{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":41,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":41,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"f029b2e5f93c","filters":{"venue":"Data & Knowledge Engineering"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2068040600089384,"gpt":0.3213727864468606,"spread":0.1145687264379222,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002273193,0.0000908603,0.0001919034,0.00006981372,0.00003033144,0.00003504944,0.0004431963,0.00004317294,0.000001685513],"category_scores_gemma":[0.00006103815,0.00008423061,0.000007758743,0.00007380784,0.00009879978,0.000502769,0.0006980436,0.0001259648,0.000001843641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001499552,"about_ca_system_score_gemma":0.00002572664,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002588515,"about_ca_topic_score_gemma":0.0001216695,"domain_scores_codex":[0.9993191,0.00001775521,0.0002025757,0.0002458871,0.00007966129,0.0001350291],"domain_scores_gemma":[0.9995532,0.00004579099,0.00002311222,0.0003116944,0.00002732104,0.00003889999],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007647307,0.001262172,0.1095713,0.001326634,0.0001628042,0.00001445494,0.04012346,0.03489918,0.01074694,0.4806792,0.001644273,0.3194931],"study_design_scores_gemma":[0.0002241891,0.00001411962,0.008797843,0.00004344913,0.000002738082,0.000004472856,0.0001442938,0.9894146,0.0002750837,0.00005673995,0.0009252313,0.00009724808],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7649767,0.007917881,0.2266285,0.0001109258,0.00009631587,0.00008146682,0.0000190077,0.00007051418,0.00009866662],"genre_scores_gemma":[0.9417224,0.00003368832,0.05817609,0.000005983918,0.00003792866,0.000002249148,0.00001433807,0.000003363551,0.000003950879],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9545154,"threshold_uncertainty_score":0.3434825,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03013581955046483,"gpt":0.2583486271505941,"spread":0.2282128076001293,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003803062,0.0001652028,0.0002343122,0.000102986,0.00007008075,0.0001284699,0.0004373655,0.00009274278,4.52043e-7],"category_scores_gemma":[0.00002615193,0.0001631891,0.00002299206,0.0001260826,0.00001166582,0.0008864878,0.0004517922,0.0001047783,2.397226e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002538006,"about_ca_system_score_gemma":0.0000171357,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004875147,"about_ca_topic_score_gemma":0.00007451303,"domain_scores_codex":[0.9989553,0.00002508738,0.0003302803,0.0003805296,0.00009707328,0.0002117263],"domain_scores_gemma":[0.9991613,0.0001180348,0.0001194207,0.0004713885,0.00007602657,0.00005383758],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001994304,0.0001866121,0.8776051,0.004088221,0.0002068142,0.00001926041,0.002671586,0.00002971145,0.02864679,0.02118962,0.006902366,0.058434],"study_design_scores_gemma":[0.0008705874,0.00006617182,0.03945971,0.0008073795,0.00001850115,0.0000183616,0.0001001419,0.9497548,0.00173504,0.00003669231,0.006879447,0.0002531283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7628296,0.0007037088,0.2349301,0.00008313589,0.0006268543,0.000353594,0.0001425514,0.0002729338,0.00005748745],"genre_scores_gemma":[0.9667707,0.00003017606,0.03273155,0.000006885795,0.0002124643,0.00002566633,0.0001698653,0.00002159316,0.00003109115],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9497252,"threshold_uncertainty_score":0.6654657,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05562206053334146,"gpt":0.2879527423906523,"spread":0.2323306818573109,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001715842,0.0003577741,0.0003832351,0.000147296,0.0002853672,0.0004477024,0.002568144,0.0001122716,0.000003240793],"category_scores_gemma":[0.0008591687,0.0002772148,0.00009797751,0.0004491321,0.0000981108,0.0009895324,0.001093125,0.0004798523,0.00004680631],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008306347,"about_ca_system_score_gemma":0.000219988,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005242854,"about_ca_topic_score_gemma":0.001190141,"domain_scores_codex":[0.9975635,0.00006342433,0.0005496275,0.0008498347,0.0001996825,0.0007739195],"domain_scores_gemma":[0.9960417,0.001087762,0.0001144306,0.002382209,0.0001712233,0.0002026791],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000668346,0.0008457435,0.009182418,0.003307548,0.0003199284,0.0001509809,0.003266337,0.00006354248,0.0190269,0.6273285,0.01139465,0.3250466],"study_design_scores_gemma":[0.0007315585,0.00005155501,0.002181541,0.0004060371,0.00003166293,0.00009638934,0.0002639345,0.6499594,0.0008074042,0.00003382256,0.3448209,0.0006156866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07192456,0.01370325,0.8768162,0.0002592513,0.02199094,0.004119345,0.0009596533,0.002587637,0.007639124],"genre_scores_gemma":[0.941013,0.00006540693,0.05710709,0.00001228937,0.0006653691,0.000355376,0.0005393531,0.00006540387,0.0001766874],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8690885,"threshold_uncertainty_score":0.999968,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.02252072736554118,"gpt":0.2728181693191338,"spread":0.2502974419535927,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004061922,0.0001899172,0.0001865555,0.0001993931,0.0001060122,0.0002340393,0.002035656,0.00007091455,0.000002902912],"category_scores_gemma":[0.0001847543,0.0001943869,0.00002946902,0.0005443951,0.00001002811,0.0007921478,0.000673693,0.0001317401,0.00003422016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003041499,"about_ca_system_score_gemma":0.00004339328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000355147,"about_ca_topic_score_gemma":0.000001067666,"domain_scores_codex":[0.9987097,0.00002173169,0.000296135,0.0004921056,0.0001297715,0.0003505597],"domain_scores_gemma":[0.9985397,0.00007302484,0.00007598584,0.001158064,0.0000577831,0.0000954554],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002791918,0.0001302517,0.00006156053,0.00004961788,0.00003108665,0.00001516458,0.0008521869,0.004067713,0.01635497,0.01882099,0.01055676,0.9490569],"study_design_scores_gemma":[0.0001090411,0.0000336357,0.0004872927,0.00005838272,0.000003827007,0.000006822065,0.000003008361,0.9888338,0.003861757,0.0004193727,0.00592464,0.0002583974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001429774,0.0007804515,0.9941354,0.0001606467,0.0003123985,0.00009957775,0.000004366862,0.001767362,0.001310059],"genre_scores_gemma":[0.3325177,0.00003439026,0.666806,0.00009733884,0.0002687318,0.000005699797,0.00006395108,0.00001911545,0.000186993],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9847661,"threshold_uncertainty_score":0.7926866,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1037152150446969,"gpt":0.306164189747526,"spread":0.2024489747028291,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001986814,0.0003822653,0.0005179733,0.0008558012,0.0003102128,0.001034602,0.1745504,0.0002295404,0.00001685329],"category_scores_gemma":[0.08517772,0.0004013293,0.00009950461,0.002953128,0.000061493,0.01437787,0.4642628,0.0005596271,0.00004261152],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001163404,"about_ca_system_score_gemma":0.0001395612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005433388,"about_ca_topic_score_gemma":0.00006196624,"domain_scores_codex":[0.996139,0.00005517829,0.0005900979,0.001915258,0.0004201,0.0008803129],"domain_scores_gemma":[0.94056,0.001069262,0.0001712667,0.05780837,0.0001942851,0.0001967765],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004400012,0.00007556752,0.001228642,0.0001250701,0.0005282809,0.00001559518,0.0001764376,0.0002070914,0.0001829335,0.0006174471,0.9718426,0.02499587],"study_design_scores_gemma":[0.0003160637,0.00001164813,0.0007378135,0.00003924741,0.0001001043,0.00002129709,0.000007225945,0.8643259,0.0001836136,0.0007693323,0.1330822,0.0004055985],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001526196,0.001338485,0.9861247,0.006046459,0.0008047386,0.0003611238,0.001536275,0.001938484,0.0003235228],"genre_scores_gemma":[0.02653124,0.0001213424,0.9663882,0.00008810091,0.0003743293,0.00004938721,0.006296076,0.00005938605,0.00009190698],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8641188,"threshold_uncertainty_score":0.9998438,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04931219236959951,"gpt":0.3094