{"meta":{"query_hash":"fca9349e28ed","filters":{"venue":"ACM Transactions on Information Systems"},"cohort_total":57,"direct_labels_cover":0,"predictions_cover":57,"exported":57,"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/fca9349e28ed","api":"https://metacan.xera.ac/api/v1/cohort?venue=ACM+Transactions+on+Information+Systems"},"results":[{"id":"W1969806156","doi":"10.1145/1055709.1055712","title":"A methodology for analyzing SAGE libraries for cancer profiling","year":2005,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","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":"Genome British Columbia; University of British Columbia; University of Alberta","funders":"","keywords":"Serial analysis of gene expression; Breast cancer; Computer science; Prostate cancer; Computational biology; SAGE; Cancer; Ovarian cancer; Gene expression profiling; Preprocessor; Bioinformatics; Gene expression; Biology; Artificial intelligence; Gene; Genetics","score_opus":0.06054475317927263,"score_gpt":0.33295577610078814,"score_spread":0.27241102292151553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969806156","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":[0.0057217227,0.0004000899,0.9916008,0.0006481723,0.00048610574,0.00079963665,0.00017121555,0.000033069467,0.00013917073],"genre_scores_gemma":[0.93220896,0.00019631363,0.06170036,0.00055076345,0.0003982605,0.0035209279,0.00031874306,0.000019259214,0.0010864171],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992563,0.000044959696,0.00033207072,0.00014088972,0.00007435083,0.00015140117],"domain_scores_gemma":[0.99931335,0.000063359395,0.00015600186,0.00028732434,0.00013494959,0.00004503393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002750042,0.000102848186,0.00012148377,0.000119575816,0.00019568033,0.00007007463,0.000151824,0.0001341716,0.000010432035],"category_scores_gemma":[0.00006761723,0.00009568549,0.00009909677,0.00009587473,0.000019200881,0.00005744468,0.0000035627404,0.000047922145,0.0000052251194],"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":[0.0010015459,0.000079548045,0.00017165608,0.000507805,0.00028102653,2.328837e-8,0.0014390398,0.0699016,0.27528182,0.0032918262,0.0043921378,0.64365196],"study_design_scores_gemma":[0.0008727937,0.00013989693,0.00003601955,0.00003515014,0.00003376618,0.000002375331,0.0010998003,0.004170171,0.37139735,0.000060336926,0.6219829,0.00016945426],"about_ca_topic_score_codex":0.000007361518,"about_ca_topic_score_gemma":0.000008071019,"teacher_disagreement_score":0.92990047,"about_ca_system_score_codex":0.000029400117,"about_ca_system_score_gemma":0.00008880095,"threshold_uncertainty_score":0.3901941},"labels":[],"label_agreement":null},{"id":"W1999003664","doi":"10.1145/2735629","title":"A General SIMD-Based Approach to Accelerating Compression Algorithms","year":2015,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":41,"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 de Montréal; Université du Québec","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"SIMD; Computer science; Data compression; Decoding methods; Algorithm; Compression ratio; Compression (physics); Parallel computing; Encoding (memory); Group (periodic table); Artificial intelligence","score_opus":0.06561336432163029,"score_gpt":0.2778084545504484,"score_spread":0.2121950902288181,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999003664","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":[0.0006631662,0.000016934488,0.99247515,0.00019873833,0.0012099432,0.0005693772,0.000043665925,0.00037677924,0.0044462266],"genre_scores_gemma":[0.51319385,0.0000017453244,0.4851532,0.0009149197,0.0001414705,0.0003082197,0.00010759586,0.000013739391,0.00016524651],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980195,0.00010740572,0.00057124405,0.00026644598,0.0007458626,0.00028954705],"domain_scores_gemma":[0.99799806,0.0000699281,0.00017665476,0.0011093827,0.00030797633,0.0003379888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047459127,0.00021031986,0.00022026403,0.0003615103,0.00034919247,0.0007785773,0.001137029,0.00010951166,0.000003337096],"category_scores_gemma":[0.000035020563,0.00017618896,0.00006644811,0.0006230705,0.000015423186,0.0032520478,0.00004700272,0.00020645827,0.000277585],"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":[0.000031141273,0.00016351661,0.000011071004,0.000052882155,0.000017883553,7.6335783e-7,0.0022851587,0.87520474,0.00008669882,0.00266345,0.007039732,0.112442955],"study_design_scores_gemma":[0.0007620878,0.00014076773,0.000033606215,0.000065371445,0.0000041890694,0.000015527718,0.00035188548,0.94955826,0.00067890255,0.000046820598,0.048103753,0.0002388087],"about_ca_topic_score_codex":0.000217704,"about_ca_topic_score_gemma":8.806089e-7,"teacher_disagreement_score":0.5125307,"about_ca_system_score_codex":0.00012898297,"about_ca_system_score_gemma":0.0001362859,"threshold_uncertainty_score":0.75078386},"labels":[],"label_agreement":null},{"id":"W2035512259","doi":"10.1145/333135.333137","title":"Shortest-substring retrieval and ranking","year":2000,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Algorithms and Data Compression","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 Waterloo; University of Toronto","funders":"","keywords":"Computer science; Ranking (information retrieval); Information retrieval; Relevance (law); Boolean conjunctive query; Substring; Matching (statistics); Standard Boolean model; Phrase; Learning to rank; Simple (philosophy); Theoretical computer science; Data mining; Boolean expression; Algorithm; Boolean function; And-inverter graph; Search engine; Data structure; Artificial intelligence; Web search query; Mathematics; Statistics; Web query classification","score_opus":0.013760319804854381,"score_gpt":0.2269255291116297,"score_spread":0.21316520930677532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035512259","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":[0.013002754,0.00006021274,0.9836421,0.00012722964,0.00040767787,0.00019252986,0.000015082214,0.00021807947,0.0023343393],"genre_scores_gemma":[0.9920301,0.000097326636,0.007531668,0.00011683371,0.00003437559,0.000013734998,0.000009933687,0.0000040376362,0.00016198803],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990626,0.000029932677,0.0003299717,0.00013166663,0.00029437328,0.00015148705],"domain_scores_gemma":[0.9991835,0.00007796292,0.00006443737,0.00054764457,0.00005208332,0.00007438549],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022744467,0.00010287245,0.00011158032,0.00014333999,0.00030998487,0.0004435837,0.00040549645,0.00006245962,0.000043636253],"category_scores_gemma":[0.000008642032,0.00009163724,0.000030430127,0.0002940403,0.000016043248,0.0035181344,0.000009782622,0.00013411762,0.00017339402],"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":[0.000043253345,0.000025216608,0.00003579896,0.00003661267,0.000021279813,0.000001843004,0.001730597,0.016313493,0.00003932846,0.0016224592,0.0001940818,0.97993606],"study_design_scores_gemma":[0.0019754178,0.00023771152,0.003681121,0.0003806465,0.000024776495,0.00031432242,0.0005997243,0.77433115,0.0015361984,0.00048286526,0.21570343,0.0007326474],"about_ca_topic_score_codex":0.00004718519,"about_ca_topic_score_gemma":6.068114e-7,"teacher_disagreement_score":0.9792034,"about_ca_system_score_codex":0.000030275138,"about_ca_system_score_gemma":0.000020941407,"threshold_uncertainty_score":0.4277488},"labels":[],"label_agreement":null},{"id":"W2046353967","doi":"10.1145/1740592.1740594","title":"Exploiting query logs for cross-lingual query suggestions","year":2010,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Topic Modeling","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":"Université de Montréal","funders":"Microsoft Research Asia; Chinese University of Hong Kong; Innovation and Technology Commission","keywords":"Computer science; Cross-language information retrieval; Query expansion; Query language; RDF query language; Query optimization; Information retrieval; Web query classification; Sargable; Natural language processing; Relevance (law); Web search query; Discriminative model; Query by Example; Artificial intelligence; Search engine","score_opus":0.027786355921336915,"score_gpt":0.2897494147459037,"score_spread":0.2619630588245668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046353967","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":[0.03469272,0.000008073975,0.9590926,0.00041874746,0.0038447187,0.0005231868,0.000043335855,0.00047529725,0.000901299],"genre_scores_gemma":[0.94981205,0.0000035805267,0.049170516,0.00021042359,0.00017839123,0.00036711304,0.000020335126,0.000010597647,0.00022701181],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998427,0.000030950257,0.0007040183,0.00021430082,0.0003209028,0.00030286217],"domain_scores_gemma":[0.99797195,0.00035633863,0.00021791364,0.000983466,0.00035950917,0.00011083877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000639489,0.00016366683,0.00017073037,0.0003110559,0.0005785294,0.0007132674,0.000783426,0.0001701698,0.0000098927485],"category_scores_gemma":[0.00019662296,0.00016522063,0.000119983924,0.00026597964,0.000036989808,0.0035666288,0.000014954974,0.0003625697,0.00014641478],"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":[0.000055030236,0.00021009242,0.00064419553,0.00061076786,0.00013190127,0.000002873632,0.015197644,0.35916552,0.0022671786,0.24079235,0.0005792634,0.3803432],"study_design_scores_gemma":[0.002261768,0.00020723487,0.00065187557,0.00020868996,0.00003375232,0.00022505764,0.0024885435,0.88835454,0.009206612,0.0031745739,0.09212403,0.0010633316],"about_ca_topic_score_codex":0.00014364603,"about_ca_topic_score_gemma":0.000023511535,"teacher_disagreement_score":0.9151193,"about_ca_system_score_codex":0.00006082665,"about_ca_system_score_gemma":0.00013623569,"threshold_uncertainty_score":0.6878054},"labels":[],"label_agreement":null},{"id":"W2052842594","doi":"10.1145/2590988","title":"Modeling Term Associations for Probabilistic Information Retrieval","year":2014,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; International Business Machines Corporation","keywords":"Term Discrimination; Computer science; Term (time); Bigram; Divergence-from-randomness model; Probabilistic logic; Ranking (information retrieval); Query expansion; Information retrieval; Data mining; Artificial intelligence; Web search query; Search engine; Concept search; Trigram","score_opus":0.03054072446624775,"score_gpt":0.26785701334439205,"score_spread":0.2373162888781443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052842594","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":[0.0032040454,0.0000024625615,0.9919385,0.00047325887,0.0011337996,0.0012870358,0.00014777466,0.00041740976,0.0013957367],"genre_scores_gemma":[0.98802984,0.0000050467293,0.010775107,0.00047529885,0.000060854232,0.00029387287,0.00024470926,0.00000764164,0.00010765711],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99758106,0.000078757264,0.0011015544,0.0001327279,0.0007431466,0.00036273096],"domain_scores_gemma":[0.9975281,0.0002702194,0.00031387695,0.00074885617,0.0009936354,0.00014533743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012193243,0.00019953506,0.00023203583,0.00054814434,0.00069109275,0.001033953,0.0008097646,0.00017213897,0.000008193233],"category_scores_gemma":[0.0005072763,0.0001861337,0.00015079201,0.0006404936,0.000022627155,0.010589967,0.000017300057,0.00022694602,0.00045954864],"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":[0.00012178623,0.000119692166,0.00003975174,0.00046871518,0.000074531636,9.8682875e-8,0.008178724,0.71061933,0.00003578198,0.15239625,0.0005112718,0.12743406],"study_design_scores_gemma":[0.0009147583,0.00019053118,0.00015769358,0.00003878732,0.000017224796,0.0000070815145,0.0002538302,0.98529744,0.00016166133,0.0007059237,0.011997026,0.00025804882],"about_ca_topic_score_codex":0.000033486172,"about_ca_topic_score_gemma":0.000001903244,"teacher_disagreement_score":0.9848258,"about_ca_system_score_codex":0.00026003786,"about_ca_system_score_gemma":0.00014029557,"threshold_uncertainty_score":0.9970433},"labels":[],"label_agreement":null},{"id":"W2058737869","doi":"10.1145/1247715.1247717","title":"Online supervised spam filter evaluation","year":2007,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":117,"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; Filter (signal processing); Set (abstract data type); Software; Receiver operating characteristic; Confidence interval; Information retrieval; Data mining; Machine learning; Artificial intelligence; Statistics; Mathematics; Operating system","score_opus":0.03922481280749248,"score_gpt":0.2785531126448064,"score_spread":0.23932829983731393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058737869","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":[0.017459545,0.000021027561,0.97636837,0.0003436571,0.0026281804,0.00045380412,0.000015952863,0.000324894,0.0023846],"genre_scores_gemma":[0.9929525,0.0000067723604,0.0064195786,0.00031937155,0.00010757362,0.000045270088,0.000044886787,0.0000060980456,0.00009795129],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983114,0.000073814386,0.00053171173,0.00015406123,0.0007096652,0.00021932731],"domain_scores_gemma":[0.9985028,0.0001449955,0.00014689473,0.00076327956,0.0003499627,0.000092050446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014233451,0.00013404565,0.00012017483,0.00043958428,0.00025254104,0.00032422814,0.0005265882,0.00011687289,0.000050344814],"category_scores_gemma":[0.000060932478,0.00012716647,0.00007486576,0.00061472325,0.000014232221,0.0031878264,0.000007364036,0.00018523142,0.00043067703],"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":[0.00007374081,0.00026002867,0.00015870907,0.00009997499,0.00007899866,0.000001634502,0.0067622415,0.05287727,0.00042587213,0.0034385577,0.001183537,0.93463945],"study_design_scores_gemma":[0.0024320732,0.00041690347,0.007154703,0.00014485909,0.00005299967,0.00011207339,0.0020089594,0.8989283,0.006475163,0.0006632661,0.08093654,0.00067415665],"about_ca_topic_score_codex":0.00012388424,"about_ca_topic_score_gemma":0.000031212636,"teacher_disagreement_score":0.97549295,"about_ca_system_score_codex":0.0001704604,"about_ca_system_score_gemma":0.000058695514,"threshold_uncertainty_score":0.5535626},"labels":[],"label_agreement":null},{"id":"W2063529879","doi":"10.1145/358108.358114","title":"Beyond intratransaction association analysis","year":2000,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":153,"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":"Badan Riset dan Inovasi Nasional; Helsingin Yliopisto","keywords":"Association rule learning; Apriori algorithm; Database transaction; Computer science; Association (psychology); Transaction data; Affinity analysis; Data mining; Data science; Psychology; Database","score_opus":0.007761500766622136,"score_gpt":0.22556361950399387,"score_spread":0.21780211873737174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063529879","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":[0.0015007339,0.000010560898,0.98804486,0.0008291939,0.0003739925,0.00023863722,0.00015510058,0.00036351517,0.008483386],"genre_scores_gemma":[0.96814173,0.00009958945,0.028510453,0.0005184757,0.000071976436,0.0003180427,0.00023308664,0.000009193347,0.002097438],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984878,0.00006256729,0.0005343498,0.00020282112,0.0004873721,0.00022509458],"domain_scores_gemma":[0.99853873,0.000121660145,0.00018499605,0.00090714113,0.00015250593,0.00009493841],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00044545846,0.00014241681,0.00019168301,0.00045098594,0.0003719051,0.0006408253,0.0006646636,0.00012170147,0.00022739782],"category_scores_gemma":[0.000011826205,0.00014243719,0.00014295486,0.0019708816,0.000011363486,0.0036280658,0.000003173706,0.00018603315,0.0014623494],"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":[0.000008188953,0.000088817236,0.000059677008,0.00001586168,0.00043040194,3.1112816e-7,0.0013480736,0.078483604,0.000012349273,0.003929523,0.0012321192,0.9143911],"study_design_scores_gemma":[0.00083048415,0.00013870944,0.002892619,0.00002539555,0.00039002832,0.000018420966,0.00046111434,0.7025983,0.00055506214,0.00060145,0.29088488,0.0006035568],"about_ca_topic_score_codex":0.00020368795,"about_ca_topic_score_gemma":0.000013786857,"teacher_disagreement_score":0.966641,"about_ca_system_score_codex":0.00020994928,"about_ca_system_score_gemma":0.000040362615,"threshold_uncertainty_score":0.99931514},"labels":[],"label_agreement":null},{"id":"W2067662418","doi":"10.1145/1344411.1344415","title":"Locality-Based