{"meta":{"query_hash":"f029b2e5f93c","filters":{"venue":"Data & Knowledge Engineering"},"cohort_total":41,"direct_labels_cover":1,"predictions_cover":41,"exported":41,"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/f029b2e5f93c","api":"https://metacan.xera.ac/api/v1/cohort?venue=Data+%26+Knowledge+Engineering"},"results":[{"id":"W1966678916","doi":"10.1016/j.datak.2009.08.006","title":"Sorting improves word-aligned bitmap indexes","year":2009,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":74,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick; Université du Québec à Montréal","funders":"","keywords":"Bitmap; Lexicographical order; Sorting; Sorting algorithm; sort; Aggregate (composite); Table (database); Construct (python library); Simple (philosophy)","score_opus":0.02252072736554118,"score_gpt":0.27281816931913383,"score_spread":0.25029744195359266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966678916","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":[0.0014297736,0.00078045146,0.9941354,0.00016064668,0.0003123985,0.00009957775,0.000004366862,0.0017673622,0.0013100595],"genre_scores_gemma":[0.33251774,0.000034390257,0.66680604,0.00009733884,0.00026873185,0.000005699797,0.00006395108,0.000019115452,0.00018699297],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987097,0.000021731694,0.000296135,0.0004921056,0.00012977149,0.0003505597],"domain_scores_gemma":[0.9985397,0.000073024836,0.000075985845,0.0011580636,0.0000577831,0.0000954554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004061922,0.0001899172,0.00018655547,0.00019939311,0.00010601221,0.00023403927,0.0020356565,0.00007091455,0.0000029029125],"category_scores_gemma":[0.00018475433,0.00019438686,0.000029469024,0.0005443951,0.0000100281095,0.0007921478,0.00067369296,0.00013174009,0.00003422016],"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":[0.000002791918,0.00013025173,0.00006156053,0.000049617884,0.00003108665,0.000015164579,0.00085218693,0.004067713,0.016354974,0.018820988,0.010556758,0.9490569],"study_design_scores_gemma":[0.00010904107,0.000033635697,0.00048729268,0.00005838272,0.000003827007,0.0000068220647,0.000003008361,0.98883384,0.0038617565,0.00041937266,0.0059246398,0.0002583974],"about_ca_topic_score_codex":0.00000355147,"about_ca_topic_score_gemma":0.000001067666,"teacher_disagreement_score":0.9847661,"about_ca_system_score_codex":0.000030414989,"about_ca_system_score_gemma":0.00004339328,"threshold_uncertainty_score":0.7926866},"labels":[],"label_agreement":null},{"id":"W1983768816","doi":"10.1016/s0169-023x(02)00133-7","title":"Optimizing temporal queries: efficient handling of duplicates","year":2002,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; SQL; Query language; Query optimization; Query by Example; Relational database; Temporal database; Semantics (computer science); Expressive power; Context (archaeology); Sargable; Information retrieval; Programming language; Database; Web search query; Search engine","score_opus":0.038932829926481824,"score_gpt":0.24963580992641615,"score_spread":0.21070297999993431,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983768816","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":[0.002597634,0.004951668,0.99105537,0.000030483317,0.0004519214,0.0001146523,0.00011728258,0.0002551437,0.00042582798],"genre_scores_gemma":[0.24701671,0.00007795201,0.7524112,0.000006976171,0.00018422169,0.000019541312,0.00012054651,0.00003151137,0.00013134349],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987204,0.000015209714,0.00035800785,0.0004596657,0.0001454366,0.0003012916],"domain_scores_gemma":[0.9981726,0.000116397256,0.00009292264,0.001461944,0.00006450477,0.00009163408],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002660633,0.00018360205,0.00026458476,0.0001307764,0.00008080752,0.000043909964,0.0010330449,0.00004202917,0.000016600197],"category_scores_gemma":[0.00014434161,0.00017575844,0.000038174745,0.00041626472,0.000033445915,0.0007169941,0.0010717625,0.0001246381,0.000049939616],"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":[0.000021951062,0.0011953537,0.00095489336,0.003318026,0.00041658402,0.00014818803,0.026172785,0.16430269,0.074234806,0.40812358,0.012063931,0.30904722],"study_design_scores_gemma":[0.00013552095,0.000015627682,0.00001851232,0.00014528379,0.0000041427734,0.00001045516,0.000044928212,0.91735476,0.0031905174,0.0000022201773,0.07889098,0.00018702894],"about_ca_topic_score_codex":0.000019547597,"about_ca_topic_score_gemma":0.000006012369,"teacher_disagreement_score":0.7530521,"about_ca_system_score_codex":0.000027239257,"about_ca_system_score_gemma":0.000016280657,"threshold_uncertainty_score":0.7167221},"labels":[],"label_agreement":null},{"id":"W1984778493","doi":"10.1016/j.datak.2010.01.005","title":"The consistency extractor system: Answer set programs for consistent query answering in databases","year":2010,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Logic, Reasoning, and Knowledge","field":"Computer Science","cited_by":82,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Datalog; Answer set programming; Database theory; Consistency (knowledge bases); Extractor; Programming language; Relational database; Deductive database; Set (abstract data type); Information retrieval; Database; Artificial intelligence","score_opus":0.055622060533341455,"score_gpt":0.2879527423906523,"score_spread":0.23233068185731087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984778493","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":[0.07192456,0.013703249,0.8768162,0.00025925133,0.021990944,0.0041193445,0.00095965335,0.002587637,0.0076391236],"genre_scores_gemma":[0.94101304,0.00006540693,0.057107087,0.000012289365,0.0006653691,0.00035537605,0.0005393531,0.00006540387,0.00017668738],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99756354,0.00006342433,0.00054962747,0.0008498347,0.00019968249,0.00077391946],"domain_scores_gemma":[0.9960417,0.0010877623,0.00011443063,0.0023822088,0.00017122335,0.0002026791],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017158418,0.0003577741,0.00038323514,0.00014729596,0.00028536725,0.00044770236,0.002568144,0.00011227165,0.0000032407934],"category_scores_gemma":[0.0008591687,0.00027721483,0.00009797751,0.00044913215,0.0000981108,0.0009895324,0.0010931254,0.00047985232,0.00004680631],"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":[0.000066834604,0.00084574346,0.009182418,0.003307548,0.0003199284,0.00015098094,0.003266337,0.00006354248,0.0190269,0.62732846,0.011394652,0.32504663],"study_design_scores_gemma":[0.0007315585,0.000051555013,0.0021815414,0.00040603714,0.000031662927,0.00009638934,0.00026393455,0.64995944,0.0008074042,0.00003382256,0.34482095,0.00061568664],"about_ca_topic_score_codex":0.000052428542,"about_ca_topic_score_gemma":0.0011901414,"teacher_disagreement_score":0.8690885,"about_ca_system_score_codex":0.000083063474,"about_ca_system_score_gemma":0.00021998801,"threshold_uncertainty_score":0.999968},"labels":[],"label_agreement":null},{"id":"W2002413229","doi":"10.1016/j.datak.2012.09.005","title":"Comparing functionality of software systems: An ontological approach","year":2012,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Software system; Software engineering; Adaptation (eye); Function (biology); USable; Software development; Software; Software metric; Software quality; Point (geometry); Software construction; Function point; Quality (philosophy); Software sizing; World Wide Web; Programming language","score_opus":0.13962881508491679,"score_gpt":0.31436609711026914,"score_spread":0.17473728202535235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002413229","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":[0.050819542,0.002733613,0.9443146,0.000003117107,0.0010350482,0.00015680262,0.00003434524,0.00071727665,0.00018566234],"genre_scores_gemma":[0.8515052,0.0000040100645,0.14789876,0.0000016997009,0.0003381411,0.000027243761,0.00017904634,0.000021680273,0.000024228288],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99816346,0.00007482049,0.00033880974,0.0004797511,0.00036604452,0.0005771198],"domain_scores_gemma":[0.9971197,0.0005820525,0.00005219298,0.00183882,0.00011495168,0.00029223404],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013693817,0.00021068557,0.00034183214,0.00018225258,0.000059803988,0.0000933281,0.0023746036,0.000105337545,0.0000061920264],"category_scores_gemma":[0.0010511217,0.00020369042,0.000040267685,0.00052893336,0.000032479446,0.0016311125,0.0013940736,0.0003245126,0.00004028163],"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":[0.00003072188,0.0029669537,0.80337745,0.0036190979,0.00046960864,0.000016335784,0.003398962,0.044443265,0.0020116428,0.09199996,0.005686636,0.041979395],"study_design_scores_gemma":[0.00016152333,0.00002488301,0.11266162,0.000041775245,0.000007931992,0.000036526435,0.00002255839,0.8826084,0.000081614584,0.000003846496,0.0041119987,0.00023731479],"about_ca_topic_score_codex":0.000033079978,"about_ca_topic_score_gemma":0.0000013776339,"teacher_disagreement_score":0.83816516,"about_ca_system_score_codex":0.00010037035,"about_ca_system_score_gemma":0.00005193785,"threshold_uncertainty_score":0.8306254},"labels":[],"label_agreement":null},{"id":"W2011939484","doi":"10.1016/j.datak.2014.09.004","title":"Privacy-preserving trajectory stream publishing","year":2014,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Data publishing; Trajectory; Computer science; Publishing; Internet privacy; World Wide Web; Political science; Law; Physics","score_opus":0.04019297403125713,"score_gpt":0.2642967261602062,"score_spread":0.2241037521289491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011939484","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":[0.0041553252,0.0010022619,0.9807773,0.003501168,0.0016045424,0.00019217527,0.00011562164,0.004089155,0.0045624543],"genre_scores_gemma":[0.14764786,0.000053584627,0.85099816,0.000069532376,0.00059829414,0.00003205697,0.00044516625,0.0000809137,0.00007444621],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969972,0.00008499795,0.00044389465,0.0012470597,0.00039742343,0.00082947523],"domain_scores_gemma":[0.96985626,0.000722671,0.00012520255,0.02896617,0.00011148245,0.00021821076],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0016962532,0.00037174884,0.00034518482,0.00042683238,0.00016086474,0.0014160834,0.104983486,0.00022742167,0.000025397278],"category_scores_gemma":[0.07867241,0.00039445356,0.00005714437,0.0010485267,0.000046565034,0.008616095,0.25783485,0.00080855493,0.0001391097],"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":[0.000002123328,0.0001060245,0.0005003645,0.0002149204,0.000069613394,0.000015769372,0.00022794923,0.00008923356,0.0024608718,0.0077742487,0.6205953,0.3679436],"study_design_scores_gemma":[0.00022816568,0.000020235271,0.0007669864,0.00011649064,0.000008022851,0.0000137078005,0.000010992448,0.8619301,0.0012850788,0.0032129735,0.13200969,0.0003975806],"about_ca_topic_score_codex":0.000039956638,"about_ca_topic_score_gemma":0.000025136776,"teacher_disagreement_score":0.86184084,"about_ca_system_score_codex":0.00013183327,"about_ca_system_score_gemma":0.00008496379,"threshold_uncertainty_score":0.99985075},"labels":[],"label_agreement":null},{"id":"W2017416607","doi":"10.1016/j.datak.2009.01.003","title":"Formalizing visibility characteristics in hierarchical