{"meta":{"query_hash":"6c72437377aa","filters":{"topic":"Data Mining Algorithms and Applications"},"cohort_total":1100,"direct_labels_cover":1,"predictions_cover":1100,"exported":1100,"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/6c72437377aa","api":"https://metacan.xera.ac/api/v1/cohort?topic=Data+Mining+Algorithms+and+Applications"},"results":[{"id":"W101016380","doi":"","title":"The K-behaviour of p-trees.","year":2007,"lang":"en","type":"article","venue":"Ars Combinatoria","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics","score_opus":0.012089685359108678,"score_gpt":0.25906609948653836,"score_spread":0.24697641412742968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W101016380","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39394292,0.003976906,0.4867493,0.0076983487,0.0002602516,0.00009638774,0.0020368549,0.0017073465,0.10353179],"genre_scores_gemma":[0.934166,0.001138392,0.05236077,0.0005678514,0.00017452199,0.00008796556,0.00088424,0.00030002178,0.010320205],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976922,0.000729434,0.00019358091,0.0005350961,0.00052552344,0.00032412735],"domain_scores_gemma":[0.98121405,0.012824033,0.0012902752,0.0023552952,0.001398101,0.0009181614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020043747,0.00044611335,0.000851059,0.002086696,0.0020749292,0.005422958,0.001536283,0.0017475421,0.006250813],"category_scores_gemma":[0.027847897,0.0006597115,0.0010102032,0.0028254234,0.0038316264,0.008158316,0.0023355968,0.0024060705,0.0023723012],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001936772,0.000057687077,0.0070957704,0.0002140863,0.000058980848,0.0007619951,0.0013658497,0.006381926,0.0022041006,0.94099814,0.0071213725,0.033546448],"study_design_scores_gemma":[0.000013970847,0.000017914852,0.00069889164,0.00004450075,0.000019185585,0.00076387404,0.00018109173,0.018558415,0.00069795543,0.9745105,0.0044774814,0.000016257054],"about_ca_topic_score_codex":0.0018478779,"about_ca_topic_score_gemma":0.0013401641,"teacher_disagreement_score":0.006250813,"about_ca_system_score_codex":0.0015639166,"about_ca_system_score_gemma":0.00088600867,"threshold_uncertainty_score":0.020910978},"labels":[],"label_agreement":null},{"id":"W1011630013","doi":"10.1016/b978-0-12-381479-1.00007-1","title":"Advanced Pattern Mining","year":2012,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Data mining; Computer science; K-optimal pattern discovery; Outlier; Association rule learning; Cluster analysis; Ambiguity; Process (computing); Artificial intelligence","score_opus":0.019450589105434696,"score_gpt":0.24593995748376818,"score_spread":0.22648936837833347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1011630013","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039333687,0.0249344,0.7349195,0.0024880536,0.0025444403,0.00036828837,0.004550016,0.014416419,0.21184553],"genre_scores_gemma":[0.012783575,0.022950172,0.45691237,0.0010573132,0.0011491204,0.00034683757,0.013108888,0.0018597641,0.48983198],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993735,0.000046152658,0.000053312106,0.00018480494,0.0003090343,0.000033272736],"domain_scores_gemma":[0.999173,0.00026180784,0.00003729099,0.0002687764,0.00020812279,0.000051049108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078728475,0.001796186,0.0014604944,0.003308296,0.00064629415,0.0029029786,0.0017608101,0.0010543704,0.09935342],"category_scores_gemma":[0.0020388346,0.0010685642,0.0012732708,0.005405377,0.00046401724,0.0039457213,0.002075324,0.0018384131,0.099808715],"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":[0.00001711496,0.000034823035,0.00018344879,0.000374871,0.000027021666,0.00007079694,0.00004342485,0.00070690544,0.0031883805,0.0083292145,0.109072015,0.877952],"study_design_scores_gemma":[0.000016727367,0.0000732823,0.0012531758,0.00036150712,0.0000632238,0.0015618455,0.000068253685,0.016050886,0.008236818,0.07039033,0.9018841,0.00003983359],"about_ca_topic_score_codex":0.00060455495,"about_ca_topic_score_gemma":0.0011910229,"teacher_disagreement_score":0.09935342,"about_ca_system_score_codex":0.00036539053,"about_ca_system_score_gemma":0.0008354974,"threshold_uncertainty_score":0.33237028},"labels":[],"label_agreement":null},{"id":"W106071789","doi":"10.4018/978-1-60566-010-3.ch082","title":"Data Mining with Incomplete Data","year":2009,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint Mary's University","funders":"","keywords":"Missing data; Data mining; Ambiguity; Computer science; Survey data collection; Data set; Set (abstract data type); Data science; Knowledge extraction; Statistics; Artificial intelligence; Machine learning; Mathematics","score_opus":0.07953766576169785,"score_gpt":0.29236435246534354,"score_spread":0.21282668670364568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W106071789","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031265821,0.010300634,0.972323,0.0034059247,0.00041586524,0.00067026063,0.003834919,0.0009286463,0.0049942606],"genre_scores_gemma":[0.043336645,0.013699643,0.92701215,0.0015972386,0.00089777174,0.001399446,0.008669161,0.00019993099,0.0031879763],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9658685,0.01534531,0.0042618364,0.0057000695,0.008278206,0.00054608705],"domain_scores_gemma":[0.9303494,0.0460277,0.0038247455,0.014985149,0.004291911,0.00052103697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023900244,0.0020682495,0.0041296124,0.009240178,0.0019840205,0.008623335,0.0063643907,0.0029522565,0.004697737],"category_scores_gemma":[0.070900775,0.0015686092,0.0046696193,0.015704291,0.0029287112,0.013288022,0.008592636,0.005044933,0.0037807794],"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":[0.00022686763,0.00029783274,0.008210179,0.008760084,0.0013899805,0.0012851635,0.0022612663,0.027709307,0.0015617423,0.18368885,0.046313293,0.7182954],"study_design_scores_gemma":[0.00008625888,0.00020041413,0.0023248035,0.0032614295,0.0003901853,0.0023142796,0.001416872,0.11445253,0.004374724,0.6233043,0.24771458,0.00015956358],"about_ca_topic_score_codex":0.0010904289,"about_ca_topic_score_gemma":0.0012283594,"teacher_disagreement_score":0.023900244,"about_ca_system_score_codex":0.0016164728,"about_ca_system_score_gemma":0.0036575813,"threshold_uncertainty_score":0.12639809},"labels":[],"label_agreement":null},{"id":"W107081620","doi":"10.4018/978-1-59904-853-6.ch024","title":"Incremental Discovery of Fuzzy Functional Dependencies","year":2008,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"New York Institute of Technology","funders":"","keywords":"Computer science; Data mining; Functional dependency; Viewpoints; Fuzzy logic; Property (philosophy); Relational database; Similarity (geometry); Monotonic function; Information retrieval; Artificial intelligence; Mathematics; Image (mathematics)","score_opus":0.027213919301474557,"score_gpt":0.23526667701150647,"score_spread":0.2080527577100319,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W107081620","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17925617,0.0007427162,0.8118452,0.000374638,0.000047075057,0.00024308002,0.00091634697,0.0015957578,0.004979012],"genre_scores_gemma":[0.4912545,0.00030529557,0.5047289,0.00009235962,0.00002760047,0.000163356,0.0017655375,0.000084368476,0.0015781203],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984341,0.0002507921,0.0000936987,0.0003266295,0.00075719296,0.00013755346],"domain_scores_gemma":[0.9937496,0.0041060615,0.0002905354,0.0006894739,0.0010626299,0.00010168499],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015967756,0.00065189076,0.0010959953,0.003080403,0.0006910504,0.0012889599,0.0020000774,0.0008391764,0.0024838971],"category_scores_gemma":[0.013267183,0.00049383065,0.0013746127,0.0022421854,0.0005027609,0.0024883826,0.0016222477,0.0008142708,0.00043472563],"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":[0.00031636792,0.00029881243,0.012585825,0.00043966668,0.0001619073,0.0008050381,0.0006077593,0.08187383,0.01376606,0.028216656,0.0056149717,0.8553132],"study_design_scores_gemma":[0.000033444092,0.00009679861,0.003310104,0.000045168414,0.0000990809,0.00046851428,0.00020986151,0.9385536,0.010376591,0.041804083,0.0049679503,0.000034846173],"about_ca_topic_score_codex":0.004528965,"about_ca_topic_score_gemma":0.0057013454,"teacher_disagreement_score":0.004528965,"about_ca_system_score_codex":0.00087941805,"about_ca_system_score_gemma":0.0016657424,"threshold_uncertainty_score":0.009005189},"labels":[],"label_agreement":null},{"id":"W107313290","doi":"","title":"Classification Of Large Sets By Trades.","year":2007,"lang":"en","type":"article","venue":"Ars Combinatoria","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics","score_opus":0.017176328003992672,"score_gpt":0.2803211263112628,"score_spread":0.26314479830727017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W107313290","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5643894,0.008794455,0.34776688,0.005996216,0.000974949,0.00066807546,0.020631935,0.0031978993,0.04758018],"genre_scores_gemma":[0.8972444,0.0013514947,0.07620106,0.00035962436,0.00066609686,0.00031709118,0.01193408,0.00027189424,0.011654247],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997017,0.000542804,0.0003649215,0.0007002006,0.0010099472,0.00036521393],"domain_scores_gemma":[0.9826857,0.00953674,0.0018545097,0.0034497841,0.0014239429,0.001049378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035318078,0.0007015222,0.00171932,0.007864207,0.0016717806,0.0048420127,0.0021217403,0.0015039522,0.012307966],"category_scores_gemma":[0.02642146,0.00047918392,0.0020157374,0.008553938,0.002079092,0.007115774,0.0024109855,0.0021244728,0.0026720667],"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":[0.0015961869,0.00083412376,0.15300989,0.001024019,0.00052493333,0.001085893,0.00050456164,0.04389684,0.0037262472,0.24774618,0.052720807,0.49333042],"study_design_scores_gemma":[0.00011839896,0.00030624002,0.025730666,0.0003323082,0.00018686411,0.0020083769,0.001017288,0.322484,0.003561845,0.6141486,0.030031927,0.00007351867],"about_ca_topic_score_codex":0.0014127817,"about_ca_topic_score_gemma":0.0017506492,"teacher_disagreement_score":0.012307966,"about_ca_system_score_codex":0.0015277555,"about_ca_system_score_gemma":0.0012560814,"threshold_uncertainty_score":0.041174293},"labels":[],"label_agreement":null},{"id":"W107532537","doi":"10.4018/978-1-60960-102-7.ch013","title":"iVAS","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Visualization; Database transaction; Set (abstract data type); Information retrieval; Data mining; Information visualization; Data science; Database; Programming language","score_opus":0.031448488649753165,"score_gpt":0.2471299384026578,"score_spread":0.21568144975290462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W107532537","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050555547,0.0032544478,0.16967376,0.0019107243,0.0018217077,0.0004002144,0.008601084,0.034417678,0.7748648],"genre_scores_gemma":[0.047174558,0.0040799323,0.13473381,0.0010910085,0.0005404532,0.0005540696,0.01750403,0.0058203517,0.7885018],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990631,0.00014757505,0.00006834922,0.00019323872,0.000431339,0.000096397875],"domain_scores_gemma":[0.9990877,0.0001545118,0.000053353717,0.00025935177,0.00030867412,0.00013632588],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00072175433,0.0009172078,0.00052333256,0.00198157,0.0008854897,0.0045813955,0.002045647,0.0011222761,0.24934924],"category_scores_gemma":[0.0026145396,0.0004922844,0.00073116785,0.0024162817,0.00045140443,0.003152383,0.0027846792,0.0011682543,0.14494923],"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":[0.0002171291,0.00007113518,0.0005453607,0.0005054528,0.000020563155,0.00019943698,0.0005128258,0.0011704979,0.0052454453,0.114513926,0.43740788,0.4395903],"study_design_scores_gemma":[0.000010375479,0.000020510015,0.00015653372,0.00006797676,0.000006134618,0.00022304033,0.000085311905,0.0011426358,0.0012207123,0.009155342,0.98790246,0.000009011381],"about_ca_topic_score_codex":0.0012500236,"about_ca_topic_score_gemma":0.0015454252,"teacher_disagreement_score":0.75065076,"about_ca_system_score_codex":0.001101054,"about_ca_system_score_gemma":0.00097327615,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W11261568","doi":"10.1093/ps/80.3.358","title":"SyGMA: Reducing Symmetry in Graph Mining","year":2007,"lang":"en","type":"article","venue":"Les Cahiers du GERAD","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Limiting; Data mining; Task (project management); Graph; Efficient algorithm; Theoretical computer science; Symmetry (geometry); Algorithm; Mathematics; Engineering","score_opus":0.009793538500813591,"score_gpt":0.235508042000786,"score_spread":0.2257145034999724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W11261568","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035524067,0.0012070134,0.9054959,0.0014107513,0.0003373742,0.00064273924,0.004685547,0.046443887,0.004252706],"genre_scores_gemma":[0.07951525,0.00033135663,0.9066329,0.00046012888,0.00013598076,0.0005588325,0.0077897445,0.0016013209,0.002974555],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955764,0.0014957688,0.0003798045,0.0011343935,0.0010373181,0.00037646628],"domain_scores_gemma":[0.9897537,0.00508165,0.0007208199,0.0033325127,0.0007364471,0.00037485786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045349905,0.002464208,0.0026761184,0.004250359,0.0012776648,0.0022743423,0.0043173847,0.0022488977,0.012501691],"category_scores_gemma":[0.020032512,0.0013099468,0.0041008247,0.0036619562,0.0017401495,0.0059559057,0.0048473347,0.002959346,0.0055677122],"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":[0.0015842376,0.00072766276,0.0057325955,0.0012018299,0.0004108888,0.00044724863,0.00058538973,0.040202614,0.009692667,0.027096817,0.07758872,0.8347292],"study_design_scores_gemma":[0.00064503564,0.00043568917,0.0016487521,0.00014274777,0.0001200905,0.0004614141,0.0003734921,0.8091128,0.007125881,0.15031289,0.02956898,0.0000523249],"about_ca_topic_score_codex":0.0025019418,"about_ca_topic_score_gemma":0.005691234,"teacher_disagreement_score":0.012501691,"about_ca_system_score_codex":0.000962417,"about_ca_system_score_gemma":0.003320387,"threshold_uncertainty_score":0.041822314},"labels":[],"label_agreement":null},{"id":"W113596500","doi":"10.5006/c2005-05479","title":"Development of SCC Susceptibility Model Using Decision Tree Approach","year":2005,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Imperial Oil (Canada); Alberta Energy","funders":"","keywords":"Decision tree; Computer science; Data mining","score_opus":0.06808064058755181,"score_gpt":0.3046246459191895,"score_spread":0.23654400533163766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W113596500","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10034195,0.00021964857,0.89549994,0.000364058,0.00003276925,0.00010865505,0.00059167,0.0005979756,0.0022433926],"genre_scores_gemma":[0.88097584,0.0002243206,0.11611964,0.00007550648,0.000024235218,0.00021889822,0.0007308823,0.000028137298,0.0016024921],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99943537,0.00019439445,0.000042863674,0.000105690626,0.00014078052,0.000080841375],"domain_scores_gemma":[0.9975533,0.0017739546,0.0001576662,0.0000497936,0.00039081046,0.00007454744],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013334816,0.00064180314,0.0008709291,0.0012395509,0.00040983074,0.00075436005,0.0009948057,0.0007869011,0.0020460375],"category_scores_gemma":[0.0034427387,0.00042453362,0.0009588265,0.0010006921,0.0002886835,0.00084679486,0.0004134446,0.00074469927,0.00024454878],"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":[0.000023671675,0.000020089046,0.0010544817,0.000018525245,0.00001603668,0.00004308933,0.0000122740885,0.98811454,0.00019757774,0.0016622036,0.00022974938,0.008607788],"study_design_scores_gemma":[0.0000013079022,0.0000039385213,0.00003947119,0.0000011173539,0.0000019999811,0.000002867519,0.0000013781003,0.99923813,0.000052545027,0.00062141207,0.000034919874,9.3032855e-7],"about_ca_topic_score_codex":0.01861083,"about_ca_topic_score_gemma":0.007767226,"teacher_disagreement_score":0.01861083,"about_ca_system_score_codex":0.0009470053,"about_ca_system_score_gemma":0.0012585027,"threshold_uncertainty_score":0.037005007},"labels":[],"label_agreement":null},{"id":"W1145739401","doi":"10.1007/s13369-015-1811-x","title":"FPS-Tree Algorithm to Find Top-k Closed Itemsets in Data Streams","year":2015,"lang":"en","type":"article","venue":"Arabian Journal for Science and Engineering","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":"Toronto Metropolitan University","funders":"","keywords":"Bitmap; Data mining; Computer science; Sliding window protocol; Data stream mining; Association rule learning; Benchmark (surveying); Algorithm; Tree (set theory); Value (mathematics); Data stream; Window (computing); Mathematics; Artificial intelligence; Machine learning; Geography","score_opus":0.05292506731557937,"score_gpt":0.30429651775862543,"score_spread":0.25137145044304604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1145739401","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17463772,0.0032653713,0.80345035,0.001137,0.00034947429,0.00085901737,0.008017273,0.003850624,0.0044331695],"genre_scores_gemma":[0.33680114,0.000990103,0.64466304,0.00025079833,0.00015718772,0.00041319398,0.012584784,0.00016120591,0.0039786],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988777,0.0001147369,0.0001617971,0.000284564,0.00039592176,0.0001652257],"domain_scores_gemma":[0.9977501,0.0011273536,0.00014379002,0.00018926564,0.0006471203,0.00014234432],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001187979,0.0009563317,0.0018477584,0.003748904,0.0015929003,0.0016859431,0.0022606452,0.0016881975,0.0035155069],"category_scores_gemma":[0.005438127,0.00052557053,0.001701648,0.0045148153,0.00046143914,0.0024879482,0.0012502975,0.0012313115,0.0012309197],"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":[0.001010142,0.0007321168,0.023483437,0.0009839117,0.00035847066,0.0011257336,0.00053096033,0.085018106,0.00830136,0.008490344,0.025466166,0.8444993],"study_design_scores_gemma":[0.000117181226,0.00032231893,0.0037537368,0.00012281096,0.00017895339,0.0011963302,0.00047598165,0.9618002,0.0040867515,0.020560281,0.0073502134,0.00003533901],"about_ca_topic_score_codex":0.0067018126,"about_ca_topic_score_gemma":0.008978285,"teacher_disagreement_score":0.0067018126,"about_ca_system_score_codex":0.00081096555,"about_ca_system_score_gemma":0.0032713278,"threshold_uncertainty_score":0.013325632},"labels":[],"label_agreement":null},{"id":"W115653890","doi":"","title":"Feature