{"meta":{"query_hash":"962ff7d3bf67","filters":{"venue":"Knowledge and Information Systems"},"cohort_total":123,"direct_labels_cover":0,"predictions_cover":123,"exported":123,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/962ff7d3bf67","api":"https://metacan.xera.ac/api/v1/cohort?venue=Knowledge+and+Information+Systems"},"results":[{"id":"W1599200063","doi":"10.1007/s10115-015-0871-2","title":"Partial materialization for online analytical processing over multi-tagged document collections","year":2015,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"University of Waterloo; Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Computer science; Centroid; Information retrieval; Medoid; Document clustering; Digital library; Data mining; Artificial intelligence; Cluster analysis","score_opus":0.04078338301597355,"score_gpt":0.3180951839573361,"score_spread":0.27731180094136254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1599200063","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021712866,0.0002650388,0.9950373,0.00003879578,0.0010356335,0.00049999513,0.00006143301,0.000112809874,0.00077770953],"genre_scores_gemma":[0.8922313,0.00006840146,0.098324224,0.000257217,0.0013527446,0.00085523515,0.0011238521,0.000030982428,0.0057560536],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99910265,0.00003982036,0.00045120053,0.0001232565,0.00013265922,0.00015039182],"domain_scores_gemma":[0.9991637,0.000018989158,0.00016686767,0.00015912717,0.00039582545,0.000095483985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032814356,0.0001034401,0.00016318794,0.00013655199,0.00022694419,0.00038519528,0.00008555238,0.000052112155,0.0000013699216],"category_scores_gemma":[0.00007502371,0.00008570332,0.000022167136,0.0003215932,0.000022030868,0.004519872,0.00006864893,0.00003081387,0.000015835876],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013559806,0.00027538787,0.00045764225,0.001677187,0.00007665205,0.0000011453338,0.022926439,0.0025238853,0.0001778904,0.87403667,0.0445534,0.05315813],"study_design_scores_gemma":[0.000744401,0.000046871435,0.00006260084,0.00005496607,0.000004933818,0.000009152409,0.0002892494,0.46124965,0.00008198141,0.000020402005,0.5373421,0.00009372511],"about_ca_topic_score_codex":0.0000341365,"about_ca_topic_score_gemma":0.000014348227,"teacher_disagreement_score":0.8967131,"about_ca_system_score_codex":0.00007795891,"about_ca_system_score_gemma":0.00012906358,"threshold_uncertainty_score":0.3714447},"labels":[],"label_agreement":null},{"id":"W1967641500","doi":"10.1007/s101150200002","title":"Correlation-Based Web Document Clustering for Adaptive Web Interface Design","year":2002,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Web page; Cluster analysis; Web modeling; Data Web; Web mining; Information retrieval; Web navigation; Data mining; World Wide Web; Static web page; Web design; Machine learning","score_opus":0.03196732839296157,"score_gpt":0.24740335138207364,"score_spread":0.21543602298911207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967641500","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022226114,0.0005684492,0.9923332,0.00009397809,0.0004283903,0.00029464246,0.00001362707,0.00010269018,0.005942804],"genre_scores_gemma":[0.990203,0.000023769762,0.008850805,0.00005452051,0.000055303914,0.00008344197,0.000014650524,0.000003996693,0.0007104943],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991438,0.0000624973,0.00038214223,0.00013568897,0.00012130469,0.00015456327],"domain_scores_gemma":[0.99917114,0.00017834999,0.00017016435,0.00023783841,0.00017373209,0.000068762456],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045279032,0.000114082875,0.00015745747,0.00020622824,0.0001700508,0.0004136189,0.0002437634,0.000053124022,0.000008810863],"category_scores_gemma":[0.00003994754,0.00010001751,0.000042467615,0.00024981398,0.000015749361,0.0026614352,0.00006644181,0.000053392647,0.00026523633],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009808494,0.00020075038,0.00058858347,0.0011279949,0.0003672446,0.0000018442387,0.039989445,0.365644,0.00029497553,0.047791447,0.20958985,0.33430576],"study_design_scores_gemma":[0.00047861633,0.00008933064,0.000009684044,0.00008886608,0.000009803757,0.0000032753173,0.00024183985,0.9059012,0.00005244755,0.000006584794,0.09300082,0.00011752717],"about_ca_topic_score_codex":0.000006612961,"about_ca_topic_score_gemma":0.0000031949385,"teacher_disagreement_score":0.98998076,"about_ca_system_score_codex":0.000052726926,"about_ca_system_score_gemma":0.00004111159,"threshold_uncertainty_score":0.40785956},"labels":[],"label_agreement":null},{"id":"W1968727285","doi":"10.1007/s10115-012-0546-1","title":"Out-of-core detection of periodicity from sequence databases","year":2012,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Tree traversal; Computer science; Scalability; Suffix tree; Pruning; Suffix; Out-of-core algorithm; Sequence (biology); Auxiliary memory; Tree (set theory); Core (optical fiber); Data structure; Time complexity; Algorithm; Generalized suffix tree; Series (stratigraphy); Theoretical computer science; Data mining; Database; Mathematics","score_opus":0.06032132968878795,"score_gpt":0.29010241177526475,"score_spread":0.2297810820864768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968727285","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15489282,0.0019306537,0.83875257,0.000003978191,0.0016068812,0.00015596686,0.00014236028,0.00004598844,0.002468786],"genre_scores_gemma":[0.9980935,0.00004655065,0.0016978204,0.000007546699,0.000085918095,0.000006290296,0.000049977298,0.0000013477401,0.000011062507],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.999351,0.000028447119,0.00033181199,0.000063055566,0.00013086926,0.00009480254],"domain_scores_gemma":[0.9992582,0.000049260063,0.00022519408,0.00027338602,0.00013763309,0.000056314093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023802624,0.00006662902,0.00013552951,0.00007612772,0.00006423347,0.00003815247,0.00017253085,0.000033260756,0.0000028359323],"category_scores_gemma":[0.000030500905,0.000052628486,0.000018975841,0.00011726038,0.0000308405,0.005503072,0.00015717912,0.00004258985,0.000034477976],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047513222,0.00025551947,0.032974686,0.0014493878,0.00008330744,4.7874875e-7,0.07268022,0.00005446666,0.057009146,0.08382105,0.002933645,0.7486906],"study_design_scores_gemma":[0.00091188593,0.00016164471,0.037796803,0.00064804003,0.000025585068,0.000019599362,0.0018367482,0.42178378,0.060195755,0.00008112916,0.47607198,0.00046707081],"about_ca_topic_score_codex":0.00025176318,"about_ca_topic_score_gemma":0.000004623627,"teacher_disagreement_score":0.8432007,"about_ca_system_score_codex":0.000012887698,"about_ca_system_score_gemma":0.00002388659,"threshold_uncertainty_score":0.39895943},"labels":[],"label_agreement":null},{"id":"W1970296249","doi":"10.1007/s10115-011-0379-3","title":"Aggregate keyword search on large relational databases","year":2011,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Aggregate (composite); Information retrieval; Tuple; Set (abstract data type); Keyword density; Relational database; Keyword search; Matching (statistics); Data mining; Table (database); Focus (optics); Database; Mathematics","score_opus":0.06452476657364406,"score_gpt":0.26599489127396836,"score_spread":0.2014701247003243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970296249","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034396322,0.00031640643,0.55427015,0.00013295271,0.0010123296,0.00033813942,0.00005910416,0.00018659589,0.44024467],"genre_scores_gemma":[0.98430926,0.00022466117,0.0068510617,0.0008825165,0.00020479396,0.000061874955,0.00045965303,0.000009610009,0.006996584],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99926406,0.000038158927,0.00024078053,0.0001172706,0.0001800222,0.0001597261],"domain_scores_gemma":[0.9994392,0.000031997268,0.00007162324,0.00030031757,0.000095018135,0.00006187703],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00047105367,0.00008336749,0.00008337432,0.00019263627,0.00014886014,0.00017863873,0.00026673533,0.000019796958,0.00002855905],"category_scores_gemma":[0.000017680746,0.00006873176,0.000017416422,0.00022189153,0.000014737084,0.0063533452,0.00024569876,0.000068783884,0.0013507513],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003902895,0.000030447716,0.0006966776,0.000044256933,0.000010357351,9.3812025e-7,0.0025532118,0.0000035307173,6.300089e-7,0.95443344,0.010627315,0.03159532],"study_design_scores_gemma":[0.000328833,0.000045178593,0.004696186,0.000059406386,0.0000021622222,0.0000048263005,0.0001519209,0.0992353,0.00005623495,0.00004844988,0.89525557,0.00011590782],"about_ca_topic_score_codex":0.000015159787,"about_ca_topic_score_gemma":0.000001932389,"teacher_disagreement_score":0.9808696,"about_ca_system_score_codex":0.000014980187,"about_ca_system_score_gemma":0.000021417207,"threshold_uncertainty_score":0.99942684},"labels":[],"label_agreement":null},{"id":"W1971159983","doi":"10.1007/s10115-012-0610-x","title":"Fuzzy set-oriented neural networks based on fuzzy polynomial inference and dynamic genetic optimization","year":2013,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Mathematical optimization; Fuzzy logic; Computer science; Polynomial; Mathematics; Adaptive neuro fuzzy inference system; Neuro-fuzzy; Algorithm; Fuzzy control system; Artificial intelligence","score_opus":0.007798783949087225,"score_gpt":0.22675202680502993,"score_spread":0.2189532428559427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971159983","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026326865,0.00039932577,0.96407306,0.0003759949,0.0006921645,0.00091791444,0.000006077573,0.00018258378,0.007026026],"genre_scores_gemma":[0.99782616,0.0000623814,0.0014974175,0.00028119906,0.00008626305,0.00013781872,0.000040790914,0.000005545479,0.00006244268],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990359,0.00005613426,0.00038407213,0.00018383091,0.00013064023,0.00020940583],"domain_scores_gemma":[0.9991652,0.0000915393,0.00016075456,0.0002825167,0.00016854056,0.00013150033],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010954968,0.00015503656,0.00014809392,0.00013538051,0.00022667261,0.00057675526,0.00020857246,0.00008514731,0.0000033090716],"category_scores_gemma":[0.0000120682425,0.00013199735,0.000023209492,0.00035254678,0.000037483216,0.0018709498,0.00009548975,0.000113125076,0.0000491859],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007258953,0.000029673474,0.00084033376,0.00007109281,0.0000080386335,2.9224125e-7,0.0005821941,0.90538967,0.000013679122,0.009508823,0.003436782,0.08011217],"study_design_scores_gemma":[0.00033855165,0.00007139106,0.0038731347,0.000034344273,0.0000035708151,0.0000070339097,0.000034976118,0.9920129,0.0000020591444,0.000019326786,0.003452051,0.00015067145],"about_ca_topic_score_codex":0.00003427941,"about_ca_topic_score_gemma":0.000003092277,"teacher_disagreement_score":0.97149926,"about_ca_system_score_codex":0.000027106595,"about_ca_system_score_gemma":0.000024697487,"threshold_uncertainty_score":0.5561664},"labels":[],"label_agreement":null},{"id":"W1971324060","doi":"10.1007/pl00011676","title":"Parallel and Sequential Algorithms for Data Mining Using Inductive Logic","year":2001,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada); Queen's University","funders":"","keywords":"Computer science; Inductive logic programming; Algorithm; Data mining; Artificial intelligence","score_opus":0.09966565189006675,"score_gpt":0.33770732626556443,"score_spread":0.23804167437549767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971324060","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0073911487,0.0007349274,0.9880199,0.00008325535,0.00065930485,0.00025944304,0.000011152833,0.0000775071,0.0027633726],"genre_scores_gemma":[0.6858633,0.0002329166,0.3114687,0.00023212706,0.001147605,0.000061445084,0.00021511303,0.000017261511,0.00076152745],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918896,0.00005162134,0.0002924807,0.00018978218,0.000100941936,0.00017622273],"domain_scores_gemma":[0.9993036,0.00006271758,0.00015047895,0.00028663417,0.00012418973,0.00007240928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005356062,0.00011101673,0.00015686995,0.0001251124,0.00024650103,0.00041649537,0.0003015587,0.00006437734,9.032349e-7],"category_scores_gemma":[0.000050032777,0.000094148,0.000015146807,0.00016980409,0.000028578479,0.0036939376,0.0002915363,0.000076280325,0.00000977358],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026326254,0.000052523665,0.0021139907,0.00046694808,0.00010088533,0.000004379678,0.020227266,0.0012535051,0.000049673956,0.060087506,0.002996197,0.9126208],"study_design_scores_gemma":[0.00043613397,0.000046008467,0.00016329867,0.000039636794,0.0000064524675,0.000108923494,0.00040814138,0.90374374,0.0000022643346,0.00008082942,0.09484187,0.00012271867],"about_ca_topic_score_codex":0.00008292831,"about_ca_topic_score_gemma":0.000002223913,"teacher_disagreement_score":0.91249806,"about_ca_system_score_codex":0.000017565086,"about_ca_system_score_gemma":0.000044281045,"threshold_uncertainty_score":0.40162745},"labels":[],"label_agreement":null},{"id":"W1973249903","doi":"10.1007/s10115-012-0585-7","title":"Models of distributed data clustering in peer-to-peer environments","year":2012,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; D2L (Canada)","funders":"","keywords":"Cluster analysis; Computer science; Automatic summarization; Scalability; Data mining; Distributed computing; Process (computing); Data stream clustering; Node (physics); Correlation clustering; Set (abstract data type); CURE data clustering algorithm; Machine learning; Artificial intelligence; Database; Engineering","score_opus":0.04619821659333672,"score_gpt":0.2805203146211613,"score_spread":0.23432209802782455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973249903","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029425414,0.00016233373,0.99233896,0.00011376448,0.00020170271,0.0001864368,0.00027876842,0.000019134342,0.0037563923],"genre_scores_gemma":[0.9926476,0.000013642219,0.006543067,0.000022324488,0.000040496045,0.000031705567,0.000507163,0.0000024142519,0.00019157915],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992382,0.000017240465,0.00032856726,0.00009060482,0.00018424274,0.00014117607],"domain_scores_gemma":[0.99923444,0.000022235365,0.000086442386,0.00052437524,0.0000518299,0.00008065182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006625629,0.00006355355,0.00010552718,0.000096486125,0.00004014586,0.00008986786,0.00048464027,0.00003223629,7.924266e-7],"category_scores_gemma":[0.000028192168,0.000058143432,0.0000070125016,0.00021754458,0.000010232363,0.0057384027,0.0005571681,0.000041062744,0.00008275505],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015031877,0.00057899195,0.007792468,0.00072453835,0.000074747324,4.891171e-7,0.07850846,0.011652478,0.000349345,0.17586589,0.08008521,0.6443524],"study_design_scores_gemma":[0.00012696853,0.000007175678,0.0021684365,0.00002940879,0.0000014446633,0.000003177016,0.00021916222,0.70765674,0.000026786012,0.000008675582,0.2896893,0.00006273994],"about_ca_topic_score_codex":0.00004162135,"about_ca_topic_score_gemma":0.0000024946755,"teacher_disagreement_score":0.9897051,"about_ca_system_score_codex":0.00002333253,"about_ca_system_score_gemma":0.000012697406,"threshold_uncertainty_score":0.41602036},"labels":[],"label_agreement":null},{"id":"W1974256760","doi":"10.1007/s10115-009-0237-8","title":"A general measure of similarity for categorical sequences","year":2009,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Categorical variable; Similarity (geometry); Computer science; Data mining; Matching (statistics); Similarity measure; Pattern recognition (psychology); Artificial intelligence; Range (aeronautics); Domain (mathematical analysis); Measure (data warehouse); Process (computing); Sequence (biology); Noise (video); Mathematics; Machine learning; Statistics; Image (mathematics)","score_opus":0.024416134772725646,"score_gpt":0.2734250690558867,"score_spread":0.24900893428316107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1974256760","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018932987,0.00048663758,0.98596627,0.0003157705,0.00019652079,0.0002968145,0.000031695112,0.000059997226,0.010752988],"genre_scores_gemma":[0.9850036,0.00002513041,0.014595366,0.00008393449,0.000092029084,0.000046930054,0.000035167697,0.0000012673715,0.000116584924],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99945873,0.000013727977,0.00026808365,0.00007819594,0.00009018845,0.00009107185],"domain_scores_gemma":[0.99943876,0.000028088147,0.00009913321,0.00017046959,0.00021740298,0.000046138433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028696927,0.000057927304,0.00011311485,0.00006209648,0.0000870053,0.00012098805,0.0002171129,0.000041601124,3.2087493e-7],"category_scores_gemma":[0.000023112825,0.00004692666,0.000023657465,0.00017999666,0.00001536625,0.0015689016,0.000025067855,0.000031747713,0.000008311342],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002200736,0.000030211842,0.00004546435,0.00007122772,0.000007106214,5.779373e-8,0.0020756342,0.000027782866,0.00012298264,0.75161684,0.0076129423,0.23838754],"study_design_scores_gemma":[0.00039223395,0.00016685156,0.0015492189,0.000030002746,0.000007004767,0.000020480667,0.00014843507,0.6643068,0.00044864835,0.0015402831,0.33123484,0.00015516192],"about_ca_topic_score_codex":0.000016326658,"about_ca_topic_score_gemma":7.9554957e-7,"teacher_disagreement_score":0.9831103,"about_ca_system_score_codex":0.000012375438,"about_ca_system_score_gemma":0.00005029297,"threshold_uncertainty_score":0.19136137},"labels":[],"label_agreement":null},{"id":"W1976274084","doi":"10.1007/s10115-007-0120-4","title":"A framework for simulating real-time multi-agent systems","year":2008,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Multi-Agent Systems and Negotiation","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Multi-agent system; Context (archaeology); Architecture; Distributed computing; Autonomous agent; Real-time computing; Artificial intelligence","score_opus":0.045866521007289794,"score_gpt":0.2892687766946496,"score_spread":0.24340225568735982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976274084","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015542004,0.00083516364,0.97609985,0.00002655725,0.0020302231,0.0014846814,0.0000180616,0.00032015747,0.0036432736],"genre_scores_gemma":[0.98576695,0.00013185559,0.012049653,0.000034939843,0.00037790363,0.00026385888,0.000038683727,0.000014386562,0.0013217855],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981981,0.00010807167,0.00089114247,0.0002364912,0.00025608615,0.00031011156],"domain_scores_gemma":[0.99827725,0.0002873621,0.00046889935,0.0004145569,0.00039931305,0.00015260893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006750845,0.00021200594,0.00035065608,0.00022571182,0.00049924676,0.00036431564,0.00029726655,0.00018095596,0.0000023066762],"category_scores_gemma":[0.00013080309,0.0001853014,0.00008166044,0.00029017875,0.000023319455,0.0030889583,0.00009397011,0.00008982385,0.00041138774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006591157,0.00042145152,0.008257468,0.0061726817,0.00033090956,0.000009165008,0.12585256,0.023594853,0.0015706399,0.7845305,0.02659845,0.022595368],"study_design_scores_gemma":[0.00074072974,0.0000620583,0.0012452758,0.00025613428,0.0000061070928,0.00004645845,0.00028882932,0.92635953,0.000043176973,0.000015563193,0.07069047,0.00024564628],"about_ca_topic_score_codex":0.00011211795,"about_ca_topic_score_gemma":0.0000010850284,"teacher_disagreement_score":0.9702249,"about_ca_system_score_codex":0.00009138621,"about_ca_system_score_gemma":0.00007251158,"threshold_uncertainty_score":0.75563717},"labels":[],"label_agreement":null},{"id":"W1976355580","doi":"10.1007/s10115-011-0439-8","title":"Finding best evidence for evidence-based best practice recommendations in health care: the initial decision support system design","year":2011,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Best practice; Medical prescription; Clinical decision support system; Decision support system; Harm; Health care; Quality (philosophy); eHealth; Evidence-based practice; Medicine; Risk analysis (engineering); Computer science; Data mining; Nursing; Psychology; Alternative medicine","score_opus":0.539744659034669,"score_gpt":0.4976609918738763,"score_spread":0.04208366716079265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976355580","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00045683808,0.004046795,0.9736748,0.0026020787,0.002696932,0.0037808493,0.00011380267,0.000060661983,0.0125672715],"genre_scores_gemma":[0.9879296,0.000609986,0.009169791,0.0010180823,0.00017237136,0.0007149783,0.00006680217,0.000011298208,0.00030710443],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99551815,0.0011935574,0.0019788905,0.0002883934,0.000723738,0.0002972798],"domain_scores_gemma":[0.9866272,0.010610133,0.001032666,0.0006218566,0.0009825462,0.00012559367],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021306742,0.00016788527,0.00032426917,0.0005301597,0.0006133903,0.00084466866,0.00068921724,0.00008535634,0.000029806963],"category_scores_gemma":[0.010161366,0.0001137103,0.00006559705,0.0008075533,0.00006141597,0.010797429,0.00016445635,0.00013567123,0.00077147345],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010049428,0.0002513301,0.0004499779,0.0021624637,0.000042759355,0.0000031010252,0.09895134,0.0006792665,0.000001981751,0.067830525,0.15898974,0.66963255],"study_design_scores_gemma":[0.00086473516,0.00083361927,0.00018328597,0.0036075711,0.00003859261,0.00002038893,0.13100518,0.018965557,0.000035843026,0.000088143555,0.8441218,0.00023527854],"about_ca_topic_score_codex":0.00055333367,"about_ca_topic_score_gemma":0.00015655845,"teacher_disagreement_score":0.9874728,"about_ca_system_score_codex":0.00029106246,"about_ca_system_score_gemma":0.0005215887,"threshold_uncertainty_score":0.99817646},"labels":[],"label_agreement":null},{"id":"W1977437156","doi":"10.1007/s10115-010-0347-3","title":"Class separation through variance: a new application of outlier detection","year":2010,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Mahalanobis distance; Linear subspace; Outlier; Subspace topology; Anomaly detection; Pattern recognition (psychology); Computer science; Artificial intelligence; Ranking (information retrieval); Variance (accounting); Class (philosophy); Data mining; Mathematics; Algorithm","score_opus":0.008671805795515073,"score_gpt":0.26656406260817367,"score_spread":0.2578922568126586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977437156","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003024511,0.000063575964,0.9738854,0.000088003275,0.00034934972,0.00042665246,0.0000025890695,0.00019776245,0.021962157],"genre_scores_gemma":[0.9929659,0.000025134854,0.006387071,0.0000406039,0.00012540864,0.00013787637,0.000008481117,0.0000036264707,0.00030591176],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99921954,0.000019075671,0.00041813636,0.0001297049,0.000117803276,0.00009574486],"domain_scores_gemma":[0.9990529,0.000024222789,0.00028025673,0.0003515299,0.00023599157,0.000055129825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021879606,0.00009098149,0.00012115571,0.00010905864,0.0001358579,0.00013142182,0.00019700587,0.00012493411,0.0000025730676],"category_scores_gemma":[0.000014524379,0.000085241394,0.000032472806,0.00041888515,0.000025938974,0.0030278238,0.000050440634,0.000121127094,0.00010053465],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000050453573,0.000029441166,0.00011039145,0.000075991935,0.000009886669,1.890105e-8,0.0025288472,0.00004184838,0.017638681,0.73964965,0.0016090974,0.23830108],"study_design_scores_gemma":[0.00025038226,0.00006139628,0.00097239343,0.000010960773,0.0000062664553,0.000023286166,0.00008582873,0.19543631,0.020319602,0.0018629775,0.7808281,0.00014248202],"about_ca_topic_score_codex":0.000115344585,"about_ca_topic_score_gemma":0.00002315689,"teacher_disagreement_score":0.98994136,"about_ca_system_score_codex":0.000019129197,"about_ca_system_score_gemma":0.00005555339,"threshold_uncertainty_score":0.34760433},"labels":[],"label_agreement":null},{"id":"W1981324119","doi":"10.1007/s10115-010-0292-1","title":"Architecturing large integrated complex information systems: an application to healthcare","year":2010,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Electronic Health Records Systems","field":"Health Professions","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Knowledge management; Enterprise architecture; Information system; Schema (genetic algorithms); Key (lock); Enterprise information system; Multitude; Data science; Enterprise integration; Health care; Architecture; Process management; Enterprise software; Business; Engineering; Computer security","score_opus":0.03302324811347194,"score_gpt":0.38800239655700186,"score_spread":0.3549791484435299,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981324119","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62872636,0.0010554211,0.20436391,0.0022144702,0.01676917,0.027233884,0.0011407975,0.0025157246,0.11598026],"genre_scores_gemma":[0.99480003,0.00002587208,0.00015962399,0.0008992504,0.00077633007,0.0019664038,0.0010799327,0.000025369758,0.0002672143],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955548,0.0007113949,0.0021855682,0.0002332746,0.00037471447,0.0009402286],"domain_scores_gemma":[0.99635935,0.00021821269,0.0008152229,0.0006465563,0.0012801111,0.00068056275],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0031728153,0.0003102436,0.0005368994,0.00070993,0.001251826,0.00018015763,0.00030705333,0.00046943658,0.000023212493],"category_scores_gemma":[0.00022681816,0.00027126822,0.00004011899,0.00065494824,0.000027495638,0.0036802082,0.00011083317,0.0011742228,0.0028717597],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039821732,0.00021266767,0.037318975,0.03251325,0.00011551937,7.43625e-7,0.21962392,0.0005065512,0.0018435821,0.492197,0.03888719,0.17638238],"study_design_scores_gemma":[0.0008550823,0.00016627884,0.0059204535,0.00038489647,0.000006776512,0.000022894157,0.012599485,0.049820285,0.00000796591,0.000012249455,0.92992395,0.00027965943],"about_ca_topic_score_codex":0.0038599214,"about_ca_topic_score_gemma":0.0024885947,"teacher_disagreement_score":0.8910368,"about_ca_system_score_codex":0.0004357975,"about_ca_system_score_gemma":0.0007793673,"threshold_uncertainty_score":0.99997395},"labels":[],"label_agreement":null},{"id":"W1981664281","doi":"10.1007/s10115-012-0593-7","title":"A multi-phase correlation search framework for mining non-taxonomic relations from unstructured text","year":2012,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Canarie","keywords":"Computer science; Ontology; Taxonomy (biology); Taxonomic rank; Domain (mathematical analysis); Information retrieval; Sentence; Information extraction; Relationship extraction; Lift (data mining); Natural language processing; Artificial intelligence; Data science; Data mining; Mathematics; Ecology; Biology","score_opus":0.03944275429594141,"score_gpt":0.3070370740464318,"score_spread":0.2675943197504904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981664281","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.069587715,0.00082004233,0.9254197,0.000050137813,0.0016725964,0.00046752766,0.000017924616,0.00009266184,0.0018717089],"genre_scores_gemma":[0.8845752,0.0000099406725,0.1149816,0.000032465807,0.00019293778,0.0000622927,0.000049069695,0.0000039395986,0.000092554794],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991233,0.000041567844,0.0003986325,0.00011312821,0.0000931294,0.00023026293],"domain_scores_gemma":[0.9989875,0.000377144,0.00016265524,0.000244661,0.00013352721,0.00009451605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003478927,0.000114354465,0.00017012938,0.00016018265,0.00024055017,0.0002507555,0.00019557825,0.00015363542,0.0000048525876],"category_scores_gemma":[0.0001312691,0.000099667675,0.000040176,0.00017848794,0.00002613684,0.0037737715,0.00007115582,0.00009596807,0.00018850643],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000930102,0.00027079423,0.07606488,0.00047381158,0.00020337115,4.832391e-7,0.17413773,0.0014051297,0.00031653538,0.46752477,0.014141888,0.2653676],"study_design_scores_gemma":[0.0012848254,0.000049907143,0.02723216,0.00010880042,0.000013745984,0.0000080060645,0.0025148066,0.93312883,0.00012158734,0.00013664957,0.035208248,0.00019241069],"about_ca_topic_score_codex":0.000040784696,"about_ca_topic_score_gemma":0.0000043903815,"teacher_disagreement_score":0.9317237,"about_ca_system_score_codex":0.00004763914,"about_ca_system_score_gemma":0.000062823994,"threshold_uncertainty_score":0.406433},"labels":[],"label_agreement":null},{"id":"W1981679236","doi":"10.1007/s10115-004-0150-0","title":"Multiknowledge for decision making","year":2004,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Reduct; Rough set; Computer science; Data mining; Artificial intelligence; Decision system; Naive Bayes classifier; Machine learning; Classifier (UML); Decision table; Mathematics; Support vector machine","score_opus":0.01815329828864976,"score_gpt":0.2729560177640058,"score_spread":0.25480271947535604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981679236","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017019234,0.0010616012,0.96080434,0.00006200893,0.0012302442,0.0004325931,0.000005162497,0.00012564902,0.034576464],"genre_scores_gemma":[0.96703184,0.000036882404,0.032591835,0.00009946701,0.00012822897,0.00006638327,0.000005026364,0.000003789162,0.00003654264],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992212,0.000012760846,0.00035653068,0.0001250567,0.00010355922,0.00018089704],"domain_scores_gemma":[0.9992919,0.00011521414,0.00010667995,0.00022840426,0.00019773038,0.000060045142],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033916358,0.000105672494,0.00014172154,0.00014783548,0.00020598585,0.00038926787,0.00027060698,0.00007176932,8.9846026e-7],"category_scores_gemma":[0.00007956972,0.00008264155,0.000042856587,0.00020499523,0.000015622712,0.0027864913,0.00010476494,0.00004659445,0.00022178913],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000113167225,0.00003446008,0.00008014955,0.00019527628,0.000010279881,4.3003848e-7,0.006956055,0.0005826049,0.000008333506,0.52416515,0.0032669096,0.46468902],"study_design_scores_gemma":[0.0017633874,0.00019007856,0.0014453968,0.00044603,0.0000063937036,0.000053683194,0.00034650878,0.23811492,0.000050448372,0.0052091796,0.75201917,0.0003548278],"about_ca_topic_score_codex":0.0000045748334,"about_ca_topic_score_gemma":0.0000032565856,"teacher_disagreement_score":0.96532995,"about_ca_system_score_codex":0.000050336028,"about_ca_system_score_gemma":0.000057748213,"threshold_uncertainty_score":0.3753719},"labels":[],"label_agreement":null},{"id":"W1982481381","doi":"10.1007/pl00011667","title":"ActiveCBR: An Agent System That Integrates Case-Based Reasoning and Active Databases","year":2001,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"AI-based Problem Solving and Planning","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Active database; Computer science; Case-based reasoning; Property (philosophy); Artificial intelligence; Reasoning system; Feature (linguistics); Database; Data mining; Event (particle physics); Expert system; Machine learning","score_opus":0.034879124724015026,"score_gpt":0.26716649458248526,"score_spread":0.23228736985847023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982481381","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25270215,0.0022543413,0.72370136,0.00006731561,0.0008668048,0.00063001586,0.00009035348,0.0006134705,0.019074174],"genre_scores_gemma":[0.99775594,0.000034182634,0.0019144941,0.000047023594,0.000062877305,0.00003917164,0.00008142954,0.0000061975393,0.00005870843],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890894,0.00016700677,0.00032916295,0.00021573088,0.00014958033,0.00022955278],"domain_scores_gemma":[0.99892014,0.00018832211,0.0002377404,0.00031490333,0.00017068058,0.00016819827],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000626237,0.00018670004,0.00021540571,0.00022435423,0.00042298075,0.00056734163,0.00017373201,0.00006689233,0.0000018630691],"category_scores_gemma":[0.00003643083,0.00015377684,0.000023812458,0.0002482202,0.000033292563,0.005689398,0.00008394447,0.0001371192,0.000026367312],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003040222,0.0002284856,0.04938471,0.0042029787,0.0002846793,0.0007375802,0.12150211,0.0027640269,0.00020381347,0.19805674,0.0063334582,0.6159974],"study_design_scores_gemma":[0.00066665944,0.00016115782,0.0010427978,0.0009995883,0.000019563455,0.0026020438,0.0134268375,0.8882624,0.0006064984,0.000004564121,0.091828436,0.00037948648],"about_ca_topic_score_codex":0.0004147634,"about_ca_topic_score_gemma":0.00003027445,"teacher_disagreement_score":0.88549834,"about_ca_system_score_codex":0.00008072267,"about_ca_system_score_gemma":0.00008257564,"threshold_uncertainty_score":0.6270838},"labels":[],"label_agreement":null},{"id":"W1988047293","doi":"10.1007/s10115-013-0617-y","title":"Analyzing topics and authors in chat logs for crime investigation","year":2013,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Topic Modeling","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Computer science; Exploit; Latent Dirichlet allocation; Online chat; Process (computing); The Internet; Order (exchange); Volume (thermodynamics); Channel (broadcasting); Topic model; Data science; World Wide Web; Information retrieval; Computer