systems","year":2009,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Service-Oriented Architecture and Web Services","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Visibility; Hierarchy; Computer science; Theoretical computer science; Coherence (philosophical gambling strategy); Artificial intelligence; Mathematics; Physics; Statistics; Optics","score_opus":0.019145620733663993,"score_gpt":0.2609460380770489,"score_spread":0.24180041734338492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017416607","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":[0.16203132,0.0017636706,0.83117,0.00033387326,0.0018263527,0.0003761205,0.00008502795,0.0006881411,0.0017254968],"genre_scores_gemma":[0.9837616,0.000019588075,0.01558434,0.00011569727,0.00032296224,0.0000068279855,0.00016708986,0.000012332583,0.000009541006],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984106,0.000042051564,0.0003964002,0.00054433924,0.00016917025,0.00043745717],"domain_scores_gemma":[0.9982147,0.00012261755,0.000051168034,0.0014390241,0.000040333663,0.00013212464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000527021,0.0002010575,0.0002667981,0.0002186032,0.00005572465,0.00019707195,0.0021986116,0.00007555151,0.0000019501838],"category_scores_gemma":[0.000041993586,0.00019259567,0.000028933755,0.0006351797,0.000007672624,0.00089805963,0.00071557675,0.0003372356,0.000036001704],"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":[0.000040342886,0.00082732004,0.0066812057,0.0012364046,0.000072279545,0.0002254987,0.012608049,0.0013930782,0.007894601,0.15863508,0.0004590367,0.8099271],"study_design_scores_gemma":[0.0001933716,0.00003459278,0.023616899,0.00014225913,0.0000037306204,0.000019042109,0.000019695963,0.9588424,0.000112722,0.00008938282,0.01669744,0.00022845992],"about_ca_topic_score_codex":0.00003137715,"about_ca_topic_score_gemma":0.000032541404,"teacher_disagreement_score":0.9574493,"about_ca_system_score_codex":0.000047070876,"about_ca_system_score_gemma":0.00004401094,"threshold_uncertainty_score":0.7853824},"labels":[],"label_agreement":null},{"id":"W2025155398","doi":"10.1016/j.datak.2009.10.001","title":"Skyline queries with constraints: Integrating skyline and traditional query operators","year":2009,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Skyline; Computer science; Pruning; Class (philosophy); Space (punctuation); Operator (biology); Database; Computation; Information retrieval; Data mining; Theoretical computer science; Algorithm; Artificial intelligence","score_opus":0.027096740140654725,"score_gpt":0.23442299360009852,"score_spread":0.2073262534594438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025155398","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":[0.0030807725,0.00059033884,0.99320185,0.00045973842,0.00028127333,0.00013776816,0.00025567508,0.0003344732,0.001658136],"genre_scores_gemma":[0.25622475,0.00010808918,0.74036884,0.000253862,0.0006895861,0.00001555769,0.0020993978,0.00003117584,0.00020873712],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998889,0.00001512692,0.00021296977,0.0004796399,0.00014702673,0.00025618522],"domain_scores_gemma":[0.9990953,0.00007184409,0.00003580853,0.00064642925,0.00004592728,0.00010467745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003073956,0.00020863363,0.00018410753,0.0001378957,0.00009571339,0.0003540949,0.00097583025,0.000034405446,0.00001554127],"category_scores_gemma":[0.00008187606,0.00017580668,0.000014560957,0.00034033132,0.000063260464,0.0021840166,0.00036381307,0.00016657398,0.000010105253],"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":[0.0000054474717,0.00015517803,0.000119232995,0.00007108259,0.00007234331,0.00007777423,0.00052432035,0.00008383017,0.0006018363,0.27365872,0.0057377187,0.7188925],"study_design_scores_gemma":[0.00044495863,0.000118150594,0.0011054002,0.00016627103,0.000014641643,0.000055877503,0.00009188385,0.96962327,0.00023560553,0.00013103483,0.027638927,0.00037397473],"about_ca_topic_score_codex":0.0000036978965,"about_ca_topic_score_gemma":0.000014255083,"teacher_disagreement_score":0.96953946,"about_ca_system_score_codex":0.000020859288,"about_ca_system_score_gemma":0.000044921882,"threshold_uncertainty_score":0.7169188},"labels":[],"label_agreement":null},{"id":"W2036207056","doi":"10.1016/s0169-023x(01)00018-0","title":"Using information extraction and natural language generation to answer e-mail","year":2001,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"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; Natural language generation; Question answering; Domain (mathematical analysis); Natural language; Information extraction; Text messaging; Natural language processing; Frequently asked questions; Information retrieval; World Wide Web; Artificial intelligence","score_opus":0.03129771263752603,"score_gpt":0.3164762397476485,"score_spread":0.2851785271101225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036207056","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":[0.023318725,0.004158417,0.9712756,0.00005312577,0.0005576073,0.000113761234,0.0000072753332,0.00043968082,0.00007579325],"genre_scores_gemma":[0.2765829,0.00001457203,0.7229263,0.000077950055,0.00023276692,0.000005168913,0.00011716842,0.000007610902,0.000035568748],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993882,0.000010721442,0.00014304553,0.00020316098,0.00010288091,0.00015198252],"domain_scores_gemma":[0.99938554,0.000017079808,0.000034200722,0.00043803063,0.000065353815,0.00005982883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018837734,0.00010942085,0.00007888849,0.00020541488,0.000064691216,0.0002863805,0.00048139546,0.000048277612,0.0000023686264],"category_scores_gemma":[0.00012841779,0.00010784633,0.00000921354,0.00035297323,0.00000464776,0.003971684,0.00040686768,0.00014014663,0.000014352704],"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":[0.0000020677767,0.000012350339,0.000027501603,0.00003648796,0.00000532258,0.0000058321243,0.0009981478,0.000060670816,0.09440889,0.0015502523,0.0009414354,0.901951],"study_design_scores_gemma":[0.000055086726,0.0000075858197,0.00007144889,0.000041829186,0.0000038169,0.00007834158,0.000019648318,0.9758386,0.007577732,0.000014620823,0.016139712,0.00015157762],"about_ca_topic_score_codex":0.000031215925,"about_ca_topic_score_gemma":0.000018429955,"teacher_disagreement_score":0.9757779,"about_ca_system_score_codex":0.00006879753,"about_ca_system_score_gemma":0.000036314636,"threshold_uncertainty_score":0.4397846},"labels":[],"label_agreement":null},{"id":"W2043640532","doi":"10.1016/j.datak.2004.12.009","title":"Complexity and clarity in conceptual modeling: Comparison of mandatory and optional properties","year":2005,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":239,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"CLARITY; Computer science; Grammar; Cognitive psychology; Natural language processing; Rule-based machine translation; Domain (mathematical analysis); Domain model; Linguistics; Psychology; Artificial intelligence; Domain knowledge; Mathematics","score_opus":0.20680406000893842,"score_gpt":0.32137278644686057,"score_spread":0.11456872643792215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043640532","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76497674,0.007917881,0.22662848,0.00011092579,0.00009631587,0.000081466824,0.000019007695,0.00007051418,0.00009866662],"genre_scores_gemma":[0.9417224,0.00003368832,0.05817609,0.000005983918,0.000037928665,0.0000022491479,0.000014338066,0.0000033635513,0.0000039508786],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993191,0.000017755212,0.00020257568,0.00024588706,0.00007966129,0.00013502908],"domain_scores_gemma":[0.9995532,0.000045790992,0.000023112223,0.00031169437,0.00002732104,0.00003889999],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022731925,0.000090860296,0.00019190343,0.00006981372,0.000030331443,0.000035049445,0.00044319627,0.00004317294,0.0000016855126],"category_scores_gemma":[0.00006103815,0.00008423061,0.000007758743,0.00007380784,0.000098799785,0.00050276896,0.00069804356,0.0001259648,0.0000018436409],"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":[0.00007647307,0.0012621725,0.109571345,0.0013266336,0.00016280422,0.000014454936,0.040123455,0.034899175,0.01074694,0.48067918,0.001644273,0.3194931],"study_design_scores_gemma":[0.0002241891,0.00001411962,0.008797843,0.000043449127,0.0000027380822,0.0000044728563,0.00014429378,0.9894146,0.00027508373,0.000056739955,0.0009252313,0.000097248085],"about_ca_topic_score_codex":0.000025885154,"about_ca_topic_score_gemma":0.00012166952,"teacher_disagreement_score":0.9545154,"about_ca_system_score_codex":0.000014995519,"about_ca_system_score_gemma":0.000025726644,"threshold_uncertainty_score":0.34348246},"labels":[],"label_agreement":null},{"id":"W2052266824","doi":"10.1016/j.datak.2003.10.007","title":"Conceptual construction on incomplete survey data","year":2003,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Data mining; Knowledge extraction; Raw data; Data science; Conceptual model; Set (abstract data type); Information retrieval; Database","score_opus":0.15590708562556674,"score_gpt":0.294042282112188,"score_spread":0.1381351964866213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052266824","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":[0.0028790222,0.0007278628,0.98325014,0.000035012556,0.002946185,0.0001728783,0.0010273657,0.00038072478,0.0085808],"genre_scores_gemma":[0.5806437,0.000080645,0.41448203,0.000108523425,0.00041929688,0.000008864528,0.004140956,0.000048417754,0.0000675542],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99850553,0.00010769247,0.00022181828,0.0007022487,0.00015593601,0.00030675824],"domain_scores_gemma":[0.99645,0.000287786,0.00004468008,0.0030690632,0.000043217817,0.0001052216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089223945,0.00017997055,0.00018585288,0.000089021305,0.00008993988,0.00014893487,0.00303433,0.000058667418,0.000022207068],"category_scores_gemma":[0.0005768776,0.00017058986,0.000014764952,0.00040120003,0.00005079081,0.0008478516,0.0012833893,0.0002049535,0.00023996262],"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":[0.0000120169525,0.00028427245,0.0030275644,0.00006246833,0.00014427376,0.000051828698,0.0009497125,0.00083315815,0.00038955602,0.6539582,0.054395024,0.28589195],"study_design_scores_gemma":[0.00030404574,0.000041057236,0.003131385,0.000024978177,0.000005085279,0.00003075637,0.000021876547,0.7735812,0.000076487726,0.00008324466,0.2223892,0.00031067527],"about_ca_topic_score_codex":0.00002267289,"about_ca_topic_score_gemma":0.000030558527,"teacher_disagreement_score":0.77274805,"about_ca_system_score_codex":0.000031519463,"about_ca_system_score_gemma":0.000067664565,"threshold_uncertainty_score":0.6956453},"labels":[],"label_agreement":null},{"id":"W2068851374","doi":"10.1016/j.datak.2010.01.001","title":"Towards an accurate functional size measurement procedure for conceptual models in an MDA environment","year":2010,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Service-Oriented Architecture and Web Services","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Function point; Computer science; Measure (data warehouse); Function (biology); Software; Phase (matter); Data mining; Software development; Programming