819476933262,"spread":0.2601697553237267,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002519094,0.0001472722,0.0001180398,0.0002472433,0.00007370016,0.0004071466,0.0008940719,0.00007670767,0.000004944014],"category_scores_gemma":[0.0001231538,0.0001400477,0.00001987578,0.0005601778,0.00003425457,0.001286346,0.0007719047,0.0001800129,0.00009020637],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007620501,"about_ca_system_score_gemma":0.00003418062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005098803,"about_ca_topic_score_gemma":0.000002220187,"domain_scores_codex":[0.9989894,0.00001694631,0.0001609418,0.0005411881,0.00009655448,0.0001949833],"domain_scores_gemma":[0.9988191,0.0001900226,0.00002473445,0.0008875146,0.00002819763,0.00005040084],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[8.676244e-7,0.00002347563,0.00009825209,0.0001527444,0.00003624986,0.000005839518,0.0004128938,0.00001672452,0.02223007,0.1486993,0.002350505,0.825973],"study_design_scores_gemma":[0.00006077505,0.00001190403,0.001815586,0.00008393756,0.0000108021,0.00001295044,0.00002606875,0.9251232,0.001904855,0.0002897153,0.0705009,0.0001593432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008288466,0.006318005,0.9817908,0.0003773586,0.0007573832,0.0002188747,0.00002400855,0.001592662,0.0006323743],"genre_scores_gemma":[0.9438424,0.0001292412,0.05555006,0.000009459266,0.0001516366,0.00004043996,0.0000644263,0.00002555523,0.0001867975],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9355539,"threshold_uncertainty_score":0.5710978,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.07354628162855453,"gpt":0.3157645917063224,"spread":0.2422183100777679,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004098205,0.000385805,0.0003829757,0.0003537515,0.00007352676,0.0002559702,0.0007206149,0.0001619376,0.000006477763],"category_scores_gemma":[0.0001547356,0.000415589,0.0001065855,0.0005345274,0.000008893289,0.0005203139,0.0001833762,0.0002910799,0.00008553124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001372366,"about_ca_system_score_gemma":0.00002796899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005601803,"about_ca_topic_score_gemma":0.000005327635,"domain_scores_codex":[0.9982722,0.00001356922,0.0004527238,0.000506429,0.0001365392,0.0006185767],"domain_scores_gemma":[0.998179,0.0006235449,0.00001889892,0.001009238,0.0000502418,0.0001190665],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001153699,0.0000232616,0.000001577138,0.003244034,0.0002876915,0.00001178882,0.002337536,0.9287157,0.01315459,0.03902806,0.01069683,0.002497804],"study_design_scores_gemma":[0.0001503399,0.000008722698,0.000004919401,0.0003693012,0.0000633251,0.00002273978,0.0006447636,0.9120185,0.0003976456,0.00001547718,0.08588193,0.0004222933],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003072546,0.03158188,0.9555716,0.00002027833,0.003156071,0.0006151502,0.001527993,0.004161814,0.0002926968],"genre_scores_gemma":[0.9027181,0.0002779238,0.09121478,0.000002833004,0.002037492,0.001167703,0.001811362,0.0004403841,0.0003294623],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8996455,"threshold_uncertainty_score":0.9998296,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04019297403125713,"gpt":0.2642967261602062,"spread":0.2241037521289491,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001696253,0.0003717488,0.0003451848,0.0004268324,0.0001608647,0.001416083,0.1049835,0.0002274217,0.00002539728],"category_scores_gemma":[0.07867241,0.0003944536,0.00005714437,0.001048527,0.00004656503,0.008616095,0.2578349,0.0008085549,0.0001391097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001318333,"about_ca_system_score_gemma":0.00008496379,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003995664,"about_ca_topic_score_gemma":0.00002513678,"domain_scores_codex":[0.9969972,0.00008499795,0.0004438946,0.00124706,0.0003974234,0.0008294752],"domain_scores_gemma":[0.9698563,0.000722671,0.0001252026,0.02896617,0.0001114824,0.0002182108],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002123328,0.0001060245,0.0005003645,0.0002149204,0.00006961339,0.00001576937,0.0002279492,0.00008923356,0.002460872,0.007774249,0.6205953,0.3679436],"study_design_scores_gemma":[0.0002281657,0.00002023527,0.0007669864,0.0001164906,0.000008022851,0.0000137078,0.00001099245,0.8619301,0.001285079,0.003212973,0.1320097,0.0003975806],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004155325,0.001002262,0.9807773,0.003501168,0.001604542,0.0001921753,0.0001156216,0.004089155,0.004562454],"genre_scores_gemma":[0.1476479,0.00005358463,0.8509982,0.00006953238,0.0005982941,0.00003205697,0.0004451663,0.0000809137,0.00007444621],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8618408,"threshold_uncertainty_score":0.9998507,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1526888925603266,"gpt":0.3559568294766817,"spread":0.2032679369163551,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009966115,0.0001913234,0.0001616471,0.0002033815,0.0002223657,0.0002040927,0.001058525,0.00009183252,0.000002302849],"category_scores_gemma":[0.0002478801,0.0002090163,0.00003865441,0.0006390592,0.00001439167,0.0007554052,0.000197131,0.0001496407,0.00004175855],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001498147,"about_ca_system_score_gemma":0.00009879238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001269052,"about_ca_topic_score_gemma":0.00004722614,"domain_scores_codex":[0.9984755,0.00002055065,0.0003438344,0.0006513313,0.0001587771,0.0003500273],"domain_scores_gemma":[0.998504,0.0002711075,0.0001265091,0.0007930297,0.0001983753,0.0001069333],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[7.46868e-7,0.0001808018,0.00001703095,0.00001340042,0.00001712757,3.457908e-7,0.000125045,2.335334e-7,0.002992515,0.0009751442,0.00213753,0.9935401],"study_design_scores_gemma":[0.0005923766,0.00003392663,0.001002312,0.00002490215,0.00001509074,0.000001339904,0.00002536666,0.9871152,0.001640552,0.000005175317,0.009304229,0.0002395479],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002651029,0.0003057951,0.9971143,0.00007208563,0.0008084655,0.0003850968,0.0006267375,0.0003479097,0.00007452199],"genre_scores_gemma":[0.00009094799,0.00001104152,0.9960799,0.00001749337,0.0005288424,0.0001604088,0.002928495,0.00002620325,0.0001566271],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9933006,"threshold_uncertainty_score":0.8523439,"prediction_status":"machine_predicted_unvalidated"},"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":"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06113214184253724,"gpt":0.2597888943664013,"spread":0.1986567525238641,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005664471,0.0002436434,0.0001899433,0.0001034083,0.0000816754,0.0001295642,0.001640762,0.00009432356,0.00001946097],"category_scores_gemma":[0.00003568929,0.0002321574,0.00003145219,0.0002016122,0.0000202035,0.001843994,0.0005500687,0.0002981604,0.00001290672],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000516803,"about_ca_system_score_gemma":0.0001401539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000236245,"about_ca_topic_score_gemma":0.000792049,"domain_scores_codex":[0.9982632,0.0000243781,0.0002711024,0.0007332951,0.0003221343,0.0003858871],"domain_scores_gemma":[0.9984378,0.00006717893,0.00005017115,0.001165649,0.00008629303,0.0001928786],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002186309,0.002844686,0.0008151999,0.001032182,0.0002741033,0.00002841734,0.04322544,0.2018656,0.273825,0.1444255,0.0009635103,0.3304817],"study_design_scores_gemma":[0.0005397056,0.00008632302,0.002171937,0.00002717863,0.000009343547,0.00000544439,0.0001195476,0.9833861,0.001785722,0.0004203145,0.01115142,0.0002969477],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1082799,0.0003280198,0.8890134,0.0001680204,0.001141221,0.0005275006,0.0001418982,0.0002474675,0.0001526434],"genre_scores_gemma":[0.9123219,0.000006483681,0.08652043,0.0001297987,0.0005215117,0.0001376157,0.0003209955,0.0000324942,0.000008829927],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.804042,"threshold_uncertainty_score":0.9467102,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02300508494314149,"gpt":0.2321864369908625,"spread":0.209181352047721,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001087038,0.0002007569,0.0001691635,0.0001127163,0.00007871657,0.0009008776,0.001226964,0.00004