security","score_opus":0.026709074949374544,"score_gpt":0.2508178429459265,"score_spread":0.22410876799655197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988047293","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18069315,0.0010049746,0.8112191,0.00060307985,0.00069560064,0.00079689635,0.0000012603045,0.000081333565,0.004904574],"genre_scores_gemma":[0.99607676,0.000023541505,0.0034380008,0.00007023927,0.0000751913,0.00007781833,0.000005507286,0.0000019270647,0.00023101685],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994371,0.000024806917,0.00029308663,0.0000885246,0.000050249437,0.000106258114],"domain_scores_gemma":[0.9996111,0.00003247681,0.00007583302,0.00011796373,0.000105542895,0.0000571171],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032117916,0.000060926664,0.00009823649,0.00015818048,0.00006161073,0.0002883639,0.000093995164,0.00005785878,5.4869224e-7],"category_scores_gemma":[0.00004028002,0.000054568525,0.000010343667,0.00012198282,0.0000118672815,0.0033662536,0.000054028085,0.00004471911,0.00001750556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020979542,0.000011527392,0.020187732,0.0009843673,0.00001396367,1.6019636e-7,0.042568237,0.00031616905,0.0002247831,0.5953673,0.002050033,0.3382736],"study_design_scores_gemma":[0.00027307146,0.000020292606,0.008983702,0.00006382536,0.0000016677301,0.000004216295,0.0003341092,0.9718997,0.00010115577,0.0012235107,0.016996376,0.0000983695],"about_ca_topic_score_codex":0.000075585995,"about_ca_topic_score_gemma":0.000004022404,"teacher_disagreement_score":0.97158355,"about_ca_system_score_codex":0.000022945487,"about_ca_system_score_gemma":0.000022521706,"threshold_uncertainty_score":0.27806997},"labels":[],"label_agreement":null},{"id":"W1991278297","doi":"10.1007/pl00011645","title":"Intentions in the Coordinated Generation of Graphics and Text from Tabular Data","year":2000,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Graphics; Computer science; Wizard; Chart; Set (abstract data type); Table (database); Declaration; ASCII; Computer graphics (images); Information retrieval; Focus (optics); Plotter; Programming language; Data mining; World Wide Web","score_opus":0.05029146975346122,"score_gpt":0.2904555233044631,"score_spread":0.2401640535510019,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991278297","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1406749,0.00460981,0.82363206,0.00088963425,0.00063641684,0.00089520484,0.00044373868,0.000115611445,0.028102644],"genre_scores_gemma":[0.9986356,0.00045330936,0.00013150151,0.00012094837,0.000025743047,0.000004223161,0.00056650327,0.0000012255766,0.000060958173],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993726,0.00006938519,0.00031127574,0.000082306564,0.00011031562,0.000054086773],"domain_scores_gemma":[0.99943036,0.000033483426,0.00007567388,0.0003449594,0.00009479986,0.000020723337],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042281862,0.00005057245,0.00008281993,0.00010931153,0.00006764962,0.0002380663,0.00033385883,0.000032839514,0.000007424723],"category_scores_gemma":[0.000029587838,0.000036715883,0.000007322506,0.00039177362,0.000027860831,0.0026897744,0.000076031116,0.00004088875,0.00001657671],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000066966336,0.00017711116,0.005406687,0.00019826775,0.000058801947,0.000001004331,0.024306376,0.00029042785,0.00021505645,0.7412269,0.055079196,0.17303345],"study_design_scores_gemma":[0.00019824237,0.000011827757,0.0016047616,0.000029903214,0.00000457872,0.000002550176,0.00035507878,0.8326009,0.000015515445,0.000046291974,0.16508347,0.000046893838],"about_ca_topic_score_codex":0.0001159011,"about_ca_topic_score_gemma":0.00006728024,"teacher_disagreement_score":0.8579607,"about_ca_system_score_codex":0.000003936365,"about_ca_system_score_gemma":0.00002112452,"threshold_uncertainty_score":0.22956789},"labels":[],"label_agreement":null},{"id":"W1991959600","doi":"10.1007/s10115-008-0145-3","title":"Resolution-based outlier factor: detecting the top-n most outlying data points in engineering data","year":2008,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Outlier; Anomaly detection; Data mining; Computer science; Identification (biology); Local outlier factor; Rank (graph theory); Nonparametric statistics; Domain (mathematical analysis); Artificial intelligence; Mathematics; Statistics","score_opus":0.05467301865057345,"score_gpt":0.27022438014433875,"score_spread":0.2155513614937653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991959600","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0077521675,0.0003638553,0.989426,0.00016483403,0.00023585919,0.00039657977,0.000055065655,0.00024059598,0.0013650467],"genre_scores_gemma":[0.99668777,0.000026441814,0.003007786,0.00006665395,0.000061302075,0.00003903719,0.0000719672,0.000004710284,0.000034352775],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990644,0.00003502484,0.00040406207,0.00019903296,0.00013736526,0.00016012859],"domain_scores_gemma":[0.99827373,0.000113415445,0.00012736073,0.0013607689,0.00007928891,0.00004541376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054812594,0.00010015873,0.0001114876,0.00016321069,0.00031504995,0.00019540197,0.0011298617,0.00005829458,0.0000016970275],"category_scores_gemma":[0.00010974147,0.0000785164,0.000011715091,0.00048212914,0.000021166526,0.0034002485,0.00057248725,0.00014731912,0.00004179456],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005546916,0.00047651495,0.09279066,0.0020645945,0.00021220559,0.000012443346,0.058679115,0.019774754,0.0010366612,0.09381883,0.05334174,0.677737],"study_design_scores_gemma":[0.0001465762,0.0000075224125,0.0036550632,0.000037278554,0.0000014537954,0.000013333463,0.000103935,0.8664418,0.00007154227,0.0000037300472,0.12941802,0.000099780955],"about_ca_topic_score_codex":0.00009437228,"about_ca_topic_score_gemma":0.000013651289,"teacher_disagreement_score":0.9889356,"about_ca_system_score_codex":0.0000426557,"about_ca_system_score_gemma":0.00006961913,"threshold_uncertainty_score":0.3201806},"labels":[],"label_agreement":null},{"id":"W2004295584","doi":"10.1007/s10115-008-0187-6","title":"The analysis and management of non-canonical requirement specifications through a belief integration game","year":2009,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Software Engineering Research","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Viewpoints; Set (abstract data type); Analogy; Outcome (game theory); Theoretical computer science; Mathematics; Programming language; Mathematical economics","score_opus":0.029788926324930975,"score_gpt":0.29060839348361633,"score_spread":0.26081946715868537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004295584","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0067648906,0.0010893383,0.98411024,0.0002887202,0.0001240309,0.00033261237,0.0000016061826,0.00004537262,0.007243165],"genre_scores_gemma":[0.9966857,0.000752591,0.0023419473,0.000009848665,0.000018970915,0.000032416963,0.000005280241,0.000001218828,0.00015203372],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9992086,0.000025352347,0.0003578899,0.00009305138,0.00020229282,0.00011279331],"domain_scores_gemma":[0.9992662,0.000114924565,0.00009115803,0.00032372354,0.00016603967,0.000037921127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046518262,0.00006698399,0.00011258669,0.00014361095,0.000106140265,0.0002352588,0.00022605491,0.000028287977,6.5698777e-7],"category_scores_gemma":[0.000028160024,0.000046823236,0.000029312303,0.0007485061,0.000029259236,0.001197687,0.00006931123,0.000052192012,0.000015137513],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009660689,0.00006653925,0.0012300812,0.00023731386,0.00031833537,5.79344e-7,0.011933737,0.00042703905,0.00015470356,0.6305183,0.0020717797,0.3530319],"study_design_scores_gemma":[0.00066777493,0.00020794742,0.46952078,0.00022524713,0.00009295357,0.000009254308,0.0011213906,0.37159133,0.00060696277,0.00033417597,0.15535837,0.0002638131],"about_ca_topic_score_codex":0.000011281506,"about_ca_topic_score_gemma":0.0000026256325,"teacher_disagreement_score":0.9899208,"about_ca_system_score_codex":0.000040215324,"about_ca_system_score_gemma":0.000018856708,"threshold_uncertainty_score":0.2268606},"labels":[],"label_agreement":null},{"id":"W2007800125","doi":"10.1007/s10115-014-0801-8","title":"Greedy column subset selection for large-scale data sets","year":2014,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Column (typography); Selection (genetic algorithm); Greedy algorithm; Algorithm; Representation (politics); Matrix (chemical analysis); Big data; Data mining; Artificial intelligence; Frame (networking)","score_opus":0.02411245776584549,"score_gpt":0.2674305953687463,"score_spread":0.2433181376029008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007800125","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006806211,0.00014371338,0.979907,0.00013322993,0.0010669945,0.0005097776,0.000097756456,0.00017465283,0.011160683],"genre_scores_gemma":[0.9927744,0.000048097245,0.0047563086,0.00037131182,0.00027226217,0.00014665822,0.00096946245,0.000008039655,0.00065345224],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992038,0.000052737756,0.00029577373,0.00015893436,0.00011640451,0.00017237013],"domain_scores_gemma":[0.9991722,0.000064187814,0.0001260481,0.0003340843,0.00023157234,0.000071869166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007320938,0.00008673998,0.00012662252,0.000108576125,0.0002348054,0.00034483513,0.00032849898,0.00007902023,0.0000037098446],"category_scores_gemma":[0.000048470672,0.000077441546,0.000019271354,0.00018447636,0.000007396207,0.004973713,0.00015571444,0.000051348256,0.00025499353],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033915483,0.000119627395,0.0028305145,0.0010845923,0.000037629532,7.303117e-8,0.008913418,0.00007722973,0.00036899684,0.037645385,0.7684908,0.18039784],"study_design_scores_gemma":[0.0003450435,0.00003966329,0.00022814827,0.000034881374,0.0000029413525,0.0000065888116,0.000115545095,0.51180005,0.00011916652,0.000051763054,0.48718363,0.00007257593],"about_ca_topic_score_codex":0.00001627208,"about_ca_topic_score_gemma":0.000039180162,"teacher_disagreement_score":0.9859682,"about_ca_system_score_codex":0.00001499206,"about_ca_system_score_gemma":0.000029437262,"threshold_uncertainty_score":0.36058217},"labels":[],"label_agreement":null},{"id":"W2009423697","doi":"10.1007/s10115-013-0658-2","title":"Email mining: tasks, common techniques, and tools","year":2013,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Categorization; World Wide Web; Data science; Visualization; Information retrieval; Data mining; Artificial intelligence","score_opus":0.015393168495726351,"score_gpt":0.22877223111903855,"score_spread":0.2133790626233122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009423697","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4495901,0.0058072694,0.11893517,0.0008664399,0.003206076,0.0023327318,0.000010753158,0.0017007561,0.41755074],"genre_scores_gemma":[0.9985225,0.00006858673,0.0008617189,0.00007741179,0.00010146847,0.00007686704,0.000006866403,0.0000029170442,0.00028161512],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993973,0.000037753172,0.00026786255,0.00009093162,0.00009219969,0.00011398311],"domain_scores_gemma":[0.9994678,0.00005265635,0.0001025156,0.00019274048,0.00011290011,0.00007141756],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00026968398,0.00008651211,0.000118246484,0.00012410546,0.00013705678,0.0011254676,0.00014755694,0.000076489225,0.0000032225344],"category_scores_gemma":[0.000017744835,0.000073617106,0.0000138627365,0.00016642996,0.000020313677,0.007821758,0.000094267874,0.0000626214,0.00015177244],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002228769,0.000012443495,0.0011675365,0.00020132582,0.000010552042,4.7475191e-7,0.0070399283,0.0000014485441,0.0001184494,0.035136674,0.026785575,0.92952335],"study_design_scores_gemma":[0.0003308432,0.00015285607,0.004331955,0.00013554355,0.0000043683185,0.00018188379,0.000699776,0.04502887,0.0010054226,0.00017328854,0.9476953,0.00025990565],"about_ca_topic_score_codex":0.00012333784,"about_ca_topic_score_gemma":0.0000041161998,"teacher_disagreement_score":0.9292635,"about_ca_system_score_codex":0.000018466673,"about_ca_system_score_gemma":0.00001565341,"threshold_uncertainty_score":0.9999115},"labels":[],"label_agreement":null},{"id":"W2011191813","doi":"10.1007/s10115-009-0226-y","title":"Subspace and projected clustering: experimental evaluation and analysis","year":2009,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Subspace topology; Computer science; Data mining; Range (aeronautics); Clustering high-dimensional data; Consensus clustering; Artificial intelligence; Correlation clustering; CURE data clustering algorithm; Engineering","score_opus":0.0260607623732046,"score_gpt":0.33560897402197565,"score_spread":0.30954821164877105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011191813","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1953805,0.0056063333,0.7869529,0.00021878233,0.00023814755,0.0011398525,0.00000442101,0.0002142725,0.010244761],"genre_scores_gemma":[0.9974134,0.000052033334,0.002330999,0.000023246339,0.000026219048,0.000035017954,0.000010712169,0.0000020130087,0.00010633305],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991026,0.00007900471,0.0002449848,0.00016515401,0.00025407414,0.00015417022],"domain_scores_gemma":[0.99937695,0.00003089116,0.0000859172,0.0001892623,0.00022382653,0.00009315759],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005176085,0.00010210883,0.0001579597,0.0003600104,0.00014965238,0.00044407163,0.000110966765,0.0000484272,0.0000012533822],"category_scores_gemma":[0.000033573888,0.00009121774,0.000016118545,0.00058724673,0.000027439468,0.0029540102,0.00013033015,0.00006182487,0.000007393433],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000589572,0.00012586568,0.0026834046,0.00038344643,0.0002763455,0.000002794536,0.07744251,0.0031610806,0.0023356008,0.013434878,0.00042923682,0.8996659],"study_design_scores_gemma":[0.00045949343,0.00011097882,0.0113820685,0.000019901614,0.000015320606,0.000027186436,0.00060252164,0.9844515,0.0002112004,0.000015009641,0.0025908903,0.00011395427],"about_ca_topic_score_codex":0.000013809658,"about_ca_topic_score_gemma":0.000003917117,"teacher_disagreement_score":0.9812904,"about_ca_system_score_codex":0.000057293968,"about_ca_system_score_gemma":0.000031569543,"threshold_uncertainty_score":0.4282193},"labels":[],"label_agreement":null},{"id":"W2014564114","doi":"10.1007/pl00011661","title":"An Artificial Network Simulating Cause-to-Effect Reasoning: Cancellation Interactions and Numerical Studies","year":2001,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Probabilistic logic; Artificial neural network; Class (philosophy); Causal reasoning; Task (project management); Artificial intelligence; Variety (cybernetics); Causal model; Machine learning; Stability (learning theory); Mathematics; Cognition","score_opus":0.044046718684036715,"score_gpt":0.3379794475689115,"score_spread":0.2939327288848748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014564114","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12842952,0.0006930605,0.86698604,0.000097812466,0.0008181525,0.00023778818,9.725328e-7,0.00015472334,0.002581965],"genre_scores_gemma":[0.9984454,0.000040584207,0.0010807555,0.000068406305,0.00028304633,0.00002781292,0.0000044851845,0.000003589096,0.000045900873],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991185,0.00010331762,0.0003446271,0.00015150463,0.000103499035,0.00017853692],"domain_scores_gemma":[0.9992664,0.00013735952,0.00010961406,0.0001689242,0.00019484675,0.00012289122],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004401902,0.00011515649,0.00017758315,0.00009486396,0.00031431837,0.00040105972,0.00010027048,0.00004237197,7.826755e-7],"category_scores_gemma":[0.00006762968,0.00009932439,0.000015003804,0.0003255376,0.00001651341,0.0023396085,0.00006542514,0.00009293336,0.000036532543],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000076088894,0.00005929245,0.016153669,0.00030280396,0.00012938709,0.0000043808,0.057638198,0.24061781,0.00037134488,0.14113243,0.0034159909,0.5400986],"study_design_scores_gemma":[0.00009976143,0.00013652355,0.0006929791,0.00013521264,0.000007408742,0.000030632207,0.0003679012,0.9860432,0.000030301391,0.00012133769,0.012200754,0.00013396837],"about_ca_topic_score_codex":0.000038648046,"about_ca_topic_score_gemma":0.000016365102,"teacher_disagreement_score":0.8700159,"about_ca_system_score_codex":0.00004164547,"about_ca_system_score_gemma":0.00002588824,"threshold_uncertainty_score":0.4050331},"labels":[],"label_agreement":null},{"id":"W2016772176","doi":"10.1007/s10115-009-0279-y","title":"A knowledge encapsulation approach to ontology modularization","year":2010,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Ontology; Ontology components; Modular design; Modular programming; Encapsulation (networking); Process ontology; Upper ontology; Modularity (biology); Ontology-based data integration; Web Ontology Language; Formalism (music); Software engineering; Information retrieval; Suggested Upper Merged Ontology; Domain knowledge; Semantic Web; Programming language","score_opus":0.01550687693980566,"score_gpt":0.24548345380183273,"score_spread":0.22997657686202708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016772176","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030611767,0.00024027581,0.79207623,0.00011029384,0.0018668083,0.00043151347,0.0000015895612,0.00023102484,0.17443049],"genre_scores_gemma":[0.9931383,0.000007401266,0.006256634,0.000078867255,0.00013023318,0.000066309265,0.000018591083,0.0000035333717,0.000300113],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907976,0.000053777287,0.00038088573,0.00017795125,0.00011271905,0.0001948779],"domain_scores_gemma":[0.9991045,0.00004810051,0.00010821123,0.0003520748,0.0002813042,0.00010582408],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042967228,0.00012629903,0.00018062674,0.00029651608,0.00015499665,0.0003188763,0.00033824466,0.00014788056,0.0000015168853],"category_scores_gemma":[0.00010944168,0.00010808003,0.000026667138,0.00040780852,0.000027483624,0.0027634464,0.00013883036,0.00011933663,0.00032272725],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037395366,0.000059408256,0.0012941961,0.0001319781,0.000011035024,1.4269649e-7,0.014691347,0.00012057795,0.00079502893,0.9376719,0.0021772753,0.043043356],"study_design_scores_gemma":[0.0005116257,0.00007368734,0.024814744,0.000027204342,0.0000073201136,0.00008510149,0.00048764306,0.70668536,0.0004326471,0.00047842125,0.26607966,0.00031657735],"about_ca_topic_score_codex":0.00002572256,"about_ca_topic_score_gemma":0.00002503685,"teacher_disagreement_score":0.96252656,"about_ca_system_score_codex":0.000020120653,"about_ca_system_score_gemma":0.00006315553,"threshold_uncertainty_score":0.44073758},"labels":[],"label_agreement":null},{"id":"W2017217509","doi":"10.1007/s10115-011-0397-1","title":"Scalable clustering methods for the name disambiguation problem","year":2011,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Illinois at Urbana-Champaign; University of British Columbia; Advanced Digital Sciences Center; Pennsylvania State University; National Science Foundation","keywords":"Cluster analysis; Computer science; Scalability; Artificial intelligence; Natural language processing; Entity linking; Data mining; Database","score_opus":0.22575786155557567,"score_gpt":0.43212848195334813,"score_spread":0.20637062039777246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017217509","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012937761,0.000703313,0.90046537,0.00013182373,0.0007820256,0.00079595624,0.00001585072,0.00003346075,0.09694281],"genre_scores_gemma":[0.9021753,0.0004080944,0.0719536,0.0008394708,0.00045901418,0.0016313,0.00013387321,0.000024234669,0.022375083],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986074,0.0001951491,0.0007045777,0.00012115891,0.00023139805,0.00014029424],"domain_scores_gemma":[0.9983549,0.00066864403,0.00026701315,0.00034204163,0.0003204006,0.000047007983],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008740007,0.00008212918,0.00014915277,0.00013020082,0.00030244596,0.000546005,0.00035219773,0.000043261236,0.000042697156],"category_scores_gemma":[0.00058292464,0.00004699517,0.000042760585,0.00025244823,0.000042807915,0.0032755341,0.00017210074,0.000041907344,0.00037130123],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020388208,0.00001623201,0.00008231983,0.00013298626,0.000021040254,1.5692297e-8,0.015726142,0.000055867484,0.0000044098892,0.097619966,0.02069665,0.865624],"study_design_scores_gemma":[0.00021545541,0.000033797,0.00068207143,0.000021841912,0.000011635265,0.0000018658945,0.005581904,0.12435448,0.000035411224,0.0022609758,0.8667283,0.00007222288],"about_ca_topic_score_codex":0.00008203866,"about_ca_topic_score_gemma":0.000021590738,"teacher_disagreement_score":0.90204597,"about_ca_system_score_codex":0.000019809855,"about_ca_system_score_gemma":0.000019895027,"threshold_uncertainty_score":0.5265139},"labels":[],"label_agreement":null},{"id":"W2017760966","doi":"10.1007/s10115-009-0214-2","title":"Fuzzy clustering-based discretization for gene expression classification","year":2009,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Artificial intelligence; Classifier (UML); Computer science; Data mining; Fuzzy logic; Machine learning; Cluster analysis; Fuzzy classification; Pattern recognition (psychology); Association rule learning; Margin classifier; Support vector machine; Fuzzy rule; Fuzzy set; Feature vector; Fuzzy clustering","score_opus":0.016106872941808476,"score_gpt":0.26921761253277804,"score_spread":0.2531107395909696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017760966","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03385708,0.0014063728,0.9440359,0.00036649703,0.00073062914,0.0012244326,0.000046342997,0.000074494266,0.018258244],"genre_scores_gemma":[0.9974228,0.00008969439,0.0005525279,0.00019309044,0.00023370198,0.00014581953,0.0010111446,0.0000069219664,0.00034429124],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99927497,0.000037931648,0.000315011,0.00016099824,0.000089778885,0.00012130594],"domain_scores_gemma":[0.9993059,0.0000072827806,0.00017554103,0.00022083234,0.0002219958,0.00006842173],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018924892,0.000113477785,0.00009716584,0.000100317666,0.00014339134,0.00009177317,0.000082909566,0.00013686708,0.0000014665247],"category_scores_gemma":[0.000039018953,0.00010023187,0.00003973002,0.00009528693,0.00001727439,0.00006265334,0.000014367481,0.000031111755,0.000010777605],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021407145,0.000059840968,0.00037601823,0.00016555372,0.000008396943,2.483986e-8,0.00041490654,0.0010841079,0.9557944,0.003106024,0.016385684,0.02239097],"study_design_scores_gemma":[0.002053753,0.00046496344,0.0078698555,0.00012538582,0.000018167642,0.000005961577,0.00067634415,0.056234293,0.2038508,0.000075071395,0.72822386,0.0004015495],"about_ca_topic_score_codex":7.357685e-7,"about_ca_topic_score_gemma":0.0000012623683,"teacher_disagreement_score":0.9635657,"about_ca_system_score_codex":0.000019708157,"about_ca_system_score_gemma":0.000053105316,"threshold_uncertainty_score":0.4087337},"labels":[],"label_agreement":null},{"id":"W2019619214","doi":"10.1007/s10115-012-0551-4","title":"A new approach to radial basis function-based polynomial neural networks: analysis and design","year":2012,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Particle swarm optimization; Radial basis function; Polynomial; Computer science; Artificial neural network; Perceptron; Radial basis function network; Algorithm; Mathematical optimization; Artificial intelligence; Mathematics","score_opus":0.020905094039850285,"score_gpt":0.23030253814077742,"score_spread":0.20939744410092714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019619214","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010335994,0.0005971999,0.9947283,0.0001084944,0.00039895927,0.0003896674,0.0000020197367,0.0000785547,0.0026632033],"genre_scores_gemma":[0.99214894,0.000008323321,0.006750954,0.00031221798,0.0005309757,0.00008676308,0.000017117483,0.0000038692997,0.00014083876],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99912727,0.00007295605,0.00030592782,0.00014470705,0.000107127446,0.00024203511],"domain_scores_gemma":[0.9991725,0.000095334384,0.00009891119,0.00024662056,0.00006343109,0.00032318587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035526673,0.00012608059,0.00018731698,0.00026615267,0.00020976414,0.00041195934,0.00017478858,0.00006288793,0.0000032891332],"category_scores_gemma":[0.000008323731,0.0001070532,0.000049797938,0.0011346833,0.000013015728,0.002007751,0.00006514172,0.000069746304,0.00004148424],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010435959,0.00015061049,0.011949059,0.00012079615,0.00038898885,1.4507556e-7,0.005960444,0.28243995,0.00003246237,0.042179674,0.1650411,0.4916324],"study_design_scores_gemma":[0.0002587788,0.000028293778,0.0054217232,0.000004377983,0.000061008013,0.000004127111,0.000037176826,0.9457096,0.000008636898,0.000002322963,0.0483298,0.00013416857],"about_ca_topic_score_codex":0.00006486605,"about_ca_topic_score_gemma":0.0000027498202,"teacher_disagreement_score":0.99111533,"about_ca_system_score_codex":0.00002190785,"about_ca_system_score_gemma":0.000031069896,"threshold_uncertainty_score":0.4365503},"labels":[],"label_agreement":null},{"id":"W2019942346","doi":"10.1007/s10115-012-0485-x","title":"Impact of query intent and search context on clickthrough behavior in sponsored search","year":2012,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Consumer Market Behavior and Pricing","field":"Business, Management and Accounting","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Microsoft Research","keywords":"Computer science; Information retrieval; Web search query; Web query classification; Query expansion; Search engine; Context (archaeology); Rank (graph theory); Ranking (information retrieval); Query optimization; Sargable; Query language; World Wide Web; Mathematics","score_opus":0.04596005764990982,"score_gpt":0.3114538059106155,"score_spread":0.2654937482607057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019942346","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98284566,0.0006012171,0.000023583472,0.000013600291,0.00023687059,0.00042964058,0.000006126631,0.000021073378,0.015822234],"genre_scores_gemma":[0.99964666,0.000049129983,0.0000023163775,0.000030035442,0.00012785208,0.000030018991,0.000023720308,0.0000071583477,0.000083127925],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99906504,0.000037699534,0.00042206273,0.00007838971,0.00015263172,0.00024416018],"domain_scores_gemma":[0.99947256,0.00008146205,0.00010344458,0.00012464257,0.00018988964,0.00002802266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010025817,0.00012562648,0.00022373801,0.00051577645,0.00007149041,0.00015621347,0.000067254085,0.00006845121,0.000039328082],"category_scores_gemma":[0.000044338358,0.00010132765,0.000046923353,0.00029708707,0.000047529724,0.0032924763,0.00009954581,0.00013361206,0.00010463624],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010389099,0.000082251725,0.9381455,0.0003251594,0.000010051405,3.7910536e-7,0.0023246037,0.0000028018374,0.00008239398,0.0021224832,0.00027203144,0.056528438],"study_design_scores_gemma":[0.0006740047,0.000035455665,0.9858197,0.00015584318,0.000020770012,0.0000067974916,0.0024910632,0.0011432541,0.000027611224,9.5173453e-7,0.009492664,0.00013190944],"about_ca_topic_score_codex":0.0021993665,"about_ca_topic_score_gemma":0.000044616987,"teacher_disagreement_score":0.05639653,"about_ca_system_score_codex":0.000044696873,"about_ca_system_score_gemma":0.00002375574,"threshold_uncertainty_score":0.41320217},"labels":[],"label_agreement":null},{"id":"W2025568499","doi":"10.1007/s10115-012-0538-1","title":"Efficient greedy feature selection for unsupervised learning","year":2012,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":95,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Feature selection; Dimensionality reduction; Computer science; Artificial intelligence; Greedy algorithm; Machine learning; Pattern recognition (psychology); Curse of dimensionality; Feature (linguistics); Feature learning; Unsupervised learning; Selection (genetic algorithm); Dimension (graph theory); Data mining; Algorithm; Mathematics","score_opus":0.013086839058054958,"score_gpt":0.237677893728842,"score_spread":0.22459105467078702,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025568499","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09279111,0.0019269248,0.88054115,0.00017634759,0.0022948624,0.0008842178,0.000005366993,0.0003736144,0.021006402],"genre_scores_gemma":[0.99791306,0.000014837752,0.0011487423,0.000052828706,0.00018487798,0.0000859169,0.000025297071,0.000003366648,0.0005710715],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994179,0.000042187356,0.00017830987,0.00007273553,0.00009977439,0.00018910531],"domain_scores_gemma":[0.9995151,0.000045390574,0.00008623075,0.00007556179,0.00019394617,0.000083760926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003802798,0.000082460465,0.000094505944,0.00013076526,0.0002434827,0.00018211488,0.00008628201,0.000080565675,0.0000024891872],"category_scores_gemma":[0.00003358276,0.0000674449,0.0000301008,0.00020291087,0.000006949208,0.0017924153,0.000038315586,0.00007961185,0.00018172091],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011164439,0.00038465625,0.019771926,0.0029064473,0.00012170743,1.581867e-7,0.098248914,0.010797775,0.006056101,0.14867263,0.14574379,0.56718427],"study_design_scores_gemma":[0.00039116523,0.00005058342,0.0009833355,0.00005899123,0.000004224927,0.00001433144,0.00046571955,0.59828293,0.00056266633,0.000005969938,0.3990671,0.00011299059],"about_ca_topic_score_codex":0.0000054598995,"about_ca_topic_score_gemma":4.470164e-7,"teacher_disagreement_score":0.9051219,"about_ca_system_score_codex":0.000025307974,"about_ca_system_score_gemma":0.000018014884,"threshold_uncertainty_score":0.27503228},"labels":[],"label_agreement":null},{"id":"W2026962484","doi":"10.1007/s10115-006-0002-1","title":"A collaborative filtering framework based on fuzzy association rules and multiple-level similarity","year":2006,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":114,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Research Council Canada; Hong Kong Polytechnic University; University of Rochester","keywords":"Collaborative filtering; Recommender system; Computer science; Association rule learning; Similarity (geometry); Popularity; Fuzzy logic; Data mining; Product (mathematics); Information retrieval; Quality (philosophy); The Internet; Machine learning; Artificial intelligence; World Wide Web; Mathematics","score_opus":0.014067022931369966,"score_gpt":0.24111992388868606,"score_spread":0.2270529009573161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026962484","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012357092,0.0005545839,0.9167571,0.00046568402,0.0008995661,0.00082347245,0.000095046504,0.00041094903,0.06763653],"genre_scores_gemma":[0.9915185,0.000021160022,0.008037348,0.00012227873,0.00011000174,0.000053634776,0.000022171218,0.0000044343633,0.00011045618],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898064,0.00011147987,0.00040767103,0.00014635231,0.00019040165,0.00016346936],"domain_scores_gemma":[0.9988968,0.00031164824,0.00027830558,0.00020309855,0.0002585449,0.000051640272],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058948586,0.00014043828,0.00020326032,0.00017691986,0.00020483014,0.0006418438,0.00013818909,0.0001576058,7.623974e-7],"category_scores_gemma":[0.00009788845,0.0001226631,0.000024749557,0.000239998,0.00001166154,0.0018816687,0.000067418245,0.00011736295,0.000022672264],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045770987,0.00025933122,0.07623462,0.0014529581,0.000095485084,0.000003642796,0.014880029,0.00058738416,0.00021719729,0.7797562,0.06515287,0.06131452],"study_design_scores_gemma":[0.001198706,0.00022919766,0.050167963,0.0007479326,0.000010289005,0.000010790675,0.00044453164,0.60165155,0.0011666862,0.0021856886,0.34157243,0.00061424926],"about_ca_topic_score_codex":0.000106056315,"about_ca_topic_score_gemma":0.000015737503,"teacher_disagreement_score":0.97916144,"about_ca_system_score_codex":0.0001100249,"about_ca_system_score_gemma":0.00004066246,"threshold_uncertainty_score":0.6189315},"labels":[],"label_agreement":null},{"id":"W2027417703","doi":"10.1007/s10115-010-0287-y","title":"An information gain-based approach for recommending useful product reviews","year":2010,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Helpfulness; Computer science; Product (mathematics); Recommender system; Ranking (information retrieval); Quality (philosophy); Order (exchange); Task (project management); Information retrieval; Data