pruning methods for web search","year":2008,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Algorithms and Data Compression","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 Alberta","funders":"Fundação para a Ciência e a Tecnologia; Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Pruning; Computer science; Locality; Search engine; Simple (philosophy); Reduction (mathematics); Data mining; Artificial intelligence; Phrase; Information retrieval; Machine learning; Mathematics","score_opus":0.0624142167311531,"score_gpt":0.34392714943000924,"score_spread":0.28151293269885613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067662418","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":[0.00025372676,0.000024959641,0.99752486,0.00027751326,0.0007356094,0.0005037675,0.000046749316,0.00025431745,0.0003784918],"genre_scores_gemma":[0.29526123,0.000010087243,0.7039942,0.00030791055,0.000043830194,0.00023481646,0.000045061974,0.00000770541,0.00009510431],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987373,0.00014077911,0.0004333644,0.00016008085,0.0003066157,0.00022189025],"domain_scores_gemma":[0.9983115,0.00038880296,0.000108199056,0.00085072836,0.0002421964,0.000098535354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007803608,0.0001231237,0.00016140612,0.00027580242,0.0006134291,0.00019523656,0.00073245994,0.000085578715,0.000007285078],"category_scores_gemma":[0.000035299738,0.0001077008,0.000085031854,0.0004133723,0.00003292536,0.0022698243,0.000014371426,0.00015077746,0.00008583968],"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":[0.000076728014,0.00015824866,0.000043306387,0.0003765487,0.00006235423,0.0000017608288,0.003292443,0.25980332,0.00045042066,0.009173029,0.0022568083,0.72430503],"study_design_scores_gemma":[0.0005823182,0.00009048778,0.000058864473,0.00004647573,0.000003665603,0.00002187394,0.00013586746,0.8781237,0.0018550297,0.000046990386,0.11889699,0.00013771768],"about_ca_topic_score_codex":0.00005921684,"about_ca_topic_score_gemma":5.1698026e-7,"teacher_disagreement_score":0.7241673,"about_ca_system_score_codex":0.00007026043,"about_ca_system_score_gemma":0.00018607917,"threshold_uncertainty_score":0.4718063},"labels":[],"label_agreement":null},{"id":"W2069870183","doi":"10.1145/582415.582418","title":"Cumulated gain-based evaluation of IR techniques","year":2002,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":4634,"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":"Tampereen Yliopisto; McGill University","keywords":"Relevance (law); Computer science; Information retrieval; Precision and recall; Recall; Data mining","score_opus":0.05912903173965583,"score_gpt":0.31352136319328217,"score_spread":0.25439233145362633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069870183","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":[0.005777515,0.000017299508,0.9864181,0.00027726206,0.00036644103,0.00086381694,0.00002742869,0.00034075577,0.0059113745],"genre_scores_gemma":[0.9948713,0.0000070831306,0.004692726,0.00015798902,0.000010190476,0.0001602443,0.00001790574,0.000004247733,0.000078280376],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99758935,0.000138947,0.0007376975,0.00010105169,0.0012512616,0.00018170847],"domain_scores_gemma":[0.99769807,0.00009719337,0.00029115393,0.00073181064,0.0011076443,0.00007410062],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011189589,0.00013030731,0.00015988553,0.00060242694,0.00017958162,0.00017640341,0.00058538135,0.00011232541,0.00014736608],"category_scores_gemma":[0.0000715113,0.00011702866,0.000091578106,0.0008259898,0.00003252311,0.0026726874,0.0000066316734,0.00015072021,0.00034558447],"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":[0.000028689403,0.0002578782,0.000050563736,0.00020961695,0.000045981957,5.160217e-7,0.0043130787,0.15229763,0.00036859006,0.0052124904,0.0009082671,0.8363067],"study_design_scores_gemma":[0.0006689828,0.00015367227,0.00016077746,0.000068224945,0.00001941634,0.0000067983838,0.00016775768,0.97221327,0.020393409,0.000049263246,0.00593581,0.00016263181],"about_ca_topic_score_codex":0.00004254759,"about_ca_topic_score_gemma":7.4114905e-7,"teacher_disagreement_score":0.98909384,"about_ca_system_score_codex":0.00014916518,"about_ca_system_score_gemma":0.00007812011,"threshold_uncertainty_score":0.47722903},"labels":[],"label_agreement":null},{"id":"W2070641109","doi":"10.1145/1777432.1777433","title":"Dynamic lightweight text compression","year":2010,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":32,"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":"Agencia Española de Cooperación Internacional para el Desarrollo; Fondo Nacional de Desarrollo Científico y Tecnológico; Xunta de Galicia; Mountain Equipment Co-operative","keywords":"Computer science; Uncompressed video; Communication source; Novelty; Lossless compression; Gas compressor; Compression (physics); Compression ratio; Natural language; Data compression; Semantic compression; Artificial intelligence; Telecommunications; Video processing","score_opus":0.008293689010632505,"score_gpt":0.23601764425665225,"score_spread":0.22772395524601974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070641109","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":[0.0023675654,0.000018176332,0.98997307,0.00040765476,0.003592109,0.00028413965,0.00004002959,0.00037819045,0.002939054],"genre_scores_gemma":[0.9606893,0.000019532441,0.03859787,0.00018871712,0.000039857474,0.00007934728,0.000044304423,0.000008025066,0.00033301723],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864525,0.000039799783,0.00046245303,0.00018876027,0.00044649933,0.00021723758],"domain_scores_gemma":[0.99806255,0.000104636514,0.00017997045,0.001377168,0.0001446913,0.00013097494],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00022271462,0.0001655342,0.00015841628,0.00028726412,0.00043188766,0.00049722946,0.0011812508,0.0001421968,0.000057325116],"category_scores_gemma":[0.000016247262,0.00013105391,0.00006910115,0.00035039015,0.000028018449,0.004170322,0.000034178876,0.0003917186,0.001052057],"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":[0.000048636557,0.00032727682,0.000049035472,0.0001766769,0.00007211687,0.000005701939,0.0033890104,0.012439471,0.0053064153,0.04003722,0.0071390076,0.9310094],"study_design_scores_gemma":[0.0006881784,0.00008888029,0.0006818399,0.00010201062,0.00000767088,0.0000841779,0.0001494084,0.5936887,0.0018893295,0.0003872958,0.4018727,0.00035979733],"about_ca_topic_score_codex":0.000054802946,"about_ca_topic_score_gemma":0.000006554284,"teacher_disagreement_score":0.95832175,"about_ca_system_score_codex":0.00003397757,"about_ca_system_score_gemma":0.000046869394,"threshold_uncertainty_score":0.99972576},"labels":[],"label_agreement":null},{"id":"W2089201173","doi":"10.1145/2629530","title":"Trust Prediction via Belief Propagation","year":2014,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Advanced Graph Neural Networks","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 Ottawa","funders":"Ministry of Science and Technology of the People's Republic of China; National Natural Science Foundation of China","keywords":"Computer science; Belief propagation; Graphical model; Factor graph; Probabilistic logic; Inference; Exploit; Machine learning; Expectation propagation; Artificial intelligence; Solver; Propagation of uncertainty; Theoretical computer science; Approximate inference; Data mining; Algorithm","score_opus":0.00904383903233889,"score_gpt":0.21179865925749425,"score_spread":0.20275482022515537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089201173","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":[0.0007944592,0.000007790103,0.9937553,0.00038954846,0.0017985585,0.00049052294,0.000009673161,0.0006374403,0.0021167358],"genre_scores_gemma":[0.9905234,0.000009841814,0.008697668,0.00029639827,0.000121695644,0.00018435883,0.000024980052,0.00000862634,0.00013305547],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99849135,0.00009147198,0.00055550324,0.00019219599,0.00044180674,0.00022769212],"domain_scores_gemma":[0.99853307,0.00008229535,0.00023747308,0.00086931343,0.000181363,0.000096488184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032247562,0.00016328777,0.00014807277,0.00031366522,0.00035180865,0.00024737883,0.00058084907,0.00011410059,0.000007352907],"category_scores_gemma":[0.000030342697,0.0001514375,0.00007112646,0.00065373024,0.000027876347,0.00463226,0.000009643823,0.0002178332,0.00032875768],"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":[0.000027773101,0.000068968286,0.00007760137,0.00009356939,0.000034405835,3.6573562e-7,0.0011489484,0.433894,0.00018717571,0.018171003,0.00061987614,0.5456763],"study_design_scores_gemma":[0.00061403133,0.00027044633,0.0009785829,0.000063120126,0.000008843835,0.000049546805,0.000071403934,0.9511583,0.0010564984,0.0012721742,0.044213466,0.00024359282],"about_ca_topic_score_codex":0.000020397125,"about_ca_topic_score_gemma":0.0000013423356,"teacher_disagreement_score":0.9897289,"about_ca_system_score_codex":0.00008472865,"about_ca_system_score_gemma":0.000019310317,"threshold_uncertainty_score":0.6175442},"labels":[],"label_agreement":null},{"id":"W2142905080","doi":"10.1145/2094072.2094073","title":"Word-based self-indexes for natural language text","year":2012,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":79,"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":"Fondo Nacional de Desarrollo Científico y Tecnológico; Xunta de Galicia; Ministerio de Ciencia e Innovación","keywords":"Computer science; Word (group theory); Phrase; Search engine indexing; Inverted index; Natural language processing; Space (punctuation); Artificial intelligence; Natural language; Index (typography); Sequence (biology); Full text search; Information retrieval; Search engine; Linguistics; World Wide Web","score_opus":0.01209488053201561,"score_gpt":0.2518274829218977,"score_spread":0.23973260238988212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142905080","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":[0.0013226697,0.00014012035,0.99516165,0.00016769409,0.002077803,0.0004337243,0.000058054364,0.00037025698,0.0002680534],"genre_scores_gemma":[0.9378502,0.0000030406502,0.061443478,0.00026761278,0.00010003966,0.00017668231,0.000050666513,0.0000060221396,0.00010230236],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990122,0.000033849712,0.00031394904,0.00010077145,0.00027974937,0.00025951295],"domain_scores_gemma":[0.9988409,0.00017471325,0.00013169936,0.00066119083,0.000096296775,0.0000951454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028565276,0.00012657078,0.00012336596,0.00019987574,0.00027362272,0.00025834882,0.00056159665,0.00007163437,0.000008799624],"category_scores_gemma":[0.00001826845,0.000103231774,0.000076365286,0.00025041235,0.000009674152,0.003988056,0.000010167689,0.00012036559,0.00019274693],"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":[0.000105991996,0.00050104,0.00020539966,0.00060704263,0.00014854717,9.011568e-7,0.018543754,0.02220205,0.00025547916,0.0121897,0.008516783,0.9367233],"study_design_scores_gemma":[0.0016931993,0.00011824174,0.0007294498,0.00013025524,0.00002426454,0.00002796518,0.001219958,0.7470699,0.0032395157,0.000032978725,0.24521342,0.0005008821],"about_ca_topic_score_codex":0.00003905144,"about_ca_topic_score_gemma":0.0000013440897,"teacher_disagreement_score":0.9365275,"about_ca_system_score_codex":0.00006745898,"about_ca_system_score_gemma":0.000040981457,"threshold_uncertainty_score":0.42096695},"labels":[],"label_agreement":null},{"id":"W2168625136","doi":"10.1145/944012.944013","title":"Measuring praise and criticism","year":2003,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":1509,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"National Aeronautics and Space Administration","keywords":"Computer science; Praise; Natural language processing; Artificial intelligence; Orientation (vector space); Pointwise mutual information; Noun; Set (abstract data type); Word (group theory); Latent semantic analysis; Criticism; Semantics (computer science); Linguistics; Psychology; Mutual information; Mathematics","score_opus":0.03905183252988257,"score_gpt":0.24862510286070227,"score_spread":0.2095732703308197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168625136","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":[0.0024529288,0.0000670041,0.9900006,0.00019482589,0.0005411352,0.000114285234,0.000001728287,0.00009103302,0.0065364796],"genre_scores_gemma":[0.9921177,0.000018684315,0.0074343123,0.0001560159,0.000009881243,0.000027937129,0.0000013362715,0.0000026855425,0.00023146613],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99916047,0.0000536994,0.0003052591,0.0001013452,0.0002536721,0.00012557727],"domain_scores_gemma":[0.9993221,0.0000765637,0.00007773475,0.00037132914,0.0000877827,0.00006448733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003450503,0.00008236932,0.000103888735,0.00023414068,0.00022402374,0.0003896186,0.0002029239,0.000038277194,0.000015817997],"category_scores_gemma":[0.00003592147,0.00007662295,0.00004157337,0.0002694822,0.000012084301,0.0019036332,0.000003890769,0.00007352517,0.00012747817],"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":[0.000022907534,0.00026297438,0.0013483068,0.000526619,0.0004822649,0.0000059158783,0.025074476,0.04123302,0.00047189463,0.66554254,0.0021079727,0.2629211],"study_design_scores_gemma":[0.003784993,0.00033676205,0.0020189704,0.00049517886,0.0001052115,0.00030774449,0.009785664,0.27904788,0.014391582,0.0018831994,0.6862599,0.0015828809],"about_ca_topic_score_codex":0.000011671187,"about_ca_topic_score_gemma":8.3632915e-7,"teacher_disagreement_score":0.98966473,"about_ca_system_score_codex":0.000022520548,"about_ca_system_score_gemma":0.000020279724,"threshold_uncertainty_score":0.3757101},"labels":[],"label_agreement":null},{"id":"W2271008577","doi":"10.1145/2838731","title":"A Tensor-Based Information Framework for Predicting the Stock Market","year":2016,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":98,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"National Natural Science Foundation of China; Fundamental Research Funds for the Central Universities; National Science Foundation","keywords":"Computer science; Stock market; Stock (firearms); Tensor (intrinsic definition); Curse of dimensionality; Data mining; Dimensionality reduction; Artificial intelligence; Econometrics; Machine learning; Economics; Mathematics; Engineering; Geography","score_opus":0.08894259654104707,"score_gpt":0.365239191310019,"score_spread":0.2762965947689719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2271008577","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":[0.0022424606,0.000008919202,0.9860278,0.0029021788,0.002489877,0.0017196918,0.00037116135,0.00023962611,0.0039982903],"genre_scores_gemma":[0.935864,0.00000503238,0.060360376,0.0010572022,0.00018194332,0.0015100838,0.000012147059,0.000021981976,0.0009872629],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953747,0.0005310159,0.0017823724,0.00021743856,0.001691725,0.0004027485],"domain_scores_gemma":[0.97421634,0.021881912,0.0010524642,0.0015573514,0.0011621295,0.0001298184],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008678154,0.00025236004,0.00031655512,0.00073949795,0.00087903795,0.00083259103,0.0012647734,0.00023711626,0.00029164145],"category_scores_gemma":[0.021364346,0.00013045204,0.00026175063,0.001073096,0.000105413514,0.0040291524,0.000015648584,0.00024958557,0.0004724752],"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":[0.00054899463,0.000026742135,0.001057744,0.00007423611,0.000057032794,9.660578e-8,0.0016403322,0.009237536,0.000008550917,0.0026976068,0.011441605,0.9732095],"study_design_scores_gemma":[0.0035073524,0.0006428243,0.010448334,0.0008103907,0.00010764367,0.00005442771,0.007931512,0.19378017,0.000499734,0.019646285,0.7617581,0.00081323343],"about_ca_topic_score_codex":0.000024749275,"about_ca_topic_score_gemma":0.0000028728546,"teacher_disagreement_score":0.9723963,"about_ca_system_score_codex":0.00018213084,"about_ca_system_score_gemma":0.00017112141,"threshold_uncertainty_score":0.9868791},"labels":[],"label_agreement":null},{"id":"W2507254902","doi":"10.1145/2956234","title":"TopPRF","year":2016,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Information