Selection for Improving Case-Based Classifiers on High-Dimensional Data Sets.","year":2005,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Feature selection; Artificial intelligence; Logistic regression; Data mining; Rank (graph theory); Machine learning; Selection (genetic algorithm); Class (philosophy); Feature (linguistics); Pattern recognition (psychology); Mathematics","score_opus":0.04098017083029297,"score_gpt":0.2931227851169678,"score_spread":0.25214261428667484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W115653890","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032644726,0.00072815735,0.96186155,0.00053187896,0.0001154336,0.00036494373,0.0005045551,0.0023861157,0.0008626499],"genre_scores_gemma":[0.32114384,0.0003782975,0.67406464,0.0002408367,0.00021279685,0.00084409874,0.0023739124,0.00011399201,0.00062754744],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99583423,0.001513503,0.00055184786,0.00050947035,0.0013925456,0.00019837737],"domain_scores_gemma":[0.9837141,0.012129281,0.0009404625,0.0010022549,0.0019966634,0.00021715235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008205963,0.0014285212,0.0016274336,0.0060106623,0.0007337221,0.0017057079,0.0020729266,0.0013808011,0.0021055038],"category_scores_gemma":[0.03455493,0.0004553291,0.0013084443,0.0039255894,0.00054564397,0.0024858462,0.0015860581,0.0013385854,0.00094910816],"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":[0.00035929846,0.00045269786,0.016826937,0.00031687043,0.00027374015,0.00045819514,0.00021049523,0.06566281,0.004454585,0.0049292333,0.011978135,0.89407694],"study_design_scores_gemma":[0.0001560454,0.00017574565,0.0040613655,0.00006842991,0.00014650388,0.0004470957,0.00009395564,0.97136176,0.004285347,0.015870627,0.003290844,0.000042349286],"about_ca_topic_score_codex":0.0020735888,"about_ca_topic_score_gemma":0.0017851238,"teacher_disagreement_score":0.008205963,"about_ca_system_score_codex":0.00082967937,"about_ca_system_score_gemma":0.0010083374,"threshold_uncertainty_score":0.043397784},"labels":[],"label_agreement":null},{"id":"W120315634","doi":"10.4018/978-1-59140-553-5.ch409","title":"Process-Based Data Mining","year":2005,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Aga Khan Foundation","funders":"","keywords":"Pentium; Integrator; Computer science; Database; Process (computing); Operating system; Telecommunications; Bandwidth (computing)","score_opus":0.04584112973066332,"score_gpt":0.30028044632292983,"score_spread":0.2544393165922665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W120315634","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007848762,0.0091934195,0.95408964,0.001453146,0.00036770815,0.000599594,0.0037501259,0.005165992,0.017531672],"genre_scores_gemma":[0.18239586,0.0125578875,0.7692134,0.00087210914,0.0004970716,0.00071690045,0.016555073,0.00041548844,0.016776305],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981188,0.00021429054,0.00015039596,0.000629828,0.0007908433,0.0000957086],"domain_scores_gemma":[0.99854195,0.00061996345,0.00011837932,0.0003617308,0.00032052037,0.000037491267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015673088,0.0017641977,0.0018391983,0.0036897664,0.00092174445,0.0033892954,0.0035352292,0.001532774,0.007947094],"category_scores_gemma":[0.004501817,0.0005736732,0.0021823975,0.0060036243,0.00079678727,0.0032102116,0.0016340128,0.0016480765,0.007608904],"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":[0.00019100103,0.00034661387,0.004243027,0.0012811181,0.0003721439,0.000393521,0.00018526001,0.044220187,0.003944587,0.028248854,0.03324174,0.8833321],"study_design_scores_gemma":[0.000054454693,0.00023673743,0.003300108,0.00041407533,0.0002661614,0.0014109374,0.0002633351,0.65184873,0.01642424,0.15872675,0.16697872,0.00007578563],"about_ca_topic_score_codex":0.0022292105,"about_ca_topic_score_gemma":0.0027700039,"teacher_disagreement_score":0.007947094,"about_ca_system_score_codex":0.0008368954,"about_ca_system_score_gemma":0.0015030755,"threshold_uncertainty_score":0.026585639},"labels":[],"label_agreement":null},{"id":"W1203759442","doi":"10.1007/s10489-015-0703-9","title":"Weighted frequent itemset mining over uncertain databases","year":2015,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":54,"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 Moncton","funders":"","keywords":"Computer science; Scalability; Data mining; Database transaction; Apriori algorithm; Consistency (knowledge bases); A priori and a posteriori; Association rule learning; Property (philosophy); Database; Artificial intelligence","score_opus":0.09126512991551503,"score_gpt":0.32008685466808234,"score_spread":0.22882172475256732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1203759442","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2261555,0.0038988686,0.7643778,0.0006767339,0.00018616806,0.0002321951,0.0024019682,0.0006001011,0.0014706552],"genre_scores_gemma":[0.71743864,0.0017066542,0.2754912,0.00012665722,0.00024386245,0.0001835821,0.003628683,0.00005211354,0.001128637],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99431676,0.0009323234,0.0012915907,0.0010038469,0.0021860367,0.00026937234],"domain_scores_gemma":[0.986963,0.007241373,0.0017534186,0.0014563922,0.0022356834,0.00035019664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003549978,0.0009479866,0.0017698752,0.005507571,0.0010635301,0.0028252648,0.0023966783,0.0010992278,0.0010122668],"category_scores_gemma":[0.02307074,0.0007271507,0.001334823,0.008196592,0.0004647399,0.006247857,0.0014427527,0.0009834742,0.000319004],"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":[0.0025153633,0.0005901914,0.067445226,0.002016414,0.001732528,0.0061335526,0.0007420683,0.15289813,0.012755931,0.026469603,0.006316929,0.7203841],"study_design_scores_gemma":[0.00006862772,0.0003195187,0.005768968,0.00019011005,0.00055007776,0.0029528353,0.00058424694,0.90816104,0.0094430465,0.06612659,0.005772388,0.00006257122],"about_ca_topic_score_codex":0.0010695216,"about_ca_topic_score_gemma":0.0013805631,"teacher_disagreement_score":0.005507571,"about_ca_system_score_codex":0.00055606925,"about_ca_system_score_gemma":0.0008227242,"threshold_uncertainty_score":0.01877433},"labels":[],"label_agreement":null},{"id":"W125402927","doi":"","title":"Customizing the rpart library for multivariate gaussian outcomes: the longRPart library","year":2008,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Categorical variable; Recursive partitioning; Deviance (statistics); Algorithm; Computer science; Binary data; Statistics; Binary number; Binary search tree; Binary tree; Mathematics; Data mining; Arithmetic","score_opus":0.03730992775957601,"score_gpt":0.2614178288446756,"score_spread":0.22410790108509962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W125402927","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022673393,0.00017054465,0.8264032,0.00016163792,0.000099423094,0.00028030644,0.009353489,0.15837814,0.0028860027],"genre_scores_gemma":[0.033778455,0.000299348,0.8716512,0.00045318378,0.00014423957,0.0030272591,0.022809919,0.057626028,0.01021041],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967083,0.0009467132,0.00046039384,0.0007266491,0.00094984047,0.00020811807],"domain_scores_gemma":[0.9829327,0.011391728,0.0009126885,0.0022830067,0.00225463,0.00022523808],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00825211,0.002163936,0.0019372423,0.0023921828,0.0008410556,0.0030656531,0.004310994,0.0009008693,0.05605413],"category_scores_gemma":[0.0360631,0.001657325,0.0026752634,0.0025681588,0.00061048585,0.0024645915,0.002666044,0.0029552418,0.037914004],"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":[0.0012277964,0.0003212216,0.01158622,0.0017907658,0.00091060996,0.0006570981,0.0010260041,0.020541789,0.0052118856,0.028752724,0.29366842,0.63430554],"study_design_scores_gemma":[0.00064475805,0.00032608781,0.01731558,0.0006084928,0.0005611914,0.0013769412,0.00020950203,0.35391474,0.051317398,0.06915154,0.5040388,0.0005349413],"about_ca_topic_score_codex":0.004375917,"about_ca_topic_score_gemma":0.0052694506,"teacher_disagreement_score":0.05605413,"about_ca_system_score_codex":0.00093703193,"about_ca_system_score_gemma":0.0025135465,"threshold_uncertainty_score":0.18751973},"labels":[],"label_agreement":null},{"id":"W125829645","doi":"10.1007/978-3-319-10160-6_12","title":"Discovering Statistically Significant Co-location Rules in Datasets with Extended Spatial Objects","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":24,"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; Data mining; Association rule learning; A priori and a posteriori; Apriori algorithm; Database transaction; Exploit; Artificial intelligence; Database","score_opus":0.012379491443248267,"score_gpt":0.2552597956391003,"score_spread":0.24288030419585202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W125829645","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7921627,0.0068941936,0.15646091,0.0018191942,0.00032266858,0.00028646566,0.036313232,0.0019060563,0.0038345847],"genre_scores_gemma":[0.8189058,0.0013679597,0.12447099,0.00029720762,0.00025582954,0.00017649285,0.05333858,0.00011059564,0.0010766108],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959787,0.0006426925,0.0005097598,0.0015057267,0.0010534754,0.00030959095],"domain_scores_gemma":[0.9828703,0.011951431,0.00168715,0.0021355222,0.0009584292,0.00039730105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030006045,0.0010728913,0.0015031585,0.006411207,0.001238681,0.0032828879,0.0027982406,0.0016512775,0.0013329115],"category_scores_gemma":[0.014755216,0.0005148094,0.0027133862,0.009896624,0.0008733415,0.0030519858,0.0018611266,0.0019441118,0.0010799664],"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":[0.0013484438,0.0010430268,0.6368661,0.0015102151,0.0025734548,0.003419281,0.0008156574,0.040998217,0.008921511,0.005299433,0.01863218,0.27857244],"study_design_scores_gemma":[0.00026549422,0.00058805535,0.23414096,0.0006506098,0.0026091004,0.0067852377,0.004418286,0.63964415,0.014319807,0.07171044,0.024658984,0.00020885655],"about_ca_topic_score_codex":0.00641883,"about_ca_topic_score_gemma":0.01462164,"teacher_disagreement_score":0.00641883,"about_ca_system_score_codex":0.0007693842,"about_ca_system_score_gemma":0.0018907918,"threshold_uncertainty_score":0.015868902},"labels":[],"label_agreement":null},{"id":"W129429178","doi":"10.1515/sagmb-2014-0033","title":"Testing genotypes-phenotype relationships using permutation tests on association rules","year":2015,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Permutation (music); Association (psychology); Genotype; Phenotype; Genetics; Statistics; Biology; Computational biology; Mathematics; Psychology; Gene","score_opus":0.05919948829962234,"score_gpt":0.33482303618062387,"score_spread":0.2756235478810015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W129429178","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26330632,0.00017223155,0.7299737,0.0010863745,0.00020227444,0.0004261898,0.0009735951,0.00085091835,0.0030084471],"genre_scores_gemma":[0.8362489,0.00009266233,0.16085015,0.0002500371,0.00010129501,0.00071009423,0.00095676945,0.00009452409,0.00069560175],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9501219,0.03587386,0.0024560157,0.0063900035,0.004171525,0.0009868196],"domain_scores_gemma":[0.6323393,0.34077448,0.006138482,0.01715982,0.0026090783,0.0009788595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.036913652,0.00097146456,0.0016371296,0.0029004663,0.0012306841,0.0022887634,0.0028771015,0.0015221266,0.0052268924],"category_scores_gemma":[0.206745,0.00050864014,0.003063523,0.0033486835,0.0034575304,0.003104959,0.0023345961,0.0035393657,0.00063290645],"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":[0.004115601,0.0018622094,0.2951326,0.0006448064,0.0076401937,0.004073946,0.0016239753,0.07872059,0.009540447,0.09787232,0.005078576,0.49369466],"study_design_scores_gemma":[0.00081645604,0.002720255,0.05053212,0.000090990005,0.00091239694,0.0019153873,0.00060979475,0.6182658,0.0055922945,0.31518465,0.0032245577,0.00013534566],"about_ca_topic_score_codex":0.0018815016,"about_ca_topic_score_gemma":0.0014281962,"teacher_disagreement_score":0.036913652,"about_ca_system_score_codex":0.00058263645,"about_ca_system_score_gemma":0.0022493245,"threshold_uncertainty_score":0.19522035},"labels":[],"label_agreement":null},{"id":"W130319693","doi":"10.1137/1.9781611972771.49","title":"HP2PC: Scalable Hierarchically-Distributed Peer-to-Peer Clustering","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Cluster analysis; Scalability; Partition (number theory); Peer-to-peer; Distributed computing; Data mining; Modularity (biology); Consensus clustering; Theoretical computer science; Canopy clustering algorithm; Correlation clustering; Artificial intelligence; Database","score_opus":0.01818911720333706,"score_gpt":0.2821583553010592,"score_spread":0.26396923809772216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W130319693","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01748781,0.0003868529,0.97374403,0.00024750203,0.000080118916,0.00033130028,0.00020966119,0.005480115,0.0020326755],"genre_scores_gemma":[0.19890751,0.00025027187,0.79630244,0.00010872543,0.000060485905,0.00033931702,0.0008609272,0.00023306001,0.0029372894],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901116,0.0002118473,0.000045446435,0.00020194321,0.000442164,0.000087352695],"domain_scores_gemma":[0.998755,0.0002965193,0.00008133149,0.000424106,0.00035380037,0.00008920419],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012513686,0.0006049786,0.00087608444,0.0008783286,0.0013605763,0.00095632585,0.002408182,0.00091331615,0.0016350315],"category_scores_gemma":[0.002676863,0.00040040395,0.0004855558,0.002054988,0.0005699353,0.0017660006,0.0019026397,0.0008742944,0.0009702455],"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":[0.00031279307,0.00026864998,0.0026501103,0.0003824011,0.00019039122,0.00027766376,0.00041611746,0.40527192,0.018733311,0.019947236,0.023998113,0.52755135],"study_design_scores_gemma":[0.00006157527,0.00006442598,0.00047187792,0.000006509518,0.00001823727,0.000117741656,0.000051607527,0.9747351,0.00643165,0.0115449345,0.006477005,0.000019403884],"about_ca_topic_score_codex":0.009296398,"about_ca_topic_score_gemma":0.012415551,"teacher_disagreement_score":0.009296398,"about_ca_system_score_codex":0.0008187969,"about_ca_system_score_gemma":0.0019106779,"threshold_uncertainty_score":0.018484533},"labels":[],"label_agreement":null},{"id":"W139735270","doi":"10.4018/978-1-60566-010-3.ch083","title":"Data Pattern Tutor for AprioriAll and PrefixSpan","year":2009,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; TUTOR; Usability; Interface (matter); Focus (optics); Data mining; Data science; Value (mathematics); Information retrieval; Machine learning; Human–computer interaction; Programming language","score_opus":0.048637932496149054,"score_gpt":0.285341230224938,"score_spread":0.23670329772878895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W139735270","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0066613345,0.0025577731,0.8083611,0.0023385203,0.00091582263,0.0006593866,0.0026330478,0.02796779,0.14790526],"genre_scores_gemma":[0.023560576,0.0023867616,0.6332458,0.0024378248,0.0003287923,0.0010074943,0.004784726,0.0054515195,0.3267965],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99952316,0.00007703139,0.00004029067,0.0001529685,0.00018033224,0.00002628388],"domain_scores_gemma":[0.99830854,0.0010867417,0.000058782967,0.00019786705,0.00025458343,0.00009354015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008266526,0.0014297924,0.00082927983,0.0015539845,0.0004375886,0.0018467773,0.0019704031,0.001706555,0.10658212],"category_scores_gemma":[0.0038614005,0.0006111571,0.0010069348,0.0018627961,0.000524173,0.0051352605,0.0017073157,0.0024785602,0.053693786],"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":[0.00020479764,0.00027195134,0.0007084887,0.0011361941,0.000023311073,0.0007241413,0.0013486836,0.0016484077,0.007767418,0.05941131,0.24693193,0.6798234],"study_design_scores_gemma":[0.00008856313,0.00018444892,0.0007529065,0.00032689518,0.000018792753,0.002678427,0.00017530433,0.019499253,0.006196534,0.02988131,0.94015235,0.00004520037],"about_ca_topic_score_codex":0.0003591077,"about_ca_topic_score_gemma":0.00061118795,"teacher_disagreement_score":0.10658212,"about_ca_system_score_codex":0.0006658775,"about_ca_system_score_gemma":0.0007425199,"threshold_uncertainty_score":0.35655272},"labels":[],"label_agreement":null},{"id":"W14376236","doi":"10.1007/978-1-4615-1497-8_6","title":"From Data to Intelligent Agents, Directions in a Data Intensive Data Processing Project","year":2002,"lang":"en","type":"book-chapter","venue":"","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":"Nortel (Canada)","funders":"","keywords":"Variety (cybernetics); Key (lock); Data science; Computer science; Data processing; Management science; Engineering; Artificial intelligence; Database; Computer security","score_opus":0.30714949558063964,"score_gpt":0.37010968701920155,"score_spread":0.06296019143856191,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W14376236","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00870523,0.23477945,0.494118,0.18081203,0.0053429026,0.00017916539,0.0004748386,0.00096901535,0.07461931],"genre_scores_gemma":[0.09388401,0.17619474,0.6294078,0.013500139,0.0043877517,0.00035643872,0.000785444,0.0007006497,0.080782965],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99842346,0.0005674742,0.00012435229,0.00022376303,0.00057557353,0.000085311105],"domain_scores_gemma":[0.9917338,0.0053625014,0.00015978461,0.00091293105,0.0011107393,0.0007202792],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005869764,0.0007788044,0.0009881364,0.0018178212,0.0015152921,0.013321306,0.0021372256,0.0030503427,0.0057085915],"category_scores_gemma":[0.008553044,0.0010742019,0.00069436803,0.004641905,0.005848555,0.021949539,0.0033906614,0.0061365073,0.0020454272],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007022062,0.00013424412,0.00046416163,0.00051108934,0.000029171231,0.00007063664,0.00078903144,0.002228081,0.00052152167,0.6580031,0.096893266,0.2402855],"study_design_scores_gemma":[0.000017026447,0.00002908303,0.00014716701,0.00031484108,0.000013619053,0.000106607484,0.0006033013,0.009550822,0.000593735,0.7114674,0.27713722,0.00001916545],"about_ca_topic_score_codex":0.0028523037,"about_ca_topic_score_gemma":0.0031975475,"teacher_disagreement_score":0.013321306,"about_ca_system_score_codex":0.0019164783,"about_ca_system_score_gemma":0.0033303623,"threshold_uncertainty_score":0.031042635},"labels":[],"label_agreement":null},{"id":"W146817024","doi":"10.1023/a:1008980332240","title":"Hierarchical