159949,0.00000529313],"category_scores_gemma":[0.0001291887,0.0001941127,0.00005082151,0.0003017659,0.00003451807,0.002693376,0.0007711345,0.00008624576,0.000223727],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004424399,"about_ca_system_score_gemma":0.00006853037,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001155468,"about_ca_topic_score_gemma":0.0000175279,"domain_scores_codex":[0.9987897,0.000004813422,0.0002486324,0.0004413346,0.0001318579,0.0003836167],"domain_scores_gemma":[0.9985476,0.0001581365,0.00004112622,0.001001645,0.00008454589,0.000166949],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003283369,0.0001658308,0.0003896834,0.0005495517,0.0001173596,0.000008035715,0.0005870084,0.002697739,0.0009105752,0.053773,0.0364923,0.9043056],"study_design_scores_gemma":[0.0002446545,0.00003419963,0.0002466253,0.00007350635,0.000007649985,0.000005516285,0.000008895027,0.9771532,0.0007371469,0.001418581,0.01980945,0.0002605248],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006381615,0.0001223755,0.9907607,0.0002174032,0.000640729,0.0003830612,0.000111874,0.0003797278,0.001002522],"genre_scores_gemma":[0.8234453,0.000001876692,0.1745082,0.0001030608,0.0002473028,0.0001738758,0.001072483,0.00004979402,0.0003980605],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9744555,"threshold_uncertainty_score":0.8687183,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada; Western University","funders":"","keywords":"Enterprise integration; Business; Process management; Enterprise software","retraction":null,"screen_n_in":null,"score":{"opus":0.08516768738760731,"gpt":0.4081140141277604,"spread":0.3229463267401531,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001365215,0.0001266626,0.0001495858,0.0001436356,0.0001637867,0.000299856,0.0007274818,0.00005232869,0.00004688251],"category_scores_gemma":[0.001821049,0.0001055639,0.00003869116,0.0002765413,0.00005436168,0.0007761987,0.0002853488,0.00009256765,0.0001189033],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003073513,"about_ca_system_score_gemma":0.00002808891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000247216,"about_ca_topic_score_gemma":0.00001558626,"domain_scores_codex":[0.9988411,0.00002203975,0.0003511937,0.0004614402,0.0001602777,0.0001639658],"domain_scores_gemma":[0.9983643,0.0006097005,0.00007604134,0.0007382456,0.0001165623,0.00009519458],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002645242,0.0005519039,0.002100735,0.0001112935,0.0001109794,0.000004297068,0.008292696,0.002405532,0.01715563,0.1299204,0.01624897,0.8228331],"study_design_scores_gemma":[0.002051981,0.00009865245,0.005955846,0.0001800338,0.00005006346,0.00004537166,0.001129458,0.4213112,0.01162773,0.03775096,0.5191088,0.0006899331],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08587217,0.0005501919,0.9116827,0.0001563222,0.0004538118,0.0002638439,0.0003541454,0.00009977075,0.0005670488],"genre_scores_gemma":[0.9838482,0.00004153558,0.01429221,0.00002257289,0.0002643742,0.000090166,0.0001926366,0.00002062119,0.001227709],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.897976,"threshold_uncertainty_score":0.430477,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06344754137285828,"gpt":0.3806975017838266,"spread":0.3172499604109683,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001761459,0.0001538534,0.0002188736,0.000107496,0.0003534935,0.0002852979,0.0008544903,0.0000910688,0.00005967268],"category_scores_gemma":[0.0006337023,0.000152794,0.00005397241,0.0002810367,0.00003664425,0.0005481283,0.0000942149,0.0001239546,0.00002740001],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001482453,"about_ca_system_score_gemma":0.0001782675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008693116,"about_ca_topic_score_gemma":0.00145551,"domain_scores_codex":[0.9985969,0.00007364287,0.0002547885,0.0003346991,0.0003217854,0.0004182056],"domain_scores_gemma":[0.9988084,0.0004145914,0.00007664209,0.0003609826,0.0002521208,0.00008729062],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002354497,0.001351188,0.01418507,0.0007534332,0.0006022059,0.00001406114,0.006367222,0.4547422,0.004580232,0.155225,0.06434496,0.297599],"study_design_scores_gemma":[0.001070757,0.000007239467,0.002229719,0.00004234826,0.00008590448,2.843204e-7,0.00007942275,0.920154,0.00004793374,0.0001041371,0.07598655,0.000191707],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1450154,0.02129097,0.7844322,0.001892857,0.006810693,0.005721744,0.002557749,0.001363129,0.03091525],"genre_scores_gemma":[0.9972783,0.00001022624,0.0004997138,0.00001941044,0.001521754,0.00005351631,0.0005044467,0.00002407175,0.00008855923],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8522629,"threshold_uncertainty_score":0.6230759,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0577024843604405,"gpt":0.2827958738468403,"spread":0.2250933894863998,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000319387,0.0001659742,0.0001896493,0.00007897551,0.0001396665,0.0001390368,0.0004817066,0.00003588834,0.000007099898],"category_scores_gemma":[0.0001268684,0.0001636859,0.00001501045,0.0002745225,0.00001262281,0.001729883,0.0008453011,0.00009492777,0.00004238788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002824703,"about_ca_system_score_gemma":0.00002228348,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000250779,"about_ca_topic_score_gemma":0.00006582506,"domain_scores_codex":[0.9988936,0.00002508607,0.0002466194,0.0004432851,0.00008971312,0.0003016968],"domain_scores_gemma":[0.9989333,0.00005266454,0.00005034405,0.0008177169,0.00004568981,0.0001002716],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004120832,0.0002811063,0.002094593,0.001302093,0.0002338603,0.0004747452,0.007630446,0.0007886342,0.1711292,0.2207682,0.01515642,0.5800995],"study_design_scores_gemma":[0.000277659,0.00003531048,0.0003925654,0.0001740314,0.000008060771,0.0002009812,0.00005343207,0.3635798,0.002296767,0.00002611415,0.6325634,0.0003919412],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01188475,0.001327723,0.985107,0.00004787896,0.0007142583,0.0001220729,0.00006895684,0.0004637207,0.000263645],"genre_scores_gemma":[0.2993267,0.0004860096,0.6976799,0.00007425396,0.001254578,0.00007753138,0.0006936949,0.00009605613,0.000311266],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6174069,"threshold_uncertainty_score":0.6674917,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0151796263670819,"gpt":0.2519409794108211,"spread":0.2367613530437392,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003847527,0.0002109683,0.0002473075,0.0001521717,0.00007986178,0.00006558894,0.0003083812,0.000127101,0.00002501274],"category_scores_gemma":[0.001165147,0.0002188856,0.00004311258,0.000367744,0.00004048179,0.0002621129,0.000180298,0.0003339954,0.00002973197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000949997,"about_ca_system_score_gemma":0.00002292042,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001806943,"about_ca_topic_score_gemma":0.000004436551,"domain_scores_codex":[0.9988229,0.00001528557,0.0002730849,0.0003507109,0.0001000028,0.0004380544],"domain_scores_gemma":[0.998961,0.0004015589,0.00002581876,0.0004415032,0.00005962807,0.0001104982],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004344317,0.00001005672,0.00002855837,0.0003678456,0.0000442259,0.000001776723,0.0003860969,0.9871569,0.0001373545,0.002823902,0.00203689,0.006962995],"study_design_scores_gemma":[0.0004429934,0.00005768453,0.0001293295,0.0002504019,0.00002189366,0.000001103288,0.00004939542,0.9624031,0.0001734157,0.0003500323,0.03589674,0.0002239695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008190874,0.0002793643,0.9962403,0.00005534691,0.0007003124,0.0004450754,0.00005766993,0.0009104589,0.0004923776],"genre_scores_gemma":[0.8465778,0.001090084,0.1468556,0.00004430668,0.000893839,0.0005807516,0.00308114,0.0002545026,0.0006219138],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8493847,"threshold_uncertainty_score":0.8925897,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02709674014065473,"gpt":0.2344229936000985,"spread":0.2073262534594438,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003073956,0.0002086336,0.0001841075,0.0001378957,0.00009571339,0.0003540949,0.0009758302,0.00003440545,0.00001554127],"category_scores_gemma":[0.00008187606,0.0001758067,0.00001456096,0.0003403313,0.00006326046,0.002184017,0.0003638131