Retrieval and Search Behavior","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":"York University","funders":"","keywords":"Computer science; Relevance feedback; Relevance (law); Information retrieval; Selection (genetic algorithm); Probabilistic logic; Reliability (semiconductor); Key (lock); Entropy (arrow of time); Identification (biology); Data mining; Artificial intelligence","score_opus":0.02379832225572686,"score_gpt":0.252434260286498,"score_spread":0.22863593803077115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2507254902","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":[0.0015197286,0.000003871315,0.9899155,0.0014540693,0.00094198575,0.0002517324,0.000024238521,0.0003087088,0.00558015],"genre_scores_gemma":[0.99510705,0.000017091645,0.002859571,0.00038005144,0.000025074609,0.00009130953,0.0000032083065,0.0000034546865,0.0015132029],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987539,0.000037194855,0.0004351937,0.000089659756,0.00047259295,0.0002114746],"domain_scores_gemma":[0.99875444,0.0001118614,0.000110295754,0.0007005971,0.00021636114,0.0001064572],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00029417063,0.00010437346,0.000102092556,0.00028953303,0.00020583894,0.00028101416,0.0007152398,0.000069241956,0.00007198486],"category_scores_gemma":[0.000036030033,0.00006576267,0.00006731655,0.0003651833,0.000023872642,0.0055329683,0.000011249588,0.000082184306,0.0035644849],"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":[0.000024155062,0.00004771874,0.00006123128,0.00004269132,0.000023836556,0.0000012458318,0.0018450503,0.0005956055,0.00022624338,0.08284354,0.001672969,0.9126157],"study_design_scores_gemma":[0.0031189837,0.00053519104,0.0027015586,0.00024288626,0.000015240163,0.0001496193,0.0008272618,0.013068806,0.0151073905,0.00097131607,0.96236145,0.00090030686],"about_ca_topic_score_codex":0.000017139051,"about_ca_topic_score_gemma":5.498101e-7,"teacher_disagreement_score":0.9935873,"about_ca_system_score_codex":0.00009025353,"about_ca_system_score_gemma":0.00005973255,"threshold_uncertainty_score":0.99721134},"labels":[],"label_agreement":null},{"id":"W2515155379","doi":"10.1145/2948065","title":"Trip Recommendation Meets Real-World Constraints","year":2016,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":44,"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":"Higher Education Discipline Innovation Project; Natural Sciences and Engineering Research Council of Canada; Renmin University of China","keywords":"Computer science; Constraint (computer-aided design); Time constraint; Point of interest; Window (computing); Recommender system; Sequence (biology); Space (punctuation); Budget constraint; Diversity (politics); Information retrieval; World Wide Web; Operations research; Artificial intelligence; Mathematics","score_opus":0.030090377110567636,"score_gpt":0.2725916044633616,"score_spread":0.24250122735279397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2515155379","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":[0.00011169492,0.0000039904467,0.95913255,0.0045079156,0.0016798956,0.0005245631,0.000042932254,0.0007375797,0.033258893],"genre_scores_gemma":[0.9904534,0.000077788165,0.008087637,0.0002666987,0.000048227073,0.00025394713,0.0000112979305,0.000009044213,0.0007919598],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982705,0.00014430062,0.00080919126,0.00021122544,0.00030778907,0.00025699247],"domain_scores_gemma":[0.99823815,0.00024918225,0.0003394988,0.0008714289,0.00018585497,0.0001158804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006893767,0.00018758723,0.00022764523,0.0005881166,0.00023688561,0.00033348505,0.0006933053,0.00010174558,0.00010914714],"category_scores_gemma":[0.000025647696,0.00013325228,0.000098000986,0.0004892519,0.00003925662,0.003943333,0.000014382,0.00011051152,0.00051292323],"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":[0.000010115124,0.000039506365,0.000065094995,0.00004169228,0.000045001107,6.191891e-7,0.000515266,0.000029463734,0.000099976256,0.050649013,0.005527102,0.94297713],"study_design_scores_gemma":[0.0019961149,0.00027655778,0.000793371,0.00049762457,0.000017001565,0.00009589107,0.00038583134,0.0035937596,0.007725099,0.0015637734,0.9823305,0.00072446093],"about_ca_topic_score_codex":0.00021860856,"about_ca_topic_score_gemma":0.00003131346,"teacher_disagreement_score":0.9903417,"about_ca_system_score_codex":0.0002464704,"about_ca_system_score_gemma":0.000065216984,"threshold_uncertainty_score":0.6592761},"labels":[],"label_agreement":null},{"id":"W2560965260","doi":"10.1145/2988230","title":"Time-Aware Click Model","year":2016,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Information Retrieval and Search Behavior","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":"Université de Montréal","funders":"National Natural Science Foundation of China","keywords":"Computer science; Perplexity; Relevance (law); Click-through rate; Information retrieval; Learning to rank; Search engine; Dwell time; Artificial intelligence; Language model","score_opus":0.024924444805847993,"score_gpt":0.2537497258937442,"score_spread":0.22882528108789624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560965260","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":[0.0016228968,0.0000025464751,0.9929622,0.001030565,0.00040364292,0.00033722297,0.00006959732,0.00039021703,0.0031811132],"genre_scores_gemma":[0.9911223,0.000018120163,0.0037454388,0.0004925709,0.000024887806,0.00013397688,0.000010979839,0.0000072480593,0.0044445004],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99843603,0.000040318697,0.00055596395,0.00011974028,0.0005821228,0.0002658496],"domain_scores_gemma":[0.99848896,0.000101475795,0.00014990577,0.0008185691,0.00030391625,0.0001371711],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00034227897,0.00014246689,0.00014207675,0.00033646272,0.000264673,0.00027552774,0.00083588087,0.00010184967,0.00006885065],"category_scores_gemma":[0.000026360749,0.000094562805,0.00009136692,0.00038139406,0.00003812205,0.0062629217,0.000016679414,0.00011156498,0.006664173],"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":[0.000100495046,0.00018057563,0.00003757599,0.00016772792,0.00008504099,0.0000025625222,0.007241146,0.08944851,0.0007624534,0.045630395,0.009743736,0.84659976],"study_design_scores_gemma":[0.0014717283,0.00019870687,0.00012108495,0.00013789955,0.000011007147,0.000047738962,0.0002756664,0.9363098,0.0032224276,0.00034994833,0.057349917,0.0005040327],"about_ca_topic_score_codex":0.0000103118045,"about_ca_topic_score_gemma":4.0823858e-7,"teacher_disagreement_score":0.9894994,"about_ca_system_score_codex":0.0001261688,"about_ca_system_score_gemma":0.00010736061,"threshold_uncertainty_score":0.9941093},"labels":[],"label_agreement":null},{"id":"W2585936885","doi":"10.1145/3007186","title":"Inverted Treaps","year":2017,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Algorithms and Data Compression","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; Inverted index; Merge (version control); Identifier; ENCODE; Intersection (aeronautics); Thresholding; Representation (politics); Index (typography); Data mining; Information retrieval; Search engine indexing; Theoretical computer science; Artificial intelligence; Image (mathematics)","score_opus":0.02721772894203236,"score_gpt":0.2607516944946491,"score_spread":0.2335339655526167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2585936885","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":[0.00042420093,0.000009493291,0.9902737,0.0004993499,0.0014848198,0.00017700712,0.000030738767,0.00019698079,0.006903692],"genre_scores_gemma":[0.9906826,0.000021990129,0.008570081,0.00020133257,0.00004355449,0.00006015666,0.000017237304,0.000004245075,0.000398809],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991227,0.000025659398,0.00029315767,0.00011970557,0.00029220647,0.00014660417],"domain_scores_gemma":[0.99752504,0.000039905066,0.00022406147,0.0020262753,0.00010225551,0.000082487924],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00017314269,0.000104266546,0.00011503285,0.0001434672,0.0009365194,0.0011704578,0.0015748418,0.00006885969,0.000014843206],"category_scores_gemma":[0.00003218886,0.00008679677,0.000049869624,0.00008658378,0.000026637881,0.006682963,0.000030822834,0.000115451774,0.0006995884],"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":[0.00001894363,0.00007892178,0.00008379066,0.00006206226,0.00005047183,0.0000030013066,0.0016838958,0.0038187928,0.000047630936,0.020886201,0.0062634246,0.96700287],"study_design_scores_gemma":[0.0016062055,0.0001590369,0.004204226,0.00017758322,0.000013510727,0.000061626895,0.00032915853,0.58811104,0.001202042,0.00079308706,0.40285495,0.000487555],"about_ca_topic_score_codex":0.00028847513,"about_ca_topic_score_gemma":0.000004368301,"teacher_disagreement_score":0.9902584,"about_ca_system_score_codex":0.000036527734,"about_ca_system_score_gemma":0.000036435944,"threshold_uncertainty_score":0.9998664},"labels":[],"label_agreement":null},{"id":"W2674238586","doi":"10.1145/3091107","title":"Search by Screenshots for Universal Article Clipping in Mobile Apps","year":2017,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Web Data Mining and Analysis","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":"Université de Montréal","funders":"","keywords":"Computer science; Information retrieval; Chunking (psychology); Usability; Clipping (morphology); Rank (graph theory); Learning to rank; Key (lock); Artificial intelligence; Human–computer interaction; Ranking (information retrieval)","score_opus":0.029745840002553325,"score_gpt":0.28246270193654077,"score_spread":0.25271686193398746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2674238586","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":[0.027553383,0.000014019173,0.9707691,0.00029977268,0.00019576757,0.00027586904,0.00008315694,0.00007034206,0.00073860446],"genre_scores_gemma":[0.99568385,0.000014519704,0.003929389,0.00004522194,0.000015358286,0.00008483375,0.000022275397,0.0000034054374,0.00020115908],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991174,0.000033868226,0.0002997166,0.00013601895,0.000214832,0.00019816228],"domain_scores_gemma":[0.9986514,0.00009870183,0.000120456316,0.00097424677,0.00009182572,0.00006338304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005010613,0.000080996164,0.00012820006,0.00022181481,0.000524865,0.0006927365,0.00093551644,0.000056295157,0.000004669391],"category_scores_gemma":[0.00003292443,0.000080451115,0.000056733443,0.00018286218,0.000028139579,0.0035238285,0.000017716655,0.00010601095,0.00009933066],"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":[0.00008858674,0.0002439485,0.0026113668,0.0002543051,0.00017573487,0.0000031496988,0.010231916,0.13986284,0.0009845257,0.006950509,0.0043924637,0.8342007],"study_design_scores_gemma":[0.0017991123,0.0001776613,0.0010247953,0.00016508618,0.00001796699,0.000008129167,0.005009876,0.92645425,0.0032921196,0.00004728915,0.061666667,0.00033707515],"about_ca_topic_score_codex":0.00040320837,"about_ca_topic_score_gemma":0.000019246785,"teacher_disagreement_score":0.96813047,"about_ca_system_score_codex":0.000063413216,"about_ca_system_score_gemma":0.00003960895,"threshold_uncertainty_score":0.6680074},"labels":[],"label_agreement":null},{"id":"W2751820697","doi":"10.1145/3091995","title":"Modeling and Mining Domain Shared Knowledge for Sentiment Analysis","year":2017,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Sentiment Analysis and Opinion Mining","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":"York University","funders":"Fundamental Research Funds for the Central Universities","keywords":"Computer science; Sentiment analysis; Domain (mathematical analysis); Sentence; Artificial intelligence; Data mining; Natural language processing; Mathematics","score_opus":0.040456273623900925,"score_gpt":0.2987172456892563,"score_spread":0.25826097206535537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2751820697","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":[0.015218408,0.00005123786,0.98302156,0.0002710245,0.000424997,0.0002529253,0.000017607861,0.000065562264,0.0006767057],"genre_scores_gemma":[0.96831113,0.000011635572,0.031283,0.00003435792,0.000031543714,0.00010652231,0.00002037803,0.000004186875,0.00019726178],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989122,0.00002879586,0.00047467125,0.00019467088,0.00021241144,0.00017722751],"domain_scores_gemma":[0.9985254,0.000075244265,0.00024070147,0.0009189628,0.00016017578,0.00007954258],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00053218653,0.0001281294,0.0002397878,0.0005196402,0.0010905144,0.0015736605,0.0006282278,0.000059238882,0.000008237935],"category_scores_gemma":[0.000021171,0.00012029675,0.00017748111,0.00025195067,0.000016528185,0.0025743458,0.000025715108,0.00005397987,0.000027910455],"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":[0.000056112476,0.00016273778,0.0016520168,0.0002783059,0.0034857816,9.1242697e-7,0.033953164,0.7990158,0.000079725636,0.016063135,0.0005433532,0.14470895],"study_design_scores_gemma":[0.00048183414,0.000026597098,0.0002121584,0.000039631163,0.00012657917,0.0000015740559,0.0012081023,0.99511075,0.000054039858,0.000058593945,0.0025365702,0.00014356543],"about_ca_topic_score_codex":0.00004979348,"about_ca_topic_score_gemma":0.00001391234,"teacher_disagreement_score":0.9530927,"about_ca_system_score_codex":0.00004241396,"about_ca_system_score_gemma":0.000023163087,"threshold_uncertainty_score":0.9994628},"labels":[],"label_agreement":null},{"id":"W2898640137","doi":"10.1145/3231937","title":"Learning to Adaptively Rank Document Retrieval System Configurations","year":2018,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Information Retrieval and Search Behavior","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":"Université de Montréal","funders":"Agence Nationale de la Recherche","keywords":"Computer science; Ranking (information retrieval); Set (abstract data type); Rank (graph theory); Selection (genetic algorithm); Exploit; Information retrieval; Query expansion; Task (project management); Learning to rank; Data mining; Grid; Document retrieval; Artificial intelligence; Mathematics","score_opus":0.021105244454159438,"score_gpt":0.2655919473717483,"score_spread":0.24448670291758887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898640137","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":[0.006452768,0.0000037037353,0.9802871,0.00063345017,0.0015960508,0.00095361983,0.000027269429,0.0006545858,0.009391497],"genre_scores_gemma":[0.99295086,0.0000034837635,0.005530915,0.00030961508,0.00009109441,0.00012122153,0.0000177507,0.000008129967,0.0009669439],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974733,0.00014444653,0.0008689776,0.00020120837,0.00093377946,0.0003782946],"domain_scores_gemma":[0.99762666,0.00013059124,0.00024329612,0.0007292655,0.0010080747,0.00026211372],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000830273,0.00020951507,0.00022340752,0.0006472743,0.0009799094,0.00095182535,0.0008782753,0.000119237564,0.000060341423],"category_scores_gemma":[0.0000944946,0.00019041159,0.000099498066,0.0012301233,0.000049809212,0.0042716055,0.000025867334,0.00029137093,0.0056723207],"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":[0.001339769,0.00029770838,0.00008416733,0.0008667512,0.00045010448,0.000015233582,0.14308217,0.14145648,0.002800314,0.38845506,0.0062408815,0.31491137],"study_design_scores_gemma":[0.004628361,0.005376552,0.0020952942,0.0008159262,0.00008443397,0.00035216883,0.036483184,0.2888319,0.030614344,0.00009905851,0.6285691,0.0020496333],"about_ca_topic_score_codex":0.000079310834,"about_ca_topic_score_gemma":0.0000023848957,"teacher_disagreement_score":0.98649806,"about_ca_system_score_codex":0.0003438148,"about_ca_system_score_gemma":0.00016046077,"threshold_uncertainty_score":0.99510187},"labels":[],"label_agreement":null},{"id":"W2904119337","doi":"10.1145/3233773","title":"A Deep Bayesian Tensor-Based System for Video Recommendation","year":2018,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Tensor decomposition and applications","field":"Mathematics","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":"Simon Fraser University","funders":"Tencent","keywords":"Computer science; Recommender system; Surprise; Exploit; Artificial intelligence; Ranking (information