science; Business; Engineering","score_opus":0.03250743570292643,"score_gpt":0.2886427697291577,"score_spread":0.2561353340262313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2027417703","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016822106,0.00028593984,0.9844014,0.000094966046,0.0010972127,0.0009095948,0.0000052199234,0.000110176195,0.011413278],"genre_scores_gemma":[0.9344091,0.00007158634,0.063233495,0.00047505967,0.0005065442,0.00044736677,0.0007122741,0.000008457447,0.00013612841],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988187,0.00006111907,0.00067879027,0.00013488223,0.00013150818,0.00017498244],"domain_scores_gemma":[0.99881965,0.000043402837,0.0003775078,0.00041004125,0.00025579234,0.00009362265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00168109,0.0001323409,0.00022344876,0.00032364822,0.00024600307,0.00083219114,0.00032181878,0.00006106167,0.000004373206],"category_scores_gemma":[0.00007993868,0.000107508495,0.00006476539,0.00033591615,0.000014101679,0.008852879,0.00003562311,0.00009994797,0.000074954296],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029437027,0.00020293726,0.005209516,0.0024002423,0.00007151206,6.50985e-8,0.022047836,0.0018167581,0.0007490002,0.14682347,0.06088854,0.7597607],"study_design_scores_gemma":[0.000236451,0.000028218961,0.00010535586,0.000021576016,0.0000050560698,0.0000020042723,0.0001468684,0.5339448,0.0002090446,0.00000435077,0.4651918,0.00010444956],"about_ca_topic_score_codex":0.0000052780656,"about_ca_topic_score_gemma":0.000001087375,"teacher_disagreement_score":0.93272686,"about_ca_system_score_codex":0.000018917315,"about_ca_system_score_gemma":0.000044027256,"threshold_uncertainty_score":0.8024838},"labels":[],"label_agreement":null},{"id":"W2028187934","doi":"10.1007/s10115-015-0835-6","title":"Efficient discovery of contrast subspaces for object explanation and characterization","year":2015,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Natural Science Foundation of China; China Postdoctoral Science Foundation; China Computer Federation","keywords":"Linear subspace; Contrast (vision); Pruning; Computer science; Object (grammar); Kernel (algebra); Range (aeronautics); Stability (learning theory); Set (abstract data type); Mathematics; Artificial intelligence; Characterization (materials science); Data mining; Pattern recognition (psychology); Algorithm; Machine learning; Combinatorics","score_opus":0.01964182712551702,"score_gpt":0.24757300972635435,"score_spread":0.22793118260083733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028187934","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042851083,0.0003552876,0.9546719,0.00007399722,0.0002234258,0.00039591154,0.000020091822,0.00005917756,0.001349082],"genre_scores_gemma":[0.99933964,0.00004230444,0.0003710102,0.000013839917,0.000027468597,0.00004524256,0.000045163495,0.0000017758364,0.00011357523],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99945694,0.000026187568,0.00027429513,0.00007178109,0.00010384963,0.000066957466],"domain_scores_gemma":[0.99927044,0.000039285304,0.00019952048,0.000094062896,0.00035835095,0.000038334492],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003978275,0.00006063051,0.00011079367,0.000119810975,0.000047186302,0.00020250567,0.000077792516,0.000039014823,9.144891e-8],"category_scores_gemma":[0.00004813038,0.000049109534,0.0000135193995,0.00014399693,0.000023412196,0.001845156,0.000028318067,0.000018892364,0.0000028179188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008000655,0.00010753276,0.0011784877,0.001162992,0.000035060883,1.2525159e-7,0.025176214,0.000025770205,0.021832125,0.82594347,0.00089067494,0.12356755],"study_design_scores_gemma":[0.0014604797,0.00032554867,0.007882713,0.00017791793,0.000014173566,0.000019976396,0.0015279131,0.8666557,0.049161002,0.00017208904,0.07230338,0.00029910676],"about_ca_topic_score_codex":0.0000047721674,"about_ca_topic_score_gemma":3.803362e-7,"teacher_disagreement_score":0.95648855,"about_ca_system_score_codex":0.000019478337,"about_ca_system_score_gemma":0.000044777044,"threshold_uncertainty_score":0.20026287},"labels":[],"label_agreement":null},{"id":"W2028936054","doi":"10.1007/s101150050009","title":"An Index Structure for Data Mining and Clustering","year":2000,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Fudan University; National Science Foundation","keywords":"Cluster analysis; Euclidean distance; Data mining; Computer science; Metric (unit); Set (abstract data type); Index (typography); Visualization; Mathematics; Data set; Computation; Approximation error; Algorithm; Pattern recognition (psychology); Artificial intelligence","score_opus":0.02296360961186923,"score_gpt":0.2681822105133437,"score_spread":0.24521860090147446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028936054","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02200378,0.00058947847,0.96319354,0.00006924679,0.00064214837,0.0005528611,0.00014345697,0.00015455394,0.012650948],"genre_scores_gemma":[0.9863914,0.00007617244,0.012195712,0.00011980368,0.00021238178,0.000015286332,0.00048106376,0.0000048854913,0.0005032803],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994803,0.000013792662,0.00019436784,0.00013527273,0.0000675955,0.00010867911],"domain_scores_gemma":[0.9994371,0.000017197755,0.000050352395,0.00040995344,0.000034513534,0.000050872444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023139834,0.00007206283,0.0000865042,0.000077658486,0.00012779013,0.0007807057,0.0004406526,0.000032236923,0.000004268629],"category_scores_gemma":[0.0000054583775,0.0000619935,0.000005084823,0.00009635787,0.000011329451,0.010704032,0.00019053234,0.000023174342,0.000007243217],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031497789,0.0000037549403,0.0002432576,0.00015336467,0.000007670604,1.170747e-7,0.0021312903,0.000034503548,0.000003089254,0.00203041,0.0034430118,0.9919464],"study_design_scores_gemma":[0.0002194739,0.000022272174,0.0004670079,0.000019685638,0.0000021363062,0.0000060051116,0.00015954055,0.7034905,0.0000019340403,0.000011846232,0.29553285,0.00006676715],"about_ca_topic_score_codex":0.000010090938,"about_ca_topic_score_gemma":0.000009649344,"teacher_disagreement_score":0.99187964,"about_ca_system_score_codex":0.0000050907856,"about_ca_system_score_gemma":0.000009659576,"threshold_uncertainty_score":0.77601653},"labels":[],"label_agreement":null},{"id":"W2029902517","doi":"10.1007/s10115-012-0511-z","title":"How you move reveals who you are: understanding human behavior by analyzing trajectory data","year":2012,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":80,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Process (computing); Inference; Field (mathematics); Human behavior; Data science; Trajectory; Artificial intelligence; Knowledge extraction; Business process discovery; Human–computer interaction; Work in process; Business process; Engineering","score_opus":0.07373967419833824,"score_gpt":0.28297431501211756,"score_spread":0.20923464081377932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029902517","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012113767,0.004857827,0.956411,0.0002644265,0.002349176,0.0009025019,0.0003208819,0.0003400543,0.022440383],"genre_scores_gemma":[0.9960933,0.000094619776,0.00038620125,0.000054446762,0.0002891152,0.000030161398,0.00052641105,0.000008269855,0.00251751],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988152,0.000063622705,0.00037416007,0.00019684088,0.00023251522,0.00031770812],"domain_scores_gemma":[0.998701,0.000024905263,0.00029319135,0.00078293233,0.000060355105,0.00013764105],"candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0009921666,0.00016089613,0.00021665983,0.00022785181,0.00031017736,0.0014029908,0.0008291722,0.00006423355,0.0000024260637],"category_scores_gemma":[0.000022485718,0.00014436194,0.000027283537,0.0003307691,0.00003671293,0.023225388,0.0005329265,0.00009855857,0.00005109182],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000057465745,0.00027502645,0.046958663,0.0013344953,0.00019805203,0.0000034699008,0.020332932,0.0000062784065,0.00045212248,0.27204362,0.5895072,0.06888239],"study_design_scores_gemma":[0.0011173284,0.00006573282,0.0081267925,0.00031744767,0.00009809782,0.000020274132,0.012305099,0.046621628,0.00010924388,0.00006744514,0.9302734,0.0008775232],"about_ca_topic_score_codex":0.000016806627,"about_ca_topic_score_gemma":0.000001700167,"teacher_disagreement_score":0.9839795,"about_ca_system_score_codex":0.00009220568,"about_ca_system_score_gemma":0.000011103225,"threshold_uncertainty_score":0.99963367},"labels":[],"label_agreement":null},{"id":"W2031366103","doi":"10.1007/s10115-002-8192-7","title":"Knowledge Discovery Through Self-Organizing Maps: Data Visualization and Query Processing","year":2002,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Knowledge extraction; Visualization; Data mining; Set (abstract data type); Information retrieval; Heuristic; Premise; Data visualization; Information visualization; Data science; Artificial intelligence","score_opus":0.047145981158898155,"score_gpt":0.3028134019006688,"score_spread":0.2556674207417706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2031366103","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009806429,0.007853058,0.95494956,0.00009662916,0.00061650795,0.00032996078,0.000055750963,0.0004517989,0.03466608],"genre_scores_gemma":[0.993314,0.0021663478,0.0018975823,0.00033699724,0.0003044466,0.000014609232,0.0005873268,0.000020734316,0.0013579236],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875003,0.0000783987,0.0005331711,0.0002655942,0.00017850792,0.00019429676],"domain_scores_gemma":[0.9989105,0.000045531655,0.00023046882,0.0004997357,0.00023219449,0.00008156337],"candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.00040021748,0.0001681894,0.00020025506,0.0001784791,0.0003156508,0.0019212022,0.00048373186,0.000083730745,0.0000042089414],"category_scores_gemma":[0.00006984765,0.00015015312,0.000013800777,0.0006752092,0.00003586432,0.025069382,0.0005709207,0.000072108625,0.00015760405],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028091067,0.00024994047,0.0013528952,0.0025948125,0.00006417793,0.000001599066,0.06997391,0.00001712391,0.000035418798,0.7880519,0.08302036,0.054635078],"study_design_scores_gemma":[0.00025006806,0.000017275306,0.00006408594,0.00013981576,0.000010912067,0.000024719178,0.00064502965,0.5940569,0.000025767527,0.000035748584,0.40456277,0.00016692458],"about_ca_topic_score_codex":0.000010475106,"about_ca_topic_score_gemma":0.0000042410993,"teacher_disagreement_score":0.9923334,"about_ca_system_score_codex":0.000036642796,"about_ca_system_score_gemma":0.000054003336,"threshold_uncertainty_score":0.9991149},"labels":[],"label_agreement":null},{"id":"W2031582216","doi":"10.1007/s10115-006-0062-2","title":"Toward understanding the importance of gesture in distributed scientific collaboration","year":2007,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"University of Victoria","keywords":"Artifact (error); Computer science; Gesture; Coding (social sciences); Set (abstract data type); Data science; Human–computer interaction; Software; Artificial intelligence; Sociology","score_opus":0.03044051358999905,"score_gpt":0.25883442101330445,"score_spread":0.2283939074233054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2031582216","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08371049,0.0018923777,0.89225906,0.00026824686,0.0026232842,0.0007461958,0.000027251135,0.00007332478,0.01839976],"genre_scores_gemma":[0.9997965,0.000006769173,0.00006862875,0.000017643384,0.000042023425,0.000008076081,0.000030038345,0.0000014849692,0.000028798197],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99899346,0.000043612712,0.00051200046,0.00009682642,0.00019718967,0.00015689396],"domain_scores_gemma":[0.9991938,0.000089095105,0.00023133465,0.000228909,0.00021121444,0.000045655866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017575322,0.00007298556,0.0001264577,0.00019973547,0.0001279914,0.00035996208,0.00023073035,0.00006264416,5.3165866e-7],"category_scores_gemma":[0.000073976444,0.000050993956,0.000017792367,0.0011755668,0.000055147964,0.002093159,0.000052661228,0.00006062662,0.000014492519],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026454287,0.000036369107,0.03813289,0.00041047594,0.000015304697,0.0000024058677,0.049775578,0.00020348096,0.0002967464,0.90249,0.006569366,0.0020409257],"study_design_scores_gemma":[0.0063945563,0.00045288494,0.21485491,0.0012965988,0.000029537037,0.00022001565,0.15634984,0.23601162,0.005029762,0.008366068,0.36948285,0.00151137],"about_ca_topic_score_codex":0.000018078961,"about_ca_topic_score_gemma":0.00015016027,"teacher_disagreement_score":0.9160861,"about_ca_system_score_codex":0.00012120443,"about_ca_system_score_gemma":0.00010315569,"threshold_uncertainty_score":0.34711227},"labels":[],"label_agreement":null},{"id":"W2032469362","doi":"10.1007/s10115-006-0032-8","title":"CanTree: a canonical-order tree for incremental frequent-pattern mining","year":2006,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":140,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Data mining; Tree (set theory); GSP Algorithm; Database transaction; Tree structure; A priori and a posteriori; Association rule learning; Apriori algorithm; Database; Mathematics; Algorithm; Binary tree","score_opus":0.01329467542214002,"score_gpt":0.24506175368626992,"score_spread":0.2317670782641299,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032469362","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01007841,0.00050167483,0.9589057,0.00025646706,0.00046091652,0.0005374212,0.0001284529,0.00013962634,0.028991306],"genre_scores_gemma":[0.9777804,0.000016692109,0.0198578,0.00019148548,0.0003567098,0.00045784653,0.0003961672,0.000009487901,0.00093340187],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99917144,0.000015405747,0.00038460028,0.0001368479,0.000108579,0.00018310377],"domain_scores_gemma":[0.9993578,0.00005801074,0.00013030306,0.00023777153,0.0001589832,0.00005708275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022892568,0.00010171769,0.00012683554,0.00009636548,0.00019205954,0.00036397306,0.0002646018,0.00004684648,0.0000021242558],"category_scores_gemma":[0.000013193586,0.0000911038,0.00002537921,0.00021305935,0.000020645917,0.001855865,0.00009218301,0.000037528906,0.000054959623],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000042444613,0.00010159576,0.0027019286,0.00028258844,0.000039664934,6.9701804e-7,0.0038941521,0.000060196096,0.00026068193,0.1270139,0.09229397,0.77334636],"study_design_scores_gemma":[0.00072689954,0.00005013138,0.0019741175,0.000056023844,0.000007778801,0.000021734184,0.00034840626,0.44389325,0.00014369606,0.000040107985,0.55253977,0.00019807507],"about_ca_topic_score_codex":0.0008626219,"about_ca_topic_score_gemma":0.00023280122,"teacher_disagreement_score":0.967702,"about_ca_system_score_codex":0.000044093555,"about_ca_system_score_gemma":0.00008177441,"threshold_uncertainty_score":0.3715105},"labels":[],"label_agreement":null},{"id":"W2034485749","doi":"10.1007/s10115-008-0190-y","title":"Effectiveness of NAQ-tree as index structure for similarity search in high-dimensional metric space","year":2009,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Nearest neighbor search; Metric space; Tree (set theory); Tree traversal; Mathematics; Computer science; Cover tree; Data mining; Metric (unit); Disjoint sets; Algorithm; Pattern recognition (psychology); Artificial intelligence; Combinatorics; Cluster analysis; Discrete mathematics","score_opus":0.009903275750799953,"score_gpt":0.28998444828426806,"score_spread":0.2800811725334681,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034485749","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.095590174,0.00093800446,0.9006771,0.00005010457,0.00020159634,0.0009534939,0.000017088334,0.0000826312,0.0014897925],"genre_scores_gemma":[0.9971531,0.00002033735,0.002725569,0.000026483825,0.00002115915,0.000013248227,0.000013827445,0.0000025052382,0.00002375717],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990692,0.00010039611,0.00033018822,0.00013606776,0.00020126715,0.00016285697],"domain_scores_gemma":[0.99897647,0.00025043244,0.00011608866,0.00020192571,0.00040248357,0.000052603933],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007234361,0.00011318854,0.00025175422,0.00046202893,0.00006113452,0.00007719929,0.00021799756,0.00010498525,7.546592e-7],"category_scores_gemma":[0.00014316617,0.00009503032,0.000033550594,0.0008389863,0.00002281652,0.002571238,0.00007239063,0.00011581286,0.0000036978074],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050945464,0.00022822162,0.0063636242,0.0036541405,0.000054579672,0.000004044006,0.003579268,0.0018287699,0.007844221,0.5575461,0.0010636598,0.41732392],"study_design_scores_gemma":[0.0067245103,0.0027421492,0.27840707,0.0015294689,0.000021141494,0.00009373822,0.00026874884,0.2778988,0.38404694,0.03086307,0.016310856,0.0010935253],"about_ca_topic_score_codex":0.000037621896,"about_ca_topic_score_gemma":0.0000020764785,"teacher_disagreement_score":0.9015629,"about_ca_system_score_codex":0.00006019512,"about_ca_system_score_gemma":0.00007797482,"threshold_uncertainty_score":0.3875224},"labels":[],"label_agreement":null},{"id":"W2038021410","doi":"10.1007/s10115-010-0290-3","title":"Study of select items in different data sources by grouping","year":2010,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Measure (data warehouse); Computer science; Set (abstract data type); Data mining; Database; Association rule learning; Information retrieval","score_opus":0.022332729292336054,"score_gpt":0.2703498052012024,"score_spread":0.24801707590886635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038021410","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96143913,0.00021160798,0.03539631,0.00003281262,0.00035196636,0.00041525616,0.000049951268,0.000053279146,0.0020496813],"genre_scores_gemma":[0.9995604,0.00001029188,0.00023010821,0.000006649251,0.000040237373,0.000034802626,0.00008261005,0.0000019768001,0.000032895947],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992467,0.000027405456,0.0003816398,0.00013277268,0.00011304501,0.00009844799],"domain_scores_gemma":[0.9991495,0.000054517714,0.00013869895,0.00055956695,0.00005851563,0.000039174654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037795838,0.000075559125,0.00014070523,0.0001187594,0.000068147725,0.00020636177,0.00064527686,0.000033803844,6.809406e-7],"category_scores_gemma":[0.000022358798,0.00005884976,0.000006439524,0.00026684185,0.000013814559,0.002433174,0.00031586457,0.00009941851,0.000013519682],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010132869,0.0023859574,0.11085185,0.00073584664,0.00012181887,0.0000011064819,0.15874697,0.00004520517,0.003536385,0.050632186,0.04361092,0.62932163],"study_design_scores_gemma":[0.0013168177,0.00021275728,0.03455165,0.00009345416,0.00000954542,0.0000192043,0.0060026455,0.7510009,0.0003228385,0.00002037471,0.20612545,0.00032439484],"about_ca_topic_score_codex":0.0001480675,"about_ca_topic_score_gemma":0.00007214032,"teacher_disagreement_score":0.75095564,"about_ca_system_score_codex":0.000005898893,"about_ca_system_score_gemma":0.000015730686,"threshold_uncertainty_score":0.23998235},"labels":[],"label_agreement":null},{"id":"W2043301550","doi":"10.1007/s10115-003-0101-1","title":"Data Mining: How Research Meets Practical Development?","year":2003,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Data science; Computer science; Data mining; Panel discussion; Development (topology); Business","score_opus":0.19245540659425892,"score_gpt":0.3901175826814103,"score_spread":0.19766217608715136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043301550","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018996216,0.001131186,0.807824,0.0022670538,0.0008733597,0.0006441115,0.000055397464,0.00022895979,0.1850763],"genre_scores_gemma":[0.5824712,0.00016189329,0.41234243,0.00013039362,0.00021147744,0.00025213198,0.0004768486,0.0000146865605,0.0039389497],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99890655,0.000122013094,0.00026542044,0.00020397089,0.00027871775,0.00022334566],"domain_scores_gemma":[0.9985375,0.00018879533,0.00008404316,0.0007758656,0.00029703008,0.00011676453],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002260996,0.00007971915,0.00010130421,0.00016561859,0.00035500113,0.0010227808,0.0005974293,0.00005617317,0.0000022414406],"category_scores_gemma":[0.00038082208,0.000068751244,0.0000066747966,0.0004813038,0.000038485745,0.006693568,0.00041588282,0.000115737486,0.00034394357],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011225246,0.00006175315,0.00012174135,0.00011008176,0.000022343178,0.0000012107516,0.0070681097,7.3464383e-7,0.000015057299,0.54492664,0.26123646,0.18643473],"study_design_scores_gemma":[0.00012879937,0.000013193598,0.00013225923,0.0000273623,0.0000012396031,0.000045626042,0.0009234733,0.051142298,0.000063049985,0.000014535045,0.94741935,0.00008880736],"about_ca_topic_score_codex":0.000003171998,"about_ca_topic_score_gemma":0.0000026048513,"teacher_disagreement_score":0.6861829,"about_ca_system_score_codex":0.000027136532,"about_ca_system_score_gemma":0.00029712686,"threshold_uncertainty_score":0.98626983},"labels":[],"label_agreement":null},{"id":"W2044979776","doi":"10.1007/s10115-012-0515-8","title":"Anonymizing bag-valued sparse data by semantic similarity-based clustering","year":2012,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Semantic similarity; Cluster analysis; Information retrieval; Vocabulary; Data publishing; WordNet; Similarity (geometry); Differential privacy; Data mining; Artificial intelligence","score_opus":0.05574438451177503,"score_gpt":0.28777105456625324,"score_spread":0.2320266700544782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044979776","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002658932,0.0023750148,0.9843837,0.0010527098,0.0014309909,0.000386317,0.000104067156,0.0007933152,0.0068149436],"genre_scores_gemma":[0.9504251,0.00006534623,0.048695486,0.00023769987,0.00012336038,0.000030805946,0.00036937697,0.000011240643,0.00004157914],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985305,0.00008153171,0.00050340005,0.0002298398,0.00024837488,0.00040633103],"domain_scores_gemma":[0.9940308,0.00011081902,0.00021086681,0.00543428,0.00009564028,0.00011762968],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0014849902,0.00017596783,0.0002195594,0.0002128116,0.00021237663,0.0005310396,0.00908161,0.00014067885,0.0000037147786],"category_scores_gemma":[0.0021990992,0.00016321217,0.000020466627,0.00039458205,0.00004902357,0.012536382,0.027561434,0.00018006378,0.0002082435],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008851103,0.00010195766,0.003387315,0.0011655504,0.0000484839,0.0000011439193,0.0013412491,0.000071761344,0.00032799676,0.0048512067,0.93722993,0.051464543],"study_design_scores_gemma":[0.00029820565,0.000014786207,0.00015507035,0.000106772204,0.0000061246897,0.000014678931,0.000083218045,0.78747576,0.00038841262,0.000060627794,0.21121229,0.00018402933],"about_ca_topic_score_codex":0.000041239688,"about_ca_topic_score_gemma":0.000003973359,"teacher_disagreement_score":0.9477662,"about_ca_system_score_codex":0.00006290734,"about_ca_system_score_gemma":0.000052564086,"threshold_uncertainty_score":0.9962797},"labels":[],"label_agreement":null},{"id":"W2046943275","doi":"10.1007/s10115-012-0524-7","title":"Common understanding in a multi-agent system using ontology-guided learning","year":2012,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Western University","funders":"","keywords":"Computer science; Ontology; Flexibility (engineering); Set (abstract data type); Process (computing); Multi-agent system; Intelligent agent; Common knowledge (logic); Autonomous agent; Artificial intelligence; Human–computer interaction; Description logic; Epistemic modal logic","score_opus":0.13382357076986137,"score_gpt":0.31820717832592593,"score_spread":0.18438360755606456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046943275","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16612184,0.0028350286,0.8119948,0.000027616905,0.0018983112,0.00036641746,6.530778e-7,0.00027081982,0.016484542],"genre_scores_gemma":[0.9987265,0.000015574244,0.0011460774,0.000018114219,0.000041417406,0.000011790588,0.0000022112536,0.0000031150644,0.000035186524],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988677,0.00015414375,0.0004767586,0.000092095506,0.00011036265,0.0002989394],"domain_scores_gemma":[0.9994506,0.00008111458,0.00017933479,0.00016407539,0.00004912537,0.00007575302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008514908,0.00011566692,0.00023741137,0.00026994673,0.00017660874,0.00019299956,0.0001826585,0.000095017785,5.0874974e-7],"category_scores_gemma":[0.000037682563,0.0000997692,0.00002656514,0.00024732182,0.000023927269,0.0032201875,0.00012468205,0.000116232746,0.0000586981],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008500866,0.00007463553,0.3400375,0.0012928497,0.000041361047,0.0000046534524,0.070283905,0.0016221742,0.00014484332,0.5821139,0.00036736482,0.004008295],"study_design_scores_gemma":[0.0007740465,0.000026636053,0.011665595,0.00033735848,0.000007245222,0.0002147644,0.018902352,0.9605907,0.000052630465,0.000012212163,0.0071961014,0.00022031873],"about_ca_topic_score_codex":0.00025183448,"about_ca_topic_score_gemma":0.000043299096,"teacher_disagreement_score":0.9589686,"about_ca_system_score_codex":0.00032520236,"about_ca_system_score_gemma":0.000032526157,"threshold_uncertainty_score":0.40684697},"labels":[],"label_agreement":null},{"id":"W2049619678","doi":"10.1007/s10115-012-0486-9","title":"Skyline distance: a measure of multidimensional competence","year":2012,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Skyline; Computer science; Scalability; Measure (data warehouse); Data mining; sort; Point (geometry); Theoretical computer science; Information retrieval; Database; Mathematics","score_opus":0.01418241925939989,"score_gpt":0.23315883989896102,"score_spread":0.21897642063956113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049619678","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033405975,0.0033215852,0.9514333,0.000060638136,0.0014322628,0.00028721656,0.000025708483,0.00008880316,0.040009916],"genre_scores_gemma":[0.99576306,0.000036055393,0.0038386858,0.000030718566,0.000079681464,0.000010174391,0.000027456255,0.0000016335963,0.00021253161],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99930674,0.000027014634,0.0002894177,0.000059171958,0.00018225613,0.00013541074],"domain_scores_gemma":[0.99942154,0.000028643492,0.00013028945,0.00020192518,0.0001519318,0.000065660875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046032542,0.00007165393,0.00011751843,0.00008997624,0.00006108734,0.00006340846,0.00019347519,0.000025176354,0.0000024516528],"category_scores_gemma":[0.00001853964,0.00005688281,0.000019303772,0.00020369703,0.000024199218,0.0057027387,0.00014799651,0.0000378466,0.00010923727],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000050340564,0.00007576064,0.0036077525,0.00034536762,0.000024233916,1.7396641e-7,0.004354739,0.00001837429,0.00007525786,0.9212184,0.0065816618,0.063693255],"study_design_scores_gemma":[0.0005551383,0.000034496064,0.008187594,0.00013751096,0.0000067717956,0.000010746594,0.00035390485,0.18046011,0.0001961503,0.000022006117,0.8098569,0.00017869078],"about_ca_topic_score_codex":0.0000066509297,"about_ca_topic_score_gemma":5.210117e-7,"teacher_disagreement_score":0.99242246,"about_ca_system_score_codex":0.000010842768,"about_ca_system_score_gemma":0.000014995844,"threshold_uncertainty_score":0.41343477},"labels":[],"label_agreement":null},{"id":"W2050175694","doi":"10.1007/s10115-012-0527-4","title":"A new approach for maximizing bichromatic reverse nearest neighbor search","year":2012,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Natural Science Foundation of China; National Science Foundation","keywords":"k-nearest neighbors algorithm; Best bin first; Nearest neighbor search; Large margin nearest neighbor; Nearest-neighbor chain algorithm; Computer science; Nearest neighbor graph; Metric space; Metric (unit); Fixed-radius near neighbors; Algorithm; Space (punctuation); Mathematics; Data mining; Artificial intelligence; Discrete mathematics; Cluster analysis","score_opus":0.036402218891202674,"score_gpt":0.26517865462145235,"score_spread":0.22877643573024967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050175694","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014003807,0.00047199382,0.9495576,0.00007064566,0.0005907592,0.0005529718,0.0000066865114,0.00009239161,0.04851689],"genre_scores_gemma":[0.5731216,0.00016845971,0.4081356,0.0005066012,0.0021521868,0.000368729,0.0004834361,0.000031525928,0.015031831],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99916464,0.0000319903,0.00028603707,0.00010098317,0.00014784659,0.00026852422],"domain_scores_gemma":[0.99935913,0.000043880344,0.00008331051,0.0002934078,0.00007390276,0.00014634628],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007358426,0.000099764984,0.00013574003,0.00016668257,0.00014781459,0.00056286325,0.0003369793,0.00004125321,0.000005026831],"category_scores_gemma":[0.000024852758,0.000083644,0.00003053297,0.0002835173,0.000011017908,0.008684679,0.00019982267,0.000049562357,0.0003199797],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000086181535,0.00007138297,0.0005260217,0.0019076054,0.00006284449,2.1219203e-7,0.015743406,0.00007254089,0.000016200023,0.4417636,0.19869615,0.34113142],"study_design_scores_gemma":[0.00048854563,0.000023412547,0.00033161108,0.000040334304,0.000007831654,0.000009412418,0.0006599497,0.44692242,0.000018751047,0.000015382082,0.5513446,0.00013777323],"about_ca_topic_score_codex":0.00003185462,"about_ca_topic_score_gemma":2.757121e-7,"teacher_disagreement_score":0.5729816,"about_ca_system_score_codex":0.000027137017,"about_ca_system_score_gemma":0.000039687537,"threshold_uncertainty_score":0.6296183},"labels":[],"label_agreement":null},{"id":"W2054521721","doi":"10.1007/s10115-009-0245-8","title":"Mining incomplete survey data through classification","year":2009,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint Mary's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Missing data; Data mining; Computer science; Classifier (UML); Complete information; Data set; Artificial intelligence; Machine learning; Mathematics","score_opus":0.11564483165384673,"score_gpt":0.3234492842129648,"score_spread":0.20780445255911809,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054521721","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019228609,0.00051022734,0.95118356,0.0003523874,0.00039017378,0.00025843864,0.00014575032,0.0001982892,0.045038328],"genre_scores_gemma":[0.9741927,0.000110731606,0.023534935,0.0002604011,0.0001259238,0.000021672005,0.0015899357,0.000003533229,0.00016016008],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990896,0.000062942854,0.00038671313,0.00019397514,0.00013050946,0.00013628909],"domain_scores_gemma":[0.99862367,0.00008506371,0.00016546506,0.000908927,0.00016256663,0.000054317617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076240284,0.000092617076,0.00012388726,0.00007432222,0.00019991024,0.0005544264,0.000829316,0.000047179223,0.0000010063633],"category_scores_gemma":[0.00006347284,0.00008305009,0.000009601961,0.0003940124,0.000018485616,0.007777039,0.0002056111,0.00005653798,0.00018531192],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028034056,0.000053656466,0.0007877338,0.00004946192,0.000014331264,2.0131475e-7,0.00693646,0.000009888283,0.00004569829,0.25161406,0.072211854,0.66827387],"study_design_scores_gemma":[0.00015019129,0.000026955582,0.034887843,0.000027303073,0.0000022641977,0.000011116078,0.00021622956,0.54174864,0.0000069789107,0.00006968384,0.4227348,0.000118013704],"about_ca_topic_score_codex":0.00006196569,"about_ca_topic_score_gemma":0.000006809192,"teacher_disagreement_score":0.97226983,"about_ca_system_score_codex":0.000018022833,"about_ca_system_score_gemma":0.00004826876,"threshold_uncertainty_score":0.56381655},"labels":[],"label_agreement":null},{"id":"W2054765427","doi":"10.1007/s10115-011-0467-4","title":"A countably infinite mixture model for clustering and feature selection","year":2011,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Concordia University","funders":"","keywords":"Mixture model; Cluster analysis; Model selection; Computer science; Artificial intelligence; Feature selection; Dirichlet process; Dirichlet distribution; Machine learning; Bayesian inference; Inference; Pattern recognition (psychology); Data mining; Mathematics; Bayesian probability","score_opus":0.028644784435366628,"score_gpt":0.25466713485173914,"score_spread":0.2260223504163725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054765427","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00044848878,0.0006697313,0.983844,0.00003446662,0.0002879308,0.0003435014,0.000007453755,0.0000810636,0.014283411],"genre_scores_gemma":[0.5823224,0.00015790867,0.4155915,0.00039338527,0.00014919639,0.00015249958,0.000012269414,0.00001141436,0.0012093772],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99939626,0.00003087386,0.00021854686,0.00012970761,0.000070458984,0.0001541486],"domain_scores_gemma":[0.99945915,0.000027392574,0.00010652881,0.0001321803,0.00019805052,0.000076724165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040311506,0.00011881401,0.0001515694,0.000126446,0.00015826603,0.00022365493,0.0001213337,0.00012883489,4.2281198e-7],"category_scores_gemma":[0.00001484988,0.00009857066,0.000024656249,0.00014444429,0.000014560534,0.0027501464,0.00006778618,0.00008676936,0.0000045450215],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006700397,0.000036670037,0.00028484064,0.0014938479,0.000058549544,3.388237e-7,0.09350681,0.0002370422,0.00031088587,0.6711775,0.013733292,0.2190932],"study_design_scores_gemma":[0.00033839996,0.000044498658,0.0001425324,0.00005167727,0.0000069530884,0.000042600557,0.000057978647,0.9687272,0.00006251068,0.0011458519,0.029247742,0.0001320728],"about_ca_topic_score_codex":0.000008812988,"about_ca_topic_score_gemma":0.0000074603367,"teacher_disagreement_score":0.9684901,"about_ca_system_score_codex":0.000018271903,"about_ca_system_score_gemma":0.00004115783,"threshold_uncertainty_score":0.40195948},"labels":[],"label_agreement":null},{"id":"W2057822545","doi":"10.1007/s10115-014-0736-0","title":"Finding