priors for Bayesian CART shrinkage","year":2000,"lang":"en","type":"article","venue":"Statistics and Computing","topic":"Data Mining Algorithms and Applications","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":"University of Waterloo","funders":"University of Chicago; National Science Foundation","keywords":"Prior probability; Tree (set theory); Shrinkage; Computer science; Bayesian probability; Artificial intelligence; Mathematics; Machine learning; Combinatorics","score_opus":0.010022684140043881,"score_gpt":0.264471543213006,"score_spread":0.2544488590729621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W146817024","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017502902,0.00025224572,0.99650973,0.00015917177,0.00003598052,0.000031503438,0.000118817574,0.00027658313,0.00086570485],"genre_scores_gemma":[0.15248044,0.0013699356,0.83471525,0.00050185656,0.0004304893,0.00062800007,0.0016381792,0.0006622946,0.0075735264],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9947754,0.0030645381,0.00025186146,0.0006477742,0.00096728536,0.00029309595],"domain_scores_gemma":[0.98081595,0.013641995,0.0008429007,0.002713869,0.0016481788,0.00033717716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01079688,0.0011328236,0.002252862,0.002110029,0.0011487216,0.0022699353,0.0029027343,0.0023028157,0.00859576],"category_scores_gemma":[0.051376294,0.0020740752,0.0016305587,0.0032326167,0.0023761617,0.0036711416,0.003212237,0.0045244847,0.0028911957],"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":[0.0002444656,0.00008730966,0.0008311684,0.00029135073,0.00019922233,0.00011115215,0.0001969414,0.34967744,0.0014250994,0.45993483,0.011624657,0.17537639],"study_design_scores_gemma":[0.00003986844,0.000022093058,0.0003421235,0.000052780448,0.000031488133,0.000048556525,0.000015409327,0.6779375,0.0004985975,0.3175128,0.0034661733,0.00003254653],"about_ca_topic_score_codex":0.0044435547,"about_ca_topic_score_gemma":0.0061149024,"teacher_disagreement_score":0.01079688,"about_ca_system_score_codex":0.0013174533,"about_ca_system_score_gemma":0.0025253596,"threshold_uncertainty_score":0.057099998},"labels":[],"label_agreement":null},{"id":"W1482003340","doi":"10.1007/978-3-540-30075-5_48","title":"On Efficient and Effective Association Rule Mining from XML Data","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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 Toronto","funders":"","keywords":"Computer science; XML; Association rule learning; Generalization; Data mining; Automatic summarization; Tree (set theory); Constraint (computer-aided design); Metric (unit); XML Schema (W3C); Document Structure Description; Task (project management); Theoretical computer science; Information retrieval; XML Encryption; World Wide Web","score_opus":0.015164265382221164,"score_gpt":0.25250655097178665,"score_spread":0.2373422855895655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1482003340","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0077433432,0.0019456944,0.986246,0.00056578754,0.00014628518,0.00019667072,0.00043950224,0.0015542312,0.0011625803],"genre_scores_gemma":[0.041398164,0.001906471,0.95037454,0.00045137358,0.0002993723,0.0002675167,0.002138223,0.00021751464,0.0029469316],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9930716,0.0022475435,0.0008490307,0.0006741837,0.002843787,0.00031380987],"domain_scores_gemma":[0.9762115,0.01785321,0.00048981095,0.003789654,0.0014671945,0.000188544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005853381,0.0013819279,0.0024367291,0.0045991326,0.0011747949,0.003136216,0.00353263,0.0018388726,0.002909268],"category_scores_gemma":[0.024376266,0.0014001916,0.0015968545,0.007855949,0.00182069,0.008598085,0.0038994297,0.0026568095,0.0020800203],"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":[0.00030878646,0.00030275912,0.0016715226,0.0003141853,0.00015372128,0.00027881315,0.00020453866,0.03576321,0.005452188,0.020574518,0.016026774,0.91894895],"study_design_scores_gemma":[0.00019723487,0.00022770825,0.0019673994,0.00015908838,0.00019518778,0.0010095299,0.0002191631,0.7932418,0.014430018,0.1658876,0.02236931,0.0000960708],"about_ca_topic_score_codex":0.0044033206,"about_ca_topic_score_gemma":0.005640483,"teacher_disagreement_score":0.005853381,"about_ca_system_score_codex":0.0007388118,"about_ca_system_score_gemma":0.001857219,"threshold_uncertainty_score":0.03095603},"labels":[],"label_agreement":null},{"id":"W1482810056","doi":"10.1007/3-540-47887-6_34","title":"Top Down FP-Growth for Association Rule Mining","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":136,"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":"Association rule learning; Pruning; Computer science; Tree (set theory); Data mining; Space (punctuation); Depth-first search; Order (exchange); Algorithm; Search algorithm; Mathematics; Combinatorics","score_opus":0.017554770548165666,"score_gpt":0.24475105189772578,"score_spread":0.2271962813495601,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1482810056","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009144033,0.002634874,0.9775622,0.0006316657,0.00041765015,0.00014939783,0.0010001904,0.005625545,0.002834463],"genre_scores_gemma":[0.11654727,0.00141813,0.8705649,0.00040700007,0.0005327894,0.00031958506,0.003562004,0.00066636794,0.0059819603],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958016,0.0013060267,0.00035354175,0.0005799768,0.001699818,0.00025903594],"domain_scores_gemma":[0.9865588,0.008206884,0.00029272638,0.0025328286,0.0022084538,0.00020035404],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041601136,0.0016493127,0.002419774,0.0032508823,0.0010697335,0.0021067306,0.002650356,0.0016504861,0.0047024526],"category_scores_gemma":[0.02013781,0.0007508035,0.0013941228,0.0042709387,0.00077826064,0.0028045827,0.0016653126,0.0035665908,0.004979011],"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":[0.0005163811,0.00021105105,0.0017832342,0.00039326967,0.000109142806,0.00035282248,0.000071216455,0.04496499,0.0048096287,0.012733842,0.031799864,0.9022546],"study_design_scores_gemma":[0.000043060678,0.00015006194,0.0005488888,0.00006109945,0.000076956516,0.00051589747,0.000033376702,0.9175825,0.007190314,0.064616576,0.009148632,0.00003268123],"about_ca_topic_score_codex":0.002589772,"about_ca_topic_score_gemma":0.0027728768,"teacher_disagreement_score":0.0047024526,"about_ca_system_score_codex":0.00057360897,"about_ca_system_score_gemma":0.0012424233,"threshold_uncertainty_score":0.022001088},"labels":[],"label_agreement":null},{"id":"W148359012","doi":"10.1007/978-3-642-35236-2_53","title":"An Innovative Way for Mining Clinical and Administrative Healthcare Data","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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":"Athabasca University","funders":"","keywords":"Cosine similarity; Computer science; Sequence (biology); Similarity (geometry); Benchmark (surveying); Data mining; Set (abstract data type); String (physics); Value (mathematics); Vector space model; Rough set; Resource (disambiguation); Similarity measure; Term (time); Space (punctuation); Artificial intelligence; Information retrieval; Algorithm; Machine learning; Pattern recognition (psychology); Mathematics","score_opus":0.1612009757850798,"score_gpt":0.41129959153838225,"score_spread":0.25009861575330244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W148359012","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00979081,0.0005054758,0.979083,0.0011920357,0.00032030718,0.00020003616,0.0030891043,0.0026349546,0.0031841628],"genre_scores_gemma":[0.050516687,0.00041251225,0.9394218,0.00054802897,0.00019546728,0.0002456905,0.0044535543,0.00015785718,0.004048369],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973736,0.00049148226,0.00029162076,0.0006391273,0.0011173881,0.00008678728],"domain_scores_gemma":[0.9963553,0.0019025621,0.00020549238,0.0008503122,0.0005769027,0.00010945137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002629441,0.00073018845,0.00094661023,0.003499301,0.0006259725,0.0030810635,0.0013776597,0.0011549691,0.0042159883],"category_scores_gemma":[0.00860568,0.0006271916,0.0020815192,0.0054327087,0.00046164967,0.0031506887,0.002500513,0.0014298537,0.002866334],"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":[0.00025615052,0.00034778778,0.010789999,0.00038313726,0.0006129734,0.00052863685,0.00055208243,0.0061530066,0.0119841555,0.04315542,0.038625024,0.88661164],"study_design_scores_gemma":[0.00019570194,0.00035084467,0.015471772,0.0002946465,0.00064389093,0.004290515,0.00061903463,0.42145616,0.02778588,0.30887866,0.21980855,0.00020437088],"about_ca_topic_score_codex":0.001237044,"about_ca_topic_score_gemma":0.0023415466,"teacher_disagreement_score":0.0042159883,"about_ca_system_score_codex":0.00034182955,"about_ca_system_score_gemma":0.0012545759,"threshold_uncertainty_score":0.014103889},"labels":[],"label_agreement":null},{"id":"W1486245092","doi":"10.1109/bigdataservice.2015.23","title":"Index Selection on MapReduce Relational-Databases","year":2015,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Index selection; Index (typography); Relational database; Task (project management); Selection (genetic algorithm); Set (abstract data type); Data mining; Process (computing); Database; Database design; Relational database management system; Factor (programming language); Artificial intelligence; Engineering","score_opus":0.08623181636501051,"score_gpt":0.29966483122927656,"score_spread":0.21343301486426605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1486245092","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12892103,0.0017676387,0.83639663,0.00045004406,0.00014814662,0.0005686492,0.0013141766,0.01999898,0.010434835],"genre_scores_gemma":[0.49228033,0.00057156873,0.5011647,0.00015190078,0.0000634753,0.00027118178,0.0016605331,0.00053258816,0.0033037586],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998434,0.00033494717,0.00012002728,0.00021727296,0.0007797364,0.00011404995],"domain_scores_gemma":[0.99878365,0.00035936528,0.00007403608,0.00030759297,0.0003831826,0.0000922324],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014758046,0.00061342947,0.00070165464,0.0009848512,0.0009656262,0.0019487725,0.0020238159,0.00035434566,0.0013746782],"category_scores_gemma":[0.00339222,0.00041118904,0.00060060766,0.0016340245,0.00035172232,0.0014234985,0.0009793409,0.0005052752,0.00061794196],"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":[0.0012743056,0.0006505761,0.010797163,0.00083402765,0.00035551155,0.0008364344,0.0006840615,0.20689423,0.059652805,0.027150579,0.028477589,0.66239274],"study_design_scores_gemma":[0.00008930146,0.00019780677,0.0029237976,0.00003038341,0.000063806634,0.0003629397,0.00031624298,0.9092274,0.04365737,0.023629487,0.019445892,0.000055628567],"about_ca_topic_score_codex":0.0040842528,"about_ca_topic_score_gemma":0.0043260762,"teacher_disagreement_score":0.0040842528,"about_ca_system_score_codex":0.00068875117,"about_ca_system_score_gemma":0.0012434698,"threshold_uncertainty_score":0.008120954},"labels":[],"label_agreement":null},{"id":"W1487276429","doi":"10.1007/978-3-540-74976-9_43","title":"A Method for Multi-relational Classification Using Single and Multi-feature Aggregation Functions","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":34,"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":"Joins; Computer science; Inductive logic programming; Relational database; Artificial intelligence; Representation (politics); Feature (linguistics); Process (computing); Data mining; Statistical relational learning; Theoretical computer science; Machine learning; Pattern recognition (psychology); Programming language","score_opus":0.1350912368396089,"score_gpt":0.3465016342739291,"score_spread":0.2114103974343202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1487276429","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014638423,0.00015242383,0.9965827,0.000059409427,0.00008157578,0.000052445284,0.000082563034,0.0012535531,0.0002714868],"genre_scores_gemma":[0.016465472,0.00010645566,0.98014075,0.000069530484,0.000085255706,0.00012953338,0.00039836543,0.00022600955,0.00237871],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99756384,0.00036104457,0.00018806808,0.00061531534,0.0011232538,0.00014844544],"domain_scores_gemma":[0.9974847,0.00080413243,0.000099782315,0.0006434887,0.00086719217,0.00010072483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025923513,0.0010858176,0.0019132849,0.003005343,0.0014721798,0.0025037646,0.0030928012,0.0015989832,0.0055261455],"category_scores_gemma":[0.0042825146,0.000807207,0.0023023973,0.0037716955,0.0007723284,0.0028122063,0.002390292,0.0027052243,0.0037880964],"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":[0.00018833722,0.00017354773,0.0011634517,0.00015055916,0.00021197832,0.00012583326,0.00016082228,0.008176772,0.0111644715,0.014934935,0.012781839,0.95076746],"study_design_scores_gemma":[0.00009672773,0.00014439218,0.0024234017,0.000057476387,0.00022223215,0.000786352,0.00014228704,0.88540196,0.020331513,0.057582386,0.032677326,0.00013397413],"about_ca_topic_score_codex":0.00306433,"about_ca_topic_score_gemma":0.004180034,"teacher_disagreement_score":0.0055261455,"about_ca_system_score_codex":0.00067345425,"about_ca_system_score_gemma":0.0012798432,"threshold_uncertainty_score":0.018486857},"labels":[],"label_agreement":null},{"id":"W1490955312","doi":"10.1007/3-540-45876-x_7","title":"Profit Mining: From Patterns to Actions","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":88,"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; Statistic; Data mining; Profit (economics); Obstacle; Artificial intelligence; Operations research; Statistics; Mathematics","score_opus":0.03961843418157557,"score_gpt":0.2697600465324612,"score_spread":0.23014161235088565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1490955312","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040095117,0.0035306977,0.93271613,0.0025403257,0.00026102446,0.0002608744,0.0043333066,0.007029614,0.009232929],"genre_scores_gemma":[0.3196667,0.0029281487,0.6611234,0.00052746176,0.00027252073,0.00033394125,0.0067223706,0.0004915741,0.007933915],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902,0.0001707672,0.00008498987,0.00030756486,0.0003558697,0.000060768612],"domain_scores_gemma":[0.99797183,0.0012864431,0.0001626318,0.00028574333,0.00020942706,0.000083914456],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008721041,0.00082250906,0.0008713515,0.001916908,0.0004830585,0.001911632,0.0015701536,0.0007152481,0.0033431835],"category_scores_gemma":[0.005505607,0.00054726587,0.00096962304,0.0025037692,0.0007534928,0.0037020221,0.0013458072,0.001315674,0.0018655059],"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":[0.00022441914,0.0002046513,0.0070292763,0.00046018886,0.00010949098,0.00028467507,0.00024813353,0.016897185,0.0019174262,0.034658194,0.028905237,0.90906113],"study_design_scores_gemma":[0.00007085352,0.00011554199,0.0041754013,0.0002474163,0.00013859064,0.00085443864,0.00037230583,0.45384732,0.0074438876,0.5012791,0.031408228,0.000046831232],"about_ca_topic_score_codex":0.0016937082,"about_ca_topic_score_gemma":0.0023140681,"teacher_disagreement_score":0.0033431835,"about_ca_system_score_codex":0.00051995023,"about_ca_system_score_gemma":0.000978868,"threshold_uncertainty_score":0.011184096},"labels":[],"label_agreement":null},{"id":"W149151211","doi":"10.1007/978-3-319-10840-7_12","title":"Fast Frequent Pattern Detection Using Prime Numbers","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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":"University of Calgary","funders":"","keywords":"Computer science; Scalability; Prime (order theory); Representation (politics); Data mining; Space (punctuation); Process (computing); Database; Mathematics; Combinatorics; Programming language","score_opus":0.018600121928188044,"score_gpt":0.2501351124034765,"score_spread":0.23153499047528847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W149151211","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018812628,0.0019955905,0.97058624,0.00031954574,0.00029428475,0.00016448995,0.00061713654,0.004230638,0.0029793791],"genre_scores_gemma":[0.11973987,0.0009646419,0.8721678,0.0001468545,0.0002058779,0.00022575348,0.0017180373,0.00023698232,0.0045942],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983569,0.00030163492,0.00016239398,0.00042116648,0.0006539505,0.000103817416],"domain_scores_gemma":[0.9948021,0.0030564906,0.00030813192,0.0009028607,0.00078054273,0.00014995283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015381405,0.0012244147,0.0016328567,0.003752735,0.000784571,0.0023934848,0.0015054696,0.0008652643,0.008244383],"category_scores_gemma":[0.009540375,0.00089166395,0.0011802679,0.003638195,0.0006452451,0.0044287373,0.0017285255,0.0017015346,0.00543207],"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":[0.0010059836,0.00014569699,0.0029453868,0.00072646746,0.00012010441,0.00043464926,0.00015651858,0.010222299,0.02180845,0.03601666,0.014752496,0.9116652],"study_design_scores_gemma":[0.000335688,0.0006429533,0.002673509,0.00024099268,0.0001754091,0.004220232,0.00020830943,0.6034971,0.040047184,0.30373982,0.04407542,0.00014349457],"about_ca_topic_score_codex":0.0005566436,"about_ca_topic_score_gemma":0.00056902564,"teacher_disagreement_score":0.008244383,"about_ca_system_score_codex":0.00052496674,"about_ca_system_score_gemma":0.000924682,"threshold_uncertainty_score":0.027580261},"labels":[],"label_agreement":null},{"id":"W1496655772","doi":"10.1007/978-3-540-39666-6_5","title":"Associative