retrieval); Machine learning; Tensor (intrinsic definition); Metric (unit); Cluster analysis; Bayesian probability; Information retrieval; Collaborative filtering; Latent variable","score_opus":0.038135568599120005,"score_gpt":0.306795895461837,"score_spread":0.268660326862717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2904119337","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":[0.0007595949,0.0000018500783,0.9906396,0.0011169327,0.0007309647,0.0015738762,0.00021087694,0.0006254462,0.0043408093],"genre_scores_gemma":[0.95619226,7.195661e-7,0.041257292,0.00048562585,0.00015835407,0.0015741566,0.00015628122,0.000028869696,0.00014643208],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984037,0.000074933385,0.00084892707,0.00018412281,0.00024299927,0.00024529576],"domain_scores_gemma":[0.99771905,0.0005102904,0.00039277322,0.000670972,0.00058981654,0.000117123425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004155247,0.00020264403,0.0002494122,0.00036015452,0.00065159774,0.00020248353,0.00026284865,0.00012565537,0.00013050053],"category_scores_gemma":[0.000085785316,0.00019382947,0.00015205523,0.00036495482,0.000048285037,0.0006945527,0.0000028713912,0.00011939857,0.00054897874],"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":[0.0021367134,0.0021442727,0.00017852083,0.008211018,0.0011474128,0.0000018875945,0.011236277,0.020807873,0.0015575805,0.62616044,0.0785866,0.24783142],"study_design_scores_gemma":[0.005200606,0.00072121737,0.00009359678,0.000529768,0.0002673433,0.00009651963,0.008400592,0.54250956,0.007971285,0.004758107,0.42845035,0.0010010723],"about_ca_topic_score_codex":0.000021720312,"about_ca_topic_score_gemma":0.000012907655,"teacher_disagreement_score":0.95543265,"about_ca_system_score_codex":0.00023269176,"about_ca_system_score_gemma":0.00004905429,"threshold_uncertainty_score":0.7904137},"labels":[],"label_agreement":null},{"id":"W2973947483","doi":"10.1145/3345557","title":"Question Answering in Knowledge Bases","year":2019,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Topic Modeling","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 Ottawa","funders":"Dream Project of Ministry of Science and Technology of the People's Republic of China; Fundamental Research Funds for the Central Universities; Foundation for Innovative Research Groups of the National Natural Science Foundation of China; State Key Laboratory of Software Development Environment","keywords":"Computer science; Correctness; Question answering; Bottleneck; Knowledge base; Relation (database); Information bottleneck method; Artificial intelligence; Information retrieval; Machine learning; Data mining; Programming language","score_opus":0.018027592806274667,"score_gpt":0.2547266321229922,"score_spread":0.2366990393167175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2973947483","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":[0.02507856,0.000027226164,0.96769655,0.0001331723,0.001378116,0.00030355892,0.0000027065546,0.00018803045,0.005192105],"genre_scores_gemma":[0.99489707,0.000007841607,0.0047346083,0.00006712925,0.000017508237,0.000051560248,0.0000031838579,0.000003487371,0.00021759338],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991094,0.00005346349,0.00038665457,0.00012438204,0.00017897687,0.00014712039],"domain_scores_gemma":[0.99912554,0.00008198915,0.00007622812,0.0006077478,0.000069592614,0.000038873728],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00034666166,0.00008995636,0.000113488364,0.0003614702,0.00005788518,0.00016792047,0.0004144112,0.00006241322,0.000010891715],"category_scores_gemma":[0.000015656216,0.00009003766,0.00003424982,0.0003555902,0.000005139439,0.0028599177,0.000008622498,0.00013075177,0.0008399507],"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":[0.000015325924,0.00009521942,0.0014476976,0.00034859852,0.00001859518,0.0000010892467,0.0094121145,0.66096646,0.00020735379,0.050751038,0.00005983065,0.27667665],"study_design_scores_gemma":[0.00063479214,0.00006573444,0.0012488578,0.00025105765,0.0000024329343,0.000018525658,0.00070355076,0.97679037,0.0007039488,0.00016583162,0.019180575,0.00023433156],"about_ca_topic_score_codex":0.00015390613,"about_ca_topic_score_gemma":0.00001344621,"teacher_disagreement_score":0.96981853,"about_ca_system_score_codex":0.00011956194,"about_ca_system_score_gemma":0.000045944038,"threshold_uncertainty_score":0.999938},"labels":[],"label_agreement":null},{"id":"W3081520483","doi":"10.1145/3406116","title":"Pairwise Link Prediction Model for Out of Vocabulary Knowledge Base Entities","year":2020,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Advanced Graph Neural Networks","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 Ottawa","funders":"Foundation for Innovative Research Groups of the National Natural Science Foundation of China","keywords":"Computer science; Pairwise comparison; Discriminative model; Relation (database); Artificial intelligence; Benchmark (surveying); Dependency (UML); Word (group theory); Machine learning; A priori and a posteriori; Representation (politics); Theoretical computer science; Data mining; Mathematics","score_opus":0.041519174015214017,"score_gpt":0.25393608106521703,"score_spread":0.21241690705000302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3081520483","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":[0.0002558318,0.00007018983,0.9964858,0.0007068308,0.0010530408,0.0006657242,0.00015485434,0.00031981335,0.00028788732],"genre_scores_gemma":[0.97680426,0.0000406291,0.022359269,0.00028486614,0.00009036133,0.00024342214,0.00003505547,0.000010183029,0.00013198366],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998738,0.000038687038,0.00062856224,0.00016460232,0.00023835455,0.00019183234],"domain_scores_gemma":[0.9987736,0.00011931717,0.00022491746,0.00049595715,0.0002674482,0.00011875836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017892336,0.00014592428,0.00019733964,0.0001823381,0.00016396045,0.0000887297,0.00051903806,0.000098362354,0.0000022290787],"category_scores_gemma":[0.000039259758,0.00014373854,0.00013745824,0.0003408453,0.00003170325,0.0028589135,0.000013604568,0.00014937368,0.00003873839],"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":[0.000050090686,0.00003338348,0.000012570718,0.00035724835,0.00003634408,1.6503925e-7,0.008620582,0.94668156,0.00008266128,0.004528742,0.001157501,0.038439132],"study_design_scores_gemma":[0.0005052405,0.00016486901,0.0000101423875,0.00006276891,0.000014001492,0.0000019384786,0.00024361924,0.9920369,0.00066411763,0.00035828468,0.0058184825,0.00011966417],"about_ca_topic_score_codex":0.0000023571988,"about_ca_topic_score_gemma":0.0000020335244,"teacher_disagreement_score":0.9765484,"about_ca_system_score_codex":0.000043546963,"about_ca_system_score_gemma":0.00006817114,"threshold_uncertainty_score":0.58614874},"labels":[],"label_agreement":null},{"id":"W3102793640","doi":"10.1145/3423322","title":"Neural Feature-aware Recommendation with Signed Hypergraph Convolutional Network","year":2020,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Recommender Systems and Techniques","field":"Computer Science","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":"York University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Collaborative filtering; Recommender system; Bridging (networking); Hypergraph; Profiling (computer programming); Feature (linguistics); Convolutional neural network; Embedding; Graph; Information retrieval; Preference; Artificial intelligence; Machine learning; Data mining; Theoretical computer science","score_opus":0.02140057928735824,"score_gpt":0.22119482330704704,"score_spread":0.1997942440196888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3102793640","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":[0.00013063739,0.000022154572,0.9861092,0.010165277,0.000756245,0.00058182905,0.00003176125,0.0007204001,0.0014824913],"genre_scores_gemma":[0.98476905,0.000010217517,0.012757419,0.0019789196,0.0001314769,0.00021136158,0.00007828934,0.000010978337,0.000052291914],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985664,0.00012199575,0.0004708968,0.00022635784,0.0003543349,0.00026001822],"domain_scores_gemma":[0.99879885,0.00010529784,0.00026562682,0.00046171428,0.0002115309,0.00015698343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023436175,0.00020962849,0.00023367569,0.00014792886,0.00036756194,0.00042593526,0.00059765007,0.00011712236,0.000021606194],"category_scores_gemma":[0.000009074695,0.0001732373,0.00008669625,0.0007433589,0.000022279062,0.0028930479,0.000014539334,0.00025439772,0.00009108942],"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":[0.0006641515,0.00032447433,0.0018967391,0.0010159325,0.0009342163,0.000015024776,0.011567852,0.19710785,0.00012706645,0.08062583,0.22428894,0.48143193],"study_design_scores_gemma":[0.002080605,0.0013348047,0.00096257136,0.00020357885,0.00003784368,0.0002066495,0.0010723611,0.6064156,0.00043457007,0.00028258754,0.38600537,0.0009634258],"about_ca_topic_score_codex":0.00005707061,"about_ca_topic_score_gemma":0.00000530232,"teacher_disagreement_score":0.9846384,"about_ca_system_score_codex":0.00007065004,"about_ca_system_score_gemma":0.000058268426,"threshold_uncertainty_score":0.7064412},"labels":[],"label_agreement":null},{"id":"W3159852056","doi":"10.1145/3451161","title":"Assessing Top- Preferences","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Mobile Crowdsensing and Crowdsourcing","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; Crowdsourcing; Preference; Learning to rank; Artificial intelligence; Information retrieval; Rank (graph theory); Measure (data warehouse); Quality (philosophy); Machine learning; Natural language processing; Data mining; Ranking (information retrieval); Statistics; Mathematics; World Wide Web","score_opus":0.030429623778512566,"score_gpt":0.26641945636743347,"score_spread":0.2359898325889209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3159852056","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":[0.013605914,0.00004224959,0.97443694,0.00031418935,0.0013087485,0.00009147749,0.000002872928,0.00027103466,0.009926582],"genre_scores_gemma":[0.98668355,0.000009818987,0.012783342,0.000210604,0.000032865948,0.000025010175,0.000006254235,0.0000036113465,0.00024492625],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890333,0.00008464146,0.00036780475,0.00014990632,0.0003174966,0.00017679577],"domain_scores_gemma":[0.9986998,0.00012867054,0.00011722625,0.0007588436,0.0002266337,0.000068819885],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002574132,0.00010610156,0.00012980543,0.00014307314,0.00033928562,0.0017660685,0.00036878872,0.000072349816,0.000017752944],"category_scores_gemma":[0.000044813678,0.00010003472,0.000061189116,0.0004627963,0.000015779953,0.0038153874,0.000011144004,0.00015408683,0.00021468055],"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":[0.000004410328,0.00006472477,0.00012091064,0.00018177614,0.000066677676,0.000009965549,0.005940927,0.06004736,0.00056798436,0.012125022,0.00062541367,0.9202448],"study_design_scores_gemma":[0.0033675178,0.00038168125,0.0056518493,0.0021400116,0.000111645415,0.0017798084,0.042971447,0.42724738,0.11465111,0.0047254465,0.39416668,0.0028054097],"about_ca_topic_score_codex":0.000036100093,"about_ca_topic_score_gemma":0.0000027461615,"teacher_disagreement_score":0.97307765,"about_ca_system_score_codex":0.000050805986,"about_ca_system_score_gemma":0.00013155838,"threshold_uncertainty_score":0.9992702},"labels":[],"label_agreement":null},{"id":"W3164333934","doi":"10.1145/3450289","title":"CoSam: An Efficient Collaborative Adaptive Sampler for Recommendation","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Recommender Systems and Techniques","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":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Computer science; Recommender system; Collaborative filtering; Sampling (signal processing); Heuristic; Normalization (sociology); Machine learning; Offset (computer science); Sampling bias; Data mining; Convergence (economics); Stability (learning theory); Domain (mathematical analysis); Artificial intelligence; Sample size determination; Statistics","score_opus":0.040938741939123655,"score_gpt":0.28908844000881745,"score_spread":0.24814969806969378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164333934","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":[0.0001794617,0.00001849411,0.9931695,0.0010818378,0.0014691964,0.0009641193,0.00020657743,0.00035055834,0.0025602498],"genre_scores_gemma":[0.86923474,0.000021763886,0.12848996,0.0005406593,0.00007006241,0.0012015272,0.000230075,0.000014095815,0.00019712302],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985135,0.0001788662,0.00060103997,0.00024361127,0.00024936313,0.00021359301],"domain_scores_gemma":[0.9977778,0.00023477363,0.00026497684,0.00071628956,0.0009051422,0.00010098435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005110401,0.00016897918,0.0002229652,0.00022933143,0.00038522502,0.0005421978,0.00040928583,0.000091109534,0.000023322249],"category_scores_gemma":[0.000037108548,0.00016159251,0.00008165307,0.00062658574,0.000014297542,0.0022476672,0.000012261256,0.00011855764,0.000047948022],"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":[0.00016772082,0.0007707682,0.00002959537,0.00032209101,0.00036358443,0.0000025988984,0.021864334,0.055976328,0.00021022047,0.2876828,0.018615618,0.61399436],"study_design_scores_gemma":[0.0015690943,0.00068470516,0.00011984906,0.00014303427,0.000024921748,0.000066988316,0.008072432,0.37128606,0.010217916,0.0009855392,0.60622126,0.0006081838],"about_ca_topic_score_codex":0.000084474064,"about_ca_topic_score_gemma":0.000028109174,"teacher_disagreement_score":0.8690553,"about_ca_system_score_codex":0.00017244485,"about_ca_system_score_gemma":0.00017207331,"threshold_uncertainty_score":0.65895516},"labels":[],"label_agreement":null},{"id":"W3198536471","doi":"10.1145/3446426","title":"Multi-Stage Conversational Passage Retrieval: An Approach to Fusing Term Importance Estimation and Neural Query Rewriting","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Topic Modeling","field":"Computer Science","cited_by":55,"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":"Canada First Research Excellence Fund; Natural Sciences and Engineering Research Council of Canada; Ministry of Science and Technology, Taiwan","keywords":"Computer science; Information retrieval; Leverage (statistics); Query expansion; Term (time); Artificial intelligence; Query language; Rewriting; Context (archaeology); Natural language processing; Programming language","score_opus":0.059295514660712485,"score_gpt":0.2863921894774662,"score_spread":0.22709667481675372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3198536471","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":[0.03589182,0.000022950098,0.96228564,0.0004043916,0.00042974923,0.00031421246,0.000019239425,0.00020950343,0.0004224817],"genre_scores_gemma":[0.82479095,0.0000039822803,0.17466816,0.00034119113,0.000033733286,0.00002986314,0.000049755658,0.0000067104547,0.00007564544],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984218,0.000100568905,0.0006097925,0.00028425513,0.000391386,0.00019218994],"domain_scores_gemma":[0.9986579,0.000093970724,0.00019924232,0.00067947246,0.00024149081,0.00012796726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049642305,0.00014541874,0.00016568945,0.00021617487,0.0003357707,0.00051859446,0.0003052938,0.000086498156,0.000004772251],"category_scores_gemma":[0.00010526247,0.00015466403,0.000034610155,0.00042456633,0.000022096025,0.0042392993,0.000019685587,0.00017133584,0.000010559163],"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":[0.00003054335,0.00012072467,0.0011126597,0.00050837797,0.00004550224,0.000006653342,0.021333044,0.8744144,0.0018125509,0.015898846,0.00002925411,0.08468747],"study_design_scores_gemma":[0.00041428985,0.000023063067,0.0014929692,0.000054573895,0.000005677213,0.000060872928,0.0020180233,0.9951903,0.0003280869,0.000033480163,0.0002060565,0.00017256926],"about_ca_topic_score_codex":0.000055509317,"about_ca_topic_score_gemma":0.000004671011,"teacher_disagreement_score":0.7888991,"about_ca_system_score_codex":0.00011455424,"about_ca_system_score_gemma":0.00007322223,"threshold_uncertainty_score":0.6307016},"labels":[],"label_agreement":null},{"id":"W3214350751","doi":"10.1145/3466754","title":"Direction-Aware User Recommendation Based on