,0.0002371455,0.0043870853,0.006580694,0.039469805,0.5475175,0.13644047,0.26065502],"study_design_scores_gemma":[0.00695868,0.0020047366,0.00045574343,0.000324373,0.0002966239,0.004265939,0.0326381,0.053821802,0.7006986,0.067339376,0.12943706,0.0017589364],"about_ca_topic_score_codex":0.000051306233,"about_ca_topic_score_gemma":0.00001879571,"teacher_disagreement_score":0.66122884,"about_ca_system_score_codex":0.00023568427,"about_ca_system_score_gemma":0.000054375327,"threshold_uncertainty_score":0.9408132},"labels":[],"label_agreement":null},{"id":"W4313172799","doi":"10.14778/3551793.3551826","title":"Finding locally densest subgraphs","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":19,"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":"Graph; Graph factorization; Computer science; Combinatorics; Regular polygon; Pruning; Theoretical computer science; Mathematics; Graph power; Biology; Line graph","score_opus":0.009705402500551377,"score_gpt":0.20046701625810603,"score_spread":0.19076161375755465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313172799","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":[0.9679524,0.00038563638,0.0074203047,0.003781439,0.0018893235,0.0008882583,0.000013510713,0.00029735567,0.01737181],"genre_scores_gemma":[0.9956981,0.0000066755942,0.0034565218,0.00033036343,0.000024732379,0.0000735543,2.5526492e-7,0.000008054468,0.00040177623],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987021,0.000015958602,0.00021752587,0.0002844289,0.0005093694,0.00027062965],"domain_scores_gemma":[0.99944764,0.000038342176,0.00019179453,0.00019430528,0.0000737476,0.000054182845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059449614,0.000121539095,0.0001335959,0.00012201344,0.0004836708,0.0000706572,0.0018813096,0.00001688623,0.000035562844],"category_scores_gemma":[0.000029472769,0.00009210049,0.00014664138,0.000776655,0.000067511544,0.00021484964,0.0013177794,0.00020280103,0.0000044646945],"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":[0.00002117544,0.00022076086,0.0052275932,0.000042767675,0.000054402786,0.0000033052686,0.0023746733,0.00020805998,0.032078724,0.9485599,0.0020420232,0.0091666365],"study_design_scores_gemma":[0.0020074388,0.00090086577,0.008921229,0.00012689676,0.000071575436,0.00034887623,0.0025856306,0.010345114,0.41376334,0.53974783,0.020240534,0.0009406414],"about_ca_topic_score_codex":0.000010224595,"about_ca_topic_score_gemma":3.609443e-7,"teacher_disagreement_score":0.40881202,"about_ca_system_score_codex":0.000054906875,"about_ca_system_score_gemma":0.000028142973,"threshold_uncertainty_score":0.3755749},"labels":[],"label_agreement":null},{"id":"W4317767745","doi":"10.14778/3570690.3570700","title":"FirmTruss Community Search in Multilayer Networks","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":25,"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":"Computer science; Community structure; Homophily; Theoretical computer science; Approximation algorithm; Mathematical optimization; Algorithm; Mathematics","score_opus":0.01712011195363708,"score_gpt":0.25401919604076983,"score_spread":0.23689908408713276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317767745","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":[0.98727757,0.00004621638,0.00013503291,0.0002832355,0.000051777522,0.000423897,0.000008468025,0.00003226161,0.011741573],"genre_scores_gemma":[0.9991479,0.000002513561,0.00028861273,0.00005389192,0.000059367536,0.00018844075,0.0000045745583,0.000013992305,0.00024072554],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989715,0.000057586207,0.00027082718,0.00014284707,0.00029832663,0.0002589174],"domain_scores_gemma":[0.9995155,0.000058604986,0.00014041206,0.00019319974,0.000059800524,0.000032494143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007919746,0.000118791664,0.0002031512,0.00008451203,0.000372327,0.000024642302,0.00079292466,0.000013187935,0.00039351307],"category_scores_gemma":[0.0000040735886,0.00009704953,0.00014628578,0.0005387555,0.00005060262,0.00005867445,0.0013925815,0.0007094116,9.889073e-7],"study_design_candidate":"observational","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":[0.00007793749,0.0012401119,0.91497236,0.00003294164,0.000173086,2.6493112e-7,0.003001417,0.018941114,0.0055871517,0.0333086,0.007966531,0.014698475],"study_design_scores_gemma":[0.006327161,0.00094627566,0.31492037,0.00040344408,0.00039639525,0.000010812161,0.03755207,0.33591494,0.15964647,0.10204114,0.039611682,0.0022292614],"about_ca_topic_score_codex":0.0019946888,"about_ca_topic_score_gemma":0.000015819458,"teacher_disagreement_score":0.600052,"about_ca_system_score_codex":0.000108669905,"about_ca_system_score_gemma":0.000015026021,"threshold_uncertainty_score":0.43086922},"labels":[],"label_agreement":null},{"id":"W4317767825","doi":"10.14778/3570690.3570704","title":"FILM","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Data Storage Technologies","field":"Computer Science","cited_by":27,"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":"Computer science; Search engine indexing; Overhead (engineering); Data structure; Range query (database); Parallel computing; Auxiliary memory; Database; Distributed computing; Information retrieval; Operating system; Sargable; Search engine; Web search query","score_opus":0.012163401002412973,"score_gpt":0.2179784930603923,"score_spread":0.20581509205797932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317767825","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":[0.63223785,0.003234373,0.13496497,0.073210925,0.006766968,0.005646385,0.0002496625,0.006957941,0.13673091],"genre_scores_gemma":[0.96520203,0.000010008324,0.033901475,0.00024243878,0.000010977215,0.0001339222,3.8832226e-7,0.000006235781,0.0004924933],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99903953,0.0000034048435,0.00014605986,0.00023215373,0.0003977351,0.0001811219],"domain_scores_gemma":[0.999455,0.000018532537,0.00016703608,0.0002957349,0.000045142784,0.000018553807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018542437,0.00008196872,0.00009648458,0.00006665917,0.00022133946,0.00002768872,0.002763104,0.000012912773,0.0000238791],"category_scores_gemma":[0.00007652559,0.000060306535,0.000052393607,0.00049475266,0.000059069625,0.00029643142,0.0044433954,0.0001688296,0.000004578487],"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":[0.000008838451,0.00013614068,0.0009539518,0.00003029165,0.000024211593,0.000001758685,0.00083542103,0.00039929518,0.04982453,0.8955407,0.030757895,0.021486973],"study_design_scores_gemma":[0.0006821784,0.00034953374,0.0010128969,0.000024868954,0.000015116037,0.00009711571,0.0017548862,0.005205652,0.58286905,0.23057239,0.17702448,0.00039184687],"about_ca_topic_score_codex":0.0000075525036,"about_ca_topic_score_gemma":1.9224208e-7,"teacher_disagreement_score":0.6649683,"about_ca_system_score_codex":0.000109420565,"about_ca_system_score_gemma":0.000016630496,"threshold_uncertainty_score":0.5538375},"labels":[],"label_agreement":null},{"id":"W4321448317","doi":"10.14778/3574245.3574246","title":"Cache Me If You Can","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Privacy-Preserving Technologies in Data","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":"University of Waterloo","funders":"","keywords":"Computer science; Differential privacy; Cache; Workload; Private information retrieval; CPU cache; Process (computing); Differential (mechanical device); Query optimization; Information retrieval; Data mining; Computer network; Computer security; Operating system","score_opus":0.023773982768973453,"score_gpt":0.23969471304651568,"score_spread":0.21592073027754222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321448317","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":[0.48138314,0.00082426704,0.0028881715,0.47672677,0.0031385508,0.0022652354,0.00018188462,0.002557931,0.030034028],"genre_scores_gemma":[0.96342427,0.000020371626,0.035602342,0.0004026627,0.000026315704,0.00017200712,0.0000013204624,0.000013033245,0.0003376648],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982344,0.000011994438,0.00025254473,0.00042986256,0.0007211846,0.00035003494],"domain_scores_gemma":[0.9973161,0.00003538716,0.00025246872,0.0022716168,0.00008019226,0.00004420817],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0006107194,0.00014570517,0.00016479418,0.00011107884,0.00032285444,0.000077710865,0.036583107,0.00003402596,0.000032936805],"category_scores_gemma":[0.0025444215,0.00011187868,0.00008577237,0.00073193875,0.00009329498,0.00025338805,0.15633816,0.00034789514,0.000004186477],"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":[0.000020743779,0.00036942042,0.009592274,0.00011337395,0.00013710986,0.0000047876297,0.0017970385,0.00006224915,0.08289924,0.124800526,0.76119584,0.01900738],"study_design_scores_gemma":[0.0007433558,0.0002748206,0.0016179013,0.000046142904,0.00003311268,0.00009412013,0.0011367976,0.017798765,0.40735525,0.51782644,0.052598637,0.0004746615],"about_ca_topic_score_codex":0.00012806457,"about_ca_topic_score_gemma":0.0000017143349,"teacher_disagreement_score":0.70859724,"about_ca_system_score_codex":0.00027134866,"about_ca_system_score_gemma":0.00005250814,"threshold_uncertainty_score":0.9686294},"labels":[],"label_agreement":null},{"id":"W4321448342","doi":"10.14778/3574245.3574273","title":"On Efficient Approximate Queries over Machine Learning Models","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Machine Learning and Algorithms","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":"University of British Columbia","funders":"Agence Nationale de la Recherche","keywords":"Oracle; Computer science; Heuristic; Quality (philosophy); Random oracle; Machine learning; Artificial intelligence; Data mining; Theoretical computer science; Information retrieval; Programming language","score_opus":0.011615232348690043,"score_gpt":0.2104266141063533,"score_spread":0.19881138175766325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321448342","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":[0.91286707,0.0006099934,0.03276918,0.0062808227,0.0015829197,0.0012849842,0.000022425334,0.00083681586,0.04374577],"genre_scores_gemma":[0.9948067,0.0000067071355,0.0034758125,0.00024417517,0.000028720931,0.00008645527,9.852125e-7,0.000015625108,0.0013348022],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99830544,0.00003059281,0.00023102148,0.00036905863,0.00077139615,0.00029251515],"domain_scores_gemma":[0.9993998,0.000047604703,0.0002580055,0.00018914239,0.000052852472,0.000052629104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060503714,0.0001687919,0.00018065184,0.00010657921,0.00058907294,0.00009077561,0.0011765138,0.000018122899,0.000045658384],"category_scores_gemma":[0.000055240875,0.00011928632,0.00012031499,0.00040655458,0.00004167911,0.0001181296,0.0014752323,0.0004972352,0.0000033519282],"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":[0.00004129985,0.00031019494,0.00079362764,0.00006430878,0.000037278412,0.0000013720656,0.003496643,0.45708725,0.0033401726,0.5279143,0.0007094203,0.006204132],"study_design_scores_gemma":[0.00041043022,0.000250817,0.0001357919,0.000025517367,0.000007677729,0.000014518399,0.00012315925,0.9787383,0.0055315276,0.011891608,0.002710026,0.00016060327],"about_ca_topic_score_codex":0.00009070305,"about_ca_topic_score_gemma":2.5011136e-7,"teacher_disagreement_score":0.5216511,"about_ca_system_score_codex":0.000099885416,"about_ca_system_score_gemma":0.00002136491,"threshold_uncertainty_score":0.4864355},"labels":[],"label_agreement":null},{"id":"W4323343708","doi":"10.14778/3579075.3579080","title":"Change Propagation Without Joins","year":2023,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":15,"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; Computer science; Query plan; Latency (audio); Query optimization; Constant (computer programming); Operator (biology); Theoretical computer science; Plan (archaeology); Space (punctuation); Distributed computing; Information retrieval; Sargable; Search engine; Web search query; Telecommunications","score_opus":0.040322326480228064,"score_gpt":0.2605863433371262,"score_spread":0.22026401685689814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323343708","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":[0.83750457,0.00057617296,0.08935692,0.02790295,0.0047899517,0.00772509,0.0000955238,0.0029021287,0.02914669],"genre_scores_gemma":[0.9874137,0.000043393426,0.011069729,0.00014923143,0.00013975037,0.0002627166,0.000001975067,0.000010910877,0.00090861315],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999108,0.000003970711,0.00017601404,0.0002091359,0.00031338914,0.00018946892],"domain_scores_gemma":[0.99950475,0.000009666958,0.00017141321,0.00017130995,0.00010748125,0.000035356938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025020947,0.00009145958,0.00011656978,0.00007117084,0.00011215403,0.000028861528,0.0004252658,0.000019737077,0.0000021498577],"category_scores_gemma":[0.00004625134,0.00005776369,0.00004753809,0.00054070953,0.000036246387,0.0006464584,0.00048399385,0.000056721743,0.00003159224],"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":[0.000009753016,0.000055047283,0.007950511,0.00028641577,0.000027139118,9.324026e-7,0.004131531,0.000009618399,0.08677301,0.8786518,0.004633863,0.017470395],"study_design_scores_gemma":[0.0012017128,0.00029078417,0.037631355,0.0007885854,0.000028796714,0.000046007204,0.0011428202,0.016466072,0.7530881,0.013489779,0.1751709,0.00065509824],"about_ca_topic_score_codex":0.000036161182,"about_ca_topic_score_gemma":0.0000031311383,"teacher_disagreement_score":0.865162,"about_ca_system_score_codex":0.000031909723,"about_ca_system_score_gemma":0.000013983528,"threshold_uncertainty_score":0.23555349},"labels":[],"label_agreement":null},{"id":"W4323343774","doi":"10.14778/3579075.3579091","title":"A Hierarchical Grouping Algorithm for the Multi-Vehicle Dial-a-Ride Problem","year":2023,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Transportation and Mobility Innovations","field":"Engineering","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":"Polytechnique Montréal","funders":"","keywords":"Computer science; Latency (audio); Set (abstract data type); State (computer science); Destinations; Algorithm; Point (geometry); Mathematical optimization; Mathematics; Telecommunications","score_opus":0.021500584599856626,"score_gpt":0.24308542913708225,"score_spread":0.22158484453722563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323343774","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":[0.85583806,0.0003652159,0.10814803,0.017225808,0.0021843347,0.009728078,0.00040648784,0.0028979324,0.003206042],"genre_scores_gemma":[0.9828841,0.000058101785,0.015603866,0.0001097618,0.00009264099,0.00088003743,0.000009185936,0.000033007356,0.00032931677],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991977,0.0000016242032,0.00027221185,0.00012695156,0.00017874994,0.00022274777],"domain_scores_gemma":[0.99965256,0.00008150792,0.000047435653,0.00008586261,0.00010131075,0.000031325788],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002793113,0.000104459126,0.00010788987,0.000062813946,0.00015471487,0.000028944176,0.00025654852,0.000036026093,0.000006583021],"category_scores_gemma":[0.000033490236,0.0000667855,0.00009998112,0.0004926745,0.00005563331,0.00008325866,0.000032364627,0.00013188884,0.000006048555],"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":[0.000060542665,0.0005038825,0.008156665,0.0017127979,0.0009358429,0.0000011509861,0.017110059,0.024704887,0.424715,0.11381201,0.022812763,0.3854744],"study_design_scores_gemma":[0.0031593272,0.00010522007,0.062317044,0.00023148333,0.00018989733,0.000006407295,0.0021865845,0.7090432,0.16999955,0.0080062,0.044226628,0.00052842556],"about_ca_topic_score_codex":0.000017424129,"about_ca_topic_score_gemma":0.000009848003,"teacher_disagreement_score":0.68433833,"about_ca_system_score_codex":0.00003663631,"about_ca_system_score_gemma":0.000010979422,"threshold_uncertainty_score":0.27234337},"labels":[],"label_agreement":null},{"id":"W4323343874","doi":"10.14778/3579075.3579086","title":"On the Risks of Collecting Multidimensional Data Under Local Differential Privacy","year":2023,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Agence Nationale de la Recherche","keywords":"Differential privacy; Computer science; Robustness (evolution); Inference; Data mining; Population; Identification (biology); Hash function; Computer security; Artificial intelligence","score_opus":0.15583339640858118,"score_gpt":0.33671182075033285,"score_spread":0.18087842434175166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323343874","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":[0.9251988,0.000045245928,0.019337168,0.052239425,0.00075944443,0.0009293079,0.000085961714,0.00056902034,0.00083565596],"genre_scores_gemma":[0.9860856,0.000027509966,0.0136529775,0.000108875705,0.000024845678,0.000028214496,0.000004969456,0.000013229636,0.0000537662],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997899,0.000021750368,0.00036877563,0.000532022,0.0008329331,0.00034551413],"domain_scores_gemma":[0.99495,0.0006005464,0.0003721316,0.0039048549,0.0001373243,0.000035127126],"candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00083359575,0.00017668067,0.00021324257,0.00013586311,0.0002515823,0.000060433904,0.030497944,0.00007414406,0.0000147696555],"category_scores_gemma":[0.009758117,0.00010036176,0.000074345124,0.0010571056,0.0002629001,0.00028905357,0.13577957,0.00032013076,0.000014083817],"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":[0.000087350134,0.00048557267,0.0021727732,0.0001780759,0.00032211313,0.0000020068796,0.0005991977,0.00028198495,0.09472903,0.23101535,0.65755266,0.012573865],"study_design_scores_gemma":[0.00073911715,0.00013833243,0.006415383,0.00029912835,0.00003473987,0.000008855093,0.00041700283,0.34999514,0.34409344,0.2970413,0.00057367363,0.00024389446],"about_ca_topic_score_codex":0.00008053943,"about_ca_topic_score_gemma":0.0000020201019,"teacher_disagreement_score":0.656979,"about_ca_system_score_codex":0.0000805585,"about_ca_system_score_gemma":0.000055970413,"threshold_uncertainty_score":0.99858314},"labels":[],"label_agreement":null},{"id":"W4366660614","doi":"10.14778/3583140.3583159","title":"NV-SQL: Boosting OLTP Performance with Non-Volatile DIMMs","year":2023,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Cloud Computing and Resource Management","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":"Simon Fraser University","funders":"","keywords":"Computer science; SQL; Operating system; Commit; Online transaction processing; Cache; In-Memory Processing; Database; Overhead (engineering); Parallel computing; Database transaction; Transaction processing; Query by Example; World Wide Web","score_opus":0.008316156622858105,"score_gpt":0.189260400132968,"score_spread":0.18094424351010988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366660614","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":[0.9812495,0.000025997853,0.00035254323,0.0015478156,0.0002482354,0.00036145153,4.1196256e-7,0.00029498685,0.015919037],"genre_scores_gemma":[0.9949234,0.000009487855,0.0023109817,0.00012561517,0.000084732674,0.000028307182,2.481352e-7,0.000015420113,0.0025017778],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99839324,0.000004647995,0.00025471346,0.0003701093,0.0005696878,0.00040757895],"domain_scores_gemma":[0.99928284,0.00004139417,0.00023455695,0.00027298683,0.00010674416,0.00006148154],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000469092,0.00017590432,0.000179212,0.00011976788,0.0002742361,0.0001229392,0.0013707898,0.000029087538,0.0000032560088],"category_scores_gemma":[0.000025754516,0.00010770192,0.000077062396,0.0010256239,0.00006002485,0.00006851617,0.001340201,0.00015310549,0.000040094226],"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":[0.00032577684,0.0011437905,0.30029288,0.0040661315,0.0010528589,0.000032517288,0.04438849,0.09237169,0.05130429,0.054665186,0.082231954,0.36812446],"study_design_scores_gemma":[0.0014410457,0.0005968368,0.07195686,0.0011262099,0.00005896962,0.00003612937,0.0008213586,0.8289937,0.082346134,0.001170011,0.010794965,0.00065781275],"about_ca_topic_score_codex":0.00002734576,"about_ca_topic_score_gemma":6.611263e-7,"teacher_disagreement_score":0.736622,"about_ca_system_score_codex":0.000054524462,"about_ca_system_score_gemma":0.000023086632,"threshold_uncertainty_score":0.4391957},"labels":[],"label_agreement":null},{"id":"W4366660902","doi":"10.14778/3583140.3583143","title":"<i> B <sup>link</sup> </i> -hash: An Adaptive Hybrid Index for In-Memory Time-Series Databases","year":2023,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":14,"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; Hash function; B-tree; Scalability; Hash table; Node (physics); Merkle tree; Parallel computing; Timestamp; Throughput; Tree (set theory); Data structure; Computer network; Cryptographic hash function; Database; Mathematics; Operating