Classifiers for Medical Images","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":39,"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; Association rule learning; Associative property; Data mining; Artificial intelligence; Architecture; Association (psychology); Pattern recognition (psychology)","score_opus":0.019384155260222174,"score_gpt":0.2787657067286354,"score_spread":0.2593815514684132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1496655772","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023016468,0.009089109,0.9501797,0.00078477856,0.00074226543,0.00018573244,0.0014638449,0.004810245,0.009727866],"genre_scores_gemma":[0.24213856,0.008687603,0.7170676,0.00042640895,0.0010070355,0.00037305758,0.004074156,0.0003746377,0.025850978],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99959034,0.0000510436,0.000036858324,0.000077170036,0.00020854776,0.000036062887],"domain_scores_gemma":[0.9993749,0.0002149967,0.00006220546,0.00013362289,0.00018589031,0.000028446724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080995227,0.00062550313,0.0009876747,0.0024396426,0.00044379046,0.0013676996,0.0010313159,0.0009902385,0.008489068],"category_scores_gemma":[0.0022204323,0.00037382822,0.00071553414,0.0019439557,0.00035887447,0.0019131529,0.0011686622,0.0009294801,0.0051506218],"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":[0.00012826713,0.00008129567,0.0007608223,0.00036074544,0.00006191648,0.00017652177,0.00004366817,0.008043469,0.016854594,0.015357137,0.02120409,0.9369274],"study_design_scores_gemma":[0.0000549189,0.0002531346,0.004713663,0.00027794557,0.00026971928,0.0027707142,0.00015415378,0.71523124,0.07547889,0.11517405,0.0855492,0.00007243732],"about_ca_topic_score_codex":0.00057498453,"about_ca_topic_score_gemma":0.0013037521,"teacher_disagreement_score":0.008489068,"about_ca_system_score_codex":0.00031935427,"about_ca_system_score_gemma":0.00054327806,"threshold_uncertainty_score":0.028398752},"labels":[],"label_agreement":null},{"id":"W1496656439","doi":"10.1007/978-1-4614-8265-9_170","title":"Frequent Itemset Mining with Constraints","year":2018,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Database Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":60,"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","score_opus":0.01845004272450687,"score_gpt":0.23436309959507037,"score_spread":0.2159130568705635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1496656439","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008174474,0.004850945,0.9736534,0.00048421562,0.00030674852,0.00034651413,0.0034956108,0.001635121,0.0070528886],"genre_scores_gemma":[0.05561377,0.0047335704,0.9216141,0.00022908371,0.0003524689,0.0004599162,0.011138499,0.00024279786,0.005615719],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977723,0.0003986299,0.00036363018,0.00051217707,0.0008631832,0.00009010132],"domain_scores_gemma":[0.9953206,0.002985648,0.000238245,0.0007530665,0.0006108181,0.00009160764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016256402,0.0013613746,0.0017774835,0.0034232312,0.00079148484,0.002967403,0.0027835765,0.0008607678,0.009282008],"category_scores_gemma":[0.01206463,0.0011102955,0.0018875513,0.009438309,0.0004821759,0.003949612,0.0020357517,0.0018801212,0.005568211],"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":[0.00028634848,0.00021017983,0.0024234962,0.0017325241,0.00028983166,0.0008114812,0.00014507686,0.020201197,0.004120311,0.030099526,0.031022148,0.9086579],"study_design_scores_gemma":[0.00015398067,0.0003381716,0.0030388243,0.00090139714,0.00041714121,0.0051878826,0.00028922054,0.6201491,0.01493655,0.23284349,0.121605106,0.00013927002],"about_ca_topic_score_codex":0.00076529407,"about_ca_topic_score_gemma":0.0010319538,"teacher_disagreement_score":0.009282008,"about_ca_system_score_codex":0.00041046296,"about_ca_system_score_gemma":0.0017178106,"threshold_uncertainty_score":0.031051457},"labels":[],"label_agreement":null},{"id":"W1498058970","doi":"","title":"Distributed data mining: why do more than aggregating models","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Disjoint sets; Computer science; Data mining; Cover (algebra); Constraint (computer-aided design); Association rule learning; Data modeling; Mathematics; Database; Engineering","score_opus":0.06916825381192836,"score_gpt":0.31113429894528577,"score_spread":0.2419660451333574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1498058970","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023804298,0.0069290223,0.92519623,0.035210356,0.00080505677,0.00018812432,0.0003057761,0.0014968036,0.006064397],"genre_scores_gemma":[0.3915878,0.006076215,0.58770335,0.0063935523,0.0022531406,0.00044571978,0.00089108554,0.00066166,0.003987538],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98480505,0.0060070795,0.00080037885,0.003232004,0.004535502,0.00061990676],"domain_scores_gemma":[0.939822,0.025454072,0.002688951,0.023955043,0.006314554,0.0017653166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023261363,0.0016013219,0.0038371466,0.0018681216,0.0019718308,0.006987515,0.0047809267,0.0038264259,0.0027187828],"category_scores_gemma":[0.06216265,0.0014031583,0.002048667,0.004092757,0.0034326857,0.034751784,0.0072888113,0.0071647284,0.0021007473],"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":[0.00058398064,0.00044091596,0.023258958,0.0015137679,0.0015127772,0.00045845247,0.0024631517,0.09689033,0.003442763,0.3238588,0.034658507,0.5109175],"study_design_scores_gemma":[0.00010242996,0.00013520471,0.0017509435,0.0004228977,0.0002280678,0.0003358786,0.00096475583,0.1804543,0.0019388932,0.7749567,0.038613077,0.0000968582],"about_ca_topic_score_codex":0.002927443,"about_ca_topic_score_gemma":0.0028728067,"teacher_disagreement_score":0.023261363,"about_ca_system_score_codex":0.0014122981,"about_ca_system_score_gemma":0.0023083,"threshold_uncertainty_score":0.12301934},"labels":[],"label_agreement":null},{"id":"W1498299751","doi":"10.1109/icdm.2003.1250956","title":"Objective and subjective algorithms for grouping association rules","year":2004,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Association rule learning; Computer science; Tree (set theory); Data mining; Association (psychology); Algorithm; Artificial intelligence; Machine learning; Mathematics","score_opus":0.01688733191537938,"score_gpt":0.2661652144815771,"score_spread":0.2492778825661977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1498299751","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018980997,0.00023261648,0.99598926,0.00013165738,0.00004509717,0.0001690985,0.0001566618,0.00040494816,0.0009726252],"genre_scores_gemma":[0.024240868,0.0003434208,0.9729505,0.00011598319,0.00012341978,0.0005659773,0.00062849047,0.00012575995,0.000905505],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.969491,0.010194978,0.0040128017,0.004487996,0.011334832,0.00047836336],"domain_scores_gemma":[0.9279801,0.03650811,0.008456662,0.010827391,0.015188045,0.0010397042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027179215,0.0024037333,0.0021144042,0.011018917,0.0015400369,0.008155041,0.0045790668,0.0022743056,0.005237917],"category_scores_gemma":[0.10665585,0.0010770994,0.0017430584,0.008089153,0.002577858,0.009435773,0.0034024038,0.0027037838,0.0031273896],"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":[0.000293526,0.0005098978,0.0102173155,0.0013399696,0.0005514866,0.0001358204,0.0011162718,0.034973767,0.0037868533,0.0987782,0.008197971,0.8400989],"study_design_scores_gemma":[0.00026182062,0.00050608796,0.009357024,0.0006526756,0.00048676296,0.0008312278,0.0011746862,0.5695354,0.012775838,0.358199,0.04586035,0.00035921988],"about_ca_topic_score_codex":0.0013194035,"about_ca_topic_score_gemma":0.0021334847,"teacher_disagreement_score":0.027179215,"about_ca_system_score_codex":0.0013387207,"about_ca_system_score_gemma":0.00211094,"threshold_uncertainty_score":0.1437391},"labels":[],"label_agreement":null},{"id":"W1498847583","doi":"10.1007/978-3-540-24677-0_7","title":"Fuzzy OLAP Association Rules Mining Based Novel Approach for Multiagent Cooperative Learning","year":2004,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms 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 Calgary","funders":"","keywords":"Online analytical processing; Computer science; Association rule learning; Fuzzy logic; Robustness (evolution); Data mining; Artificial intelligence; Data cube; Machine learning; Cube (algebra); Data warehouse","score_opus":0.022428665202239687,"score_gpt":0.2613589941269323,"score_spread":0.23893032892469263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1498847583","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021265583,0.00020598338,0.97549427,0.0002404064,0.0000678549,0.00012244753,0.00013154114,0.00053212984,0.0019397371],"genre_scores_gemma":[0.23365097,0.00017983165,0.76247334,0.0001371957,0.00006241895,0.00026762378,0.0003343084,0.00003491499,0.002859508],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983834,0.00036885563,0.0001642402,0.00031024998,0.00069120014,0.000082038496],"domain_scores_gemma":[0.9971681,0.001047106,0.0002491001,0.0003539884,0.001076662,0.00010497116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002045359,0.0006739024,0.0011413548,0.001589452,0.0009660269,0.0017850004,0.0022282794,0.0008696678,0.0019044245],"category_scores_gemma":[0.004349893,0.00040885067,0.0008105831,0.001804097,0.00040390948,0.0016672394,0.0016578947,0.0012190394,0.00065986393],"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":[0.00040688255,0.00090671435,0.00763844,0.00031279708,0.00056132925,0.0006395413,0.000598715,0.072963566,0.011481253,0.015753381,0.006651072,0.8820863],"study_design_scores_gemma":[0.0000340091,0.00011127698,0.0014532845,0.000027112917,0.000105340056,0.0004765848,0.00020365315,0.96650743,0.007522107,0.019668847,0.003853422,0.00003697311],"about_ca_topic_score_codex":0.0018756523,"about_ca_topic_score_gemma":0.002882195,"teacher_disagreement_score":0.0022282794,"about_ca_system_score_codex":0.0004244658,"about_ca_system_score_gemma":0.00085578684,"threshold_uncertainty_score":0.010817051},"labels":[],"label_agreement":null},{"id":"W1498871448","doi":"10.1109/icdm.2001.989550","title":"H-mine: hyper-structure mining of frequent patterns in large databases","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":408,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Data mining; Scalability; Overhead (engineering); Process (computing); Set (abstract data type); Database; GSP Algorithm; Association rule learning; Apriori algorithm","score_opus":0.03236253180025632,"score_gpt":0.26034279749472133,"score_spread":0.227980265694465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1498871448","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0392856,0.0009436585,0.95179534,0.00049846055,0.00008460147,0.0003459182,0.0017017407,0.0044644494,0.0008802628],"genre_scores_gemma":[0.11057382,0.00046296313,0.8845419,0.00017620125,0.000106667816,0.0003357707,0.0027963608,0.00015373765,0.0008526726],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986552,0.00035728439,0.00015570404,0.0002630511,0.0004951757,0.00007365629],"domain_scores_gemma":[0.99440044,0.0033373644,0.0006854302,0.00082620175,0.0005716637,0.00017896388],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002300002,0.00075832277,0.0010720774,0.003917022,0.0009124177,0.0013373538,0.0019073287,0.0009996117,0.0014900636],"category_scores_gemma":[0.00993496,0.0006545185,0.0009156875,0.003922861,0.00073061994,0.0032752424,0.0013841228,0.00090608996,0.0010148396],"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":[0.0006749117,0.0004596098,0.018453743,0.0008847728,0.0004228011,0.000641374,0.000637886,0.049126085,0.013035332,0.018754527,0.016759902,0.88014895],"study_design_scores_gemma":[0.00032507308,0.0004867192,0.0059457053,0.0001317067,0.00014931757,0.0019662562,0.00038538733,0.8569765,0.025556374,0.08838577,0.019598115,0.0000930728],"about_ca_topic_score_codex":0.0008472004,"about_ca_topic_score_gemma":0.001281781,"teacher_disagreement_score":0.003917022,"about_ca_system_score_codex":0.00035962538,"about_ca_system_score_gemma":0.0013932567,"threshold_uncertainty_score":0.012163758},"labels":[],"label_agreement":null},{"id":"W1498978191","doi":"10.1007/978-3-540-68125-0_60","title":"FIsViz: A Frequent Itemset Visualizer","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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 Manitoba","funders":"","keywords":"Computer science; Visualization; Representation (politics); Raw data; Information retrieval; Data mining; Information visualization; Programming language","score_opus":0.024085340206847175,"score_gpt":0.2721176414016298,"score_spread":0.24803230119478265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1498978191","genre_codex":"software","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022255268,0.0015883051,0.41068888,0.0007415144,0.00032487113,0.00041809308,0.11412287,0.44198433,0.007875923],"genre_scores_gemma":[0.090239905,0.0013997027,0.7670182,0.0004693564,0.00017621295,0.0010473356,0.11157234,0.017183643,0.01089331],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99951255,0.000064984204,0.00007399704,0.00010349971,0.00020989747,0.00003499402],"domain_scores_gemma":[0.99836606,0.00091682456,0.00015635094,0.00023367735,0.00022664604,0.00010041562],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084810826,0.0019811532,0.0011580195,0.0067637903,0.0005087257,0.0019514877,0.001806682,0.001194763,0.027543947],"category_scores_gemma":[0.005063363,0.0009564229,0.0014192389,0.003891511,0.00017797324,0.00222086,0.0016328082,0.0011860525,0.0082737105],"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":[0.0018707928,0.00028477283,0.008137575,0.0024447087,0.00057273335,0.0014467565,0.00065596605,0.010094417,0.023805475,0.009454934,0.34684926,0.5943826],"study_design_scores_gemma":[0.00110564,0.00059112336,0.011369717,0.000664706,0.00054333266,0.004058702,0.00044712616,0.3706598,0.059834607,0.0533676,0.49701664,0.0003409993],"about_ca_topic_score_codex":0.0017051608,"about_ca_topic_score_gemma":0.0024859218,"teacher_disagreement_score":0.027543947,"about_ca_system_score_codex":0.00030416815,"about_ca_system_score_gemma":0.00059576554,"threshold_uncertainty_score":0.092143655},"labels":[],"label_agreement":null},{"id":"W1500035374","doi":"10.1007/3-540-45153-6_3","title":"A Low-Scan Incremental Association Rule Maintenance Method Based on the Apriori Property","year":2001,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":32,"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":"Association rule learning; Apriori algorithm; Property (philosophy); Data mining; A priori and a posteriori; Computer science; Association (psychology); Psychology; Philosophy","score_opus":0.018131908722941844,"score_gpt":0.2554127638247678,"score_spread":0.23728085510182595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1500035374","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0095915515,0.0004629764,0.9827077,0.00014772065,0.00011075758,0.00012373825,0.00032728032,0.0056396746,0.000888604],"genre_scores_gemma":[0.044226877,0.00015344293,0.9527708,0.000104142004,0.00009641101,0.0001380538,0.0008356036,0.00021826719,0.0014564119],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875224,0.00018132711,0.00015379714,0.00030529592,0.0005636906,0.000043708624],"domain_scores_gemma":[0.9931899,0.0033283713,0.00041236152,0.0013768554,0.0015027162,0.00018979714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022140383,0.00073753536,0.0015713495,0.0034723568,0.0007357313,0.0015603475,0.0031615938,0.0008566484,0.003747907],"category_scores_gemma":[0.007419437,0.0007905843,0.00082644704,0.0030206938,0.00046208833,0.0024285065,0.0011325798,0.0014599791,0.0021039927],"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":[0.00036462815,0.00021973302,0.0017637565,0.00014389485,0.00013615028,0.00022063636,0.000099223886,0.003699523,0.01280295,0.0023776311,0.006672933,0.97149897],"study_design_scores_gemma":[0.0006339941,0.0008503997,0.003958384,0.00009220386,0.0006865484,0.004574312,0.00015894385,0.8660646,0.065051034,0.031595152,0.026145246,0.00018919761],"about_ca_topic_score_codex":0.0011631564,"about_ca_topic_score_gemma":0.0021731819,"teacher_disagreement_score":0.003747907,"about_ca_system_score_codex":0.00021554623,"about_ca_system_score_gemma":0.0008758106,"threshold_uncertainty_score":0.012538016},"labels":[],"label_agreement":null},{"id":"W1500622093","doi":"10.1007/978-3-642-11164-8_100","title":"Evolutionary and Iterative Crisp and Rough Clustering I: Theory","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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":"Saint Mary's University","funders":"","keywords":"Cluster analysis; Rough set; Computer science; Data mining; Medoid; Canopy clustering algorithm; CURE data clustering algorithm; Correlation clustering; Single-linkage clustering; Algorithm; Artificial intelligence","score_opus":0.013991867339433119,"score_gpt":0.24997972367051774,"score_spread":0.23598785633108463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1500622093","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0053777234,0.001350487,0.98791564,0.0003098381,0.00008315965,0.000025843674,0.00003009543,0.00006255461,0.0048445594],"genre_scores_gemma":[0.22890534,0.0030642299,0.75269896,0.00029113106,0.00044195534,0.00027965487,0.00018172654,0.00017032046,0.013966748],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99805176,0.00067180593,0.00011539724,0.00031202694,0.00073785346,0.00011108594],"domain_scores_gemma":[0.9933343,0.004604564,0.00040888612,0.00073182245,0.0007834278,0.0001369365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00336477,0.00074480753,0.0015532558,0.001834831,0.0011950635,0.00253373,0.003058964,0.0018211337,0.0030591139],"category_scores_gemma":[0.015138384,0.0010491812,0.0018234391,0.0036050002,0.0036055811,0.0035641787,0.0026116623,0.002490969,0.0005443437],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024689023,0.000025290708,0.00044693577,0.00014169961,0.000054325723,0.000044792592,0.00024554512,0.11701981,0.0005729453,0.8129912,0.0023446665,0.06608815],"study_design_scores_gemma":[0.0000074741433,0.000028574723,0.0003382775,0.000036201534,0.00002056008,0.00011368197,0.00005093592,0.39709517,0.00045643278,0.59773177,0.004094419,0.00002645905],"about_ca_topic_score_codex":0.0022353258,"about_ca_topic_score_gemma":0.0017944964,"teacher_disagreement_score":0.00336477,"about_ca_system_score_codex":0.0020485616,"about_ca_system_score_gemma":0.001226299,"threshold_uncertainty_score":0.017794847},"labels":[],"label_agreement":null},{"id":"W1500871275","doi":"10.1007/3-540-39963-1_59","title":"Parametric