top- $$k\\, r$$ k r -cliques for keyword search from graphs in polynomial delay","year":2014,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Clique; Substructure; Keyword search; Graph; Set (abstract data type); Theoretical computer science; Context (archaeology); Combinatorics; Mathematics; Information retrieval","score_opus":0.017632627432734232,"score_gpt":0.2689965599923172,"score_spread":0.25136393255958295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057822545","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07873421,0.00056529924,0.9102139,0.00007665797,0.0011316168,0.00044263247,0.000038238213,0.000098890916,0.008698554],"genre_scores_gemma":[0.9947914,0.000039691862,0.0046922117,0.00006679822,0.0001866948,0.00005084909,0.00007793503,0.000003876956,0.000090575646],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991431,0.000064109496,0.00035753785,0.00013943893,0.00011463309,0.00018114514],"domain_scores_gemma":[0.9993484,0.00016856115,0.000082736544,0.00023352835,0.000097800046,0.000068951515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005512421,0.00009459407,0.00015912765,0.00021789972,0.000127939,0.00036094766,0.00029381274,0.00007724724,0.0000020487075],"category_scores_gemma":[0.00003234287,0.000078893274,0.000028904444,0.0001793207,0.000014344385,0.0030581318,0.0001605556,0.0000765844,0.000045163306],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006570692,0.000074465,0.008459819,0.00037697915,0.000029784856,8.488189e-7,0.024069915,0.0002474949,0.0002496733,0.19411725,0.031102,0.74120605],"study_design_scores_gemma":[0.0007350158,0.00007483082,0.0029860216,0.00012948434,0.0000018134483,0.0000034976604,0.0001686699,0.6777065,0.00029908563,0.00030142497,0.31743604,0.00015763807],"about_ca_topic_score_codex":0.00023915432,"about_ca_topic_score_gemma":0.000015377234,"teacher_disagreement_score":0.91605717,"about_ca_system_score_codex":0.000026598213,"about_ca_system_score_gemma":0.00003431658,"threshold_uncertainty_score":0.34806266},"labels":[],"label_agreement":null},{"id":"W2064848265","doi":"10.1007/s10115-011-0405-5","title":"Effectiveness of NAQ-tree in handling reverse nearest-neighbor queries in high-dimensional metric space","year":2011,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Pruning; Metric (unit); k-nearest neighbors algorithm; Nearest neighbor search; Euclidean distance; Tree (set theory); Data mining; Metric space; Artificial intelligence; Mathematics","score_opus":0.014143569775840109,"score_gpt":0.2202502816969014,"score_spread":0.20610671192106128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064848265","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75671375,0.0024771844,0.17911401,0.00005267061,0.0031893332,0.0019309728,0.000024513794,0.00017903095,0.056318555],"genre_scores_gemma":[0.99834776,0.000031166226,0.0015010253,0.000006313941,0.0000133340045,0.000024237446,0.000013402227,0.00000243026,0.000060316717],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99912643,0.00011739137,0.00036106416,0.00011834705,0.0001408769,0.0001358586],"domain_scores_gemma":[0.9994262,0.00010961093,0.0001310386,0.00019998367,0.00009926773,0.00003389507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010131375,0.00009458957,0.00020647769,0.00065735437,0.000034889268,0.00007882955,0.00022784685,0.00004525179,0.0000029182177],"category_scores_gemma":[0.000064281165,0.000082345745,0.000018478884,0.0008940004,0.000026519921,0.004273344,0.00019432907,0.0000646139,0.000054452106],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022065676,0.00040649535,0.09121481,0.005924434,0.00009145197,0.00002672451,0.025690317,0.00081842236,0.00020981349,0.75030965,0.0014110168,0.12367622],"study_design_scores_gemma":[0.005377288,0.0004050879,0.6561119,0.0024969545,0.000018983787,0.000017538834,0.0014005404,0.31118113,0.0037647055,0.00081951707,0.017634872,0.00077150617],"about_ca_topic_score_codex":0.0006182879,"about_ca_topic_score_gemma":0.00004867017,"teacher_disagreement_score":0.74949014,"about_ca_system_score_codex":0.000034886947,"about_ca_system_score_gemma":0.00003444059,"threshold_uncertainty_score":0.3357962},"labels":[],"label_agreement":null},{"id":"W2073825221","doi":"10.1007/s10115-007-0090-6","title":"Robust projected clustering","year":2007,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":70,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of Alberta","funders":"Yale University","keywords":"Cluster analysis; Categorical variable; Disjoint sets; Linear subspace; Outlier; Data mining; CURE data clustering algorithm; Cluster (spacecraft); Subspace topology; Set (abstract data type); Computer science; Data set; Correlation clustering; Clustering high-dimensional data; Single-linkage clustering; Algorithm; Pattern recognition (psychology); Mathematics; Artificial intelligence; Machine learning; Combinatorics","score_opus":0.1299341584742713,"score_gpt":0.38931893886732927,"score_spread":0.25938478039305796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073825221","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017898541,0.00011920617,0.90614986,0.0000060401667,0.0002800014,0.00028300646,0.0000070985443,0.0000863159,0.091278635],"genre_scores_gemma":[0.6925923,0.00004283055,0.30514243,0.00006464681,0.00029554806,0.000050254403,0.000020452893,0.000021480942,0.0017700237],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991851,0.000031123996,0.0004419923,0.00006978751,0.000097005024,0.00017502253],"domain_scores_gemma":[0.99921465,0.00031825883,0.000114082315,0.00010984081,0.0001642522,0.000078928446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082551327,0.000091396134,0.00016044009,0.000100586614,0.0000920442,0.000055189783,0.000046140143,0.000064309315,0.0000052954433],"category_scores_gemma":[0.00032000107,0.000073473966,0.000017905273,0.00012155451,0.000021365748,0.0008334933,0.00003622701,0.00007563677,0.000033539938],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004090311,0.00003689801,0.00007536812,0.0012330383,0.000023322593,0.0000015844721,0.00665426,0.00009137197,0.00009727305,0.84500265,0.0023382895,0.14440507],"study_design_scores_gemma":[0.002441571,0.00025619197,0.001112861,0.00067873346,0.00006310017,0.000175044,0.006964,0.35182533,0.00054841157,0.02908387,0.60590327,0.00094762957],"about_ca_topic_score_codex":0.00000588111,"about_ca_topic_score_gemma":0.000008509334,"teacher_disagreement_score":0.81591874,"about_ca_system_score_codex":0.00003000185,"about_ca_system_score_gemma":0.000014908257,"threshold_uncertainty_score":0.29961812},"labels":[],"label_agreement":null},{"id":"W2077179394","doi":"10.1007/s10115-006-0035-5","title":"Handicapping attacker's confidence: an alternative to k-anonymization","year":2006,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":120,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Property (philosophy); Computer science; Data mining; Limit (mathematics); Domain (mathematical analysis); Set (abstract data type); Monotonic function; Limiting; Dual (grammatical number); Data set; Information sensitivity; Transformation (genetics); Information retrieval; Artificial intelligence; Computer security; Mathematics","score_opus":0.021496679816238064,"score_gpt":0.27713976483394576,"score_spread":0.2556430850177077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077179394","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00928923,0.00026824547,0.9686565,0.0009735858,0.0006726133,0.0003710242,0.000014118422,0.0005120419,0.019242665],"genre_scores_gemma":[0.98541474,0.000027956026,0.014047409,0.00012724423,0.00013752888,0.000058789476,0.00007041431,0.0000049516552,0.00011096079],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894077,0.00005584085,0.00040382502,0.00019557927,0.0002091459,0.00019484242],"domain_scores_gemma":[0.9978014,0.000048420563,0.0001664053,0.0016651734,0.00024780788,0.000070766575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045781804,0.00011828647,0.00014306782,0.00030845276,0.00017128317,0.0006589549,0.0038917582,0.000084006766,0.0000030437252],"category_scores_gemma":[0.00094621,0.000109407156,0.000014928634,0.0004719485,0.00003500073,0.007391031,0.005672321,0.00008162848,0.00027278002],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001058592,0.00007158263,0.0022370117,0.00023846596,0.000030531817,0.0000029573546,0.0047331727,0.0009992184,0.00043884956,0.56983757,0.37188497,0.049515087],"study_design_scores_gemma":[0.0004035831,0.00010282363,0.001976676,0.00015220758,0.000003681787,0.000021988872,0.00032332636,0.7930243,0.0014422958,0.009981899,0.1922595,0.00030772018],"about_ca_topic_score_codex":0.00015686508,"about_ca_topic_score_gemma":0.000014079683,"teacher_disagreement_score":0.97612554,"about_ca_system_score_codex":0.000064278254,"about_ca_system_score_gemma":0.00004215418,"threshold_uncertainty_score":0.723192},"labels":[],"label_agreement":null},{"id":"W2077378918","doi":"10.1007/s10115-009-0252-9","title":"A binary decision diagram based approach for mining frequent subsequences","year":2009,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Bottleneck; Data mining; Prefix; Sequence (biology); Binary decision diagram; Representation (politics); Theoretical computer science","score_opus":0.022212111231806726,"score_gpt":0.2688086613249732,"score_spread":0.2465965500931665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077378918","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023427026,0.0005378344,0.98941094,0.00010422267,0.00018089531,0.0004238867,0.00002169666,0.00011503381,0.0068628127],"genre_scores_gemma":[0.76550484,0.000026059073,0.23372617,0.00018063265,0.00009135356,0.00023867152,0.00015581852,0.0000030859117,0.000073366966],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918854,0.000018644381,0.0003473122,0.00015836339,0.00012768187,0.00015944528],"domain_scores_gemma":[0.9992609,0.00009758542,0.00012557895,0.00028300667,0.00015147027,0.00008147467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044678836,0.00010247224,0.00013411939,0.00015318675,0.00021863934,0.0004587353,0.00033551033,0.000054771073,4.845606e-7],"category_scores_gemma":[0.000037252263,0.0000833743,0.000034450146,0.00030844778,0.00001787585,0.002438879,0.000034566685,0.000039334165,0.000017851076],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000056299905,0.00008091303,0.00008453787,0.00009213775,0.000006432008,2.0459797e-7,0.0021498883,0.0005966033,0.000049260387,0.07816522,0.011430918,0.90733826],"study_design_scores_gemma":[0.0003070518,0.00012039115,0.000554992,0.00005017618,0.0000032855578,0.000007034547,0.0001866865,0.91639864,0.00004663195,0.000100969606,0.08210491,0.00011924623],"about_ca_topic_score_codex":0.0000068030695,"about_ca_topic_score_gemma":3.5168276e-7,"teacher_disagreement_score":0.915802,"about_ca_system_score_codex":0.000025348456,"about_ca_system_score_gemma":0.000059472924,"threshold_uncertainty_score":0.4423595},"labels":[],"label_agreement":null},{"id":"W2078765398","doi":"10.1007/s10115-011-0400-x","title":"Early classification on time series","year":2011,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":123,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Beijing Institute of Technology; University of Windsor; Simon Fraser University; National Science Foundation","keywords":"Series (stratigraphy); Classifier (UML); Time series; Computer science; k-nearest neighbors algorithm; Benchmark (surveying); Data mining; Artificial intelligence; Pattern recognition (psychology); Machine learning; Geography","score_opus":0.02641227350953722,"score_gpt":0.20786184290149232,"score_spread":0.18144956939195508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078765398","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027139688,0.00024457107,0.07118143,0.00007411138,0.00052416476,0.00025216278,0.0000046776618,0.00026703504,0.9003122],"genre_scores_gemma":[0.99730897,0.000015658834,0.00069103,0.000029058507,0.000050420214,0.0000147409855,0.000006827684,0.0000026825255,0.0018806092],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994039,0.000027126842,0.0002779236,0.00008883696,0.000095169235,0.000107050924],"domain_scores_gemma":[0.9994541,0.000012832478,0.00013716194,0.00021429565,0.00012981844,0.000051837633],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00021776141,0.00007778206,0.000106856176,0.00012444341,0.00013360652,0.00022973507,0.00017254622,0.000043042535,0.000014368929],"category_scores_gemma":[0.000012335431,0.00006245097,0.000027110309,0.00021823462,0.000019357105,0.0041050417,0.000050162856,0.000043937143,0.0013889333],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014848626,0.000029337505,0.0006827807,0.00006500819,0.00002983995,4.1538064e-7,0.021480484,0.000007705678,0.00007328449,0.883163,0.0028095385,0.09164381],"study_design_scores_gemma":[0.0005245428,0.0006407677,0.07129269,0.00015656023,0.000019747613,0.0000454733,0.0013494572,0.3524329,0.0005753417,0.00042056368,0.5719837,0.0005582616],"about_ca_topic_score_codex":0.000018153598,"about_ca_topic_score_gemma":6.1899914e-7,"teacher_disagreement_score":0.9701693,"about_ca_system_score_codex":0.000014597701,"about_ca_system_score_gemma":0.000014628291,"threshold_uncertainty_score":0.9993886},"labels":[],"label_agreement":null},{"id":"W2081471536","doi":"10.1007/s10115-007-0097-z","title":"A compact multi-resolution index for variable length queries in time series databases","year":2007,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Search engine indexing; Scalability; Computer science; Ranging; Series (stratigraphy); Piecewise; Data mining; Algorithm; Univariate; Variable (mathematics); Database; Mathematics; Artificial intelligence; Multivariate statistics; Machine learning","score_opus":0.022915543555870287,"score_gpt":0.25871462556820385,"score_spread":0.23579908201233357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081471536","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003046213,0.00047420443,0.9894127,0.00002726473,0.00021757203,0.0003137775,0.000025657895,0.00008217384,0.0064004306],"genre_scores_gemma":[0.9796105,0.000039398583,0.018645873,0.000048403243,0.0001289147,0.00002428837,0.00014218694,0.0000082528895,0.0013521976],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998958,0.000028400878,0.0005226142,0.00012327998,0.00012150948,0.00024620985],"domain_scores_gemma":[0.9992867,0.00009600252,0.00018120688,0.0001969014,0.00017503918,0.00006413378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001137714,0.000117066455,0.00021625141,0.00025938617,0.00018211143,0.00030352653,0.00018953644,0.000050421713,0.000004173969],"category_scores_gemma":[0.0000794374,0.00010202613,0.0000315794,0.00042846103,0.000031133637,0.0061230734,0.00008762014,0.000060240396,0.000037387446],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038503023,0.0003800368,0.050435524,0.0020421327,0.00021274258,0.0000037127152,0.033281613,0.011585878,0.00044367704,0.81141466,0.014542071,0.07527294],"study_design_scores_gemma":[0.0005278733,0.00005575092,0.0056619802,0.000101597034,0.0000048765082,0.000015934884,0.00062525773,0.72383255,0.000089640314,0.000019734802,0.26890552,0.00015925936],"about_ca_topic_score_codex":0.00022870446,"about_ca_topic_score_gemma":0.00010896538,"teacher_disagreement_score":0.9765643,"about_ca_system_score_codex":0.000049545702,"about_ca_system_score_gemma":0.000045732504,"threshold_uncertainty_score":0.44390804},"labels":[],"label_agreement":null},{"id":"W2081778498","doi":"10.1007/s10115-008-0188-5","title":"Protecting buying agents in e-marketplaces by direct experience trust modelling","year":2009,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Blockchain Technology Applications and Security","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Quality (philosophy); Context (archaeology); Computer science; Trustworthiness; Value (mathematics); Business; Risk analysis (engineering); Marketing; Internet privacy; Computer security; Microeconomics; Economics","score_opus":0.017957197094414755,"score_gpt":0.25437709880640913,"score_spread":0.23641990171199437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081778498","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30294216,0.0014838943,0.65903485,0.00018631807,0.00017314604,0.00069645944,0.000002323193,0.0003374377,0.03514343],"genre_scores_gemma":[0.9988172,0.000074194126,0.0008809113,0.000043835604,0.000013217112,0.00010556059,0.0000023848859,0.0000016306491,0.00006105177],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99919116,0.000045221146,0.00035142823,0.00014822307,0.00009327287,0.00017070319],"domain_scores_gemma":[0.99952364,0.000035098466,0.00011926445,0.00022133876,0.00006129899,0.00003934484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005350745,0.00009435334,0.00013236949,0.00017230694,0.00022494225,0.00017578679,0.00029016283,0.00009545238,7.680905e-7],"category_scores_gemma":[0.000025895464,0.00008828531,0.000014767963,0.0004295125,0.000019584693,0.001838112,0.00005646005,0.00014354281,0.000016217742],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030896725,0.0003673808,0.0070890873,0.00053219235,0.000030411653,0.000003112365,0.17669106,0.0100124,0.00088855485,0.2089506,0.0048654745,0.59053886],"study_design_scores_gemma":[0.00018738928,0.000022694174,0.00024354456,0.00007018548,6.577159e-7,0.000007766715,0.00072995404,0.9538966,0.00058475335,0.00012972017,0.0440009,0.00012584792],"about_ca_topic_score_codex":0.000032303913,"about_ca_topic_score_gemma":0.0000014337112,"teacher_disagreement_score":0.9438842,"about_ca_system_score_codex":0.000036784753,"about_ca_system_score_gemma":0.000015716469,"threshold_uncertainty_score":0.36001706},"labels":[],"label_agreement":null},{"id":"W2081877265","doi":"10.1007/s10115-012-0504-y","title":"An efficient concept-based retrieval model for enhancing text retrieval quality","year":2012,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Topic Modeling","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; D2L (Canada)","funders":"","keywords":"Computer science; Sentence; Information retrieval; Natural language processing; Weighting; Term (time); Semantics (computer science); Latent semantic analysis; Term Discrimination; Representation (politics); Artificial intelligence; Graph; Document retrieval; Relevance (law); Concept search; Theoretical computer science; Search engine","score_opus":0.03897948914390884,"score_gpt":0.30871514418177404,"score_spread":0.2697356550378652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081877265","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04477603,0.0005222336,0.9514875,0.000030910523,0.00090316747,0.0004642868,0.00001439149,0.00014106296,0.0016604097],"genre_scores_gemma":[0.9937932,0.0000016367139,0.005727135,0.00014389883,0.00021018596,0.000013896123,0.000022491116,0.0000052564583,0.000082313934],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852663,0.00009047816,0.0006527013,0.00015694508,0.00025182724,0.00032141348],"domain_scores_gemma":[0.998698,0.00012681335,0.00022863115,0.00042312586,0.0003359472,0.00018749667],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019344195,0.00013409289,0.000208799,0.00012253034,0.00020717742,0.00025848736,0.00028665987,0.0001083833,9.284833e-7],"category_scores_gemma":[0.000114778995,0.000120572586,0.000049550825,0.00019956804,0.000023996889,0.0029730937,0.000056979854,0.00008326902,0.000034887333],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018223972,0.00028473246,0.00046774565,0.0014956951,0.00003767591,1.378807e-7,0.0964549,0.3204377,0.0033793882,0.55198497,0.0008601121,0.024414735],"study_design_scores_gemma":[0.0005631037,0.000042972883,0.00008713656,0.000035105168,0.000004231048,0.0000019392119,0.00034977155,0.99251586,0.0022992224,0.000017719067,0.003912589,0.00017031835],"about_ca_topic_score_codex":0.0000070601345,"about_ca_topic_score_gemma":9.780152e-7,"teacher_disagreement_score":0.94901717,"about_ca_system_score_codex":0.00009253265,"about_ca_system_score_gemma":0.00013652348,"threshold_uncertainty_score":0.4916807},"labels":[],"label_agreement":null},{"id":"W2084144913","doi":"10.1007/s10115-011-0399-z","title":"Best papers from the Fifth International Conference on Advanced Data Mining and Applications (ADMA 2009)","year":2011,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Data science; Data mining","score_opus":0.06692820956384166,"score_gpt":0.2819794512247109,"score_spread":0.21505124166086925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084144913","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060180025,0.0020546927,0.49459255,0.0012336044,0.00127745,0.0013913962,0.0019870617,0.00028361264,0.49116164],"genre_scores_gemma":[0.9594375,0.001408681,0.035178557,0.00063723244,0.00045157637,0.00056928507,0.0015459994,0.00001256359,0.00075861666],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99932367,0.000020428099,0.0002516057,0.00019489221,0.00011372471,0.00009565454],"domain_scores_gemma":[0.99895996,0.000084014704,0.00013127255,0.0006604892,0.00010453655,0.000059739377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019837011,0.00009031381,0.00008497977,0.000045603763,0.00021212963,0.0003255632,0.00088292395,0.000035558303,0.000011843397],"category_scores_gemma":[0.00002094603,0.000065874956,0.000008537462,0.00012922587,0.00004749372,0.0022197596,0.0003598263,0.000060042137,0.00013178107],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032810074,0.000034980814,0.00026134215,0.000013010237,0.000022810818,1.2426041e-7,0.00894243,0.0000017338922,0.000018896013,0.14675385,0.0041027684,0.83984476],"study_design_scores_gemma":[0.0002698275,0.00003232867,0.0020951196,0.00008080361,0.000007723397,0.0000077362265,0.0026836467,0.15189959,0.0000133400545,0.000105856845,0.84266746,0.00013658551],"about_ca_topic_score_codex":0.00007538775,"about_ca_topic_score_gemma":0.00001587261,"teacher_disagreement_score":0.9534195,"about_ca_system_score_codex":0.000009500447,"about_ca_system_score_gemma":0.000034900935,"threshold_uncertainty_score":0.31394133},"labels":[],"label_agreement":null},{"id":"W2087414729","doi":"10.1007/s10115-006-0020-z","title":"Detecting outlying subspaces for high-dimensional data: the new task, algorithms, and performance","year":2006,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":143,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint Mary's University; Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Linear subspace; Outlier; Subspace topology; Pruning; Computer science; Dimension (graph theory); Heuristic; Anomaly detection; Task (project management); Algorithm; Pattern recognition (psychology); Clustering high-dimensional data; Measure (data warehouse); Point (geometry); Process (computing); Artificial intelligence; Data point; Mathematics; Data mining; Cluster analysis; Combinatorics","score_opus":0.0196734787435495,"score_gpt":0.2493453736811592,"score_spread":0.2296718949376097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087414729","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016596075,0.001124521,0.9797473,0.00038443142,0.00025471576,0.00050948304,0.000014730287,0.00017611796,0.0011926171],"genre_scores_gemma":[0.9860743,0.000046996312,0.013052841,0.00005373231,0.00019957894,0.00008487619,0.00003112161,0.0000040054388,0.000452508],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993365,0.000015420484,0.0002844697,0.00014449406,0.00009272856,0.00012637794],"domain_scores_gemma":[0.99929947,0.00008638251,0.00015042422,0.000317427,0.00010744212,0.000038853654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042097186,0.00008859661,0.000097392025,0.000071867806,0.0005302755,0.00036137938,0.0002788234,0.000045648078,4.2136793e-7],"category_scores_gemma":[0.000012413883,0.00006308322,0.00001240741,0.0001782208,0.00002597897,0.0025729886,0.0001485814,0.000063423104,0.000011776164],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013360251,0.000025736592,0.000723471,0.00030532503,0.000027644857,1.198611e-7,0.0016621514,0.00030280053,0.00046351977,0.23348196,0.0423804,0.72061354],"study_design_scores_gemma":[0.00025967383,0.000063211504,0.001898043,0.00003551926,0.0000072410317,0.000037668517,0.00011203804,0.7220818,0.00090809976,0.00027532564,0.2741825,0.00013892072],"about_ca_topic_score_codex":0.000163025,"about_ca_topic_score_gemma":0.00001474463,"teacher_disagreement_score":0.96947825,"about_ca_system_score_codex":0.0000148015915,"about_ca_system_score_gemma":0.000039046015,"threshold_uncertainty_score":0.4078504},"labels":[],"label_agreement":null},{"id":"W2094160481","doi":"10.1007/s10115-003-0105-x","title":"A Linguistic Approach to Extracting Acronym Expansions from Text","year":2004,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Lexicography and Language Studies","field":"Arts and Humanities","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Acronym; Natural language processing; Lexicon; Computer science; Artificial intelligence; Linguistics","score_opus":0.025754580464048802,"score_gpt":0.24229241205647079,"score_spread":0.216537831592422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094160481","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055387057,0.0028167793,0.001843175,0.000042717067,0.001134231,0.00035495887,0.000075070835,0.00013647196,0.93820953],"genre_scores_gemma":[0.9980599,0.000022825538,0.00012230896,0.00014406646,0.0008869773,0.00006524609,0.00004648749,0.00000604088,0.0006461346],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.99932855,0.000017343533,0.00030559505,0.00009657857,0.00009591815,0.0001560345],"domain_scores_gemma":[0.999511,0.00004908539,0.0000832367,0.000117427815,0.00016424348,0.00007498959],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012266253,0.00011894754,0.00015554938,0.00014034072,0.00050155754,0.00035689794,0.00007028404,0.000035418358,0.000032959913],"category_scores_gemma":[0.000071611794,0.000091768125,0.000042842144,0.0000632927,0.000052302177,0.00083106087,0.00004104908,0.000085669126,0.00032478722],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007714769,0.000048308477,0.00005155838,0.0001172035,0.000043327844,4.4558377e-7,0.8039319,0.00004095821,0.000008186509,0.19011678,0.0014481319,0.004185495],"study_design_scores_gemma":[0.00037686471,0.000035673565,0.00029617574,0.0001629876,0.00001825107,0.0000031911054,0.09140216,0.00014516008,0.000013895235,0.00009632081,0.90727377,0.00017553377],"about_ca_topic_score_codex":0.00087421446,"about_ca_topic_score_gemma":0.00015008816,"teacher_disagreement_score":0.94267285,"about_ca_system_score_codex":0.000021809412,"about_ca_system_score_gemma":0.000021875667,"threshold_uncertainty_score":0.41745907},"labels":[],"label_agreement":null},{"id":"W2102549231","doi":"10.1007/s10115-006-0023-9","title":"Node similarity in the citation graph","year":2006,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":69,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Dalhousie University","funders":"Southeast University; Dalhousie University","keywords":"Computer science; Graph; Complementarity (molecular biology); Theoretical computer science; Similarity (geometry); Citation; Random geometric graph; Similitude; Information retrieval; Data mining; Artificial intelligence; Line graph; Voltage graph; World Wide Web","score_opus":0.01017648760587226,"score_gpt":0.24321623998598907,"score_spread":0.23303975238011682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102549231","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23801003,0.00058782595,0.07877822,0.00017292157,0.00017587536,0.00068649166,0.00002169198,0.000095497395,0.68147147],"genre_scores_gemma":[0.9995604,0.0000028059758,0.00004592026,0.000025394107,0.00014819451,0.00005084126,0.00010798638,0.0000018638876,0.000056593355],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994363,0.000059842016,0.0002857473,0.000048131595,0.000082114464,0.00008782809],"domain_scores_gemma":[0.99966997,0.000045906712,0.000090743415,0.0001121735,0.00007038453,0.000010795227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035871362,0.00006564549,0.00009419722,0.00012664798,0.00008327612,0.00013223733,0.000076104065,0.00002113797,0.000009745947],"category_scores_gemma":[0.0000017582859,0.000047502588,0.000033338547,0.00031229903,0.000015351712,0.0006746443,0.000014386683,0.000065947745,0.000032055228],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005987396,0.00009833739,0.14573576,0.00007590455,0.000024207815,1.4320817e-7,0.004603974,0.00078719563,0.000023732475,0.7829243,0.05171754,0.014002911],"study_design_scores_gemma":[0.0008893238,0.000036210284,0.19858457,0.00010781173,0.000042635354,0.0000028948348,0.0048438786,0.086844295,0.00010374742,0.019029101,0.6891016,0.0004139278],"about_ca_topic_score_codex":0.0005513974,"about_ca_topic_score_gemma":0.00003798954,"teacher_disagreement_score":0.7638952,"about_ca_system_score_codex":0.000009877157,"about_ca_system_score_gemma":0.000009138165,"threshold_uncertainty_score":0.19370994},"labels":[],"label_agreement":null},{"id":"W2110958602","doi":"10.1007/s10115-011-0415-3","title":"Knowledge-empowered agent information system for privacy payoff in eCommerce","year":2011,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Privacy, Security, and Data Protection","field":"Social Sciences","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Reputation; Personally identifiable information; Computer science; Asset (computer security); Stochastic game; Information system; Valuation (finance); Knowledge management; Business; Internet privacy; Computer security; Economics","score_opus":0.050463113740772295,"score_gpt":0.2996881609855993,"score_spread":0.24922504724482702,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110958602","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053173743,0.0021123101,0.034486517,0.00026756662,0.0077541377,0.006777188,0.00022978563,0.0007105031,0.8944883],"genre_scores_gemma":[0.998662,0.00017117623,0.00014997588,0.000037472793,0.00023732106,0.00039239632,0.00013266817,0.0000072050902,0.00020978418],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982373,0.00022386048,0.00086177676,0.00013011931,0.00019374523,0.00035317795],"domain_scores_gemma":[0.9987056,0.00008139079,0.00034105568,0.0003021236,0.00041010254,0.0001597251],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019788572,0.00017241538,0.00026567007,0.00044529804,0.0005288024,0.0003054334,0.00037477785,0.00022598218,0.000019762136],"category_scores_gemma":[0.00043554805,0.00016541783,0.0000616652,0.00042807983,0.00007296783,0.008473021,0.00015897701,0.00013204456,0.0005024791],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019058185,0.0001533109,0.0036424836,0.0029115463,0.000046668494,4.020249e-7,0.69110733,0.000004409811,0.000007932497,0.1958153,0.022553915,0.08356611],"study_design_scores_gemma":[0.0011461693,0.00008135244,0.0036575007,0.00022572554,0.0000132457135,0.0000044995377,0.037322465,0.0028443884,0.00006320223,0.00014697126,0.95423627,0.00025822278],"about_ca_topic_score_codex":0.0015778982,"about_ca_topic_score_gemma":0.00037727907,"teacher_disagreement_score":0.9454883,"about_ca_system_score_codex":0.0003390684,"about_ca_system_score_gemma":0.00020514375,"threshold_uncertainty_score":0.67455435},"labels":[],"label_agreement":null},{"id":"W2118013824","doi":"10.1007/s10115-010-0367-z","title":"Statistical semantics for enhancing document clustering","year":2010,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Semantic similarity; Computer science; Cluster analysis; Document clustering; Similarity (geometry); Vector space model; Explicit semantic analysis; Semantics (computer science); Representation (politics); Benchmark (surveying); Context (archaeology); Artificial intelligence; Information retrieval; Distributional semantics; Data mining; Natural language processing; Semantic computing; Semantic technology; Semantic Web","score_opus":0.012131819968422273,"score_gpt":0.3032534578081119,"score_spread":0.29112163783968964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118013824","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013238626,0.000054168762,0.9943241,0.00007007845,0.0011739304,0.00037061237,0.000006977087,0.000093411414,0.0025828967],"genre_scores_gemma":[0.8967787,0.000019171086,0.10235521,0.00003892464,0.00022022243,0.00013908125,0.000014138799,0.000007988332,0.00042658744],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991048,0.000019729408,0.00034423478,0.00012377354,0.00016583475,0.00024163265],"domain_scores_gemma":[0.9991529,0.00018624391,0.00007727305,0.00024257849,0.00022995948,0.00011105931],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000537654,0.00009313502,0.0001294619,0.00011989107,0.00017353744,0.00046499373,0.0002491954,0.000056958997,0.0000021586357],"category_scores_gemma":[0.00012047925,0.00008362466,0.00001741457,0.00011960101,0.000026468455,0.0024741609,0.00022686127,0.00013390738,0.00007456307],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001982205,0.000036683417,0.00011393069,0.0020168263,0.000037517526,0.0000022007778,0.010729343,0.0009884767,0.0032402375,0.53394,0.0014741666,0.44740078],"study_design_scores_gemma":[0.00039161573,0.00006480171,0.00015884021,0.00004177726,0.0000019512665,0.000039675404,0.00017182526,0.82432014,0.00059765007,0.0002712749,0.17380065,0.00013980485],"about_ca_topic_score_codex":0.00000824185,"about_ca_topic_score_gemma":0.000030395173,"teacher_disagreement_score":0.8954548,"about_ca_system_score_codex":0.0000307707,"about_ca_system_score_gemma":0.00005157014,"threshold_uncertainty_score":0.4483945},"labels":[],"label_agreement":null},{"id":"W2121566986","doi":"10.1007/s10115-008-0179-6","title":"PADS: a simple yet effective pattern-aware dynamic search method for fast maximal frequent pattern mining","year":2008,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Executable; Data mining; Benchmark (surveying); Pattern search; Simple (philosophy); Linear subspace; Tree (set theory); Algorithm; Mathematics; Programming language","score_opus":0.019725056746500533,"score_gpt":0.2976702125706421,"score_spread":0.27794515582414153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121566986","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010135972,0.00014533423,0.98750556,0.00008023189,0.00025970876,0.00081980415,0.00025122846,0.000114556446,0.0006876058],"genre_scores_gemma":[0.9800624,0.000032088043,0.018277166,0.00013811361,0.00009954888,0.0008512819,0.00038041925,0.00001267233,0.00014630778],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988135,0.00008124654,0.0004150139,0.00023783593,0.00017728999,0.00027509322],"domain_scores_gemma":[0.998871,0.00025479036,0.00014132449,0.0003564502,0.00026573654,0.00011066137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005285197,0.00015937691,0.00022385968,0.00016833318,0.00037019188,0.00026570857,0.00036821878,0.00007347024,0.0000025258614],"category_scores_gemma":[0.000023406961,0.0001414897,0.000052962798,0.00025408078,0.00002939418,0.0019755187,0.00018201448,0.00009278842,0.00009786879],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002387997,0.00003171597,0.0007883478,0.0002445879,0.00002873267,0.0000011076849,0.012315801,0.00006544156,0.000026388756,0.0006548791,0.0036834623,0.9821572],"study_design_scores_gemma":[0.0005303204,0.00012102892,0.0036821282,0.000074353906,0.0000061684004,0.00008793639,0.00095571287,0.9571458,0.00009206307,0.000014957635,0.037096012,0.00019349571],"about_ca_topic_score_codex":0.00015486077,"about_ca_topic_score_gemma":0.000013276731,"teacher_disagreement_score":0.98196363,"about_ca_system_score_codex":0.00007016634,"about_ca_system_score_gemma":0.00006464611,"threshold_uncertainty_score":0.5769782},"labels":[],"label_agreement":null},{"id":"W2126734246","doi":"10.1007/s10115-009-0198-y","title":"Boosting support vector machines for imbalanced data sets","year":2009,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":279,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"National Institutes of Health","keywords":"Support vector machine; Boosting (machine learning); Classifier (UML); Machine learning; Artificial intelligence; Computer science; Margin classifier; Data mining; Structured support vector machine; Relevance vector machine; Pattern recognition (psychology)","score_opus":0.03635550629993588,"score_gpt":0.3092264469905259,"score_spread":0.27287094069059004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126734246","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00030400776,0.0002586794,0.9745212,0.0005168449,0.0005639926,0.0007288966,0.00023053076,0.00059368956,0.022282144],"genre_scores_gemma":[0.96882296,0.000055441826,0.028502557,0.0005063423,0.00017705618,0.00009187179,0.0014960638,0.000006733002,0.0003409789],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990044,0.000027045357,0.0004564001,0.00019995008,0.00012635757,0.00018582982],"domain_scores_gemma":[0.9985817,0.000069946866,0.00022725403,0.0008392452,0.00021611065,0.00006570998],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059661234,0.00011875759,0.00016655664,0.00012891996,0.00015362256,0.0004052713,0.0008417442,0.000063250576,0.0000014742138],"category_scores_gemma":[0.00013897926,0.00010437658,0.000018244116,0.00020187491,0.000014579133,0.0067414413,0.00016578712,0.000059138438,0.00006596997],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014071827,0.000047680925,0.00044861907,0.00033745478,0.000016969805,4.4143673e-7,0.002476966,0.000004635871,0.0010871666,0.3098598,0.18014185,0.50556433],"study_design_scores_gemma":[0.00041159446,0.00011092589,0.004568014,0.00005826338,0.0000045038314,0.000029413097,0.00004517331,0.39337018,0.00065873173,0.00035524054,0.60017294,0.00021501498],"about_ca_topic_score_codex":0.000004030068,"about_ca_topic_score_gemma":8.2318917e-7,"teacher_disagreement_score":0.968519,"about_ca_system_score_codex":0.000028593848,"about_ca_system_score_gemma":0.00006388925,"threshold_uncertainty_score":0.4887382},"labels":[],"label_agreement":null},{"id":"W2126966660","doi":"10.1007/s10115-005-0233-6","title":"Capabilities of outlier detection schemes in large datasets, framework and methodologies","year":2006,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":86,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Outlier; Computer science; Anomaly detection; Data mining; Scheme (mathematics); Credit card fraud; Matching (statistics); Artificial intelligence; Machine learning; Pattern recognition (psychology); Credit card; Mathematics; Statistics","score_opus":0.016619104645449252,"score_gpt":0.28303760100419423,"score_spread":0.266418496358745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126966660","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024747571,0.0008766822,0.9720842,0.000029543913,0.00008447139,0.00021114486,0.000029789719,0.00009607807,0.0018404662],"genre_scores_gemma":[0.9841559,0.000074553944,0.0156149445,0.000012304313,0.000022421284,0.00006869684,0.000012999972,0.0000017174739,0.000036449605],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993566,0.000052733772,0.00034359508,0.00009200653,0.000061632396,0.00009338761],"domain_scores_gemma":[0.9994852,0.000113044174,0.0001229879,0.00019410042,0.00006690444,0.000017792956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048669978,0.00006728902,0.00012849607,0.00017171465,0.00007489952,0.0000853056,0.00010515928,0.000079867146,0.0000010784433],"category_scores_gemma":[0.000048793077,0.00005913479,0.000014298465,0.00024751827,0.000038012302,0.0014279209,0.000090606,0.00006999655,0.0000051798997],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000055581636,0.00003665255,0.0035506394,0.00037396746,0.0000072458856,9.920094e-8,0.0024974623,0.000028451284,0.00038789306,0.9295632,0.0007257841,0.06282304],"study_design_scores_gemma":[0.00078826805,0.0002087126,0.043026894,0.00025322844,0.000013241259,0.000047082634,0.004335439,0.09365165,0.029970787,0.024954472,0.8021916,0.00055857725],"about_ca_topic_score_codex":0.0001203423,"about_ca_topic_score_gemma":0.000023462846,"teacher_disagreement_score":0.95940834,"about_ca_system_score_codex":0.000016512222,"about_ca_system_score_gemma":0.000011946108,"threshold_uncertainty_score":0.24114467},"labels":[],"label_agreement":null},{"id":"W2127094475","doi":"10.1007/s10115-004-0189-y","title":"Optimizing complex queries based on similarities of subqueries","year":2005,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada)","funders":"International Business Machines Corporation","keywords":"Computer science; Query optimization; Joins; Key (lock); Similarity (geometry); Information retrieval; Graph; Database; Query expansion; Query language; Data mining; Theoretical computer science; Artificial intelligence","score_opus":0.021749295487071173,"score_gpt":0.24014789906072057,"score_spread":0.2183986035736494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127094475","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013277468,0.00050018664,0.7749097,0.00061349076,0.0005396666,0.00035840715,0.00004173606,0.00022561954,0.2214835],"genre_scores_gemma":[0.98399043,0.000043682416,0.015164386,0.00027094953,0.00008545162,0.000019860767,0.00005822731,0.000003390834,0.00036361042],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993129,0.00003095977,0.0003197676,0.00007807141,0.00014554815,0.00011279036],"domain_scores_gemma":[0.999452,0.000050795214,0.00012245058,0.0002335932,0.000107567714,0.00003361402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027318968,0.0000906757,0.00014267216,0.00018975743,0.00010140267,0.00030115966,0.00024276682,0.000028128019,0.0000068608992],"category_scores_gemma":[0.000016057998,0.00007848248,0.000023721383,0.00016278359,0.000044742967,0.0047620526,0.000099012876,0.00003777944,0.00004626101],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001665493,0.000068521964,0.00030006646,0.00079844974,0.000026174106,4.8192334e-7,0.010201539,0.004699821,0.000027665166,0.8459261,0.02210415,0.11583037],"study_design_scores_gemma":[0.00021659961,0.00004693391,0.00033528658,0.00005466639,0.0000019374172,8.4933606e-7,0.00040388774,0.5573569,0.00018512894,0.000011694002,0.44130236,0.00008376533],"about_ca_topic_score_codex":0.000009567724,"about_ca_topic_score_gemma":0.0000030991328,"teacher_disagreement_score":0.9826627,"about_ca_system_score_codex":0.00001570091,"about_ca_system_score_gemma":0.000021264008,"threshold_uncertainty_score":0.3452373},"labels":[],"label_agreement":null},{"id":"W2127392028","doi":"10.1007/s10115-010-0298-8","title":"User-centric query refinement and processing using granularity-based strategies","year":2010,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Granularity; Unification; Ontology; Context (archaeology); Information retrieval; Data mining; Data science","score_opus":0.015292020251002863,"score_gpt":0.25043735842326176,"score_spread":0.23514533817225888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127392028","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20527865,0.002396124,0.75564367,0.00023457858,0.001577017,0.00063699635,0.0000068884965,0.00027843064,0.033947643],"genre_scores_gemma":[0.99330324,0.000018538583,0.006489893,0.0000861472,0.000069610134,0.000010178912,0.0000067818128,0.0000027795338,0.000012848118],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992475,0.000033768694,0.000307538,0.000117714844,0.00013210469,0.00016136699],"domain_scores_gemma":[0.99944556,0.000023720828,0.00013641216,0.00017333211,0.0001468883,0.00007411197],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00043628583,0.0001092417,0.00013652391,0.0001620298,0.00025258533,0.0011294282,0.0001506408,0.0000746011,0.0000012586497],"category_scores_gemma":[0.000013246285,0.00008573317,0.000016559881,0.00024523147,0.000035406523,0.0035560138,0.00007031581,0.00011683585,0.000010997421],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022385098,0.00018798247,0.011768837,0.0036779074,0.000033386925,0.0000065888275,0.015622383,0.0010067944,0.0012845714,0.5489231,0.0017884935,0.4156776],"study_design_scores_gemma":[0.0005600897,0.000043823788,0.0030809967,0.000094648094,0.000007309812,0.0000381634,0.000514692,0.84705585,0.000059291102,0.00016131377,0.1481641,0.0002197193],"about_ca_topic_score_codex":0.00005861298,"about_ca_topic_score_gemma":0.00001017604,"teacher_disagreement_score":0.8460491,"about_ca_system_score_codex":0.000014286849,"about_ca_system_score_gemma":0.00013584804,"threshold_uncertainty_score":0.9999075},"labels":[],"label_agreement":null},{"id":"W2127408419","doi":"10.1007/s10115-009-0202-6","title":"Integrating multiple document features in language models for expert finding","year":2009,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Expert finding and Q&A systems","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Engineering and Physical Sciences Research Council; Commonwealth Scientific and Industrial Research Organisation","keywords":"Computer science; Information retrieval; Language model; Paragraph; Document retrieval; Document management system; Question answering; PageRank; Intranet; Key (lock); Subject-matter expert; Expert system; Artificial intelligence; Natural language processing; World Wide Web; The Internet","score_opus":0.016461128839897702,"score_gpt":0.2821247681681098,"score_spread":0.2656636393282121,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127408419","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028769817,0.009788663,0.91270274,0.00040901967,0.001882097,0.0015925316,0.000009792342,0.00037544448,0.044469893],"genre_scores_gemma":[0.9962328,0.000030879488,0.0030050767,0.00013294368,0.00012804357,0.00010377678,0.0000145268705,0.0000035582264,0.0003483838],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99899584,0.000045650148,0.0004510571,0.00014913523,0.00012946893,0.00022882287],"domain_scores_gemma":[0.9994031,0.00011192858,0.00013431268,0.0002075612,0.00008109167,0.00006198976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052897795,0.00013555663,0.00020482659,0.000259945,0.0001404174,0.00044746892,0.00025102208,0.000087598986,3.2890344e-7],"category_scores_gemma":[0.00005965599,0.00010881149,0.00004167459,0.00021280334,0.0000073133015,0.0033736217,0.000041924097,0.00008505226,0.000012686846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023639006,0.00006288664,0.0003253711,0.00031439838,0.000019334695,0.0000021902956,0.38755143,0.0014659548,0.0015107557,0.40382966,0.014379884,0.19051449],"study_design_scores_gemma":[0.0015722924,0.00017832345,0.0003864556,0.0007275147,0.0000019019509,0.000043547057,0.012049321,0.9333828,0.0015354526,0.000395465,0.049318265,0.00040866918],"about_ca_topic_score_codex":0.00013507775,"about_ca_topic_score_gemma":0.00002449997,"teacher_disagreement_score":0.967463,"about_ca_system_score_codex":0.00008166504,"about_ca_system_score_gemma":0.000029389468,"threshold_uncertainty_score":0.44372037},"labels":[],"label_agreement":null},{"id":"W2134522724","doi":"10.1007/s10115-006-0015-9","title":"Applying language modeling to session identification from database trace logs","year":2006,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Service-Oriented Architecture and Web Services","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Session (web analytics); TRACE (psycholinguistics); Database; Language model; Identification (biology); Data modeling; Artificial intelligence; Data mining; Natural language processing; Machine learning; Information retrieval","score_opus":0.009350929948738405,"score_gpt":0.2408473831906952,"score_spread":0.2314964532419568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134522724","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14203325,0.0011550875,0.8499448,0.00009072863,0.0006186276,0.00045115763,0.000026400046,0.00017534533,0.005504609],"genre_scores_gemma":[0.9974011,0.000009393246,0.0017856334,0.00019436803,0.00020400148,0.00011006807,0.00021097848,0.0000046236787,0.00007983001],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901617,0.000043316948,0.00041845988,0.00018375735,0.00018629554,0.00015201831],"domain_scores_gemma":[0.99927413,0.000039669994,0.00011828148,0.00036732425,0.00012632145,0.0000742599],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025902523,0.000115385286,0.00012243571,0.00020234041,0.00017490644,0.00044679144,0.00032894086,0.000052145937,0.0000022282225],"category_scores_gemma":[0.0000047622216,0.0000992177,0.000021326021,0.0003638882,0.0000042957786,0.0032948712,0.00015201143,0.00007238147,0.00030503108],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007380202,0.00028245276,0.0018934958,0.0019910587,0.00008051913,0.00000873536,0.20381029,0.09289258,0.06587638,0.16949552,0.0069547384,0.45664042],"study_design_scores_gemma":[0.00026731557,0.000011634214,0.00038961892,0.00015863837,0.000006416335,0.00000614096,0.0022393512,0.9420461,0.0020524764,0.00009654575,0.052540787,0.00018497508],"about_ca_topic_score_codex":0.001287183,"about_ca_topic_score_gemma":0.0001024397,"teacher_disagreement_score":0.85536784,"about_ca_system_score_codex":0.00002240498,"about_ca_system_score_gemma":0.00002209483,"threshold_uncertainty_score":0.430842},"labels":[],"label_agreement":null},{"id":"W2135868586","doi":"10.1007/s10115-010-0341-9","title":"Classifier-based acronym extraction for business documents","year":2010,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Acronym; Computer science; Classifier (UML); Information extraction; Precision and recall; Natural language processing; Artificial intelligence; Information retrieval; Data mining; Linguistics","score_opus":0.013582429754063777,"score_gpt":0.29530810560313925,"score_spread":0.2817256758490755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135868586","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.816701,0.0013762059,0.14687541,0.00042985802,0.0061014984,0.000996172,0.00009189217,0.0001194791,0.027308468],"genre_scores_gemma":[0.99792624,0.000031017775,0.00062362425,0.00007641476,0.0002647578,0.00008927946,0.00023521777,0.000004958126,0.0007485044],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995133,0.0000131773595,0.00020538025,0.00009088847,0.0000569819,0.00012027224],"domain_scores_gemma":[0.9995094,0.000019840872,0.00009009084,0.00012644829,0.00020079767,0.000053418356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021649938,0.00008177895,0.00008775217,0.00004795366,0.000100346784,0.00007162784,0.00006651192,0.00019979745,0.0000041943686],"category_scores_gemma":[0.00013567106,0.000066702014,0.000026680225,0.00006185996,0.000054190074,0.00003118622,0.0000193138,0.0000601433,0.000023235738],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037632827,0.00018700425,0.006138292,0.0013616896,0.00010744064,4.4276896e-7,0.00070704555,0.000033183154,0.2743364,0.003513841,0.107815035,0.6054233],"study_design_scores_gemma":[0.0006265939,0.00007997183,0.0030578654,0.000017098333,0.000006327099,0.0000082031775,0.00014727106,0.0014514059,0.00558539,0.0000065877475,0.98891443,0.00009887177],"about_ca_topic_score_codex":0.000009471749,"about_ca_topic_score_gemma":0.000013883149,"teacher_disagreement_score":0.8810994,"about_ca_system_score_codex":0.0000049982814,"about_ca_system_score_gemma":0.000058275273,"threshold_uncertainty_score":0.2720029},"labels":[],"label_agreement":null},{"id":"W2139151761","doi":"10.1007/s10115-006-0031-9","title":"Mining gene–sample–time microarray data: a coherent gene cluster discovery approach","year":2006,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Division of Biological Infrastructure; National Institutes of Health","keywords":"Microarray analysis techniques; Data mining; Computational biology; Gene; Sample (material); Microarray databases; Microarray; Cluster analysis; Set (abstract data type); Computer science; Data set; Gene chip analysis; DNA microarray; Biology; Bioinformatics; Gene expression; Genetics; Artificial intelligence; Physics","score_opus":0.016347351486732498,"score_gpt":0.24262301528054223,"score_spread":0.22627566379380973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139151761","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6276664,0.011611104,0.30086082,0.00010799674,0.0013741655,0.0014069614,0.00063771685,0.000085641856,0.056249157],"genre_scores_gemma":[0.98560095,0.00014918623,0.0011930058,0.00011896513,0.00074012217,0.0000981882,0.007952677,0.000015124132,0.004131761],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99902266,0.000060280487,0.00040054708,0.00024162795,0.000110278175,0.00016461681],"domain_scores_gemma":[0.999161,0.000010362319,0.0001738507,0.00049575075,0.00010504012,0.000053966618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002560575,0.00014524267,0.0001428087,0.000074917596,0.000114065726,0.0002137609,0.00020425642,0.00012963198,0.000003832666],"category_scores_gemma":[0.000019866195,0.00012350579,0.000033197342,0.000092517694,0.000034980934,0.00013607106,0.0001636863,0.00004336062,0.000042910186],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013228551,0.00015802839,0.0025747993,0.00035873495,0.00009203502,1.839336e-7,0.0008784428,0.00059569074,0.68742687,0.00051818404,0.3013371,0.0059276493],"study_design_scores_gemma":[0.00089090364,0.000049922746,0.0011495634,0.00002966238,0.000019821007,0.000027747283,0.0004900549,0.010880478,0.033879954,0.000003223058,0.9523024,0.0002762567],"about_ca_topic_score_codex":0.000029683992,"about_ca_topic_score_gemma":0.000003829757,"teacher_disagreement_score":0.6535469,"about_ca_system_score_codex":0.00001878998,"about_ca_system_score_gemma":0.00006708594,"threshold_uncertainty_score":0.50364196},"labels":[],"label_agreement":null},{"id":"W2145373745","doi":"10.1007/s10115-003-0135-4","title":"Ontologies for Knowledge Management: An Information Systems Perspective","year":2004,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":201,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Ontology; Computer science; Knowledge management; Perspective (graphical); Data science; Interdependence; Representation (politics); Knowledge representation and reasoning; Management science; Epistemology; Artificial intelligence; Sociology; Engineering","score_opus":0.021858794082854682,"score_gpt":0.27250576757426637,"score_spread":0.2506469734914117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145373745","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031423576,0.0045011523,0.7184632,0.00017603046,0.0032406596,0.0019211407,0.000022314496,0.0007733841,0.26775977],"genre_scores_gemma":[0.9965332,0.00017186945,0.0024848336,0.00006720329,0.00012919301,0.00034213252,0.000040787694,0.00000558318,0.00022516884],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.998628,0.000054604363,0.00062655605,0.0001891029,0.00017608184,0.00032564512],"domain_scores_gemma":[0.9984395,0.00008624583,0.0002628038,0.00043448128,0.0006748024,0.00010219439],"candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0005542017,0.00021894206,0.00029629993,0.00043041163,0.00032489764,0.0010579606,0.0005472283,0.00013896039,4.0932238e-7],"category_scores_gemma":[0.00007538579,0.00018342331,0.000059620295,0.00034065344,0.000056981095,0.014036819,0.00016159345,0.00008217286,0.0002478033],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010916021,0.000033112996,0.00003768224,0.0005235082,0.000035928697,3.8020895e-7,0.02317351,0.00032526537,0.0000017746593,0.96313226,0.0008931991,0.0118324375],"study_design_scores_gemma":[0.0047056666,0.0007412161,0.0029335576,0.00050676474,0.000060024435,0.00016106581,0.13365781,0.116249934,0.00016694445,0.004576325,0.7352293,0.0010113552],"about_ca_topic_score_codex":0.00013392608,"about_ca_topic_score_gemma":0.000025209782,"teacher_disagreement_score":0.99339086,"about_ca_system_score_codex":0.00021252294,"about_ca_system_score_gemma":0.00009565656,"threshold_uncertainty_score":0.999979},"labels":[],"label_agreement":null},{"id":"W2146624380","doi":"10.1007/s10115-006-0024-8","title":"Answering ad hoc aggregate queries from data streams using prefix aggregate trees","year":2006,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National University of Singapore","keywords":"Computer science; Aggregate (composite); Scalability; Trie; Prefix; Data stream mining; Data stream; Data warehouse; Data mining; Database; Data structure; Information retrieval","score_opus":0.02539816418324298,"score_gpt":0.257263077859474,"score_spread":0.23186491367623102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146624380","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14820112,0.027809268,0.8136447,0.00004658655,0.0018604336,0.00056179217,0.0009610578,0.00046294674,0.0064521017],"genre_scores_gemma":[0.9592787,0.0011380365,0.035926715,0.000054017226,0.0007400423,0.000057731475,0.0019606438,0.000032058837,0.0008120325],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99835014,0.00007147317,0.0007223141,0.00032865483,0.00023281653,0.00029457256],"domain_scores_gemma":[0.9981638,0.0000652359,0.00042558665,0.0010909545,0.00016247867,0.00009192784],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00030381075,0.00024579137,0.0003267666,0.00016086517,0.00030911595,0.00050533586,0.0005273737,0.00008618282,0.0000030855492],"category_scores_gemma":[0.00003046955,0.00021016598,0.000032801996,0.00029959806,0.0000682815,0.015276379,0.0006061643,0.000096737924,0.00007591184],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010442687,0.0001810972,0.0053007896,0.0017933052,0.00027285356,0.000034531462,0.023164904,0.005067457,0.004679131,0.24991423,0.011720528,0.6977667],"study_design_scores_gemma":[0.00043798538,0.00003010981,0.0005905616,0.00047271233,0.000010708375,0.000036638583,0.00066444447,0.2663855,0.00064859045,0.00006070713,0.7303362,0.0003258785],"about_ca_topic_score_codex":0.0012270237,"about_ca_topic_score_gemma":0.00041438916,"teacher_disagreement_score":0.8110776,"about_ca_system_score_codex":0.000056988632,"about_ca_system_score_gemma":0.000083158026,"threshold_uncertainty_score":0.9984965},"labels":[],"label_agreement":null},{"id":"W2151207331","doi":"10.1007/s10115-008-0127-5","title":"Multirelational classification: a multiple view approach","year":2008,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Shanghai Jiao Tong University","keywords":"Computer science; Relational database; Construct (python library); Table (database); Set (abstract data type); Feature (linguistics); Data mining; Relevance (law); Artificial intelligence; Information retrieval","score_opus":0.04522474571286368,"score_gpt":0.24907032545918464,"score_spread":0.20384557974632095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151207331","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013565423,0.0008014348,0.93666154,0.000112495836,0.00023203956,0.00031867807,0.000021331822,0.00018194297,0.060314003],"genre_scores_gemma":[0.9511789,0.0001946861,0.047235306,0.00008643423,0.0001323371,0.00026021423,0.00021580585,0.000004674702,0.0006916388],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992182,0.000028755334,0.00034620802,0.00014236815,0.00014863712,0.00011582297],"domain_scores_gemma":[0.99924815,0.00006123335,0.00012228802,0.00031012014,0.00017836827,0.00007983527],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020756439,0.000090719186,0.00011247254,0.00010443522,0.00033860776,0.00015764973,0.0002717509,0.000054660923,0.0000017727058],"category_scores_gemma":[0.000027595803,0.00007946236,0.00002379653,0.00032720403,0.00004205008,0.003237837,0.00008389833,0.000069860274,0.00040314248],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003118379,0.00018516881,0.0038756111,0.00022030421,0.00003416803,5.3602366e-7,0.013790975,0.0001797678,0.000038428883,0.7252459,0.031792577,0.22463346],"study_design_scores_gemma":[0.00019377035,0.0000073939,0.009855788,0.000010306859,0.0000012207142,0.00006260054,0.00010032299,0.607186,0.0000037165005,0.0000084923295,0.38249245,0.00007789089],"about_ca_topic_score_codex":0.000012466775,"about_ca_topic_score_gemma":3.1741348e-7,"teacher_disagreement_score":0.94982237,"about_ca_system_score_codex":0.000023688915,"about_ca_system_score_gemma":0.00006290674,"threshold_uncertainty_score":0.51817155},"labels":[],"label_agreement":null},{"id":"W2153689444","doi":"10.1007/s10115-010-0311-2","title":"The k-anonymity and l-diversity approaches for privacy preservation in social networks against neighborhood attacks","year":2010,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":229,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Data publishing; Social network (sociolinguistics); Computer science; Anonymity; k-anonymity; Adversary; Internet privacy; Computer security; Information privacy; Identity (music); Diversity (politics); Data science; Publishing; Social media; World Wide Web; Sociology","score_opus":0.04483096747457849,"score_gpt":0.25951115515531614,"score_spread":0.21468018768073766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153689444","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15252675,0.00087447086,0.8183422,0.00816566,0.00193734,0.0024229335,0.00003991831,0.0005629575,0.0151277585],"genre_scores_gemma":[0.9974788,0.00009874496,0.0021458003,0.000035940284,0.00010935953,0.00007754281,0.000029613364,0.0000030807782,0.000021154885],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99913037,0.00005017011,0.00031619292,0.00016347632,0.0001234036,0.00021641018],"domain_scores_gemma":[0.99834085,0.0002415982,0.0001824298,0.0010741339,0.00012506275,0.000035927023],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0010991261,0.0001096495,0.00013374958,0.000094726114,0.00081305555,0.000500117,0.0035556809,0.00017885142,1.593308e-7],"category_scores_gemma":[0.0019042133,0.00008466261,0.0000223203,0.00026551756,0.00008964199,0.004731442,0.016162045,0.00024099638,0.0000030007639],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048617156,0.00007402392,0.050608393,0.0004445985,0.000054028224,4.1636707e-7,0.008412228,0.00008624888,0.000023885836,0.32032698,0.16189322,0.45802736],"study_design_scores_gemma":[0.0005066087,0.000019169152,0.01616073,0.0000156703,0.0000026840034,0.000002166546,0.00023924912,0.9243014,0.000013592739,0.005806982,0.05280739,0.00012434775],"about_ca_topic_score_codex":0.000013185166,"about_ca_topic_score_gemma":0.000031825453,"teacher_disagreement_score":0.92421514,"about_ca_system_score_codex":0.000030400404,"about_ca_system_score_gemma":0.000033307017,"threshold_uncertainty_score":0.99179506},"labels":[],"label_agreement":null},{"id":"W2155224116","doi":"10.1007/s10115-012-0495-8","title":"Estimating feature ratings through an effective review selection approach","year":2013,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Feature (linguistics); Purchasing; Feature selection; Product (mathematics); Recommender system; Machine learning; Selection (genetic algorithm); Sentiment analysis; Artificial intelligence; Data mining; Information retrieval; Marketing","score_opus":0.01256800742941423,"score_gpt":0.2659206055018179,"score_spread":0.2533525980724037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155224116","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027336099,0.007846014,0.9396302,0.00017049292,0.0005505912,0.0012422929,6.8780435e-7,0.00020878353,0.047617305],"genre_scores_gemma":[0.77902895,0.0012711834,0.21434113,0.0016502766,0.0009741423,0.0012648345,0.00023916904,0.000023631763,0.0012066518],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991004,0.000116122836,0.00033347093,0.00015558758,0.00015441513,0.0001400013],"domain_scores_gemma":[0.9991929,0.00003745318,0.00024073294,0.00017570794,0.00029592498,0.00005730483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046740932,0.00012182516,0.00021674298,0.00008308237,0.0002264578,0.00057425944,0.00017330772,0.000057293964,0.000006688179],"category_scores_gemma":[0.00003870663,0.00009443602,0.00004102783,0.00047001193,0.000011394916,0.011089796,0.00005788807,0.00009804017,0.00017686961],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000039599076,0.00016362799,0.0026657286,0.008597648,0.0002163472,2.4511726e-7,0.048222087,0.0015690118,0.0003309999,0.1320909,0.14242344,0.663716],"study_design_scores_gemma":[0.0001612848,0.000052722487,0.00072172604,0.00050070486,0.000012287249,0.00002078703,0.0002731382,0.9653914,0.000047285976,0.000026456171,0.032646373,0.00014585021],"about_ca_topic_score_codex":0.000038687987,"about_ca_topic_score_gemma":3.7221085e-7,"teacher_disagreement_score":0.96382236,"about_ca_system_score_codex":0.000028179762,"about_ca_system_score_gemma":0.000016012169,"threshold_uncertainty_score":0.80398345},"labels":[],"label_agreement":null},{"id":"W2184821933","doi":"10.1007/s10115-015-0888-6","title":"Mining contentious documents","year":2015,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Information retrieval; Natural language processing; Data science","score_opus":0.037327002593624904,"score_gpt":0.26374361425195963,"score_spread":0.22641661165833474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2184821933","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028199503,0.0012825041,0.76891494,0.00009112901,0.0021466203,0.00021759392,9.2169483e-7,0.00017999027,0.19896677],"genre_scores_gemma":[0.99760157,0.0000073219258,0.0013686029,0.000072568015,0.00006382887,0.000013558698,0.0000033002848,0.0000015025947,0.00086777203],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99942553,0.000025468757,0.00025400796,0.00006841917,0.00012427664,0.00010227766],"domain_scores_gemma":[0.9994683,0.0000133691565,0.00007888207,0.00016870633,0.00017916546,0.00009153503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003459912,0.000056468278,0.00008449783,0.0000842706,0.00004982697,0.00030922634,0.0001708204,0.000032593318,5.016865e-7],"category_scores_gemma":[0.000028875693,0.000048974656,0.0000122077645,0.00009699155,0.0000073136002,0.0036649108,0.0000963995,0.00003024506,0.00021063232],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000808721,0.000037148755,0.005972457,0.0002858748,0.00004805929,0.0000028295713,0.080205336,0.00060847664,0.00003514063,0.5921069,0.03481853,0.28587115],"study_design_scores_gemma":[0.00069989206,0.000035551937,0.00016414042,0.000045969242,0.0000021886078,0.000035897036,0.001371369,0.49760294,0.000033328153,0.00011859302,0.49976853,0.000121628706],"about_ca_topic_score_codex":0.000024324649,"about_ca_topic_score_gemma":0.0000010187914,"teacher_disagreement_score":0.969402,"about_ca_system_score_codex":0.000028783224,"about_ca_system_score_gemma":0.00004029515,"threshold_uncertainty_score":0.29818767},"labels":[],"label_agreement":null},{"id":"W2237502633","doi":"10.1007/s10115-015-0909-5","title":"A feature location approach supported by time-aware weighting of terms associated with developer expertise profiles","year":2016,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Software Engineering Research","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Computer science; Feature (linguistics); Weighting; Context (archaeology); Data mining; Metadata; Feature model; Software; Source code; Information retrieval; Term (time); Set (abstract data type); World Wide