system","score_opus":0.025771553727448302,"score_gpt":0.2545432789060886,"score_spread":0.22877172517864028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366660902","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":[0.6669978,0.0011688846,0.28754517,0.011924175,0.0024571111,0.012053829,0.0031711909,0.002718899,0.0119629605],"genre_scores_gemma":[0.8786419,0.00016345194,0.11529728,0.0006073564,0.0005793879,0.001157115,0.00009719029,0.000090878086,0.0033654065],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9981773,0.000013583224,0.00042318777,0.00053992,0.00040234876,0.00044368635],"domain_scores_gemma":[0.9989497,0.000102678525,0.0002526967,0.00041781366,0.00018813633,0.000088977096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056800735,0.00023337286,0.00032276614,0.0001702937,0.00018627943,0.000053698765,0.00092373614,0.000030008072,0.0000062503987],"category_scores_gemma":[0.00015869622,0.0001737244,0.000098672084,0.00058769295,0.00012362516,0.0019438872,0.00090719876,0.00013360084,0.000021756272],"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":[0.001175797,0.0008262892,0.0069130477,0.0016022227,0.00029525743,0.000035929872,0.012434653,0.010377304,0.072421335,0.7483891,0.07268095,0.07284807],"study_design_scores_gemma":[0.004587405,0.0016981515,0.002510068,0.0014023397,0.00006796057,0.00014367804,0.007869267,0.18880917,0.5922321,0.026433678,0.17246029,0.0017859064],"about_ca_topic_score_codex":0.00009555452,"about_ca_topic_score_gemma":0.000014347358,"teacher_disagreement_score":0.7219555,"about_ca_system_score_codex":0.00006359323,"about_ca_system_score_gemma":0.000068001915,"threshold_uncertainty_score":0.70842755},"labels":[],"label_agreement":null},{"id":"W4385653228","doi":"10.14778/3603581.3603585","title":"Autonomously Computable Information Extraction","year":2023,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Web Data Mining and Analysis","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":"","keywords":"Computer science; Information extraction; Perspective (graphical); Mechanism (biology); Data mining; Relation (database); Information retrieval; Artificial intelligence","score_opus":0.01020545676619336,"score_gpt":0.2254807868001845,"score_spread":0.21527533003399113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385653228","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":[0.8391898,0.0000694075,0.06641932,0.020732034,0.0022905716,0.0010468714,0.000034573175,0.0022194383,0.067997985],"genre_scores_gemma":[0.99331427,0.00001570547,0.006013122,0.00012180819,0.000031747317,0.000016774617,0.0000044493986,0.000003154154,0.00047895545],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992123,0.000003205348,0.0002170793,0.0001231146,0.00028299948,0.00016129202],"domain_scores_gemma":[0.9994956,0.000020481642,0.00019912401,0.00014206022,0.00011088332,0.000031809137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003585978,0.0000720745,0.00009765203,0.00014755146,0.00012160036,0.00015915558,0.0007093994,0.000024056728,0.000005630097],"category_scores_gemma":[0.000048254453,0.000051558298,0.00006661686,0.0008523987,0.00001855208,0.0013379552,0.00037759953,0.00006965925,0.00013326874],"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":[0.000024766005,0.00028624453,0.013327416,0.00044803755,0.0003277726,0.0000015024536,0.010677327,0.008057961,0.074668474,0.28943542,0.23758183,0.36516324],"study_design_scores_gemma":[0.00083452486,0.0001420553,0.021178717,0.00016721495,0.00007103456,0.000030632025,0.0011279739,0.6878336,0.15983042,0.011190199,0.11714959,0.00044401106],"about_ca_topic_score_codex":0.000055987548,"about_ca_topic_score_gemma":4.753452e-7,"teacher_disagreement_score":0.67977566,"about_ca_system_score_codex":0.000040123556,"about_ca_system_score_gemma":0.000022759064,"threshold_uncertainty_score":0.21024863},"labels":[],"label_agreement":null},{"id":"W4386123456","doi":"10.14778/3611479.3611516","title":"Scaling Up Structural Clustering to Large Probabilistic Graphs Using Lyapunov Central Limit Theorem","year":2023,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","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 Victoria","funders":"","keywords":"Cluster analysis; Probabilistic logic; Theoretical computer science; Correlation clustering; Computer science; Mathematics; Algorithm; Artificial intelligence","score_opus":0.02037009250056965,"score_gpt":0.27360625782669246,"score_spread":0.2532361653261228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386123456","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":[0.9965221,0.000012972541,0.0010718977,0.00013931977,0.00021257438,0.00066193123,0.000020582265,0.0001521508,0.0012064683],"genre_scores_gemma":[0.99781615,0.0000015731923,0.0017700705,0.00003381035,0.00019075998,0.000046823992,0.000005762328,0.000030869753,0.000104186736],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983408,0.000011134536,0.00038408613,0.00033344436,0.0003305329,0.0005999929],"domain_scores_gemma":[0.99933034,0.000040434767,0.00021636553,0.00017811575,0.00013342453,0.000101320154],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032010363,0.00022516944,0.00029201535,0.00014980262,0.0002596536,0.000096209274,0.0005165204,0.000028190072,0.000070867056],"category_scores_gemma":[0.000025546131,0.00016729317,0.00025912866,0.00089724245,0.000049223145,0.00011411724,0.00070459396,0.00015152915,0.0000044899625],"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":[0.00018375908,0.00021274283,0.31328404,0.00039975453,0.0008624966,0.0000010663455,0.008271181,0.019683402,0.12258802,0.5069573,0.0033646293,0.024191603],"study_design_scores_gemma":[0.0017872029,0.00015206666,0.053569052,0.0011750472,0.00070232875,0.00000754171,0.0056290524,0.41303736,0.15345983,0.36669376,0.0022655104,0.0015212622],"about_ca_topic_score_codex":0.00013790997,"about_ca_topic_score_gemma":0.000005705366,"teacher_disagreement_score":0.39335394,"about_ca_system_score_codex":0.000089064175,"about_ca_system_score_gemma":0.000020041663,"threshold_uncertainty_score":0.68220174},"labels":[],"label_agreement":null},{"id":"W4386128170","doi":"10.14778/3611479.3611493","title":"Semi-Oblivious Chase Termination for Linear Existential Rules: An Experimental Study","year":2023,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","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":"Western University","funders":"Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Chase; Set (abstract data type); Class (philosophy); Focus (optics); Existential quantification; Existentialism; Theoretical computer science; Implementation; Key (lock); Algorithm; Programming language; Database; Artificial intelligence; Mathematics; Computer security","score_opus":0.0371439558842468,"score_gpt":0.3083710072932785,"score_spread":0.2712270514090317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386128170","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":[0.9928727,0.00002210111,0.001990473,0.0005053973,0.0007868177,0.002162327,0.000028143277,0.000319892,0.0013121088],"genre_scores_gemma":[0.99344987,0.000004879849,0.0049221893,0.00005868208,0.00016537945,0.00033071262,0.000015154686,0.000014271151,0.00103888],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998673,0.0000070300407,0.00024572446,0.0003870617,0.0004330339,0.00025412237],"domain_scores_gemma":[0.99942654,0.00001614866,0.00016616582,0.00024140716,0.00009626859,0.00005346214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049890816,0.00014072358,0.00014129512,0.0001488755,0.00018802407,0.00019068157,0.0013271574,0.00002276348,0.000004552625],"category_scores_gemma":[0.000027498561,0.00010571983,0.00008245828,0.00036827906,0.000032150863,0.0008786215,0.0008622242,0.000051454503,0.00001582575],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004182665,0.025071308,0.00739454,0.0011857076,0.0008322506,0.000032620635,0.08050522,0.00016973027,0.38959378,0.1839927,0.0676931,0.24311078],"study_design_scores_gemma":[0.009569158,0.006787746,0.007942491,0.00022141643,0.0001942136,0.000016657661,0.02194554,0.2898438,0.64228183,0.0076946607,0.012223901,0.0012786065],"about_ca_topic_score_codex":0.00001604763,"about_ca_topic_score_gemma":9.053474e-7,"teacher_disagreement_score":0.28967407,"about_ca_system_score_codex":0.000043285203,"about_ca_system_score_gemma":0.000010694377,"threshold_uncertainty_score":0.43111295},"labels":[],"label_agreement":null},{"id":"W4386128184","doi":"10.14778/3611479.3611518","title":"POEM: Pattern-Oriented Explanations of Convolutional Neural Networks","year":2023,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Explainable Artificial Intelligence (XAI)","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":"","keywords":"Convolutional neural network; Poetry; Computer science; Artificial intelligence; Modular design; Classifier (UML); Image (mathematics); Meaning (existential); Pattern recognition (psychology); Deep learning; Artificial neural network; Machine learning; Psychology; Art; Literature","score_opus":0.023780839036322252,"score_gpt":0.24839148151546825,"score_spread":0.224610642479146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386128184","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":[0.8711274,0.00019797316,0.10632136,0.011544553,0.0024604485,0.0013249279,0.000030036454,0.00051498774,0.006478276],"genre_scores_gemma":[0.99879414,0.00001982221,0.00064500724,0.00014051145,0.000058412374,0.00005100702,0.0000025641789,0.000007901973,0.00028065286],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985599,0.000010486564,0.00038179703,0.00025581525,0.00048199864,0.00031001694],"domain_scores_gemma":[0.999042,0.00008548014,0.00025893605,0.00019167301,0.00036416634,0.000057788082],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035097077,0.00011782238,0.00015503251,0.0001464782,0.0001437958,0.00003819859,0.0010292347,0.00004063396,0.000017262024],"category_scores_gemma":[0.00011009485,0.00009186282,0.00010559919,0.0011322688,0.00010221143,0.00035864324,0.0005516915,0.00011638079,0.000016115402],"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":[0.000032432115,0.00037403195,0.03971645,0.00014964998,0.00013886412,0.0000039361375,0.0045387703,0.02076241,0.04004866,0.8507329,0.024949282,0.01855257],"study_design_scores_gemma":[0.00026198485,0.00013635527,0.012665882,0.00009023737,0.00001953987,0.0000114575,0.00090593996,0.8085448,0.16612725,0.009753057,0.0012645267,0.00021895856],"about_ca_topic_score_codex":0.00010542218,"about_ca_topic_score_gemma":0.000007408744,"teacher_disagreement_score":0.8409799,"about_ca_system_score_codex":0.000057438345,"about_ca_system_score_gemma":0.000026677393,"threshold_uncertainty_score":0.37460572},"labels":[],"label_agreement":null},{"id":"W4386528681","doi":"10.14778/3611540.3611548","title":"Towards General and Efficient Online Tuning for Spark","year":2023,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"Tencent","keywords":"Computer science; Overhead (engineering); SPARK (programming language); Generality; Bayesian optimization; Process (computing); Distributed computing; Cloud computing; Computer engineering; Machine learning","score_opus":0.020878018701399263,"score_gpt":0.2481364875198195,"score_spread":0.22725846881842024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386528681","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":[0.9890393,0.000079363315,0.003516775,0.005140468,0.00035318086,0.00044672415,0.0000032682156,0.00018202979,0.0012388702],"genre_scores_gemma":[0.9828041,0.000009974616,0.015745368,0.00020045138,0.00013607122,0.00003271986,6.3933777e-7,0.00001035329,0.0010602924],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99895155,0.0000040351288,0.00019510918,0.00028994886,0.00028695757,0.00027239893],"domain_scores_gemma":[0.9995751,0.0000323742,0.000121556775,0.0001384575,0.000080799946,0.000051761683],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004398147,0.000113588954,0.00013863361,0.0000990913,0.00017185682,0.000081334554,0.0007000015,0.000023105837,5.5758017e-7],"category_scores_gemma":[0.000052862073,0.00007607516,0.000082212726,0.00042484648,0.000040416915,0.0000124033895,0.0012053575,0.00006382108,0.0000016652782],"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":[0.000072331044,0.000733769,0.0040533817,0.0012945527,0.0003633546,0.000004192872,0.011980705,0.057913635,0.07871843,0.4108082,0.03305833,0.4009991],"study_design_scores_gemma":[0.000606695,0.00011397903,0.007071364,0.000110796034,0.000021035277,0.000006094816,0.0002697366,0.9698384,0.009464739,0.0031604285,0.009174173,0.00016259031],"about_ca_topic_score_codex":0.00002092796,"about_ca_topic_score_gemma":4.9115647e-7,"teacher_disagreement_score":0.9119247,"about_ca_system_score_codex":0.000033455748,"about_ca_system_score_gemma":0.000012367707,"threshold_uncertainty_score":0.3102255},"labels":[],"label_agreement":null},{"id":"W4386768533","doi":"10.14778/3611540.3611599","title":"Demonstration of SPARQL <sup> <i>ML</i> </sup> : An Interfacing Language for Supporting Graph Machine Learning for RDF Graphs","year":2023,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Graph Neural Networks","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":"Concordia University","funders":"","keywords":"SPARQL; Computer science; Named graph; RDF; RDF query language; RDF Schema; Graph; Scripting language; Information retrieval; Query language; Programming language; Web search query; Search engine; Theoretical computer science; Semantic Web; Web query classification","score_opus":0.018095438311099787,"score_gpt":0.27273469682791746,"score_spread":0.2546392585168177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386768533","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":[0.940277,0.00012647767,0.05654213,0.0006691356,0.00020619082,0.001561413,0.000018053584,0.00032162847,0.0002779649],"genre_scores_gemma":[0.9767904,0.000020050622,0.022802442,0.00006249104,0.000046815916,0.00015840791,0.000010106351,0.000025179366,0.000084065156],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982842,0.000012799391,0.000536478,0.00042240563,0.000297817,0.0004462623],"domain_scores_gemma":[0.99873865,0.00017392589,0.00061141065,0.00018562542,0.00021880408,0.0000715793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075471686,0.0001988998,0.00027986124,0.00022774696,0.00018959148,0.00006370569,0.0008520179,0.000057479443,0.0000013014169],"category_scores_gemma":[0.00018495775,0.00015659453,0.00023110854,0.00088382984,0.00006802874,0.0004914816,0.00037536034,0.00018905969,5.116971e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024418285,0.00021949441,0.01896916,0.0011379316,0.0001838032,0.0000015180512,0.01406951,0.055694073,0.69060826,0.11635988,0.0013009057,0.10121126],"study_design_scores_gemma":[0.0010221791,0.00064307643,0.0002911492,0.00021909791,0.000049099504,0.000011669475,0.0019610026,0.47805163,0.4712961,0.04600999,0.0001610975,0.00028389008],"about_ca_topic_score_codex":0.000020530317,"about_ca_topic_score_gemma":0.000006667691,"teacher_disagreement_score":0.42235756,"about_ca_system_score_codex":0.000023797296,"about_ca_system_score_gemma":0.000016949052,"threshold_uncertainty_score":0.63857394},"labels":[],"label_agreement":null},{"id":"W4386768554","doi":"10.14778/3611540.3611616","title":"Web Connector: A Unified API Wrapper to Simplify Web Data Collection","year":2023,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Web Data Mining and Analysis","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":"Simon Fraser University","funders":"","keywords":"Computer science; Application programming interface; World Wide Web; Web API; Web application; Web service; Database; Web development; Operating system","score_opus":0.04619606448523445,"score_gpt":0.2756170296515338,"score_spread":0.22942096516629934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386768554","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":[0.9433426,0.00011205877,0.0021665737,0.036072083,0.001426014,0.0013017507,0.00025411363,0.001215395,0.014109402],"genre_scores_gemma":[0.9942524,0.00005220462,0.0034883507,0.0003746894,0.00008011481,0.000044033553,0.000015815118,0.000013282731,0.0016791188],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983193,0.0000117575655,0.0002867727,0.0005720057,0.00048483422,0.0003253043],"domain_scores_gemma":[0.99880993,0.0000676205,0.00015715644,0.0007131189,0.00014631619,0.00010587704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007337097,0.00015294265,0.00021876187,0.00027743366,0.00021674152,0.00019587085,0.0029256695,0.000044633965,0.000015025877],"category_scores_gemma":[0.00026194603,0.0001113387,0.0000780308,0.002562534,0.000034886358,0.00041228204,0.00248785,0.00011456063,0.000121368925],"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":[0.000033438195,0.0001537084,0.0049021957,0.00010483048,0.00025372658,0.000001946962,0.0017261814,0.00011868926,0.2641207,0.01696649,0.7038009,0.00781717],"study_design_scores_gemma":[0.0024924343,0.00049713225,0.0063041872,0.00042722854,0.00027937643,0.000036444166,0.0023127103,0.49058554,0.13573483,0.0037775137,0.3564052,0.0011474342],"about_ca_topic_score_codex":0.00008315598,"about_ca_topic_score_gemma":0.000018418323,"teacher_disagreement_score":0.49046683,"about_ca_system_score_codex":0.00006006544,"about_ca_system_score_gemma":0.000094683324,"threshold_uncertainty_score":0.5436671},"labels":[],"label_agreement":null},{"id":"W4386768673","doi":"10.14778/3611540.3611542","title":"Taurus MM: Bringing Multi-Master to the Cloud","year":2023,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":14,"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)","funders":"","keywords":"Computer science; Cloud computing; Distributed computing; Computer network; Protocol (science); Node (physics); Operating system; Engineering","score_opus":0.02720882880582502,"score_gpt":0.2355862427393772,"score_spread":0.2083774139335522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386768673","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":[0.9424262,0.000116963296,0.005650771,0.03769814,0.0021673432,0.0011992466,0.0000017751157,0.0006445138,0.01009506],"genre_scores_gemma":[0.98974496,0.000004769912,0.0032851798,0.00094347756,0.00022031803,0.000047953272,1.09864715e-7,0.000015271698,0.005737956],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99841577,0.000011003367,0.00026479084,0.0003728415,0.00051092857,0.00042466997],"domain_scores_gemma":[0.999283,0.000050231294,0.00014470927,0.00036279068,0.000085677115,0.00007360468],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078555057,0.00015855671,0.00014887306,0.000120969155,0.0003037105,0.0001899068,0.002280708,0.000025581163,0.0000034317084],"category_scores_gemma":[0.000074508454,0.00008866341,0.00013188741,0.0010813959,0.000036228746,0.000028697947,0.0029939634,0.00014373356,0.00012853023],"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":[0.000064959386,0.0007580474,0.015589614,0.0008281323,0.0006740146,0.00002011274,0.06836491,0.08296895,0.04003794,0.1335843,0.29910254,0.35800648],"study_design_scores_gemma":[0.0016228339,0.00026469666,0.030832587,0.0007622067,0.000076892495,0.000036851365,0.002919627,0.5910389,0.05575407,0.0023966322,0.3134138,0.0008809364],"about_ca_topic_score_codex":0.000050316565,"about_ca_topic_score_gemma":0.0000026569924,"teacher_disagreement_score":0.50806993,"about_ca_system_score_codex":0.000058362748,"about_ca_system_score_gemma":0.000010863147,"threshold_uncertainty_score":0.42381608},"labels":[],"label_agreement":null},{"id":"W4386768927","doi":"10.14778/3611540.3611573","title":"Data and AI Model Markets: Opportunities for Data and Model Sharing, Discovery, and Integration","year":2023,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Scientific Computing and Data Management","field":"Decision Sciences","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":"York University","funders":"","keywords":"Data science; Data sharing; Data integration; Big data; Computer science; Emerging markets; Data modeling; Realm; Artificial intelligence; Economics; Data mining; Database; Finance","score_opus":0.44129423908556503,"score_gpt":0.411258332634344,"score_spread":0.030035906451221006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386768927","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":[0.8793621,0.00038776456,0.08733632,0.021221153,0.0005909112,0.0017731517,0.005280962,0.0001368621,0.0039107855],"genre_scores_gemma":[0.9843089,0.00034406866,0.006011321,0.00028458168,0.000033826585,0.000026415935,0.0001606066,0.00001227548,0.008817989],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978211,0.0000066086327,0.0003989646,0.0009308757,0.000651642,0.00019084541],"domain_scores_gemma":[0.9983977,0.00019700178,0.00021858516,0.0009834118,0.00013685111,0.000066460976],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0055433335,0.00012664784,0.00017981358,0.00018412618,0.00025269823,0.0011556966,0.0021670547,0.000021908088,0.0000019374536],"category_scores_gemma":[0.0014461611,0.00007830498,0.000016855689,0.00024724842,0.00016609384,0.001698425,0.010004463,0.00006336277,6.3943673e-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":[0.00016757878,0.00009381678,0.0035016113,0.00021455581,0.00007169195,4.5146467e-7,0.0018082432,0.0007215151,0.0018055543,0.048350196,0.7768599,0.1664049],"study_design_scores_gemma":[0.0002536117,0.000021977732,0.00033933474,0.000058367466,0.000033256183,0.0000018834653,0.0026717181,0.9288571,0.00011455599,0.06318818,0.004373664,0.000086349726],"about_ca_topic_score_codex":0.0000210936,"about_ca_topic_score_gemma":0.000017636085,"teacher_disagreement_score":0.9281356,"about_ca_system_score_codex":0.000011645085,"about_ca_system_score_gemma":0.000027212982,"threshold_uncertainty_score":0.9998812},"labels":[],"label_agreement":null},{"id":"W4389315073","doi":"10.14778/3617838.3617842","title":"FedGTA: Topology-Aware Averaging for Federated Graph Learning","year":2023,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; HEC Montréal","funders":"","keywords":"Scalability; Computer science; Graph; Distributed computing; Machine learning; Robustness (evolution); Artificial intelligence; Software deployment; Theoretical computer