,0.000166574,0.00001010525],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002085929,"about_ca_system_score_gemma":0.00004492188,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003697897,"about_ca_topic_score_gemma":0.00001425508,"domain_scores_codex":[0.998889,0.00001512692,0.0002129698,0.0004796399,0.0001470267,0.0002561852],"domain_scores_gemma":[0.9990953,0.00007184409,0.00003580853,0.0006464293,0.00004592728,0.0001046774],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005447472,0.000155178,0.000119233,0.00007108259,0.00007234331,0.00007777423,0.0005243203,0.00008383017,0.0006018363,0.2736587,0.005737719,0.7188925],"study_design_scores_gemma":[0.0004449586,0.0001181506,0.0011054,0.000166271,0.00001464164,0.0000558775,0.00009188385,0.9696233,0.0002356055,0.0001310348,0.02763893,0.0003739747],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003080772,0.0005903388,0.9932019,0.0004597384,0.0002812733,0.0001377682,0.0002556751,0.0003344732,0.001658136],"genre_scores_gemma":[0.2562248,0.0001080892,0.7403688,0.000253862,0.0006895861,0.00001555769,0.002099398,0.00003117584,0.0002087371],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9695395,"threshold_uncertainty_score":0.7169188,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03129771263752603,"gpt":0.3164762397476485,"spread":0.2851785271101225,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001883773,0.0001094208,0.00007888849,0.0002054149,0.00006469122,0.0002863805,0.0004813955,0.00004827761,0.000002368626],"category_scores_gemma":[0.0001284178,0.0001078463,0.00000921354,0.0003529732,0.00000464776,0.003971684,0.0004068677,0.0001401466,0.0000143527],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006879753,"about_ca_system_score_gemma":0.00003631464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003121592,"about_ca_topic_score_gemma":0.00001842996,"domain_scores_codex":[0.9993882,0.00001072144,0.0001430455,0.000203161,0.0001028809,0.0001519825],"domain_scores_gemma":[0.9993855,0.00001707981,0.00003420072,0.0004380306,0.00006535382,0.00005982883],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002067777,0.00001235034,0.0000275016,0.00003648796,0.00000532258,0.000005832124,0.0009981478,0.00006067082,0.09440889,0.001550252,0.0009414354,0.901951],"study_design_scores_gemma":[0.00005508673,0.00000758582,0.00007144889,0.00004182919,0.0000038169,0.00007834158,0.00001964832,0.9758386,0.007577732,0.00001462082,0.01613971,0.0001515776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02331872,0.004158417,0.9712756,0.00005312577,0.0005576073,0.0001137612,0.000007275333,0.0004396808,0.00007579325],"genre_scores_gemma":[0.2765829,0.00001457203,0.7229263,0.00007795006,0.0002327669,0.000005168913,0.0001171684,0.000007610902,0.00003556875],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9757779,"threshold_uncertainty_score":0.4397846,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03681758029791506,"gpt":0.3163027075077396,"spread":0.2794851272098245,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000598939,0.0003710103,0.0005677835,0.0004428699,0.0001132163,0.0001721363,0.0009763003,0.0001238794,0.0000145984],"category_scores_gemma":[0.0006128778,0.0003839189,0.00005073708,0.003537734,0.00001400287,0.001085331,0.0001421378,0.0002538037,0.0003049032],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001207928,"about_ca_system_score_gemma":0.00006863671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":2.605043e-7,"about_ca_topic_score_gemma":0.00000114518,"domain_scores_codex":[0.9980031,0.00002784955,0.0007462247,0.000458176,0.0003056411,0.000458978],"domain_scores_gemma":[0.99835,0.0001380864,0.0001159967,0.001060689,0.0001982071,0.00013703],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[4.351433e-7,0.00002461172,0.0000120088,0.5653017,0.000100769,0.00001193516,0.001580786,0.4289789,0.0005814121,0.0001367053,0.001928174,0.001342553],"study_design_scores_gemma":[0.0001044125,0.00000314361,0.00004577634,0.0792366,0.0001308453,0.00006050029,0.00009002283,0.9197471,0.0001204214,0.0000135018,0.00008738451,0.0003603393],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009680329,0.194287,0.7683752,0.0001899887,0.00175356,0.004890497,0.0002798561,0.01938078,0.0011628],"genre_scores_gemma":[0.8645231,0.02344055,0.08980066,0.0002027473,0.001705307,0.005487556,0.01275299,0.001558113,0.0005290312],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8548427,"threshold_uncertainty_score":0.9998613,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1396288150849168,"gpt":0.3143660971102691,"spread":0.1747372820253524,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001369382,0.0002106856,0.0003418321,0.0001822526,0.00005980399,0.0000933281,0.002374604,0.0001053375,0.000006192026],"category_scores_gemma":[0.001051122,0.0002036904,0.00004026769,0.0005289334,0.00003247945,0.001631113,0.001394074,0.0003245126,0.00004028163],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001003704,"about_ca_system_score_gemma":0.00005193785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003307998,"about_ca_topic_score_gemma":0.000001377634,"domain_scores_codex":[0.9981635,0.00007482049,0.0003388097,0.0004797511,0.0003660445,0.0005771198],"domain_scores_gemma":[0.9971197,0.0005820525,0.00005219298,0.00183882,0.0001149517,0.000292234],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003072188,0.002966954,0.8033774,0.003619098,0.0004696086,0.00001633578,0.003398962,0.04444326,0.002011643,0.09199996,0.005686636,0.04197939],"study_design_scores_gemma":[0.0001615233,0.00002488301,0.1126616,0.00004177525,0.000007931992,0.00003652643,0.00002255839,0.8826084,0.00008161458,0.000003846496,0.004111999,0.0002373148],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05081954,0.002733613,0.9443146,0.000003117107,0.001035048,0.0001568026,0.00003434524,0.0007172766,0.0001856623],"genre_scores_gemma":[0.8515052,0.000004010064,0.1478988,0.000001699701,0.0003381411,0.00002724376,0.0001790463,0.00002168027,0.00002422829],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8381652,"threshold_uncertainty_score":0.8306254,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04137654040511619,"gpt":0.3090537414834847,"spread":0.2676772010783685,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001380027,0.0002238119,0.0002797583,0.0003047939,0.00007822678,0.0002647597,0.00189518,0.0001497911,0.00001879767],"category_scores_gemma":[0.001391393,0.0002227019,0.00004740358,0.001139669,0.00001255582,0.001311331,0.000832617,0.0006233147,0.00002930244],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004112503,"about_ca_system_score_gemma":0.00008586884,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006597544,"about_ca_topic_score_gemma":0.0003269681,"domain_scores_codex":[0.9984485,0.00006753288,0.0003179018,0.0006311587,0.0001828447,0.0003520474],"domain_scores_gemma":[0.9976859,0.000487885,0.00008022657,0.001594738,0.00005195821,0.0000993042],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005865876,0.0001599249,0.001187569,0.0002368207,0.0001340133,0.0001031899,0.004796076,0.05869979,0.1285345,0.005520449,0.001189216,0.7994326],"study_design_scores_gemma":[0.0002063887,0.000003138769,0.0002775546,0.0000806287,0.00002428847,0.00003142155,0.00002194368,0.9936414,0.000518282,0.00004425647,0.004893872,0.000256789],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01559837,0.0004736361,0.9825179,0.00008067989,0.0007853129,0.00007229389,0.00004719188,0.0002283072,0.0001963344],"genre_scores_gemma":[0.2272448,0.000005427165,0.7723539,0.00001836734,0.0001790374,0.000003968597,0.0001453089,0.0000212157,0.00002802503],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9349416,"threshold_uncertainty_score":0.9081521,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1658117584570718,"gpt":0.315461514927751,"spread":0.1496497564706792,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0007644065,0.0002640685,0.0002565967,0.0003642251,0.0001175187,0.0001141575,0.06090396,0.0001438888,0.000005322084],"category_scores_gemma":[0.01486588,0.0002857741,0.00001876462,0.001026196,0.00004684308,0.003788664,0.2590207,0.0005897407,0.0001209806],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001379157,"about_ca_system_score_gemma":0.00008712354,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000631491,"about_ca_topic_score_gemma":0.0001307912,"domain_scores_codex":[0.9975773,0.00004312829,0.0004048384,