Algorithms for Mining Share Frequent Itemsets","year":2000,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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":"University of Regina","funders":"","keywords":"Computer science; Association rule learning; Data mining; Classifier (UML); Algorithm; Parametric statistics; Factor (programming language); Artificial intelligence; Machine learning; Mathematics; Statistics","score_opus":0.03667179637015774,"score_gpt":0.2820428196481652,"score_spread":0.24537102327800744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1500871275","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009894482,0.00056464766,0.98759216,0.00015022502,0.000027845634,0.00008666997,0.00023278646,0.0006518412,0.00079937186],"genre_scores_gemma":[0.27147046,0.001384412,0.7197973,0.00013985299,0.0002495629,0.0009658442,0.002720388,0.00027894505,0.002993193],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99505746,0.0017080625,0.0005406425,0.0007857619,0.0016327343,0.00027533245],"domain_scores_gemma":[0.9692322,0.021176826,0.0014516208,0.0058664186,0.001952913,0.00031995442],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050593764,0.0011762623,0.0029099886,0.0036817188,0.0012239342,0.0030634778,0.005770573,0.0019210358,0.004968332],"category_scores_gemma":[0.04681001,0.0014259905,0.001953796,0.007852887,0.0017075936,0.009655542,0.00500867,0.0030774684,0.0019077238],"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":[0.0007579372,0.00042755794,0.004917857,0.00063410786,0.00023292212,0.0002408415,0.00036737166,0.17325857,0.0020724437,0.09126683,0.0064273113,0.71939623],"study_design_scores_gemma":[0.000062964915,0.00020098721,0.0009553045,0.000058202048,0.000067456094,0.00048369027,0.0001784582,0.77323467,0.0014085999,0.21982652,0.0034847793,0.000038295188],"about_ca_topic_score_codex":0.0006846749,"about_ca_topic_score_gemma":0.0008268417,"teacher_disagreement_score":0.005770573,"about_ca_system_score_codex":0.0007762852,"about_ca_system_score_gemma":0.0012674237,"threshold_uncertainty_score":0.026756883},"labels":[],"label_agreement":null},{"id":"W1502241097","doi":"10.1007/3-540-45571-x_33","title":"AViz: A Visualization System for Discovering Numeric Association Rules","year":2000,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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 Waterloo","funders":"","keywords":"Computer science; Association rule learning; Visualization; Discretization; Data mining; Set (abstract data type); Data visualization; Raw data; Process (computing); Association (psychology); Information visualization; Bin; Theoretical computer science; Algorithm; Mathematics; Programming language","score_opus":0.012524215775382722,"score_gpt":0.2550527273849601,"score_spread":0.2425285116095774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1502241097","genre_codex":"software","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026582366,0.0019509674,0.41757944,0.00090444443,0.00035126504,0.00036575634,0.065444045,0.47756907,0.009252522],"genre_scores_gemma":[0.10492762,0.0024729467,0.8039283,0.000637656,0.00020225135,0.001048588,0.060703874,0.012565092,0.013513593],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994879,0.00007750432,0.00005991435,0.00009439866,0.00025255408,0.000027634807],"domain_scores_gemma":[0.99769956,0.0015247036,0.00017333422,0.00023408547,0.00027775788,0.000090696994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010826689,0.0022024151,0.0011099417,0.005403811,0.0005048792,0.0022565008,0.0014577016,0.0009525506,0.028532676],"category_scores_gemma":[0.004678999,0.00079300255,0.0010152662,0.003300817,0.00019946917,0.0016777073,0.0014464429,0.001080275,0.0059015136],"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":[0.0014541931,0.00020591414,0.007930215,0.0022370827,0.000518839,0.0008438194,0.00076994597,0.007950473,0.028071549,0.007082966,0.32148102,0.621454],"study_design_scores_gemma":[0.0014546339,0.0005836993,0.019770239,0.0008196585,0.0010398983,0.0029995332,0.00055891223,0.36751345,0.08609691,0.05872492,0.4599489,0.0004892151],"about_ca_topic_score_codex":0.0034563143,"about_ca_topic_score_gemma":0.0051806,"teacher_disagreement_score":0.028532676,"about_ca_system_score_codex":0.000309223,"about_ca_system_score_gemma":0.0007550878,"threshold_uncertainty_score":0.095451355},"labels":[],"label_agreement":null},{"id":"W1506481577","doi":"","title":"Minimum description length principle: generators are preferable to closed patterns","year":2006,"lang":"en","type":"article","venue":"National University of Singapore","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Generator (circuit theory); Cardinality (data modeling); Computer science; Algorithm; Closed set; Minimum description length; Set (abstract data type); Equivalence class (music); Digital pattern generator; Mathematics; Data mining; Discrete mathematics; Power (physics)","score_opus":0.022394672046108455,"score_gpt":0.22327938052887616,"score_spread":0.2008847084827677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1506481577","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03936413,0.0006212974,0.95234185,0.0016191035,0.00008954642,0.0001632765,0.00068411115,0.00080937153,0.0043072784],"genre_scores_gemma":[0.29870036,0.00068782916,0.69264865,0.0010243977,0.0003459872,0.00039535674,0.0019011359,0.00043726622,0.003859161],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9948271,0.0011983818,0.00055581634,0.0015999099,0.0015473156,0.0002715226],"domain_scores_gemma":[0.96376836,0.027043225,0.0018563906,0.004231079,0.0024427928,0.0006581256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0062522027,0.0006600592,0.0013871085,0.0022502665,0.0011197095,0.003445295,0.0018190885,0.0017275894,0.0056948992],"category_scores_gemma":[0.041601636,0.0009182255,0.0012489425,0.0025407546,0.0026339942,0.00864093,0.002751627,0.002631888,0.0016755635],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00085858145,0.00022661148,0.00926066,0.000979768,0.000119722936,0.0008477803,0.0008640714,0.020115972,0.017344058,0.5084796,0.015031401,0.4258717],"study_design_scores_gemma":[0.00013525915,0.0003097826,0.0016414517,0.00009601395,0.000049360016,0.0028915764,0.00021451873,0.10379102,0.013312888,0.86128604,0.016206378,0.00006582631],"about_ca_topic_score_codex":0.00041828997,"about_ca_topic_score_gemma":0.00042897082,"teacher_disagreement_score":0.0062522027,"about_ca_system_score_codex":0.000751325,"about_ca_system_score_gemma":0.0012968724,"threshold_uncertainty_score":0.0330652},"labels":[],"label_agreement":null},{"id":"W1507011461","doi":"10.1007/11553939_136","title":"On Pruning and Tuning Rules for Associative Classifiers","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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":"University of Alberta","funders":"","keywords":"Pruning; Computer science; Associative property; Association rule learning; Artificial intelligence; Machine learning; Data mining; Mathematics","score_opus":0.02461707479536234,"score_gpt":0.2688313340784305,"score_spread":0.24421425928306817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1507011461","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030396117,0.0015768385,0.96212286,0.0003876138,0.00019759822,0.00022747819,0.0002941084,0.0016201413,0.0031771932],"genre_scores_gemma":[0.21439195,0.000794531,0.77603114,0.00046780086,0.0003605458,0.00032490477,0.0017721799,0.00037673407,0.005480163],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99224526,0.0020630767,0.0011386072,0.0011421274,0.0029096475,0.00050126936],"domain_scores_gemma":[0.9517221,0.03692093,0.0010526724,0.005337271,0.00457429,0.0003928368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010479717,0.001451057,0.003415917,0.0031082046,0.0017228543,0.0029920037,0.0054746103,0.0030071365,0.0035199127],"category_scores_gemma":[0.05399074,0.0014995242,0.0017151525,0.0034363363,0.0017434285,0.0065644826,0.0026487957,0.0042357002,0.0014742273],"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":[0.00042982714,0.00038214578,0.0042274944,0.00021863215,0.00018619379,0.00019502803,0.00031070708,0.117100455,0.0032970135,0.025645819,0.010570627,0.8374361],"study_design_scores_gemma":[0.00007178373,0.00008993313,0.0012321209,0.00013478538,0.00014653742,0.00022121282,0.00008273342,0.89986855,0.0036534974,0.09091723,0.0035508678,0.000030734376],"about_ca_topic_score_codex":0.006538289,"about_ca_topic_score_gemma":0.009097632,"teacher_disagreement_score":0.010479717,"about_ca_system_score_codex":0.0010824471,"about_ca_system_score_gemma":0.0014140818,"threshold_uncertainty_score":0.055422723},"labels":[],"label_agreement":null},{"id":"W1508448864","doi":"10.1109/ines.2005.1555144","title":"Performance analysis of incremental update of association rules mining approaches","year":2005,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms 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 Calgary","funders":"","keywords":"Association rule learning; Computer science; Data mining; Association (psychology)","score_opus":0.029320136851271026,"score_gpt":0.24032304235497828,"score_spread":0.21100290550370726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1508448864","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7546088,0.005630057,0.22408618,0.0011488706,0.0005699598,0.00037639524,0.0010477318,0.0070625963,0.005469402],"genre_scores_gemma":[0.842404,0.0007887864,0.15205783,0.00016182585,0.00019935581,0.00017126252,0.0019511196,0.00024994902,0.0020157394],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9923349,0.0026902854,0.0005894353,0.00081345486,0.0030232177,0.0005487289],"domain_scores_gemma":[0.9168557,0.062109526,0.0020225325,0.008479131,0.009472325,0.0010608014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010140396,0.0009916254,0.001704711,0.0022230654,0.0008834915,0.0022535268,0.0036385597,0.001172029,0.0024208482],"category_scores_gemma":[0.06381198,0.00060564437,0.0006183729,0.0031379338,0.0005406579,0.0026424709,0.0014941961,0.0013107586,0.0008225102],"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":[0.0066762194,0.0013629199,0.028899448,0.00035229334,0.00039905065,0.00032317647,0.00030418654,0.17499433,0.008334665,0.004114806,0.007819589,0.7664193],"study_design_scores_gemma":[0.00013899144,0.0005801608,0.002720171,0.000014875987,0.00016105476,0.00031941835,0.00008354814,0.9877104,0.00541026,0.0018696913,0.0009701329,0.000021313115],"about_ca_topic_score_codex":0.0057721054,"about_ca_topic_score_gemma":0.0048654154,"teacher_disagreement_score":0.010140396,"about_ca_system_score_codex":0.0008897061,"about_ca_system_score_gemma":0.0023774551,"threshold_uncertainty_score":0.053628147},"labels":[],"label_agreement":null},{"id":"W1514433787","doi":"10.1109/nafips.2005.1548588","title":"Generating Collaborative Rule Bases Using Fuzzy C-Means with Feature Partitions","year":2005,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Institute for Biodiagnostics","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pooling; Computer science; Data mining; Feature (linguistics); Fuzzy rule; Fuzzy logic; Base (topology); Sample (material); Abstraction; Artificial intelligence; Machine learning; Fuzzy set; Mathematics","score_opus":0.01795558636845294,"score_gpt":0.26457732863772515,"score_spread":0.24662174226927222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1514433787","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006676999,0.00013114755,0.991475,0.00005395019,0.000027704356,0.00022011226,0.00008903692,0.0007561173,0.00057001616],"genre_scores_gemma":[0.100024946,0.00015409842,0.8979753,0.000092229864,0.00003979545,0.0004851242,0.0005856653,0.00009230017,0.000550564],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9942782,0.0013702475,0.00061482127,0.0012437403,0.0021990913,0.00029396004],"domain_scores_gemma":[0.98208654,0.010626373,0.0010620322,0.0021361008,0.003829279,0.000259755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0065841023,0.0014694234,0.0027310979,0.0031889842,0.001587736,0.002558313,0.0034783266,0.0016265475,0.002447088],"category_scores_gemma":[0.028939992,0.0011490498,0.0025142196,0.002774371,0.0011399813,0.0021978072,0.0023046164,0.0023110283,0.0011279264],"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":[0.00022611367,0.00020304829,0.0017316164,0.00031843528,0.0003304,0.0002700567,0.0004221377,0.45031193,0.0032698421,0.009079379,0.0025468192,0.53129023],"study_design_scores_gemma":[0.000038435483,0.000084046056,0.0002632793,0.000056471294,0.00007329642,0.00008932505,0.000069415444,0.9770179,0.0043391837,0.015815292,0.0021205817,0.000032709115],"about_ca_topic_score_codex":0.0076878797,"about_ca_topic_score_gemma":0.007427304,"teacher_disagreement_score":0.0076878797,"about_ca_system_score_codex":0.0011974524,"about_ca_system_score_gemma":0.001969072,"threshold_uncertainty_score":0.034820497},"labels":[],"label_agreement":null},{"id":"W151447164","doi":"10.1007/978-1-84996-044-1_7","title":"A Framework for Developing Effective Multi-database Mining Applications","year":2010,"lang":"en","type":"book-chapter","venue":"Advanced information and knowledge processing","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":"University of Alberta","funders":"","keywords":"Computer science; Data mining; Database; Representation (politics)","score_opus":0.022846022305936613,"score_gpt":0.3154124619201779,"score_spread":0.2925664396142413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W151447164","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00028980404,0.0000694385,0.9976695,0.0001025801,0.00001465814,0.00005499354,0.00002964665,0.0010311304,0.0007382352],"genre_scores_gemma":[0.007119971,0.00015883447,0.99083394,0.00007578837,0.000021355532,0.0001367284,0.00012600252,0.00016839,0.0013589293],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976311,0.0005280936,0.00029240406,0.00035706573,0.0010382157,0.00015310908],"domain_scores_gemma":[0.9976554,0.0008273061,0.00010507755,0.00069251,0.0005794785,0.00014019287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036070407,0.0012400617,0.0011281746,0.0018605295,0.0013433875,0.0041175596,0.004060515,0.0016620543,0.0053770468],"category_scores_gemma":[0.007928203,0.0013352521,0.0018133103,0.0023000874,0.0014777706,0.005831946,0.004510142,0.0029658505,0.004431867],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000069877606,0.00021850107,0.0007886439,0.0005235296,0.00010130962,0.00042136488,0.0005404375,0.026120208,0.009667852,0.5333071,0.020920644,0.40732062],"study_design_scores_gemma":[0.00003688044,0.00008455819,0.00023671662,0.00020006268,0.000096720374,0.00081915123,0.00016537275,0.42899734,0.016553126,0.4201691,0.13257356,0.00006745876],"about_ca_topic_score_codex":0.0018561683,"about_ca_topic_score_gemma":0.0029747966,"teacher_disagreement_score":0.0053770468,"about_ca_system_score_codex":0.00076797017,"about_ca_system_score_gemma":0.0018260307,"threshold_uncertainty_score":0.01907605},"labels":[],"label_agreement":null},{"id":"W1514516794","doi":"","title":"Mining Frequent Itemsets Using Support Constraints","year":2000,"lang":"en","type":"article","venue":"National University of Singapore","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":132,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Data mining","score_opus":0.03351622836162168,"score_gpt":0.24888331816698817,"score_spread":0.21536708980536648,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1514516794","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06611908,0.003679477,0.911036,0.0016590167,0.0002122865,0.0008472798,0.010764571,0.001887099,0.0037952114],"genre_scores_gemma":[0.2130783,0.0027819956,0.7650843,0.00032326358,0.0003049218,0.0009904788,0.01603237,0.00015691773,0.0012473932],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98875403,0.00259995,0.0023916655,0.0018257825,0.0039548213,0.00047375215],"domain_scores_gemma":[0.96362466,0.025371974,0.0038728605,0.0019989072,0.004421963,0.0007096903],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006301444,0.0017490584,0.002658737,0.010725049,0.0012397127,0.0041117994,0.003236637,0.0020899593,0.0030472076],"category_scores_gemma":[0.043581035,0.001461345,0.0020732728,0.011721422,0.0008334661,0.0074314144,0.0024952558,0.0019818651,0.002138536],"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":[0.0012342988,0.00079344393,0.04355316,0.0034260831,0.0014653567,0.0067584226,0.0011668734,0.09633197,0.014293295,0.04808441,0.021390058,0.76150256],"study_design_scores_gemma":[0.00037645779,0.0007691521,0.008468237,0.0011704687,0.00054232,0.0059730657,0.0018336356,0.6878414,0.023365488,0.22853234,0.040841784,0.00028565121],"about_ca_topic_score_codex":0.0013190837,"about_ca_topic_score_gemma":0.0011526408,"teacher_disagreement_score":0.010725049,"about_ca_system_score_codex":0.00056011736,"about_ca_system_score_gemma":0.0019025302,"threshold_uncertainty_score":0.033325613},"labels":[],"label_agreement":null},{"id":"W1515242312","doi":"10.1007/11548706_8","title":"“Rule + Exception” Strategies for Knowledge Management and Discovery","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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 Regina","funders":"","keywords":"Knowledge extraction; Computer science; Data science; Knowledge management; K-optimal pattern discovery; Artificial