language; Physics","score_opus":0.061132141842537235,"score_gpt":0.2597888943664013,"score_spread":0.19865675252386406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068851374","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":[0.108279884,0.00032801976,0.88901335,0.00016802042,0.0011412206,0.00052750064,0.00014189824,0.0002474675,0.0001526434],"genre_scores_gemma":[0.91232187,0.000006483681,0.086520426,0.00012979866,0.0005215117,0.00013761566,0.0003209955,0.000032494198,0.000008829927],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982632,0.0000243781,0.00027110238,0.0007332951,0.00032213432,0.00038588714],"domain_scores_gemma":[0.9984378,0.00006717893,0.00005017115,0.0011656493,0.00008629303,0.00019287856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005664471,0.00024364343,0.0001899433,0.00010340827,0.000081675396,0.0001295642,0.0016407619,0.000094323565,0.000019460971],"category_scores_gemma":[0.00003568929,0.00023215736,0.000031452193,0.00020161217,0.000020203504,0.0018439944,0.0005500687,0.00029816036,0.000012906725],"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":[0.00021863088,0.002844686,0.00081519986,0.0010321819,0.00027410334,0.000028417338,0.043225437,0.20186563,0.27382496,0.14442548,0.0009635103,0.33048174],"study_design_scores_gemma":[0.00053970556,0.00008632302,0.0021719371,0.00002717863,0.000009343547,0.0000054443904,0.00011954764,0.9833861,0.0017857219,0.00042031452,0.01115142,0.00029694766],"about_ca_topic_score_codex":0.000023624496,"about_ca_topic_score_gemma":0.000792049,"teacher_disagreement_score":0.804042,"about_ca_system_score_codex":0.000051680297,"about_ca_system_score_gemma":0.00014015388,"threshold_uncertainty_score":0.9467102},"labels":[],"label_agreement":null},{"id":"W2073390485","doi":"10.1016/j.datak.2004.10.001","title":"Extracting conceptual relationships from specialized documents","year":2004,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Variety (cybernetics); Granularity; Data science; Conceptual model; Representation (politics); Management science; Scientific modelling; Conceptual framework; Knowledge management; Data mining; Artificial intelligence; Database; Engineering","score_opus":0.09260547872331132,"score_gpt":0.29443267366585935,"score_spread":0.20182719494254803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073390485","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":[0.045226768,0.0015549422,0.94818795,0.00015879073,0.0017338837,0.000109845816,0.00003510273,0.00054232834,0.002450418],"genre_scores_gemma":[0.6969708,0.000027963963,0.30211484,0.000019701007,0.000580465,0.0000074437894,0.00017450227,0.000017413526,0.00008682017],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989027,0.000029063014,0.0002354251,0.00042865795,0.00014177777,0.00026238663],"domain_scores_gemma":[0.9984938,0.00034430306,0.00005214657,0.0010020088,0.000029707622,0.000078049175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002833506,0.00014558506,0.00016486719,0.00007657996,0.00011825077,0.0001699179,0.0015329034,0.00006867087,0.000024015906],"category_scores_gemma":[0.0006263851,0.00014794197,0.000027762715,0.0002433347,0.000026102736,0.0013216534,0.00072264293,0.00025043826,0.00031884882],"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":[0.000024167848,0.0005462129,0.009373243,0.000089306086,0.0004235354,0.0003398249,0.028996397,0.0038302906,0.015466337,0.7027655,0.010271353,0.22787383],"study_design_scores_gemma":[0.0046044076,0.000067331224,0.055268917,0.0005065703,0.0000847317,0.000056001503,0.0014762117,0.6773693,0.010078223,0.009008997,0.23972246,0.0017568276],"about_ca_topic_score_codex":0.000102336395,"about_ca_topic_score_gemma":0.00007239211,"teacher_disagreement_score":0.6937565,"about_ca_system_score_codex":0.000067874964,"about_ca_system_score_gemma":0.00006319708,"threshold_uncertainty_score":0.60328984},"labels":[],"label_agreement":null},{"id":"W2073874433","doi":"10.1016/j.datak.2008.06.007","title":"Data privacy protection in multi-party clustering","year":2008,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"McMaster University","keywords":"Cluster analysis; Privacy protection; Internet privacy; Computer security; Data Protection Act 1998; Information privacy; Computer science; Business; Artificial intelligence","score_opus":0.1658117584570718,"score_gpt":0.31546151492775104,"score_spread":0.14964975647067924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073874433","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":[0.0044974317,0.00065880985,0.9910626,0.00073645794,0.00075692445,0.00036525857,0.00027622367,0.0015654572,0.00008084324],"genre_scores_gemma":[0.099145815,0.00015608956,0.8997742,0.000012062642,0.00011825305,0.000049560564,0.00066724926,0.000042244526,0.00003454068],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99757725,0.00004312829,0.00040483839,0.0012189735,0.00021044324,0.00054536056],"domain_scores_gemma":[0.9747198,0.00009631928,0.000074133284,0.024991037,0.00003646229,0.00008223722],"candidate_categories":["metaresearch","metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0007644065,0.00026406854,0.00025659674,0.0003642251,0.00011751867,0.0001141575,0.06090396,0.00014388876,0.0000053220842],"category_scores_gemma":[0.014865884,0.00028577406,0.000018764624,0.0010261962,0.000046843077,0.0037886642,0.25902072,0.0005897407,0.00012098059],"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":[0.000032227923,0.0014178554,0.004787031,0.0011502457,0.00020417241,0.00085892406,0.0020417294,0.0016070431,0.022871848,0.0006515019,0.29703104,0.66734636],"study_design_scores_gemma":[0.0003677415,0.0000130582985,0.0023694236,0.0001041274,0.0000027096673,0.00008420605,0.000005507284,0.96247953,0.00064041023,0.00008294012,0.033543333,0.00030702364],"about_ca_topic_score_codex":0.0000631491,"about_ca_topic_score_gemma":0.00013079116,"teacher_disagreement_score":0.9608725,"about_ca_system_score_codex":0.00013791567,"about_ca_system_score_gemma":0.00008712354,"threshold_uncertainty_score":0.99995947},"labels":[],"label_agreement":null},{"id":"W2079690139","doi":"10.1016/j.datak.2006.11.002","title":"Load balancing and data placement for multi-tiered database systems","year":2006,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada)","funders":"","keywords":"Computer science; Database; Materialized view; View; Database server; Workload; Online analytical processing; Database tuning; Server; Table (database); IBM; Database administrator; Distributed database; Database testing; Operating system; Application server; Load balancing (electrical power); Data warehouse; Database design","score_opus":0.057066989033939385,"score_gpt":0.3019583151155923,"score_spread":0.2448913260816529,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079690139","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":[0.0003030386,0.008422992,0.9826493,0.00001594489,0.0011689977,0.00047747715,0.006645217,0.00025869595,0.000058321188],"genre_scores_gemma":[0.009541828,0.00008066116,0.9774448,0.000010855044,0.0008005237,0.00010612437,0.011484957,0.000054691518,0.0004755355],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979979,0.000023161812,0.00039585633,0.0009740911,0.00018747922,0.0004215354],"domain_scores_gemma":[0.996143,0.00016601,0.00008943301,0.0034077498,0.00008281958,0.00011102918],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000852338,0.00025304107,0.0002892262,0.00008870992,0.00014215198,0.00017298342,0.0016798454,0.00004691627,0.0000012337106],"category_scores_gemma":[0.00022471162,0.0002464539,0.000015474317,0.00019619864,0.00002136136,0.002408623,0.0034281341,0.0001116996,0.000015018125],"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":[0.000106816406,0.0011538527,0.001416517,0.012516036,0.0006084045,0.00022989622,0.0018730449,0.013300634,0.057084452,0.47317582,0.31253016,0.12600438],"study_design_scores_gemma":[0.00045055087,0.000009973002,0.000045554578,0.00014374376,0.000009314133,0.000017161903,0.00003039078,0.66957927,0.00013019006,0.0000011362382,0.329374,0.00020872109],"about_ca_topic_score_codex":0.00021743073,"about_ca_topic_score_gemma":0.0001815649,"teacher_disagreement_score":0.65627867,"about_ca_system_score_codex":0.00007663751,"about_ca_system_score_gemma":0.00009324233,"threshold_uncertainty_score":0.99999875},"labels":[],"label_agreement":null},{"id":"W2079796778","doi":"10.1016/j.datak.2013.03.005","title":"Subject-based semantic document clustering for digital forensic investigations","year":2013,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Digital and Cyber Forensics","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Subject (documents); Computer science; Cluster analysis; Information retrieval; Document clustering; Natural language processing; Artificial intelligence; Data science; World Wide Web","score_opus":0.023005084943141487,"score_gpt":0.2321864369908625,"score_spread":0.209181352047721,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079796778","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":[0.0063816146,0.00012237552,0.9907607,0.00021740318,0.00064072903,0.00038306124,0.00011187403,0.00037972777,0.0010025223],"genre_scores_gemma":[0.8234453,0.0000018766916,0.17450823,0.00010306084,0.00024730279,0.00017387584,0.0010724833,0.000049794024,0.0003980605],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987897,0.0000048134225,0.00024863236,0.0004413346,0.00013185792,0.0003836167],"domain_scores_gemma":[0.9985476,0.00015813649,0.000041126223,0.0010016449,0.000084545885,0.000166949],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010870376,0.00020075694,0.00016916348,0.000112716334,0.00007871657,0.0009008776,0.0012269642,0.000041599487,0.0000052931305],"category_scores_gemma":[0.00012918875,0.00019411265,0.000050821513,0.00030176595,0.000034518074,0.0026933756,0.0007711345,0.00008624576,0.00022372697],"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":[0.000003283369,0.00016583082,0.0003896834,0.0005495517,0.0001173596,0.000008035715,0.0005870084,0.002697739,0.0009105752,0.053773005,0.0364923,0.90430564],"study_design_scores_gemma":[0.00024465445,0.00003419963,0.00024662528,0.00007350635,0.0000076499855,0.0000055162855,0.000008895027,0.97715324,0.0007371469,0.0014185813,0.019809453,0.00026052477],"about_ca_topic_score_codex":0.000011554682,"about_ca_topic_score_gemma":0.0000175279,"teacher_disagreement_score":0.97445554,"about_ca_system_score_codex":0.000044243985,"about_ca_system_score_gemma":0.00006853037,"threshold_uncertainty_score":0.8687183},"labels":[],"label_agreement":null},{"id":"W2081024207","doi":"10.1016/j.datak.2007.05.006","title":"A tree-projection-based algorithm for multi-label recurrent-item associative-classification rule generation","year":2007,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Association rule learning; Associative property; Computer science; Data mining; Apriori algorithm; Artificial intelligence; Classifier (UML); Pattern recognition (psychology); Machine learning; Projection (relational