0.001218974,0.0002104432,0.0005453606],"domain_scores_gemma":[0.9747198,0.00009631928,0.00007413328,0.02499104,0.00003646229,0.00008223722],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003222792,0.001417855,0.004787031,0.001150246,0.0002041724,0.0008589241,0.002041729,0.001607043,0.02287185,0.0006515019,0.297031,0.6673464],"study_design_scores_gemma":[0.0003677415,0.0000130583,0.002369424,0.0001041274,0.000002709667,0.00008420605,0.000005507284,0.9624795,0.0006404102,0.00008294012,0.03354333,0.0003070236],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004497432,0.0006588098,0.9910626,0.0007364579,0.0007569244,0.0003652586,0.0002762237,0.001565457,0.00008084324],"genre_scores_gemma":[0.09914581,0.0001560896,0.8997742,0.00001206264,0.000118253,0.00004956056,0.0006672493,0.00004224453,0.00003454068],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9608725,"threshold_uncertainty_score":0.9999595,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.09260547872331132,"gpt":0.2944326736658593,"spread":0.201827194942548,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002833506,0.0001455851,0.0001648672,0.00007657996,0.0001182508,0.0001699179,0.001532903,0.00006867087,0.00002401591],"category_scores_gemma":[0.0006263851,0.000147942,0.00002776272,0.0002433347,0.00002610274,0.001321653,0.0007226429,0.0002504383,0.0003188488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006787496,"about_ca_system_score_gemma":0.00006319708,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001023364,"about_ca_topic_score_gemma":0.00007239211,"domain_scores_codex":[0.9989027,0.00002906301,0.0002354251,0.0004286579,0.0001417778,0.0002623866],"domain_scores_gemma":[0.9984938,0.0003443031,0.00005214657,0.001002009,0.00002970762,0.00007804918],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002416785,0.0005462129,0.009373243,0.00008930609,0.0004235354,0.0003398249,0.0289964,0.003830291,0.01546634,0.7027655,0.01027135,0.2278738],"study_design_scores_gemma":[0.004604408,0.00006733122,0.05526892,0.0005065703,0.0000847317,0.0000560015,0.001476212,0.6773693,0.01007822,0.009008997,0.2397225,0.001756828],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04522677,0.001554942,0.9481879,0.0001587907,0.001733884,0.0001098458,0.00003510273,0.0005423283,0.002450418],"genre_scores_gemma":[0.6969708,0.00002796396,0.3021148,0.00001970101,0.000580465,0.000007443789,0.0001745023,0.00001741353,0.00008682017],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6937565,"threshold_uncertainty_score":0.6032898,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02950059442361724,"gpt":0.3180202898758975,"spread":0.2885196954522802,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002375691,0.00009758831,0.0001240157,0.00007261695,0.00006677007,0.00008258955,0.0007303716,0.0000463368,5.038921e-7],"category_scores_gemma":[0.00002929868,0.00009666874,0.00001809219,0.0001149022,0.00001107018,0.0004251006,0.000681741,0.00007059562,0.000001745951],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002289188,"about_ca_system_score_gemma":0.00004981051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006954022,"about_ca_topic_score_gemma":0.000008988994,"domain_scores_codex":[0.999259,0.000008281281,0.0001339214,0.0003480583,0.00005778546,0.0001929291],"domain_scores_gemma":[0.999236,0.00006274327,0.00001686653,0.0006143581,0.00003816918,0.00003187902],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004270089,0.00009486183,0.00003289974,0.0001708376,0.00006403995,0.000002851126,0.001745281,0.02542021,0.002864824,0.8582488,0.001332164,0.110019],"study_design_scores_gemma":[0.0003069286,0.000007476871,0.00004078511,0.00001802668,0.00001193788,0.000001321221,0.0002204951,0.9965616,0.0001068539,0.0008254349,0.001800497,0.00009866701],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003864654,0.001930409,0.9931133,0.00009767005,0.0002745137,0.0001991287,0.00005283214,0.0001977844,0.0002697261],"genre_scores_gemma":[0.860186,0.00002399315,0.1394647,0.00002546198,0.00006626693,0.00004592255,0.0001336756,0.000006192573,0.00004774886],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9711414,"threshold_uncertainty_score":0.3942037,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04147215521048864,"gpt":0.2906286266056325,"spread":0.2491564713951439,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003894794,0.0001384328,0.0001658383,0.00009188995,0.00004349491,0.0001556177,0.001578617,0.00004020661,0.00002844464],"category_scores_gemma":[0.0001368751,0.000148461,0.00002670913,0.0005295536,0.00001208095,0.000548056,0.001063892,0.0001505282,0.00003431593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004744028,"about_ca_system_score_gemma":0.0001256835,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007111082,"about_ca_topic_score_gemma":0.0001767012,"domain_scores_codex":[0.9987159,0.00003276075,0.0002684752,0.0005980427,0.0001202728,0.0002645627],"domain_scores_gemma":[0.9982424,0.000145064,0.0000364429,0.001448787,0.00004798614,0.00007931992],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001274374,0.0003327789,0.00475311,0.0001858875,0.00002783119,0.0001227856,0.0007909045,0.000549154,0.001256435,0.003913797,0.001683939,0.9863821],"study_design_scores_gemma":[0.0001476228,0.000007765841,0.008824402,0.0001694176,0.000003621877,0.000006356838,0.00003825904,0.9776545,0.0020391,0.0000190807,0.01092477,0.0001650673],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05081657,0.0003592986,0.9475017,0.0002670697,0.000440514,0.00006610354,0.0002964442,0.0001597344,0.00009253375],"genre_scores_gemma":[0.720634,0.00001309809,0.2782812,0.00003865829,0.0001010147,0.00003682351,0.0008389571,0.00001361822,0.00004260548],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.986217,"threshold_uncertainty_score":0.6054065,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05909199711209612,"gpt":0.3912896514703549,"spread":0.3321976543582588,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001518688,0.0001778422,0.0001728154,0.0002742745,0.00004254728,0.0005884533,0.002075688,0.00005309492,0.00001489964],"category_scores_gemma":[0.00179205,0.0001173534,0.00002085655,0.001371053,0.00002714674,0.002348047,0.0009167859,0.0006615047,0.00004663845],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002234781,"about_ca_system_score_gemma":0.0000610313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001547753,"about_ca_topic_score_gemma":0.0006755233,"domain_scores_codex":[0.9983901,0.0001304571,0.0003730223,0.0003906406,0.0002795089,0.0004362374],"domain_scores_gemma":[0.9968166,0.001942039,0.00003851238,0.001109175,0.00004895693,0.00004472451],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000008424508,0.0004858442,0.5402908,0.0006922485,0.00009517398,0.0001241433,0.05665455,0.03716461,0.01676304,0.003228191,0.00266548,0.3418275],"study_design_scores_gemma":[0.0001826933,0.00000288323,0.5027856,0.0000530169,7.771844e-7,0.000001880306,0.0004130398,0.4961629,0.00008836925,0.000009925895,0.0001876833,0.0001111663],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9614783,0.001578739,0.03546179,0.0003569451,0.0005795643,0.0003708778,0.00000404499,0.0001251239,0.00004462595],"genre_scores_gemma":[0.9965087,0.000006768261,0.003180546,0.0000181106,0.00009121397,0.00005160322,0.00005768715,0.00001809344,0.00006728758],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4589983,"threshold_uncertainty_score":0.5674468,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1559070856255667,"gpt":0.294042282112188,"spread":0.1381351964866213,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008922394,0.0001799705,0.0001858529,0.00008902131,0.00008993988,0.0001489349,0.00303433,0.00005866742,0.00002220707],"category_scores_gemma":[0.0005768776,0.0001705899,0.00001476495,0.0004012,0.00005079081,0.0008478516,0.001283389,0.0002049535,0.0002399626],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003151946,"about_ca_system_score_gemma":0.00006766456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002267289,"about_ca_topic_score_gemma":0.00003055853,"domain_scores_codex":[0.9985055,0.0001076925,0.0002218183,0.0007022487,0.000155936,0.0003067582],"domain_scores_gemma":[0.99645,0.000287786,0.00004468008,0.003069063,0.00004321782,0.0001052216],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001201695,0.0002842724,0.003027564,0.00006246833,0.0001442738,0.0000518287,0.0009497125,0.0008331581,