Web","score_opus":0.008221255373777811,"score_gpt":0.2118801598688599,"score_spread":0.20365890449508212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2237502633","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07670527,0.0005302918,0.9185855,0.00014757791,0.00015133325,0.00076310075,0.00003016286,0.00037899762,0.0027078018],"genre_scores_gemma":[0.997769,0.000007359233,0.0007331476,0.00000689529,0.000018184568,0.00008762255,0.00006229968,0.0000070284073,0.0013084732],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99914515,0.000047979174,0.00024595298,0.00012707552,0.00025284538,0.00018097996],"domain_scores_gemma":[0.998935,0.0001429749,0.00014813525,0.00020855461,0.0004981954,0.00006716816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036566186,0.000113048445,0.00016102339,0.00015514542,0.00006509513,0.0001098558,0.00023431281,0.000093067334,0.0000018489184],"category_scores_gemma":[0.00022286475,0.000066864064,0.000013209768,0.00046409998,0.000030376115,0.0022358138,0.0000701076,0.000059499016,0.000039900628],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013488153,0.0006446396,0.16680606,0.0053539826,0.00081277266,0.000005880648,0.09530573,0.0002996437,0.03276305,0.0083857225,0.28967968,0.39980796],"study_design_scores_gemma":[0.0067753782,0.00073119585,0.09787468,0.005005098,0.000035481888,0.00017712376,0.001131972,0.7360407,0.063053735,0.000012632912,0.087175645,0.0019863362],"about_ca_topic_score_codex":0.0000043445907,"about_ca_topic_score_gemma":2.4590162e-7,"teacher_disagreement_score":0.9210637,"about_ca_system_score_codex":0.000084401436,"about_ca_system_score_gemma":0.00009962758,"threshold_uncertainty_score":0.27266374},"labels":[],"label_agreement":null},{"id":"W2289757941","doi":"10.1007/s10115-016-0929-9","title":"Detecting emerging and evolving novelties with locally adaptive density ratio estimation","year":2016,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Novelty; Robustness (evolution); Kernel density estimation; Benchmark (surveying); Kernel (algebra); Artificial intelligence; Set (abstract data type); Density estimation; Focus (optics); Machine learning; Data mining; Pattern recognition (psychology); Mathematics; Statistics","score_opus":0.009207441277482483,"score_gpt":0.21909077333278848,"score_spread":0.209883332055306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2289757941","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012821802,0.00014275186,0.9838319,0.000093766816,0.0000573458,0.0002454325,0.0000012341907,0.00021147839,0.0025943033],"genre_scores_gemma":[0.98784447,0.000025517407,0.011913378,0.000022643026,0.00002664704,0.000060083137,7.597321e-7,0.0000032955459,0.000103221],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993898,0.000023829693,0.00025104103,0.0001250136,0.00009952482,0.00011073523],"domain_scores_gemma":[0.9992981,0.000066217304,0.0001642147,0.0001550892,0.00026328058,0.00005309509],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024598988,0.000095247044,0.00010415095,0.00012678574,0.00030417703,0.00024070076,0.000090721696,0.000044827102,0.0000010414802],"category_scores_gemma":[0.00002679946,0.00006336424,0.000011829648,0.00019446618,0.000038449187,0.0038912122,0.000076416036,0.000045677654,0.000020365795],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013816813,0.000013225504,0.001171433,0.00011707153,0.000024594032,3.3755467e-7,0.0058690626,0.00008406947,0.0011798262,0.18549751,0.00028442946,0.80574465],"study_design_scores_gemma":[0.00048709076,0.00018690314,0.004772989,0.00029898548,0.000009055792,0.00010856303,0.0008380011,0.98105085,0.004867945,0.00035706317,0.006738772,0.00028377486],"about_ca_topic_score_codex":0.000026878884,"about_ca_topic_score_gemma":0.000010203429,"teacher_disagreement_score":0.9809668,"about_ca_system_score_codex":0.000041586278,"about_ca_system_score_gemma":0.000033715412,"threshold_uncertainty_score":0.28210348},"labels":[],"label_agreement":null},{"id":"W2292231671","doi":"10.1007/s10115-015-0906-8","title":"Managing dimensionality in data privacy anonymization","year":2015,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Curse of dimensionality; Computer science; Data mining; Closeness; Process (computing); Cluster analysis; Variety (cybernetics); Machine learning; Mathematics; Artificial intelligence","score_opus":0.07068525535148379,"score_gpt":0.30138513635749714,"score_spread":0.23069988100601335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2292231671","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008936398,0.0025237852,0.9468613,0.008123039,0.001650438,0.0006483804,0.000042852804,0.00085934903,0.030354459],"genre_scores_gemma":[0.97256607,0.00015341493,0.026669538,0.00012542206,0.00005556662,0.000024452691,0.0003330261,0.000005505066,0.000067006615],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989586,0.0000741922,0.00039975843,0.0002020675,0.0002065282,0.00015885786],"domain_scores_gemma":[0.9953856,0.000054826127,0.00013407621,0.0042181774,0.00014487836,0.000062477506],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0013320144,0.000091792346,0.00013101897,0.00024667804,0.00005432297,0.0002952095,0.007434627,0.00007164779,6.726069e-7],"category_scores_gemma":[0.0041082744,0.000083719555,0.000006604195,0.0005245368,0.000027671478,0.0111947935,0.037051238,0.00009846451,0.00011329771],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013309063,0.00008477355,0.010204655,0.00039883863,0.000022611828,0.0000047342273,0.0043889554,0.00024854773,0.000017649483,0.09837068,0.7546239,0.13162135],"study_design_scores_gemma":[0.0003528074,0.00001039911,0.0011432345,0.00006588812,0.0000012195053,0.000013018666,0.00016282218,0.82522464,0.000020857153,0.007629868,0.16526441,0.00011084314],"about_ca_topic_score_codex":0.000054475884,"about_ca_topic_score_gemma":0.000007070067,"teacher_disagreement_score":0.96362966,"about_ca_system_score_codex":0.00007407393,"about_ca_system_score_gemma":0.00008423943,"threshold_uncertainty_score":0.99793565},"labels":[],"label_agreement":null},{"id":"W2293288274","doi":"10.1007/s10115-015-0868-x","title":"Models of time series with time granulation","year":2016,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"King Abdulaziz University","keywords":"Piecewise; Series (stratigraphy); Representation (politics); Algorithm; Mathematics; Classification of discontinuities; Particle swarm optimization; Segmentation; Time series; Approximation error; Mathematical optimization; Computer science; Artificial intelligence; Statistics; Mathematical analysis","score_opus":0.007936365335809168,"score_gpt":0.1822148914027256,"score_spread":0.17427852606691643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2293288274","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01658041,0.00032402153,0.88272727,0.00017266875,0.000095872725,0.00023216862,0.000013043502,0.00013168872,0.09972287],"genre_scores_gemma":[0.99613035,0.0000200286,0.001287979,0.000007720849,0.0000380981,0.000007452851,0.000006552938,0.0000031482189,0.0024986821],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99939257,0.000022548666,0.0003000486,0.00007163805,0.000117182964,0.000096037365],"domain_scores_gemma":[0.999344,0.000026580023,0.00018716264,0.00017641718,0.00022922014,0.00003665287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022167037,0.000072631934,0.00016474533,0.00010697475,0.00006630178,0.00009345815,0.00012375966,0.000031648167,0.000009493861],"category_scores_gemma":[0.00000722797,0.000040944433,0.000022641001,0.0002028124,0.000030250083,0.006507343,0.00005092077,0.000015868027,0.00017112751],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000119398646,0.00006124174,0.0013882914,0.0006038022,0.0002117396,9.046426e-7,0.018948661,0.004585723,0.004093559,0.5858587,0.0059183994,0.3782096],"study_design_scores_gemma":[0.00068554527,0.00023402869,0.00058078294,0.00030921682,0.000016769607,0.00003916255,0.00011644282,0.95375985,0.0009996538,0.00048187896,0.042534214,0.00024244377],"about_ca_topic_score_codex":0.000007678217,"about_ca_topic_score_gemma":9.013186e-7,"teacher_disagreement_score":0.97954994,"about_ca_system_score_codex":0.000011736922,"about_ca_system_score_gemma":0.000022250442,"threshold_uncertainty_score":0.47176665},"labels":[],"label_agreement":null},{"id":"W2337195508","doi":"10.1007/s10115-016-0939-7","title":"Correlation analysis techniques for uncertain time series","year":2016,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Concordia University","keywords":"Multiset; Computer science; Timestamp; Autocorrelation; Time series; Probability density function; Probabilistic logic; Normalization (sociology); Data mining; Pruning; Correlation; Random variable; Computation; Algorithm; Artificial intelligence; Machine learning; Mathematics; Statistics","score_opus":0.009764429531435057,"score_gpt":0.2261206984437926,"score_spread":0.21635626891235754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2337195508","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00031489154,0.0001711899,0.9863366,0.00015891007,0.00009966321,0.00020042561,0.000013113775,0.00014425193,0.01256098],"genre_scores_gemma":[0.9795226,0.00008568419,0.011003338,0.000052065614,0.00016946507,0.00015298126,0.00006502277,0.000007186144,0.008941686],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992803,0.000026979455,0.00036685733,0.00010864971,0.000090037465,0.00012718033],"domain_scores_gemma":[0.9992161,0.000077782315,0.00019438082,0.00019385753,0.00027255426,0.00004536023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042117017,0.00008803733,0.0001901653,0.00028782673,0.00015478712,0.00023503316,0.0001500034,0.0000558091,0.000008651817],"category_scores_gemma":[0.000043154334,0.000056101275,0.00008113005,0.00061470154,0.000021557598,0.004486019,0.000056074816,0.000018715476,0.00008637552],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024680618,0.000019721023,0.0019874682,0.00015617773,0.00042381155,2.1748093e-7,0.0039664493,0.00031614263,0.00031891707,0.33321795,0.0077912817,0.65177715],"study_design_scores_gemma":[0.00018057489,0.000094140836,0.0005459486,0.000052667267,0.0000743428,0.0000065640215,0.000112550086,0.54201025,0.00029532873,0.00019114114,0.45626083,0.0001756513],"about_ca_topic_score_codex":0.000010214948,"about_ca_topic_score_gemma":0.0000033818499,"teacher_disagreement_score":0.9792077,"about_ca_system_score_codex":0.000031896147,"about_ca_system_score_gemma":0.000021442751,"threshold_uncertainty_score":0.32522553},"labels":[],"label_agreement":null},{"id":"W2513061279","doi":"10.1007/s10115-016-0986-0","title":"EFIM: a fast and memory efficient algorithm for high-utility itemset mining","year":2016,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":239,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Computer science; Key (lock); Data mining; Projection (relational algebra); Database transaction; Task (project management); Tree (set theory); Algorithm; High memory; Database; Mathematics; Parallel computing","score_opus":0.012865336366108314,"score_gpt":0.2381222319819108,"score_spread":0.22525689561580248,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2513061279","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006712245,0.0003578088,0.98954517,0.0001816323,0.00042065998,0.00041288193,0.00021850383,0.000104664476,0.0020464307],"genre_scores_gemma":[0.92334944,0.00008428992,0.07429645,0.000121844234,0.0003272239,0.00057721615,0.0001028264,0.0000128011525,0.0011278844],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991227,0.000025956433,0.0003644195,0.00019366558,0.00011010527,0.00018315374],"domain_scores_gemma":[0.99909204,0.00017271,0.00013784718,0.0003033266,0.00019065592,0.000103422135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054885296,0.000114391754,0.00016024747,0.000109299894,0.0002194931,0.00027700205,0.00021412801,0.00005614005,0.0000014843866],"category_scores_gemma":[0.00003823084,0.00007865322,0.00002025423,0.00016304702,0.00004770574,0.0014592917,0.00015270719,0.000029572158,0.000048237376],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010815351,0.000013942492,0.000022192164,0.000057253685,0.0000065971567,6.2817215e-8,0.0016184502,0.0000015816044,0.000019661271,0.00993299,0.0035381885,0.984788],"study_design_scores_gemma":[0.00097233587,0.00007488783,0.0013195783,0.00014375744,0.000008045311,0.000027875449,0.000555233,0.78966224,0.00026756898,0.000056502366,0.20669213,0.00021983216],"about_ca_topic_score_codex":0.000017628274,"about_ca_topic_score_gemma":0.000001267471,"teacher_disagreement_score":0.9845682,"about_ca_system_score_codex":0.000022524438,"about_ca_system_score_gemma":0.000039567763,"threshold_uncertainty_score":0.32073852},"labels":[],"label_agreement":null},{"id":"W2529045002","doi":"10.1007/s10115-016-0998-9","title":"Finding multiple stable clusterings","year":2016,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Office of Naval Research; National Science Foundation","keywords":"Cluster analysis; Computer science; Data mining; Constrained clustering; Clustering high-dimensional data; Spectral clustering; Fuzzy clustering; Correlation clustering; Consensus clustering; Partition (number theory); CURE data clustering algorithm; Stability (learning theory); Machine learning; Artificial intelligence; Mathematics","score_opus":0.022548493315349666,"score_gpt":0.2736265916603705,"score_spread":0.2510780983450208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2529045002","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047340933,0.00022384975,0.98159647,0.00012158056,0.0005395984,0.00020807842,0.0000054462907,0.00018033877,0.012390518],"genre_scores_gemma":[0.9928983,0.00007328569,0.004041505,0.000028669134,0.00008257851,0.00005321547,0.0000018511868,0.0000058419564,0.0028147802],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991032,0.00003738832,0.00028578303,0.00013057608,0.0001810781,0.0002619663],"domain_scores_gemma":[0.9992027,0.0001558547,0.00008670562,0.00027969797,0.00017034484,0.00010464793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039127754,0.00009507349,0.00011946516,0.00017933313,0.00015263738,0.00028575154,0.0003230508,0.000048431557,0.0000036538463],"category_scores_gemma":[0.00010640192,0.00006444844,0.000018719033,0.00022301638,0.000026488005,0.0063912934,0.0003625768,0.0000531164,0.00048436262],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017923303,0.000029954192,0.002227983,0.000526317,0.000030355232,0.000002948287,0.008420843,0.00024133349,0.0028659818,0.03969935,0.0034992583,0.94243777],"study_design_scores_gemma":[0.0010005746,0.00006843887,0.0012514404,0.00022511036,0.000001120048,0.00005478034,0.00017827998,0.32065454,0.0011967033,0.00008074491,0.6750448,0.00024345791],"about_ca_topic_score_codex":0.000013658701,"about_ca_topic_score_gemma":0.0000022314773,"teacher_disagreement_score":0.9881642,"about_ca_system_score_codex":0.000083933846,"about_ca_system_score_gemma":0.00003732493,"threshold_uncertainty_score":0.62256634},"labels":[],"label_agreement":null},{"id":"W2762595523","doi":"10.1007/s10115-017-1110-9","title":"Subspace multi-clustering: a review","year":2017,"lang":"en","type":"review","venue":"Knowledge and Information Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Cluster analysis; Computer science; Clustering high-dimensional data; Correlation clustering; CURE data clustering algorithm; Data mining; Consensus clustering; Canopy clustering algorithm; Data stream clustering; Fuzzy clustering; Constrained clustering; Artificial intelligence; Brown clustering; Pattern recognition (psychology); Machine learning","score_opus":0.16548597611151802,"score_gpt":0.43143692051603333,"score_spread":0.2659509444045153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2762595523","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.3744906e-9,0.7794117,0.21129814,0.000018505965,0.0007915598,0.0012017007,0.000012505463,0.0001370238,0.007128883],"genre_scores_gemma":[3.0579693e-7,0.9936709,0.0022230966,0.000024874733,0.0001305864,0.0003933708,0.00003918504,0.000018781177,0.0034989382],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977045,0.00020708391,0.0010267644,0.0003372593,0.00032904168,0.0003953597],"domain_scores_gemma":[0.9969624,0.00011570372,0.00089534675,0.0014669839,0.00034567653,0.00021384294],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010331294,0.00041730228,0.001543763,0.00035877357,0.000339932,0.0010100277,0.001688456,0.00023296583,0.000002446397],"category_scores_gemma":[0.00023885477,0.00032651811,0.00020611346,0.00033153416,0.000056684552,0.004637249,0.0012359865,0.00039827908,0.0012825627],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.5081889e-7,0.0000062991544,5.121484e-8,0.120094225,0.000023798653,0.0000021621736,0.00020250266,9.0056443e-7,3.1073215e-9,0.00040927337,0.0012705325,0.8779901],"study_design_scores_gemma":[0.00014242216,0.000021016253,3.6238467e-7,0.073073626,0.000033239405,0.00023938963,0.000008027521,0.019675223,2.3812124e-8,7.340371e-7,0.9064887,0.0003171988],"about_ca_topic_score_codex":0.000010076367,"about_ca_topic_score_gemma":0.0000030618505,"teacher_disagreement_score":0.9052182,"about_ca_system_score_codex":0.00016093592,"about_ca_system_score_gemma":0.00033340885,"threshold_uncertainty_score":0.9999187},"labels":[],"label_agreement":null},{"id":"W2784269545","doi":"10.1007/s10115-017-1147-9","title":"Localized user-driven topic discovery via boosted ensemble of nonnegative matrix factorization","year":2018,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Research Foundation of Korea","keywords":"Matrix decomposition; Computer science; Factorization; Matrix (chemical analysis); Non-negative matrix factorization; Mathematics; Artificial intelligence; Algorithm; Physics","score_opus":0.009477174681492609,"score_gpt":0.27222000813632263,"score_spread":0.26274283345483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2784269545","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008855678,0.00012224691,0.98438627,0.000015741414,0.00025055773,0.00026616032,0.0000040465006,0.0001296512,0.005969643],"genre_scores_gemma":[0.99416596,0.00002827914,0.00522039,0.000018021148,0.000072750074,0.00001907101,0.000018231027,0.0000038393664,0.00045345858],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990214,0.0000616472,0.00049897237,0.00012355116,0.00016759874,0.00012683329],"domain_scores_gemma":[0.9987667,0.000052858122,0.00033687556,0.000302989,0.00049613643,0.00004443526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015434873,0.00011462625,0.00023264493,0.00022900292,0.00009510397,0.00015631893,0.00025008322,0.00007590473,0.0000026841956],"category_scores_gemma":[0.00003804567,0.00009677953,0.000041324336,0.00048589995,0.000057744586,0.006133218,0.00012677854,0.000049158127,0.00005639518],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000074589494,0.00018656041,0.009965869,0.0011208307,0.00028577296,0.0000013972071,0.049601134,0.00036865307,0.02266013,0.7827153,0.004224543,0.12879518],"study_design_scores_gemma":[0.001671128,0.0006605422,0.00333431,0.000424275,0.00005095641,0.000021778565,0.0008624777,0.66804457,0.122110076,0.002384871,0.19969285,0.00074217445],"about_ca_topic_score_codex":0.0000356293,"about_ca_topic_score_gemma":0.000011701871,"teacher_disagreement_score":0.98531026,"about_ca_system_score_codex":0.000050832383,"about_ca_system_score_gemma":0.000038194154,"threshold_uncertainty_score":0.4446435},"labels":[],"label_agreement":null},{"id":"W2883420210","doi":"10.1007/s10115-018-1235-5","title":"Overview of the crowdsourcing process","year":2018,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Crowdsourcing; Computer science; Process (computing); Task (project management); Quality (philosophy); Data science; Human intelligence; Incentive; Artificial intelligence; Machine learning; World Wide Web; Engineering","score_opus":0.020536533582253488,"score_gpt":0.26745217543955035,"score_spread":0.24691564185729686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2883420210","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5472501,0.0059405537,0.1919339,0.00033577098,0.0043951026,0.0009605568,0.0000058659925,0.00034165653,0.24883649],"genre_scores_gemma":[0.9995651,0.0000133141675,0.00008301195,0.00007227178,0.00010068676,0.000006480708,4.131135e-7,0.0000024211768,0.00015627206],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99927765,0.00004838581,0.0003252336,0.000081659535,0.00014541703,0.00012162923],"domain_scores_gemma":[0.9990718,0.000030640593,0.00019343501,0.00033497642,0.00033167697,0.000037496073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040711876,0.00007702543,0.00012271416,0.00006917779,0.00021224114,0.00017750038,0.00031189123,0.000042855685,0.000001676127],"category_scores_gemma":[0.000044253287,0.00005041101,0.00003241693,0.00038824152,0.000071331604,0.0014042415,0.00012270211,0.000055201253,0.00004854331],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017331377,0.00009666149,0.011915402,0.00517382,0.00009393866,5.6400114e-7,0.18559104,0.00037467774,0.0015064526,0.49728036,0.014150808,0.28379893],"study_design_scores_gemma":[0.0009817738,0.00018696596,0.013134016,0.002182848,0.000024471494,0.00018310628,0.0028498955,0.38531676,0.019909326,0.00047922475,0.5742147,0.00053689646],"about_ca_topic_score_codex":0.000015673286,"about_ca_topic_score_gemma":0.0000023856962,"teacher_disagreement_score":0.5600639,"about_ca_system_score_codex":0.000012916675,"about_ca_system_score_gemma":0.000056959074,"threshold_uncertainty_score":0.20557013},"labels":[],"label_agreement":null},{"id":"W2889435016","doi":"10.1007/s10115-018-1250-6","title":"Categorizing relational facts from the web with fuzzy rough sets","year":2018,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg","funders":"Natural Sciences and Engineering Research Council of Canada; Türkiye Bilimsel ve Teknolojik Araştırma Kurumu; University of Winnipeg","keywords":"Rough set; Artificial intelligence; Computer science; Set (abstract data type); Noun; Fuzzy logic; Statistical relational learning; Fuzzy set; Machine learning; Natural language processing; Mathematics; Relational database; Data mining","score_opus":0.02216141262980433,"score_gpt":0.2288226861964595,"score_spread":0.20666127356665517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889435016","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.067802876,0.0021483123,0.20156989,0.0018653962,0.0030322885,0.00087198766,0.00005109111,0.00039016872,0.722268],"genre_scores_gemma":[0.99780834,0.000027350561,0.0014739544,0.0002563056,0.00029130286,0.000015736963,0.000030500998,0.00000306843,0.000093461844],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.999214,0.000051139756,0.00026827148,0.000119785094,0.0001930639,0.00015372035],"domain_scores_gemma":[0.99921304,0.00010247459,0.0001393673,0.00027769778,0.00021025733,0.00005716155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002680244,0.00010682511,0.00010833661,0.000048257905,0.00035007452,0.00044632357,0.00027878306,0.000058941383,0.000004826494],"category_scores_gemma":[0.000017432898,0.00005940756,0.000017603634,0.00024736393,0.00005717088,0.0032325615,0.000099335964,0.00008598534,0.0005610967],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030388685,0.000040696363,0.009870849,0.00007419643,0.00009963299,0.0000020943799,0.0609334,0.00021498773,0.000025647872,0.7910561,0.05939685,0.078255184],"study_design_scores_gemma":[0.0006146963,0.00014202735,0.021094605,0.000081704326,0.000008149141,0.000037263588,0.00063714205,0.16483754,0.000022181694,0.0008435811,0.8114493,0.00023183675],"about_ca_topic_score_codex":0.00009409862,"about_ca_topic_score_gemma":0.000026892722,"teacher_disagreement_score":0.93000543,"about_ca_system_score_codex":0.000025370155,"about_ca_system_score_gemma":0.00008618013,"threshold_uncertainty_score":0.72119504},"labels":[],"label_agreement":null},{"id":"W2906685695","doi":"10.1007/s10115-018-1278-7","title":"Combining semantic and term frequency similarities for text clustering","year":2019,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Fundação de Amparo à Pesquisa do Estado de Minas Gerais; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Natural Sciences and Engineering Research Council of Canada; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Cluster analysis; Semantic similarity; Computer science; Document clustering; Similarity (geometry); Measure (data warehouse); Information retrieval; Similarity measure; Natural language processing; Term (time); Artificial intelligence; Word (group theory); Data mining; Mathematics","score_opus":0.01570786528100131,"score_gpt":0.24286185679499328,"score_spread":0.22715399151399196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2906685695","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13045011,0.0036708564,0.7936513,0.00082191743,0.002156708,0.0018954383,0.000013558962,0.0010731603,0.06626697],"genre_scores_gemma":[0.99802655,0.00007045909,0.0012926948,0.00004641076,0.000017348028,0.000058070847,0.0000068938552,0.0000028902643,0.00047866488],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994033,0.0000120253435,0.00027825584,0.0001083929,0.00007038647,0.00012763162],"domain_scores_gemma":[0.9994855,0.00007406912,0.00011557959,0.00020667829,0.000088344554,0.000029822528],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020370024,0.00008688413,0.00013291523,0.00015652434,0.00012129542,0.00047806703,0.00018965198,0.000064885025,0.0000016493498],"category_scores_gemma":[0.000022472974,0.000075906886,0.00001730354,0.00010404798,0.000026884376,0.0032144445,0.00012706552,0.00004718287,0.000054209937],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000482765,0.000016573083,0.012695805,0.0015646797,0.000024362287,1.4369368e-7,0.011226255,0.00001200933,0.00057555217,0.8524855,0.001452804,0.119941525],"study_design_scores_gemma":[0.0028039503,0.00044998951,0.021527573,0.00064936926,0.000017236733,0.00006820701,0.008267388,0.757913,0.0010846716,0.0041264566,0.20225959,0.00083259126],"about_ca_topic_score_codex":0.0000054741954,"about_ca_topic_score_gemma":0.0000015590794,"teacher_disagreement_score":0.8675765,"about_ca_system_score_codex":0.000017304614,"about_ca_system_score_gemma":0.000018560128,"threshold_uncertainty_score":0.46100113},"labels":[],"label_agreement":null},{"id":"W2979871440","doi":"10.1007/s10115-019-01405-7","title":"$${\\textsf {SecDM}}$$: privacy-preserving data outsourcing framework with differential privacy","year":2019,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Cryptography and Data Security","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; University of Manitoba; McGill University","funders":"","keywords":"Computer science; Cloud computing; Homomorphic encryption; Encryption; Differential privacy; Information privacy; Outsourcing; Scalability; Computer security; Service provider; Cryptosystem; Database; Data mining; Service (business); Business","score_opus":0.01773065424694377,"score_gpt":0.24963610835367206,"score_spread":0.2319054541067283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979871440","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09232398,0.0007315384,0.8952467,0.000101097074,0.0010395298,0.000562924,0.00005782162,0.00022456901,0.009711834],"genre_scores_gemma":[0.99488497,0.00004708811,0.0046199276,0.00005799968,0.00015979217,0.000013294674,0.00017892933,0.000007139696,0.000030886393],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99853975,0.00007356045,0.00045350599,0.00032433282,0.00031654435,0.0002922915],"domain_scores_gemma":[0.9971989,0.00013421566,0.00023378628,0.0021518944,0.00014558282,0.00013563815],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004135686,0.00019662523,0.00026138042,0.00021744397,0.00019915683,0.0010863433,0.00204514,0.00011794416,0.000027474583],"category_scores_gemma":[0.000077790864,0.00015180508,0.000032601944,0.00046402003,0.000030250098,0.010533462,0.0022810048,0.00023738593,0.0003073127],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000114564915,0.00022540092,0.057217207,0.002911763,0.00024628613,0.0000038198314,0.07570581,0.00014712762,0.000117425705,0.79240763,0.018262306,0.05264065],"study_design_scores_gemma":[0.0014949905,0.00017670632,0.017024104,0.00091598416,0.000025624411,0.00006054724,0.0010046583,0.3987034,0.00007452847,0.0009527934,0.57887304,0.00069364463],"about_ca_topic_score_codex":0.000040176343,"about_ca_topic_score_gemma":0.000004146417,"teacher_disagreement_score":0.90256095,"about_ca_system_score_codex":0.000018925573,"about_ca_system_score_gemma":0.000062232095,"threshold_uncertainty_score":0.99995065},"labels":[],"label_agreement":null},{"id":"W3027993156","doi":"10.1007/s10115-020-01472-1","title":"Survival neural networks for time-to-event prediction in longitudinal study","year":2020,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier Universitaire de Sherbrooke; Université de Sherbrooke","funders":"National Institute of Justice; Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; National Science Foundation","keywords":"Censoring (clinical trials); Covariate; Survival analysis; Artificial neural network; Computer science; Event (particle physics); Accelerated failure time model; Prognostics; Brier score; Artificial intelligence; Machine learning; Statistics; Data mining; Mathematics","score_opus":0.09601427600990584,"score_gpt":0.35848118935826145,"score_spread":0.2624669133483556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3027993156","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052408673,0.00006276462,0.93893886,0.00010811448,0.0005104335,0.0019582903,0.000051912222,0.00007768486,0.005883254],"genre_scores_gemma":[0.9979821,0.0000012833033,0.0014538696,0.000044346063,0.00022657095,0.00017611582,0.000011976993,0.000007248615,0.00009649232],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99895364,0.00011077538,0.00055553956,0.0001119202,0.0001157708,0.00015232702],"domain_scores_gemma":[0.99910593,0.00044470892,0.000096186115,0.00008617172,0.0001456413,0.00012134573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067172974,0.00010691819,0.00025482476,0.00006568854,0.000060721708,0.00008484949,0.00007011547,0.00005004427,0.000028713635],"category_scores_gemma":[0.0006872251,0.000090079666,0.000024815205,0.00019787902,0.000008148352,0.00037513472,0.000044021057,0.00008366267,0.000079641264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015179288,0.0013816331,0.165006,0.0051580016,0.00033255326,0.0000069867106,0.076229244,0.010749881,0.000058733025,0.35862395,0.094338454,0.28659663],"study_design_scores_gemma":[0.00092373416,0.0006626672,0.017693236,0.000052732994,0.000020349833,0.0000019683769,0.0009910344,0.97253066,0.0000018416281,0.00037202658,0.006618851,0.00013087539],"about_ca_topic_score_codex":0.000007814205,"about_ca_topic_score_gemma":0.0000038412386,"teacher_disagreement_score":0.9617808,"about_ca_system_score_codex":0.000025798397,"about_ca_system_score_gemma":0.00001403279,"threshold_uncertainty_score":0.36733422},"labels":[],"label_agreement":null},{"id":"W3096565974","doi":"10.1007/s10115-020-01521-9","title":"CANE: community-aware network embedding via adversarial training","year":2020,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Novelis (Canada)","funders":"","keywords":"Computer science; Node (physics); Discriminative model; Pairwise comparison; Embedding; Adversarial system; Machine learning; Representation (politics); Feature learning; Data mining; Artificial intelligence; Community structure; Theoretical computer science; Mathematics","score_opus":0.0314213780843983,"score_gpt":0.2559193188299602,"score_spread":0.22449794074556192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3096565974","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020054453,0.0004720958,0.98532814,0.00020804716,0.0014470192,0.00029105935,0.0000037490558,0.00033090348,0.009913518],"genre_scores_gemma":[0.99745417,0.00002290612,0.0012728056,0.00065176195,0.00053227844,0.000017290185,0.000022015292,0.0000061668834,0.000020593603],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988734,0.00017751515,0.00042074782,0.00010973663,0.00014481107,0.00027380127],"domain_scores_gemma":[0.9991271,0.00015021373,0.00018389191,0.00023957856,0.000117256444,0.00018194775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034043205,0.0001462736,0.00022154809,0.00006032041,0.00047414863,0.00025309672,0.000438285,0.00008170644,0.0000019563365],"category_scores_gemma":[0.00003310089,0.0001385212,0.000040725197,0.000541997,0.000029972178,0.003942407,0.00024758413,0.00034286352,0.000071418384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000073452415,0.00003456961,0.0009194394,0.00090274273,0.00012640994,0.0000093276085,0.2576198,0.18341272,0.00007237815,0.103893444,0.042087015,0.4108487],"study_design_scores_gemma":[0.0004069096,0.00007666868,0.0000970982,0.00007345512,0.0000041655726,0.000024325906,0.0013243249,0.8611942,0.000007638696,0.00010765567,0.13650347,0.00018007326],"about_ca_topic_score_codex":0.000021783706,"about_ca_topic_score_gemma":0.000006810562,"teacher_disagreement_score":0.9954487,"about_ca_system_score_codex":0.000026375983,"about_ca_system_score_gemma":0.000039282928,"threshold_uncertainty_score":0.56487304},"labels":[],"label_agreement":null},{"id":"W3100780777","doi":"10.1007/s10115-017-1033-5","title":"Measuring in-network node similarity based on neighborhoods: a unified parametric approach","year":2017,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Similarity (geometry); Node (physics); Parametric statistics; Data mining; Computer science; Mathematics; Artificial intelligence; Theoretical computer science; Statistics; Engineering","score_opus":0.035922509109027265,"score_gpt":0.26357355829460927,"score_spread":0.227651049185582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3100780777","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027854437,0.00022003979,0.11828813,0.000040963674,0.00026961789,0.00076008093,0.000016114016,0.00011713239,0.8524335],"genre_scores_gemma":[0.9991258,0.0000044417284,0.0003777813,0.000025002368,0.00026805326,0.0000834171,0.00005267543,0.000007360219,0.000055496268],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989369,0.0000812262,0.0004409619,0.00014623307,0.00016001717,0.00023467984],"domain_scores_gemma":[0.99886584,0.000078863515,0.0003296306,0.0005388466,0.000115691895,0.000071150396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006989116,0.00016337047,0.00030235277,0.0002566765,0.0003724841,0.00046074964,0.00025415234,0.00006203987,0.000010330271],"category_scores_gemma":[0.000026642114,0.00014800798,0.00007182231,0.0002919956,0.00003225714,0.00091834145,0.00007827558,0.00018442581,0.000031614218],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008039953,0.00038202922,0.72442025,0.00040136444,0.00014408177,6.3559213e-7,0.0011577219,0.059307795,0.0000037540333,0.14670832,0.006690133,0.060703482],"study_design_scores_gemma":[0.000705482,0.000027796437,0.04609686,0.00017648148,0.000021246045,3.281978e-7,0.00015769467,0.9278237,0.000021003776,0.00037426062,0.024343051,0.00025205273],"about_ca_topic_score_codex":0.00021879752,"about_ca_topic_score_gemma":0.0000066840375,"teacher_disagreement_score":0.97127134,"about_ca_system_score_codex":0.00004456388,"about_ca_system_score_gemma":0.00004135212,"threshold_uncertainty_score":0.603559},"labels":[],"label_agreement":null},{"id":"W3195438473","doi":"10.1007/s10115-021-01605-0","title":"Model