algebra); Algorithm; Mathematics","score_opus":0.15268889256032656,"score_gpt":0.35595682947668167,"score_spread":0.2032679369163551,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081024207","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":[0.0002651029,0.00030579508,0.9971143,0.00007208563,0.00080846547,0.00038509682,0.00062673754,0.00034790966,0.00007452199],"genre_scores_gemma":[0.000090947986,0.000011041523,0.9960799,0.000017493367,0.00052884244,0.00016040876,0.0029284954,0.000026203254,0.00015662707],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984755,0.000020550655,0.00034383437,0.0006513313,0.00015877708,0.0003500273],"domain_scores_gemma":[0.99850404,0.00027110748,0.00012650911,0.0007930297,0.00019837527,0.00010693332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009966115,0.00019132342,0.00016164713,0.00020338154,0.00022236566,0.0002040927,0.0010585246,0.00009183252,0.0000023028488],"category_scores_gemma":[0.0002478801,0.00020901633,0.000038654405,0.0006390592,0.000014391672,0.00075540517,0.00019713098,0.00014964069,0.000041758554],"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":[7.4686795e-7,0.00018080177,0.000017030952,0.000013400416,0.000017127571,3.4579077e-7,0.00012504504,2.3353338e-7,0.0029925152,0.00097514415,0.0021375297,0.9935401],"study_design_scores_gemma":[0.00059237663,0.000033926633,0.0010023123,0.000024902152,0.000015090736,0.0000013399036,0.000025366662,0.9871152,0.001640552,0.000005175317,0.009304229,0.00023954788],"about_ca_topic_score_codex":0.000012690521,"about_ca_topic_score_gemma":0.00004722614,"teacher_disagreement_score":0.99330056,"about_ca_system_score_codex":0.00014981473,"about_ca_system_score_gemma":0.00009879238,"threshold_uncertainty_score":0.8523439},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2082651521","doi":"10.1016/j.datak.2006.03.005","title":"Compact access control labeling for efficient secure XML query evaluation","year":2006,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Access Control and Trust","field":"Social Sciences","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; XML Signature; Access control; XML Encryption; XML database; Efficient XML Interchange; Streaming XML; XML framework; Granularity; Data access; Database; XML validation; XML; Computer network; World Wide Web; Programming language","score_opus":0.06344754137285828,"score_gpt":0.3806975017838266,"score_spread":0.3172499604109683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082651521","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":[0.14501542,0.021290973,0.7844322,0.0018928567,0.0068106926,0.0057217437,0.0025577487,0.0013631288,0.030915255],"genre_scores_gemma":[0.9972783,0.00001022624,0.00049971376,0.00001941044,0.0015217542,0.00005351631,0.00050444674,0.000024071753,0.00008855923],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985969,0.00007364287,0.00025478847,0.00033469906,0.00032178537,0.0004182056],"domain_scores_gemma":[0.9988084,0.0004145914,0.00007664209,0.00036098264,0.0002521208,0.000087290624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001761459,0.00015385343,0.00021887361,0.00010749603,0.00035349347,0.0002852979,0.00085449027,0.0000910688,0.00005967268],"category_scores_gemma":[0.0006337023,0.00015279402,0.000053972413,0.0002810367,0.000036644247,0.00054812833,0.0000942149,0.00012395461,0.00002740001],"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":[0.00023544974,0.0013511877,0.014185066,0.00075343315,0.0006022059,0.000014061144,0.0063672224,0.45474222,0.004580232,0.15522498,0.06434496,0.297599],"study_design_scores_gemma":[0.0010707572,0.0000072394673,0.0022297187,0.00004234826,0.00008590448,2.8432038e-7,0.000079422745,0.920154,0.000047933743,0.00010413708,0.07598655,0.00019170699],"about_ca_topic_score_codex":0.00086931157,"about_ca_topic_score_gemma":0.0014555103,"teacher_disagreement_score":0.85226285,"about_ca_system_score_codex":0.00014824526,"about_ca_system_score_gemma":0.00017826747,"threshold_uncertainty_score":0.6230759},"labels":[],"label_agreement":null},{"id":"W2090992497","doi":"10.1016/j.datak.2004.06.005","title":"eMarketplaces for enterprise and cross enterprise integration","year":2004,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Auction Theory and Applications","field":"Decision Sciences","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; Western University","funders":"","keywords":"Enterprise integration; Business; Process management; Enterprise software","score_opus":0.08516768738760731,"score_gpt":0.4081140141277604,"score_spread":0.32294632674015306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090992497","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":[0.085872166,0.0005501919,0.9116827,0.0001563222,0.0004538118,0.00026384392,0.00035414545,0.00009977075,0.00056704885],"genre_scores_gemma":[0.98384815,0.000041535575,0.014292206,0.000022572885,0.00026437425,0.000090165995,0.00019263661,0.000020621192,0.0012277086],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988411,0.000022039749,0.00035119374,0.00046144018,0.00016027772,0.00016396583],"domain_scores_gemma":[0.99836427,0.00060970045,0.00007604134,0.0007382456,0.00011656226,0.00009519458],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013652152,0.00012666265,0.00014958582,0.00014363564,0.0001637867,0.00029985598,0.0007274818,0.000052328694,0.000046882513],"category_scores_gemma":[0.0018210495,0.00010556387,0.00003869116,0.0002765413,0.000054361677,0.0007761987,0.00028534877,0.00009256765,0.00011890326],"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":[0.0002645242,0.00055190385,0.0021007354,0.00011129351,0.00011097944,0.000004297068,0.0082926955,0.002405532,0.017155634,0.12992036,0.016248966,0.82283306],"study_design_scores_gemma":[0.0020519812,0.000098652454,0.0059558456,0.00018003378,0.000050063463,0.000045371657,0.0011294582,0.42131117,0.011627732,0.037750963,0.5191088,0.0006899331],"about_ca_topic_score_codex":0.0000024721598,"about_ca_topic_score_gemma":0.000015586262,"teacher_disagreement_score":0.89797604,"about_ca_system_score_codex":0.000030735133,"about_ca_system_score_gemma":0.000028088907,"threshold_uncertainty_score":0.430477},"labels":[],"label_agreement":null},{"id":"W2094060849","doi":"10.1016/j.datak.2010.03.007","title":"Ranking bias in deep web size estimation using capture recapture method","year":2010,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada; State Key Laboratory of Novel Software Technology","keywords":"Ranking (information retrieval); Computer science; Estimation; Sampling (signal processing); Data mining; Process (computing); Matching (statistics); Mark and recapture; Rank (graph theory); Limit (mathematics); Statistics; Information retrieval; Mathematics","score_opus":0.04137654040511619,"score_gpt":0.3090537414834847,"score_spread":0.2676772010783685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094060849","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":[0.015598374,0.00047363614,0.9825179,0.00008067989,0.0007853129,0.000072293886,0.000047191883,0.00022830722,0.00019633443],"genre_scores_gemma":[0.22724476,0.000005427165,0.7723539,0.000018367336,0.00017903738,0.0000039685965,0.00014530895,0.000021215697,0.000028025028],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984485,0.00006753288,0.00031790175,0.0006311587,0.0001828447,0.00035204744],"domain_scores_gemma":[0.9976859,0.000487885,0.00008022657,0.0015947378,0.000051958206,0.0000993042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013800269,0.00022381193,0.0002797583,0.00030479388,0.00007822678,0.0002647597,0.0018951797,0.00014979114,0.000018797673],"category_scores_gemma":[0.001391393,0.00022270193,0.000047403577,0.0011396693,0.00001255582,0.0013113308,0.000832617,0.0006233147,0.000029302444],"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":[0.000005865876,0.00015992488,0.001187569,0.0002368207,0.00013401327,0.000103189916,0.0047960756,0.058699787,0.12853447,0.0055204486,0.001189216,0.79943264],"study_design_scores_gemma":[0.00020638866,0.0000031387694,0.00027755456,0.0000806287,0.000024288473,0.000031421554,0.000021943675,0.99364144,0.000518282,0.000044256467,0.004893872,0.00025678898],"about_ca_topic_score_codex":0.000065975444,"about_ca_topic_score_gemma":0.00032696806,"teacher_disagreement_score":0.93494165,"about_ca_system_score_codex":0.000041125033,"about_ca_system_score_gemma":0.00008586884,"threshold_uncertainty_score":0.9081521},"labels":[],"label_agreement":null},{"id":"W2114928940","doi":"10.1016/j.datak.2013.02.001","title":"Assessing the quality factors found in in-line documentation written in natural language: The JavadocMiner","year":2013,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"U.S. Department of Defense","keywords":"Documentation; Natural (archaeology); Quality (philosophy); Line (geometry); Natural language processing; Computer science; Linguistics; Psychology; History; Mathematics; Programming language; Archaeology; Philosophy","score_opus":0.059091997112096124,"score_gpt":0.39128965147035494,"score_spread":0.3321976543582588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114928940","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9614783,0.0015787388,0.03546179,0.00035694506,0.00057956425,0.00037087782,0.00000404499,0.00012512393,0.000044625947],"genre_scores_gemma":[0.9965087,0.000006768261,0.0031805455,0.000018110599,0.00009121397,0.00005160322,0.00005768715,0.00001809344,0.000067287576],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99839014,0.00013045715,0.00037302228,0.00039064058,0.0002795089,0.00043623743],"domain_scores_gemma":[0.9968166,0.0019420392,0.00003851238,0.0011091747,0.000048956932,0.000044724507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015186877,0.0001778422,0.00017281537,0.0002742745,0.000042547283,0.00058845326,0.0020756877,0.00005309492,0.000014899637],"category_scores_gemma":[0.00179205,0.00011735342,0.000020856554,0.0013710533,0.000027146742,0.002348047,0.00091678585,0.00066150475,0.000046638448],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000084245075,0.00048584415,0.54029083,0.00069224846,0.00009517398,0.00012414332,0.05665455,0.037164606,0.016763043,0.003228191,0.0026654801,0.34182745],"study_design_scores_gemma":[0.00018269333,0.0000028832299,0.5027856,0.000053016898,7.771844e-7,0.0000018803056,0.00041303982,0.49616292,0.00008836925,0.000009925895,0.00018768327,0.00011116629],"about_ca_topic_score_codex":0.0015477533,"about_ca_topic_score_gemma":0.0006755233,"teacher_disagreement_score":0.45899832,"about_ca_system_score_codex":0.00022347808,"about_ca_system_score_gemma":0.000061031304,"threshold_uncertainty_score":0.5674468},"labels":[],"label_agreement":null},{"id":"W2134227416","doi":"10.1016/s0169-023x(00)00044-6","title":"Selecting and materializing horizontally partitioned warehouse views","year":2001,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Data warehouse; Cube (algebra); Aggregate (composite); Computer science; Table (database); Warehouse; Dimension (graph theory); Data cube; Materialized view; Dimensional modeling; Database; Constraint (computer-aided design); Online analytical processing; Data mining; Information retrieval; Mathematics; View; Geography; Database