0.000389556,0.6539582,0.05439502,0.285892],"study_design_scores_gemma":[0.0003040457,0.00004105724,0.003131385,0.00002497818,0.000005085279,0.00003075637,0.00002187655,0.7735812,0.00007648773,0.00008324466,0.2223892,0.0003106753],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002879022,0.0007278628,0.9832501,0.00003501256,0.002946185,0.0001728783,0.001027366,0.0003807248,0.0085808],"genre_scores_gemma":[0.5806437,0.000080645,0.414482,0.0001085234,0.0004192969,0.000008864528,0.004140956,0.00004841775,0.0000675542],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7727481,"threshold_uncertainty_score":0.6956453,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03893282992648182,"gpt":0.2496358099264162,"spread":0.2107029799999343,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002660633,0.0001836021,0.0002645848,0.0001307764,0.00008080752,0.00004390996,0.001033045,0.00004202917,0.0000166002],"category_scores_gemma":[0.0001443416,0.0001757584,0.00003817474,0.0004162647,0.00003344591,0.0007169941,0.001071763,0.0001246381,0.00004993962],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002723926,"about_ca_system_score_gemma":0.00001628066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000195476,"about_ca_topic_score_gemma":0.000006012369,"domain_scores_codex":[0.9987204,0.00001520971,0.0003580078,0.0004596657,0.0001454366,0.0003012916],"domain_scores_gemma":[0.9981726,0.0001163973,0.00009292264,0.001461944,0.00006450477,0.00009163408],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002195106,0.001195354,0.0009548934,0.003318026,0.000416584,0.000148188,0.02617279,0.1643027,0.07423481,0.4081236,0.01206393,0.3090472],"study_design_scores_gemma":[0.000135521,0.00001562768,0.00001851232,0.0001452838,0.000004142773,0.00001045516,0.00004492821,0.9173548,0.003190517,0.000002220177,0.07889098,0.0001870289],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002597634,0.004951668,0.9910554,0.00003048332,0.0004519214,0.0001146523,0.0001172826,0.0002551437,0.000425828],"genre_scores_gemma":[0.2470167,0.00007795201,0.7524112,0.000006976171,0.0001842217,0.00001954131,0.0001205465,0.00003151137,0.0001313435],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7530521,"threshold_uncertainty_score":0.7167221,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.5264044121500385,"gpt":0.3663522096925166,"spread":0.1600522024575219,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001447266,0.000181057,0.0002120943,0.0002660769,0.0002305342,0.0004701514,0.00152517,0.00004046151,0.0001337271],"category_scores_gemma":[0.001325022,0.0001458072,0.00001679921,0.001140058,0.00009098576,0.002594647,0.003095471,0.0002897401,0.00005861559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001053817,"about_ca_system_score_gemma":0.00006947049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006061779,"about_ca_topic_score_gemma":0.0001712306,"domain_scores_codex":[0.9983584,0.00002736447,0.0002897786,0.0006075689,0.0003423711,0.0003745042],"domain_scores_gemma":[0.9970741,0.0005428665,0.00006745724,0.001972416,0.000320775,0.00002234374],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001346537,0.0004713655,0.007456004,0.00314558,0.0001329123,0.0001125915,0.0008748415,0.001790403,0.02098837,0.01080117,0.0196545,0.9344376],"study_design_scores_gemma":[0.0001679218,0.000006055006,0.002844123,0.0006095115,0.00003218917,0.000004511501,0.000699868,0.9384574,0.0008742365,0.00001789626,0.05609267,0.0001936665],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9482692,0.003192696,0.03912041,0.001583353,0.001544819,0.0003992605,0.0004644617,0.0002831701,0.005142578],"genre_scores_gemma":[0.9958701,0.0001114758,0.002219329,0.00004459458,0.0007354103,0.00001118082,0.0009444528,0.00003606103,0.00002740419],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.936667,"threshold_uncertainty_score":0.5945845,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06691927417424057,"gpt":0.3392689324753541,"spread":0.2723496583011135,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001681191,0.0002563636,0.0002911777,0.0005122308,0.000196126,0.0002441871,0.001315227,0.00009464168,0.000006479631],"category_scores_gemma":[0.001783199,0.0002797999,0.00002590677,0.001187946,0.0000396167,0.000902659,0.002115458,0.0005805095,0.00002686219],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001638239,"about_ca_system_score_gemma":0.0001644608,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003183823,"about_ca_topic_score_gemma":0.000246959,"domain_scores_codex":[0.9978576,0.000208543,0.0005190331,0.0008911419,0.0001217794,0.0004018477],"domain_scores_gemma":[0.9980868,0.0005160269,0.00005515624,0.001097845,0.00008466942,0.0001595113],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005118783,0.0003334692,0.002764521,0.0003543318,0.00003753275,0.00001692566,0.008983845,0.1078154,0.005358594,0.2726089,0.00008330066,0.6015919],"study_design_scores_gemma":[0.000110385,0.00001911276,0.0002702101,0.0001534929,0.000007396895,0.000004737663,0.0004225113,0.991344,0.0001319211,0.0005830631,0.006690996,0.0002621753],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1475427,0.001190301,0.8501359,0.0001786241,0.0002887541,0.000216162,0.00002483418,0.0001997243,0.0002229555],"genre_scores_gemma":[0.9018036,0.00002453436,0.09783458,0.00001914051,0.00009645215,0.00002181319,0.0001566157,0.00001730776,0.00002597387],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8835285,"threshold_uncertainty_score":0.9999654,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01914562073366399,"gpt":0.2609460380770489,"spread":0.2418004173433849,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000527021,0.0002010575,0.0002667981,0.0002186032,0.00005572465,0.0001970719,0.002198612,0.00007555151,0.000001950184],"category_scores_gemma":[0.00004199359,0.0001925957,0.00002893375,0.0006351797,0.000007672624,0.0008980596,0.0007155768,0.0003372356,0.0000360017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004707088,"about_ca_system_score_gemma":0.00004401094,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003137715,"about_ca_topic_score_gemma":0.0000325414,"domain_scores_codex":[0.9984106,0.00004205156,0.0003964002,0.0005443392,0.0001691702,0.0004374572],"domain_scores_gemma":[0.9982147,0.0001226176,0.00005116803,0.001439024,0.00004033366,0.0001321246],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004034289,0.00082732,0.006681206,0.001236405,0.00007227954,0.0002254987,0.01260805,0.001393078,0.007894601,0.1586351,0.0004590367,0.8099271],"study_design_scores_gemma":[0.0001933716,0.00003459278,0.0236169,0.0001422591,0.00000373062,0.00001904211,0.00001969596,0.9588424,0.000112722,0.00008938282,0.01669744,0.0002284599],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1620313,0.001763671,0.83117,0.0003338733,0.001826353,0.0003761205,0.00008502795,0.0006881411,0.001725497],"genre_scores_gemma":[0.9837616,0.00001958807,0.01558434,0.0001156973,0.0003229622,0.000006827986,0.0001670899,0.00001233258,0.000009541006],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9574493,"threshold_uncertainty_score":0.7853824,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05706698903393938,"gpt":0.3019583151155923,"spread":0.2448913260816529,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000852338,0.0002530411,0.0002892262,0.00008870992,0.000142152,0.0001729834,0.001679845,0.00004691627,0.000001233711],"category_scores_gemma":[0.0002247116,0.0002464539,0.00001547432,0.0001961986,0.00002136136,0.002408623,0.003428134,0.0001116996,0.00001501812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007663751,"about_ca_system_score_gemma":0.00009324233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002174307,"about_ca_topic_score_gemma":0.0001815649,"domain_scores_codex":[0.9979979,0.00002316181,0.0003958563,0.0009740911,0.0001874792,0.0004215354],"domain_scores_gemma":[0.996143,0.00016601,0.00008943301,0.00340775,0.00008281958,0.0001110292],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001068164,0.001153853,0.001416517,0.01251604,0.0006084045,0.0002298962,0.001873045,0.01330063,0.05708445,0.4731758,0.3125302,0.1260044],"study_design_scores_gemma":[0.0004505509,0.000009973002,0.00004555458,0.0001437438,0.000009314133,0.0000171619,0.00003039078,0.6695793,0.0001301901,0.000001136238,0.329374,0.0002087211],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003030386,0.008422992,0.9826493,0.00001594489,0.001168