intelligence","score_opus":0.02111464550087499,"score_gpt":0.26870675107512376,"score_spread":0.24759210557424877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1515242312","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033908125,0.0004856781,0.98832744,0.00096209213,0.00015772127,0.000115672854,0.0001462896,0.0013759101,0.005038414],"genre_scores_gemma":[0.04726003,0.00042137288,0.94616574,0.0006397087,0.0001701713,0.00015338139,0.0005785405,0.00022761579,0.0043835114],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9911111,0.0034690266,0.0011186477,0.0012288332,0.0027160763,0.0003563424],"domain_scores_gemma":[0.9790718,0.010684438,0.0006362352,0.0065113306,0.0026827843,0.0004134108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009250066,0.0013816502,0.0014608881,0.0031951577,0.0016156067,0.0053419764,0.00532719,0.0023012112,0.005917736],"category_scores_gemma":[0.02890962,0.0008146914,0.0018267384,0.0034505054,0.0035317724,0.009876534,0.0034059,0.0032510695,0.0032016218],"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":[0.00021901543,0.00016187556,0.0012523712,0.00038626866,0.00016364429,0.0005165608,0.0005543324,0.009843982,0.0029205498,0.37829039,0.018422468,0.5872684],"study_design_scores_gemma":[0.000049479833,0.00009376289,0.0002231166,0.00013966022,0.000168397,0.0007519012,0.00021428734,0.12313094,0.009867474,0.8241495,0.04115399,0.000057532256],"about_ca_topic_score_codex":0.0017826053,"about_ca_topic_score_gemma":0.0028950141,"teacher_disagreement_score":0.009250066,"about_ca_system_score_codex":0.0008237153,"about_ca_system_score_gemma":0.0021353003,"threshold_uncertainty_score":0.04891956},"labels":[],"label_agreement":null},{"id":"W1516927529","doi":"","title":"Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":92,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia; University of Alberta","funders":"","keywords":"LEAPS; Computer science; Data science; Knowledge extraction; Big data; Library science; World Wide Web; Data mining","score_opus":0.10985239342913572,"score_gpt":0.31228025362724704,"score_spread":0.20242786019811132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1516927529","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02400151,0.25040743,0.27339396,0.08418304,0.17239617,0.0032324202,0.053075768,0.02835288,0.11095681],"genre_scores_gemma":[0.054428156,0.18666956,0.26893097,0.016378028,0.024569951,0.0018235109,0.19529982,0.0048764558,0.24702361],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98891467,0.0025311538,0.0012801826,0.0013994132,0.0053090514,0.0005655119],"domain_scores_gemma":[0.98456097,0.005163674,0.0008116939,0.002610703,0.0042127958,0.002640135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009396731,0.0024674642,0.0055419067,0.0073954216,0.0022191217,0.014408593,0.0054290905,0.0038590296,0.04158947],"category_scores_gemma":[0.021978194,0.0015995405,0.0027500102,0.005755857,0.0022347355,0.011232416,0.0058805915,0.007281394,0.029524524],"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":[0.00020734544,0.0002532863,0.0016747055,0.0008509424,0.0002883153,0.00021633097,0.00018168105,0.00096064375,0.00070635305,0.0032713618,0.8051631,0.18622585],"study_design_scores_gemma":[0.000071506816,0.00010889563,0.0023594124,0.00057879084,0.00014813631,0.0005622441,0.00031857868,0.005462686,0.0010243851,0.012035603,0.9772399,0.000089755355],"about_ca_topic_score_codex":0.0076422608,"about_ca_topic_score_gemma":0.012935411,"teacher_disagreement_score":0.04158947,"about_ca_system_score_codex":0.0021934884,"about_ca_system_score_gemma":0.007750295,"threshold_uncertainty_score":0.13913065},"labels":[],"label_agreement":null},{"id":"W15173781","doi":"10.1007/978-3-642-32600-4_34","title":"Mining Frequent Itemsets Using Node-Sets of a Prefix-Tree","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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":"Carleton University","funders":"","keywords":"Computer science; Trie; Data mining; Prefix; Node (physics); Set (abstract data type); Tree (set theory); Construct (python library); Database; Tree structure; Data structure; Theoretical computer science; Algorithm; Binary tree; Mathematics","score_opus":0.039212616071202765,"score_gpt":0.27851021173089596,"score_spread":0.2392975956596932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W15173781","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2137965,0.004093731,0.7604329,0.00051634276,0.00024222248,0.0008220301,0.013821027,0.0022695735,0.0040056612],"genre_scores_gemma":[0.20625035,0.0015970393,0.776827,0.00009561606,0.00010954419,0.00040382709,0.013541152,0.00009912447,0.0010764138],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99827206,0.00022951177,0.00034493514,0.00037875006,0.00067390746,0.000100736004],"domain_scores_gemma":[0.994194,0.003723906,0.00041941553,0.0004819784,0.0009527041,0.00022793747],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012145338,0.0008445342,0.001638605,0.007425793,0.0010872874,0.002463634,0.0015173076,0.0013234605,0.0023194663],"category_scores_gemma":[0.009684575,0.0007676431,0.0021237067,0.00966258,0.00058540015,0.004049035,0.0012483858,0.0010445098,0.0014692043],"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":[0.0012353536,0.0006642346,0.05418014,0.0030838079,0.00087326317,0.0036443162,0.0013697331,0.065232456,0.02547621,0.029709443,0.011741182,0.80278987],"study_design_scores_gemma":[0.00016572844,0.0008789176,0.014124375,0.00086323067,0.00075912377,0.006874508,0.0012659553,0.80895877,0.01481698,0.1271425,0.02400641,0.00014344818],"about_ca_topic_score_codex":0.0012434574,"about_ca_topic_score_gemma":0.002048211,"teacher_disagreement_score":0.007425793,"about_ca_system_score_codex":0.00042089086,"about_ca_system_score_gemma":0.0010869933,"threshold_uncertainty_score":0.0077593327},"labels":[],"label_agreement":null},{"id":"W1518466950","doi":"10.1007/11557067_6","title":"A Lookahead Branch-and-Bound Algorithm for the Maximum Quartet Consistency Problem","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":11,"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":"Heuristics; Branch and bound; Consistency (knowledge bases); Set (abstract data type); Algorithm; Heuristic; Construct (python library); Computer science; Scheme (mathematics); Running time; Upper and lower bounds; Mathematics; Mathematical optimization; Artificial intelligence","score_opus":0.018641154443467676,"score_gpt":0.25538623082764317,"score_spread":0.2367450763841755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1518466950","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025412936,0.00075646443,0.9580514,0.0012283222,0.00030471172,0.0004032675,0.00064021046,0.0045326096,0.008670052],"genre_scores_gemma":[0.12997791,0.00028893963,0.8609096,0.0005056575,0.00017031659,0.00042309143,0.0018181626,0.0010364638,0.004869945],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99839395,0.00037893976,0.00011483433,0.00044278853,0.00041176716,0.0002576285],"domain_scores_gemma":[0.99418396,0.0037594677,0.00026075915,0.0010250277,0.000502811,0.00026797818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024089692,0.001570591,0.002697546,0.0018397191,0.0016505341,0.0026792765,0.0045587267,0.0022159237,0.02238127],"category_scores_gemma":[0.010473177,0.0012593709,0.0017229256,0.0038656525,0.0012008996,0.0051944936,0.0035484552,0.0043732645,0.0027219688],"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":[0.0015464947,0.0009529622,0.0013251848,0.0007572475,0.00016913113,0.0001955328,0.00033906294,0.16878167,0.0064669373,0.059433665,0.041213103,0.7188191],"study_design_scores_gemma":[0.0006037181,0.00021177698,0.00043762603,0.0000644368,0.000120135366,0.00013029258,0.00012501075,0.8138145,0.0025684286,0.17747186,0.0044139633,0.00003816443],"about_ca_topic_score_codex":0.0040452257,"about_ca_topic_score_gemma":0.0071892156,"teacher_disagreement_score":0.02238127,"about_ca_system_score_codex":0.0014935175,"about_ca_system_score_gemma":0.003510948,"threshold_uncertainty_score":0.07487285},"labels":[],"label_agreement":null},{"id":"W1518718261","doi":"","title":"Efficiently mining frequent itemsets from very large databases","year":2004,"lang":"en","type":"dissertation","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Data mining; Computer science; Association rule learning; Scalability; Tree (set theory); Trie; Data cube; Data structure; Tree structure; Traverse; Algorithm; Database; Mathematics; Binary tree","score_opus":0.02138563043240531,"score_gpt":0.288638789436547,"score_spread":0.2672531590041417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1518718261","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10905034,0.0034743005,0.87261415,0.0011644321,0.00028485092,0.0007663293,0.0066176318,0.0040319758,0.0019959547],"genre_scores_gemma":[0.21227804,0.001532863,0.77013314,0.00028079795,0.00020676527,0.00074407103,0.0139294835,0.00015268468,0.0007421367],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9934581,0.0012278341,0.0012653765,0.0009875672,0.002764356,0.0002967717],"domain_scores_gemma":[0.97838277,0.014985158,0.0016384872,0.0018780663,0.0028137432,0.0003017887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033672622,0.0017482409,0.003058564,0.008907005,0.0014973019,0.0034782933,0.0026938757,0.0015674998,0.0010208703],"category_scores_gemma":[0.02609988,0.0013782674,0.0022467994,0.009868909,0.00062457356,0.0058024055,0.0020758654,0.0019353715,0.0012566108],"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":[0.00070307584,0.00055215746,0.027677033,0.0021545843,0.0010493003,0.0036218797,0.0008345323,0.08783394,0.021527046,0.011451191,0.01839436,0.8242009],"study_design_scores_gemma":[0.00016741543,0.00044887207,0.009607308,0.0004039407,0.000409754,0.0038026874,0.0015999547,0.8343926,0.020393455,0.110099405,0.018532949,0.00014164974],"about_ca_topic_score_codex":0.0014192754,"about_ca_topic_score_gemma":0.002155655,"teacher_disagreement_score":0.008907005,"about_ca_system_score_codex":0.0007101731,"about_ca_system_score_gemma":0.0019151086,"threshold_uncertainty_score":0.01780796},"labels":[],"label_agreement":null},{"id":"W1525895928","doi":"10.1002/sam.11394","title":"Standardizing interestingness measures for association rules","year":2018,"lang":"en","type":"preprint","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; McMaster University; Thompson Rivers University","funders":"Ontario Ministry of Research and Innovation; Natural Sciences and Engineering Research Council of Canada","keywords":"Measure (data warehouse); Lift (data mining); Computer science; Raw data; Association rule learning; Standardization; Association (psychology); Data mining; Value (mathematics); Machine learning; Psychology","score_opus":0.12011645933756977,"score_gpt":0.3973333708886629,"score_spread":0.2772169115510931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1525895928","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12049691,0.002910347,0.86872673,0.0011252942,0.00026205342,0.00043252818,0.00096805143,0.0007440138,0.004334023],"genre_scores_gemma":[0.58556116,0.0008490371,0.4091456,0.00041385472,0.00045504596,0.0011005031,0.001713499,0.0003093128,0.00045200862],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9270636,0.03142687,0.009621611,0.010938618,0.019757807,0.0011914774],"domain_scores_gemma":[0.577021,0.3136332,0.028638726,0.05472247,0.023714712,0.0022699533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07722302,0.0019437418,0.0030587527,0.012958147,0.0015925863,0.008040673,0.0032188133,0.0029100345,0.0013124344],"category_scores_gemma":[0.35292897,0.0009869298,0.0023849981,0.010109475,0.0065304176,0.011208287,0.0053651077,0.005090179,0.00041465712],"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":[0.0010301556,0.0006186695,0.059247326,0.0015680771,0.0022460595,0.00042872253,0.0018023731,0.15016076,0.010642861,0.39578864,0.004936362,0.37153006],"study_design_scores_gemma":[0.00015547365,0.00072807254,0.009950608,0.00042007022,0.00033637026,0.00063906895,0.0004844565,0.23339345,0.012096748,0.7362395,0.0053640893,0.0001920911],"about_ca_topic_score_codex":0.00045792753,"about_ca_topic_score_gemma":0.00049358263,"teacher_disagreement_score":0.07722302,"about_ca_system_score_codex":0.0025043993,"about_ca_system_score_gemma":0.0020103345,"threshold_uncertainty_score":0.40839922},"labels":[],"label_agreement":null},{"id":"W1526785773","doi":"","title":"Building predictors from vertically distributed data","year":2004,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Data mining; Raw data; Voting; Majority rule; Variety (cybernetics); Decision tree; Range (aeronautics); Tree (set theory); Volume (thermodynamics); Distributed database; Data modeling; Artificial intelligence; Distributed computing; Database","score_opus":0.030024340511999526,"score_gpt":0.27752148622518763,"score_spread":0.2474971457131881,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1526785773","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051801037,0.00051427726,0.9424629,0.00045370465,0.00007699482,0.00008845481,0.00044182324,0.0029601753,0.0012005278],"genre_scores_gemma":[0.6617856,0.0006851087,0.32842407,0.00022036197,0.00025291866,0.00037820215,0.003687767,0.00029203913,0.0042738984],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986916,0.0003508765,0.00006932077,0.00039392101,0.00034846354,0.00014580654],"domain_scores_gemma":[0.9958026,0.0019714716,0.00034281297,0.00086371595,0.0008747422,0.00014465701],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022007108,0.001226923,0.0016960704,0.0014328156,0.00077772944,0.0014075388,0.0013319802,0.0008205934,0.0020610725],"category_scores_gemma":[0.0080502285,0.0008219915,0.0007886464,0.0019306762,0.0004384767,0.0022268572,0.0019463383,0.0019642895,0.001244138],"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":[0.00032604346,0.000172546,0.015002439,0.00009796765,0.0002126556,0.00031069625,0.0001698403,0.5878337,0.0047783316,0.007620423,0.008437848,0.37503755],"study_design_scores_gemma":[0.000010725723,0.000022677725,0.0004424007,0.0000074732934,0.000012992701,0.000018949302,0.000024739216,0.992019,0.0010312787,0.005755948,0.00064984453,0.000004026748],"about_ca_topic_score_codex":0.0065146955,"about_ca_topic_score_gemma":0.00963105,"teacher_disagreement_score":0.0065146955,"about_ca_system_score_codex":0.00064720545,"about_ca_system_score_gemma":0.0015253985,"threshold_uncertainty_score":0.012953579},"labels":[],"label_agreement":null},{"id":"W1528514856","doi":"10.1007/11589990_129","title":"Mining with Constraints by Pruning and Avoiding Ineffectual Processing","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms 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 Alberta","funders":"","keywords":"Computer science; Pruning; Set (abstract data type); Association rule learning; Dual (grammatical number); Data mining; Algorithm; Theoretical computer science; Programming language","score_opus":0.012739291039529406,"score_gpt":0.23789444974604876,"score_spread":0.22515515870651936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1528514856","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040047433,0.0009100279,0.9497389,0.0011074472,0.0001448325,0.00045836926,0.0007271317,0.0024182785,0.00444756],"genre_scores_gemma":[0.115517475,0.0003917594,0.8781191,0.00041000394,0.00014987419,0.00032673028,0.002055178,0.0005146816,0.0025152052],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9916712,0.0024234804,0.0008006238,0.0010832378,0.0034297719,0.000591655],"domain_scores_gemma":[0.9660885,0.021422168,0.001210519,0.00806356,0.0028294302,0.00038591382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006007128,0.0016314619,0.0028489055,0.0031484985,0.0017767737,0.003915298,0.0052537476,0.0022432383,0.0041376916],"category_scores_gemma":[0.04284527,0.0016784007,0.0024485688,0.0048378254,0.0017180141,0.006649202,0.0033235825,0.0034876077,0.0015628472],"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":[0.0007646503,0.00058461115,0.008009093,0.0010206832,0.00045874622,0.0013172481,0.0004785815,0.09244013,0.013296194,0.054448895,0.023050409,0.80413073],"study_design_scores_gemma":[0.0001725636,0.00017540749,0.0017215447,0.00020391995,0.00035515867,0.0010976328,0.000223892,0.72927624,0.017100561,0.23156382,0.018043011,0.000066288216],"about_ca_topic_score_codex":0.0024945673,"about_ca_topic_score_gemma":0.007038993,"teacher_disagreement_score":0.006007128,"about_ca_system_score_codex":0.00070745085,"about_ca_system_score_gemma":0.0038100681,"threshold_uncertainty_score":0.031769156},"labels":[],"label_agreement":null},{"id":"W1529627684","doi":"10.1007/978-3-540-72665-4_26","title":"A Profit-Based Business Model for Evaluating Rule Interestingness","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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 Regina","funders":"","keywords":"Computer science; Profit (economics); Database transaction; Business rule; Affinity analysis; Data mining; Association rule learning; Data science; Database; Business process; Marketing; Business; Microeconomics","score_opus":0.09324250939051158,"score_gpt":0.34500686522795604,"score_spread":0.25176435583744444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1529627684","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1499676,0.0007469084,0.8369236,0.0009905985,0.00010710163,0.00048530096,0.002112225,0.0024245826,0.0062422073],"genre_scores_gemma":[0.73304445,0.00021663922,0.2611313,0.00019993613,0.00009536504,0.00036754637,0.0022510714,0.00011972161,0.002574013],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99483716,0.0010626197,0.0004645138,0.00062328886,0.0027204205,0.00029204492],"domain_scores_gemma":[0.98837644,0.007290019,0.00088261697,0.001024153,0.0020531416,0.00037355753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0062839086,0.0012713543,0.0015012875,0.0064585214,0.000740089,0.0031529374,0.002168667,0.0018174172,0.0026733414],"category_scores_gemma":[0.016791282,0.0004203019,0.0015669581,0.0038887132,0.00089513493,0.004977091,0.0012819641,0.0013233653,0.0010060889],"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":[0.0015926879,0.0013229933,0.04498649,0.00034216704,0.00061295554,0.0005312282,0.00021800502,0.352337,0.008366728,0.046973657,0.009895749,0.5328202],"study_design_scores_gemma":[0.000025828405,0.00009060948,0.001226376,0.000015647667,0.000059030197,0.00012514296,0.000029537414,0.9808872,0.0011980562,0.015726576,0.00059859775,0.00001750039],"about_ca_topic_score_codex":0.003456635,"about_ca_topic_score_gemma":0.004452362,"teacher_disagreement_score":0.0064585214,"about_ca_system_score_codex":0.0019374727,"about_ca_system_score_gemma":0.0013453958,"threshold_uncertainty_score":0.033232868},"labels":[],"label_agreement":null},{"id":"W1530348080","doi":"10.1109/nafips.2001.944678","title":"Linguistic