design; Combinatorics","score_opus":0.057702484360440495,"score_gpt":0.2827958738468403,"score_spread":0.2250933894863998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134227416","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":[0.011884748,0.0013277226,0.985107,0.000047878955,0.0007142583,0.00012207286,0.00006895684,0.00046372067,0.00026364502],"genre_scores_gemma":[0.29932675,0.00048600964,0.6976799,0.00007425396,0.0012545785,0.00007753138,0.00069369486,0.00009605613,0.00031126602],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988936,0.000025086074,0.00024661937,0.0004432851,0.00008971312,0.0003016968],"domain_scores_gemma":[0.9989333,0.00005266454,0.000050344053,0.0008177169,0.00004568981,0.00010027158],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031938698,0.00016597418,0.0001896493,0.00007897551,0.00013966655,0.00013903681,0.0004817066,0.000035888337,0.000007099898],"category_scores_gemma":[0.0001268684,0.00016368591,0.000015010449,0.00027452246,0.0000126228115,0.001729883,0.0008453011,0.000094927775,0.000042387877],"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":[0.000041208317,0.00028110627,0.002094593,0.0013020926,0.0002338603,0.0004747452,0.0076304465,0.00078863424,0.17112917,0.22076821,0.015156416,0.5800995],"study_design_scores_gemma":[0.00027765895,0.000035310477,0.00039256545,0.00017403145,0.000008060771,0.00020098122,0.000053432068,0.3635798,0.002296767,0.000026114154,0.63256335,0.00039194117],"about_ca_topic_score_codex":0.000025077903,"about_ca_topic_score_gemma":0.00006582506,"teacher_disagreement_score":0.6174069,"about_ca_system_score_codex":0.000028247034,"about_ca_system_score_gemma":0.000022283477,"threshold_uncertainty_score":0.66749173},"labels":[],"label_agreement":null},{"id":"W2144326136","doi":"10.1016/j.datak.2008.12.001","title":"Privacy-preserving data publishing for cluster analysis","year":2008,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":71,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ontario Institute of Technology; Simon Fraser University; Concordia University","funders":"","keywords":"Masking (illustration); Data publishing; Computer science; Cluster (spacecraft); ENCODE; Data mining; Process (computing); Publishing; Focus (optics); Data anonymization; Class (philosophy); Data quality; Information retrieval; Information privacy; Artificial intelligence; Computer security; Engineering","score_opus":0.10371521504469686,"score_gpt":0.30616418974752596,"score_spread":0.2024489747028291,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144326136","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":[0.0015261957,0.0013384854,0.9861247,0.006046459,0.0008047386,0.00036112376,0.0015362751,0.0019384844,0.00032352278],"genre_scores_gemma":[0.026531244,0.00012134241,0.9663882,0.00008810091,0.0003743293,0.00004938721,0.0062960763,0.000059386053,0.00009190698],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99613905,0.000055178287,0.0005900979,0.0019152584,0.00042009997,0.0008803129],"domain_scores_gemma":[0.94056004,0.0010692617,0.0001712667,0.057808366,0.00019428511,0.00019677654],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0019868144,0.00038226525,0.00051797327,0.00085580116,0.00031021275,0.0010346024,0.17455038,0.00022954041,0.000016853293],"category_scores_gemma":[0.08517772,0.00040132934,0.000099504614,0.0029531277,0.000061493,0.014377865,0.4642628,0.00055962714,0.00004261152],"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":[0.000004400012,0.00007556752,0.0012286418,0.00012507015,0.0005282809,0.000015595182,0.0001764376,0.00020709145,0.00018293351,0.0006174471,0.97184265,0.024995867],"study_design_scores_gemma":[0.00031606373,0.00001164813,0.00073781353,0.000039247414,0.000100104255,0.000021297094,0.000007225945,0.8643259,0.0001836136,0.0007693323,0.13308215,0.0004055985],"about_ca_topic_score_codex":0.000054333883,"about_ca_topic_score_gemma":0.00006196624,"teacher_disagreement_score":0.8641188,"about_ca_system_score_codex":0.000116340445,"about_ca_system_score_gemma":0.0001395612,"threshold_uncertainty_score":0.99984384},"labels":[],"label_agreement":null},{"id":"W2145399176","doi":"10.1016/j.datak.2006.06.001","title":"Combined mining of Web server logs and web contents for classifying user navigation patterns and predicting users’ future requests","year":2006,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":205,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Web mining; Computer science; Web page; Web server; Web navigation; Personalization; Static web page; World Wide Web; Web log analysis software; Information retrieval; Data Web; Web API; Database; Data mining; The Internet","score_opus":0.030135819550464835,"score_gpt":0.25834862715059415,"score_spread":0.2282128076001293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145399176","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7628296,0.0007037088,0.23493011,0.00008313589,0.0006268543,0.00035359396,0.00014255138,0.00027293377,0.000057487447],"genre_scores_gemma":[0.9667707,0.000030176061,0.03273155,0.0000068857953,0.00021246426,0.000025666332,0.00016986528,0.000021593158,0.00003109115],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989553,0.000025087384,0.00033028025,0.00038052956,0.00009707328,0.00021172626],"domain_scores_gemma":[0.9991613,0.00011803475,0.00011942074,0.00047138846,0.00007602657,0.000053837575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038030616,0.00016520277,0.00023431217,0.00010298597,0.00007008075,0.0001284699,0.00043736552,0.000092742775,4.52043e-7],"category_scores_gemma":[0.000026151927,0.00016318906,0.000022992062,0.00012608258,0.00001166582,0.0008864878,0.0004517922,0.00010477829,2.397226e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019943038,0.00018661207,0.8776051,0.004088221,0.00020681418,0.000019260415,0.0026715861,0.000029711446,0.028646786,0.021189615,0.0069023664,0.058434],"study_design_scores_gemma":[0.0008705874,0.00006617182,0.03945971,0.00080737955,0.000018501154,0.000018361601,0.00010014189,0.94975483,0.0017350396,0.00003669231,0.0068794466,0.0002531283],"about_ca_topic_score_codex":0.00004875147,"about_ca_topic_score_gemma":0.00007451303,"teacher_disagreement_score":0.94972515,"about_ca_system_score_codex":0.000025380064,"about_ca_system_score_gemma":0.000017135695,"threshold_uncertainty_score":0.66546565},"labels":[],"label_agreement":null},{"id":"W3037550867","doi":"10.1016/j.datak.2013.01.001","title":"Diamond dicing","year":2013,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université TÉLUQ; University of New Brunswick","funders":"","keywords":"Wafer dicing; Materials science; Nanotechnology; Wafer","score_opus":0.030581411111876202,"score_gpt":0.24660457927354787,"score_spread":0.21602316816167166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037550867","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":[0.017958272,0.0019670997,0.97447366,0.00023361572,0.0011158223,0.00012825357,0.00000524453,0.00064485276,0.0034731994],"genre_scores_gemma":[0.8033408,0.00004404026,0.19567913,0.00006777582,0.00038367236,0.000028920906,0.000042267162,0.000023850795,0.0003895343],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991743,0.00000954764,0.00013725249,0.00032128123,0.00008358195,0.00027406012],"domain_scores_gemma":[0.9985824,0.00013072287,0.000019538307,0.0011633915,0.000030809235,0.000073118375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014299786,0.00011558487,0.0001273636,0.0000823702,0.000045315814,0.00017460785,0.0018395596,0.000036703303,0.000023398607],"category_scores_gemma":[0.00016272686,0.00010230189,0.000018491082,0.0002209659,0.000012531835,0.0011193907,0.0011280276,0.00010551431,0.0006937518],"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":[5.443864e-7,0.00008246051,0.0020990388,0.0001375147,0.000060265756,0.000028763026,0.0016204291,0.00010206435,0.009059032,0.031650845,0.0557277,0.89943135],"study_design_scores_gemma":[0.00008799495,0.0000088380475,0.008669243,0.00003140044,0.0000033658218,0.000008522393,0.000021625487,0.9645193,0.00085135887,0.00012667297,0.025508933,0.00016271688],"about_ca_topic_score_codex":0.0000478503,"about_ca_topic_score_gemma":0.0000085321935,"teacher_disagreement_score":0.9644173,"about_ca_system_score_codex":0.000016306194,"about_ca_system_score_gemma":0.000018337461,"threshold_uncertainty_score":0.8917007},"labels":[],"label_agreement":null},{"id":"W3131740359","doi":"10.1016/j.datak.2021.101876","title":"Generation of Gaussian sets for clustering methods assessment","year":2021,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thales (Canada)","funders":"","keywords":"Cluster analysis; Computer science; Generator (circuit theory); Fuzzy clustering; Curse of dimensionality; Rand index; Mixture model; Data mining; Homogeneity (statistics); Artificial intelligence; Gaussian; Pattern recognition (psychology); Set (abstract data type); Hierarchical clustering; Maximization; Sensitivity (control systems); Algorithm; Machine learning; Mathematics; Mathematical optimization; Power (physics); Engineering","score_opus":0.1936835263463012,"score_gpt":0.47320929907024467,"score_spread":0.27952577272394347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3131740359","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":[0.0001948376,0.00061440235,0.99776083,0.00009415736,0.0007885281,0.000162281,0.00006508901,0.00011120674,0.00020865806],"genre_scores_gemma":[0.0050805747,0.000026765223,0.9942734,0.0000067981764,0.00018882786,0.000042689026,0.00022989693,0.000025186535,0.00012581483],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998595,0.00007410645,0.0002960792,0.00053847226,0.0001716829,0.00032467692],"domain_scores_gemma":[0.9980086,0.00026985034,0.000053638218,0.0013796162,0.00019230753,0.00009599596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008492214,0.00014491705,0.00022370921,0.000121965444,0.000070843715,0.000110934525,0.0011701754,0.000053957658,0.0000062972676],"category_scores_gemma":[0.00033894446,0.0001598471,0.000042356718,0.00042816153,0.000012089749,0.00067586766,0.0018962169,0.0001530196,0.0000033815977],"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":[0.0000013168949,0.000060051174,0.000006575892,0.00031777244,0.00005050607,0.000010506339,0.00025921786,0.009881406,0.15209857,0.0029831014,0.00032775934,0.8340032],"study_design_scores_gemma":[0.0002312273,0.00002428617,0.00010660747,0.000048728092,0.0000057815246,0.000017365202,0.000013080421,0.9521344,0.036181763,0.000040099952,0.011044156,0.00015254444],"about_ca_topic_score_codex":0.0000024531196,"about_ca_topic_score_gemma":0.000010880634,"teacher_disagreement_score":0.94225293,"about_ca_system_score_codex":0.000098338256,"about_ca_system_score_gemma":0.00016697761,"threshold_uncertainty_score":0.6518375},"labels":[],"label_agreement":null},{"id":"W3197885731","doi":"10.1016/j.datak.2021.101926","title":"Exploring the research landscape of data warehousing and mining based on DaWaK Conference full-text articles","year":2021,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Ministry of Science and ICT, South Korea; National Research Foundation of Korea; Conselho Nacional de Desenvolvimento Científico e Tecnológico; National Natural Science Foundation of China; National Science Foundation","keywords":"Data science; Data warehouse; Computer science; Information retrieval; Data