Asymmetric Network Embedding","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Recommender Systems and Techniques","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":"Simon Fraser University","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Computer science; Embedding; Random walk; Benchmark (surveying); Social network (sociolinguistics); Degree (music); Theoretical computer science; Friendship; Interpersonal ties; Social network analysis; Data mining; Artificial intelligence; Machine learning; World Wide Web; Social media; Mathematics","score_opus":0.019931366156918727,"score_gpt":0.2647543712801226,"score_spread":0.24482300512320385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214350751","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":[0.000050036506,0.000017813956,0.9810253,0.0013695447,0.003417879,0.00038715987,0.000019323694,0.0007152106,0.012997731],"genre_scores_gemma":[0.9760879,0.000039838014,0.021550838,0.0012869383,0.00015408483,0.00033690236,0.00008487477,0.000017795715,0.00044077603],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998024,0.00024814016,0.0007256392,0.0002799238,0.00042679603,0.00029553327],"domain_scores_gemma":[0.99789554,0.00037004956,0.00030264692,0.000989388,0.0003360982,0.000106298714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006668931,0.00021848318,0.0002536609,0.00056668255,0.00051128195,0.0007606838,0.00046956696,0.00015842517,0.00005182635],"category_scores_gemma":[0.000051016916,0.00021299804,0.00014268784,0.00176913,0.000008821859,0.0023703834,0.000015210972,0.000275594,0.000217562],"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":[0.00003170914,0.0002648907,0.00033921466,0.0002518394,0.00013831041,0.0000057648517,0.00075573334,0.30167666,0.000013084144,0.012747715,0.029626725,0.65414834],"study_design_scores_gemma":[0.00063296896,0.00017920813,0.00043118044,0.0002947089,0.00001442285,0.000049023958,0.00032578752,0.5633038,0.0013009869,0.00014790604,0.43289444,0.00042555673],"about_ca_topic_score_codex":0.00009041737,"about_ca_topic_score_gemma":0.000008135465,"teacher_disagreement_score":0.9760379,"about_ca_system_score_codex":0.00025399146,"about_ca_system_score_gemma":0.00010459861,"threshold_uncertainty_score":0.8685808},"labels":[],"label_agreement":null},{"id":"W3215214493","doi":"10.1145/3473973","title":"Graph Neural Collaborative Topic Model for Citation Recommendation","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Topic Modeling","field":"Computer Science","cited_by":34,"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; Citation; Pairwise comparison; Graph; Information retrieval; Knowledge graph; Artificial neural network; Information overload; Data science; Artificial intelligence; Machine learning; Theoretical computer science; World Wide Web","score_opus":0.042966983719350094,"score_gpt":0.276904698131039,"score_spread":0.23393771441168892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215214493","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":[0.00094769837,0.00001280284,0.9940531,0.002561706,0.0011591087,0.000443751,0.000054400647,0.00014435478,0.00062306435],"genre_scores_gemma":[0.9034551,0.000015038896,0.09507699,0.00057351607,0.000035737226,0.00035693147,0.00011940449,0.000005852775,0.00036146832],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989789,0.000060099315,0.00044878924,0.00016446078,0.00020036071,0.00014736305],"domain_scores_gemma":[0.9985864,0.0001348854,0.00015547773,0.00045549267,0.0006177326,0.000049976075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022814058,0.00010553046,0.00012377575,0.00020659354,0.00025638053,0.0003384935,0.00026216058,0.000073259216,0.000005626346],"category_scores_gemma":[0.000058167174,0.00011066424,0.00006395432,0.0005258561,0.000007812177,0.002907684,0.000006894269,0.00009297449,0.000021291837],"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":[0.000012820123,0.00003262047,0.000008183649,0.00008286653,0.000031347652,2.0863038e-7,0.005723698,0.8084937,0.00007942081,0.03174412,0.00036008874,0.15343095],"study_design_scores_gemma":[0.0004617795,0.00003336245,0.000019242396,0.000015511367,0.0000067877213,0.00000598855,0.0008693897,0.9920885,0.0007271804,0.001612849,0.0040423614,0.000117060255],"about_ca_topic_score_codex":0.000009629967,"about_ca_topic_score_gemma":0.0000082479455,"teacher_disagreement_score":0.90250736,"about_ca_system_score_codex":0.00008579992,"about_ca_system_score_gemma":0.00012089265,"threshold_uncertainty_score":0.45127568},"labels":[],"label_agreement":null},{"id":"W3215411791","doi":"10.1145/3478285","title":"Embedding Hierarchical Structures for Venue Category Representation","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Advanced Graph Neural Networks","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":"York University; Wilfrid Laurier University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Embedding; Context (archaeology); Hierarchy; Representation (politics); Semantics (computer science); Information retrieval; Theoretical computer science; Artificial intelligence","score_opus":0.02585947478299782,"score_gpt":0.2997060619374764,"score_spread":0.27384658715447857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215411791","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":[0.0015170716,0.000050965446,0.99573225,0.0004348177,0.0015722436,0.00031651402,0.000028204442,0.00016955569,0.00017840629],"genre_scores_gemma":[0.9514136,0.00001973656,0.047817234,0.00030595652,0.00008580589,0.00019107401,0.00006559638,0.000008081837,0.000092967406],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989278,0.000064956614,0.00037698058,0.00018185709,0.00025666825,0.0001917493],"domain_scores_gemma":[0.99866325,0.00027616494,0.0001399943,0.00065203104,0.00020037736,0.00006819061],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000111391666,0.000110220884,0.00013592666,0.00015876722,0.00029665203,0.00027137983,0.00037889692,0.00008218143,0.0000037896339],"category_scores_gemma":[0.00006919887,0.0001112701,0.00009261555,0.00045546834,0.00002121389,0.0019962098,0.000011068328,0.00017920052,0.000022329345],"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":[0.00003276771,0.000023805589,0.000016900669,0.000099587734,0.00004566948,0.00000384159,0.0021032938,0.7771144,0.0003565975,0.0449947,0.00065250904,0.17455596],"study_design_scores_gemma":[0.0019746607,0.00020002932,0.00072425936,0.000116952346,0.000034622375,0.0003032249,0.0015171795,0.86018777,0.017438175,0.042742457,0.07407431,0.00068637374],"about_ca_topic_score_codex":0.0000081024145,"about_ca_topic_score_gemma":0.0000016754924,"teacher_disagreement_score":0.94989645,"about_ca_system_score_codex":0.00005132575,"about_ca_system_score_gemma":0.000054522887,"threshold_uncertainty_score":0.4537463},"labels":[],"label_agreement":null},{"id":"W3217040326","doi":"10.1145/3471165","title":"Dual Gated Graph Attention Networks with Dynamic Iterative Training for Cross-Lingual Entity Alignment","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Advanced Graph Neural Networks","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":"York University","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China; National Research Foundation Singapore","keywords":"Computer science; Attention network; Graph; Embedding; Iterative and incremental development; Benchmark (surveying); Dual (grammatical number); Process (computing); Machine learning; Artificial intelligence; Theoretical computer science; Data mining","score_opus":0.0196459319324312,"score_gpt":0.27745233427603794,"score_spread":0.25780640234360674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3217040326","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":[0.020110834,0.000042836888,0.97725856,0.00014430945,0.0013561561,0.00067016424,0.000048423255,0.00026486008,0.000103863196],"genre_scores_gemma":[0.98000145,0.000022541275,0.019184962,0.000181481,0.000043134132,0.00022511123,0.0001629016,0.000012899574,0.0001655149],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982226,0.00008860636,0.0006194936,0.0003064144,0.00039787785,0.0003649989],"domain_scores_gemma":[0.9982923,0.00019080729,0.00030375796,0.0006178689,0.0004906284,0.00010463412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026922388,0.00022800529,0.00023944327,0.00020869872,0.0005667503,0.00071121915,0.0003264595,0.00012106995,0.000005035118],"category_scores_gemma":[0.0000199894,0.00020997654,0.00013896386,0.0008602783,0.00005499804,0.003287361,0.000012993354,0.00023891895,0.000011441034],"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":[0.00007250231,0.0000508302,0.000053924734,0.00005459003,0.00011695127,0.0000059741496,0.002211098,0.9663814,0.00007418288,0.002628827,0.00003395313,0.028315783],"study_design_scores_gemma":[0.0027856985,0.00046379303,0.0010393596,0.00032260435,0.000048291164,0.00024973505,0.002119405,0.9873609,0.0009477846,0.0005569068,0.0034834868,0.0006220511],"about_ca_topic_score_codex":0.000007755977,"about_ca_topic_score_gemma":0.00002530402,"teacher_disagreement_score":0.9598906,"about_ca_system_score_codex":0.00011889642,"about_ca_system_score_gemma":0.000076072225,"threshold_uncertainty_score":0.8562595},"labels":[],"label_agreement":null},{"id":"W4200199191","doi":"10.1145/3476106","title":"Are Topics Interesting or Not? An LDA-based Topic-graph Probabilistic Model for Web Search Personalization","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; Wilfrid Laurier University","funders":"Wilfrid Laurier University","keywords":"Latent Dirichlet allocation; Computer science; Personalization; Topic model; Information retrieval; Web page; Graph; Probabilistic logic; Web search query; Personalized search; User modeling; World Wide Web; User interface; Data mining; Search engine; Theoretical computer science; Artificial intelligence","score_opus":0.11641684713239055,"score_gpt":0.3228678552276038,"score_spread":0.20645100809521327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200199191","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":[0.012629115,0.0000036948945,0.9850331,0.00071428803,0.0004551617,0.0007074741,0.00013190549,0.00020066726,0.00012461562],"genre_scores_gemma":[0.9704238,0.0000033854985,0.027200533,0.0009270783,0.00005287557,0.00030212596,0.00011399815,0.000009543498,0.0009666635],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983017,0.00008898892,0.00060161104,0.00018883719,0.0005476289,0.00027123225],"domain_scores_gemma":[0.9979186,0.00015534513,0.00020435822,0.0006313804,0.0009589538,0.00013134249],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042569565,0.00015463411,0.00018123705,0.00029230744,0.00044212546,0.0006873514,0.0005230538,0.00011726969,0.0000213725],"category_scores_gemma":[0.00019648034,0.0001344841,0.00010429087,0.00061539735,0.000027767866,0.0029529748,0.00001412057,0.0001773287,0.000028696464],"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":[0.0002910142,0.0002777921,0.00012964911,0.0017626828,0.000044036875,0.0000064744168,0.011322475,0.8791852,0.00026319982,0.020375498,0.0002697846,0.086072214],"study_design_scores_gemma":[0.0006825734,0.0001126211,0.00020844689,0.000106431966,0.00001046622,0.000018578532,0.001305122,0.99451804,0.00091479014,0.000058216716,0.0018850133,0.0001796858],"about_ca_topic_score_codex":0.000013945442,"about_ca_topic_score_gemma":0.000037552272,"teacher_disagreement_score":0.9578325,"about_ca_system_score_codex":0.00015572444,"about_ca_system_score_gemma":0.00048701643,"threshold_uncertainty_score":0.6628145},"labels":[],"label_agreement":null},{"id":"W4220896903","doi":"10.1145/3507356","title":"Leveraging Narrative to Generate Movie Script","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Topic Modeling","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":"Thomson Reuters (Canada); Université de Montréal","funders":"","keywords":"Computer science; Narrative; Scripting language; Context (archaeology); Upload; Unavailability; Task (project management); Construct (python library); Information retrieval; Artificial intelligence; Natural language processing; World Wide Web; Linguistics; Programming language","score_opus":0.03357747367188199,"score_gpt":0.24551363434961782,"score_spread":0.21193616067773582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220896903","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":[0.00897415,0.000017048937,0.9854305,0.0014615185,0.0022540567,0.0003824739,0.00001472852,0.00023401098,0.0012315175],"genre_scores_gemma":[0.9821658,0.000001675315,0.015272412,0.0016131744,0.00003380532,0.00039753845,0.0000069880057,0.000005558796,0.00050300645],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985786,0.0001036981,0.00046121387,0.00017350209,0.0004822507,0.00020075343],"domain_scores_gemma":[0.9989158,0.00004417719,0.00011580299,0.00072873547,0.000105735475,0.00008973457],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004380701,0.00011375448,0.00012436349,0.00034989326,0.0008329534,0.00030554127,0.0008160637,0.000024693234,0.000042273732],"category_scores_gemma":[0.00001782222,0.00012054252,0.000050259245,0.00057073194,0.0000058501555,0.001653195,0.00004020074,0.00020668356,0.0001736993],"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":[0.000005326107,0.000013848692,0.0000039772326,0.0000127797575,0.000015521155,9.273529e-7,0.035563145,0.928872,0.00007604283,0.0033928845,0.0005708378,0.031472735],"study_design_scores_gemma":[0.0005243809,0.00014954546,0.000032861884,0.000024519428,0.0000058336773,0.00006829999,0.017491972,0.8058042,0.00090115087,0.0002558308,0.17437337,0.00036803054],"about_ca_topic_score_codex":0.00012954259,"about_ca_topic_score_gemma":0.0000013465823,"teacher_disagreement_score":0.9731917,"about_ca_system_score_codex":0.00024055122,"about_ca_system_score_gemma":0.00008111993,"threshold_uncertainty_score":0.6406488},"labels":[],"label_agreement":null},{"id":"W4282569005","doi":"10.1145/3544103","title":"GDESA: Greedy Diversity Encoder with Self-attention for Search Results Diversification","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Information Retrieval and Search Behavior","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":"Université de Montréal","funders":"National Natural Science Foundation of China","keywords":"Computer science; Diversification (marketing strategy); Leverage (statistics); Greedy algorithm; Selection (genetic algorithm); Encoder; Ranking (information retrieval); Machine learning; Artificial intelligence; Data mining; Information retrieval; Algorithm; Business","score_opus":0.03631250601771496,"score_gpt":0.2487990638902549,"score_spread":0.21248655787253995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282569005","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":[0.015622265,0.0000031064556,0.98010147,0.00077385927,0.0006001431,0.0012940691,0.00039884518,0.0003391716,0.0008670685],"genre_scores_gemma":[0.99241275,0.0000057328148,0.006392853,0.00014940872,0.000017540144,0.00032910347,0.00021477744,0.0000051686247,0.00047264688],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978534,0.000113562724,0.0004771807,0.00019376432,0.0010886673,0.0002734027],"domain_scores_gemma":[0.99836266,0.00013205789,0.00022703524,0.0006503335,0.000525746,0.00010216106],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0010240857,0.00013874509,0.00013496379,0.00049483165,0.0025928651,0.00030282783,0.0009481208,0.00005425573,0.000018589373],"category_scores_gemma":[0.000015403166,0.00012788139,0.0000902383,0.00081563625,0.000025456658,0.0038467334,0.000098359356,0.0002520356,0.00012255777],"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":[0.00476841,0.00193647,0.0027633277,0.0011901271,0.0007313012,0.000011703524,0.15633456,0.55080533,0.00027256727,0.06576147,0.01100996,0.20441476],"study_design_scores_gemma":[0.016251849,0.00488313,0.020077005,0.00010184331,0.00018916708,0.0002347813,0.034473788,0.75491256,0.0014785299,0.000220901,0.16542932,0.0017470984],"about_ca_topic_score_codex":0.00019902928,"about_ca_topic_score_gemma":0.0000036952156,"teacher_disagreement_score":0.9767905,"about_ca_system_score_codex":0.00038472554,"about_ca_system_score_gemma":0.00012269538,"threshold_uncertainty_score":0.9987056},"labels":[],"label_agreement":null},{"id":"W4288080293","doi":"10.1145/3385186","title":"OutdoorSent","year":2020,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Sentiment Analysis and Opinion Mining","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 Toronto","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Computer