998,0.0004774772,0.006645217,0.0002586959,0.00005832119],"genre_scores_gemma":[0.009541828,0.00008066116,0.9774448,0.00001085504,0.0008005237,0.0001061244,0.01148496,0.00005469152,0.0004755355],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6562787,"threshold_uncertainty_score":0.9999987,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03342681986294629,"gpt":0.2847333065404637,"spread":0.2513064866775174,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002996945,0.0001396191,0.0001184291,0.0001511167,0.00005715525,0.0003117087,0.0008259375,0.00004115988,0.000007261991],"category_scores_gemma":[0.0001003194,0.0001366184,0.00002071955,0.0003856129,0.00001049813,0.0005510327,0.001113318,0.0001380924,0.00005630737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004524998,"about_ca_system_score_gemma":0.00002645848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004620138,"about_ca_topic_score_gemma":0.00001103717,"domain_scores_codex":[0.9990394,0.000007275317,0.0001471374,0.000472539,0.0001145362,0.0002191691],"domain_scores_gemma":[0.9990206,0.0001369879,0.00001276208,0.0006760097,0.00003650857,0.0001171691],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002071565,0.00002277595,0.0001647052,0.0002885788,0.00003379129,0.00003629267,0.001278664,0.00005153507,0.00268205,0.001518667,0.00481343,0.9891074],"study_design_scores_gemma":[0.00003995921,0.00001687893,0.000325104,0.0001134268,0.000005885486,0.000006599069,0.0000177233,0.9463562,0.0009792682,0.00001116962,0.05196174,0.0001660621],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002985674,0.001849534,0.9933626,0.0002243813,0.0004567144,0.0001345665,0.0001974862,0.0007376787,0.00005137383],"genre_scores_gemma":[0.8849618,0.0002530274,0.1139348,0.00006855298,0.0003021772,0.00004293563,0.0001124468,0.00004949839,0.0002746831],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9889414,"threshold_uncertainty_score":0.5571135,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02347369987771302,"gpt":0.2815724607136532,"spread":0.2580987608359402,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003033146,0.0002562771,0.0002582219,0.0002046872,0.00009939205,0.000204336,0.00149832,0.0001037291,0.000002106043],"category_scores_gemma":[0.0001062031,0.0002248066,0.00004402537,0.0003563086,0.00001301537,0.0004710786,0.0008100041,0.0002639974,0.000003278072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009361811,"about_ca_system_score_gemma":0.0001140026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000634854,"about_ca_topic_score_gemma":0.0000929063,"domain_scores_codex":[0.9985876,0.00002360724,0.0002223399,0.0006981401,0.0001118937,0.0003563935],"domain_scores_gemma":[0.9982874,0.0001177844,0.00003871744,0.001387456,0.00008707108,0.00008151735],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001214751,0.0001647677,0.0006796999,0.001457368,0.0004232331,0.00002305263,0.002906952,0.02569207,0.01711452,0.00402225,0.003851584,0.943543],"study_design_scores_gemma":[0.001119876,0.00001741252,0.0003098304,0.0001749065,0.00003355991,0.000005311671,0.00001403271,0.9914578,0.00220277,0.00001249895,0.004400926,0.0002511174],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002312082,0.0006538056,0.9950447,0.000186022,0.0006722948,0.0006768138,0.00005727269,0.0003186132,0.00007838948],"genre_scores_gemma":[0.08574759,0.00001611814,0.9111239,0.00006587581,0.0002804568,0.0001795918,0.0009280503,0.00005063829,0.001607761],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9657657,"threshold_uncertainty_score":0.9167346,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université TÉLUQ; University of New Brunswick","funders":"","keywords":"Wafer dicing; Materials science; Nanotechnology; Wafer","retraction":null,"screen_n_in":null,"score":{"opus":0.0305814111118762,"gpt":0.2466045792735479,"spread":0.2160231681616717,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001429979,0.0001155849,0.0001273636,0.0000823702,0.00004531581,0.0001746078,0.00183956,0.0000367033,0.00002339861],"category_scores_gemma":[0.0001627269,0.0001023019,0.00001849108,0.0002209659,0.00001253183,0.001119391,0.001128028,0.0001055143,0.0006937518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001630619,"about_ca_system_score_gemma":0.00001833746,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000478503,"about_ca_topic_score_gemma":0.000008532194,"domain_scores_codex":[0.9991743,0.00000954764,0.0001372525,0.0003212812,0.00008358195,0.0002740601],"domain_scores_gemma":[0.9985824,0.0001307229,0.00001953831,0.001163392,0.00003080923,0.00007311838],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[5.443864e-7,0.00008246051,0.002099039,0.0001375147,0.00006026576,0.00002876303,0.001620429,0.0001020643,0.009059032,0.03165084,0.0557277,0.8994313],"study_design_scores_gemma":[0.00008799495,0.000008838048,0.008669243,0.00003140044,0.000003365822,0.000008522393,0.00002162549,0.9645193,0.0008513589,0.000126673,0.02550893,0.0001627169],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01795827,0.0019671,0.9744737,0.0002336157,0.001115822,0.0001282536,0.00000524453,0.0006448528,0.003473199],"genre_scores_gemma":[0.8033408,0.00004404026,0.1956791,0.00006777582,0.0003836724,0.00002892091,0.00004226716,0.00002385079,0.0003895343],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9644173,"threshold_uncertainty_score":0.8917007,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1936835263463012,"gpt":0.4732092990702447,"spread":0.2795257727239435,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008492214,0.0001449171,0.0002237092,0.0001219654,0.00007084371,0.0001109345,0.001170175,0.00005395766,0.000006297268],"category_scores_gemma":[0.0003389445,0.0001598471,0.00004235672,0.0004281615,0.00001208975,0.0006758677,0.001896217,0.0001530196,0.000003381598],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009833826,"about_ca_system_score_gemma":0.0001669776,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000245312,"about_ca_topic_score_gemma":0.00001088063,"domain_scores_codex":[0.998595,0.00007410645,0.0002960792,0.0005384723,0.0001716829,0.0003246769],"domain_scores_gemma":[0.9980086,0.0002698503,0.00005363822,0.001379616,0.0001923075,0.00009599596],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001316895,0.00006005117,0.000006575892,0.0003177724,0.00005050607,0.00001050634,0.0002592179,0.009881406,0.1520986,0.002983101,0.0003277593,0.8340032],"study_design_scores_gemma":[0.0002312273,0.00002428617,0.0001066075,0.00004872809,0.000005781525,0.0000173652,0.00001308042,0.9521344,0.03618176,0.00004009995,0.01104416,0.0001525444],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001948376,0.0006144024,0.9977608,0.00009415736,0.0007885281,0.000162281,0.00006508901,0.0001112067,0.0002086581],"genre_scores_gemma":[0.005080575,0.00002676522,0.9942734,0.000006798176,0.0001888279,0.00004268903,0.0002298969,0.00002518653,0.0001258148],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9422529,"threshold_uncertainty_score":0.6518375,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.04420924631857913,"gpt":0.2996458049990858,"spread":0.2554365586805067,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004998313,0.000156044,0.0001720022,0.0002600007,0.00007124728,0.0002055019,0.0004947414,0.00004618675,0.00002953865],"category_scores_gemma":[0.0001251851,0.0001754185,0.000009498923,0.000311637,0.00001791853,0.002421553,0.002314056,0.0001318834,0.00004269436],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006556023,"about_ca_system_score_gemma":0.00001346445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002576304,"about_ca_topic_score_gemma":0.001834802,"domain_scores_codex":[0.9989544,0.000008124009,0.0002826005,0.000450542,0.00009604168,0.0002083166],"domain_scores_gemma":[0.9991596,0.00005835957,0.00004900678,0.0007104885,0.0000111057,0.00001141279],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002248982,0.001299776,0.2421634,0.00756282,0.0003123824,0.00003912872,0.002304158,0.004898496,0.2570936,0.003214458,0.00619777,0.4746891],"study_design_scores_gemma":[0.0005348607,0.000001281257,0.03406961,0.0001309237,0.00002498059,4.439456e-7,0.0001647066,0.9514252,0.0003284507,0.00001485177,0.01314046,0.0001642332],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7616834,0.00133567,0.2300985,0.000220844,0.001510829,0.0008047404,0.0001417373,0.0002340132,0.003970316],"genre_scores_gemma":[0.9960979,0.00