mining","score_opus":0.5264044121500385,"score_gpt":0.3663522096925166,"score_spread":0.16005220245752194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197885731","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94826925,0.0031926958,0.039120406,0.0015833535,0.0015448193,0.0003992605,0.00046446171,0.00028317005,0.005142578],"genre_scores_gemma":[0.9958701,0.00011147583,0.0022193287,0.000044594577,0.00073541026,0.00001118082,0.00094445277,0.000036061032,0.000027404189],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983584,0.000027364471,0.00028977863,0.00060756895,0.0003423711,0.00037450416],"domain_scores_gemma":[0.9970741,0.0005428665,0.00006745724,0.0019724164,0.00032077503,0.000022343744],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014472659,0.00018105695,0.00021209425,0.00026607694,0.00023053422,0.0004701514,0.0015251704,0.000040461513,0.00013372708],"category_scores_gemma":[0.0013250217,0.0001458072,0.000016799206,0.0011400584,0.00009098576,0.0025946475,0.0030954706,0.00028974013,0.00005861559],"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":[0.00013465372,0.00047136546,0.0074560037,0.00314558,0.00013291233,0.000112591486,0.0008748415,0.0017904029,0.020988367,0.010801173,0.019654498,0.93443763],"study_design_scores_gemma":[0.00016792175,0.0000060550065,0.0028441232,0.0006095115,0.000032189175,0.000004511501,0.000699868,0.93845737,0.0008742365,0.000017896262,0.056092672,0.00019366646],"about_ca_topic_score_codex":0.00006061779,"about_ca_topic_score_gemma":0.00017123057,"teacher_disagreement_score":0.93666697,"about_ca_system_score_codex":0.000010538169,"about_ca_system_score_gemma":0.00006947049,"threshold_uncertainty_score":0.59458447},"labels":[],"label_agreement":null},{"id":"W3197889602","doi":"10.1016/j.datak.2021.101924","title":"Mining high utility patterns in interval-based event sequences","year":2021,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Pruning; Interval (graph theory); Computer science; Event (particle physics); Data mining; Range (aeronautics); Point (geometry); Sequential Pattern Mining; Algorithm; Mathematics; Engineering","score_opus":0.041472155210488644,"score_gpt":0.29062862660563255,"score_spread":0.2491564713951439,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197889602","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":[0.05081657,0.00035929863,0.9475017,0.00026706967,0.00044051404,0.000066103545,0.00029644417,0.00015973444,0.00009253375],"genre_scores_gemma":[0.720634,0.000013098093,0.27828124,0.00003865829,0.00010101465,0.000036823505,0.0008389571,0.000013618219,0.000042605483],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987159,0.00003276075,0.00026847524,0.0005980427,0.00012027275,0.00026456267],"domain_scores_gemma":[0.9982424,0.00014506404,0.000036442903,0.0014487869,0.000047986137,0.00007931992],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038947942,0.00013843285,0.00016583833,0.000091889946,0.000043494907,0.00015561766,0.0015786167,0.000040206614,0.000028444638],"category_scores_gemma":[0.00013687511,0.00014846103,0.000026709135,0.0005295536,0.00001208095,0.000548056,0.0010638923,0.00015052823,0.00003431593],"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":[0.000001274374,0.0003327789,0.0047531095,0.00018588753,0.000027831187,0.00012278555,0.00079090445,0.000549154,0.0012564352,0.003913797,0.0016839389,0.9863821],"study_design_scores_gemma":[0.0001476228,0.000007765841,0.0088244025,0.00016941757,0.0000036218773,0.0000063568377,0.00003825904,0.9776545,0.0020390996,0.000019080704,0.010924771,0.00016506726],"about_ca_topic_score_codex":0.00007111082,"about_ca_topic_score_gemma":0.00017670124,"teacher_disagreement_score":0.986217,"about_ca_system_score_codex":0.000047440277,"about_ca_system_score_gemma":0.00012568351,"threshold_uncertainty_score":0.60540646},"labels":[],"label_agreement":null},{"id":"W4327724188","doi":"10.1016/j.datak.2023.102177","title":"Preface","year":2023,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Geography","score_opus":0.1044293387069667,"score_gpt":0.33191004888109904,"score_spread":0.22748071017413235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327724188","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.744258,0.01284252,0.04578496,0.00045533324,0.015370411,0.00295292,0.023687262,0.06649534,0.088153265],"genre_scores_gemma":[0.94199365,0.00015007117,0.01877964,0.000022252001,0.003070892,0.0001771851,0.020056628,0.0013365085,0.014413178],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987156,0.000016458116,0.00018153059,0.00044585855,0.00015525597,0.0004853312],"domain_scores_gemma":[0.99821156,0.00011978255,0.000022187176,0.0014811065,0.000034598135,0.00013079226],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005278856,0.0001883138,0.00016330849,0.00027665996,0.00005127506,0.00005538288,0.0011103799,0.000055880937,0.00010228389],"category_scores_gemma":[0.00049329846,0.00020560886,0.000026852189,0.001350763,0.000014802657,0.00048453303,0.0011806801,0.00019332372,0.079043224],"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":[0.000010500457,0.000098128236,0.0006423613,0.00032594925,0.00015780753,0.00007343849,0.0011578136,0.0024830664,0.096355684,0.0021277613,0.8536367,0.04293081],"study_design_scores_gemma":[0.00013639384,0.0000043515493,0.0022329495,0.00003430223,0.000010973846,0.000003946335,0.000018554229,0.56423,0.0009661793,0.0000043278255,0.4321823,0.00017569262],"about_ca_topic_score_codex":0.0000055819155,"about_ca_topic_score_gemma":0.000014936168,"teacher_disagreement_score":0.56174695,"about_ca_system_score_codex":0.000064255226,"about_ca_system_score_gemma":0.000035029843,"threshold_uncertainty_score":0.92167383},"labels":[],"label_agreement":null},{"id":"W4386987509","doi":"10.1016/j.datak.2023.102229","title":"Robotic process automation using process mining — A systematic literature review","year":2023,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Robotic Process Automation Applications","field":"Engineering","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; University of Ottawa","keywords":"Computer science; Automation; Process (computing); Preprocessor; Process mining; Event (particle physics); Software engineering; Domain (mathematical analysis); Software; Data science; Construct (python library); Robot; Data mining; Work in process; Business process; Artificial intelligence; Engineering; Business process modeling","score_opus":0.036817580297915056,"score_gpt":0.3163027075077396,"score_spread":0.27948512720982455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386987509","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":[0.009680329,0.19428697,0.7683752,0.0001899887,0.0017535596,0.004890497,0.00027985612,0.01938078,0.0011627999],"genre_scores_gemma":[0.86452305,0.023440551,0.089800656,0.00020274727,0.0017053073,0.005487556,0.012752986,0.001558113,0.0005290312],"study_design_codex":"systematic_review","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980031,0.000027849554,0.00074622466,0.00045817604,0.00030564112,0.00045897797],"domain_scores_gemma":[0.99834996,0.00013808641,0.000115996714,0.0010606893,0.0001982071,0.00013703],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000598939,0.00037101033,0.0005677835,0.00044286993,0.000113216345,0.00017213632,0.0009763003,0.00012387936,0.000014598405],"category_scores_gemma":[0.00061287783,0.00038391887,0.000050737082,0.0035377336,0.000014002866,0.0010853314,0.00014213783,0.00025380374,0.00030490322],"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":[4.351433e-7,0.000024611722,0.000012008801,0.56530166,0.00010076902,0.000011935159,0.001580786,0.42897892,0.0005814121,0.00013670529,0.0019281737,0.001342553],"study_design_scores_gemma":[0.00010441252,0.0000031436102,0.000045776338,0.079236604,0.00013084529,0.00006050029,0.00009002283,0.91974705,0.000120421435,0.000013501804,0.000087384506,0.00036033933],"about_ca_topic_score_codex":2.605043e-7,"about_ca_topic_score_gemma":0.0000011451798,"teacher_disagreement_score":0.8548427,"about_ca_system_score_codex":0.000120792756,"about_ca_system_score_gemma":0.000068636706,"threshold_uncertainty_score":0.9998613},"labels":[],"label_agreement":null},{"id":"W4387842356","doi":"10.1016/j.datak.2023.102238","title":"User-generated short-text classification using cograph editing-based network clustering with an application in invoice categorization","year":2023,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Ontario Ministry of Research and Innovation; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Mitacs; Canada Foundation for Innovation","keywords":"Computer science; Categorization; Cluster analysis; Invoice; Information retrieval; Product (mathematics); Natural language processing; Data mining; Artificial intelligence; World Wide Web","score_opus":0.04509888621521016,"score_gpt":0.2994695044326596,"score_spread":0.25437061821744944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387842356","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":[0.14864871,0.000034106655,0.85044855,0.000008973858,0.00008235434,0.0002820742,0.00003766047,0.00039801525,0.000059553666],"genre_scores_gemma":[0.9744105,0.0000025942918,0.013885153,0.000003597253,0.0009449064,0.00010654708,0.010579822,0.000061504696,0.0000054178913],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986285,0.000053117907,0.00033671275,0.00050590286,0.00012811783,0.00034764095],"domain_scores_gemma":[0.9989326,0.000059227423,0.00009000693,0.00074772607,0.00009489142,0.000075565265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042949215,0.00021613514,0.00021807117,0.00031792722,0.00010390033,0.000107000145,0.0004192852,0.00005477976,0.00000864954],"category_scores_gemma":[0.000007270851,0.0002388418,0.000027046295,0.0025653988,0.000017610704,0.00044434404,0.0001498386,0.00018664612,0.000008932822],"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":[0.000015000875,0.00010671815,0.08540051,0.00005273158,0.000064933076,0.0000013556082,0.00014861878,0.8631446,0.00877,0.0014542888,0.0004267107,0.040414546],"study_design_scores_gemma":[0.00015338078,0.000013630881,0.0071028722,0.000076398734,0.00004178211,2.4651865e-7,0.00006493321,0.9900123,0.00037918965,0.000025622954,0.0018844744,0.00024520096],"about_ca_topic_score_codex":0.00019835611,"about_ca_topic_score_gemma":0.0007040629,"teacher_disagreement_score":0.8365634,"about_ca_system_score_codex":0.00006777749,"about_ca_system_score_gemma":0.000047632304,"threshold_uncertainty_score":0.9739686},"labels":[],"label_agreement":null},{"id":"W4388090033","doi":"10.1016/j.datak.2023.102240","title":"Hierarchical framework for interpretable and specialized deep reinforcement learning-based predictive maintenance","year":2023,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Reliability and Maintenance Optimization","field":"Engineering","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"H2020 Marie Skłodowska-Curie Actions; Canadian Institute of Steel Construction; Horizon 2020 Framework Programme; Österreichische Forschungsförderungsgesellschaft; Science Foundation Ireland; Horizon 2020","keywords":"Interpretability; Reinforcement learning; Machine learning; Computer science; Artificial intelligence; Probabilistic logic; Black box; Context (archaeology); Markov decision process; Risk analysis (engineering); Markov