science; Sentiment analysis; Generalization; Class (philosophy); Artificial intelligence; Context (archaeology); Information retrieval; Machine learning; Data science; Geography","score_opus":0.03513477824408741,"score_gpt":0.24907013153895155,"score_spread":0.21393535329486413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288080293","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":[0.00042374554,0.000015318114,0.9926106,0.0031156603,0.00056509464,0.00012343698,0.0000040287155,0.00019813409,0.0029440136],"genre_scores_gemma":[0.99299455,0.000010865137,0.005169462,0.0016368146,0.00005022238,0.00002455063,0.000008076268,0.0000030273332,0.000102452395],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990624,0.000029909677,0.00036439224,0.0001104008,0.00031474573,0.00011813311],"domain_scores_gemma":[0.9992857,0.00003961128,0.000115127325,0.00038378141,0.00007196724,0.00010380698],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00012102543,0.00008657766,0.00011670151,0.00012774549,0.00014228487,0.00033720932,0.0005124884,0.000036878333,0.000043049262],"category_scores_gemma":[0.000015100554,0.000077530465,0.00008507079,0.0004482383,0.000006035148,0.0016306471,0.00000882643,0.000087176144,0.0015735097],"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":[0.000059257407,0.00018982125,0.0006061963,0.00028433284,0.0005559479,0.000006056334,0.044074956,0.347186,0.00028073054,0.09988089,0.024107363,0.48276845],"study_design_scores_gemma":[0.0007054944,0.00014892664,0.00022155649,0.000039445564,0.000019624757,0.000008099276,0.0022554882,0.68023425,0.0012459706,0.000051006173,0.31474984,0.00032032476],"about_ca_topic_score_codex":0.00001274215,"about_ca_topic_score_gemma":2.4341264e-7,"teacher_disagreement_score":0.99257076,"about_ca_system_score_codex":0.000023381246,"about_ca_system_score_gemma":0.000021149077,"threshold_uncertainty_score":0.99920386},"labels":[],"label_agreement":null},{"id":"W4293083978","doi":"10.1145/3533020","title":"Learning Implicit and Explicit Multi-task Interactions for Information Extraction","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Topic Modeling","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 Ottawa","funders":"National Key Research and Development Program of China","keywords":"Computer science; Multi-task learning; Generalization; Leverage (statistics); Artificial intelligence; Task (project management); Machine learning; Sequence learning; Unobservable; Representation (politics)","score_opus":0.027401701728496257,"score_gpt":0.27734139878757036,"score_spread":0.2499396970590741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293083978","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":[0.003940925,0.000013833118,0.9925569,0.00043956074,0.0014494603,0.00079899107,0.000050644234,0.00034340704,0.00040625696],"genre_scores_gemma":[0.97970104,0.000012112967,0.018301133,0.00028007603,0.00003251629,0.001384314,0.00006788238,0.00000773391,0.00021318572],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985353,0.0000822305,0.00065473514,0.00016476231,0.0003407743,0.00022224108],"domain_scores_gemma":[0.99870837,0.00022078937,0.00033834923,0.0004789262,0.00017524726,0.000078349905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004954591,0.00015145156,0.00015371123,0.0005648671,0.0012427553,0.0004907462,0.00041537452,0.00005109738,0.000012367811],"category_scores_gemma":[0.000058242684,0.00016813185,0.00007716275,0.00035804164,0.0000089745145,0.007651147,0.00003630291,0.00038783194,0.00005071312],"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":[0.000050443145,0.000068137204,0.000056762907,0.00013827518,0.000056910194,2.5933255e-7,0.014292615,0.64217335,0.00040561624,0.013783614,0.0002131501,0.32876086],"study_design_scores_gemma":[0.0008212344,0.00016828316,0.00015375834,0.000016763435,0.000012258087,0.00010686198,0.0066510784,0.8010163,0.00016577652,0.00008754563,0.19058715,0.00021303562],"about_ca_topic_score_codex":0.000151533,"about_ca_topic_score_gemma":0.000004147361,"teacher_disagreement_score":0.9757601,"about_ca_system_score_codex":0.00023486208,"about_ca_system_score_gemma":0.000052124673,"threshold_uncertainty_score":0.95583946},"labels":[],"label_agreement":null},{"id":"W4296448351","doi":"10.1145/3564285","title":"A Multi-Objective Optimization Framework for Multi-Stakeholder Fairness-Aware Recommendation","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Recommender Systems and Techniques","field":"Computer Science","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":"Google (Canada); Microsoft (Canada); McGill University","funders":"","keywords":"Computer science; Stakeholder; Pareto principle; Ranking (information retrieval); Multi-objective optimization; Set (abstract data type); Rank (graph theory); Order (exchange); Mathematical optimization; Business; Artificial intelligence; Machine learning; Economics; Mathematics","score_opus":0.09382313345199016,"score_gpt":0.30968547861339896,"score_spread":0.2158623451614088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296448351","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":[0.00002142915,0.000012554082,0.9936816,0.0008700871,0.0023673752,0.0019631549,0.0002421856,0.00070203614,0.00013958469],"genre_scores_gemma":[0.4311497,0.00001240178,0.56334066,0.00045433026,0.00004171891,0.004593189,0.00020480253,0.00002339825,0.00017981057],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980512,0.00022048142,0.00077797496,0.00031099646,0.00035609468,0.00028325577],"domain_scores_gemma":[0.99809796,0.00023548314,0.00048666415,0.00077715225,0.00032115573,0.00008159875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074898655,0.00023120163,0.0002597266,0.0005308949,0.0011043093,0.00045792208,0.00079571386,0.00013176836,0.000058602716],"category_scores_gemma":[0.000051742096,0.00023993809,0.00013962804,0.00070539204,0.000014642459,0.002899406,0.000040670184,0.00034153144,0.000022679704],"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":[0.00008870955,0.0006383846,0.00007295021,0.00032466833,0.00021614307,9.743003e-7,0.014675091,0.81377417,0.000014823666,0.022984033,0.0027894794,0.14442055],"study_design_scores_gemma":[0.0010915794,0.00024399698,0.000054296645,0.000054767275,0.000013096788,0.000031304393,0.0043199663,0.957699,0.00021133355,0.00023938883,0.035693962,0.00034730908],"about_ca_topic_score_codex":0.0001351901,"about_ca_topic_score_gemma":0.000005948997,"teacher_disagreement_score":0.43112826,"about_ca_system_score_codex":0.000410529,"about_ca_system_score_gemma":0.000084570645,"threshold_uncertainty_score":0.9784391},"labels":[],"label_agreement":null},{"id":"W4297816431","doi":"10.1145/3555371","title":"Learning to Ask: Conversational Product Search via Representation Learning","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Information Retrieval and Search Behavior","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":"York University","funders":"","keywords":"Ask price; Product (mathematics); Computer science; Representation (politics); Human–computer interaction; Artificial intelligence; Mathematics; Business; Political science","score_opus":0.031508617344332475,"score_gpt":0.2849817503115045,"score_spread":0.25347313296717205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297816431","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":[0.02701391,0.0000042968686,0.9680218,0.0012993797,0.00096079806,0.0009049844,0.000015336967,0.00039091439,0.0013885566],"genre_scores_gemma":[0.99503416,0.0000030623164,0.0023507557,0.0002763506,0.00003779835,0.00040376122,0.00010119205,0.000007886842,0.0017850073],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99706566,0.00035110963,0.00061241584,0.00022079522,0.0014404823,0.00030956106],"domain_scores_gemma":[0.9985865,0.000158777,0.00018026152,0.0004992466,0.00042786569,0.00014738263],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012227157,0.00014300617,0.0001525859,0.000768008,0.0015736638,0.00047137408,0.00074707135,0.000037186317,0.0002183169],"category_scores_gemma":[0.00010375069,0.00015196163,0.000082747625,0.0014957251,0.000020230893,0.003412472,0.00007175672,0.00068969495,0.0009777407],"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":[0.00004670361,0.000039794177,0.00032021615,0.000030369732,0.000019448036,0.000001140625,0.016729048,0.8982514,0.0001661674,0.0013387818,0.00021280938,0.082844086],"study_design_scores_gemma":[0.0016161293,0.0013669204,0.005029762,0.00003328792,0.000018343608,0.0002095463,0.023270484,0.78392863,0.0046357424,0.00006447967,0.17906222,0.00076444173],"about_ca_topic_score_codex":0.00019082951,"about_ca_topic_score_gemma":8.644634e-7,"teacher_disagreement_score":0.96802026,"about_ca_system_score_codex":0.00033071951,"about_ca_system_score_gemma":0.0001557207,"threshold_uncertainty_score":0.9998001},"labels":[],"label_agreement":null},{"id":"W4308605908","doi":"10.1145/3570500","title":"Modeling User Reviews through Bayesian Graph Attention Networks for Recommendation","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Inference; Semantics (computer science); Graph; Recommender system; Bayesian network; User modeling; Machine learning; Theoretical computer science; Information retrieval; Artificial intelligence; User interface","score_opus":0.045832603855943496,"score_gpt":0.28289566840317415,"score_spread":0.23706306454723064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308605908","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":[0.000026706457,0.00008923903,0.9928338,0.0011266809,0.0030119265,0.0017712319,0.000032338296,0.0003883403,0.0007197177],"genre_scores_gemma":[0.91730666,0.00040785476,0.07430668,0.0012610712,0.0001320408,0.0057852683,0.0003303023,0.000028730961,0.00044139902],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803007,0.0002389155,0.000987376,0.00023223944,0.00026318346,0.00024819982],"domain_scores_gemma":[0.9986503,0.0000762586,0.0003514762,0.0007383297,0.00013204606,0.000051552142],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012763976,0.00018301918,0.0002660592,0.00028891594,0.00088873046,0.0003586333,0.00068608037,0.00007637573,0.00002592843],"category_scores_gemma":[0.000012118859,0.00017990347,0.00020902987,0.000570779,0.00000660928,0.0035452768,0.000027210439,0.00024001805,0.000019483528],"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":[0.00003900178,0.000134806,0.000023561282,0.00028877956,0.000093670205,2.4639425e-7,0.0024313738,0.71700704,0.00001220354,0.032809835,0.02238195,0.22477752],"study_design_scores_gemma":[0.00028980503,0.000114532835,0.0000017286072,0.000042723757,0.000009349414,0.000018499584,0.00040499875,0.64458764,0.000010636685,0.00060031307,0.35374957,0.00017018204],"about_ca_topic_score_codex":0.00015630906,"about_ca_topic_score_gemma":0.0000066835782,"teacher_disagreement_score":0.9185271,"about_ca_system_score_codex":0.00019198724,"about_ca_system_score_gemma":0.000026572478,"threshold_uncertainty_score":0.73362505},"labels":[],"label_agreement":null},{"id":"W4311609640","doi":"10.1145/3576922","title":"Efficient Document-at-a-Time and Score-at-a-Time Query Evaluation for Learned Sparse Representations","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Advanced Image and Video Retrieval Techniques","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 Waterloo","funders":"","keywords":"Computer science; Exploit; Transformer; Pareto principle; Ranking (information retrieval); Software deployment; Information retrieval; Data mining; Software engineering; Mathematical optimization","score_opus":0.03333565260937324,"score_gpt":0.30646139235857817,"score_spread":0.27312573974920495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311609640","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":[0.012146969,0.00009610598,0.9829222,0.0006458761,0.00040002185,0.002276484,0.00012828803,0.00042503423,0.0009590429],"genre_scores_gemma":[0.96696955,0.00004567022,0.023443272,0.00048829004,0.000048379756,0.0035866038,0.00030559118,0.000030289684,0.0050823516],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99775636,0.00020366749,0.0006374423,0.0003219053,0.00081531965,0.0002652794],"domain_scores_gemma":[0.9980617,0.000338227,0.00034907897,0.0008463449,0.00030599374,0.00009862887],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0012582407,0.00018325882,0.00021458305,0.00042666332,0.0013378082,0.00024206696,0.00049142295,0.00005835756,0.00017044987],"category_scores_gemma":[0.00012924701,0.0001912869,0.000103769635,0.00058854884,0.000043472053,0.0014028824,0.00009804275,0.00015414867,0.0002115754],"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":[0.0004037444,0.0002253767,0.000036723955,0.0001609058,0.00014682855,0.00000217273,0.0059341737,0.7874945,0.0043547093,0.0037808195,0.0057448903,0.19171515],"study_design_scores_gemma":[0.0021788923,0.0006183094,0.00018537174,0.000056895493,0.00007625481,0.00013744272,0.00053797325,0.92511845,0.011675193,0.0012972486,0.057574995,0.00054297526],"about_ca_topic_score_codex":0.00004292851,"about_ca_topic_score_gemma":0.0000017636248,"teacher_disagreement_score":0.9594789,"about_ca_system_score_codex":0.0006748651,"about_ca_system_score_gemma":0.000093250164,"threshold_uncertainty_score":0.99996233},"labels":[],"label_agreement":null},{"id":"W4313426558","doi":"10.1145/3533769","title":"Knowledge Base Embedding for Sampling-Based Prediction","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","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":"University of Ottawa","funders":"National Key Research and Development Program of China; Fundamental Research Funds for the Central Universities; State Key Laboratory of Software Development Environment","keywords":"Computer science; Latent variable; Protocol (science); Task (project management); Ranking (information retrieval); Machine learning; Sampling (signal processing); Rank (graph theory); Artificial intelligence; Data mining; Embedding; Variable (mathematics); Link (geometry); Mathematics","score_opus":0.038179926302878586,"score_gpt":0.2914206615433705,"score_spread":0.2532407352404919,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313426558","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":[0.0005176981,0.000036525744,0.9945502,0.00024465573,0.0029166208,0.00083582674,0.00018269819,0.000490684,0.00022503892],"genre_scores_gemma":[0.9651078,0.0000028637198,0.032566328,0.00033577796,0.000061631894,0.0017266327,0.00008375527,0.000012869768,0.00010236406],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861306,0.000082499784,0.0005008321,0.00020181062,0.00032586872,0.00027590955],"domain_scores_gemma":[0.9984706,0.00038545276,0.00020446212,0.0006952111,0.00015553975,0.0000887491],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046228408,0.00014660481,0.00014463787,0.00044107845,0.0010408288,0.0001794349,0.0006832456,0.000049896225,0.000014190491],"category_scores_gemma":[0.000031522053,0.00015744167,0.0001243312,0.0007852698,0.000016002585,0.0018814813,0.000018558721,0.00024541092,0.000030352883],"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":[0.00002710137,0.00004098662,0.000005424602,0.000038199294,0.000011463087,1.4424319e-7,0.000514829,0.9669723,0.00001742877,0.0030490914,0.0004989291,0.028824119],"study_design_scores_gemma":[0.00070613873,0.0002249453,0.000020577232,0.00002482131,0.000008047239,0.000013686046,0.0003269172,0.9123734,0.00019682087,0.00028275122,0.0856677,0.00015417283],"about_ca_topic_score_codex":0.000006319509,"about_ca_topic_score_gemma":0.0000015426174,"teacher_disagreement_score":0.9645901,"about_ca_system_score_codex":0.00023651352,"about_ca_system_score_gemma":0.00008909185,"threshold_uncertainty_score":0.80053186},"labels":[],"label_agreement":null},{"id":"W4317209756","doi":"10.1145/3580489","title":"Contrastive Learning for Legal Judgment Prediction","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Artificial Intelligence in Law","field":"Social Sciences","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":"Université de Montréal","funders":"","keywords":"Computer science; Task (project management); Representation (politics); Artificial intelligence; Range (aeronautics); Focus (optics); Machine learning; Law; Political