science; Database","score_opus":0.016568994672844187,"score_gpt":0.2504238959387287,"score_spread":0.23385490126588454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389315073","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":[0.76870424,0.0005074218,0.18970858,0.023419406,0.0042977477,0.0042819353,0.000011184226,0.0034842135,0.0055852556],"genre_scores_gemma":[0.99447817,0.000053230582,0.0041926783,0.0002544957,0.00007134535,0.000135822,0.0000017486719,0.000019498166,0.0007930269],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99859077,0.00000939362,0.00026513182,0.00040829947,0.00025814146,0.00046825342],"domain_scores_gemma":[0.99925196,0.000116660674,0.00023424119,0.00013001698,0.00020558645,0.00006153564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030465357,0.0001726713,0.00020759241,0.00014880569,0.00049735047,0.0001120982,0.00090546603,0.00005748729,0.000002099049],"category_scores_gemma":[0.00009993724,0.00012896693,0.00015847875,0.0011331079,0.000072861796,0.000338409,0.00057800155,0.00022663745,0.000006412808],"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":[0.00025036436,0.00032375005,0.044457808,0.0009265199,0.00053616276,0.000013930986,0.008060781,0.029904732,0.21085489,0.5192596,0.05896777,0.12644373],"study_design_scores_gemma":[0.0034355726,0.00079667586,0.007541998,0.0005074869,0.00007599146,0.00007574324,0.001693343,0.33775046,0.35855573,0.26972687,0.018599931,0.0012401739],"about_ca_topic_score_codex":0.0000068543923,"about_ca_topic_score_gemma":0.0000013191944,"teacher_disagreement_score":0.30784574,"about_ca_system_score_codex":0.00004159144,"about_ca_system_score_gemma":0.000017703152,"threshold_uncertainty_score":0.52591187},"labels":[],"label_agreement":null},{"id":"W4389539753","doi":"10.14778/3626292.3626293","title":"Cryptographically Secure Private Record Linkage using Locality-Sensitive Hashing","year":2023,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Cryptography and Data Security","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":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Hash function; Locality-sensitive hashing; Locality; Plaintext; Cryptography; Theoretical computer science; Encryption; Differential privacy; Hash table; Computer security; Data mining","score_opus":0.02040080730661333,"score_gpt":0.24468185188577368,"score_spread":0.22428104457916034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389539753","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":[0.9550017,0.000091388225,0.039216995,0.002478269,0.00072086,0.0007140534,0.000035281264,0.0005391821,0.0012022838],"genre_scores_gemma":[0.95715874,0.000087922956,0.042246092,0.000363725,0.00009961481,0.000017597671,0.0000030863491,0.000017172888,0.0000060201764],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978556,0.000025820795,0.00043451952,0.0005602592,0.00062800955,0.00049577485],"domain_scores_gemma":[0.99884516,0.00009409328,0.00033044204,0.0003608188,0.00024291564,0.00012659421],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071056455,0.00023784218,0.00028310926,0.00028002198,0.0003341052,0.00024533315,0.0015174055,0.00010753896,0.0000041902767],"category_scores_gemma":[0.0001456824,0.00018032434,0.00027803352,0.002556899,0.00017133281,0.00068661565,0.0015338218,0.0003691073,0.000010140642],"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":[0.000051618066,0.0002283395,0.009866476,0.0003330585,0.00018682935,0.000011729712,0.0057961554,0.000068198045,0.1574177,0.81615776,0.002457231,0.007424915],"study_design_scores_gemma":[0.0022305755,0.00044695585,0.022911012,0.0014616676,0.00018575031,0.0000921506,0.002507457,0.07442432,0.40301153,0.47298464,0.018108366,0.0016355714],"about_ca_topic_score_codex":0.00008277612,"about_ca_topic_score_gemma":0.0000069787834,"teacher_disagreement_score":0.34317312,"about_ca_system_score_codex":0.000045091267,"about_ca_system_score_gemma":0.00003518325,"threshold_uncertainty_score":0.7353413},"labels":[],"label_agreement":null},{"id":"W4389576335","doi":"10.14778/3626292.3626305","title":"VeLP: Vehicle Loading Plan Learning from Human Behavior in Nationwide Logistics System","year":2023,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Urban and Freight Transport Logistics","field":"Engineering","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":"McGill University","funders":"","keywords":"Computer science; Plan (archaeology); Analytics; Sorting; Process (computing); Container (type theory); Task (project management); Transport engineering; Distribution center; Logistics center; Operations research; Engineering; Data mining; Systems engineering; Business","score_opus":0.041658636348730654,"score_gpt":0.21151845366066302,"score_spread":0.16985981731193237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389576335","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":[0.9929563,0.000086006345,0.0001800976,0.0000261413,0.0003596598,0.00030071635,0.000028502585,0.00048974995,0.0055728285],"genre_scores_gemma":[0.99948055,0.000022809712,0.0001776142,0.000005470303,0.000079163285,0.000054809985,0.000020005347,0.000033360593,0.00012619622],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989607,0.0000037269385,0.00035726567,0.00016161958,0.00025728365,0.00025943053],"domain_scores_gemma":[0.9997104,0.00004190868,0.0000780738,0.00007739236,0.00004733317,0.000044935347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017605223,0.00014626204,0.00019705448,0.00013706076,0.00009211907,0.000031522417,0.0002778792,0.00007452117,0.00001022805],"category_scores_gemma":[0.000034820026,0.00012569159,0.000059915586,0.00035133754,0.000044747107,0.00006640111,0.0000497837,0.00025705041,0.00002215421],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019679012,0.000097538286,0.58897156,0.0007613625,0.00010371748,0.000028723736,0.003407845,0.030275153,0.35337168,0.021087145,0.0013302659,0.0005453336],"study_design_scores_gemma":[0.0022181093,0.00015284131,0.55062926,0.0010502366,0.0003031048,0.000008594291,0.004420343,0.18412122,0.25258023,0.001635294,0.001955667,0.00092511164],"about_ca_topic_score_codex":0.00013099214,"about_ca_topic_score_gemma":0.00002447772,"teacher_disagreement_score":0.15384607,"about_ca_system_score_codex":0.00015542256,"about_ca_system_score_gemma":0.000006219619,"threshold_uncertainty_score":0.5125554},"labels":[],"label_agreement":null},{"id":"W4391054874","doi":"10.14778/3632093.3632117","title":"The Art of Latency Hiding in Modern Database Engines","year":2023,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Data Storage Technologies","field":"Computer Science","cited_by":20,"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; Latency (audio); Interleaving; CAS latency; Speedup; Parallel computing; Operating system; Scheduling (production processes); CPU cache; Cache; Semiconductor memory; Memory controller","score_opus":0.020143839000601394,"score_gpt":0.24488364605150129,"score_spread":0.22473980705089988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391054874","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":[0.93004435,0.0017724753,0.037924226,0.019495033,0.0013246335,0.0020962395,0.00007981983,0.0018097282,0.0054534655],"genre_scores_gemma":[0.98673147,0.00036418714,0.012618212,0.000019622961,0.000011346477,0.00005690151,0.0000011803279,0.000008565634,0.00018854225],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99889606,0.000004035076,0.00027837578,0.00023804817,0.00032227358,0.00026117795],"domain_scores_gemma":[0.99920374,0.000106319065,0.00019787707,0.00039704374,0.00007712138,0.00001792129],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046303013,0.00010763096,0.00014147208,0.00013696241,0.00008557847,0.00003231624,0.0020610986,0.000029112292,5.833058e-7],"category_scores_gemma":[0.00039906593,0.000063217216,0.000044432654,0.0009782567,0.00010334879,0.00049702585,0.0018451336,0.00013404174,0.0000071071922],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002270061,0.000113728616,0.005219335,0.00022663346,0.000043075197,0.000005063343,0.0018611507,0.0009336697,0.3930581,0.51846606,0.008668086,0.071382426],"study_design_scores_gemma":[0.0005389416,0.000079295,0.0023379868,0.00032340092,0.000011222308,0.000010483164,0.0010241392,0.068669595,0.74875206,0.17372741,0.004260502,0.0002649728],"about_ca_topic_score_codex":0.000013170101,"about_ca_topic_score_gemma":0.0000047574204,"teacher_disagreement_score":0.35569397,"about_ca_system_score_codex":0.000044152388,"about_ca_system_score_gemma":0.000018578558,"threshold_uncertainty_score":0.38300684},"labels":[],"label_agreement":null},{"id":"W4391054882","doi":"10.14778/3632093.3632109","title":"Caerus: Low-Latency Distributed Transactions for Geo-Replicated Systems","year":2023,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Latency (audio); Distributed transaction; Database transaction; Transaction processing; Workload; Online transaction processing; Distributed computing; Protocol (science); Distributed database; Database; Compensating transaction; Computer network; Operating system","score_opus":0.014421848795280147,"score_gpt":0.23148567763324981,"score_spread":0.21706382883796968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391054882","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":[0.25528884,0.00074392016,0.7137724,0.009553996,0.005351442,0.00799433,0.00216352,0.0024228208,0.0027087242],"genre_scores_gemma":[0.9980581,0.00002660572,0.00036339666,0.000028051776,0.000055341163,0.00063625217,0.00001769834,0.000015504858,0.00079906074],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981995,0.00000762863,0.0005207711,0.0004386642,0.00039146983,0.0004419389],"domain_scores_gemma":[0.9988302,0.00005538038,0.0002985225,0.00032945577,0.00038980853,0.000096610296],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045656465,0.00019024336,0.0002918909,0.000086946726,0.00026852297,0.0001687013,0.0012652678,0.00007980849,0.0000027583524],"category_scores_gemma":[0.000050782175,0.00013618659,0.00019935756,0.0012253057,0.00004731024,0.00030825863,0.000102919286,0.00011251516,0.000024087412],"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":[0.0002147747,0.0016811369,0.0050094444,0.005598271,0.0012229757,0.000006553754,0.0057035247,0.0147677595,0.3461961,0.4245683,0.17179473,0.023236444],"study_design_scores_gemma":[0.0053787376,0.0005333044,0.016281554,0.0017924317,0.00021437014,0.00011154202,0.001844102,0.6537089,0.19233629,0.0081364615,0.1180317,0.0016306128],"about_ca_topic_score_codex":0.00013702859,"about_ca_topic_score_gemma":0.0000022275592,"teacher_disagreement_score":0.74276924,"about_ca_system_score_codex":0.00009509997,"about_ca_system_score_gemma":0.000045279692,"threshold_uncertainty_score":0.5553528},"labels":[],"label_agreement":null},{"id":"W4391054883","doi":"10.14778/3632093.3632118","title":"MOSER: Scalable Network Motif Discovery Using Serial Test","year":2023,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","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 British Columbia","funders":"","keywords":"Motif (music); Computer science; Scalability; Graph; Theoretical computer science; Cluster analysis; Network motif; Data mining; Artificial intelligence; Complex network; Database","score_opus":0.015416777603827437,"score_gpt":0.24724935576746154,"score_spread":0.23183257816363412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391054883","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":[0.9890305,0.00003203181,0.00047316513,0.00026641312,0.00026082937,0.0004947503,0.000023085488,0.00017146532,0.009247768],"genre_scores_gemma":[0.9964565,0.000007057895,0.0012896243,0.000022850485,0.0009109462,0.000043758228,0.000006224649,0.000027846467,0.0012351912],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99870455,0.000006370225,0.00032493327,0.0002652242,0.00029071345,0.00040818853],"domain_scores_gemma":[0.9993604,0.000055806733,0.0002631982,0.00017461162,0.00009801474,0.000047982136],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003045972,0.00018224231,0.00027555157,0.000060214632,0.00021773513,0.00012511271,0.00046029486,0.00002869323,0.00007905178],"category_scores_gemma":[0.000014532356,0.00013648924,0.00022513051,0.00092640374,0.0000630686,0.00024617935,0.00056000316,0.0001297626,0.000011881866],"study_design_candidate":"observational","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":[0.00004471805,0.00028340225,0.76311165,0.00008436435,0.00040567768,4.34707e-7,0.00026890947,0.013670171,0.10594386,0.04980777,0.063122146,0.0032569],"study_design_scores_gemma":[0.0023582673,0.00030346462,0.041336637,0.0011747996,0.00106501,0.000005563926,0.0013209124,0.14300703,0.47372147,0.3150952,0.018900689,0.0017109514],"about_ca_topic_score_codex":0.00025472412,"about_ca_topic_score_gemma":0.0000024695878,"teacher_disagreement_score":0.721775,"about_ca_system_score_codex":0.000053113956,"about_ca_system_score_gemma":0.000026639716,"threshold_uncertainty_score":0.5565869},"labels":[],"label_agreement":null},{"id":"W4391054937","doi":"10.14778/3632093.3632096","title":"Blocker and Matcher Can Mutually Benefit: A Co-Learning Framework for Low-Resource Entity Resolution","year":2023,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","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":"Vector Institute; University of Toronto","funders":"","keywords":"Benchmark (surveying); Computer science; Resource (disambiguation); Noise (video); Selection (genetic algorithm); Machine learning; Artificial intelligence; Resolution (logic); Data mining","score_opus":0.07733140174241149,"score_gpt":0.3638194075327134,"score_spread":0.2864880057903019,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391054937","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":[0.98065096,0.00007711705,0.0011062153,0.011151741,0.0002963744,0.0012148896,0.00011032599,0.00014355224,0.0052488334],"genre_scores_gemma":[0.98705167,0.000054781427,0.0032541668,0.0005706783,0.000118952674,0.0001367552,0.000011205743,0.000021001642,0.00878079],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99762446,0.00002290538,0.00049097894,0.00045093586,0.0010769072,0.00033383287],"domain_scores_gemma":[0.99863416,0.00046091896,0.00037828847,0.00022707996,0.00021494034,0.000084591724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039013666,0.00014366173,0.00024236266,0.00017956608,0.00035030325,0.00028268638,0.00077806617,0.00007797755,0.000049041246],"category_scores_gemma":[0.002621769,0.00009840118,0.000119416334,0.00068343146,0.00012699267,0.00018666708,0.00076587615,0.00017258496,0.000031713647],"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":[0.00037458443,0.0003127596,0.016926423,0.0005899199,0.00025288362,0.0000015910371,0.015736988,0.0006259845,0.008565363,0.6782655,0.21925876,0.059089243],"study_design_scores_gemma":[0.0011831772,0.0002653645,0.022419779,0.0003744437,0.00011229366,0.0000039141987,0.01934921,0.0031659456,0.018065942,0.40382552,0.5308076,0.0004268277],"about_ca_topic_score_codex":0.000057461435,"about_ca_topic_score_gemma":0.000021910007,"teacher_disagreement_score":0.31154883,"about_ca_system_score_codex":0.000051150488,"about_ca_system_score_gemma":0.000014849927,"threshold_uncertainty_score":0.40126836},"labels":[],"label_agreement":null},{"id":"W4396601617","doi":"10.14778/3648160.3648187","title":"AeonG: An Efficient Built-in Temporal Support in Graph Databases","year":2024,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Graph Theory and Algorithms","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; Graph database; Database; Graph; Theoretical computer science","score_opus":0.020735606360406958,"score_gpt":0.26751256505131277,"score_spread":0.24677695869090582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396601617","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":[0.9936811,0.0003234195,0.0016254768,0.0010516931,0.0007244279,0.00048505052,0.000014390294,0.00014478971,0.0019496662],"genre_scores_gemma":[0.9955986,0.000015697362,0.0041368986,0.0000785085,0.00003054991,0.00004342873,0.0000019150298,0.0000099551,0.00008442363],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99846774,0.000016373047,0.00034404264,0.00046871306,0.00036945083,0.00033369433],"domain_scores_gemma":[0.9995123,0.000038578073,0.00007484105,0.00026114777,0.00004155665,0.00007153962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009822589,0.00016337866,0.00018238036,0.00035960204,0.00005140373,0.00011982783,0.0012340066,0.000029153705,0.0000134232205],"category_scores_gemma":[0.000031960375,0.00011384048,0.00009503366,0.0011665864,0.0000845064,0.00050343375,0.0005020064,0.00019660895,0.00000775151],"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":[0.000036369165,0.0009519967,0.029981893,0.0003541016,0.000034894023,0.000050892148,0.0061599086,0.0006338202,0.01953992,0.9284061,0.00086182123,0.012988251],"study_design_scores_gemma":[0.003312106,0.0012189971,0.052150197,0.0024563377,0.00007395876,0.00026920965,0.003453208,0.21074526,0.4379294,0.27439174,0.012087151,0.0019124286],"about_ca_topic_score_codex":0.00011880621,"about_ca_topic_score_gemma":0.000021890479,"teacher_disagreement_score":0.6540144,"about_ca_system_score_codex":0.000049274022,"about_ca_system_score_gemma":0.00004971834,"threshold_uncertainty_score":0.464228},"labels":[],"label_agreement":null},{"id":"W4396628099","doi":"10.14778/3648160.3648165","title":"How Can We Train Deep Learning Models Across Clouds and Continents? An Experimental Study","year":2024,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Neural Network Applications","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":"University of Toronto","funders":"","keywords":"Deep learning; Geology; Data science; Computer science; Artificial intelligence","score_opus":0.03507132555401607,"score_gpt":0.2938870684634521,"score_spread":0.258815742909436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396628099","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":[0.9852037,0.0011170962,0.008478972,0.0037696678,0.00015476573,0.0008720263,0.0000029083897,0.00022493335,0.00017595543],"genre_scores_gemma":[0.9957573,0.000048929982,0.0035324423,0.00004887692,0.00006317537,0.00019937422,4.1751704e-7,0.000017241504,0.00033227314],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987418,0.000012160527,0.00018010048,0.0004800948,0.0003021219,0.00028370635],"domain_scores_gemma":[0.99956626,0.00003128398,0.000096983946,0.00016163108,0.00005576062,0.0000881095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020429157,0.00016598233,0.00015729896,0.000033900338,0.00024751454,0.00043300315,0.0007273314,0.00002695218,8.176409e-7],"category_scores_gemma":[0.00001014369,0.00012153139,0.000049542505,0.00032899893,0.00007711192,0.00072285015,0.0005962717,0.00019187787,5.596946e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052312356,0.0016676763,0.003202966,0.00018779315,0.00020366423,0.000008273506,0.171484,0.0042101517,0.42072338,0.22363251,0.00032000832,0.17430727],"study_design_scores_gemma":[0.0017350839,0.0015751983,0.00087081135,0.00020808914,0.000057031684,0.00008786005,0.03827235,0.65076137,0.2622132,0.039764624,0.0036747747,0.00077964267],"about_ca_topic_score_codex":0.000014656853,"about_ca_topic_score_gemma":0.0000072838566,"teacher_disagreement_score":0.6465512,"about_ca_system_score_codex":0.000060649792,"about_ca_system_score_gemma":0.000008531095,"threshold_uncertainty_score":0.4955906},"labels":[],"label_agreement":null},{"id":"W4399208560","doi":"10.14778/3659437.3659455","title":"Differentially Private Data Generation with Missing Data","year":2024,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","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":"","keywords":"Missing data; Synthetic data; Differential privacy; Computer science; Data mining; Data quality; Ground truth; Process (computing); Data modeling; Algorithm; Machine learning; Engineering; Database","score_opus":0.08668987133323494,"score_gpt":0.2909003034966938,"score_spread":0.20421043216345888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399208560","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":[0.12591027,0.0032581012,0.65467674,0.20307167,0.002961974,0.0021067136,0.0005918669,0.0034306822,0.003991972],"genre_scores_gemma":[0.5929699,0.00012663925,0.40648976,0.00009521964,0.00013687024,0.00001553975,0.000082109014,0.000022615399,0.00006137987],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979073,0.000008359325,0.00027621965,0.0009526436,0.00058046007,0.00027502238],"domain_scores_gemma":[0.99103034,0.00004155147,0.00015321984,0.00866363,0.0000705404,0.000040751678],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00061444787,0.00017830066,0.00015862963,0.000098781085,0.0001367176,0.0007187375,0.060671225,0.00005474001,0.0000058523206],"category_scores_gemma":[0.0021905026,0.0001087937,0.000022266582,0.000540113,0.00010871375,0.002232831,0.18800364,0.00022543383,0.0000063868765],"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":[0.000016259568,0.00016419622,0.0010032102,0.00051998656,0.00029337752,0.000009384084,0.00022537098,0.0000064224832,0.28314787,0.051512625,0.49159,0.1715113],"study_design_scores_gemma":[0.00024720404,0.00006831759,0.000303515,0.0005072265,0.00007080236,0.00006341887,0.000018264973,0.74580634,0.18501146,0.051086284,0.016539622,0.00027758034],"about_ca_topic_score_codex":0.000024586972,"about_ca_topic_score_gemma":0.00000439566,"teacher_disagreement_score":0.7457999,"about_ca_system_score_codex":0.000061706145,"about_ca_system_score_gemma":0.00007356221,"threshold_uncertainty_score":0.944411},"labels":[],"label_agreement":null},{"id":"W4399208580","doi":"10.14778/3659437.3659439","title":"Accelerating String-Key Learned Index Structures via Memoization-Based Incremental Training","year":2024,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","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":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Memoization; Bottleneck; Leverage (statistics); Key (lock); Matrix decomposition; Theoretical computer science; Parallel computing; Artificial intelligence; Machine learning; Embedded system; Operating system; Eigenvalues and