process","score_opus":0.015179626367081898,"score_gpt":0.25194097941082105,"score_spread":0.23676135304373916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388090033","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":[0.00081908744,0.00027936426,0.9962403,0.00005534691,0.00070031243,0.0004450754,0.000057669928,0.00091045885,0.00049237756],"genre_scores_gemma":[0.8465778,0.0010900835,0.14685562,0.00004430668,0.000893839,0.00058075157,0.0030811399,0.0002545026,0.00062191376],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882287,0.000015285574,0.00027308485,0.00035071088,0.0001000028,0.00043805435],"domain_scores_gemma":[0.998961,0.0004015589,0.000025818757,0.00044150325,0.00005962807,0.00011049821],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038475273,0.00021096831,0.0002473075,0.00015217168,0.00007986178,0.00006558894,0.00030838125,0.00012710098,0.000025012736],"category_scores_gemma":[0.0011651468,0.00021888565,0.000043112585,0.000367744,0.000040481787,0.00026211294,0.00018029801,0.00033399544,0.000029731966],"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":[0.00004344317,0.000010056723,0.00002855837,0.00036784564,0.000044225897,0.0000017767235,0.0003860969,0.98715687,0.00013735452,0.0028239016,0.0020368898,0.0069629946],"study_design_scores_gemma":[0.00044299342,0.000057684534,0.00012932955,0.00025040188,0.000021893658,0.000001103288,0.000049395425,0.96240306,0.00017341571,0.0003500323,0.035896745,0.00022396953],"about_ca_topic_score_codex":0.0000018069435,"about_ca_topic_score_gemma":0.000004436551,"teacher_disagreement_score":0.84938467,"about_ca_system_score_codex":0.0000949997,"about_ca_system_score_gemma":0.000022920422,"threshold_uncertainty_score":0.89258975},"labels":[],"label_agreement":null},{"id":"W4390245620","doi":"10.1016/j.datak.2023.102274","title":"Mining Keys for Graphs","year":2023,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Graph; Data deduplication; Theoretical computer science; Identification (biology); Data mining; Pruning; Database","score_opus":0.3915863678661295,"score_gpt":0.45612684361496436,"score_spread":0.06454047574883487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390245620","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":[0.036285207,0.00097127573,0.92995983,0.00208795,0.009235888,0.0013068663,0.005426869,0.002074137,0.0126519585],"genre_scores_gemma":[0.6081954,0.0005172615,0.27274084,0.00094600033,0.0045168153,0.0009858274,0.031681042,0.00050744414,0.07990935],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982215,0.000032910866,0.00041366107,0.000590915,0.00038635003,0.0003546488],"domain_scores_gemma":[0.9966078,0.0015499732,0.000055878798,0.0016106992,0.00007792504,0.000097748634],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004567647,0.00013131872,0.00020627533,0.00046921187,0.000109486595,0.00026203826,0.002229502,0.00004161456,0.00007234562],"category_scores_gemma":[0.004466019,0.00011692486,0.00005973463,0.0013795267,0.000019908366,0.00066435273,0.001509854,0.00006850877,0.0015328354],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000045760644,0.000023946304,0.00008389208,0.000055799053,0.000033361637,0.0000050958697,0.00051834463,0.00017652418,0.00018465552,0.022172429,0.72205603,0.25468534],"study_design_scores_gemma":[0.00014161725,0.000010317399,0.00052290445,0.00001627418,0.0000086979335,4.8556456e-7,0.00037129913,0.35582313,0.000057400153,0.0013434913,0.641587,0.000117367104],"about_ca_topic_score_codex":0.0000046527007,"about_ca_topic_score_gemma":0.000034737885,"teacher_disagreement_score":0.657219,"about_ca_system_score_codex":0.0000138819805,"about_ca_system_score_gemma":0.000021148533,"threshold_uncertainty_score":0.9992446},"labels":[],"label_agreement":null},{"id":"W4394987794","doi":"10.1016/j.datak.2024.102306","title":"Effective text classification using BERT, MTM LSTM, and DT","year":2024,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada); University of Calgary","funders":"","keywords":"Security token; Computer science; Artificial intelligence; Encoder; Binary classification; Transformer; Recall; Deep learning; Long short term memory; Natural language processing; Artificial neural network; Machine learning; Recurrent neural network; Support vector machine","score_opus":0.04931219236959951,"score_gpt":0.3094819476933262,"score_spread":0.2601697553237267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394987794","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":[0.008288466,0.0063180053,0.98179084,0.0003773586,0.00075738324,0.00021887469,0.000024008546,0.0015926622,0.00063237426],"genre_scores_gemma":[0.94384235,0.0001292412,0.055550065,0.000009459266,0.00015163663,0.00004043996,0.0000644263,0.00002555523,0.00018679751],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989894,0.000016946315,0.00016094184,0.0005411881,0.000096554475,0.00019498325],"domain_scores_gemma":[0.9988191,0.00019002262,0.000024734452,0.00088751456,0.00002819763,0.000050400842],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002519094,0.00014727216,0.00011803977,0.00024724327,0.00007370016,0.00040714658,0.00089407194,0.00007670767,0.000004944014],"category_scores_gemma":[0.00012315382,0.00014004766,0.000019875775,0.0005601778,0.00003425457,0.0012863459,0.00077190466,0.00018001288,0.00009020637],"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":[8.676244e-7,0.00002347563,0.000098252094,0.00015274437,0.000036249865,0.0000058395176,0.0004128938,0.000016724518,0.022230068,0.14869931,0.0023505052,0.82597303],"study_design_scores_gemma":[0.000060775048,0.000011904033,0.0018155862,0.00008393756,0.000010802101,0.000012950435,0.000026068747,0.92512316,0.0019048546,0.0002897153,0.070500895,0.00015934315],"about_ca_topic_score_codex":0.000005098803,"about_ca_topic_score_gemma":0.0000022201873,"teacher_disagreement_score":0.9355539,"about_ca_system_score_codex":0.00007620501,"about_ca_system_score_gemma":0.00003418062,"threshold_uncertainty_score":0.5710978},"labels":[],"label_agreement":null},{"id":"W4398243240","doi":"10.1016/j.datak.2024.102324","title":"Large language models: Expectations for semantics-driven systems engineering","year":2024,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Systems Engineering Methodologies and Applications","field":"Engineering","cited_by":49,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Foundation for Research and Technology-Hellas","keywords":"Computer science; Semantics (computer science); Programming language; Modeling language; Operational semantics; Software engineering","score_opus":0.07354628162855453,"score_gpt":0.31576459170632243,"score_spread":0.2422183100777679,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398243240","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":[0.0030725459,0.031581882,0.9555716,0.000020278327,0.003156071,0.0006151502,0.0015279928,0.004161814,0.0002926968],"genre_scores_gemma":[0.90271807,0.00027792383,0.091214776,0.0000028330044,0.0020374919,0.0011677033,0.0018113616,0.00044038406,0.0003294623],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982722,0.000013569221,0.00045272376,0.000506429,0.0001365392,0.00061857665],"domain_scores_gemma":[0.998179,0.0006235449,0.000018898916,0.0010092381,0.0000502418,0.0001190665],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004098205,0.00038580503,0.0003829757,0.00035375147,0.00007352676,0.00025597017,0.00072061486,0.00016193758,0.000006477763],"category_scores_gemma":[0.00015473561,0.00041558902,0.000106585474,0.00053452735,0.000008893289,0.0005203139,0.00018337618,0.00029107992,0.00008553124],"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":[0.0000011536986,0.000023261602,0.0000015771382,0.003244034,0.00028769154,0.0000117888185,0.002337536,0.9287157,0.013154587,0.03902806,0.010696828,0.0024978037],"study_design_scores_gemma":[0.00015033988,0.000008722698,0.0000049194014,0.0003693012,0.0000633251,0.000022739776,0.0006447636,0.91201854,0.0003976456,0.00001547718,0.08588193,0.00042229335],"about_ca_topic_score_codex":0.000005601803,"about_ca_topic_score_gemma":0.0000053276353,"teacher_disagreement_score":0.8996455,"about_ca_system_score_codex":0.00013723655,"about_ca_system_score_gemma":0.000027968992,"threshold_uncertainty_score":0.9998296},"labels":[],"label_agreement":null},{"id":"W4405632789","doi":"10.1016/j.datak.2024.102393","title":"Coupling MDL and Markov chain Monte Carlo to sample diverse pattern sets","year":2024,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Markov chain Monte Carlo; Coupling (piping); Statistical physics; Monte Carlo method; Markov chain; Computer science; Sample (material); Algorithm; Physics; Mathematics; Statistics; Machine learning; Materials science; Thermodynamics","score_opus":0.033426819862946294,"score_gpt":0.28473330654046375,"score_spread":0.2513064866775174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405632789","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":[0.0029856742,0.0018495345,0.9933626,0.00022438128,0.00045671445,0.00013456646,0.00019748622,0.00073767867,0.000051373834],"genre_scores_gemma":[0.88496184,0.0002530274,0.113934815,0.00006855298,0.00030217724,0.000042935626,0.00011244684,0.000049498387,0.00027468315],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903935,0.0000072753173,0.00014713744,0.00047253896,0.00011453621,0.0002191691],"domain_scores_gemma":[0.9990206,0.00013698787,0.000012762084,0.0006760097,0.000036508573,0.00011716906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029969445,0.00013961912,0.0001184291,0.00015111672,0.000057155252,0.00031170872,0.00082593755,0.00004115988,0.0000072619905],"category_scores_gemma":[0.00010031936,0.00013661836,0.000020719546,0.00038561292,0.000010498127,0.00055103266,0.0011133177,0.00013809244,0.000056307366],"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":[0.0000020715652,0.000022775948,0.00016470518,0.0002885788,0.000033791293,0.000036292673,0.001278664,0.000051535073,0.0026820502,0.0015186672,0.0048134304,0.98910743],"study_design_scores_gemma":[0.00003995921,0.000016878932,0.00032510405,0.00011342676,0.000005885486,0.0000065990694,0.0000177233,0.9463562,0.0009792682,0.000011169617,0.05196174,0.0001660621],"about_ca_topic_score_codex":0.000046201385,"about_ca_topic_score_gemma":0.000011037169,"teacher_disagreement_score":0.9889414,"about_ca_system_score_codex":0.000045249977,"about_ca_system_score_gemma":0.000026458476,"threshold_uncertainty_score":0.55711347},"labels":[],"label_agreement":null},{"id":"W4408912911","doi":"10.1016/j.datak.2025.102440","title":"Customized long short-term memory architecture for multi-document summarization with improved text feature set","year":2025,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Automatic summarization; Computer science; Term (time); Feature (linguistics); Set (abstract data type); Information retrieval; Architecture; Natural language processing; Artificial intelligence; Programming language; History; Linguistics","score_opus":0.023473699877713024,"score_gpt":0.2815724607136532,"score_spread":0.2580987608359402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408912911","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":[0.0023120823,0.00065380556,0.9950447,0.00018602196,0.0006722948,0.0006768138,0.000057272686,0.0003186132,0.00007838948],"genre_scores_gemma":[0.08574759,0.000016118142,0.91112393,0.000065875814,0.00028045682,0.00017959179,0.0009280503,0.000050638286,0.0016077615],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985876,0.000023607236,0.0002223399,0.0006981401,0.00011189374,0.00035639346],"domain_scores_gemma":[0.99828744,0.00011778441,0.000038717444,0.0013874556,0.00008707108,0.00008151735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030331462,0.0002562771,0.00025822187,0.00020468724,0.000099392055,0.00020433604,0.0014983198,0.00010372908,0.0000021060428],"category_scores_gemma":[0.00010620306,0.00022480659,0.000044025368,0.0003563086,0.000013015371,0.00047107862,0.0008100041,0.00026399735,0.0000032780717],"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":[0.0001214751,0.00016476765,0.00067969994,0.0014573685,0.00042323305,0.000023052631,0.0029069518,0.025692072,0.017114524,0.0040222504,0.0038515842,0.943543],"study_design_scores_gemma":[0.0011198762,0.000017412522,0.0003098304,0.00017490648,0.000033559914,0.000005311671,0.000014032708,0.99145776,0.00220277,0.0000124989465,0.0044009257,0.00025111742],"about_ca_topic_score_codex":0.0000063485395,"about_ca_topic_score_gemma":0.000092906295,"teacher_disagreement_score":0.9657657,"about_ca_system_score_codex":0.00009361811,"about_ca_system_score_gemma":0.00011400259,"threshold_uncertainty_score":0.91673464},"labels":[],"label_agreement":null},{"id":"W4411507372","doi":"10.1016/j.datak.2025.102480","title":"Large