complexity of deep learning: a survey","year":2021,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":388,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Deep learning; Artificial intelligence; Generalization; Machine learning; Model selection; Game complexity; Process (computing); Computational complexity theory; Worst-case complexity; Algorithm; Mathematics","score_opus":0.041583257627835754,"score_gpt":0.2735118115492377,"score_spread":0.23192855392140194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3195438473","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012631256,0.0009045778,0.9428683,0.000047527432,0.00029970883,0.00007268301,0.00000530989,0.000089487454,0.043081157],"genre_scores_gemma":[0.99685,0.000030555246,0.0024038418,0.000020745088,0.000022091317,0.0000039247498,0.00003615395,0.0000021556582,0.0006305463],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991813,0.00018237272,0.00031092422,0.00009015535,0.00012929522,0.00010600536],"domain_scores_gemma":[0.99916124,0.00006477844,0.00014229344,0.0001814776,0.00039451342,0.00005568634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005991665,0.00007211404,0.00016366332,0.00007419771,0.00010060468,0.00014208801,0.00015826088,0.000041307245,0.000003398053],"category_scores_gemma":[0.0001253672,0.000064921376,0.000026768852,0.0002758492,0.00003075425,0.0010705983,0.00013201754,0.0001134388,0.000049228838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013659359,0.00015011561,0.02834709,0.0011793956,0.000080546415,0.0000024323756,0.035289586,0.05226162,0.00014987959,0.6317839,0.0020737287,0.24866806],"study_design_scores_gemma":[0.00018684646,0.000020853966,0.008182041,0.000021105827,0.0000013617857,0.00001474394,0.00011170683,0.97891015,0.00005589762,0.00009591159,0.012323055,0.0000763204],"about_ca_topic_score_codex":0.00006306011,"about_ca_topic_score_gemma":0.000015211937,"teacher_disagreement_score":0.9842187,"about_ca_system_score_codex":0.000010136056,"about_ca_system_score_gemma":0.000056467525,"threshold_uncertainty_score":0.2647417},"labels":[],"label_agreement":null},{"id":"W3215783632","doi":"10.1007/s10115-021-01625-w","title":"An integrated framework for diagnosing process faults with incomplete features","year":2021,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Missing data; Imputation (statistics); Pooling; Dimensionality reduction; Data mining; Computer science; Curse of dimensionality; Principal component analysis; Artificial intelligence; Pattern recognition (psychology); Machine learning","score_opus":0.007338811282059134,"score_gpt":0.2464068347811218,"score_spread":0.23906802349906267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215783632","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27873728,0.0062476452,0.6872438,0.00006731663,0.0034192428,0.0019076801,0.0001659515,0.0014950492,0.020716026],"genre_scores_gemma":[0.99899083,0.000026071724,0.00033270565,0.00003810148,0.00017974374,0.0002562989,0.00009600428,0.000015783302,0.000064436805],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931926,0.000029988169,0.0002990471,0.00009419529,0.00009847637,0.00015903226],"domain_scores_gemma":[0.99929875,0.000077368604,0.000058457335,0.00014460359,0.00033388945,0.00008695069],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012507237,0.00014351918,0.00020853303,0.00009683427,0.00012607718,0.00024255142,0.00006286699,0.00012068755,0.0000033580984],"category_scores_gemma":[0.000048059163,0.00011425667,0.000025322777,0.00026019258,0.000013480919,0.0012527896,0.0000048945494,0.00012083104,0.000019006362],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00089782436,0.00040474185,0.009732024,0.02947108,0.0015500702,0.000023876315,0.14012104,0.20745242,0.0038645666,0.10224212,0.021443214,0.48279703],"study_design_scores_gemma":[0.0015451316,0.00019588141,0.0015144707,0.0010320501,0.000031277188,0.0001610896,0.0140461,0.558716,0.002370368,0.00007141484,0.41981962,0.00049656344],"about_ca_topic_score_codex":0.000011433207,"about_ca_topic_score_gemma":0.000036238707,"teacher_disagreement_score":0.7202536,"about_ca_system_score_codex":0.000038941263,"about_ca_system_score_gemma":0.000036840363,"threshold_uncertainty_score":0.4659252},"labels":[],"label_agreement":null},{"id":"W4283720480","doi":"10.1007/s10115-022-01703-7","title":"BertHANK: hierarchical attention networks with enhanced knowledge and pre-trained model for answer selection","year":2022,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Selection (genetic algorithm); Computer science; Artificial intelligence; Machine learning; Model selection","score_opus":0.011614359370299665,"score_gpt":0.2366141620126121,"score_spread":0.22499980264231242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283720480","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032502398,0.0004255946,0.96374613,0.00005641778,0.00038691773,0.0006977399,0.0000056982954,0.00012264514,0.0020564867],"genre_scores_gemma":[0.9948586,0.000018347973,0.003514121,0.000043655476,0.00011528984,0.00042406892,0.000036078316,0.000007154095,0.0009826896],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898714,0.00007177509,0.0003634077,0.00021640914,0.00014501694,0.00021625908],"domain_scores_gemma":[0.9993695,0.000056199784,0.00013514464,0.0001671541,0.00019124428,0.00008074818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049298845,0.00013224383,0.00017075239,0.0001648278,0.00045981182,0.00020257232,0.00016637168,0.000059904076,0.0000012923012],"category_scores_gemma":[0.000010514304,0.00011730904,0.000029468603,0.00026870542,0.000020964384,0.0018490612,0.00014373158,0.0001467328,0.0000022743118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030412452,0.00020487646,0.0010682154,0.0010871091,0.00013011468,3.827309e-7,0.062539265,0.49063617,0.0007432767,0.20021237,0.0029366822,0.24013741],"study_design_scores_gemma":[0.000781659,0.00017632122,0.00032183048,0.00003053991,0.000008502134,0.000027516178,0.0001391786,0.9896848,0.000021463355,0.000095691954,0.008555933,0.00015653498],"about_ca_topic_score_codex":0.000007558683,"about_ca_topic_score_gemma":0.00001331407,"teacher_disagreement_score":0.9623562,"about_ca_system_score_codex":0.00006966907,"about_ca_system_score_gemma":0.000084873085,"threshold_uncertainty_score":0.4783724},"labels":[],"label_agreement":null},{"id":"W4310276756","doi":"10.1007/s10115-022-01792-4","title":"DNETC: dynamic network embedding preserving both triadic closure evolution and community structures","year":2022,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Sichuan Province Science and Technology Support Program; National Natural Science Foundation of China","keywords":"Computer science; Embedding; Closure (psychology); Dynamic network analysis; Focus (optics); Theoretical computer science; Social network (sociolinguistics); Artificial intelligence; Algorithm; Topology (electrical circuits); Mathematics","score_opus":0.0101272855086007,"score_gpt":0.2636848183653573,"score_spread":0.2535575328567566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310276756","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88450736,0.005339028,0.06252137,0.000034232326,0.00062837097,0.0010421188,0.00009816674,0.0002688195,0.045560565],"genre_scores_gemma":[0.9992148,0.000010774263,0.00010426508,0.000010713432,0.00018420411,0.000090373054,0.00020914998,0.000008003334,0.0001676961],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867475,0.00049369066,0.00041454664,0.00008833183,0.00013764201,0.00019104402],"domain_scores_gemma":[0.9992681,0.00011240504,0.00025069862,0.00024313135,0.000068006724,0.000057650697],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0009189199,0.00013671047,0.00023675608,0.00013361289,0.0013563087,0.00017972372,0.00016563735,0.000030642655,0.00007265012],"category_scores_gemma":[0.0000065864633,0.00013519992,0.00005148439,0.00030488966,0.000029067081,0.0008271933,0.00035688665,0.0003996407,0.000003054316],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017645351,0.00023875438,0.27924943,0.0010930046,0.0009572668,5.898127e-7,0.038642634,0.08806117,0.00012433152,0.41617808,0.0922626,0.08301569],"study_design_scores_gemma":[0.00086359924,0.00014587482,0.023470316,0.00009487736,0.000091759364,0.000011562044,0.010731151,0.768951,0.0000040635778,0.007873772,0.18735786,0.00040415276],"about_ca_topic_score_codex":0.00046846332,"about_ca_topic_score_gemma":0.000023071341,"teacher_disagreement_score":0.68088984,"about_ca_system_score_codex":0.0000808317,"about_ca_system_score_gemma":0.000032806038,"threshold_uncertainty_score":0.9999438},"labels":[],"label_agreement":null},{"id":"W4327590965","doi":"10.1007/s10115-023-01850-5","title":"Towards intelligent database systems using clusters of SQL transactions","year":2023,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Online transaction processing; Troubleshooting; Database transaction; Database; DBSCAN; Credit card; Cluster analysis; Transaction processing; Data mining; SQL; Overhead (engineering); Artificial intelligence; Operating system; World Wide Web","score_opus":0.036835463230279156,"score_gpt":0.2875389323398121,"score_spread":0.25070346910953295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327590965","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00288504,0.0010131479,0.9904703,0.000018685207,0.0020378574,0.0004087677,0.00016758271,0.00019241727,0.0028062284],"genre_scores_gemma":[0.99421364,0.0004996061,0.0043577845,0.000023468438,0.0001428978,0.00009123118,0.00015838446,0.000014085822,0.0004988835],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858093,0.00007776462,0.0007301868,0.00015509511,0.00023939299,0.00021664768],"domain_scores_gemma":[0.9988875,0.000057776764,0.0002551157,0.0004399391,0.00025340408,0.000106267405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005999601,0.00014679108,0.00027516502,0.00039722756,0.00017583482,0.00012456668,0.00021392954,0.000061051425,0.0000022173633],"category_scores_gemma":[0.000023827726,0.00012656285,0.00004866007,0.00079194835,0.00004606682,0.0050601205,0.000099920595,0.0000789009,0.00011105406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043168064,0.000111771835,0.00019409403,0.009815745,0.0002454618,0.000010487031,0.04949016,0.0645797,0.0017738708,0.76996964,0.006608514,0.09715738],"study_design_scores_gemma":[0.00022927503,0.000035056128,0.00003578181,0.00036494096,0.000008945668,0.00005656521,0.0036461502,0.7215192,0.0004878613,0.0000054411157,0.27343616,0.0001746366],"about_ca_topic_score_codex":0.0003169609,"about_ca_topic_score_gemma":0.000007248711,"teacher_disagreement_score":0.9913286,"about_ca_system_score_codex":0.00005852752,"about_ca_system_score_gemma":0.00010502799,"threshold_uncertainty_score":0.51610833},"labels":[],"label_agreement":null},{"id":"W4362589576","doi":"10.1007/s10115-023-01852-3","title":"Mining frequent generators and closures in data streams with FGC-Stream","year":2023,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Sliding window protocol; Data stream mining; Data mining; Exploit; Association rule learning; Factoring; Data stream; STREAMS; Window (computing); Computer security","score_opus":0.029363750963375318,"score_gpt":0.26678572819741725,"score_spread":0.23742197723404193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362589576","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8919629,0.0027783841,0.081416525,0.0006923502,0.0007899681,0.0010670408,0.0004584197,0.0007273995,0.020107029],"genre_scores_gemma":[0.9914883,0.00031438863,0.007079957,0.000049222162,0.00010757631,0.00009803703,0.0006304067,0.000007404275,0.00022474346],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992988,0.000021608605,0.0002578042,0.00017571659,0.00010693122,0.00013912132],"domain_scores_gemma":[0.9993071,0.000045746587,0.00007871075,0.00045444173,0.00005060718,0.00006339419],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036675463,0.00008717779,0.00011198671,0.00018275119,0.00010404996,0.00038856716,0.0003309895,0.000035576755,4.6124367e-7],"category_scores_gemma":[0.000014673173,0.00006802668,0.000004679357,0.00053168734,0.00002518972,0.002877244,0.00027972492,0.000047133948,0.00004466475],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004708584,0.000053033433,0.02238384,0.00033090124,0.000044312746,0.0000062126596,0.018920101,0.00020928118,0.00004159533,0.059866387,0.047246333,0.8508933],"study_design_scores_gemma":[0.00045894508,0.00004867652,0.0089167245,0.00014162694,0.000004690011,0.000030477206,0.0018512497,0.7736908,0.000044285178,0.00002026305,0.21460149,0.00019078961],"about_ca_topic_score_codex":0.00008655433,"about_ca_topic_score_gemma":0.000059274924,"teacher_disagreement_score":0.8507025,"about_ca_system_score_codex":0.0000118930375,"about_ca_system_score_gemma":0.0000478068,"threshold_uncertainty_score":0.37469622},"labels":[],"label_agreement":null},{"id":"W4393495083","doi":"10.1007/s10115-023-02059-2","title":"Entity linking for English and other languages: a survey","year":2024,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"Aston University; UK Research and Innovation","keywords":"Linguistics; Computer science; Philosophy","score_opus":0.01679273697061635,"score_gpt":0.2900945133550044,"score_spread":0.2733017763843881,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393495083","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003612732,0.04636523,0.93946886,0.000031461404,0.0010699444,0.0004782833,0.000044392862,0.0010466444,0.007882447],"genre_scores_gemma":[0.9897726,0.000044240936,0.009534892,0.00009565432,0.00018890701,0.000051087416,0.000020718553,0.0000061831956,0.0002856861],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99951595,0.000034253757,0.00018231964,0.00010232157,0.00006820145,0.000096944066],"domain_scores_gemma":[0.99951696,0.00012793418,0.000042242173,0.000111541834,0.00016884472,0.000032477732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007712821,0.00007203638,0.00009169969,0.00013227627,0.00007264192,0.0010066362,0.00014095094,0.00006208267,6.194182e-7],"category_scores_gemma":[0.000105752355,0.00005661626,0.000015815052,0.00018102331,0.000014211676,0.002468397,0.00008105247,0.00006489334,0.000009971779],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007840554,0.000014192734,0.0021436918,0.004331892,0.000043876877,0.0000013383388,0.06177007,0.0000011002095,0.000097199336,0.6459214,0.011489091,0.27417827],"study_design_scores_gemma":[0.00027374495,0.00006683164,0.00036153698,0.0008393017,0.000008591958,0.000028993922,0.0004774955,0.12730518,0.0007144854,0.0011770925,0.868441,0.00030577238],"about_ca_topic_score_codex":0.000054342465,"about_ca_topic_score_gemma":0.00001636297,"teacher_disagreement_score":0.9861599,"about_ca_system_score_codex":0.000017054714,"about_ca_system_score_gemma":0.000029919129,"threshold_uncertainty_score":0.97070163},"labels":[],"label_agreement":null},{"id":"W4401314125","doi":"10.1007/s10115-024-02185-5","title":"An efficient approach for incremental erasable utility pattern mining from non-binary data","year":2024,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Research Foundation of Korea","keywords":"Computer science; Data mining; Binary number; Task (project management); Database; Mathematics","score_opus":0.04000251640079476,"score_gpt":0.2932303513575283,"score_spread":0.2532278349567335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401314125","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012903292,0.0005620196,0.981371,0.000025020605,0.00047252668,0.00042163074,0.00094181625,0.00014857393,0.003154115],"genre_scores_gemma":[0.96179014,0.000009941516,0.033789653,0.000035407807,0.00019461692,0.00014899675,0.0039813207,0.000005803885,0.00004408957],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990606,0.000023762186,0.00033621103,0.00030353502,0.00012400988,0.00015188803],"domain_scores_gemma":[0.9989662,0.00006838563,0.00006055477,0.0007577364,0.00006678774,0.00008029424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063383416,0.00010581624,0.00012384838,0.00008727199,0.00019357624,0.0009998335,0.0006926324,0.00004757532,0.0000024845067],"category_scores_gemma":[0.000008231741,0.000091734364,0.000017757402,0.00019816759,0.000016985747,0.0037009066,0.0003378471,0.000057409216,0.000052456326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000069700022,0.000261807,0.0006352159,0.001006762,0.00008180913,7.69647e-7,0.01899321,0.0006595673,0.00017417541,0.0052044503,0.06117845,0.9117968],"study_design_scores_gemma":[0.00015318673,0.00003204916,0.0004150676,0.00005873292,0.000007185976,0.000003854664,0.0007827266,0.92117625,0.000028289469,0.0000038815456,0.07723146,0.00010733682],"about_ca_topic_score_codex":0.00015635656,"about_ca_topic_score_gemma":0.000001921347,"teacher_disagreement_score":0.9488869,"about_ca_system_score_codex":0.000024177361,"about_ca_system_score_gemma":0.00006183321,"threshold_uncertainty_score":0.96414167},"labels":[],"label_agreement":null},{"id":"W4401504220","doi":"10.1007/s10115-024-02196-2","title":"MoRGH: movie recommender system using GNNs on heterogeneous graphs","year":2024,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Recommender system; Computer science; Artificial intelligence; Information retrieval","score_opus":0.028685631643001173,"score_gpt":0.2700012999917217,"score_spread":0.2413156683487205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401504220","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0069055213,0.009681795,0.8126011,0.00024092197,0.009409234,0.0013213125,0.000032389355,0.002887,0.15692072],"genre_scores_gemma":[0.9987868,0.00009034607,0.0006519181,0.00009474388,0.00014108697,0.0000736686,0.000008197274,0.000012988142,0.00014024763],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851704,0.00011865433,0.0006464215,0.00024901427,0.00021020448,0.00025864856],"domain_scores_gemma":[0.99911743,0.000075261574,0.00012983914,0.0004365519,0.000121803794,0.00011909507],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00060213014,0.00022259963,0.00027463483,0.0005018184,0.00020462956,0.0012140154,0.00032822657,0.00012869995,0.0000021887986],"category_scores_gemma":[0.000006060336,0.00017786551,0.000091464215,0.00044442006,0.000016020975,0.002277893,0.00013335315,0.00014303134,0.00020324638],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004276653,0.0000241425,0.00007311792,0.002334377,0.00011075248,0.000015311753,0.0048632505,0.00016433069,0.00005371366,0.90816766,0.018284999,0.06590405],"study_design_scores_gemma":[0.00016467433,0.00010873954,0.000017479406,0.00103952,0.000010240876,0.00053317903,0.00036230058,0.5897221,0.0003946316,0.000169403,0.40717107,0.00030666174],"about_ca_topic_score_codex":0.000076730044,"about_ca_topic_score_gemma":0.0000019567779,"teacher_disagreement_score":0.9918813,"about_ca_system_score_codex":0.0001565721,"about_ca_system_score_gemma":0.00005747311,"threshold_uncertainty_score":0.9998228},"labels":[],"label_agreement":null},{"id":"W4402322874","doi":"10.1007/s10115-024-02204-5","title":"CAERS-CF: enhancing convolutional autoencoder recommendations through collaborative filtering","year":2024,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Autoencoder; Collaborative filtering; Computer science; Artificial intelligence; Convolutional neural network; Pattern recognition (psychology); Information retrieval; Recommender system; Deep learning","score_opus":0.017814532704902904,"score_gpt":0.28284898012906495,"score_spread":0.26503444742416205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402322874","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011787167,0.0033815121,0.90791714,0.00071073155,0.002537665,0.00034517792,0.000027875456,0.0005727584,0.08438929],"genre_scores_gemma":[0.9742167,0.0005348549,0.022592805,0.00024147188,0.00035852424,0.000349336,0.00008269637,0.0000144172855,0.0016091736],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988321,0.000083669795,0.00056621927,0.00018410484,0.00014634612,0.00018753092],"domain_scores_gemma":[0.99924964,0.000115563525,0.00011077514,0.00021231598,0.00025214933,0.000059554266],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004947559,0.00014664681,0.00018784693,0.00020370472,0.0002499555,0.0010472751,0.00020991713,0.000082818864,0.000012986287],"category_scores_gemma":[0.00001891511,0.00012706837,0.00004108694,0.00052672223,0.000023768827,0.0076558646,0.00013439181,0.0001223911,0.00020771199],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013293828,0.000013465894,0.000026520478,0.00047186716,0.000057772893,0.0000014727739,0.026022272,0.000024591658,0.00017207717,0.85681474,0.09706585,0.01932805],"study_design_scores_gemma":[0.000103671075,0.000036214806,0.000034560337,0.00038718482,0.0000038865296,0.00005423609,0.0009616122,0.12338478,0.00061148603,0.00041251013,0.8738451,0.00016476998],"about_ca_topic_score_codex":0.00006379466,"about_ca_topic_score_gemma":0.000014307899,"teacher_disagreement_score":0.97409886,"about_ca_system_score_codex":0.000115890696,"about_ca_system_score_gemma":0.00016926682,"threshold_uncertainty_score":0.99998975},"labels":[],"label_agreement":null},{"id":"W4403155837","doi":"10.1007/s10115-024-02248-7","title":"Deep-transfer learning inspired natural language processing system for software requirements classification","year":2024,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Software Engineering Research","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Artificial intelligence; Transfer of learning; Natural language processing; Natural language; Deep learning; Software; Machine learning; Programming language","score_opus":0.0214657515274903,"score_gpt":0.28490399424704965,"score_spread":0.26343824271955935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403155837","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008455609,0.010835942,0.97714335,0.000024596837,0.0012167152,0.0005214913,0.0000028460495,0.0012035738,0.0005958852],"genre_scores_gemma":[0.99810797,0.000012133232,0.0012422131,0.0000060820266,0.00012905376,0.00019053207,0.000042696232,0.000011382222,0.0002579631],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898595,0.000037787504,0.0003489505,0.0001764781,0.0002308023,0.0002200131],"domain_scores_gemma":[0.99929774,0.0001959907,0.00003450254,0.00016146222,0.0002454995,0.00006483099],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005678132,0.000120402954,0.0001302432,0.00029503458,0.00018683611,0.0010034281,0.00023700121,0.00007431435,4.5801056e-7],"category_scores_gemma":[0.00017605668,0.0001051185,0.000036538524,0.00043092575,0.000014287664,0.0039119413,0.000050946317,0.00015268286,0.0000799563],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014150649,0.000016079912,0.0011227824,0.016852908,0.0000636144,0.0000035944865,0.040526416,0.0010322055,0.0010061844,0.023699628,0.0006896933,0.9149727],"study_design_scores_gemma":[0.00022749526,0.000034915833,0.00082868506,0.0006516851,0.000005598744,0.000023199023,0.0010542738,0.9650781,0.00018619848,0.0000015683672,0.031765122,0.00014317107],"about_ca_topic_score_codex":0.0000054168218,"about_ca_topic_score_gemma":7.8753493e-7,"teacher_disagreement_score":0.98965234,"about_ca_system_score_codex":0.00016097326,"about_ca_system_score_gemma":0.000087621935,"threshold_uncertainty_score":0.967608},"labels":[],"label_agreement":null},{"id":"W4404366193","doi":"10.1007/s10115-024-02269-2","title":"An evidence-based approach for open-domain question answering","year":2024,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Topic Modeling","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Question answering; Information retrieval; Relevance (law); Open domain; Benchmark (surveying); Context (archaeology); Graph; Construct (python library); Domain (mathematical analysis); Rank (graph theory); Knowledge graph; Artificial intelligence; Natural language processing; Theoretical computer science","score_opus":0.05172166446128868,"score_gpt":0.3110074057323632,"score_spread":0.2592857412710745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404366193","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010022159,0.0023447894,0.99084175,0.00008856031,0.00066749577,0.00063306565,0.0000031356851,0.00019508081,0.0042238925],"genre_scores_gemma":[0.9469354,0.000017379978,0.052478552,0.00006478777,0.0001597361,0.00022803455,0.000022509857,0.000004807296,0.000088775916],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992369,0.000059445232,0.0003044223,0.00017079273,0.00010251743,0.00012592989],"domain_scores_gemma":[0.99942803,0.00007041746,0.000050193234,0.00026820705,0.00011829707,0.00006486161],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0012104555,0.0000856109,0.00011008974,0.00014972597,0.00011963124,0.0018458441,0.0004273066,0.000054262026,5.0965997e-7],"category_scores_gemma":[0.000025129064,0.00007362427,0.000022189031,0.00019365533,0.000009383433,0.011280534,0.00007504325,0.000052240244,0.00001958499],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010094649,0.00002391847,0.00010134045,0.0019369846,0.000011895087,3.7922646e-7,0.007864183,0.009213188,0.00023629362,0.81852055,0.00090555666,0.16117561],"study_design_scores_gemma":[0.0001488222,0.000057019708,0.000028171648,0.0003197317,0.0000024589326,0.0000069867096,0.00018198314,0.95176196,0.00010581171,0.00017187702,0.047116302,0.000098859506],"about_ca_topic_score_codex":0.000028488292,"about_ca_topic_score_gemma":9.4577626e-7,"teacher_disagreement_score":0.9459332,"about_ca_system_score_codex":0.0000527654,"about_ca_system_score_gemma":0.00010999387,"threshold_uncertainty_score":0.99919033},"labels":[],"label_agreement":null},{"id":"W4404447912","doi":"10.1007/s10115-024-02282-5","title":"Quantum computing and quantum-inspired techniques for feature subset selection: a review","year":2024,"lang":"en","type":"review","venue":"Knowledge and Information Systems","topic":"Quantum Computing Algorithms and Architecture","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Feature selection; Quantum; Feature (linguistics); Computer science; Quantum computer; Selection (genetic algorithm); Artificial intelligence; Quantum machine learning; Theoretical computer science; Pattern recognition (psychology); Physics; Quantum mechanics","score_opus":0.023840847655537144,"score_gpt":0.31531260652412096,"score_spread":0.29147175886858384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404447912","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.5131986e-7,0.9242911,0.07131718,0.00012120253,0.0011442302,0.0020501118,0.0000697327,0.00062185334,0.0003841795],"genre_scores_gemma":[0.000017687784,0.9960237,0.00277803,0.000135899,0.0005596746,0.00018717397,0.00016306131,0.000029461145,0.00010528092],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976296,0.00018099824,0.0011220683,0.0004866306,0.00021394188,0.00036678318],"domain_scores_gemma":[0.99833816,0.00022737276,0.0006225963,0.00037780762,0.00029042698,0.00014365769],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011875598,0.0005695162,0.0016030072,0.00047562463,0.00036990474,0.0009858372,0.0004971641,0.00035663036,3.6119488e-7],"category_scores_gemma":[0.00006679343,0.0004045129,0.00029033658,0.0009457907,0.00004155964,0.0009526941,0.00036175453,0.00053730485,0.00004138896],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.765753e-7,0.0000062714853,1.5756054e-7,0.13445729,0.000057367844,8.2510195e-7,0.00040879223,6.9876563e-7,3.5519204e-8,0.018878553,0.02793827,0.81825125],"study_design_scores_gemma":[0.000066276014,0.000093923045,3.4343546e-7,0.06216473,0.00017717342,0.00048740703,0.000009318413,0.18678504,2.2969822e-7,0.000053270716,0.7498036,0.00035867374],"about_ca_topic_score_codex":0.0000069053312,"about_ca_topic_score_gemma":8.403733e-7,"teacher_disagreement_score":0.8178926,"about_ca_system_score_codex":0.00007173961,"about_ca_system_score_gemma":0.0002510406,"threshold_uncertainty_score":0.9998407},"labels":[],"label_agreement":null},{"id":"W4405700372","doi":"10.1007/s10115-024-02308-y","title":"Building a comprehensive and multi-dimensional information security ontology: elicitation process and OWL implementation","year":2024,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Information and Cyber Security","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; OWL-S; Ontology; Process (computing); Web Ontology Language; Information retrieval; Semantic Web; Semantic Web Stack; Programming language","score_opus":0.013764161713108507,"score_gpt":0.30792314758786826,"score_spread":0.29415898587475975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405700372","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6229615,0.0052466616,0.3610626,0.000910518,0.0020623459,0.0018236662,0.00008113305,0.0007392739,0.0051122718],"genre_scores_gemma":[0.9977918,0.0000970485,0.0016049561,0.00031503534,0.00003659649,0.0000539388,0.00008931937,0.0000033117442,0.000007944321],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987914,0.000061776795,0.0006099982,0.00014028257,0.00021027461,0.00018629838],"domain_scores_gemma":[0.9990923,0.00008257127,0.00017462244,0.00011673831,0.00042877675,0.00010498565],"candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.00040107663,0.0001681306,0.00017337801,0.0004027411,0.00027803777,0.0010480105,0.00010520488,0.000102608676,0.0000031701509],"category_scores_gemma":[0.00002216056,0.00015159366,0.000022235898,0.00031528025,0.0000502694,0.016410911,0.00011519149,0.00013874233,0.000058415433],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013852644,0.000018016699,0.00044992322,0.0021736014,0.000052924745,8.608658e-7,0.13411966,0.000057870417,0.000053897642,0.6853027,0.001800793,0.17595592],"study_design_scores_gemma":[0.0009806078,0.00007852199,0.006818501,0.0001714774,0.000014582435,0.00017439407,0.004943731,0.87566745,0.00015223079,0.0008217476,0.10988759,0.00028915808],"about_ca_topic_score_codex":0.000063690524,"about_ca_topic_score_gemma":0.000016861184,"teacher_disagreement_score":0.8756096,"about_ca_system_score_codex":0.000048328722,"about_ca_system_score_gemma":0.00008855703,"threshold_uncertainty_score":0.999989},"labels":[],"label_agreement":null},{"id":"W4406070280","doi":"10.1007/s10115-024-02321-1","title":"Fake news detection: comparative evaluation of BERT-like models and large language models with generative AI-annotated data","year":2025,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":43,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; Vector Institute","funders":"","keywords":"Computer science; Generative grammar; Language model; Fake news; Artificial intelligence; Natural language processing; Generative model; Information retrieval","score_opus":0.1036317786528191,"score_gpt":0.3879677179702772,"score_spread":0.2843359393174581,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406070280","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17312394,0.0036180723,0.2474,0.00032020052,0.0006045795,0.0025196446,0.00030670702,0.00012588759,0.57198095],"genre_scores_gemma":[0.9988016,0.00013548002,0.00007013625,0.00017867137,0.000037871203,0.0000179741,0.0001871253,0.0000025743682,0.000568554],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858916,0.00026798592,0.00045704297,0.0001150184,0.00040942908,0.0001613891],"domain_scores_gemma":[0.99843377,0.00005632556,0.0002415698,0.00023148056,0.0009519738,0.000084867905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015649728,0.00011864428,0.00023073603,0.00022914793,0.00038442592,0.000235608,0.0001335461,0.000092295624,0.000013423259],"category_scores_gemma":[0.000060848688,0.000094919866,0.0000137339275,0.00045919922,0.00009327559,0.0076462803,0.000065908884,0.00008607855,0.000010227973],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010182446,0.000060548973,0.000087078406,0.00030832106,0.00015985043,1.043115e-7,0.81934494,0.008169045,0.00002971821,0.12292698,0.010105977,0.0387056],"study_design_scores_gemma":[0.0011512032,0.00003690513,0.00013330346,0.00011439004,0.000050343617,0.0000015586393,0.1116527,0.85436285,0.0000923136,0.00018998428,0.03209783,0.00011661952],"about_ca_topic_score_codex":0.0006241133,"about_ca_topic_score_gemma":0.002479651,"teacher_disagreement_score":0.8461938,"about_ca_system_score_codex":0.00007114086,"about_ca_system_score_gemma":0.00036297616,"threshold_uncertainty_score":0.5543369},"labels":[],"label_agreement":null},{"id":"W4406711870","doi":"10.1007/s10115-025-02338-0","title":"Unlocking wisdom: enhancing biomedical question answering with domain knowledge","year":2025,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Question answering; Domain (mathematical analysis); Computer science; Information retrieval; Domain knowledge; Data science; Knowledge