eigenvectors","score_opus":0.03452865552063113,"score_gpt":0.26440748166450906,"score_spread":0.22987882614387795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399208580","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":[0.21336515,0.0005955445,0.7766411,0.001981402,0.0015940275,0.0011304702,0.00003683203,0.0006538062,0.0040016747],"genre_scores_gemma":[0.9629935,0.0000045330703,0.036661044,0.00011249923,0.000109404464,0.0000341813,0.0000033187837,0.00001551365,0.00006600257],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998534,0.000009621013,0.00034744974,0.00037626008,0.00047714062,0.00025549653],"domain_scores_gemma":[0.99944955,0.000052977808,0.0001741677,0.00016687787,0.00010104759,0.000055391596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031621353,0.0001766228,0.00017850549,0.00011333823,0.00021556592,0.00020444914,0.0005750226,0.000039628754,0.000019203793],"category_scores_gemma":[0.00007346878,0.00012318914,0.00008415805,0.00046640594,0.000054860313,0.000747411,0.00036192988,0.00017251683,0.0000025409536],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018604014,0.00003829108,0.0020313186,0.0005182699,0.00009715129,0.0000029741022,0.0056743613,0.0027435967,0.17905872,0.7596544,0.0004802883,0.049682025],"study_design_scores_gemma":[0.00097266684,0.00017785034,0.0013891091,0.00093900115,0.000038952916,0.00004299826,0.002081065,0.28157654,0.6869001,0.014110438,0.011153536,0.0006177651],"about_ca_topic_score_codex":0.00007187649,"about_ca_topic_score_gemma":0.0000065649,"teacher_disagreement_score":0.74962837,"about_ca_system_score_codex":0.00009469214,"about_ca_system_score_gemma":0.000085203654,"threshold_uncertainty_score":0.5023507},"labels":[],"label_agreement":null},{"id":"W4401353058","doi":"10.14778/3675034.3675040","title":"Incremental Sliding Window Connectivity over Streaming Graphs","year":2024,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Search engine indexing; Sliding window protocol; Computation; Leverage (statistics); Latency (audio); Window (computing); Stream processing; Throughput; Graph; Theoretical computer science; Data mining; Parallel computing; Algorithm; Artificial intelligence","score_opus":0.012101642950259544,"score_gpt":0.2308971289352785,"score_spread":0.21879548598501897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401353058","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":[0.9635087,0.0006268731,0.00550683,0.0017941558,0.0021258737,0.00092913856,0.000025787334,0.00055437046,0.024928248],"genre_scores_gemma":[0.9964734,0.00003247933,0.0030276396,0.00010001422,0.00006995688,0.00002607836,0.0000010419368,0.000010994226,0.00025840598],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986052,0.0000066268694,0.00021655994,0.00041372175,0.00047949774,0.00027838603],"domain_scores_gemma":[0.99957377,0.00004595874,0.00009813009,0.00019231558,0.000041523137,0.00004830046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048575492,0.00016356882,0.00014741211,0.0001542772,0.00014208046,0.0004736598,0.0011631026,0.000026865928,0.000017078719],"category_scores_gemma":[0.000031268388,0.00011568248,0.00012874384,0.0006147509,0.000038642294,0.0013665155,0.001306697,0.00013901952,0.00001115981],"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":[0.0000067163555,0.00013136766,0.0084956745,0.0002925964,0.00019239866,0.0000052273026,0.0008001485,0.0000044966737,0.0850118,0.8448679,0.006433308,0.053758364],"study_design_scores_gemma":[0.0017424822,0.00037516758,0.03896959,0.0014757494,0.0002169297,0.00004851704,0.0010866739,0.06186323,0.7781497,0.09128588,0.023601832,0.0011842482],"about_ca_topic_score_codex":0.000067988054,"about_ca_topic_score_gemma":0.0000028582542,"teacher_disagreement_score":0.753582,"about_ca_system_score_codex":0.00008570928,"about_ca_system_score_gemma":0.00001638894,"threshold_uncertainty_score":0.47173947},"labels":[],"label_agreement":null},{"id":"W4401353529","doi":"10.14778/3675034.3675050","title":"DEX: Scalable Range Indexing on Disaggregated Memory","year":2024,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Algorithms and Data Compression","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":"Search engine indexing; Scalability; Range (aeronautics); Computer science; Parallel computing; Information retrieval; Database; Engineering","score_opus":0.01133561931545859,"score_gpt":0.2271684346161253,"score_spread":0.2158328153006667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401353529","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":[0.7531277,0.009441759,0.04335983,0.018805075,0.010622019,0.003834727,0.00008446526,0.0028838352,0.15784056],"genre_scores_gemma":[0.99172914,0.00005895807,0.0063862004,0.00023330362,0.0001313065,0.000040506824,9.954006e-7,0.0000160945,0.0014034695],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987078,0.0000060818456,0.00020677228,0.00036796715,0.0004707212,0.00024070489],"domain_scores_gemma":[0.99950534,0.000046573394,0.000084805935,0.00023222492,0.000067882764,0.00006318471],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002934986,0.0001441901,0.0001411505,0.00009534238,0.00013485811,0.00025414556,0.0011042678,0.00004329538,0.000017251055],"category_scores_gemma":[0.00003156433,0.000086584034,0.00008906222,0.00047731178,0.000044452405,0.0005557118,0.00077405176,0.00017929143,0.000036529895],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008827711,0.00056526106,0.0015591816,0.00092710176,0.00023388746,0.000019681056,0.0043554245,0.0002596446,0.098294385,0.35110572,0.08430947,0.45828196],"study_design_scores_gemma":[0.0012188752,0.00036257817,0.0021892688,0.0033726944,0.00006271085,0.00006188518,0.00024580272,0.21362773,0.6969268,0.027336173,0.053905945,0.0006895848],"about_ca_topic_score_codex":0.000040612733,"about_ca_topic_score_gemma":5.117496e-7,"teacher_disagreement_score":0.5986324,"about_ca_system_score_codex":0.0000731481,"about_ca_system_score_gemma":0.000029562127,"threshold_uncertainty_score":0.35307944},"labels":[],"label_agreement":null},{"id":"W4402042375","doi":"10.14778/3681954.3681998","title":"Optimizing Video Queries with Declarative Clues","year":2024,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Image and Video Retrieval Techniques","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":"York University; University of Toronto","funders":"","keywords":"Computer science; Leverage (statistics); Query optimization; Limiting; Query expansion; Query language; Information retrieval; Domain (mathematical analysis); Web query classification; Extensibility; Data mining; Web search query; Machine learning; Search engine","score_opus":0.011642662368546322,"score_gpt":0.2542588442781897,"score_spread":0.24261618190964335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402042375","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":[0.0181903,0.004653681,0.94889915,0.004672812,0.00033765676,0.0010221195,0.0000050623935,0.0012470821,0.020972155],"genre_scores_gemma":[0.7758155,0.00022863942,0.2231098,0.00018440027,0.00004691817,0.00006970076,1.8808294e-7,0.00001596325,0.0005288991],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99893165,0.0000050057192,0.00019242924,0.0003255443,0.00033155404,0.00021379846],"domain_scores_gemma":[0.99948245,0.000051090952,0.00009696679,0.00015760818,0.00016995183,0.00004192882],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019791033,0.00015751495,0.00016227782,0.00008512315,0.00011207179,0.00024895335,0.00076265156,0.000031548505,0.0000039277784],"category_scores_gemma":[0.000046689885,0.00008859087,0.00007671933,0.00057436037,0.00011865246,0.0011920601,0.00042367217,0.00015995542,0.000003842465],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008130544,0.000111032205,0.000607522,0.00048599704,0.00020439191,0.000013255054,0.0118715055,0.000041924653,0.14339285,0.7642643,0.0058436277,0.07308233],"study_design_scores_gemma":[0.000097645316,0.00022149955,0.00007162797,0.00042424598,0.000016124994,0.000028309365,0.00023194497,0.0010172795,0.9605271,0.024537545,0.01267971,0.00014694511],"about_ca_topic_score_codex":0.000009841146,"about_ca_topic_score_gemma":8.68324e-7,"teacher_disagreement_score":0.81713426,"about_ca_system_score_codex":0.00006872544,"about_ca_system_score_gemma":0.00004475158,"threshold_uncertainty_score":0.3612631},"labels":[],"label_agreement":null},{"id":"W4402042395","doi":"10.14778/3681954.3682002","title":"DDS: DPU-Optimized Disaggregated Storage","year":2024,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Cloud Computing and Resource Management","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 Toronto","funders":"","keywords":"Computer science; Operating system; Latency (audio); Throughput; Server; Embedded system; Overhead (engineering)","score_opus":0.008606006174710003,"score_gpt":0.21326284760540754,"score_spread":0.20465684143069754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402042395","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":[0.88449544,0.003750197,0.01767703,0.029012635,0.004266187,0.0017019816,0.000005971721,0.0021479714,0.056942616],"genre_scores_gemma":[0.991044,0.000018481756,0.004863465,0.00017542251,0.000111739995,0.0000286806,2.1664201e-7,0.000015819403,0.0037421633],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99849325,0.000007637863,0.00028559112,0.0004244997,0.0004892994,0.00029970906],"domain_scores_gemma":[0.99942416,0.000050503615,0.0001185447,0.00026698053,0.00007356892,0.00006624552],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045005672,0.00017738706,0.00018735525,0.00011884571,0.00013555598,0.00031529582,0.0014740855,0.000038344362,0.000011416614],"category_scores_gemma":[0.000039441806,0.0001102591,0.00018636324,0.00070042035,0.00006367727,0.00005934624,0.0012074218,0.00017607058,0.000029362787],"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":[0.00008443603,0.00085733953,0.0006955695,0.0020139287,0.0010910677,0.00004376875,0.016564779,0.020345254,0.040206105,0.5699753,0.13451393,0.21360855],"study_design_scores_gemma":[0.0013282165,0.00023774651,0.0007604612,0.0014844527,0.00013103925,0.000058792568,0.00047700503,0.825079,0.059415344,0.013843411,0.09649617,0.00068835507],"about_ca_topic_score_codex":0.000029622937,"about_ca_topic_score_gemma":3.2872074e-7,"teacher_disagreement_score":0.80473375,"about_ca_system_score_codex":0.00009796419,"about_ca_system_score_gemma":0.000023464572,"threshold_uncertainty_score":0.44962355},"labels":[],"label_agreement":null},{"id":"W4402043623","doi":"10.14778/3681954.3682026","title":"Blueprinting the Cloud: Unifying and Automatically Optimizing Cloud Data Infrastructures with BRAD","year":2024,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":6,"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; National Science Foundation","keywords":"Cloud computing; Computer science; Blueprint; Operating system; Engineering","score_opus":0.016380022218180846,"score_gpt":0.24502677028409897,"score_spread":0.22864674806591812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402043623","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":[0.31902942,0.0037603066,0.65393394,0.011071129,0.0021767134,0.0019631442,0.000086717824,0.0009275362,0.0070511177],"genre_scores_gemma":[0.75263613,0.000056750894,0.24687204,0.00014111442,0.00019432217,0.000020757876,0.0000017050186,0.000017557384,0.000059646496],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867606,0.000010853903,0.000276334,0.00043392673,0.0003603626,0.00024247535],"domain_scores_gemma":[0.99911314,0.00011827371,0.00014885738,0.0005045007,0.000066881774,0.00004832188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005831619,0.00016590721,0.00016975403,0.000045284894,0.0002601484,0.0003206978,0.0012818112,0.0000262967,0.0000028786517],"category_scores_gemma":[0.00009812901,0.00007950298,0.000029547355,0.0003280314,0.00016079142,0.0008674492,0.0025265303,0.00021028522,0.000001331512],"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":[0.0000102836075,0.0000141319415,0.00063818425,0.0006047442,0.0001129085,0.0000034126135,0.0037798276,0.0002310911,0.009950764,0.9631822,0.0012262688,0.0202462],"study_design_scores_gemma":[0.0018028831,0.0004536508,0.00802519,0.008977245,0.0003704162,0.0016234257,0.009795209,0.61866,0.11972956,0.060429633,0.16826709,0.0018657257],"about_ca_topic_score_codex":0.00004729576,"about_ca_topic_score_gemma":0.00000420114,"teacher_disagreement_score":0.9027526,"about_ca_system_score_codex":0.00002630607,"about_ca_system_score_gemma":0.00004566995,"threshold_uncertainty_score":0.32420373},"labels":[],"label_agreement":null},{"id":"W4402043624","doi":"10.14778/3681954.3682027","title":"Aleph Filter: To Infinity in Constant Time","year":2024,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Caching and Content Delivery","field":"Computer Science","cited_by":6,"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":"Infinity; Constant (computer programming); Aleph; Mathematics; Filter (signal processing); Mathematical analysis; Physics; Computer science; Programming language; Particle physics","score_opus":0.010547553289931642,"score_gpt":0.21081831526496186,"score_spread":0.20027076197503021,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402043624","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":[0.9337267,0.0005501734,0.0009986492,0.009900881,0.00087405875,0.0006585718,0.000013120746,0.00028894242,0.052988887],"genre_scores_gemma":[0.9975607,0.000013297427,0.0007237637,0.0004451276,0.000030365505,0.00002630795,1.6248632e-7,0.0000057461743,0.0011945706],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990473,0.000006099103,0.00021406257,0.00026545304,0.00026980744,0.00019727976],"domain_scores_gemma":[0.99966156,0.000046128807,0.00003993532,0.00014222856,0.000055366087,0.000054799137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003556118,0.00010277884,0.00013275312,0.00013429692,0.000039122107,0.0001504841,0.0007723571,0.000025250298,0.000012944375],"category_scores_gemma":[0.00005401309,0.00007144994,0.00008157912,0.00045607393,0.000026450256,0.00021633241,0.0005476628,0.000137719,0.000084070016],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055019726,0.0003049544,0.0058061136,0.00034425437,0.00009202189,0.000028165989,0.007475081,0.00013603613,0.52706695,0.3577624,0.050101157,0.050827872],"study_design_scores_gemma":[0.0030369526,0.0014350218,0.009764128,0.006825929,0.00013231493,0.00039514687,0.0010012396,0.21367943,0.5288795,0.07759264,0.15486267,0.0023949759],"about_ca_topic_score_codex":0.00009748161,"about_ca_topic_score_gemma":0.000003547663,"teacher_disagreement_score":0.28016976,"about_ca_system_score_codex":0.000081218765,"about_ca_system_score_gemma":0.000037612725,"threshold_uncertainty_score":0.2913644},"labels":[],"label_agreement":null},{"id":"W4404181113","doi":"10.14778/3685800.3685876","title":"Demonstration of DB-GPT: Next Generation Data Interaction System Empowered by Large Language Models","year":2024,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Scientific Computing and Data Management","field":"Decision Sciences","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","score_opus":0.21580710100271508,"score_gpt":0.38459209005308537,"score_spread":0.1687849890503703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404181113","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":[0.90631264,0.0019355221,0.05132519,0.0021485053,0.0062814127,0.0016956937,0.00088253734,0.00024535912,0.029173134],"genre_scores_gemma":[0.9978544,0.000011641672,0.0007189631,0.000024258812,0.00009668706,0.0000136968865,0.0000675536,0.000007712548,0.0012050789],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99729604,0.000027195136,0.00069014536,0.00061851746,0.0012048295,0.00016328285],"domain_scores_gemma":[0.9986352,0.00011147187,0.00035744903,0.00063771603,0.00021870213,0.000039469116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003925027,0.000114014,0.00017760803,0.0001923334,0.00009793195,0.00063337636,0.0013854023,0.000035830733,0.00003051536],"category_scores_gemma":[0.0002868489,0.00007232639,0.0000758753,0.0006703563,0.000038773087,0.0013343382,0.0009009637,0.00009081837,0.000024635254],"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":[0.000033480403,0.00020412914,0.00026795032,0.00031218448,0.00010584173,0.0000010184679,0.003981119,0.00074595877,0.34619957,0.05177092,0.5404081,0.055969752],"study_design_scores_gemma":[0.0001886518,0.000032741802,0.00003291567,0.00024186545,0.000051946412,0.000006775381,0.009230407,0.92315584,0.05315167,0.0007755117,0.013026124,0.000105523286],"about_ca_topic_score_codex":0.00008144322,"about_ca_topic_score_gemma":0.000013263982,"teacher_disagreement_score":0.9224099,"about_ca_system_score_codex":0.000075299904,"about_ca_system_score_gemma":0.000028397077,"threshold_uncertainty_score":0.61076623},"labels":[],"label_agreement":null},{"id":"W4404181204","doi":"10.14778/3685800.3685811","title":"Db2une: Tuning Under Pressure via Deep Learning","year":2024,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Ferroelectric and Negative Capacitance Devices","field":"Engineering","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":"IBM (Canada)","funders":"","keywords":"Computer science; Artificial intelligence; Deep learning; Psychology","score_opus":0.006234418694740766,"score_gpt":0.19458057697407258,"score_spread":0.18834615827933182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404181204","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":[0.7308531,0.07834131,0.013062435,0.001243224,0.0027786156,0.0013638092,0.000009885935,0.0025333185,0.16981432],"genre_scores_gemma":[0.9982535,0.00028594065,0.00025738103,0.000032050553,0.00009741384,0.00003461175,5.9497575e-7,0.000035985377,0.0010024753],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991669,0.000003975458,0.00018079583,0.00016983412,0.00023346774,0.00024503513],"domain_scores_gemma":[0.9997577,0.00004626565,0.000037896207,0.000054295848,0.00006411034,0.00003969616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014572438,0.00015654477,0.0001508444,0.000078538986,0.000076472075,0.00006294481,0.00022942333,0.000053425385,0.000054049204],"category_scores_gemma":[0.000026879196,0.000112179485,0.00009030178,0.0003817323,0.000042065796,0.00021459859,0.00005166464,0.00032817785,0.000017923116],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030867926,0.000047556197,0.0021368272,0.003118953,0.0010478157,0.0000028029217,0.0068650283,0.029916253,0.8715313,0.04252073,0.0059854514,0.03679638],"study_design_scores_gemma":[0.00040265944,0.00012839923,0.0022804635,0.00096906116,0.00028556256,0.000035794106,0.0018074083,0.43300918,0.4979484,0.008234276,0.054335345,0.0005634579],"about_ca_topic_score_codex":0.0000055479577,"about_ca_topic_score_gemma":0.0000010498122,"teacher_disagreement_score":0.40309292,"about_ca_system_score_codex":0.000064556705,"about_ca_system_score_gemma":0.0000064488017,"threshold_uncertainty_score":0.45745465},"labels":[],"label_agreement":null},{"id":"W4404181435","doi":"10.14778/3685800.3685894","title":"Demonstration of the VeriEQL Equivalence Checker for Complex SQL Queries","year":2024,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","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":"Simon Fraser University","funders":"","keywords":"Programming language; Computer science; Equivalence (formal languages); SQL; SQL/PSM; Database; Stored procedure; Information retrieval; Query by Example; Mathematics; Discrete mathematics; Web search query","score_opus":0.02881900024655679,"score_gpt":0.2677268580327518,"score_spread":0.23890785778619503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404181435","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":[0.1464201,0.0025318344,0.8169294,0.010569954,0.0041050604,0.0044674575,0.00037503615,0.00041666295,0.014184477],"genre_scores_gemma":[0.947389,0.000028308803,0.05182381,0.00007071934,0.00006626411,0.00011142911,0.0000012737241,0.000009390393,0.00049977034],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989875,0.0000058823207,0.00030041096,0.00023437066,0.00030395598,0.00016787856],"domain_scores_gemma":[0.99937165,0.00003865616,0.00018493962,0.00021987883,0.00016078245,0.00002411839],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026858042,0.00011567494,0.00015143794,0.000030689207,0.00011065862,0.000051746163,0.0006429987,0.000026376852,0.000004150536],"category_scores_gemma":[0.000065188695,0.000063807856,0.00012760125,0.0002914683,0.0001687725,0.00055643485,0.0004232334,0.00006816746,0.0000012662211],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008390122,0.000018436702,0.00028791034,0.00043387793,0.000021282767,6.441016e-8,0.0007947243,0.000014144198,0.12309909,0.8713035,0.0021161053,0.001902471],"study_design_scores_gemma":[0.0002942308,0.00014720944,0.0018930936,0.00081494055,0.000037659815,0.000023034416,0.00061869127,0.013748119,0.86860013,0.012499658,0.10110622,0.00021703137],"about_ca_topic_score_codex":0.000026326597,"about_ca_topic_score_gemma":0.000004879708,"teacher_disagreement_score":0.85880387,"about_ca_system_score_codex":0.000039076116,"about_ca_system_score_gemma":0.000056764668,"threshold_uncertainty_score":0.2602009},"labels":[],"label_agreement":null},{"id":"W4404988426","doi":"10.14778/3749646.3749657","title":"TabulaX: Leveraging Large Language Models for Multi-Class Table Transformations","year":2025,"lang":"en","type":"preprint","venue":"Proceedings of the VLDB Endowment","topic":"Big Data Technologies and Applications","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 Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Table (database); Class (philosophy); Computer science; Programming language; Natural language processing; Theoretical computer science; Artificial