002436364,0.00136379,0.00005434073,0.0002279899,0.00000870134,0.002158566,0.00001733689,0.00004697362],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9465267,"threshold_uncertainty_score":0.715336,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04509888621521016,"gpt":0.2994695044326596,"spread":0.2543706182174494,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004294922,0.0002161351,0.0002180712,0.0003179272,0.0001039003,0.0001070001,0.0004192852,0.00005477976,0.00000864954],"category_scores_gemma":[0.000007270851,0.0002388418,0.0000270463,0.002565399,0.0000176107,0.000444344,0.0001498386,0.0001866461,0.000008932822],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006777749,"about_ca_system_score_gemma":0.0000476323,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001983561,"about_ca_topic_score_gemma":0.0007040629,"domain_scores_codex":[0.9986285,0.00005311791,0.0003367128,0.0005059029,0.0001281178,0.0003476409],"domain_scores_gemma":[0.9989326,0.00005922742,0.00009000693,0.0007477261,0.00009489142,0.00007556527],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001500087,0.0001067182,0.08540051,0.00005273158,0.00006493308,0.000001355608,0.0001486188,0.8631446,0.00877,0.001454289,0.0004267107,0.04041455],"study_design_scores_gemma":[0.0001533808,0.00001363088,0.007102872,0.00007639873,0.00004178211,2.465187e-7,0.00006493321,0.9900123,0.0003791896,0.00002562295,0.001884474,0.000245201],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1486487,0.00003410666,0.8504485,0.000008973858,0.00008235434,0.0002820742,0.00003766047,0.0003980153,0.00005955367],"genre_scores_gemma":[0.9744105,0.000002594292,0.01388515,0.000003597253,0.0009449064,0.0001065471,0.01057982,0.0000615047,0.000005417891],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8365634,"threshold_uncertainty_score":0.9739686,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.08647812660475818,"gpt":0.3363630339300379,"spread":0.2498849073252797,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.003257731,0.001182523,0.001278349,0.001800143,0.0003819769,0.0008987782,0.005350573,0.0006334391,0.00003328144],"category_scores_gemma":[0.006377832,0.001382329,0.00007170892,0.002408631,0.00007915158,0.001907009,0.01518914,0.003025018,0.0001138943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005121934,"about_ca_system_score_gemma":0.0008858722,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007644292,"about_ca_topic_score_gemma":0.001405194,"domain_scores_codex":[0.9929832,0.0003579837,0.001490739,0.003519843,0.0004063137,0.001241909],"domain_scores_gemma":[0.9934874,0.0006866326,0.000228104,0.004539991,0.0002962784,0.000761572],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002077432,0.001400532,0.001179142,0.007516304,0.0005411881,0.0001990672,0.02920811,0.1134738,0.002118791,0.02528538,0.2075058,0.6113642],"study_design_scores_gemma":[0.0001541543,0.00005131591,0.000086825,0.001089854,0.00005186854,0.00002010711,0.0002443817,0.7356282,0.000009950872,0.00003048194,0.2616655,0.0009673018],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002478756,0.01275604,0.9694457,0.0002720031,0.01146512,0.001082711,0.00122679,0.0005604174,0.0007124765],"genre_scores_gemma":[0.1867883,0.002798283,0.6892267,0.0003173668,0.0132539,0.0008164771,0.06242466,0.001417905,0.04295646],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6221544,"threshold_uncertainty_score":0.999275,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.3915863678661295,"gpt":0.4561268436149644,"spread":0.06454047574883487,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004567647,0.0001313187,0.0002062753,0.0004692119,0.0001094866,0.0002620383,0.002229502,0.00004161456,0.00007234562],"category_scores_gemma":[0.004466019,0.0001169249,0.00005973463,0.001379527,0.00001990837,0.0006643527,0.001509854,0.00006850877,0.001532835],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001388198,"about_ca_system_score_gemma":0.00002114853,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004652701,"about_ca_topic_score_gemma":0.00003473788,"domain_scores_codex":[0.9982215,0.00003291087,0.0004136611,0.000590915,0.00038635,0.0003546488],"domain_scores_gemma":[0.9966078,0.001549973,0.0000558788,0.001610699,0.00007792504,0.00009774863],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000004576064,0.0000239463,0.00008389208,0.00005579905,0.00003336164,0.00000509587,0.0005183446,0.0001765242,0.0001846555,0.02217243,0.722056,0.2546853],"study_design_scores_gemma":[0.0001416172,0.0000103174,0.0005229044,0.00001627418,0.000008697933,4.855646e-7,0.0003712991,0.3558231,0.00005740015,0.001343491,0.641587,0.0001173671],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03628521,0.0009712757,0.9299598,0.00208795,0.009235888,0.001306866,0.005426869,0.002074137,0.01265196],"genre_scores_gemma":[0.6081954,0.0005172615,0.2727408,0.0009460003,0.004516815,0.0009858274,0.03168104,0.0005074441,0.07990935],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.657219,"threshold_uncertainty_score":0.9992446,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.1044293387069667,"gpt":0.331910048881099,"spread":0.2274807101741324,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005278856,0.0001883138,0.0001633085,0.00027666,0.00005127506,0.00005538288,0.00111038,0.00005588094,0.0001022839],"category_scores_gemma":[0.0004932985,0.0002056089,0.00002685219,0.001350763,0.00001480266,0.000484533,0.00118068,0.0001933237,0.07904322],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006425523,"about_ca_system_score_gemma":0.00003502984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005581916,"about_ca_topic_score_gemma":0.00001493617,"domain_scores_codex":[0.9987156,0.00001645812,0.0001815306,0.0004458585,0.000155256,0.0004853312],"domain_scores_gemma":[0.9982116,0.0001197825,0.00002218718,0.001481107,0.00003459814,0.0001307923],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001050046,0.00009812824,0.0006423613,0.0003259493,0.0001578075,0.00007343849,0.001157814,0.002483066,0.09635568,0.002127761,0.8536367,0.04293081],"study_design_scores_gemma":[0.0001363938,0.000004351549,0.002232949,0.00003430223,0.00001097385,0.000003946335,0.00001855423,0.56423,0.0009661793,0.000004327826,0.4321823,0.0001756926],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.744258,0.01284252,0.04578496,0.0004553332,0.01537041,0.00295292,0.02368726,0.06649534,0.08815327],"genre_scores_gemma":[0.9419937,0.0001500712,0.01877964,0.000022252,0.003070892,0.0001771851,0.02005663,0.001336509,0.01441318],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.561747,"threshold_uncertainty_score":0.9216738,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Volume (thermodynamics); Computer science; Conceptual model; Data science; Database; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.04627239330600777,"gpt":0.3163658736183723,"spread":0.2700934803123646,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.001074483,0.0007948877,0.0008633182,0.0005298976,0.0002010205,0.0004922353,0.004615683,0.0005243515,0.000007136638],"category_scores_gemma":[0.000190044,0.0009272375,0.00007047363,0.0004936509,0.00002496529,0.001444486,0.009784036,0.000977141,0.00001518314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002308317,"about_ca_system_score_gemma":0.0005402283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005271902,"about_ca_topic_score_gemma":0.00009081574,"domain_scores_codex":[0.9952891,0.0000379216,0.0007856376,0.0026326,0.0003381659,0.000916539],"domain_scores_gemma":[0.9943653,0.0001074482,0.0001351859,0.004777072,0.000238308,0.0003766876],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001220162,0.0002730143,0.00001228479,0.003448069,0.0005011586,0.00002176996,0.003312944,0.09341214,0.0006278785,0.03069008,0.7660681,0.1016204],"study_design_scores_gemma":[0.0003871156,0.00002042305,0.000007246107,0.0003520067,0.0001002528,0.000007390844,0.00006429783,0.764114,0.00000434316,0.00003389368,0.2342374,0.0006716223],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00004089796,0.01544063,0.9657997,0.0001003903,0.01296836,0.001240404,0.003242298,0.0004711647,0.0006960836],"genre_scores_gemma":[0.02518448,0.001431865,0.858094,0.0002007008,0.007396874,0.001066929,0.04255036,0.0005248603,0.06354989],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6707019,"threshold_uncertainty_score":0.9993178,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}