management; Mathematics","score_opus":0.007620119195518866,"score_gpt":0.24825661733302845,"score_spread":0.2406364981375096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406711870","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015041825,0.0012130084,0.9452497,0.0001387915,0.000990955,0.00024075928,8.372139e-7,0.00021704452,0.036907073],"genre_scores_gemma":[0.99403775,0.00002432292,0.005339477,0.00005335662,0.000117263065,0.000039812676,0.0000073608026,0.000004064561,0.0003765686],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885774,0.00007750055,0.0004948245,0.0001873089,0.00015750252,0.00022513785],"domain_scores_gemma":[0.9992308,0.00007524601,0.00011680394,0.00029542425,0.00019574311,0.000085968844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007678481,0.00014221703,0.0001965296,0.00038582337,0.00021819833,0.0003465538,0.00027263377,0.00009518193,9.797824e-7],"category_scores_gemma":[0.00003362226,0.000116906485,0.00002304333,0.0005845396,0.000040762614,0.0026449568,0.00016825451,0.00012880036,0.000056909503],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014553037,0.00005742777,0.00091334636,0.0013826238,0.00006105044,0.0000026454577,0.0275071,0.0004173287,0.0009601196,0.78332525,0.000966062,0.1843925],"study_design_scores_gemma":[0.0011519918,0.000095882126,0.00053005666,0.0017009428,0.000012954393,0.000059983053,0.0017576998,0.5850967,0.0008149694,0.00041055537,0.40799952,0.0003687305],"about_ca_topic_score_codex":0.00003391446,"about_ca_topic_score_gemma":0.00001734103,"teacher_disagreement_score":0.9789959,"about_ca_system_score_codex":0.00010288748,"about_ca_system_score_gemma":0.00017013437,"threshold_uncertainty_score":0.4767308},"labels":[],"label_agreement":null},{"id":"W4407052498","doi":"10.1007/s10115-025-02346-0","title":"A novel contrastive multi-view framework for heterogeneous graph embedding","year":2025,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Royal University","funders":"","keywords":"Embedding; Computer science; Graph; Theoretical computer science; Artificial intelligence; Mathematics; Natural language processing","score_opus":0.0197432400307529,"score_gpt":0.30193892668569033,"score_spread":0.28219568665493744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407052498","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002531213,0.0051515726,0.9916275,0.00005459028,0.0013384133,0.0007279244,0.000011772289,0.00014337208,0.0006916898],"genre_scores_gemma":[0.86416775,0.00043286275,0.13391168,0.000715573,0.0001220777,0.00046088532,0.000017576212,0.000009995875,0.0001615923],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906117,0.000025142333,0.00042876953,0.000172337,0.00007896562,0.00023362407],"domain_scores_gemma":[0.998983,0.00029429304,0.00016012327,0.00023730363,0.0002585853,0.0000666575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019683059,0.00015028575,0.00022994798,0.00020626844,0.00021615658,0.00026327776,0.00027986386,0.00010799844,3.2569844e-7],"category_scores_gemma":[0.00006502746,0.00013246223,0.0000692569,0.0004898693,0.00003212758,0.0018871243,0.00010592327,0.000109955734,0.000012865938],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018001432,0.000043046683,0.000083029205,0.00045658599,0.000063851694,4.0808075e-7,0.0023318366,0.004409906,0.00007815482,0.8781603,0.0010222853,0.11333257],"study_design_scores_gemma":[0.0011267189,0.00006602984,0.00016941893,0.0006731154,0.000010095903,0.000026941625,0.00014590951,0.83796906,0.00023105569,0.0026074587,0.15671194,0.00026228212],"about_ca_topic_score_codex":0.0000021567387,"about_ca_topic_score_gemma":0.0000014029523,"teacher_disagreement_score":0.87555283,"about_ca_system_score_codex":0.000028879926,"about_ca_system_score_gemma":0.000027983255,"threshold_uncertainty_score":0.5401653},"labels":[],"label_agreement":null},{"id":"W4408468809","doi":"10.1007/s10115-025-02373-x","title":"Integrated deep learning and blockchain-based framework for cloud manufacturing with improved customer satisfaction","year":2025,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Digital Transformation in Industry","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Blockchain; Customer satisfaction; Cloud computing; Deep learning; Computer science; Artificial intelligence; Cloud manufacturing; Data science; Business; Marketing; Computer security","score_opus":0.0062192971478256314,"score_gpt":0.21846607383437658,"score_spread":0.21224677668655095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408468809","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22844613,0.0006737212,0.70701236,0.000032596003,0.0012463657,0.001122697,0.000029072926,0.000668252,0.06076881],"genre_scores_gemma":[0.99895936,0.000018440045,0.0006239397,0.000019987103,0.000048182672,0.00014494863,0.00003102547,0.000011890459,0.00014222528],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99935,0.000013181987,0.00034289274,0.00007385747,0.000063259555,0.00015676934],"domain_scores_gemma":[0.99958205,0.00012512109,0.000058479596,0.00007169262,0.00010955153,0.000053107222],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013802286,0.00015321681,0.00016149977,0.00023747138,0.00013211684,0.00022998788,0.00003564937,0.00016428219,0.000004053723],"category_scores_gemma":[0.00002423538,0.00013258486,0.000020166639,0.00016656399,0.000026064039,0.0005366375,0.000006848452,0.00022284899,0.000013626341],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000265281,0.000030117239,0.0070488895,0.011552679,0.00045858114,4.6785078e-7,0.008587221,0.18189952,0.00024964142,0.044746675,0.0013944661,0.7437665],"study_design_scores_gemma":[0.0013133754,0.00007399737,0.0010056357,0.0008171621,0.000036348178,0.00000782268,0.004343882,0.74130666,0.003642228,0.00006330495,0.24705407,0.00033550314],"about_ca_topic_score_codex":0.000009020987,"about_ca_topic_score_gemma":0.0000065396107,"teacher_disagreement_score":0.77051324,"about_ca_system_score_codex":0.000071789116,"about_ca_system_score_gemma":0.000022900287,"threshold_uncertainty_score":0.5406654},"labels":[],"label_agreement":null},{"id":"W4409393577","doi":"10.1007/s10115-025-02389-3","title":"Atom search optimization: a systematic review of current variants and applications","year":2025,"lang":"en","type":"review","venue":"Knowledge and Information Systems","topic":"Metaheuristic Optimization Algorithms Research","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Current (fluid); Computer science; Atom (system on chip); Algorithm; Theoretical computer science; Mathematics; Engineering; Parallel computing; Electrical engineering","score_opus":0.04351094629363648,"score_gpt":0.3644960439534498,"score_spread":0.3209850976598133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409393577","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.6318981e-10,0.5221266,0.47189298,0.000005091087,0.00014535288,0.0030489168,0.000037159818,0.000031579657,0.0027122989],"genre_scores_gemma":[1.0856919e-7,0.9941581,0.0037018117,0.000016000471,0.00004653805,0.0015529657,0.0001622167,0.00000875373,0.00035352272],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.99616337,0.0006953427,0.0021207419,0.00030754233,0.00049692584,0.00021607314],"domain_scores_gemma":[0.99630684,0.0005764286,0.0008623727,0.00088312436,0.0012103046,0.00016094305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019730628,0.00031301653,0.0020036274,0.00083125866,0.00015217585,0.00038852452,0.00079058245,0.00015515044,0.000008359215],"category_scores_gemma":[0.00032307918,0.0002426614,0.00013317943,0.0018803718,0.000058753834,0.0013501978,0.0005388192,0.00024236285,0.000080370024],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.2435163e-7,0.00001510846,6.420402e-8,0.81315166,0.000046624296,9.968296e-8,0.00008158216,0.000024141675,3.446734e-10,0.035524398,0.0003368447,0.15081939],"study_design_scores_gemma":[0.000083677056,0.000010410522,4.9542496e-8,0.48568586,0.00021220035,0.000032337677,0.000010029978,0.051349387,1.8244647e-8,0.0000026990574,0.46246338,0.00014996719],"about_ca_topic_score_codex":0.000002164479,"about_ca_topic_score_gemma":5.994736e-8,"teacher_disagreement_score":0.47203147,"about_ca_system_score_codex":0.00007775316,"about_ca_system_score_gemma":0.00086639187,"threshold_uncertainty_score":0.98954445},"labels":[],"label_agreement":null},{"id":"W4409602824","doi":"10.1007/s10115-025-02408-3","title":"Convolution neural network-AlexNet with gazelle optimization algorithm-based software defect prediction","year":2025,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Software Engineering Research","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Artificial neural network; Software; Convolution (computer science); Convolutional neural network; Algorithm; Artificial intelligence; Pattern recognition (psychology); Data mining; Machine learning","score_opus":0.006693307644077392,"score_gpt":0.21677554290158868,"score_spread":0.2100822352575113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409602824","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006839642,0.0009836253,0.99536085,0.000033101976,0.0008464536,0.00044766776,0.000008153954,0.0005282106,0.0011079919],"genre_scores_gemma":[0.9340183,0.00006160816,0.06444283,0.00013133229,0.0002635918,0.00029008763,0.00026624213,0.000017029806,0.000508962],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900675,0.00007151429,0.00030694946,0.00016394646,0.00021305494,0.0002377603],"domain_scores_gemma":[0.99896663,0.00023118785,0.00008367301,0.00027670054,0.00037121776,0.00007055845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004200017,0.00013289489,0.00014475088,0.00028426075,0.00020387165,0.00033442688,0.00020623935,0.00009143025,0.0000022957843],"category_scores_gemma":[0.00010641892,0.00011603496,0.000030351232,0.00082765496,0.000030451627,0.0022757885,0.00007258312,0.00012438763,0.000023268394],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010576972,0.0000140492275,0.0075857565,0.00023509082,0.000024040219,4.6976436e-7,0.0002581075,0.9592556,7.6361175e-7,0.001684281,0.0052916235,0.025639655],"study_design_scores_gemma":[0.000609028,0.00009519563,0.0045866286,0.00015693778,0.000007622621,0.000009241045,0.000018405686,0.9815416,0.00001476256,0.000006366156,0.012847038,0.00010722694],"about_ca_topic_score_codex":0.000015665808,"about_ca_topic_score_gemma":0.0000013678708,"teacher_disagreement_score":0.93333435,"about_ca_system_score_codex":0.00010533441,"about_ca_system_score_gemma":0.00014268291,"threshold_uncertainty_score":0.4731768},"labels":[],"label_agreement":null},{"id":"W4409677710","doi":"10.1007/s10115-025-02381-x","title":"A Bayesian hierarchical model for orthogonal Tucker decomposition with oblivious tensor compression","year":2025,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Tensor decomposition and applications","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Tucker decomposition; Tensor decomposition; Decomposition; Compression (physics); Tensor (intrinsic definition); Bayesian probability; Mathematics; Computer science; Artificial intelligence; Algorithm; Pattern recognition (psychology); Pure mathematics; Chemistry; Physics","score_opus":0.022339431200952747,"score_gpt":0.32378291151621913,"score_spread":0.30144348031526635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409677710","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026341474,0.000095425436,0.95416147,0.0004073281,0.000092335395,0.00110456,0.0000868695,0.00015652912,0.017553987],"genre_scores_gemma":[0.98977023,0.000010629544,0.007997139,0.00018321132,0.00004527226,0.0005013629,0.00013958229,0.000010093548,0.001342463],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906915,0.000036794678,0.00047353326,0.00013609856,0.00012067453,0.00016372457],"domain_scores_gemma":[0.999095,0.00016421107,0.00014271503,0.00019169367,0.00032159087,0.00008479263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017944587,0.00014772416,0.00022977252,0.00021540927,0.00030310257,0.0001423012,0.00009018325,0.00009999698,0.0000043284654],"category_scores_gemma":[0.000021820488,0.00011346453,0.00005160233,0.00018622029,0.000045061694,0.00061504904,0.000031470292,0.000102420505,0.000019925188],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017817535,0.00019027399,0.00024967958,0.00086336234,0.00006498961,1.9566343e-7,0.0019867462,0.0006843399,0.00028484597,0.963722,0.02507124,0.0067041456],"study_design_scores_gemma":[0.0013768254,0.000055569235,0.000440285,0.00032990024,0.00005118426,0.000026355308,0.00022383576,0.953728,0.00008766598,0.009869594,0.033627175,0.00018361578],"about_ca_topic_score_codex":0.000002157563,"about_ca_topic_score_gemma":0.000005205286,"teacher_disagreement_score":0.9634288,"about_ca_system_score_codex":0.00003977707,"about_ca_system_score_gemma":0.00006752692,"threshold_uncertainty_score":0.4626949},"labels":[],"label_agreement":null},{"id":"W4410692212","doi":"10.1007/s10115-025-02417-2","title":"Providing and evaluating a model for big data anonymization streams by using in-memory processing","year":2025,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Regional Municipality of Niagara","funders":"","keywords":"Computer science; Big data; Data stream mining; Data mining; STREAMS; Data anonymization; Data science; Artificial intelligence; Information privacy; Computer security","score_opus":0.10863723861002288,"score_gpt":0.3474931435090034,"score_spread":0.2388559048989805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410692212","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0137854675,0.0022032508,0.9817787,0.0002704536,0.0002761521,0.00066108437,0.00004025012,0.00016430912,0.00082032743],"genre_scores_gemma":[0.9350904,0.000073262025,0.064434424,0.00005560295,0.000041292507,0.00008479782,0.00015535965,0.0000064524997,0.000058405665],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989764,0.00003562296,0.00044457804,0.00025219296,0.00011603474,0.00017518482],"domain_scores_gemma":[0.99808115,0.00008960612,0.00019325473,0.0014488369,0.0001634238,0.000023726892],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0011136938,0.0001096266,0.000155299,0.00030218574,0.00020500072,0.0005631141,0.0026745934,0.00009387461,4.2081833e-8],"category_scores_gemma":[0.0031945582,0.00010523479,0.0000070183432,0.00046969447,0.000030225588,0.0065684095,0.010181382,0.000079675665,5.810193e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000069674425,0.00001851442,0.0005657072,0.0015440322,0.000009304968,7.209192e-8,0.0015881582,0.0012483979,0.00051005185,0.0009782285,0.012776799,0.9807538],"study_design_scores_gemma":[0.0004393176,0.0000131917295,0.000013246414,0.0004547363,0.000006127083,0.0000029322764,0.00032409362,0.9961186,0.00016875689,0.0011118482,0.0012389355,0.00010819492],"about_ca_topic_score_codex":0.000024519393,"about_ca_topic_score_gemma":0.000006695203,"teacher_disagreement_score":0.99487025,"about_ca_system_score_codex":0.00007685055,"about_ca_system_score_gemma":0.00021623014,"threshold_uncertainty_score":0.9978241},"labels":[],"label_agreement":null},{"id":"W4411073803","doi":"10.1007/s10115-025-02479-2","title":"A new privacy-preserving approach for publishing periodical reporting systems data","year":2025,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nipissing University","funders":"National Natural Science Foundation of China","keywords":"Data publishing; Computer science; Publishing; Information privacy; Data science; Information retrieval; Internet privacy; Data mining; World Wide Web; Political science","score_opus":0.07142405149752376,"score_gpt":0.31387815178908424,"score_spread":0.24245410029156048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411073803","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002228649,0.0032758862,0.96026033,0.002771263,0.0015168642,0.0010237063,0.00004937393,0.00086041505,0.0300193],"genre_scores_gemma":[0.37743482,0.00013522361,0.6181165,0.0002588398,0.00064218673,0.00050015136,0.0013556121,0.000029723964,0.0015269706],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99677294,0.00009036885,0.0018009316,0.00055537693,0.00034022384,0.00044012847],"domain_scores_gemma":[0.9877782,0.00031338024,0.0012523466,0.010087573,0.00042573974,0.00014276698],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.003961612,0.00022547592,0.00043440177,0.00048834586,0.00052651414,0.008718552,0.024121825,0.0002814733,8.968986e-7],"category_scores_gemma":[0.06828947,0.00020281695,0.000047127338,0.00091989525,0.000054079184,0.024714524,0.08166124,0.00031542906,0.000010363783],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000055319497,0.000016446738,0.0006677669,0.0014562325,0.000049725684,6.285777e-7,0.0008098877,0.000041125764,0.000012790081,0.04714648,0.9037761,0.046017293],"study_design_scores_gemma":[0.00032417788,0.000012612128,0.00009904303,0.00024048293,0.000008338189,0.000029778887,0.0004992575,0.64944595,0.000015386946,0.0008812241,0.34829524,0.00014850317],"about_ca_topic_score_codex":0.0002600306,"about_ca_topic_score_gemma":0.0000028451416,"teacher_disagreement_score":0.6494048,"about_ca_system_score_codex":0.000115386254,"about_ca_system_score_gemma":0.0005704598,"threshold_uncertainty_score":0.99231046},"labels":[],"label_agreement":null},{"id":"W4413243437","doi":"10.1007/s10115-025-02553-9","title":"Light spectral-based graph convolutional networks: optimizing ranking and longtail awareness for e-commerce recommendation systems","year":2025,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Recommender system; Graph; Ranking (information retrieval); Information retrieval; Theoretical computer science; Artificial intelligence; Data mining","score_opus":0.016379129920057144,"score_gpt":0.2629572443075103,"score_spread":0.24657811438745314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413243437","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00035913856,0.0027786824,0.9830283,0.0006038444,0.00216227,0.0010590095,0.000009349645,0.00028072955,0.00971867],"genre_scores_gemma":[0.99514604,0.00017827612,0.003469082,0.00022962788,0.00017270277,0.000508976,0.00009537396,0.000009792125,0.00019012854],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984113,0.00014375574,0.0007866305,0.0002602103,0.000118901524,0.00027922823],"domain_scores_gemma":[0.99872947,0.00024765133,0.00031882018,0.00026371813,0.0003593897,0.00008096012],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011765276,0.00022274206,0.0003667807,0.0004727439,0.0004917487,0.00095453346,0.00027129916,0.00015796044,9.447021e-7],"category_scores_gemma":[0.000024573306,0.0002020728,0.000066496206,0.00043953696,0.000022950238,0.002712232,0.0001033881,0.00011581745,0.0000033839808],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046934543,0.00007484043,0.0043887235,0.0029047297,0.00016076413,4.813854e-7,0.0018951773,0.0030771345,0.000050699102,0.9002284,0.042555466,0.044616673],"study_design_scores_gemma":[0.00087028,0.000054486063,0.00042920528,0.00056374696,0.000013889815,0.000015351463,0.00027609995,0.7672605,0.000103288454,0.00014987001,0.23003522,0.00022807185],"about_ca_topic_score_codex":0.0000945339,"about_ca_topic_score_gemma":0.000008094718,"teacher_disagreement_score":0.9947869,"about_ca_system_score_codex":0.000099073535,"about_ca_system_score_gemma":0.000105746214,"threshold_uncertainty_score":0.92045885},"labels":[],"label_agreement":null},{"id":"W4413982584","doi":"10.1007/s10115-025-02581-5","title":"A knowledge-based approach for pseudo-relevance feedback by exploiting semantic relevance","year":2025,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Relevance (law); Relevance feedback; Computer science; Information retrieval; Artificial intelligence; Image retrieval","score_opus":0.019883780679341264,"score_gpt":0.2714622971701461,"score_spread":0.2515785164908048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413982584","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021317862,0.0019866386,0.96165425,0.00014616181,0.00068992283,0.0011461059,0.000022611895,0.00024965132,0.031972867],"genre_scores_gemma":[0.9812482,0.00013391243,0.01225126,0.00049938174,0.000111237634,0.00081722136,0.00015609688,0.000013825167,0.004768839],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982432,0.0000624633,0.0008195271,0.00023882532,0.00023258348,0.00040337935],"domain_scores_gemma":[0.9981246,0.00035531312,0.00025127208,0.00039541456,0.0007525367,0.000120836296],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008265418,0.00023234263,0.00031757817,0.00035147794,0.000441705,0.00067098415,0.00053781725,0.00013662431,0.0000014227675],"category_scores_gemma":[0.00023520018,0.00020671118,0.000089009256,0.000859862,0.000059552745,0.00449843,0.0001367984,0.00016469017,0.00012029698],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017283246,0.00054558384,0.00091129204,0.015344845,0.00012964464,6.741955e-7,0.016405942,0.0011644774,0.0014638542,0.42205688,0.18864632,0.35315764],"study_design_scores_gemma":[0.0011426578,0.00006559083,0.00008986909,0.00025835654,0.000010256683,0.000004497243,0.0004656796,0.6546278,0.0015511981,0.00004816016,0.34149766,0.00023830387],"about_ca_topic_score_codex":0.000007494961,"about_ca_topic_score_gemma":7.7511834e-7,"teacher_disagreement_score":0.97911644,"about_ca_system_score_codex":0.00011152016,"about_ca_system_score_gemma":0.00024178503,"threshold_uncertainty_score":0.8429437},"labels":[],"label_agreement":null},{"id":"W4414874910","doi":"10.1007/s10115-025-02552-w","title":"LINDAS: a learned approach to index algorithm selection","year":2025,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"National Natural Science Foundation of China","keywords":"Search engine indexing; Index (typography); Selection (genetic algorithm); Hash function; Index selection; Range (aeronautics)","score_opus":0.012550522390299163,"score_gpt":0.2511002347204886,"score_spread":0.23854971233018943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414874910","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007132782,0.0001371476,0.8365177,0.000099455436,0.0005633287,0.00032071682,0.000002663563,0.0001480274,0.16213961],"genre_scores_gemma":[0.85140175,0.00023810587,0.094872355,0.002469576,0.0008318606,0.0008217132,0.00027965545,0.00002323446,0.049061727],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992145,0.000036196765,0.0002921486,0.00015920601,0.00013764936,0.00016035771],"domain_scores_gemma":[0.9994842,0.000016044974,0.00006507611,0.00021689187,0.00015648818,0.000061343046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041517467,0.00010161928,0.00012845549,0.0004508929,0.00015693741,0.0007615437,0.00033740522,0.00005536457,8.740039e-7],"category_scores_gemma":[0.000019328805,0.00009124732,0.0000212673,0.00097333314,0.00000966753,0.0039059825,0.0002536025,0.00007779367,0.00021361308],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002618065,0.00003751556,0.00016420489,0.00016752744,0.000027105285,8.650459e-8,0.0018137451,0.00014769862,0.000002454457,0.14056532,0.02589077,0.83118093],"study_design_scores_gemma":[0.00020026613,0.000018353709,0.0005297449,0.000026903073,0.0000025284555,0.0000022179688,0.0001827867,0.5257933,0.000013349312,0.000054635195,0.47309965,0.00007626199],"about_ca_topic_score_codex":0.000027478303,"about_ca_topic_score_gemma":0.0000010467595,"teacher_disagreement_score":0.85133046,"about_ca_system_score_codex":0.00003892784,"about_ca_system_score_gemma":0.000044262906,"threshold_uncertainty_score":0.7343584},"labels":[],"label_agreement":null},{"id":"W4415139805","doi":"10.1007/s10115-025-02601-4","title":"Learning to rank under uncertainty: a robust neural approach","year":2025,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"ENCODE; Probabilistic logic; Relevance (law); Generalizability theory; Ambiguity; Divergence-from-randomness model; Rank (graph theory); Space (punctuation); Learning to rank","score_opus":0.011889342082284602,"score_gpt":0.2471812885091502,"score_spread":0.2352919464268656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415139805","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047762576,0.00036986606,0.89070284,0.00045311375,0.0007478398,0.00025084132,7.231359e-7,0.00024422733,0.10245427],"genre_scores_gemma":[0.9926482,0.00000939176,0.0019241496,0.0003913725,0.000088884895,0.000032213502,0.0000129466125,0.0000033703398,0.0048894784],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991453,0.00010671015,0.00029263168,0.00014821446,0.00012246006,0.00018466255],"domain_scores_gemma":[0.9994598,0.00005903081,0.00007134265,0.00019422981,0.00013519333,0.00008042708],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045851467,0.00011463176,0.00016154409,0.0002774864,0.000248581,0.0005174648,0.00027247806,0.000055103275,0.0000014808113],"category_scores_gemma":[0.000055155713,0.00009538212,0.00003124026,0.00058517675,0.000013358042,0.001213412,0.00017259174,0.00018622643,0.00010768897],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000085855045,0.00002576371,0.00057565444,0.00032108495,0.000030045327,3.3897507e-7,0.012052589,0.64782166,0.000008797171,0.1246482,0.0061682933,0.20833898],"study_design_scores_gemma":[0.00026299714,0.00003522455,0.00049504486,0.000043259977,0.0000026015446,0.0000080949985,0.00083871477,0.8323424,0.0000025147342,0.000018176028,0.16585435,0.00009665219],"about_ca_topic_score_codex":0.00006461511,"about_ca_topic_score_gemma":0.0000012137039,"teacher_disagreement_score":0.98787194,"about_ca_system_score_codex":0.000034292334,"about_ca_system_score_gemma":0.00005025634,"threshold_uncertainty_score":0.49899253},"labels":[],"label_agreement":null},{"id":"W4415500225","doi":"10.1007/s10115-025-02604-1","title":"X-HEART: eXplainable heterogeneous log anomaly detection using robust transformers","year":2025,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; IBM Canada; Vector Institute","keywords":"Interpretability; Anomaly detection; Raw data; Anomaly (physics); Transparency (behavior); Transformer","score_opus":0.012437552983026049,"score_gpt":0.23720021654328957,"score_spread":0.22476266356026353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415500225","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21467775,0.0013953093,0.7693207,0.00004425218,0.0021459728,0.00056756235,0.0000026964874,0.00024481263,0.011600884],"genre_scores_gemma":[0.9992115,0.000034123594,0.0003792474,0.000068461624,0.00005096966,0.000042817446,0.0000030405909,0.0000033358654,0.00020652838],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884915,0.00006557135,0.0005252742,0.00017635022,0.00013590368,0.0002477499],"domain_scores_gemma":[0.9992891,0.000042377105,0.00010121202,0.000270433,0.00022849611,0.00006839587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005190967,0.00014897343,0.00022300135,0.0003143035,0.00037127335,0.0003135965,0.00019444004,0.0001351603,0.0000017913065],"category_scores_gemma":[0.000019074781,0.000127021,0.00006363058,0.00056536915,0.000034595596,0.0038964874,0.00006057928,0.000094847455,0.000071134265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002933867,0.0005500956,0.0646947,0.021805806,0.0006687718,0.000010539073,0.053592287,0.13270894,0.0041208146,0.037784006,0.0063593457,0.6774113],"study_design_scores_gemma":[0.0006376035,0.000094256255,0.0018631672,0.00021838174,0.00001471121,0.00012281662,0.0005435778,0.84394073,0.0026450255,0.00003352909,0.14962025,0.00026595074],"about_ca_topic_score_codex":0.00011871823,"about_ca_topic_score_gemma":0.000011908325,"teacher_disagreement_score":0.78453374,"about_ca_system_score_codex":0.00013418366,"about_ca_system_score_gemma":0.000115837975,"threshold_uncertainty_score":0.51797664},"labels":[],"label_agreement":null},{"id":"W632121358","doi":"10.1007/s10115-015-0851-6","title":"On strategies for building effective ensembles of relative clustering validity criteria","year":2015,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Computer science; Measure (data warehouse); Data mining; Set (abstract data type); Partition (number theory); Complementarity (molecular biology); Consensus clustering; Stability (learning theory); Variety (cybernetics); Machine learning; Artificial intelligence; Mathematics; Fuzzy clustering; CURE data clustering algorithm","score_opus":0.06181771647573652,"score_gpt":0.357017140401257,"score_spread":0.29519942392552045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W632121358","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016492497,0.00016483449,0.9745897,0.000017674725,0.00055584015,0.00059819495,0.0000102322665,0.00006760026,0.0075034453],"genre_scores_gemma":[0.98634577,0.000006751727,0.013393821,0.000008417455,0.000058505786,0.00012299583,0.0000031103543,0.0000049691057,0.000055684282],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907625,0.000109964494,0.00032427377,0.00012845572,0.00018780425,0.00017325886],"domain_scores_gemma":[0.9985195,0.0004888867,0.00015958372,0.00020228892,0.00054308225,0.00008668181],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008216946,0.00011045772,0.0002008773,0.0001926438,0.00009577546,0.00023862028,0.00021583193,0.00005922846,2.5568437e-7],"category_scores_gemma":[0.00027931845,0.000095826064,0.000030347652,0.00019452452,0.000035197027,0.00465257,0.00016844024,0.00007696984,0.000011752716],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026972528,0.00008882697,0.00007553841,0.0032089546,0.00010330462,0.0000017875425,0.07651583,0.023316473,0.0016873197,0.7712,0.0019820165,0.1215502],"study_design_scores_gemma":[0.0010059719,0.0007093091,0.00014795637,0.00032119715,0.000003919751,0.000015734413,0.0018065613,0.9790575,0.0017183134,0.006533852,0.0085010035,0.00017867451],"about_ca_topic_score_codex":0.000015783038,"about_ca_topic_score_gemma":0.0000018527362,"teacher_disagreement_score":0.9698532,"about_ca_system_score_codex":0.00009050864,"about_ca_system_score_gemma":0.00008313302,"threshold_uncertainty_score":0.39076737},"labels":[],"label_agreement":null},{"id":"W646176396","doi":"10.1007/s10115-015-0892-x","title":"Continuous similarity search for evolving queries","year":2015,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; British Columbia Institute of Technology","funders":"","keywords":"Multiset; Nearest neighbor search; Computer science; Set (abstract data type); Similarity (geometry); Data stream; Data mining; Hash function; Result set; Theoretical computer science; Information retrieval; Mathematics; Artificial intelligence","score_opus":0.03910859700177923,"score_gpt":0.31033596522634793,"score_spread":0.2712273682245687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W646176396","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00054056983,0.0017144489,0.9735508,0.00007481598,0.000319481,0.0004275684,0.0000065299005,0.00024762642,0.023118181],"genre_scores_gemma":[0.9807817,0.00008734138,0.018086892,0.00013750698,0.00014634266,0.00009671382,0.000016107599,0.0000063056605,0.0006411145],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992782,0.000035417565,0.00028237127,0.00010002463,0.00013501743,0.00016900888],"domain_scores_gemma":[0.99876535,0.00007732426,0.000078851015,0.00020288839,0.000769362,0.00010622071],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006997318,0.00008889096,0.00015539772,0.00010963609,0.00011758015,0.00039982726,0.00021794361,0.000058673693,4.937071e-7],"category_scores_gemma":[0.00015341157,0.00007587548,0.000026490976,0.0001892815,0.000030167661,0.006316911,0.00012749966,0.00006437496,0.00003130276],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049303042,0.000058852493,0.0025387106,0.0008791144,0.000034987348,0.0000015926627,0.027471388,0.00003495727,0.00017236518,0.5570451,0.077790424,0.3339232],"study_design_scores_gemma":[0.0005787567,0.00024264917,0.00022628199,0.00007354104,0.0000033986894,0.000024712015,0.0011068302,0.07047516,0.0062807556,0.0008270815,0.9199483,0.00021255664],"about_ca_topic_score_codex":0.000015714519,"about_ca_topic_score_gemma":8.887407e-7,"teacher_disagreement_score":0.9802411,"about_ca_system_score_codex":0.000044136417,"about_ca_system_score_gemma":0.000088268425,"threshold_uncertainty_score":0.4579608},"labels":[],"label_agreement":null},{"id":"W7117313584","doi":"10.1007/s10115-025-02657-2","title":"Enhanced software defect prediction using edge feature and self-attention GAN with pelican optimization","year":2025,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Feature (linguistics); Convolutional neural network; Software; Enhanced Data Rates for GSM Evolution; Artificial neural network; Software bug; Pattern recognition (psychology); Software system; Deep learning","score_opus":0.006036464635271571,"score_gpt":0.22966269469882605,"score_spread":0.22362623006355448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117313584","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037348177,0.00058586954,0.9600637,0.000026428828,0.00035299687,0.0003811351,0.0000037783498,0.00039217842,0.00084576255],"genre_scores_gemma":[0.98810923,0.00007270918,0.0115294745,0.000017532997,0.000051743664,0.000044801338,0.000027840322,0.0000060902175,0.00014059427],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99926525,0.000044890407,0.00020256282,0.00016018792,0.00017185803,0.00015522381],"domain_scores_gemma":[0.9991679,0.0000965494,0.00007527798,0.00020635696,0.00039199993,0.00006188146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029615688,0.00011643966,0.00012656313,0.00033406683,0.00018870154,0.0004383021,0.0001329424,0.000089876106,4.3312843e-7],"category_scores_gemma":[0.000109361354,0.00010028769,0.000017122411,0.0007253024,0.000018559867,0.0025577252,0.00007296375,0.000108489105,0.000004735399],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002008835,0.0004743965,0.19028364,0.0156125,0.0010819976,0.000006651125,0.04692124,0.48933804,0.002416472,0.033751957,0.01396118,0.20595104],"study_design_scores_gemma":[0.0006617949,0.0000933604,0.020847207,0.0003989053,0.000020353114,0.000035461406,0.000153226,0.97223,0.00027438454,0.0000038111434,0.005122651,0.00015885127],"about_ca_topic_score_codex":0.000009069001,"about_ca_topic_score_gemma":0.0000013826101,"teacher_disagreement_score":0.950761,"about_ca_system_score_codex":0.00009827519,"about_ca_system_score_gemma":0.00010244075,"threshold_uncertainty_score":0.4226557},"labels":[],"label_agreement":null}]}