intelligence; Database","score_opus":0.20772441500396746,"score_gpt":0.38232798555009745,"score_spread":0.17460357054613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404988426","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":[0.0804909,0.0037007448,0.7906835,0.03810385,0.0021142354,0.01572897,0.024625953,0.0010228312,0.043529022],"genre_scores_gemma":[0.94836456,0.00029950135,0.0420296,0.00038330173,0.00006541371,0.0022644235,0.00008020388,0.00002424962,0.006488776],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972925,0.000007665031,0.00087402586,0.0006501473,0.00077464787,0.00040102378],"domain_scores_gemma":[0.997761,0.00017859811,0.0006476376,0.00072055997,0.00064054225,0.000051674466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014522112,0.00027074906,0.00046269485,0.00028344453,0.0003878936,0.00029443775,0.003320588,0.0002453949,0.000026220983],"category_scores_gemma":[0.0006134996,0.00017857902,0.00032747473,0.0006769834,0.0000908163,0.00031613387,0.0021580865,0.00044311065,0.0000065193312],"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":[0.000070237445,0.0011960123,0.00048756783,0.0014459601,0.00038693528,2.2990461e-7,0.011041853,0.01306438,0.012276915,0.69742894,0.20822413,0.05437686],"study_design_scores_gemma":[0.0015865577,0.0000331223,0.000109914516,0.0005973117,0.00020420711,0.00000269647,0.012634895,0.4488056,0.08868796,0.31053224,0.13624528,0.00056020985],"about_ca_topic_score_codex":0.000098009274,"about_ca_topic_score_gemma":0.00003123651,"teacher_disagreement_score":0.8678736,"about_ca_system_score_codex":0.00011964114,"about_ca_system_score_gemma":0.00012937322,"threshold_uncertainty_score":0.7282241},"labels":[],"label_agreement":null},{"id":"W4407385487","doi":"10.14778/3696435.3696437","title":"CUTTANA: Scalable Graph Partitioning for Faster Distributed Graph Databases and Analytics","year":2024,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","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 British Columbia","funders":"","keywords":"Computer science; Scalability; Graph database; Analytics; Graph; Database; Theoretical computer science","score_opus":0.022006714325906684,"score_gpt":0.24875675482104148,"score_spread":0.2267500404951348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407385487","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":[0.23346858,0.0034687587,0.7514938,0.005956783,0.0015699033,0.001621721,0.0005780212,0.0005092982,0.0013331571],"genre_scores_gemma":[0.9867967,0.000086303226,0.0126882605,0.0001099052,0.000052469528,0.00007626887,0.000008692672,0.000010730952,0.00017071767],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989793,0.0000057648417,0.00022249918,0.00033359925,0.00020599725,0.00025289218],"domain_scores_gemma":[0.999514,0.00008598014,0.000081092,0.00014559904,0.00010781575,0.00006553359],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037968322,0.00013620198,0.0001502821,0.00012158079,0.0001976088,0.00025017458,0.00044972566,0.000023555676,0.0000039284196],"category_scores_gemma":[0.000046128232,0.000093402625,0.000120805606,0.0006618086,0.00011167539,0.00055202504,0.0002980125,0.00009008918,0.0000013836391],"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":[0.00001591384,0.00009123946,0.002759791,0.0004497018,0.00017136472,0.0000014256668,0.00052690547,0.00006551714,0.007907005,0.97871137,0.0045244936,0.0047752643],"study_design_scores_gemma":[0.000991823,0.0002997435,0.0022719472,0.0010653423,0.00028972028,0.00006670174,0.00068320544,0.08050269,0.2104904,0.68347436,0.019252237,0.00061182625],"about_ca_topic_score_codex":0.0000066186844,"about_ca_topic_score_gemma":0.0000012458477,"teacher_disagreement_score":0.7533281,"about_ca_system_score_codex":0.000016631106,"about_ca_system_score_gemma":0.000015535672,"threshold_uncertainty_score":0.38088483},"labels":[],"label_agreement":null},{"id":"W4407694628","doi":"10.14778/3704965.3704979","title":"Eventual Durability","year":2024,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","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":"University of Waterloo","funders":"","keywords":"Durability; Materials science; Composite material","score_opus":0.006778615071000851,"score_gpt":0.2150393170096381,"score_spread":0.20826070193863724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407694628","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":[0.84243166,0.0051006684,0.037791807,0.023448043,0.0077237133,0.002168942,0.000081915736,0.0012511698,0.08000209],"genre_scores_gemma":[0.99840075,0.000010461824,0.0008388808,0.00005346768,0.000060218008,0.000032205528,2.480644e-7,0.000004789291,0.0005989603],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99893516,0.0000048078687,0.00024495943,0.00028689025,0.00034397002,0.00018422063],"domain_scores_gemma":[0.9995895,0.000023585508,0.00006726029,0.00017913528,0.000096086354,0.000044415672],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003708143,0.0000995651,0.00012503858,0.000032192504,0.00006277006,0.00016639281,0.0009350317,0.00003030174,0.000008655227],"category_scores_gemma":[0.000036111935,0.000061359584,0.00012130506,0.0004635238,0.000043065127,0.0003301079,0.00031702704,0.00010431386,0.000024522247],"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":[0.0000068743243,0.00014538938,0.0025077462,0.0005400298,0.00007239902,0.0000019308864,0.0016969902,0.000018537496,0.031062562,0.91765904,0.020766357,0.025522167],"study_design_scores_gemma":[0.0011163645,0.0003629712,0.030288717,0.0019261722,0.00007492176,0.00018893534,0.0006118295,0.05708325,0.34493735,0.10904338,0.45336708,0.0009990265],"about_ca_topic_score_codex":0.000020970092,"about_ca_topic_score_gemma":5.712025e-7,"teacher_disagreement_score":0.8086156,"about_ca_system_score_codex":0.00006599223,"about_ca_system_score_gemma":0.000033550026,"threshold_uncertainty_score":0.2502171},"labels":[],"label_agreement":null},{"id":"W4408061126","doi":"10.14778/3705829.3705850","title":"Making CRDTs Not So Eventual","year":2024,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Blockchain Technology Applications and Security","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":"Concordia University; University of Toronto","funders":"","keywords":"Computer science","score_opus":0.02123369697432146,"score_gpt":0.2670379170096228,"score_spread":0.24580422003530136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408061126","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":[0.8129536,0.0039845067,0.056770366,0.091986455,0.002331064,0.0022149105,0.000018802419,0.002747616,0.026992673],"genre_scores_gemma":[0.9926598,0.000022396756,0.0067479583,0.0002570946,0.000040470426,0.00007559383,1.0126436e-7,0.0000065145123,0.00019004502],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990979,0.000002664765,0.00018573787,0.00029279332,0.00023280043,0.00018813311],"domain_scores_gemma":[0.99960756,0.000026462094,0.000070772934,0.0002078868,0.00006500675,0.000022311682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027443294,0.00009715712,0.00010109209,0.00008827762,0.00014846608,0.00013178958,0.0012345669,0.000060931743,0.00000765207],"category_scores_gemma":[0.00002382055,0.000067508714,0.000084808904,0.00047227368,0.00009566357,0.0001448457,0.00068130915,0.00018290574,0.000020508156],"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":[0.0000014558389,0.00003913893,0.00012705784,0.000052752686,0.00002151777,4.3257418e-7,0.0007285989,0.0000018248459,0.0124883475,0.95490384,0.0021507961,0.029484235],"study_design_scores_gemma":[0.00030501414,0.00011399393,0.0016279288,0.00038739218,0.000043494656,0.0000875912,0.00022788154,0.036056917,0.5354989,0.28487208,0.14041172,0.0003670834],"about_ca_topic_score_codex":0.000007215352,"about_ca_topic_score_gemma":8.602761e-7,"teacher_disagreement_score":0.6700318,"about_ca_system_score_codex":0.000047312966,"about_ca_system_score_gemma":0.000031667878,"threshold_uncertainty_score":0.27529255},"labels":[],"label_agreement":null},{"id":"W4408061162","doi":"10.14778/3705829.3705830","title":"RED: Effective Trajectory Representation Learning with Comprehensive Information","year":2024,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","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":"Kootenay Association for Science & Technology","funders":"","keywords":"Trajectory; Representation (politics); Computer science; Artificial intelligence; Human–computer interaction; Political science; Physics; Politics","score_opus":0.00837476942388125,"score_gpt":0.22392301270177595,"score_spread":0.2155482432778947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408061162","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":[0.50482297,0.0010483109,0.30609658,0.012289286,0.0039993245,0.008744637,0.00002257394,0.0027657133,0.1602106],"genre_scores_gemma":[0.99161595,0.000031390922,0.0077938302,0.00008765902,0.00004694363,0.00009178045,0.000004958463,0.0000065005133,0.00032097983],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918926,0.000008761836,0.00015242465,0.00018225826,0.00033949007,0.0001278246],"domain_scores_gemma":[0.99960095,0.000043033066,0.000111518326,0.0001022394,0.00011978534,0.000022488197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015877608,0.00009620791,0.000093263916,0.00012075528,0.00008824639,0.00030655164,0.00045676983,0.000017122982,0.0000033134613],"category_scores_gemma":[0.000023445611,0.000060406554,0.00004611606,0.0005008037,0.000034420314,0.002183919,0.00029361848,0.00013057487,0.000014051015],"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":[0.00011139493,0.00013040379,0.0047144457,0.0015957385,0.000576887,0.0000062074128,0.016582046,0.0029343327,0.02219659,0.22430067,0.021517243,0.70533407],"study_design_scores_gemma":[0.003112573,0.001867511,0.06459003,0.0020825483,0.00029530784,0.00008982325,0.0065757865,0.36436224,0.33117238,0.012997905,0.21163271,0.0012211954],"about_ca_topic_score_codex":0.000020865606,"about_ca_topic_score_gemma":3.3791656e-7,"teacher_disagreement_score":0.7041128,"about_ca_system_score_codex":0.000051598316,"about_ca_system_score_gemma":0.000011564071,"threshold_uncertainty_score":0.29560846},"labels":[],"label_agreement":null},{"id":"W4408061173","doi":"10.14778/3705829.3705846","title":"Can Graph Reordering Speed Up Graph Neural Network Training? An Experimental Study","year":2024,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","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 Toronto","funders":"","keywords":"Computer science; Graph; Artificial neural network; Artificial intelligence; Machine learning; Theoretical computer science","score_opus":0.02788617619331354,"score_gpt":0.26391288883681896,"score_spread":0.23602671264350542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408061173","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":[0.9945008,0.00051019195,0.00021376491,0.00049773185,0.0022223657,0.00069019926,0.0000029425019,0.0003382815,0.001023723],"genre_scores_gemma":[0.9980528,0.00000615505,0.0014150823,0.00012555033,0.00019882848,0.000051787567,5.428399e-7,0.000023899938,0.00012538533],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980147,0.000031019823,0.00035774623,0.0006041093,0.00049549027,0.0004969486],"domain_scores_gemma":[0.99936265,0.000034514473,0.000119200435,0.00028354762,0.00006409998,0.0001359872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071342685,0.00027354396,0.000259053,0.00016725266,0.0003008803,0.00037812252,0.0015279013,0.000040268762,0.000010383657],"category_scores_gemma":[0.000012334849,0.00019755935,0.00020595694,0.0011101541,0.00011474797,0.0005906217,0.00051656796,0.00025405711,0.0000019464728],"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":[0.00014451379,0.0022438825,0.007742835,0.00022564674,0.0006935132,0.00005228962,0.19805673,0.0022228302,0.11564227,0.63611364,0.0018634488,0.034998417],"study_design_scores_gemma":[0.0046000904,0.007610138,0.0076756016,0.0009880454,0.00031867574,0.00042127486,0.07302833,0.091095395,0.32743967,0.48283863,0.001250076,0.002734088],"about_ca_topic_score_codex":0.000042230306,"about_ca_topic_score_gemma":0.0000049804294,"teacher_disagreement_score":0.21179739,"about_ca_system_score_codex":0.000039109287,"about_ca_system_score_gemma":0.00002723545,"threshold_uncertainty_score":0.80562365},"labels":[],"label_agreement":null},{"id":"W4408061184","doi":"10.14778/3705829.3705833","title":"Efficient and Effective Algorithms for A Family of Influence Maximization Problems with A Matroid Constraint","year":2024,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","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 British Columbia","funders":"","keywords":"Matroid; Constraint (computer-aided design); Matroid partitioning; Weighted matroid; Maximization; Oriented matroid; Combinatorics; Algorithm; Computer science; Mathematics; Mathematical optimization; Graphic matroid; Geometry","score_opus":0.006558692355830441,"score_gpt":0.23206969491545273,"score_spread":0.22551100255962228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408061184","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":[0.96384704,0.00019633042,0.03318721,0.00010597513,0.000019931967,0.0018152707,0.00003193016,0.000044125398,0.0007522138],"genre_scores_gemma":[0.99125504,0.0000034069458,0.008298427,0.000006466374,0.00002611467,0.0003796588,0.0000016992325,0.000011672824,0.00001752157],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993237,0.000003776216,0.00020005082,0.00019558986,0.00015219579,0.00012463861],"domain_scores_gemma":[0.99953717,0.000050088052,0.00014627527,0.000058697227,0.00018423802,0.000023539327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018511633,0.000114772185,0.00018493755,0.000064510175,0.000044900604,0.000038679605,0.00011289564,0.000014427561,0.0000027870665],"category_scores_gemma":[0.000004766968,0.00007204124,0.00007915947,0.00023816088,0.000117075,0.000037730737,0.00007870703,0.000061056904,1.5433768e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023367583,0.0006383321,0.026382606,0.0027708733,0.0017205338,3.124329e-7,0.0053708362,0.030704018,0.42685464,0.3853796,0.0006286661,0.119315915],"study_design_scores_gemma":[0.0021684633,0.0014596698,0.009696037,0.003809082,0.0010820759,0.000011130617,0.00206705,0.4399158,0.4746652,0.063259065,0.001188681,0.0006777584],"about_ca_topic_score_codex":0.000056470697,"about_ca_topic_score_gemma":3.999747e-7,"teacher_disagreement_score":0.40921178,"about_ca_system_score_codex":0.000027082104,"about_ca_system_score_gemma":0.000020389536,"threshold_uncertainty_score":0.29377568},"labels":[],"label_agreement":null},{"id":"W4409231750","doi":"10.14778/3712221.3712227","title":"How Reliable are Streams? End-to-End Processing-Guarantee Validation and Performance Benchmarking of Stream Processing Systems","year":2024,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Distributed systems and fault tolerance","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":"","keywords":"Benchmarking; Stream processing; STREAMS; Computer science; End-to-end principle; Real-time computing; Distributed computing; Computer network; Business","score_opus":0.012008114402951214,"score_gpt":0.220075315563754,"score_spread":0.2080672011608028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409231750","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":[0.9836027,0.005281876,0.0062772445,0.0012125139,0.00070003734,0.0010574227,0.000040122213,0.00018373964,0.0016443231],"genre_scores_gemma":[0.99777716,0.00009234342,0.0015064344,0.000015756095,0.00011350497,0.00009027287,0.0000023676027,0.00001783581,0.00038431623],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979001,0.000008853878,0.0004954385,0.0005522479,0.0006990411,0.00034426778],"domain_scores_gemma":[0.99880266,0.000023887535,0.0004905125,0.00020150155,0.00041043997,0.000070967115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005555667,0.00024950222,0.00036422475,0.00016363777,0.00019988646,0.0009788572,0.0007452754,0.00007324849,0.00000113775],"category_scores_gemma":[0.000033974295,0.0001751386,0.00007086747,0.00088681467,0.000074172865,0.0013415348,0.00030100698,0.00016445002,0.000001105878],"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":[0.000103295344,0.0004525361,0.03799323,0.03154788,0.0002286608,0.000006713861,0.011318127,0.0024766258,0.080289215,0.028236818,0.0037578654,0.80358905],"study_design_scores_gemma":[0.00090943393,0.0006496123,0.0064049987,0.023361316,0.00014013155,0.00014000243,0.0031203085,0.70281345,0.2507963,0.0006634847,0.010118541,0.0008824221],"about_ca_topic_score_codex":0.000052305262,"about_ca_topic_score_gemma":0.0000013996296,"teacher_disagreement_score":0.8027066,"about_ca_system_score_codex":0.00009727423,"about_ca_system_score_gemma":0.00009417335,"threshold_uncertainty_score":0.94391423},"labels":[],"label_agreement":null},{"id":"W4410543982","doi":"10.14778/3717755.3717766","title":"WeShap: Weak Supervision Source Evaluation with Shapley Values","year":2024,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","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":"University of Toronto","funders":"","keywords":"Shapley value; Mathematical economics; Mathematics; Game theory","score_opus":0.024034614301506736,"score_gpt":0.2549961208786427,"score_spread":0.23096150657713596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410543982","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":[0.8487367,0.0024040902,0.11072988,0.011369716,0.0011294037,0.0017446864,0.0000027333958,0.0006366245,0.02324619],"genre_scores_gemma":[0.9861711,0.000020416554,0.012987473,0.00009228596,0.00009480488,0.000055244345,4.2307417e-7,0.0000131778,0.0005650326],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99823666,0.000010617748,0.0002256262,0.00040854525,0.00091086264,0.00020769493],"domain_scores_gemma":[0.9994029,0.000035147146,0.00007535826,0.00021790955,0.00022202419,0.000046656205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008368109,0.00013737737,0.00012505209,0.0000938663,0.000101820384,0.00023854773,0.00089510385,0.000036391506,0.000023170978],"category_scores_gemma":[0.000047368318,0.00008142887,0.000071827235,0.00036751447,0.000035061155,0.0005132367,0.00043531362,0.0001289268,0.000014938435],"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":[0.000052944153,0.00026496124,0.006220908,0.0009672827,0.00029268034,0.0000019668253,0.018643849,0.0060661607,0.10847002,0.36348766,0.010216412,0.48531514],"study_design_scores_gemma":[0.00039253625,0.0001476023,0.00079860626,0.000562084,0.0000663659,0.000038256843,0.00033473922,0.92077965,0.050922617,0.020758934,0.004988681,0.00020994118],"about_ca_topic_score_codex":0.000041964988,"about_ca_topic_score_gemma":0.0000017548498,"teacher_disagreement_score":0.9147135,"about_ca_system_score_codex":0.00010853578,"about_ca_system_score_gemma":0.000067568595,"threshold_uncertainty_score":0.3320573},"labels":[],"label_agreement":null},{"id":"W4410544001","doi":"10.14778/3717755.3717771","title":"In-Depth Analysis of Densest Subgraph Discovery in a Unified Framework","year":2024,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","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":"Computer science; Computational biology; Biology","score_opus":0.00938181969614827,"score_gpt":0.2451218865393913,"score_spread":0.23574006684324303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410544001","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":[0.9914291,0.000499041,0.0054239137,0.00090009073,0.00034120827,0.00022893176,0.0000056278027,0.000035779325,0.0011363202],"genre_scores_gemma":[0.9970369,0.000058971385,0.0027049258,0.00006364616,0.000012563506,0.000021264403,2.800127e-7,0.000005892112,0.000095592026],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987866,0.000014656695,0.00036005036,0.00031817722,0.00030452292,0.00021593962],"domain_scores_gemma":[0.999471,0.00013626652,0.00011418561,0.00020062792,0.000047349604,0.000030534044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055236364,0.00012708303,0.00028558433,0.00082996365,0.000024875322,0.00010455371,0.00092962955,0.000053392658,0.0000050412345],"category_scores_gemma":[0.000061323335,0.00008803722,0.0002364209,0.005187818,0.0000849567,0.0005420805,0.00029321542,0.0002078059,0.0000012589564],"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":[0.000017544296,0.00016340952,0.0313738,0.00014962441,0.0002546639,0.0000057574157,0.003603575,0.0002765453,0.006396192,0.95646447,0.000045119523,0.001249296],"study_design_scores_gemma":[0.0004590089,0.000153334,0.12669033,0.001187444,0.00034515813,0.000008462043,0.00090055563,0.02305698,0.11265003,0.73398393,0.00016639341,0.0003983918],"about_ca_topic_score_codex":0.000089654175,"about_ca_topic_score_gemma":0.000023733633,"teacher_disagreement_score":0.22248057,"about_ca_system_score_codex":0.000041052223,"about_ca_system_score_gemma":0.000028662529,"threshold_uncertainty_score":0.35900533},"labels":[],"label_agreement":null},{"id":"W4413755882","doi":"10.14778/3718057.3718059","title":"Esc: An Early-Stopping Checker for Budget-Aware Index Tuning","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","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":"Simon Fraser University","funders":"","keywords":"Index (typography); Computer science; Model checking; Programming