association rules","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Association rule learning; Computer science; ENCODE; Association (psychology); Class (philosophy); Apriori algorithm; A priori and a posteriori; Database transaction; Hypercube; Fuzzy logic; Artificial intelligence; Data mining; Natural language processing; Theoretical computer science; Information retrieval; Programming language","score_opus":0.020691566905689292,"score_gpt":0.2343969811271816,"score_spread":0.2137054142214923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1530348080","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009844349,0.0056982245,0.95255196,0.002723605,0.001031067,0.00093477784,0.005203567,0.0016544141,0.020358069],"genre_scores_gemma":[0.15581885,0.005949021,0.8151544,0.0020675894,0.0013357365,0.0019703156,0.008271932,0.00019565706,0.009236471],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98670644,0.0034981023,0.0019932126,0.0029576623,0.0044896887,0.00035483128],"domain_scores_gemma":[0.9710977,0.018515225,0.0026612782,0.0028790513,0.0045731254,0.00027363584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007489816,0.0017171736,0.002145003,0.009076006,0.00213621,0.006030389,0.0029268558,0.002353057,0.011101102],"category_scores_gemma":[0.04303732,0.0007150276,0.0023595598,0.0075098984,0.0016705038,0.0073145092,0.0026002254,0.002378144,0.007010225],"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":[0.0004140007,0.00041015414,0.009934614,0.002626364,0.0009447262,0.0013139787,0.0005881898,0.021658339,0.002693854,0.23429225,0.040932324,0.6841911],"study_design_scores_gemma":[0.00016554189,0.00021327575,0.0031875079,0.0011518741,0.00075893814,0.003137912,0.0005967018,0.13674209,0.0053074844,0.7197307,0.12878862,0.00021939774],"about_ca_topic_score_codex":0.0010365172,"about_ca_topic_score_gemma":0.001270303,"teacher_disagreement_score":0.011101102,"about_ca_system_score_codex":0.00089124136,"about_ca_system_score_gemma":0.0017092727,"threshold_uncertainty_score":0.039610386},"labels":[],"label_agreement":null},{"id":"W1530928975","doi":"10.46430/phen0040","title":"Counting and mining research data with Unix","year":2014,"lang":"en","type":"article","venue":"The Programming Historian","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Unix; Computer science; Operating system","score_opus":0.08445026300515274,"score_gpt":0.32801695271005105,"score_spread":0.2435666897048983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1530928975","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010915477,0.0028571126,0.8639277,0.019951724,0.003990038,0.0003416144,0.0053028553,0.0485629,0.04415054],"genre_scores_gemma":[0.03813229,0.002834168,0.91765517,0.0029462618,0.0018028714,0.0006936888,0.003910419,0.006961522,0.025063595],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99170893,0.0025894532,0.0013529474,0.0012688201,0.0027238904,0.00035593577],"domain_scores_gemma":[0.96520907,0.014316952,0.003420664,0.011549571,0.004229099,0.0012746098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011293009,0.0018342242,0.0015675864,0.006964554,0.002277468,0.014626201,0.0026691798,0.00135453,0.017794294],"category_scores_gemma":[0.075194545,0.0014805568,0.0016058886,0.012586389,0.003161334,0.023319384,0.0069034686,0.005202619,0.017385347],"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":[0.00034575057,0.0000972449,0.011704431,0.0006282182,0.00010534122,0.0002520619,0.0028400444,0.0015058477,0.0018915761,0.27341154,0.18365754,0.5235604],"study_design_scores_gemma":[0.000069902926,0.000114716866,0.004653725,0.00085859693,0.000062084255,0.00066593254,0.0012051226,0.010741744,0.005622971,0.3738923,0.60194397,0.00016898217],"about_ca_topic_score_codex":0.0018429761,"about_ca_topic_score_gemma":0.0016553443,"teacher_disagreement_score":0.017794294,"about_ca_system_score_codex":0.001436884,"about_ca_system_score_gemma":0.003474499,"threshold_uncertainty_score":0.059723854},"labels":[],"label_agreement":null},{"id":"W1533087746","doi":"10.1023/a:1008303008006","title":"Enhancing the Effectiveness of Interactive Case-Based Reasoning with Clustering and Decision Forests","year":2001,"lang":"en","type":"article","venue":"Applied Intelligence","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":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Cluster analysis; Component (thermodynamics); Process (computing); Feature (linguistics); Interface (matter); Knowledge base; Architecture; Case-based reasoning; User interface; Human–computer interaction; Artificial intelligence; Data mining","score_opus":0.012228412820756268,"score_gpt":0.27037196986798795,"score_spread":0.2581435570472317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1533087746","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0976102,0.0006601656,0.88989973,0.00064090546,0.000084363994,0.00027273732,0.00018158209,0.002656857,0.007993411],"genre_scores_gemma":[0.4928913,0.0002525544,0.5050167,0.00015233508,0.00007358923,0.000121263576,0.00037447756,0.00014447603,0.0009733832],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99251705,0.0033043583,0.00048707065,0.00073356024,0.0025895005,0.00036847332],"domain_scores_gemma":[0.9532716,0.03988037,0.0010576249,0.0030510926,0.002299223,0.00043999864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008585591,0.001373777,0.0016707409,0.0030026112,0.0010980635,0.002755242,0.0034180717,0.0021651532,0.0058769328],"category_scores_gemma":[0.041363865,0.0006917083,0.0011762264,0.0021653953,0.0008257354,0.0059063155,0.0029734208,0.0016938039,0.0011420023],"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":[0.0019518574,0.002313919,0.0063687623,0.0005515448,0.0004405608,0.00041394477,0.0008239807,0.2101911,0.011621525,0.019502688,0.005565077,0.74025506],"study_design_scores_gemma":[0.00014776658,0.000112378446,0.0008388714,0.00004833212,0.0001355102,0.000202991,0.00011837606,0.96087754,0.007898254,0.027656866,0.0019293894,0.00003369113],"about_ca_topic_score_codex":0.003598084,"about_ca_topic_score_gemma":0.004120476,"teacher_disagreement_score":0.008585591,"about_ca_system_score_codex":0.000828379,"about_ca_system_score_gemma":0.0013583157,"threshold_uncertainty_score":0.045405447},"labels":[],"label_agreement":null},{"id":"W153355562","doi":"10.1007/978-3-319-14717-8_3","title":"Novel Concise Representations of High Utility Itemsets Using Generator Patterns","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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":"Université de Moncton","funders":"","keywords":"Generator (circuit theory); Computer science; Representation (politics); Set (abstract data type); Task (project management); Data mining; Theoretical computer science; Power (physics); Programming language; Engineering","score_opus":0.039064917401673456,"score_gpt":0.28872565386140603,"score_spread":0.24966073645973258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W153355562","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037982877,0.0010483307,0.95037454,0.00047625013,0.00017642039,0.00019615254,0.004099361,0.0022468483,0.0033991917],"genre_scores_gemma":[0.28916278,0.0013026767,0.6920719,0.00021953676,0.00019411594,0.00037889922,0.010725302,0.00033993827,0.0056048655],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991165,0.0002152525,0.0001157579,0.0001497997,0.00033898026,0.00006375729],"domain_scores_gemma":[0.9968797,0.001526367,0.00038664645,0.0005827974,0.00052854454,0.00009591798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084140874,0.0009115257,0.0007151718,0.0027644155,0.00038567773,0.002106565,0.0012920437,0.00081509096,0.0044529475],"category_scores_gemma":[0.008258251,0.00042855678,0.00067478477,0.0041699316,0.00036015338,0.003324331,0.0012624761,0.0012063242,0.0013486929],"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":[0.0007762331,0.00023998102,0.004931989,0.0008784054,0.00016043747,0.0014652205,0.00062035845,0.07470502,0.012458414,0.15778401,0.028352236,0.71762764],"study_design_scores_gemma":[0.00007739068,0.00021983904,0.0012880156,0.0002250835,0.00010645137,0.0013631481,0.0003101749,0.6914167,0.007155817,0.27717957,0.020607043,0.000050756855],"about_ca_topic_score_codex":0.0006212688,"about_ca_topic_score_gemma":0.0014329527,"teacher_disagreement_score":0.0044529475,"about_ca_system_score_codex":0.00037129998,"about_ca_system_score_gemma":0.00055204256,"threshold_uncertainty_score":0.014896572},"labels":[],"label_agreement":null},{"id":"W1534184292","doi":"10.1007/3-540-45372-5_31","title":"Algorithms for Mining Share Frequent Itemsets Containing Infrequent Subsets","year":2000,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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 Regina","funders":"","keywords":"Computer science; Measure (data warehouse); Heuristic; Database transaction; Closure (psychology); Data mining; Algorithm; Artificial intelligence; Database","score_opus":0.0348531844896007,"score_gpt":0.2800269790353039,"score_spread":0.24517379454570318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1534184292","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024775347,0.0016163306,0.9686441,0.000312041,0.00015633469,0.000433694,0.00080982636,0.0018045139,0.0014478356],"genre_scores_gemma":[0.09129159,0.001170161,0.8988123,0.00022466178,0.000389793,0.00072397914,0.004543299,0.00015775124,0.0026864326],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99743575,0.00036427728,0.00038108235,0.00050824264,0.0011628392,0.00014775709],"domain_scores_gemma":[0.9885833,0.006997921,0.0007733662,0.0018726835,0.0015329556,0.00023982547],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038721638,0.001912988,0.003229318,0.0055719484,0.0015540761,0.0033385998,0.004405543,0.002541672,0.004653104],"category_scores_gemma":[0.014036143,0.0012976051,0.0021262455,0.009349785,0.0009223265,0.007180994,0.0026249506,0.0018684639,0.002863848],"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":[0.000814543,0.00057112525,0.005453404,0.00061853736,0.00036995896,0.00027417866,0.00021737858,0.025725005,0.0048979474,0.01386671,0.00890245,0.93828875],"study_design_scores_gemma":[0.0005091652,0.0008089789,0.003420981,0.00017950317,0.0005219782,0.0023030515,0.00048112773,0.8484389,0.011795909,0.118089534,0.01336498,0.00008593032],"about_ca_topic_score_codex":0.00051682396,"about_ca_topic_score_gemma":0.0012101561,"teacher_disagreement_score":0.0055719484,"about_ca_system_score_codex":0.0006350693,"about_ca_system_score_gemma":0.0011316976,"threshold_uncertainty_score":0.020478249},"labels":[],"label_agreement":null},{"id":"W1534866524","doi":"10.1007/3-540-45571-x_19","title":"COE: Clustering with Obstacles Entities A Preliminary Study","year":2000,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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":"Cluster analysis; Computer science; Data mining; Obstacle; Canopy clustering algorithm; Correlation clustering; CURE data clustering algorithm; Artificial intelligence; Geography","score_opus":0.017078148201986606,"score_gpt":0.24304088995653075,"score_spread":0.22596274175454414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1534866524","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08490135,0.0023070753,0.8883359,0.0010780353,0.00031547804,0.00040969186,0.001778516,0.0030021488,0.017871834],"genre_scores_gemma":[0.25163367,0.001377242,0.71188533,0.0003998041,0.00041354183,0.00029668873,0.006178575,0.001369877,0.026445331],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972645,0.0006296869,0.00015791666,0.0007469752,0.0009898618,0.00021116454],"domain_scores_gemma":[0.9891011,0.00528317,0.00028909996,0.0029667143,0.0019498975,0.0004100597],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024719518,0.0011017837,0.0020495856,0.0030902543,0.0023602084,0.0038926457,0.0046306015,0.0018999451,0.00958137],"category_scores_gemma":[0.020940842,0.0007862876,0.0014288934,0.0074682175,0.0016779781,0.0070283185,0.0033668976,0.0016452287,0.0026508057],"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":[0.0011319878,0.00062428124,0.01363356,0.0008251924,0.00032921537,0.00037063495,0.0011449496,0.16557497,0.008184475,0.15312052,0.035281003,0.61977917],"study_design_scores_gemma":[0.00009666653,0.00022061869,0.004665103,0.00006154075,0.00013131021,0.0005053905,0.00068475486,0.87812495,0.010126678,0.07951578,0.025795173,0.00007207898],"about_ca_topic_score_codex":0.018344985,"about_ca_topic_score_gemma":0.016572269,"teacher_disagreement_score":0.018344985,"about_ca_system_score_codex":0.0015800957,"about_ca_system_score_gemma":0.0015118913,"threshold_uncertainty_score":0.036476433},"labels":[],"label_agreement":null},{"id":"W1535035109","doi":"10.1016/b978-012088469-8.50142-x","title":"CORDS","year":2004,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":11,"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":"Scalability; Benchmark (surveying); Column (typography); Computer science; Set (abstract data type); Range (aeronautics); Data mining; Database; Engineering; Programming language","score_opus":0.017309700185021617,"score_gpt":0.24225151381157778,"score_spread":0.22494181362655616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1535035109","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004526469,0.0011806481,0.003441872,0.00061550405,0.0009287459,0.000048350576,0.0007447227,0.0019480927,0.9906393],"genre_scores_gemma":[0.0007324647,0.0004491861,0.0008251443,0.00014687562,0.000077522556,0.000015390868,0.00049559696,0.00022171636,0.9970361],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99966955,0.00002605526,0.00001776906,0.00007483394,0.0001747796,0.00003696749],"domain_scores_gemma":[0.9994305,0.00006833309,0.000025260735,0.00012971571,0.00022419944,0.00012199804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036105167,0.0012842781,0.00071109756,0.0023388045,0.0012081923,0.0032724258,0.001149046,0.0013554409,0.74520665],"category_scores_gemma":[0.0014088872,0.00045808818,0.00052766246,0.0020752263,0.0005200328,0.0022864563,0.0021603093,0.0011908687,0.68224525],"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":[0.000040738712,0.00004566237,0.00017166398,0.0001810506,0.0000052905484,0.00012374627,0.000085608044,0.00018497555,0.0016935043,0.015196214,0.44939938,0.5328722],"study_design_scores_gemma":[0.00000451119,0.000011125116,0.0001570371,0.000066302135,0.0000032664823,0.00012875334,0.000024410949,0.00011418047,0.00040068905,0.0020961044,0.99698997,0.000003663803],"about_ca_topic_score_codex":0.0026741591,"about_ca_topic_score_gemma":0.0050078765,"teacher_disagreement_score":0.74520665,"about_ca_system_score_codex":0.00076974795,"about_ca_system_score_gemma":0.0010764227,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W1536848116","doi":"10.1007/978-3-642-30220-6_27","title":"RadialViz: An Orientation-Free Frequent Pattern Visualizer","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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":"University of Manitoba","funders":"","keywords":"Legibility; Computer science; Graph; Orientation (vector space); Face (sociological concept); Representation (politics); Information retrieval; Human–computer interaction; Theoretical computer science; Artificial intelligence; Computer graphics (images); Mathematics; Geometry; Art; Visual arts","score_opus":0.023182608932740007,"score_gpt":0.28423811563833223,"score_spread":0.26105550670559224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1536848116","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008358571,0.0006526102,0.8383987,0.00024771824,0.00012049163,0.00016299813,0.00911232,0.14049439,0.0024523453],"genre_scores_gemma":[0.06118491,0.00069860613,0.9071205,0.0002069338,0.000094291776,0.0004528446,0.015506575,0.009664515,0.0050708824],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921393,0.000113500566,0.000092703456,0.0001486856,0.00036921285,0.00006193062],"domain_scores_gemma":[0.99842775,0.0007578358,0.0001586514,0.00033415254,0.00022967305,0.00009195454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010183806,0.0018581757,0.0013885987,0.003822633,0.00047541133,0.0023913477,0.0022378669,0.001144837,0.018502682],"category_scores_gemma":[0.0054745576,0.0011312892,0.001786869,0.0025623743,0.00027894857,0.0028890837,0.002517077,0.0014140664,0.008498625],"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":[0.0015824505,0.00019482562,0.0029276886,0.0011532126,0.0002920409,0.00075823476,0.00039188028,0.010410215,0.028100679,0.014276379,0.099035114,0.8408774],"study_design_scores_gemma":[0.0007311484,0.00044004733,0.0035735236,0.00036860857,0.00027191415,0.0030653076,0.000280209,0.6341751,0.06899215,0.079835035,0.20797588,0.00029110102],"about_ca_topic_score_codex":0.0012380984,"about_ca_topic_score_gemma":0.0017319451,"teacher_disagreement_score":0.018502682,"about_ca_system_score_codex":0.0003016171,"about_ca_system_score_gemma":0.00060171034,"threshold_uncertainty_score":0.061897635},"labels":[],"label_agreement":null},{"id":"W1541719409","doi":"10.1007/3-540-45372-5_47","title":"Applying Objective Interestingness Measures in Data Mining Systems","year":2000,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":45,"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":"Ranking (information retrieval); Spurious relationship; Computer science; Data mining; Independence (probability theory); Interpretation (philosophy); Association rule learning; Process (computing); Task (project management); Focus (optics); Artificial intelligence; Machine