science","score_opus":0.05367930586555467,"score_gpt":0.3340259175124735,"score_spread":0.2803466116469188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317209756","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":[0.0069726976,0.0000066257294,0.96614003,0.0013807231,0.0037626722,0.0015554463,0.000107174164,0.0009215079,0.019153105],"genre_scores_gemma":[0.99635786,0.000038204504,0.00011107369,0.00007097768,0.00019077,0.0005518282,0.00005117059,0.000008137773,0.0026199745],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.99863774,0.0001048798,0.00044065464,0.00010434503,0.0004301798,0.0002822215],"domain_scores_gemma":[0.998884,0.00045805366,0.0001411907,0.00015089235,0.0002808996,0.0000849627],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009975084,0.000090637004,0.00011735631,0.0002369856,0.0013577348,0.00025206088,0.00018486063,0.000116730596,0.000060020393],"category_scores_gemma":[0.00032760692,0.00009465974,0.000081683065,0.0005041431,0.00009760077,0.0016319709,0.0000024837427,0.00015317305,0.00095330406],"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":[0.0002151164,0.00007549888,0.00027304655,0.00012018772,0.00014624993,9.0816314e-7,0.07244509,0.63664174,0.00011543947,0.13699491,0.0070943753,0.14587745],"study_design_scores_gemma":[0.00022798186,0.0001695394,0.0001404029,0.00006475602,0.000023110326,0.0000011557504,0.07336137,0.032611135,0.0006020645,0.0004114108,0.8922248,0.0001623147],"about_ca_topic_score_codex":0.0010790739,"about_ca_topic_score_gemma":0.00014666696,"teacher_disagreement_score":0.9893852,"about_ca_system_score_codex":0.00021948028,"about_ca_system_score_gemma":0.00010780818,"threshold_uncertainty_score":0.99994236},"labels":[],"label_agreement":null},{"id":"W4318617465","doi":"10.1145/3582426","title":"A Dense Representation Framework for Lexical and Semantic Matching","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","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 Waterloo","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Representation (politics); Matching (statistics); Semantic matching; Lexical database; Information retrieval; WordNet; Mathematics","score_opus":0.040472218124865324,"score_gpt":0.3386158581131831,"score_spread":0.2981436399883178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318617465","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":[0.0020497788,0.000015315913,0.9957265,0.0005955267,0.00032890597,0.0004885914,0.000010639601,0.00070394826,0.00008076194],"genre_scores_gemma":[0.86195797,0.00009645316,0.13731122,0.00022807594,0.000034421068,0.00025093724,0.000012573266,0.0000076271895,0.000100705205],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999169,0.000029662306,0.00031121378,0.00013558875,0.00019946828,0.00015508971],"domain_scores_gemma":[0.998891,0.00044644572,0.00009992628,0.0004150848,0.000096025164,0.000051551186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026997112,0.00008937863,0.0001179099,0.00025868783,0.00025090214,0.00029845355,0.00024245903,0.00007739756,0.0000012423612],"category_scores_gemma":[0.00012436791,0.0000838851,0.000048080874,0.00056309754,0.000017413871,0.002336431,0.000012356988,0.0001160291,0.000069471746],"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":[0.000099703255,0.00004853284,0.0000718393,0.0005928349,0.0000773587,0.000004992972,0.011270964,0.0107422685,0.00041866087,0.24912722,0.0011727639,0.72637284],"study_design_scores_gemma":[0.0020597004,0.00084611203,0.0021119758,0.0010478257,0.00006343216,0.00024188177,0.006971666,0.4061319,0.03213847,0.505862,0.041265484,0.0012595811],"about_ca_topic_score_codex":0.000018666695,"about_ca_topic_score_gemma":5.444952e-7,"teacher_disagreement_score":0.8599082,"about_ca_system_score_codex":0.000027392125,"about_ca_system_score_gemma":0.000016480963,"threshold_uncertainty_score":0.3420735},"labels":[],"label_agreement":null},{"id":"W4318775883","doi":"10.1145/3582553","title":"TME: Tree-guided Multi-task Embedding Learning towards Semantic Venue Annotation","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Human Mobility and Location-Based Analysis","field":"Social 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; Wilfrid Laurier University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Task (project management); Annotation; Information retrieval; Embedding; Feature (linguistics); Semantic similarity; Natural language processing; Artificial intelligence; Hierarchy; Tree (set theory); Exploit","score_opus":0.04848614744543105,"score_gpt":0.34552204317668656,"score_spread":0.2970358957312555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318775883","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":[0.13827363,0.000043702406,0.8501539,0.0018150061,0.0016323344,0.0011216,0.00006999,0.0013541337,0.005535668],"genre_scores_gemma":[0.99771094,0.00006478272,0.00012526747,0.00006754254,0.000094365125,0.00016466127,0.00014941728,0.000009514719,0.0016134963],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981405,0.00032588514,0.00054364407,0.00014943258,0.0005677587,0.0002727557],"domain_scores_gemma":[0.99888706,0.00022199759,0.00021654848,0.0002898618,0.00028403132,0.00010047525],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014460674,0.0001229931,0.00018138936,0.00056126557,0.0015200383,0.00031189175,0.0002455732,0.00013550077,0.00008135821],"category_scores_gemma":[0.0004376377,0.00013374658,0.0001281123,0.0013773324,0.000078712466,0.001184787,0.0000036906588,0.00022789392,0.0014977787],"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":[0.00001676264,0.00006494234,0.0005747884,0.00019424195,0.0001106478,0.0000015145621,0.10944794,0.70891064,0.000080936115,0.0006209283,0.00058160274,0.17939505],"study_design_scores_gemma":[0.0013944897,0.00011014798,0.007383763,0.0003263583,0.00016961011,0.000003439877,0.14904296,0.6732612,0.00021623155,0.00016050336,0.1672794,0.00065183965],"about_ca_topic_score_codex":0.0052773682,"about_ca_topic_score_gemma":0.0011079417,"teacher_disagreement_score":0.85943735,"about_ca_system_score_codex":0.00023908918,"about_ca_system_score_gemma":0.00018436917,"threshold_uncertainty_score":0.9997798},"labels":[],"label_agreement":null},{"id":"W4362554832","doi":"10.1145/3589762","title":"A Variational Neural Architecture for Skill-based Team Formation","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","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":"York University; University of Windsor; Toronto Metropolitan University","funders":"","keywords":"Computer science; Heuristics; Machine learning; Bayesian network; Task (project management); Set (abstract data type); Identification (biology); Artificial intelligence; Architecture; Artificial neural network; Range (aeronautics); Cover (algebra); Space (punctuation); Bayesian optimization; Theoretical computer science","score_opus":0.015551157534069838,"score_gpt":0.23988162223202208,"score_spread":0.22433046469795226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362554832","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":[0.0015622643,0.000004688746,0.9941448,0.0012305595,0.0011196431,0.00065640337,0.000057476907,0.000792671,0.00043147538],"genre_scores_gemma":[0.9846542,0.0000015084679,0.01412271,0.00047079436,0.00007263766,0.0003977493,0.00013950325,0.000010153605,0.00013076677],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986232,0.000059745456,0.00048788753,0.0001562526,0.0004008185,0.0002720883],"domain_scores_gemma":[0.99854374,0.00038241068,0.00019006286,0.00059241685,0.00021349596,0.000077868885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048985175,0.00015242842,0.00014609765,0.00057024276,0.0005159522,0.0004818828,0.00044059654,0.00009796273,0.000003453272],"category_scores_gemma":[0.00007888544,0.00014222547,0.00012382535,0.00077801896,0.00001379633,0.0016816579,0.000007298157,0.0001475559,0.00019699035],"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":[0.000020495263,0.00001991248,0.000004600421,0.00013150083,0.000015851543,2.777557e-7,0.002456943,0.9181817,0.000060433358,0.0039399927,0.0018578286,0.073310465],"study_design_scores_gemma":[0.0006704882,0.000089445064,0.00011702801,0.00005425543,0.000007840047,0.000023634435,0.00034480533,0.9674731,0.0005363458,0.0003612491,0.030151352,0.00017045847],"about_ca_topic_score_codex":0.00002041741,"about_ca_topic_score_gemma":0.0000027856224,"teacher_disagreement_score":0.9830919,"about_ca_system_score_codex":0.00008685628,"about_ca_system_score_gemma":0.0000758457,"threshold_uncertainty_score":0.57997864},"labels":[],"label_agreement":null},{"id":"W4382396965","doi":"10.1145/3606369","title":"Coarse-to-Fine Knowledge-Enhanced Multi-Interest Learning Framework for Multi-Behavior Recommendation","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Recommender Systems and Techniques","field":"Computer Science","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":"McGill University; Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Purchasing; Preference; Artificial intelligence; Machine learning","score_opus":0.12479876670118102,"score_gpt":0.3673304309339685,"score_spread":0.2425316642327875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382396965","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":[0.00071069517,0.000006431469,0.9917379,0.00067279994,0.0029798532,0.001851781,0.00004457816,0.0017588042,0.00023716877],"genre_scores_gemma":[0.75524133,0.000017327593,0.24012081,0.00012324838,0.00007342626,0.0033834004,0.00009849043,0.000027848768,0.0009141216],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99814326,0.00013454031,0.00085853715,0.00030719012,0.00018256818,0.0003738946],"domain_scores_gemma":[0.9981347,0.00035061958,0.00030603365,0.00070513034,0.0003535648,0.00014995418],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00080256717,0.00024931657,0.00030428774,0.00078783254,0.0005139184,0.00052484486,0.0007586097,0.00020720305,0.000011395623],"category_scores_gemma":[0.00015668671,0.00024433533,0.00014763579,0.0010566146,0.000013579381,0.001833327,0.000035954494,0.00033284078,0.00096668466],"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":[0.000038936374,0.00030531132,0.00006584321,0.0003555902,0.000086198525,7.927553e-7,0.011058863,0.0058313673,0.00048792688,0.011371262,0.0034133417,0.96698457],"study_design_scores_gemma":[0.0021908162,0.00071442587,0.00063488,0.0007649552,0.000034610195,0.000023680546,0.0033611916,0.71279013,0.010376273,0.00019823236,0.26796895,0.00094184844],"about_ca_topic_score_codex":0.000052590967,"about_ca_topic_score_gemma":0.000039513838,"teacher_disagreement_score":0.9660427,"about_ca_system_score_codex":0.00017155349,"about_ca_system_score_gemma":0.000047220896,"threshold_uncertainty_score":0.9998112},"labels":[],"label_agreement":null},{"id":"W4385780698","doi":"10.1145/3613447","title":"Toward Best Practices for Training Multilingual Dense Retrieval Models","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Topic Modeling","field":"Computer Science","cited_by":12,"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; Canada First Research Excellence Fund; Compute Canada","keywords":"Computer science; Transformer; Language model; Architecture; Encoder; Relevance (law); Natural language processing; Artificial intelligence; Transfer of learning; Training set; Information retrieval; Variety (cybernetics); Data science","score_opus":0.2134837990183883,"score_gpt":0.3481269699009422,"score_spread":0.13464317088255393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385780698","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":[0.007504959,0.000015934775,0.98795485,0.000755369,0.0016699877,0.000628518,0.00003830377,0.00060394855,0.0008281048],"genre_scores_gemma":[0.9672398,0.00002245314,0.03183729,0.00014261183,0.00009359882,0.00014523194,0.000020359625,0.000010975019,0.00048768552],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983472,0.000050189443,0.0005984201,0.00021650991,0.000482953,0.00030471277],"domain_scores_gemma":[0.9980779,0.0005123182,0.00039190237,0.00065923977,0.00026596163,0.000092636394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009457923,0.00014643479,0.00018145723,0.00039414503,0.00031997747,0.00050079083,0.0007458408,0.00012057057,0.0000019913348],"category_scores_gemma":[0.0002891851,0.0001458087,0.00009769045,0.0005747566,0.000015265854,0.004577052,0.000015380869,0.00017554242,0.00020487877],"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":[0.000051213072,0.000026296375,0.0000014284213,0.00018858789,0.000050079398,0.0000020402292,0.03348321,0.7803218,0.00007470679,0.0064497646,0.0000969495,0.17925397],"study_design_scores_gemma":[0.00053987524,0.000079848454,0.0000020103448,0.000053905263,0.000012601991,0.000027930471,0.006578961,0.9803803,0.00047136066,0.0005670862,0.011118516,0.00016760125],"about_ca_topic_score_codex":0.00011525138,"about_ca_topic_score_gemma":0.000004654075,"teacher_disagreement_score":0.95973486,"about_ca_system_score_codex":0.00007703271,"about_ca_system_score_gemma":0.00015884767,"threshold_uncertainty_score":0.59459066},"labels":[],"label_agreement":null},{"id":"W4391680357","doi":"10.1145/3640460","title":"Revisiting Bag of Words Document Representations for Efficient Ranking with Transformers","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"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":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Canadian Institute of Steel Construction","keywords":"Computer science; Transformer; Search engine indexing; Inference; ENCODE; Artificial intelligence; Question answering; Information retrieval; Machine learning; Natural language processing; Voltage","score_opus":0.01808328787664678,"score_gpt":0.2747271749205496,"score_spread":0.25664388704390284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391680357","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":[0.0025118857,0.000082314196,0.9940825,0.0006229039,0.0006710633,0.0007713886,0.00002121889,0.0002108096,0.001025911],"genre_scores_gemma":[0.9643445,0.000011994009,0.03523245,0.00003554615,0.00003523369,0.00025590687,0.000009307414,0.0000075176877,0.000067524445],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985862,0.000031670108,0.00062063814,0.00018148929,0.00040039048,0.00017961675],"domain_scores_gemma":[0.99897724,0.00026303006,0.00011424007,0.00045331233,0.00014428433,0.00004791402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005478102,0.00011781611,0.00015938948,0.00036590395,0.0001847407,0.00033578638,0.00033382003,0.00004549051,0.000005463615],"category_scores_gemma":[0.000016063495,0.00009823524,0.00010059636,0.000538689,0.000018510971,0.0014055751,0.000004399389,0.000109455345,0.000014239608],"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":[0.000018037896,0.000010171224,0.0000037930226,0.0006387458,0.00006666733,4.6604825e-7,0.007618749,0.77832764,0.000056879908,0.02665157,0.000010576122,0.18659668],"study_design_scores_gemma":[0.00057433575,0.00008955682,0.0000148129,0.0007390813,0.000037353355,0.00002763761,0.002190396,0.9892214,0.00150757,0.00016503084,0.005257777,0.00017504841],"about_ca_topic_score_codex":0.000054352415,"about_ca_topic_score_gemma":0.0000013721759,"teacher_disagreement_score":0.96183264,"about_ca_system_score_codex":0.00009506903,"about_ca_system_score_gemma":0.000091812006,"threshold_uncertainty_score":0.4005917},"labels":[],"label_agreement":null},{"id":"W4400650325","doi":"10.1145/3678003","title":"A Knowledge Graph Embedding Model for Answering Factoid Entity Questions","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Topic Modeling","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Question answering; Computer science; Embedding; Knowledge graph; Information retrieval; Graph; Artificial intelligence; Natural language processing; Theoretical computer science","score_opus":0.03891582147792144,"score_gpt":0.30215229729600357,"score_spread":0.2632364758180821,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400650325","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":[0.00056184997,0.00023946384,0.994743,0.00018782902,0.0021346172,0.00049290387,0.000058062757,0.00079462986,0.0007876737],"genre_scores_gemma":[0.94697034,0.000040470797,0.052178014,0.000039563864,0.00004823208,0.00035735106,0.000010857991,0.000010024831,0.0003451675],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988507,0.000025887584,0.0004792798,0.00021013383,0.00020707963,0.00022689195],"domain_scores_gemma":[0.99895394,0.0001443206,0.00005943039,0.0006137089,0.00014898751,0.00007963143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035821306,0.00014678108,0.00014018606,0.00051717815,0.00033853055,0.000814836,0.0005267646,0.00009136316,0.0000028977167],"category_scores_gemma":[0.000019120762,0.00014511384,0.0001386085,0.0004406696,0.0000135002565,0.003893112,0.00001306957,0.0001778155,0.000114025774],"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":[0.000002808842,0.000020619183,0.0000013246782,0.00030947805,0.00003543616,2.4345218e-7,0.0064926464,0.8569275,0.00009335052,0.07337823,0.00017778038,0.06256057],"study_design_scores_gemma":[0.00014313721,0.000023209666,0.0000022272857,0.00016104773,0.000008821325,0.000011725178,0.0001781528,0.9820682,0.00015828543,0.001387859,0.015705217,0.0001521597],"about_ca_topic_score_codex":0.000033916745,"about_ca_topic_score_gemma":0.0000067327846,"teacher_disagreement_score":0.94640845,"about_ca_system_score_codex":0.00013755307,"about_ca_system_score_gemma":0.00010221447,"threshold_uncertainty_score":0.78574824},"labels":[],"label_agreement":null},{"id":"W4400976991","doi":"10.1145/3681784","title":"A