language","score_opus":0.012348128414331278,"score_gpt":0.2604888289779635,"score_spread":0.24814070056363222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413755882","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":[0.12909666,0.00020324177,0.8637857,0.0012763967,0.00085119664,0.0011594916,0.00002107505,0.0002008008,0.0034054646],"genre_scores_gemma":[0.9204472,0.000009258564,0.077454925,0.00032867666,0.000064124186,0.00019475454,0.0000018811722,0.000013047355,0.0014861887],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99884135,0.0000054154402,0.0002921119,0.0003551884,0.00022657974,0.00027934075],"domain_scores_gemma":[0.99921584,0.000024625788,0.00020423834,0.00027305633,0.0002296706,0.000052592088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030785325,0.00015202416,0.00020567757,0.000098190154,0.0002451858,0.0000760357,0.0007964289,0.00004517774,0.0000018268693],"category_scores_gemma":[0.0000724281,0.00011052223,0.00009161659,0.00033901847,0.0000544915,0.0008325347,0.00058577507,0.000106037805,0.0000011806682],"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":[0.00003340728,0.00008382213,0.009973976,0.00037685913,0.0000648429,3.5174023e-7,0.0016088847,0.00006651774,0.031809326,0.9461116,0.0014146954,0.008455723],"study_design_scores_gemma":[0.0039610495,0.0005739675,0.0238138,0.0026546326,0.00010152906,0.00002182874,0.003895184,0.108488075,0.62862307,0.028259406,0.19828458,0.001322853],"about_ca_topic_score_codex":0.00007676139,"about_ca_topic_score_gemma":0.000005640119,"teacher_disagreement_score":0.91785216,"about_ca_system_score_codex":0.00006696922,"about_ca_system_score_gemma":0.000047938334,"threshold_uncertainty_score":0.4506966},"labels":[],"label_agreement":null},{"id":"W4413755894","doi":"10.14778/3718057.3718071","title":"Cabinet: Dynamically Weighted Consensus Made Fast","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","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":"University of Toronto; Concordia University","funders":"","keywords":"Cabinet (room); Consensus conference; Computer science; History; Library science; Archaeology","score_opus":0.004561944860713993,"score_gpt":0.21195633322434074,"score_spread":0.20739438836362675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413755894","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":[0.6503596,0.0011251885,0.050931405,0.04387285,0.0040370016,0.0028511814,0.000117984506,0.0007096771,0.24599516],"genre_scores_gemma":[0.9922834,0.000008166343,0.00408646,0.00029980353,0.000025060584,0.000039554918,8.12755e-7,0.000005559173,0.003251171],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987016,0.0000079636675,0.00037294385,0.00032492244,0.00031855298,0.00027404705],"domain_scores_gemma":[0.99921596,0.000031823827,0.00020145453,0.00025065953,0.00024642068,0.00005366249],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021493429,0.00015432826,0.00022858329,0.00007127457,0.00011513899,0.000106779895,0.0012967394,0.000057900612,0.0000045790985],"category_scores_gemma":[0.000042285763,0.00010499943,0.00011018165,0.0006047031,0.00008190897,0.000094706775,0.00045171398,0.00013237954,0.000009042058],"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":[0.00003604531,0.00029032675,0.0052591744,0.00031530386,0.00016165739,0.0000025572594,0.00059512723,0.000039536888,0.11401966,0.8262026,0.034007836,0.019070195],"study_design_scores_gemma":[0.0074518444,0.00043212096,0.06660543,0.0028778375,0.00019168218,0.00014917093,0.0011267962,0.23473954,0.42931283,0.083531074,0.17184035,0.0017413225],"about_ca_topic_score_codex":0.00005939519,"about_ca_topic_score_gemma":0.000003253296,"teacher_disagreement_score":0.7426715,"about_ca_system_score_codex":0.000088702036,"about_ca_system_score_gemma":0.000058000467,"threshold_uncertainty_score":0.42817524},"labels":[],"label_agreement":null},{"id":"W4413755925","doi":"10.14778/3718057.3718077","title":"FLEET: High-Performance Durable Replicated State Machines Using Scattered and Coordinated Log Entries","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","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":"","keywords":"State (computer science); Computer science; Environmental science; Algorithm","score_opus":0.007847050474531114,"score_gpt":0.2207120930686482,"score_spread":0.2128650425941171,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413755925","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":[0.99250644,0.0004031485,0.0032042393,0.0019539336,0.00032235423,0.00046850296,0.000017589318,0.00010408364,0.0010197286],"genre_scores_gemma":[0.99751866,0.000059978465,0.0013314224,0.00016240499,0.000012129732,0.000028966866,0.0000012356161,0.0000069695293,0.0008782052],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987068,0.000009250412,0.00038980288,0.00038902895,0.00021396577,0.00029114034],"domain_scores_gemma":[0.9991428,0.000021565458,0.00028017611,0.0002572214,0.00025196557,0.000046239926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030174173,0.00018000237,0.00027169555,0.00009464311,0.00024230323,0.000190034,0.00079280534,0.000042127333,0.0000021764458],"category_scores_gemma":[0.000035673365,0.00012604785,0.0000413609,0.0007202574,0.00010224499,0.00041821576,0.00049768476,0.000110263754,0.0000016880847],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025443942,0.00047580485,0.16041873,0.0023468004,0.0005253431,0.0000037932173,0.0020702307,0.0015315213,0.6861364,0.08881836,0.011442597,0.045975957],"study_design_scores_gemma":[0.0020863318,0.00011712857,0.049714103,0.001152659,0.000058800997,0.00004363121,0.00009686054,0.13741918,0.79933757,0.0055891583,0.003908764,0.0004758467],"about_ca_topic_score_codex":0.00026009826,"about_ca_topic_score_gemma":0.0000020008613,"teacher_disagreement_score":0.13588765,"about_ca_system_score_codex":0.00007010621,"about_ca_system_score_gemma":0.000038679373,"threshold_uncertainty_score":0.5140082},"labels":[],"label_agreement":null},{"id":"W4413812270","doi":"10.14778/3725688.3725720","title":"A Flexible Framework for Query-Oriented Interactive Community Search","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Peer-to-Peer Network Technologies","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; Query optimization; Information retrieval; Web search query; Query expansion; Query language; Theoretical computer science; Search engine","score_opus":0.024246797064614276,"score_gpt":0.3154671397279443,"score_spread":0.29122034266333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413812270","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":[0.17620778,0.00019209296,0.774045,0.029771173,0.0012856405,0.0028430058,0.00001927964,0.0010149968,0.014621022],"genre_scores_gemma":[0.82056886,0.000011332061,0.17767426,0.0006566937,0.00002341079,0.00031557915,4.932602e-7,0.000008896404,0.0007404519],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99869245,0.000020763811,0.00027649087,0.00029624143,0.00032097942,0.00039307415],"domain_scores_gemma":[0.9984057,0.0004060927,0.00013586841,0.000519724,0.0004830636,0.000049582985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007289858,0.00016999285,0.0002396642,0.00019447121,0.0003183674,0.00012294426,0.0030892012,0.000095448195,0.0000012824088],"category_scores_gemma":[0.00084102195,0.00012810694,0.000121702906,0.00113553,0.00010722805,0.00026237647,0.0030400997,0.00059159694,0.00000350229],"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":[0.00008789669,0.0002610106,0.0010868914,0.00013710874,0.00011256474,1.311628e-7,0.0030975281,0.000070949005,0.006119574,0.9509746,0.016273962,0.021777818],"study_design_scores_gemma":[0.00043699384,0.0002883421,0.0012521937,0.0005915318,0.0000211642,0.0000026732246,0.0016449369,0.0025229498,0.7313072,0.24519365,0.016542636,0.00019572291],"about_ca_topic_score_codex":0.00017057748,"about_ca_topic_score_gemma":0.0000062644817,"teacher_disagreement_score":0.72518766,"about_ca_system_score_codex":0.00022964846,"about_ca_system_score_gemma":0.000055493896,"threshold_uncertainty_score":0.57405555},"labels":[],"label_agreement":null},{"id":"W4413812283","doi":"10.14778/3725688.3725721","title":"Tabular: Efficiently Building Efficient Indexes","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","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":"","keywords":"Computer science","score_opus":0.003819544727282654,"score_gpt":0.2172714366275403,"score_spread":0.21345189190025765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413812283","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":[0.85472083,0.001273978,0.10820852,0.004040956,0.0025351958,0.0013165252,0.000016658993,0.0002951736,0.02759216],"genre_scores_gemma":[0.9962987,0.0000061672476,0.0028691934,0.00019380433,0.000027884902,0.000046639485,2.3774201e-7,0.0000055799023,0.0005518394],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983859,0.000007998908,0.00039347756,0.00039437748,0.00048072147,0.00033751564],"domain_scores_gemma":[0.9991534,0.000033579243,0.00023573016,0.0002953817,0.00022895605,0.00005295582],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047778734,0.00017046531,0.0002363288,0.00012563188,0.00020383029,0.00017436255,0.0017387815,0.000055079952,0.0000025442505],"category_scores_gemma":[0.00007768048,0.00011729364,0.00014095775,0.0010221984,0.00006996985,0.00012601336,0.00076624355,0.00014215168,0.0000056418767],"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":[0.0000150579035,0.00031771732,0.0053490666,0.00024796446,0.00007552688,8.1291597e-7,0.0006047437,0.0024549426,0.06917038,0.90727586,0.0066732913,0.007814625],"study_design_scores_gemma":[0.0022624384,0.00013860497,0.013204361,0.0017716611,0.000071532246,0.000017675753,0.0004186212,0.09654362,0.80746365,0.009427817,0.06799141,0.0006885836],"about_ca_topic_score_codex":0.000031146697,"about_ca_topic_score_gemma":6.6391397e-7,"teacher_disagreement_score":0.89784807,"about_ca_system_score_codex":0.000106490304,"about_ca_system_score_gemma":0.000052613064,"threshold_uncertainty_score":0.47830957},"labels":[],"label_agreement":null},{"id":"W4413825196","doi":"10.14778/3734839.3734849","title":"Accio: Bolt-on Query Federation","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","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":"Simon Fraser University","funders":"","keywords":"Russian federation; Computer science; Information retrieval; Geography; Regional science","score_opus":0.005557855411297835,"score_gpt":0.22850257909836866,"score_spread":0.22294472368707083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413825196","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":[0.2652851,0.0012472558,0.45073313,0.03265786,0.006186342,0.00350303,0.000036781395,0.0008321065,0.23951837],"genre_scores_gemma":[0.98220885,0.000026895315,0.014723677,0.00071214273,0.000055531425,0.00007469351,7.96096e-7,0.0000054780653,0.00219194],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991816,0.0000048749457,0.00021063103,0.00023125704,0.00022473477,0.00014688203],"domain_scores_gemma":[0.9995006,0.000027861923,0.00013601492,0.00019964545,0.000112548005,0.000023363846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018361676,0.00010213245,0.00012466521,0.000064691194,0.00020109703,0.000067031615,0.0004583232,0.00002669642,0.000002718044],"category_scores_gemma":[0.0000752507,0.000066840956,0.000058151047,0.00026747384,0.000030124944,0.00041870936,0.00036580695,0.00007922569,0.000006447361],"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":[0.000008953588,0.000039463048,0.00056391425,0.000056556753,0.000014033903,1.2584623e-7,0.00017165083,0.000022441734,0.019574638,0.96822935,0.006372961,0.0049459],"study_design_scores_gemma":[0.0006482901,0.00012544937,0.003380006,0.0005303831,0.000014257012,0.0000062331433,0.0003429566,0.0019588205,0.840261,0.023574194,0.12891743,0.00024096898],"about_ca_topic_score_codex":0.00002955954,"about_ca_topic_score_gemma":0.0000037880457,"teacher_disagreement_score":0.9446552,"about_ca_system_score_codex":0.000059087713,"about_ca_system_score_gemma":0.000032837597,"threshold_uncertainty_score":0.2725695},"labels":[],"label_agreement":null},{"id":"W4413825311","doi":"10.14778/3725688.3725693","title":"Efficient Historical Butterfly Counting in Large Temporal Bipartite Networks via Graph Structure-Aware Index","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","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":"","keywords":"Bipartite graph; Computer science; Butterfly; Graph; Index (typography); Theoretical computer science; Artificial intelligence; World Wide Web; Biology; Ecology","score_opus":0.0045790634591464825,"score_gpt":0.22311424491938264,"score_spread":0.21853518146023615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413825311","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":[0.96469724,0.00025822117,0.03113424,0.00055092265,0.00031944574,0.00071017805,0.000012381647,0.00008450822,0.002232876],"genre_scores_gemma":[0.99931246,0.0000018156352,0.0002522906,0.00007490541,0.00013247026,0.000054905024,0.000005219003,0.00001454564,0.00015138723],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984477,0.000012985643,0.00051543757,0.00032983258,0.00028686307,0.00040714213],"domain_scores_gemma":[0.9992918,0.000029487614,0.00032377875,0.00017352018,0.0001390592,0.000042388918],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031941847,0.0002196865,0.00036487042,0.0002183376,0.00014298486,0.000048830945,0.00046912863,0.000055132135,0.000051767318],"category_scores_gemma":[0.000006385256,0.00017014334,0.00021123013,0.0009836142,0.00004332342,0.00004734616,0.00038845337,0.00032625123,5.4831e-7],"study_design_candidate":"observational","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":[0.000028822808,0.00022727063,0.9795265,0.000037433205,0.00010258551,1.9604965e-7,0.00013624514,0.00453859,0.001752032,0.008600784,0.003152302,0.0018972277],"study_design_scores_gemma":[0.003855187,0.00015254063,0.18022403,0.0012608647,0.0005093215,0.000002386636,0.00077308004,0.685754,0.029665692,0.07632391,0.020042874,0.0014361009],"about_ca_topic_score_codex":0.00068866374,"about_ca_topic_score_gemma":0.000042957632,"teacher_disagreement_score":0.79930246,"about_ca_system_score_codex":0.00028678428,"about_ca_system_score_gemma":0.00002574503,"threshold_uncertainty_score":0.6938244},"labels":[],"label_agreement":null},{"id":"W4413827533","doi":"10.14778/3725688.3725702","title":"G-View: View Management for Graph Databases","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management 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":"McGill University","funders":"","keywords":"Computer science; Graph database; Database; Graph; Information retrieval; Theoretical computer science","score_opus":0.019736695528153752,"score_gpt":0.26537238348359177,"score_spread":0.24563568795543803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413827533","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":[0.003544098,0.006517343,0.704534,0.035432015,0.0055776085,0.011312382,0.00018390757,0.00082023244,0.2320784],"genre_scores_gemma":[0.17980383,0.0072743976,0.75260484,0.0101361275,0.00033248452,0.0033335306,0.00006298009,0.00007294657,0.046378836],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99876356,0.000004120002,0.0002830835,0.0003938288,0.00028852464,0.00026690282],"domain_scores_gemma":[0.99931353,0.000029142644,0.00014984363,0.0003834215,0.00009272903,0.00003134461],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043670257,0.00015272021,0.00018168143,0.00015752122,0.00015486337,0.00014173915,0.00208151,0.000013445477,0.000005517251],"category_scores_gemma":[0.000023908227,0.00010605235,0.00012885721,0.000667628,0.000044324534,0.0005555601,0.0018403237,0.000052735813,0.0000058386513],"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":[0.0000057830116,0.00010536232,0.00018654476,0.00061891007,0.00010865628,2.525989e-7,0.000037891277,0.0000020560362,0.00024206744,0.81674397,0.07242507,0.10952346],"study_design_scores_gemma":[0.0010053793,0.000059796213,0.0010373612,0.0005483097,0.00014111033,0.0000011326885,0.00014447422,0.0018008369,0.022867534,0.052304223,0.91984177,0.0002480948],"about_ca_topic_score_codex":0.000010796845,"about_ca_topic_score_gemma":0.000001143375,"teacher_disagreement_score":0.8474167,"about_ca_system_score_codex":0.00003307833,"about_ca_system_score_gemma":0.000009844149,"threshold_uncertainty_score":0.43246895},"labels":[],"label_agreement":null},{"id":"W4413943427","doi":"10.14778/3742728.3742754","title":"CatDB: Data-Catalog-Guided, LLM-Based Generation of Data-Centric ML Pipelines","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Machine Learning and Data Classification","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":"Concordia University","funders":"","keywords":"Pipeline transport; Computer science; Environmental science","score_opus":0.10422959380219059,"score_gpt":0.32988666442145576,"score_spread":0.22565707061926515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413943427","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":[0.12207971,0.0037642193,0.77877444,0.06870809,0.0040067737,0.003967969,0.0014612548,0.0008087559,0.016428798],"genre_scores_gemma":[0.9618042,0.00006762869,0.036685206,0.0003480705,0.000107081905,0.000020269816,0.0005647264,0.000008437706,0.00039434005],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982977,0.000022621556,0.00049220625,0.0005959546,0.00041173233,0.0001797687],"domain_scores_gemma":[0.9976485,0.000064514694,0.00045354362,0.001523611,0.0002728242,0.000037012956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00097248756,0.0001416655,0.00019822606,0.00016919553,0.00012389537,0.000102159545,0.0045214887,0.00004703688,0.000005222705],"category_scores_gemma":[0.00051652576,0.0001019236,0.000038601127,0.0007505009,0.000063018095,0.00077889033,0.0018996816,0.00012732144,0.000006308883],"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":[0.000057692516,0.0014953341,0.040131994,0.0011893446,0.00020262419,6.73699e-7,0.0004949994,0.0010599345,0.18693104,0.19132194,0.38838005,0.18873438],"study_design_scores_gemma":[0.0010381844,0.00006313557,0.0048008813,0.00016291605,0.000113254464,0.000004536686,0.00005136023,0.78914046,0.13819465,0.000968196,0.06522674,0.00023571198],"about_ca_topic_score_codex":0.00025178306,"about_ca_topic_score_gemma":0.00001286109,"teacher_disagreement_score":0.83972454,"about_ca_system_score_codex":0.00004373011,"about_ca_system_score_gemma":0.0001504682,"threshold_uncertainty_score":0.8402126},"labels":[],"label_agreement":null},{"id":"W4413943450","doi":"10.14778/3742728.3742738","title":"Asymmetric Linearizable Local Reads","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","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":"University of Toronto","funders":"","keywords":"Computer science; Programming language; Mathematics; Process management; Business","score_opus":0.005162037269071246,"score_gpt":0.21707470301876206,"score_spread":0.2119126657496908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413943450","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":[0.015217753,0.0025796616,0.59066516,0.010347088,0.0031682302,0.0015028014,0.000029878855,0.00042550243,0.37606394],"genre_scores_gemma":[0.9920134,0.000023014867,0.0037939833,0.00028951673,0.00003188239,0.000036269175,4.674008e-7,0.0000044074877,0.0038070772],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988515,0.000005289892,0.00030005974,0.00027758811,0.00032315453,0.00024244047],"domain_scores_gemma":[0.999318,0.000027492319,0.00015339488,0.00023630128,0.0002217013,0.000043122716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033009035,0.000118593285,0.00019111855,0.00012122694,0.00011081997,0.00011296882,0.001343171,0.00005175343,0.0000024139977],"category_scores_gemma":[0.00006822992,0.000080196376,0.00009827281,0.0015429758,0.00005601787,0.0002218441,0.0005153634,0.00012105671,0.000011640454],"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":[0.000016720736,0.00027249838,0.0028982598,0.0002831254,0.00009025564,9.1019933e-7,0.0002389016,0.00015583723,0.009676969,0.8333809,0.08016745,0.07281817],"study_design_scores_gemma":[0.0018439834,0.00019547481,0.0073222015,0.0008116674,0.000056868805,0.00002319457,0.00026936515,0.06559712,0.51609147,0.025245363,0.38203192,0.0005113603],"about_ca_topic_score_codex":0.00008052291,"about_ca_topic_score_gemma":8.675389e-7,"teacher_disagreement_score":0.9767956,"about_ca_system_score_codex":0.00008193474,"about_ca_system_score_gemma":0.000053570373,"threshold_uncertainty_score":0.3270313},"labels":[],"label_agreement":null},{"id":"W4413948809","doi":"10.14778/3746405.3746414","title":"KEIGO: Co-Designing Log-Structured Merge Key-Value Stores with a Non-Volatile, Concurrency-Aware Storage Hierarchy","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Data Storage Technologies","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":"McGill University","funders":"","keywords":"Merge (version control); Computer science; Concurrency; Hierarchy; Memory hierarchy; Database; Key (lock); Parallel computing; Distributed computing; Operating system","score_opus":0.007952278613537941,"score_gpt":0.24574192578378504,"score_spread":0.2377896471702471,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413948809","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":[0.22307724,0.00139244,0.7554803,0.0029578505,0.0014169936,0.0034307593,0.00013697792,0.0017961223,0.010311316],"genre_scores_gemma":[0.92327076,0.000038607803,0.07605485,0.00015976105,0.00002768936,0.00014200478,0.000003791472,0.000021277574,0.000281237],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9976063,0.000016953514,0.00044272127,0.00074491533,0.0006511481,0.00053797587],"domain_scores_gemma":[0.99841887,0.00010190973,0.00047907347,0.00067536504,0.0002503927,0.00007438775],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00030074976,0.00039413638,0.00045732426,0.00032100428,0.00032411583,0.00014002107,0.0031728817,0.00012328579,0.00000798549],"category_scores_gemma":[0.00017443494,0.00026619426,0.00010838229,0.001144941,0.00037865213,0.00085087353,0.0013918384,0.00046848325,0.000003627804],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030435048,0.00039567632,0.020591099,0.0011193365,0.00067883043,0.000028993167,0.0068934183,0.0016766558,0.27733722,0.6154674,0.037106663,0.038400307],"study_design_scores_gemma":[0.0026192742,0.0006225953,0.0054391404,0.0010457532,0.0001226952,0.00004148274,0.0014652747,0.016396925,0.91251945,0.0513282,0.007430007,0.00096917764],"about_ca_topic_score_codex":0.00003971156,"about_ca_topic_score_gemma":0.0000057066845,"teacher_disagreement_score":0.7001935,"about_ca_system_score_codex":0.00026585377,"about_ca_system_score_gemma":0.00018446006,"threshold_uncertainty_score":0.999979},"labels":[],"label_agreement":null},{"id":"W4413953194","doi":"10.14778/3742728.3742730","title":"Oze: Decentralized Graph-Based Concurrency Control for Long-Running Update Transactions","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","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":"Nautilus Environmental","funders":"","keywords":"Concurrency control; Computer science; Concurrency; Graph; Control (management); Distributed computing; Programming language; Theoretical computer science; Database transaction; Artificial intelligence","score_opus":0.007703296319875869,"score_gpt":0.24421487510674494,"score_spread":0.23651157878686907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413953194","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":[0.004752785,0.0006040714,0.98710626,0.004492371,0.0009195286,0.0012525523,0.00006398191,0.00011316557,0.0006952647],"genre_scores_gemma":[0.99533755,0.00002146671,0.0036944335,0.00045567332,0.000015986263,0.00030312993,0.000002137849,0.000006792753,0.0001628372],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99862695,0.00000806765,0.00042695273,0.00033664567,0.00025744052,0.0003439739],"domain_scores_gemma":[0.99910736,0.00005516879,0.0002484423,0.00020049015,0.0003249962,0.000063538515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032773567,0.00017427627,0.0002914998,0.00009572849,0.00023515393,0.00013485012,0.0010147197,0.00005533208,0.0000069084244],"category_scores_gemma":[0.000033404576,0.00012923428,0.00026105804,0.0005696493,0.00006584578,0.00024061048,0.000033147295,0.00010937337,0.0000016462201],"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":[0.00049117045,0.0013616342,0.018603522,0.0021033797,0.0009209264,0.0000018026677,0.0010758905,0.0036349632,0.03658173,0.8386704,0.028439865,0.06811477],"study_design_scores_gemma":[0.036120217,0.00051207986,0.0125851715,0.0029731449,0.0007031078,0.00001883219,0.0003431571,0.29213154,0.46728662,0.03828,0.14744172,0.0016044066],"about_ca_topic_score_codex":0.000019556868,"about_ca_topic_score_gemma":0.0000030973022,"teacher_disagreement_score":0.99058473,"about_ca_system_score_codex":0.00006249616,"about_ca_system_score_gemma":0.00008773111,"threshold_uncertainty_score":0.5270021},"labels":[],"label_agreement":null},{"id":"W4413953529","doi":"10.14778/3742728.3742753","title":"Robust Plan Evaluation Based on Approximate Probabilistic Machine Learning","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Rough Sets and Fuzzy Logic","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":"IBM (Canada); University of Ottawa","funders":"","keywords":"Plan (archaeology); Probabilistic logic; Computer science; Machine learning; Artificial intelligence","score_opus":0.03655889814260427,"score_gpt":0.24015690820941218,"score_spread":0.20359801006680792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413953529","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":[0.10767514,0.0009820121,0.12156023,0.03778073,0.0032426172,0.010800806,0.000024046743,0.0012420088,0.7166924],"genre_scores_gemma":[0.98742056,0.000005779293,0.011823272,0.00043244584,0.000020049627,0.000118639124,0.0000021983342,0.0000059692547,0.00017110998],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986692,0.000023266013,0.00023526468,0.0003326748,0.0005307074,0.00020889306],"domain_scores_gemma":[0.9993613,0.000060843067,0.00018246514,0.0001926639,0.00017119183,0.000031588937],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093741703,0.00013980755,0.00015673232,0.00010872562,0.0001823877,0.000112656424,0.00082932005,0.00003877117,0.000009998591],"category_scores_gemma":[0.00026409412,0.0000884228,0.00007394229,0.00044422643,0.000039297203,0.00012035741,0.00025886387,0.00017305063,0.000003689221],"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":[0.00023613237,0.0014050084,0.019647395,0.0013613378,0.00014459805,0.0000014183064,0.0018975735,0.346534,0.007741678,0.5112867,0.0054200776,0.104324095],"study_design_scores_gemma":[0.0005806446,0.00013267758,0.0015480986,0.00018150297,0.00002764999,0.0000010545923,0.000025618003,0.9785664,0.0039525516,0.014303535,0.000581029,0.00009920854],"about_ca_topic_score_codex":0.000019218887,"about_ca_topic_score_gemma":0.0000013913061,"teacher_disagreement_score":0.8797454,"about_ca_system_score_codex":0.00013298285,"about_ca_system_score_gemma":0.000059716946,"threshold_uncertainty_score":0.3605777},"labels":[],"label_agreement":null},{"id":"W4413968449","doi":"10.14778/3746405.3746413","title":"Locality-Aware Cache Replacement Policy for Graph Traversals","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","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 Waterloo","funders":"","keywords":"Locality; Cache; Computer science; Locality of reference; Graph; Parallel computing; Theoretical computer science","score_opus":0.008567600864450518,"score_gpt":0.2535545745113512,"score_spread":0.2449869736469007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413968449","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":[0.10973862,0.00073288236,0.7796397,0.05940191,0.002968736,0.0068950136,0.00009867685,0.0006770018,0.039847452],"genre_scores_gemma":[0.9905823,0.000020769803,0.006626283,0.0011303648,0.00005726381,0.00018752636,7.816767e-7,0.000007810464,0.0013869111],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99871415,0.000012236686,0.00031955412,0.00036884006,0.00026481145,0.00032041012],"domain_scores_gemma":[0.9992094,0.00007113988,0.0001797829,0.00028579458,0.00019613403,0.000057767873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071636727,0.00016397628,0.00020800928,0.00019909955,0.0002115022,0.0000845985,0.0013390966,0.000050734878,0.0000038674452],"category_scores_gemma":[0.00008223247,0.000115438335,0.00022609244,0.0008213516,0.00009621593,0.00019179782,0.00042604082,0.0000993022,0.0000015763336],"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":[0.000041958945,0.00012990013,0.0004669645,0.00017820873,0.00009221271,9.978331e-8,0.00069171155,0.000015075924,0.0037235094,0.9826879,0.00372994,0.008242513],"study_design_scores_gemma":[0.0013493677,0.00021426576,0.0005499723,0.00019550047,0.000051258772,0.0000044133176,0.00066941394,0.0035349594,0.341785,0.64248145,0.008937408,0.00022701068],"about_ca_topic_score_codex":0.000043225715,"about_ca_topic_score_gemma":9.989478e-7,"teacher_disagreement_score":0.88084364,"about_ca_system_score_codex":0.0000846769,"about_ca_system_score_gemma":0.00007970907,"threshold_uncertainty_score":0.4707439},"labels":[],"label_agreement":null},{"id":"W4413978687","doi":"10.14778/3749646.3749676","title":"Environmental Footprints of Query Processing: A Vision for Sustainable Database Architectures","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Cloud Computing and Resource Management","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; Database; Information retrieval","score_opus":0.005778839045125856,"score_gpt":0.230482807218248,"score_spread":0.22470396817312213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413978687","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":[0.97088027,0.0004523696,0.016445465,0.0022415812,0.00014578892,0.0014973296,0.000003902941,0.00008451721,0.008248748],"genre_scores_gemma":[0.9902365,0.0000037066266,0.0077180457,0.0001125097,0.000021097218,0.000057941175,3.7603604e-7,0.0000066343932,0.0018431958],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998778,0.0000072718585,0.0002960596,0.0003353488,0.00030658094,0.00027674952],"domain_scores_gemma":[0.9993377,0.000047295056,0.0002463657,0.00024721416,0.0000882997,0.000033148495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004389843,0.00013674858,0.00018129052,0.00014840171,0.00017784101,0.00006510296,0.0011880748,0.000028739765,9.325317e-7],"category_scores_gemma":[0.000079846606,0.00009375157,0.00010885961,0.0003489956,0.00009019104,0.000031267376,0.0017442941,0.00008586021,3.271718e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037366152,0.0025744783,0.012092358,0.008975583,0.0003801673,0.0000034739621,0.005814573,0.0044183508,0.20305148,0.37192217,0.012359521,0.37803417],"study_design_scores_gemma":[0.0034992762,0.00071378006,0.020546734,0.001865052,0.00017451502,0.000011854393,0.003539065,0.10225848,0.77398366,0.05514915,0.03761814,0.0006403094],"about_ca_topic_score_codex":0.00002449357,"about_ca_topic_score_gemma":3.9029268e-7,"teacher_disagreement_score":0.57093215,"about_ca_system_score_codex":0.000077877,"about_ca_system_score_gemma":0.000039674203,"threshold_uncertainty_score":0.38230783},"labels":[],"label_agreement":null},{"id":"W4413978785","doi":"10.14778/3749646.3749727","title":"ParSEval: Plan-Aware Test Database Generation for SQL Equivalence Evaluation","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Scientific Computing and Data Management","field":"Decision Sciences","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":"","keywords":"Computer science; Database; SQL; Parseval's theorem; Plan (archaeology); Equivalence (formal languages); Programming language; Mathematics; Discrete mathematics","score_opus":0.30194040095456554,"score_gpt":0.43839978790090695,"score_spread":0.1364593869463414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413978785","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":[0.8814117,0.00079823803,0.05190799,0.016888615,0.011637061,0.009902502,0.0010023138,0.00024298005,0.02620863],"genre_scores_gemma":[0.99422836,0.0000096559015,0.002612843,0.0002779416,0.00011592112,0.00017928005,0.0000312577,0.000005546544,0.002539205],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99670935,0.000023027193,0.0006235163,0.00069383834,0.0017181817,0.00023207076],"domain_scores_gemma":[0.9972804,0.00060298486,0.00041311258,0.00057386915,0.0010852789,0.000044343466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009009007,0.0001275901,0.00017300578,0.00024045506,0.00032772621,0.00037367485,0.0014031696,0.00003026,0.00008697494],"category_scores_gemma":[0.0081132,0.00008153628,0.00010622425,0.0009047411,0.0000748065,0.00034303518,0.00078936334,0.00006250628,0.000017931752],"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":[0.00005309268,0.00030587486,0.011154183,0.00013110029,0.000046481633,1.11906154e-7,0.00045866356,0.0008512009,0.084483854,0.020018978,0.77851605,0.10398039],"study_design_scores_gemma":[0.0020885693,0.00016958496,0.005885048,0.00040325534,0.00028683362,0.0000025409097,0.0024756535,0.67658347,0.19234847,0.06170914,0.057686698,0.00036077166],"about_ca_topic_score_codex":0.000021392032,"about_ca_topic_score_gemma":0.000012143974,"teacher_disagreement_score":0.72082937,"about_ca_system_score_codex":0.00010020745,"about_ca_system_score_gemma":0.00008794876,"threshold_uncertainty_score":0.97128445},"labels":[],"label_agreement":null},{"id":"W4413980865","doi":"10.14778/3749646.3749703","title":"Sphinx: A Succinct Perfect Hash Index for x86","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Data Storage Technologies","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 Toronto","funders":"","keywords":"Hash function; Sphinx; Index (typography); Computer science; x86; Computer security; History; World Wide Web; Programming language; Archaeology","score_opus":0.00943147209938856,"score_gpt":0.24889599828362524,"score_spread":0.2394645261842367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413980865","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":[0.115346074,0.0016192547,0.84424096,0.020316016,0.0015890016,0.0038830421,0.00004205764,0.0015642451,0.011399334],"genre_scores_gemma":[0.943225,0.000044467633,0.05570468,0.0002750294,0.000021305364,0.00022445942,5.613011e-7,0.000008758868,0.0004957422],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988083,0.0000027459523,0.00024905024,0.00039959766,0.00024059454,0.00029970007],"domain_scores_gemma":[0.9991348,0.000082786886,0.00018584654,0.00039746807,0.00017396908,0.000025158051],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002793213,0.00016475917,0.00021352035,0.00015471765,0.00016403265,0.00008834212,0.0024010371,0.000065157445,0.0000022991144],"category_scores_gemma":[0.0002894661,0.0001150882,0.00011645189,0.0006127405,0.00010587995,0.00045568636,0.00158024,0.00014457945,0.0000028246727],"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":[0.000050538794,0.00015593051,0.005116499,0.00027982294,0.0000859753,5.953367e-7,0.00033007917,0.00005520607,0.0463079,0.8429737,0.027036887,0.07760687],"study_design_scores_gemma":[0.0015134983,0.0002197455,0.0029140145,0.00025841765,0.00003144387,0.000010043909,0.0002472492,0.0056827553,0.6688647,0.25731587,0.06261017,0.0003320718],"about_ca_topic_score_codex":0.00001304193,"about_ca_topic_score_gemma":0.0000021524904,"teacher_disagreement_score":0.8278789,"about_ca_system_score_codex":0.0001286948,"about_ca_system_score_gemma":0.00004140823,"threshold_uncertainty_score":0.46931607},"labels":[],"label_agreement":null},{"id":"W4413985233","doi":"10.14778/3748191.3748215","title":"PS-MI: Accurate, Efficient, and Private Data Valuation in Vertical Federated Learning","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Privacy-Preserving Technologies in Data","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":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Valuation (finance); Federated learning; Computer science; Business; Artificial intelligence; Finance","score_opus":0.04816835999275128,"score_gpt":0.30465121280028323,"score_spread":0.25648285280753197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413985233","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":[0.9434501,0.00029108074,0.023806449,0.028808702,0.0003059226,0.0007078379,0.0000055408655,0.00036385134,0.0022605432],"genre_scores_gemma":[0.98101,0.000057115296,0.018780278,0.000087154076,0.0000061757314,0.000023155815,0.0000034815127,0.0000052730816,0.000027325897],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998572,0.000021532078,0.00030995463,0.000519298,0.00031576393,0.00026144568],"domain_scores_gemma":[0.99823934,0.00011492668,0.000108941436,0.0014159147,0.00009531804,0.000025563746],"candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.000963407,0.00012606622,0.00015882112,0.00015939484,0.00014924041,0.0002175852,0.012175968,0.00007160461,0.0000018120325],"category_scores_gemma":[0.01542342,0.000097178774,0.000017836192,0.0009021521,0.000102337,0.00048012732,0.075022295,0.0002921904,0.0000022349811],"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":[0.00022027075,0.0011400037,0.16805638,0.0010604389,0.00031806628,0.000006900073,0.0012115323,0.0013159505,0.3170422,0.27991465,0.09507675,0.13463683],"study_design_scores_gemma":[0.00074334466,0.000046234287,0.015880823,0.000294733,0.000017026603,0.000004308517,0.00008872184,0.78879356,0.12109754,0.07217609,0.0007052579,0.00015234677],"about_ca_topic_score_codex":0.000027883205,"about_ca_topic_score_gemma":0.0000029824494,"teacher_disagreement_score":0.7874776,"about_ca_system_score_codex":0.00008711705,"about_ca_system_score_gemma":0.000047830574,"threshold_uncertainty_score":0.99316865},"labels":[],"label_agreement":null},{"id":"W4413986970","doi":"10.14778/3748191.3748195","title":"Déjà Vu: Efficient Video-Language Query Engine with Learning-Based Inter-Frame Computation Reuse","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Multimodal Machine Learning Applications","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":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Reuse; Déjà vu; Frame (networking); Computation; Artificial intelligence; Natural language processing; Programming language; Computer network; Engineering; Psychology","score_opus":0.0037931050791894048,"score_gpt":0.24165399323101416,"score_spread":0.23786088815182477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413986970","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":[0.5481965,0.00007601039,0.43889576,0.009459417,0.00016477353,0.0008095074,0.00000187378,0.00038961563,0.002006523],"genre_scores_gemma":[0.95854926,0.0000014245213,0.040700175,0.00032213458,0.000019750978,0.00012030779,0.0000021901008,0.000014019594,0.00027071548],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985976,0.000025252104,0.00031048074,0.0004346843,0.0003766759,0.00025531],"domain_scores_gemma":[0.9988494,0.00015111965,0.00030402956,0.00038896166,0.00024777482,0.00005871621],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004027556,0.00019776456,0.00020685502,0.00021760644,0.00018824107,0.00013236476,0.0014451675,0.000049597016,0.00000598591],"category_scores_gemma":[0.00032772758,0.00013925364,0.00008572943,0.00082918647,0.00008308865,0.000103159175,0.0006119481,0.00036797917,0.000012665251],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012998679,0.0010601173,0.019983426,0.0005842034,0.00019163701,0.000002187144,0.007576079,0.83196187,0.0627114,0.03501408,0.0021860686,0.03859892],"study_design_scores_gemma":[0.00097353914,0.00017216578,0.009407695,0.00035755493,0.00003531475,0.0000045842808,0.00019027607,0.9290221,0.05805768,0.00051644904,0.0010582367,0.00020440343],"about_ca_topic_score_codex":0.000276922,"about_ca_topic_score_gemma":0.0000032278306,"teacher_disagreement_score":0.41035277,"about_ca_system_score_codex":0.0001517321,"about_ca_system_score_gemma":0.00007515073,"threshold_uncertainty_score":0.5678598},"labels":[],"label_agreement":null},{"id":"W4414003971","doi":"10.14778/3749646.3749707","title":"OasisDB: An Oblivious and Scalable System for Relational Data","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Cryptography and Data Security","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":"Scalability; Computer science; Relational database; Database","score_opus":0.02953292981573211,"score_gpt":0.26023942873683936,"score_spread":0.23070649892110726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414003971","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":[0.5219597,0.0065266085,0.40090504,0.016340764,0.00404695,0.0075156335,0.0014663317,0.0011531026,0.04008581],"genre_scores_gemma":[0.9497371,0.000018329358,0.05003173,0.000094077936,0.000030675426,0.000040967447,0.000011719901,0.0000034853067,0.00003194881],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991355,0.000004763172,0.00018372945,0.00035080497,0.00018330093,0.00014190208],"domain_scores_gemma":[0.9992987,0.00005624126,0.00010454225,0.000383164,0.00011763355,0.000039702398],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039602423,0.00008300589,0.000114763745,0.00007966535,0.00018663016,0.000120653094,0.0013375026,0.000034024768,7.789458e-7],"category_scores_gemma":[0.000058131987,0.000060383303,0.000034189976,0.00032878894,0.000051171544,0.00076814095,0.0010899215,0.000058327907,4.3769631e-7],"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":[0.00001296107,0.00006230245,0.0030727172,0.00020493724,0.000025990483,4.201893e-8,0.0001918577,0.0000016563798,0.0013335575,0.9882578,0.0037560558,0.0030800884],"study_design_scores_gemma":[0.006371885,0.0006955225,0.054660678,0.001909817,0.00043883573,0.000082969316,0.0031981738,0.23751287,0.10952001,0.46833417,0.11607564,0.0011994274],"about_ca_topic_score_codex":0.000031769043,"about_ca_topic_score_gemma":0.0000041782264,"teacher_disagreement_score":0.5199237,"about_ca_system_score_codex":0.000022930903,"about_ca_system_score_gemma":0.000032881613,"threshold_uncertainty_score":0.24854349},"labels":[],"label_agreement":null},{"id":"W4414003972","doi":"10.14778/3749646.3749704","title":"NaviX: A Native Vector Index Design for Graph DBMSs With Robust Predicate-Agnostic Search Performance","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Graph Theory 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 Waterloo","funders":"","keywords":"Computer science; Predicate (mathematical logic); Graph; Programming language; Theoretical computer science","score_opus":0.017912365227868456,"score_gpt":0.22755192029124968,"score_spread":0.20963955506338122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414003972","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":[0.34475243,0.00020176338,0.6481917,0.0019341519,0.0004175535,0.0029146455,0.000012916013,0.00017263746,0.0014021822],"genre_scores_gemma":[0.9796585,0.000026199212,0.019486126,0.000114791554,0.000023833782,0.00037885163,4.7572345e-7,0.000010331941,0.00030092197],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985302,0.000018597591,0.00023992908,0.00040788844,0.00042211066,0.0003812873],"domain_scores_gemma":[0.9989421,0.00022941019,0.00015335924,0.00020582446,0.00040400203,0.00006529762],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000751777,0.00019637583,0.00021702271,0.0001997073,0.00031102484,0.00010001679,0.0015023849,0.00005196093,0.0000023031012],"category_scores_gemma":[0.00009483388,0.00012368537,0.00009627486,0.0010773253,0.00019845123,0.00036982985,0.00035260626,0.00019753719,0.0000012730266],"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":[0.0019075221,0.0017511635,0.042242777,0.0027316536,0.0013321799,0.000003268659,0.01238594,0.039118025,0.021820772,0.84552073,0.003978176,0.027207796],"study_design_scores_gemma":[0.0041560754,0.0020280033,0.02571418,0.0017198076,0.00015356095,0.000025106423,0.0006909505,0.25095505,0.65449375,0.059063762,0.00033446052,0.000665289],"about_ca_topic_score_codex":0.000008661921,"about_ca_topic_score_gemma":4.9793573e-7,"teacher_disagreement_score":0.78645694,"about_ca_system_score_codex":0.00006193234,"about_ca_system_score_gemma":0.000114576935,"threshold_uncertainty_score":0.5043743},"labels":[],"label_agreement":null},{"id":"W4414004064","doi":"10.14778/3749646.3749702","title":"ThriftLLM: On Cost-Effective Selection of Large Language Models for Classification Queries","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","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":"Selection (genetic algorithm); Computer science; Natural language processing; Artificial intelligence; Information retrieval","score_opus":0.09834815259862227,"score_gpt":0.4145340017749151,"score_spread":0.31618584917629283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414004064","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":[0.5803645,0.0003804481,0.15552944,0.019755337,0.002064,0.025336618,0.00093051937,0.0002262028,0.21541293],"genre_scores_gemma":[0.9961619,0.000015132986,0.0006128923,0.00032023204,0.000019580777,0.0006632246,0.0000044916083,0.0000049164305,0.0021976524],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99850607,0.000026503025,0.00043044638,0.00029698684,0.00058439095,0.00015559634],"domain_scores_gemma":[0.99859476,0.00036713108,0.0004082665,0.00018823045,0.00042113476,0.00002045828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023218372,0.000100669124,0.00021614583,0.00019056893,0.00012981067,0.00006280022,0.00056791486,0.000043113134,0.000015836597],"category_scores_gemma":[0.0010895476,0.00006373677,0.000121068355,0.00055930106,0.00006504696,0.00030057595,0.0002024984,0.00006840115,0.0000036606534],"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":[0.00024352982,0.00027290577,0.0005469158,0.00012654062,0.00006211047,1.3252652e-8,0.0016728443,0.000094482755,0.022499759,0.9178571,0.021165498,0.035458308],"study_design_scores_gemma":[0.0017091456,0.00041660317,0.008408657,0.0002607367,0.000114170325,4.0421176e-7,0.017176539,0.01797265,0.63215995,0.25082785,0.07076044,0.00019287037],"about_ca_topic_score_codex":0.000037848666,"about_ca_topic_score_gemma":0.000027975462,"teacher_disagreement_score":0.66702926,"about_ca_system_score_codex":0.00007445316,"about_ca_system_score_gemma":0.00002401068,"threshold_uncertainty_score":0.259911},"labels":[],"label_agreement":null},{"id":"W4414078184","doi":"10.14778/3749646.3749706","title":"Robust Recursive Query Parallelism in Graph Database Management Systems","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","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 Waterloo","funders":"","keywords":"Computation; Graph; Variety (cybernetics); Node (physics); Query optimization; Graph database; Parallelism (grammar); Directed acyclic graph; Materialized view","score_opus":0.013331584993892084,"score_gpt":0.21476247281281138,"score_spread":0.2014308878189193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414078184","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":[0.4053853,0.011050508,0.24536397,0.020962568,0.015665768,0.013235135,0.0000876646,0.0010415727,0.28720754],"genre_scores_gemma":[0.98246294,0.00033832915,0.014713616,0.0003832549,0.000034603334,0.00028161652,0.0000016806829,0.0000099844265,0.0017739695],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986173,0.00002153205,0.00036041974,0.00040018986,0.0003042665,0.00029628366],"domain_scores_gemma":[0.9993316,0.000038839233,0.00017080976,0.00032487378,0.00009084031,0.000043029704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069655373,0.0001639627,0.00020823207,0.000313573,0.00010571764,0.000102627084,0.0015805523,0.000038995484,0.0000018813253],"category_scores_gemma":[0.00002430929,0.000119690805,0.00009965255,0.00104754,0.00007033838,0.00035831166,0.00084348634,0.00015696374,0.0000036646443],"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":[0.0000141056225,0.00012863688,0.00072560925,0.0002426274,0.000055939945,0.000003599368,0.00035953982,0.00043712027,0.0005267468,0.99374014,0.0021892264,0.0015766991],"study_design_scores_gemma":[0.005645423,0.0002565696,0.012125646,0.006317487,0.00020661342,0.00004752277,0.0069160094,0.02199205,0.054369234,0.8768902,0.013885639,0.0013476388],"about_ca_topic_score_codex":0.000058683494,"about_ca_topic_score_gemma":0.0000022546178,"teacher_disagreement_score":0.5770777,"about_ca_system_score_codex":0.000065733155,"about_ca_system_score_gemma":0.00001766249,"threshold_uncertainty_score":0.4880849},"labels":[],"label_agreement":null},{"id":"W4414266787","doi":"10.14778/3750601.3750638","title":"SQL:Trek Automated Index Design at Airbnb","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management 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":"Air Canada","funders":"","keywords":"Index (typography); Scalability; Index selection; False positive paradox; Selection (genetic algorithm); Database index; Compiler; Relational database","score_opus":0.011183793592322706,"score_gpt":0.22989208488466692,"score_spread":0.2187082912923442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414266787","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":[0.09391152,0.0014062906,0.49477482,0.04851554,0.007466677,0.008349009,0.000042305317,0.007322901,0.33821094],"genre_scores_gemma":[0.94988614,0.00005203732,0.035834104,0.00093905977,0.00004267291,0.00010579652,0.0000019063585,0.0000134043175,0.013124888],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874806,0.00000896589,0.00025617183,0.00034632138,0.00036168986,0.00027880847],"domain_scores_gemma":[0.99937415,0.000034744382,0.00016546533,0.00028317844,0.00010178428,0.00004068915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039438205,0.00015342745,0.00016317112,0.00014418873,0.0001651807,0.00016570257,0.001996736,0.000035887246,0.000011883264],"category_scores_gemma":[0.00004769432,0.000107206026,0.0000785027,0.0007392616,0.000056989233,0.00048799376,0.0020723739,0.00008212798,0.000027246571],"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":[0.000072010334,0.0005130765,0.010418103,0.00042493502,0.00040788445,0.000004529574,0.0010985931,0.00042074014,0.024659628,0.306394,0.5821592,0.07342727],"study_design_scores_gemma":[0.0025296554,0.00020708084,0.02239292,0.0004769096,0.000116302064,0.000010076249,0.00020324248,0.5147537,0.3541705,0.03187958,0.07259785,0.00066221436],"about_ca_topic_score_codex":0.00002275244,"about_ca_topic_score_gemma":9.749665e-7,"teacher_disagreement_score":0.8559746,"about_ca_system_score_codex":0.00011267105,"about_ca_system_score_gemma":0.000027929878,"threshold_uncertainty_score":0.4371735},"labels":[],"label_agreement":null},{"id":"W4414266922","doi":"10.14778/3750601.3750685","title":"Beyond Quacking: Deep Integration of Language Models and RAG into DuckDB","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Natural Language Processing Techniques","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; Polytechnique Montréal","funders":"","keywords":"Schema (genetic algorithms); Data integration; Data modeling; Relational database; Context (archaeology); SQL; Language model; Context model; Rapid prototyping","score_opus":0.008653647840289753,"score_gpt":0.2656501601318978,"score_spread":0.256996512291608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414266922","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":[0.44902977,0.01663191,0.5080837,0.006982036,0.00049778004,0.0014752208,0.0000036182034,0.0005973258,0.016698621],"genre_scores_gemma":[0.8198452,0.000030741434,0.17981929,0.00014469394,0.000010352769,0.000019350915,3.2567047e-7,0.000004554774,0.00012548927],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99909866,0.0000075021517,0.00026692534,0.00024560303,0.0002476933,0.00013359444],"domain_scores_gemma":[0.9993179,0.00003537786,0.00022505342,0.00017769993,0.00021857493,0.000025419673],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003184528,0.00012386366,0.00018168699,0.00015521617,0.00007159523,0.00007574625,0.00087148783,0.000056891877,0.000001167624],"category_scores_gemma":[0.000120236495,0.00008305855,0.00005393431,0.00044967883,0.000082747254,0.0004915234,0.00063166936,0.00013457636,1.9234803e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011584975,0.000045612855,0.00017178702,0.00021943141,0.000020518917,2.4208447e-7,0.0079922415,0.000005333914,0.3429043,0.5893523,0.00025177764,0.059024837],"study_design_scores_gemma":[0.00013312517,0.000029520017,0.000045696685,0.00018443727,0.000012278037,0.0000025157508,0.00038955142,0.009148172,0.6675795,0.3223919,0.000018394543,0.00006492574],"about_ca_topic_score_codex":0.00011767844,"about_ca_topic_score_gemma":0.000008585963,"teacher_disagreement_score":0.37081543,"about_ca_system_score_codex":0.000055237648,"about_ca_system_score_gemma":0.000028766857,"threshold_uncertainty_score":0.33870292},"labels":[],"label_agreement":null},{"id":"W4414267806","doi":"10.14778/3750601.3750656","title":"Analytics Are Heavy. The DBMS Is Busy. When Will My Mission-Critical Transaction Start Running?","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","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":"","keywords":"Scheduling (production processes); Preemption; Context switch; Database transaction; Transaction processing; Concurrency; Concurrency control; Analytics","score_opus":0.04457798281609549,"score_gpt":0.2847344295664768,"score_spread":0.24015644675038134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414267806","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":[0.43321192,0.0026027276,0.010914999,0.45215815,0.0066941488,0.0036915345,0.0000980874,0.00059681793,0.0900316],"genre_scores_gemma":[0.9930098,0.00006409595,0.00017258983,0.0048084324,0.000361132,0.000022763195,0.000003356205,0.0000179704,0.0015398255],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984167,0.0000026135042,0.00040422083,0.00034068988,0.0005075415,0.00032822124],"domain_scores_gemma":[0.9989257,0.00005276445,0.00024706172,0.00024404608,0.00051393564,0.000016496047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003896677,0.00022921566,0.00025010787,0.00015653185,0.00041738286,0.00034067666,0.0008537396,0.000085877124,0.00028305064],"category_scores_gemma":[0.00022975575,0.00013301153,0.0001591651,0.00072468363,0.00021001555,0.0009549458,0.0002838471,0.00025177677,0.000020890151],"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":[0.00086280267,0.0014727662,0.10724894,0.0056929793,0.0006136236,0.0000047580825,0.001699081,0.00022143869,0.017119179,0.19618914,0.6265594,0.042315904],"study_design_scores_gemma":[0.000932217,0.000034173412,0.012207489,0.0023863101,0.00096753467,0.000009532057,0.0060371775,0.01285294,0.062712215,0.07986072,0.82128465,0.0007150115],"about_ca_topic_score_codex":0.00031292802,"about_ca_topic_score_gemma":0.000013048247,"teacher_disagreement_score":0.5597979,"about_ca_system_score_codex":0.000055796878,"about_ca_system_score_gemma":0.000027170157,"threshold_uncertainty_score":0.5424053},"labels":[],"label_agreement":null},{"id":"W7080011846","doi":"10.14778/3749646.3749664","title":"Diva: Dynamic Range Filter for Var-Length Keys and Queries","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Geochemistry and Geologic Mapping","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","funders":"","keywords":"Range query (database); Range (aeronautics); Trie; Probabilistic logic; Filter (signal processing); Data structure; Query optimization; State (computer science)","score_opus":0.0073251686661112755,"score_gpt":0.21609304688765688,"score_spread":0.2087678782215456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7080011846","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":[0.5043289,0.0026165154,0.071957804,0.16572411,0.0022359556,0.004445532,0.000041005824,0.00058420905,0.24806595],"genre_scores_gemma":[0.9886851,0.00003270872,0.006341814,0.0002776552,0.000014994593,0.00009888989,3.9875533e-7,0.0000016267815,0.004546861],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99929917,0.0000029555242,0.00015912247,0.00024637955,0.00010706701,0.00018529031],"domain_scores_gemma":[0.9995603,0.000059120914,0.00009571524,0.00013057506,0.00012944077,0.000024822792],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021863442,0.00010607699,0.00013761321,0.000032741144,0.0001368056,0.000061386796,0.0005812445,0.000040213217,0.000005795538],"category_scores_gemma":[0.00015050238,0.00007264805,0.00006125913,0.00015092177,0.00007066453,0.00013468435,0.0005469829,0.00006592035,5.826354e-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":[0.00012098636,0.00031044235,0.024935195,0.0030983214,0.00030973632,0.0000010358876,0.0048986003,0.00005338544,0.13626063,0.7465197,0.028186074,0.05530594],"study_design_scores_gemma":[0.0026534135,0.00024144111,0.027731972,0.000645186,0.000099254175,0.000024516847,0.0008853814,0.027150854,0.48087147,0.33889666,0.120192744,0.0006070988],"about_ca_topic_score_codex":0.0000083745335,"about_ca_topic_score_gemma":0.0000011948566,"teacher_disagreement_score":0.48435614,"about_ca_system_score_codex":0.000022134163,"about_ca_system_score_gemma":0.000016591513,"threshold_uncertainty_score":0.29625016},"labels":[],"label_agreement":null},{"id":"W7118911591","doi":"10.14778/3773731.3773734","title":"Sampling-Based Predictive Database Buffer Management","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","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":"Workload; Buffer (optical fiber); Sample (material); Volume (thermodynamics); Set (abstract data type); Data access; Data set","score_opus":0.011922581415300254,"score_gpt":0.25314774292857595,"score_spread":0.2412251615132757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7118911591","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":[0.0047865445,0.00030339858,0.96735066,0.0020262368,0.00079849374,0.0011280747,0.0000731154,0.0001857108,0.023347763],"genre_scores_gemma":[0.7110049,0.000065362874,0.28490305,0.0011958326,0.00007192541,0.00043216985,0.000009944066,0.00001850089,0.0022982901],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986844,0.000007149065,0.000297428,0.00039975316,0.0003627006,0.0002485524],"domain_scores_gemma":[0.99915963,0.00004046215,0.00017789948,0.00042331463,0.00015319756,0.000045521654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002896395,0.00016379698,0.00018263081,0.00012493096,0.00016282723,0.000044767436,0.00092888577,0.00002629521,0.0000053483873],"category_scores_gemma":[0.000045500274,0.00011196778,0.000086812935,0.0005134356,0.00007722339,0.00041697195,0.0010616119,0.00010332683,0.000004631298],"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":[0.00003892135,0.00013674752,0.0011510135,0.00046344864,0.00008973541,9.1437784e-7,0.0001529076,0.0002049994,0.0057675145,0.9825922,0.005290797,0.0041107954],"study_design_scores_gemma":[0.0036859375,0.00028338924,0.009871834,0.003247009,0.00020357959,0.000009771141,0.0010907106,0.023124,0.5264743,0.024883224,0.40628225,0.00084402744],"about_ca_topic_score_codex":0.000028022368,"about_ca_topic_score_gemma":0.000002021155,"teacher_disagreement_score":0.95770895,"about_ca_system_score_codex":0.00009027891,"about_ca_system_score_gemma":0.0000374949,"threshold_uncertainty_score":0.45659137},"labels":[],"label_agreement":null},{"id":"W763614111","doi":"10.14778/2735479.2735491","title":"Mining revenue-maximizing bundling configuration","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Consumer Market Behavior and Pricing","field":"Business, Management and Accounting","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":"Simon Fraser University","funders":"Singapore Telecommunications Limited","keywords":"Bundle; Revenue; Perspective (graphical); Set (abstract data type); Heuristic; Computer science; Marketing; Data set; Business; Artificial intelligence","score_opus":0.04354427650522499,"score_gpt":0.240351671876838,"score_spread":0.19680739537161301,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W763614111","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":[0.9381849,0.00013360115,0.000030024305,0.0011229734,0.00062541175,0.00032552768,9.816347e-7,0.000066894216,0.05950969],"genre_scores_gemma":[0.99845237,0.00000418566,0.00035928006,0.00031203206,0.00038091507,0.000023104372,0.0000018391056,0.000018404633,0.0004478745],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989384,0.0000024953226,0.0002984133,0.00019021008,0.00035508996,0.00021539083],"domain_scores_gemma":[0.9991546,0.000022253085,0.00038062304,0.000097306714,0.00032863897,0.00001655272],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006889699,0.00013727199,0.00016867644,0.00012133544,0.0001440236,0.00018068276,0.0003039135,0.00003863181,0.00003207516],"category_scores_gemma":[0.0003071633,0.00010696226,0.00008032011,0.00035023762,0.00003956206,0.00065841764,0.00024226552,0.00010433043,0.00002088209],"study_design_candidate":"observational","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":[0.00033303516,0.0003134349,0.623653,0.0010369436,0.00014450138,0.000004115848,0.0033018983,0.00015037123,0.21384212,0.028440496,0.040708322,0.08807173],"study_design_scores_gemma":[0.010276225,0.0001532881,0.12909976,0.0037454157,0.0020739825,0.00007133716,0.021469299,0.0093693,0.23113137,0.030034916,0.55953246,0.0030426306],"about_ca_topic_score_codex":0.00032075864,"about_ca_topic_score_gemma":0.000015017273,"teacher_disagreement_score":0.51882416,"about_ca_system_score_codex":0.0000440279,"about_ca_system_score_gemma":0.000020667912,"threshold_uncertainty_score":0.43617943},"labels":[],"label_agreement":null},{"id":"W79208629","doi":"10.14778/2732269.2732275","title":"Computing k-regret minimizing sets","year":2014,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":73,"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 Victoria","funders":"","keywords":"Regret; Dimension (graph theory); Relaxation (psychology); Set (abstract data type); Greedy algorithm; Linear programming relaxation; Dynamic programming; Linear programming; Duality (order theory); Mathematics; Combinatorics; Computer science; Mathematical optimization; Algorithm; Statistics","score_opus":0.011085699081155623,"score_gpt":0.21721503497013323,"score_spread":0.2061293358889776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W79208629","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":[0.45378727,0.00034630904,0.22654872,0.024933774,0.005233695,0.002512747,0.000014398966,0.0013056644,0.28531742],"genre_scores_gemma":[0.93735296,0.000006539087,0.061782744,0.00041853587,0.00008893707,0.0000061442947,7.6645745e-7,0.00000844547,0.00033490823],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988177,0.0000073209817,0.00023412456,0.00029790046,0.00037572687,0.0002672703],"domain_scores_gemma":[0.999373,0.00003741206,0.00022471715,0.00023869042,0.000077916644,0.00004827343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000567185,0.00012956068,0.00015346892,0.000069609654,0.00014169746,0.00018763503,0.0018037357,0.00002261317,0.0000039544416],"category_scores_gemma":[0.00006562323,0.000089213696,0.00007868458,0.00030710903,0.00004220296,0.00046237308,0.0014521478,0.00008981234,0.0000157704],"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":[0.00000790178,0.00019155622,0.0066395523,0.00026583177,0.00010160838,7.8856993e-7,0.0019584685,0.00006957029,0.009921095,0.5897314,0.030256039,0.3608562],"study_design_scores_gemma":[0.002958069,0.0004134999,0.017951425,0.0008355926,0.000111503796,0.00003574712,0.0006513271,0.59521705,0.20629328,0.048918616,0.12536195,0.0012519498],"about_ca_topic_score_codex":0.0000129950595,"about_ca_topic_score_gemma":3.7176676e-7,"teacher_disagreement_score":0.59514743,"about_ca_system_score_codex":0.000025796258,"about_ca_system_score_gemma":0.000006999463,"threshold_uncertainty_score":0.36380288},"labels":[],"label_agreement":null},{"id":"W808055529","doi":"10.14778/2850578.2850581","title":"From competition to complementarity","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":216,"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":"Complementarity (molecular biology); Computer science; Maximization; Competition (biology); Mathematical optimization; Cellular automaton; Set (abstract data type); Margin (machine learning); Theoretical computer science; Artificial intelligence; Machine learning; Mathematics","score_opus":0.027410872042148204,"score_gpt":0.27390038399454764,"score_spread":0.24648951195239943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W808055529","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":[0.96108496,0.000013753962,0.0017617239,0.0016528209,0.000115124276,0.0004903999,0.000057022713,0.000057106743,0.034767076],"genre_scores_gemma":[0.9941154,2.7113654e-7,0.0053474824,0.00011092619,0.0002593559,0.000045955225,0.000014921343,0.0000078183175,0.000097886885],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99920255,0.0000057313523,0.0002135987,0.00016735062,0.00026551235,0.00014527682],"domain_scores_gemma":[0.9994872,0.000013350828,0.00013629704,0.00011680075,0.00016044168,0.00008586152],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016590809,0.00010218187,0.0001680766,0.000036660902,0.000054943568,0.00003417901,0.00035000127,0.000010028393,0.00024822203],"category_scores_gemma":[0.0000048623638,0.00007728636,0.000094671406,0.000188131,0.000026641672,0.0000660825,0.00032751824,0.000070869304,0.00001701224],"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":[0.000082035294,0.0006288564,0.40733987,0.00001583208,0.00039453423,9.8411505e-8,0.0031097503,0.00010189835,0.04268632,0.3564099,0.17943192,0.0097989645],"study_design_scores_gemma":[0.0013772808,0.00020688679,0.018310364,0.00018150418,0.00024369251,4.5410897e-7,0.0041543255,0.000972848,0.39978912,0.4613099,0.11296378,0.0004898339],"about_ca_topic_score_codex":0.002687273,"about_ca_topic_score_gemma":0.000019087553,"teacher_disagreement_score":0.3890295,"about_ca_system_score_codex":0.00006660913,"about_ca_system_score_gemma":0.000013222881,"threshold_uncertainty_score":0.4062371},"labels":[],"label_agreement":null}]}