language models for conceptual modeling: Assessment and application potential","year":2025,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Fundação para a Ciência e a Tecnologia; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science","score_opus":0.029500594423617237,"score_gpt":0.3180202898758975,"score_spread":0.28851969545228023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411507372","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":[0.0038646536,0.0019304095,0.9931133,0.000097670054,0.00027451367,0.00019912874,0.000052832136,0.00019778438,0.00026972612],"genre_scores_gemma":[0.86018604,0.000023993154,0.13946468,0.000025461975,0.000066266926,0.00004592255,0.00013367557,0.0000061925734,0.00004774886],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999259,0.000008281281,0.00013392139,0.00034805833,0.00005778546,0.00019292913],"domain_scores_gemma":[0.999236,0.000062743275,0.000016866534,0.00061435805,0.000038169183,0.000031879023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023756908,0.00009758831,0.00012401574,0.000072616946,0.00006677007,0.00008258955,0.00073037157,0.0000463368,5.0389207e-7],"category_scores_gemma":[0.000029298682,0.00009666874,0.00001809219,0.000114902236,0.00001107018,0.00042510056,0.000681741,0.00007059562,0.0000017459514],"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":[0.000004270089,0.000094861825,0.000032899745,0.00017083756,0.00006403995,0.000002851126,0.0017452809,0.025420206,0.0028648244,0.8582488,0.0013321636,0.11001902],"study_design_scores_gemma":[0.00030692862,0.0000074768714,0.000040785108,0.000018026676,0.0000119378765,0.0000013212212,0.00022049515,0.9965616,0.00010685395,0.00082543486,0.001800497,0.000098667006],"about_ca_topic_score_codex":0.0000069540215,"about_ca_topic_score_gemma":0.000008988994,"teacher_disagreement_score":0.9711414,"about_ca_system_score_codex":0.000022891876,"about_ca_system_score_gemma":0.00004981051,"threshold_uncertainty_score":0.39420366},"labels":[],"label_agreement":null},{"id":"W4411540031","doi":"10.1016/j.datak.2025.102482","title":"Domain knowledge in artificial intelligence: Using conceptual modeling to increase machine learning accuracy and explainability","year":2025,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Artificial intelligence; Computer science; Domain (mathematical analysis); Machine learning; Domain knowledge; Artificial Intelligence System; Mathematics","score_opus":0.06691927417424057,"score_gpt":0.33926893247535406,"score_spread":0.27234965830111346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411540031","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":[0.14754272,0.0011903007,0.8501359,0.00017862406,0.00028875415,0.000216162,0.000024834184,0.00019972427,0.00022295552],"genre_scores_gemma":[0.90180355,0.000024534358,0.09783458,0.000019140507,0.000096452146,0.000021813188,0.00015661566,0.000017307759,0.00002597387],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99785763,0.000208543,0.0005190331,0.0008911419,0.00012177945,0.00040184773],"domain_scores_gemma":[0.9980868,0.0005160269,0.000055156237,0.0010978455,0.00008466942,0.00015951133],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016811909,0.00025636362,0.0002911777,0.0005122308,0.00019612595,0.00024418713,0.0013152265,0.00009464168,0.000006479631],"category_scores_gemma":[0.0017831986,0.00027979995,0.000025906767,0.0011879462,0.0000396167,0.00090265897,0.0021154578,0.0005805095,0.000026862193],"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":[0.000051187828,0.00033346922,0.0027645214,0.00035433183,0.000037532747,0.000016925658,0.008983845,0.107815444,0.005358594,0.27260888,0.00008330066,0.60159194],"study_design_scores_gemma":[0.000110384965,0.000019112756,0.00027021006,0.00015349292,0.000007396895,0.000004737663,0.00042251128,0.991344,0.00013192107,0.00058306305,0.006690996,0.0002621753],"about_ca_topic_score_codex":0.0003183823,"about_ca_topic_score_gemma":0.000246959,"teacher_disagreement_score":0.88352853,"about_ca_system_score_codex":0.00016382389,"about_ca_system_score_gemma":0.00016446077,"threshold_uncertainty_score":0.9999654},"labels":[],"label_agreement":null},{"id":"W4412980931","doi":"10.1016/j.datak.2025.102499","title":"Corrigendum to “Large Language Models for Conceptual Modeling: Assessment and Application Potential” [Knowledge and Data Engineering Volume 160, November 2025, 102480]","year":2025,"lang":"en","type":"erratum","venue":"Data & Knowledge Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Volume (thermodynamics); Computer science; Conceptual model; Data science; Database; Physics","score_opus":0.04627239330600777,"score_gpt":0.3163658736183723,"score_spread":0.2700934803123646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412980931","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":[0.000040897958,0.0154406335,0.96579975,0.00010039028,0.012968363,0.0012404041,0.0032422985,0.00047116473,0.0006960836],"genre_scores_gemma":[0.025184482,0.0014318654,0.85809404,0.0002007008,0.0073968736,0.0010669294,0.042550355,0.00052486034,0.06354989],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99528915,0.0000379216,0.00078563765,0.0026326003,0.00033816588,0.000916539],"domain_scores_gemma":[0.9943653,0.00010744819,0.00013518588,0.004777072,0.00023830803,0.0003766876],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0010744828,0.0007948877,0.0008633182,0.00052989763,0.00020102048,0.0004922353,0.0046156826,0.0005243515,0.000007136638],"category_scores_gemma":[0.00019004404,0.0009272375,0.00007047363,0.0004936509,0.00002496529,0.0014444855,0.009784036,0.000977141,0.000015183138],"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":[0.000012201615,0.0002730143,0.00001228479,0.0034480693,0.00050115865,0.000021769963,0.0033129435,0.09341214,0.00062787853,0.03069008,0.7660681,0.10162038],"study_design_scores_gemma":[0.00038711564,0.000020423051,0.0000072461066,0.00035200667,0.000100252764,0.0000073908436,0.000064297834,0.76411396,0.00000434316,0.000033893677,0.23423742,0.0006716223],"about_ca_topic_score_codex":0.000052719024,"about_ca_topic_score_gemma":0.00009081574,"teacher_disagreement_score":0.67070186,"about_ca_system_score_codex":0.00023083169,"about_ca_system_score_gemma":0.00054022827,"threshold_uncertainty_score":0.9993178},"labels":[],"label_agreement":null},{"id":"W4413052970","doi":"10.1016/j.datak.2025.102500","title":"Corrigendum to “Domain knowledge in artificial intelligence: Using conceptual modeling to increase machine learning accuracy and explainability” [Knowledge and Data Engineering Volume 160, November 2025, 102482]","year":2025,"lang":"en","type":"erratum","venue":"Data & Knowledge Engineering","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Computer science; Domain knowledge; Artificial intelligence; Domain (mathematical analysis); Volume (thermodynamics); Machine learning; Knowledge engineering; Mathematics","score_opus":0.08647812660475818,"score_gpt":0.3363630339300379,"score_spread":0.24988490732527974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413052970","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":[0.0024787565,0.012756038,0.9694457,0.00027200315,0.011465122,0.0010827109,0.0012267901,0.0005604174,0.0007124765],"genre_scores_gemma":[0.18678826,0.0027982828,0.6892267,0.0003173668,0.013253903,0.00081647706,0.062424656,0.0014179047,0.042956457],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9929832,0.00035798372,0.001490739,0.0035198433,0.00040631366,0.0012419086],"domain_scores_gemma":[0.9934874,0.0006866326,0.00022810402,0.004539991,0.0002962784,0.00076157204],"candidate_categories":["metaepi_narrow","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0032577312,0.0011825225,0.0012783494,0.0018001433,0.00038197692,0.0008987782,0.005350573,0.0006334391,0.000033281438],"category_scores_gemma":[0.0063778316,0.0013823294,0.00007170892,0.002408631,0.00007915158,0.001907009,0.015189141,0.0030250177,0.00011389428],"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":[0.00020774324,0.0014005317,0.0011791424,0.0075163036,0.00054118806,0.00019906719,0.029208105,0.1134738,0.0021187908,0.025285376,0.20750576,0.6113642],"study_design_scores_gemma":[0.00015415435,0.000051315907,0.000086825,0.0010898544,0.00005186854,0.000020107107,0.00024438166,0.73562825,0.000009950872,0.000030481937,0.26166552,0.00096730184],"about_ca_topic_score_codex":0.00076442916,"about_ca_topic_score_gemma":0.0014051938,"teacher_disagreement_score":0.6221544,"about_ca_system_score_codex":0.0005121934,"about_ca_system_score_gemma":0.0008858722,"threshold_uncertainty_score":0.999275},"labels":[],"label_agreement":null},{"id":"W4416703099","doi":"10.1016/j.datak.2025.102536","title":"Enhancing clustering stability, compactness, and separation in multimodal data environments","year":2025,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Ministério da Ciência, Tecnologia, Inovações e Comunicações","keywords":"Cluster analysis; Benchmark (surveying); Stability (learning theory); Rand index; Hierarchical clustering; Benchmarking; Consensus clustering; Embedding; Focus (optics); Core (optical fiber)","score_opus":0.04420924631857913,"score_gpt":0.29964580499908583,"score_spread":0.2554365586805067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416703099","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7616834,0.0013356702,0.23009847,0.00022084395,0.0015108287,0.00080474035,0.00014173728,0.00023401322,0.003970316],"genre_scores_gemma":[0.9960979,0.000024363637,0.0013637904,0.000054340726,0.00022798989,0.00000870134,0.0021585664,0.000017336894,0.00004697362],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99895436,0.000008124009,0.0002826005,0.00045054202,0.00009604168,0.00020831656],"domain_scores_gemma":[0.99915963,0.000058359572,0.000049006783,0.00071048853,0.000011105701,0.000011412786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004998313,0.00015604403,0.0001720022,0.0002600007,0.00007124728,0.00020550194,0.00049474137,0.000046186746,0.000029538645],"category_scores_gemma":[0.00012518515,0.00017541854,0.000009498923,0.000311637,0.000017918528,0.002421553,0.0023140556,0.0001318834,0.00004269436],"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":[0.00022489816,0.0012997757,0.24216343,0.0075628203,0.00031238236,0.00003912872,0.0023041577,0.004898496,0.2570936,0.0032144578,0.00619777,0.47468907],"study_design_scores_gemma":[0.0005348607,0.0000012812571,0.034069613,0.0001309237,0.000024980593,4.439456e-7,0.00016470662,0.9514252,0.00032845067,0.000014851773,0.013140458,0.00016423319],"about_ca_topic_score_codex":0.00025763043,"about_ca_topic_score_gemma":0.0018348015,"teacher_disagreement_score":0.9465267,"about_ca_system_score_codex":0.00006556023,"about_ca_system_score_gemma":0.0000134644515,"threshold_uncertainty_score":0.715336},"labels":[],"label_agreement":null}]}