Self-Distilled Learning to Rank Model for <i>Ad Hoc</i> Retrieval","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Domain Adaptation and Few-Shot Learning","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":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Outlier; Generalizability theory; Artificial intelligence; Rank (graph theory); Sample (material); Learning to rank; Machine learning; Feature (linguistics); Information retrieval; Ranking (information retrieval); Statistics; Mathematics","score_opus":0.022097195304718847,"score_gpt":0.2622081396623819,"score_spread":0.24011094435766303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400976991","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":[0.00026729115,0.00009471478,0.9937084,0.0008697131,0.0010187322,0.0008037264,0.000024088302,0.001359794,0.0018535518],"genre_scores_gemma":[0.8389747,0.000055906832,0.15608843,0.0006704983,0.000043074313,0.00029710482,0.000024291265,0.000024363864,0.0038216012],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99838614,0.000057373247,0.00057000184,0.0002490365,0.00045210755,0.00028532624],"domain_scores_gemma":[0.9988051,0.00027786923,0.00009666008,0.00045241663,0.00020887873,0.0001590622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007571656,0.00018159545,0.00019959464,0.00048641875,0.00042632566,0.0010362135,0.0005342453,0.00010414209,0.0000063684965],"category_scores_gemma":[0.00010915769,0.00017640431,0.00014759599,0.0007757084,0.00001117228,0.002229187,0.000012976018,0.000288687,0.0005349277],"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":[0.00005951944,0.000016516668,3.342607e-7,0.000217428,0.000043456523,5.7337803e-7,0.017862447,0.93750036,0.000058031404,0.008124456,0.0006562927,0.0354606],"study_design_scores_gemma":[0.0004070643,0.00009349841,0.000001275327,0.00007635504,0.000013290037,0.000011034923,0.0005809619,0.82602245,0.000059123257,0.000119211145,0.17243972,0.00017599904],"about_ca_topic_score_codex":0.000002282386,"about_ca_topic_score_gemma":0.0000011482798,"teacher_disagreement_score":0.83870745,"about_ca_system_score_codex":0.00016306507,"about_ca_system_score_gemma":0.00017793875,"threshold_uncertainty_score":0.9992231},"labels":[],"label_agreement":null},{"id":"W4405553425","doi":"10.1145/3704438","title":"The In-Situ Effect of Offensive Ads on Search Engine Users","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Digital Communication and Language","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":"Microsoft (Canada)","funders":"","keywords":"Offensive; In situ; Advertising; Computer science; Business; Engineering; Chemistry; Operations research","score_opus":0.013390246452844907,"score_gpt":0.26318151220803726,"score_spread":0.24979126575519237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405553425","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":[0.08667963,0.00079011754,0.7093149,0.004055234,0.0024515851,0.0020086933,0.000058581605,0.0007712136,0.19387008],"genre_scores_gemma":[0.9994227,0.00002896027,0.000072908,0.0000688246,0.000005002303,0.000053027754,0.0000062768067,0.0000037773743,0.00033851297],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99907064,0.00012237784,0.00031211643,0.00007720135,0.00029785608,0.000119815646],"domain_scores_gemma":[0.9982007,0.0008671094,0.000041431158,0.00079356926,0.00006273103,0.00003441751],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058772607,0.00008578094,0.000104053186,0.00028088607,0.00009371112,0.00036475208,0.00069082656,0.000040911087,0.0000029423832],"category_scores_gemma":[0.000035504083,0.00005654865,0.000062647596,0.0005504865,0.000027939535,0.00094365014,0.000013375441,0.00020023773,0.00029943598],"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":[0.000115172115,0.00006655037,0.000024235287,0.00059429236,0.00012754013,0.0000053063827,0.012543078,0.04360005,0.00025738482,0.07752235,0.0012200152,0.863924],"study_design_scores_gemma":[0.0031547325,0.0031476724,0.0027213702,0.0025967262,0.000041174048,0.0001174251,0.008864876,0.28343114,0.0643397,0.00018138684,0.63039166,0.0010121526],"about_ca_topic_score_codex":0.000054785603,"about_ca_topic_score_gemma":0.000010948964,"teacher_disagreement_score":0.9127431,"about_ca_system_score_codex":0.00006321636,"about_ca_system_score_gemma":0.000035606852,"threshold_uncertainty_score":0.38487437},"labels":[],"label_agreement":null},{"id":"W4408930227","doi":"10.1145/3726864","title":"Enhancing Sequential Personalized Product Search with External Out-of-sequence Knowledge","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Recommender Systems and 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":"Université de Montréal; Hôtel-Dieu de Montréal","funders":"National Natural Science Foundation of China","keywords":"Sequence (biology); Product (mathematics); Computer science; Information retrieval; Computational biology; Mathematics; Biology; Genetics","score_opus":0.04322400138114205,"score_gpt":0.3138986129252901,"score_spread":0.270674611544148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408930227","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":[0.0013946687,0.00010553884,0.9903578,0.00019886973,0.0012535835,0.0006195656,0.00001037387,0.0002513821,0.005808213],"genre_scores_gemma":[0.97784835,0.000019553672,0.020834202,0.0000459746,0.0000318974,0.0001762549,0.0000033955762,0.0000055532037,0.0010348338],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99844384,0.00014677297,0.00062019454,0.00020824256,0.00036526096,0.0002156745],"domain_scores_gemma":[0.9984811,0.000092755145,0.00018253548,0.000801015,0.0003874195,0.0000551746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007228627,0.00016113615,0.00025175896,0.00046548454,0.00021137517,0.00028079285,0.00079739164,0.000065541084,0.000007678224],"category_scores_gemma":[0.000013224272,0.00013086868,0.00007939247,0.00058083254,0.000054540884,0.0018596152,0.000021035907,0.00019914519,0.00004389772],"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":[0.0003571369,0.0006513069,0.0007146366,0.005919809,0.00085958245,0.000011536568,0.06782683,0.006142208,0.02632988,0.33489874,0.0013612043,0.5549271],"study_design_scores_gemma":[0.0053247446,0.0013648331,0.0006646619,0.008433251,0.00013282635,0.0003167779,0.0069326116,0.069035985,0.7332619,0.0012736806,0.17137119,0.0018875777],"about_ca_topic_score_codex":0.00025669287,"about_ca_topic_score_gemma":0.000026082378,"teacher_disagreement_score":0.97645366,"about_ca_system_score_codex":0.00013959773,"about_ca_system_score_gemma":0.00028157246,"threshold_uncertainty_score":0.53366697},"labels":[],"label_agreement":null},{"id":"W4410502462","doi":"10.1145/3736402","title":"Query Performance Prediction Using Relevance Judgments Generated by Large Language Models","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Information Retrieval and Search Behavior","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":"HORIZON EUROPE Framework Programme; Ministerie van Economische Zaken en Klimaat; China Scholarship Council; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Ministerie van Onderwijs, Cultuur en Wetenschap; European Commission","keywords":"Relevance (law); Computer science; Interpretability; Recall; Metric (unit); Measure (data warehouse); Precision and recall; Scalar (mathematics); Information retrieval; Data mining; Machine learning; Artificial intelligence; Cognitive psychology; Mathematics; Psychology","score_opus":0.021212261811749022,"score_gpt":0.26395895870168035,"score_spread":0.24274669688993133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410502462","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":[0.06238215,0.00006102789,0.9336707,0.0000945575,0.0011203001,0.00049384264,0.00017783054,0.0003198308,0.001679754],"genre_scores_gemma":[0.99515665,0.00008632135,0.0028066216,0.00046139295,0.000017189503,0.00010627474,0.00010178856,0.000005908267,0.0012578696],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982315,0.000065897766,0.00068848394,0.00016048415,0.0005349883,0.00031865342],"domain_scores_gemma":[0.9987402,0.000047577774,0.00017998929,0.0006560065,0.00029675078,0.00007949092],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004519051,0.00017311552,0.00016783562,0.00044617787,0.0005468149,0.0004453083,0.0005874636,0.00013319236,0.000012013393],"category_scores_gemma":[0.000019317225,0.00016403885,0.000062925385,0.00095934526,0.000020290325,0.0080218185,0.000021737058,0.000250524,0.00011564778],"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":[0.00017295312,0.00042907684,0.00039385748,0.0009313038,0.00020848945,0.0000024489068,0.012310266,0.79805344,0.0037051497,0.016200598,0.007690731,0.15990166],"study_design_scores_gemma":[0.00070708175,0.000050931052,0.000094700285,0.0001228169,0.000011404626,0.000008232812,0.0005216417,0.98138934,0.0061232005,0.000020583662,0.010787408,0.00016266656],"about_ca_topic_score_codex":0.00007522427,"about_ca_topic_score_gemma":0.0000011824106,"teacher_disagreement_score":0.9327745,"about_ca_system_score_codex":0.00025681377,"about_ca_system_score_gemma":0.00013419948,"threshold_uncertainty_score":0.668931},"labels":[],"label_agreement":null},{"id":"W4411644201","doi":"10.1145/3742423","title":"Utilizing Large Language Model for Conversational Information Seeking via Dual-Query Generation and Joint-Encoding","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; Western University","funders":"","keywords":"Computer science; Encoding (memory); Joint (building); Dual (grammatical number); Natural language processing; Language model; Artificial intelligence; Linguistics; Engineering","score_opus":0.033160082311940495,"score_gpt":0.2612312934812345,"score_spread":0.22807121116929402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411644201","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":[0.0031525576,0.000025565718,0.9938998,0.00044416697,0.0008442985,0.0006099224,0.000046289097,0.00020418782,0.00077317015],"genre_scores_gemma":[0.9656764,0.000009591732,0.033219468,0.00068733457,0.00003865819,0.00018143564,0.00008929903,0.0000039847123,0.00009381293],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866617,0.00003570917,0.00067639526,0.00014532641,0.00027108096,0.00020532073],"domain_scores_gemma":[0.99900556,0.00009940778,0.00021454002,0.00040488728,0.00022723182,0.000048352056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006654394,0.00013965808,0.00015907314,0.0005334285,0.00047755058,0.0005145292,0.00018504307,0.000111033565,0.0000023375305],"category_scores_gemma":[0.000065532484,0.00014771489,0.00006061698,0.0002527896,0.0000121249195,0.0064121573,0.000020147223,0.00013118648,0.000015755453],"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":[0.000024912817,0.000037335525,0.00005794761,0.00072688976,0.00009813172,3.300356e-7,0.032523353,0.6822756,0.002049417,0.1859357,0.0003837042,0.09588668],"study_design_scores_gemma":[0.00064178125,0.000013848904,0.000025725885,0.00006588036,0.000011427746,0.000007803206,0.0016823558,0.99521184,0.00074616814,0.00029351175,0.0011657594,0.00013387266],"about_ca_topic_score_codex":0.00003284104,"about_ca_topic_score_gemma":0.0000063040607,"teacher_disagreement_score":0.9625239,"about_ca_system_score_codex":0.00014290628,"about_ca_system_score_gemma":0.00010590052,"threshold_uncertainty_score":0.6023639},"labels":[],"label_agreement":null},{"id":"W4413243547","doi":"10.1145/3759453","title":"A Survey of Conversational Search","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Topic Modeling","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":"Université de Montréal","funders":"","keywords":"Computer science; Semantic search; Context (archaeology); Unison; Search engine; Natural language; Data science; Human–computer interaction; World Wide Web; Information retrieval; Artificial intelligence","score_opus":0.0433947417254156,"score_gpt":0.28226504420324516,"score_spread":0.23887030247782956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413243547","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":[0.0033127973,0.000013859898,0.99337155,0.0002798527,0.0006574129,0.00018204298,0.000026539716,0.00006442662,0.002091526],"genre_scores_gemma":[0.995971,0.0000038974804,0.0037031514,0.000103428036,0.0000041275875,0.00002145909,0.000011233549,0.0000011870834,0.00018047125],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906737,0.00008351748,0.00039377026,0.000082026076,0.00028076585,0.00009257338],"domain_scores_gemma":[0.9988011,0.00023231018,0.00007203894,0.0005285759,0.00034010605,0.000025844343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000602113,0.000057987407,0.00010234836,0.0003184773,0.00008474823,0.00008712861,0.0004986364,0.000049073376,0.000007804228],"category_scores_gemma":[0.000045439203,0.000057172965,0.000031347885,0.0005282895,0.000017051949,0.0010100158,0.000009812542,0.000088222856,0.000060301045],"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":[0.00005299033,0.0001261607,0.004963432,0.00054551905,0.00020462227,4.149145e-7,0.0064253653,0.5541232,0.000082104736,0.1969564,0.00076007255,0.23575972],"study_design_scores_gemma":[0.0007223128,0.000043020602,0.02323084,0.00009267439,0.000005657038,0.0000033583644,0.00043583685,0.9708231,0.0013994504,0.00022313253,0.0028831863,0.00013739835],"about_ca_topic_score_codex":0.00079954654,"about_ca_topic_score_gemma":0.00001020493,"teacher_disagreement_score":0.99265826,"about_ca_system_score_codex":0.000054637574,"about_ca_system_score_gemma":0.00017041212,"threshold_uncertainty_score":0.23314458},"labels":[],"label_agreement":null},{"id":"W4413418666","doi":"10.1145/3748719","title":"SparseFraudNet: A Graph-based Approach for Cold-start Fraud Detection with Information Aggregation","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Spectral clustering; Leverage (statistics); Graph; Cluster analysis; Adjacency matrix; Purchasing; Data mining; Machine learning; Artificial intelligence; Theoretical computer science","score_opus":0.0131978670232608,"score_gpt":0.21174336607158148,"score_spread":0.19854549904832067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413418666","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":[0.0011033408,0.000015791124,0.99384,0.00021046892,0.0012299562,0.0016413307,0.00003841068,0.00055446825,0.0013662769],"genre_scores_gemma":[0.96981823,0.00000538371,0.02816686,0.0005038159,0.00003305302,0.0012970949,0.00009225957,0.000008087648,0.000075226366],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983416,0.00007357943,0.00065525575,0.00020925392,0.00045636774,0.0002638989],"domain_scores_gemma":[0.9980889,0.00016616377,0.0003629606,0.00079629687,0.0005092083,0.00007646008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005269806,0.00023474205,0.00021381969,0.0011357912,0.0006479564,0.0008213211,0.0005080948,0.0002041384,0.0000024531005],"category_scores_gemma":[0.000050663934,0.00021645222,0.000114524184,0.0015317311,0.000036065652,0.0062305843,0.0000062593276,0.00022012109,0.000042671443],"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":[0.00046111972,0.00015882301,0.00006558291,0.0008484174,0.0001690651,1.8322112e-7,0.0020235723,0.78992283,0.00032762243,0.0118596135,0.0008413796,0.19332181],"study_design_scores_gemma":[0.0031295372,0.00066487637,0.00020806567,0.0002164968,0.000066757355,0.000013661931,0.00071636675,0.8956008,0.030987607,0.0004005025,0.06751353,0.00048178024],"about_ca_topic_score_codex":0.00016627635,"about_ca_topic_score_gemma":0.000021022479,"teacher_disagreement_score":0.9687149,"about_ca_system_score_codex":0.00022494972,"about_ca_system_score_gemma":0.00016210013,"threshold_uncertainty_score":0.88266647},"labels":[],"label_agreement":null}]}