learning; Statistics; Mathematics; Engineering","score_opus":0.05861183514258421,"score_gpt":0.2854879178597035,"score_spread":0.2268760827171193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1541719409","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036613703,0.0007902197,0.9603657,0.00018672594,0.00005156777,0.00009404279,0.00013049864,0.00035012118,0.001417388],"genre_scores_gemma":[0.47663903,0.00060172274,0.5201772,0.00010532255,0.00020865125,0.0002628612,0.000371704,0.00015748366,0.0014759955],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99321634,0.0022450637,0.00077072415,0.0007578857,0.0028255524,0.00018445993],"domain_scores_gemma":[0.9750378,0.018397061,0.0016171673,0.001975959,0.0025663672,0.0004057188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008295556,0.00086909655,0.0012931764,0.0044105677,0.00051638327,0.002918783,0.0015024737,0.0007265156,0.0014987263],"category_scores_gemma":[0.034176923,0.00052489724,0.0009811546,0.0032759847,0.0011967021,0.0053236564,0.0021359771,0.0014669724,0.00027664754],"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":[0.0006258833,0.0004785131,0.016456319,0.0009374587,0.00051923486,0.00021060371,0.0004144131,0.14339149,0.011217751,0.12892826,0.0027854003,0.69403464],"study_design_scores_gemma":[0.000039828232,0.00030773043,0.0025195084,0.000071060844,0.00012757888,0.00018892286,0.00009530136,0.8218705,0.010850619,0.1614828,0.0024066826,0.000039451523],"about_ca_topic_score_codex":0.00034420006,"about_ca_topic_score_gemma":0.00057775876,"teacher_disagreement_score":0.008295556,"about_ca_system_score_codex":0.0009890547,"about_ca_system_score_gemma":0.0007802121,"threshold_uncertainty_score":0.04387158},"labels":[],"label_agreement":null},{"id":"W1546703457","doi":"10.1137/1.9781611972733.6","title":"Hierarchical Document Clustering Using Frequent Itemsets","year":2003,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":469,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Cluster analysis; Computer science; Document clustering; Information retrieval; Hierarchical clustering; Brown clustering; Intuition; Vocabulary; Artificial intelligence; Library science; Fuzzy clustering; Canopy clustering algorithm; Psychology","score_opus":0.030531234367910925,"score_gpt":0.2888526014938362,"score_spread":0.25832136712592524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1546703457","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01236632,0.0010651785,0.9816865,0.00019667242,0.00008757701,0.00037798448,0.0010351023,0.0019767864,0.0012079347],"genre_scores_gemma":[0.11030448,0.0007689231,0.8834099,0.0000669574,0.00012637064,0.00045339882,0.003752519,0.00012330395,0.0009941801],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958973,0.0011979607,0.00045258595,0.0009429297,0.0012917047,0.00021758491],"domain_scores_gemma":[0.9937807,0.002857612,0.0007371727,0.0008447085,0.0016350851,0.00014464662],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027364425,0.0014621615,0.002356941,0.012997911,0.0015915987,0.002668737,0.0019517452,0.0012750578,0.0017388286],"category_scores_gemma":[0.0140844295,0.00074166345,0.0017957108,0.01063476,0.00057767425,0.0026317541,0.001308696,0.001131503,0.002090389],"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":[0.0003007356,0.00024855736,0.00747498,0.00077801803,0.00052667485,0.000515512,0.00050639274,0.14413816,0.0056521404,0.016832128,0.014419647,0.8086071],"study_design_scores_gemma":[0.00005526491,0.00010989167,0.002207426,0.000112693655,0.00015123542,0.0006399642,0.00026922603,0.92289114,0.0047303573,0.058135733,0.010616283,0.00008077128],"about_ca_topic_score_codex":0.004226096,"about_ca_topic_score_gemma":0.004023103,"teacher_disagreement_score":0.012997911,"about_ca_system_score_codex":0.0010295818,"about_ca_system_score_gemma":0.001428309,"threshold_uncertainty_score":0.014471889},"labels":[],"label_agreement":null},{"id":"W1547844424","doi":"10.1109/icdm.2004.10116","title":"Mining Frequent Itemsets from Secondary Memory","year":2005,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Association rule learning; Data mining; Scalability; Database","score_opus":0.01568274074135982,"score_gpt":0.24320155639678737,"score_spread":0.22751881565542753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1547844424","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34709886,0.0036407984,0.62976515,0.001014407,0.00036294048,0.00064628065,0.005034607,0.0073471316,0.005089814],"genre_scores_gemma":[0.5542465,0.0016411046,0.42163873,0.00036648597,0.0003299159,0.00080207526,0.014706924,0.00036329878,0.0059049716],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99808085,0.00028969324,0.0002943625,0.00043933268,0.00070567307,0.0001901314],"domain_scores_gemma":[0.9895886,0.0046529896,0.0008760084,0.002603058,0.0019258746,0.00035354117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001361407,0.0012560167,0.0018054819,0.004119846,0.0011588747,0.0023389705,0.0024394244,0.0010136642,0.0027764156],"category_scores_gemma":[0.015343828,0.0007451057,0.0010676765,0.0050144484,0.0005073161,0.0040292176,0.0019961437,0.0011174835,0.0024731536],"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":[0.002274449,0.0006189393,0.022593535,0.000984282,0.00042704958,0.002719706,0.0008094083,0.024556054,0.058577973,0.0064465716,0.0159139,0.86407816],"study_design_scores_gemma":[0.0006077721,0.0022458346,0.021080146,0.00036357093,0.00075421785,0.007126314,0.001960472,0.6475185,0.17090882,0.107138015,0.040122237,0.00017411698],"about_ca_topic_score_codex":0.00091377663,"about_ca_topic_score_gemma":0.0018016427,"teacher_disagreement_score":0.004119846,"about_ca_system_score_codex":0.00036444273,"about_ca_system_score_gemma":0.001082526,"threshold_uncertainty_score":0.009288013},"labels":[],"label_agreement":null},{"id":"W1548844896","doi":"10.1023/a:1011276003319","title":"Parametric Algorithms for Mining Share Frequent Itemsets","year":2001,"lang":"en","type":"article","venue":"Journal of Intelligent Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":11,"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 Regina","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Association rule learning; Data mining; Classifier (UML); Factor (programming language); Measure (data warehouse); Artificial intelligence; Machine learning","score_opus":0.05764236875585299,"score_gpt":0.30549727500668516,"score_spread":0.24785490625083217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1548844896","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018194625,0.0006125144,0.9795009,0.00017747769,0.000028974342,0.00009119334,0.0002310762,0.00054941,0.0006138992],"genre_scores_gemma":[0.44326797,0.0013037209,0.54967284,0.00012548939,0.00022555803,0.0007697054,0.0023616457,0.00020360938,0.0020694272],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99478674,0.0018578564,0.00062543584,0.0008136889,0.0016174259,0.00029881462],"domain_scores_gemma":[0.9651115,0.024662863,0.0019966823,0.0054671834,0.0023877292,0.0003740355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005834327,0.0010469486,0.002769585,0.004538072,0.0014259728,0.003225713,0.0050757877,0.0019560514,0.0033550537],"category_scores_gemma":[0.051333245,0.001304859,0.0019446226,0.0074096634,0.001620343,0.008893788,0.004468921,0.002767143,0.0012257933],"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":[0.0009813713,0.0005219766,0.008917091,0.0006090943,0.00034463077,0.0003597903,0.0004937036,0.23150212,0.0023277646,0.08677959,0.0043652602,0.66279763],"study_design_scores_gemma":[0.000060276783,0.00019814767,0.0010675943,0.000046940342,0.00007070995,0.00042470993,0.00016659072,0.8438859,0.0011015817,0.15072116,0.0022220116,0.00003439942],"about_ca_topic_score_codex":0.0008768218,"about_ca_topic_score_gemma":0.00096730527,"teacher_disagreement_score":0.005834327,"about_ca_system_score_codex":0.000731761,"about_ca_system_score_gemma":0.0014263965,"threshold_uncertainty_score":0.030855238},"labels":[],"label_agreement":null},{"id":"W1550195227","doi":"10.1109/iscc.2004.1358390","title":"Genetic algorithms based optimization of membership functions for fuzzy weighted association rules mining","year":2004,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Association rule learning; Data mining; Cluster analysis; Computer science; Fuzzy logic; Fuzzy set; Membership function; Fuzzy clustering; Genetic algorithm; Algorithm; Artificial intelligence; Machine learning","score_opus":0.020633915643848474,"score_gpt":0.24578851114107478,"score_spread":0.2251545954972263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1550195227","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040167566,0.00027734978,0.9580312,0.00013365933,0.000023481858,0.00006906554,0.000031593532,0.00023685413,0.0010293431],"genre_scores_gemma":[0.42142963,0.00027226273,0.57623714,0.000114758084,0.000027662554,0.00036279045,0.00015737383,0.00007760538,0.0013207436],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898547,0.0004060465,0.00006695213,0.00017243938,0.00028516253,0.00008392067],"domain_scores_gemma":[0.9983053,0.001115923,0.00017261195,0.00007751405,0.00029044537,0.000038120164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020953086,0.0010746163,0.0011067226,0.0017904225,0.000602365,0.0009214801,0.0015260071,0.0014227064,0.0007477044],"category_scores_gemma":[0.006555539,0.00060356467,0.0008504069,0.0016390667,0.00090985576,0.0010353442,0.0007981528,0.0009846198,0.00025519053],"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":[0.00004848377,0.00007370098,0.0008348513,0.000046370165,0.000055054436,0.000060462295,0.00009511637,0.9217203,0.002253572,0.0056720315,0.00037504497,0.06876499],"study_design_scores_gemma":[0.0000111338595,0.00002499782,0.00013305416,0.0000068548793,0.000009654832,0.000015653803,0.000015460957,0.99495244,0.0006861273,0.00392832,0.00021002743,0.000006270296],"about_ca_topic_score_codex":0.005051675,"about_ca_topic_score_gemma":0.0041837594,"teacher_disagreement_score":0.005051675,"about_ca_system_score_codex":0.0012972059,"about_ca_system_score_gemma":0.0011071844,"threshold_uncertainty_score":0.011081219},"labels":[],"label_agreement":null},{"id":"W1551002398","doi":"10.1007/978-3-540-76928-6_88","title":"Merging Algorithm to Reduce Dimensionality in Application to Web-Mining","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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":"Suncor Energy (Canada)","funders":"","keywords":"Computer science; Dimensionality reduction; Data mining; Matrix (chemical analysis); Cluster (spacecraft); Dimension (graph theory); Process (computing); Divergence (linguistics); Algorithm; Independence (probability theory); Attractor; Theoretical computer science; Artificial intelligence; Mathematics; Statistics; Combinatorics","score_opus":0.02452607990758312,"score_gpt":0.2976618000369684,"score_spread":0.2731357201293853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1551002398","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0106857,0.000538212,0.9842674,0.00015540351,0.00013367688,0.00014155239,0.00027538562,0.0028654397,0.00093722454],"genre_scores_gemma":[0.037625328,0.00019792418,0.9590287,0.00010359528,0.00007956072,0.00017813133,0.0008243248,0.00034348227,0.0016189397],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978465,0.0004946247,0.00023720929,0.00040810416,0.0008559383,0.00015767374],"domain_scores_gemma":[0.9961831,0.0013698156,0.0002151277,0.0010030649,0.0010825912,0.00014620363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003113164,0.00095843244,0.0022768832,0.0031044066,0.0021880423,0.001772212,0.0028137525,0.0015001699,0.005887205],"category_scores_gemma":[0.007768445,0.0008980574,0.0020203337,0.006272208,0.00067825185,0.0028410463,0.0027182915,0.001855769,0.00249626],"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":[0.00033962782,0.00028730952,0.003092081,0.0002449963,0.0002839539,0.00018497347,0.00032636017,0.02034547,0.012492756,0.010570249,0.016237915,0.9355943],"study_design_scores_gemma":[0.00014105848,0.00031997505,0.0048743095,0.000059810223,0.00038757783,0.0010580698,0.00028355638,0.877968,0.04335309,0.03522132,0.036232203,0.00010108412],"about_ca_topic_score_codex":0.0020786617,"about_ca_topic_score_gemma":0.0032828958,"teacher_disagreement_score":0.005887205,"about_ca_system_score_codex":0.0005808818,"about_ca_system_score_gemma":0.0016555886,"threshold_uncertainty_score":0.019694686},"labels":[],"label_agreement":null},{"id":"W155192273","doi":"10.1007/978-3-642-32584-7_24","title":"Mining Popular Patterns from Transactional Databases","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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 Manitoba","funders":"","keywords":"Popularity; Computer science; Data mining; Transactional leadership; Tree (set theory); Space (punctuation); Theoretical computer science; Mathematics","score_opus":0.03628745681093394,"score_gpt":0.266679770341694,"score_spread":0.23039231353076006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W155192273","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58145535,0.0075166686,0.38603154,0.0014097753,0.0003246693,0.00047755206,0.011649852,0.003696011,0.0074386285],"genre_scores_gemma":[0.74663895,0.003271222,0.22083253,0.00020096767,0.00039978288,0.0002906566,0.022094073,0.00028740818,0.00598442],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985844,0.000125316,0.00019556178,0.00028671278,0.0006812341,0.00012678931],"domain_scores_gemma":[0.9967001,0.0014989087,0.0004341323,0.0004900594,0.0006943288,0.00018240124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006096794,0.00081177196,0.001056319,0.0064452128,0.00069853116,0.0023058162,0.0020037205,0.00091090926,0.002470499],"category_scores_gemma":[0.006969443,0.0006263225,0.0011517665,0.009343277,0.00048001227,0.0052925632,0.0012634757,0.0010472942,0.0016580872],"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":[0.0009573137,0.0004741639,0.06185399,0.001164488,0.0004702768,0.0021679904,0.0006482208,0.011109685,0.018492766,0.01446926,0.015308557,0.87288326],"study_design_scores_gemma":[0.00021542465,0.0007148019,0.041296955,0.0003361644,0.00066036155,0.010176833,0.0020119858,0.76050484,0.029558832,0.124215245,0.030181946,0.00012659308],"about_ca_topic_score_codex":0.00078366953,"about_ca_topic_score_gemma":0.0018206727,"teacher_disagreement_score":0.0064452128,"about_ca_system_score_codex":0.00035644727,"about_ca_system_score_gemma":0.0005557201,"threshold_uncertainty_score":0.008264601},"labels":[],"label_agreement":null},{"id":"W1556196612","doi":"10.3233/ida-2011-0501","title":"Mining sequential patterns with extensible knowledge representation","year":2011,"lang":"en","type":"article","venue":"Intelligent Data Analysis","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Data mining; Knowledge extraction; Representation (politics); Set (abstract data type); Pruning; Knowledge representation and reasoning; Association rule learning; K-optimal pattern discovery; Apriori algorithm; A priori and a posteriori; Machine learning; Artificial intelligence","score_opus":0.182989932994737,"score_gpt":0.3504488406659183,"score_spread":0.1674589076711813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1556196612","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041411288,0.0005938362,0.95033157,0.00044841462,0.00005389416,0.00026566422,0.0014807311,0.0031880706,0.0022265695],"genre_scores_gemma":[0.17980468,0.0007697383,0.81273717,0.00017813538,0.000043348286,0.00027248383,0.0047630942,0.000083366096,0.0013480383],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99836415,0.00034897306,0.00037728308,0.00032632513,0.00050039095,0.00008293834],"domain_scores_gemma":[0.99589765,0.0018334757,0.00048291482,0.0012501131,0.00045420585,0.00008158022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002235093,0.00059238414,0.00068993395,0.003412938,0.00038783645,0.0021417527,0.0016345062,0.00070914545,0.001936173],"category_scores_gemma":[0.010446126,0.00046065246,0.0011756036,0.003976878,0.00055207487,0.0052115307,0.001872405,0.0010141326,0.00058119104],"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":[0.00039913357,0.00039950982,0.008794835,0.00058720703,0.00032572745,0.0013280261,0.00068279024,0.07430415,0.009762631,0.06176614,0.005222535,0.8364274],"study_design_scores_gemma":[0.00008067258,0.00019111241,0.002229824,0.00023898098,0.00024641684,0.0009410848,0.0002585297,0.79411435,0.010315027,0.17438662,0.01694213,0.000055258373],"about_ca_topic_score_codex":0.0016610555,"about_ca_topic_score_gemma":0.0019789971,"teacher_disagreement_score":0.003412938,"about_ca_system_score_codex":0.0003811658,"about_ca_system_score_gemma":0.0007901784,"threshold_uncertainty_score":0.011820495},"labels":[],"label_agreement":null},{"id":"W1556550766","doi":"10.1007/978-3-642-12659-8_20","title":"Interactive Data Mining on a CBEA Cluster","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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":"Trent University","funders":"","keywords":"Computer science; Implementation; Cluster (spacecraft); Data mining; Architecture; Tree (set theory); Decision tree; Broadband; Parallel computing; Operating system; Programming language","score_opus":0.03327072161653707,"score_gpt":0.2918810401726122,"score_spread":0.25861031855607514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1556550766","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09049454,0.00046051748,0.8718842,0.00059454073,0.00016409086,0.0002794761,0.0010860167,0.01551874,0.01951791],"genre_scores_gemma":[0.24798064,0.00018888061,0.73033357,0.00010544288,0.00006835644,0.00020709669,0.0017661147,0.00080287963,0.018547017],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99924856,0.0001313962,0.000035713052,0.00017861363,0.00030295472,0.00010270367],"domain_scores_gemma":[0.99871457,0.00037837107,0.00002772634,0.00039584257,0.0003266966,0.0001567699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008942109,0.00064893084,0.00081808673,0.0013501793,0.001871472,0.0015906162,0.0024949184,0.0005897333,0.013392472],"category_scores_gemma":[0.0027664907,0.0005523138,0.00073358475,0.0026977551,0.00047658925,0.0015889351,0.0023119948,0.0009013153,0.0026144786],"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":[0.0021807137,0.00048840407,0.007826192,0.0004052207,0.00020895507,0.000757198,0.0010093548,0.13875143,0.050876003,0.03559976,0.049161088,0.71273565],"study_design_scores_gemma":[0.0000955928,0.00013681641,0.0023040709,0.00003129667,0.000047613164,0.00020882074,0.00030324588,0.924728,0.019292237,0.0265148,0.026304979,0.00003251702],"about_ca_topic_score_codex":0.010330472,"about_ca_topic_score_gemma":0.016259475,"teacher_disagreement_score":0.013392472,"about_ca_system_score_codex":0.0009977786,"about_ca_system_score_gemma":0.0012926193,"threshold_uncertainty_score":0.044802308},"labels":[],"label_agreement":null},{"id":"W1559068944","doi":"10.1007/978-3-540-70504-8_2","title":"Efficient Mining of Frequent Itemsets from Data Streams","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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":"University of Manitoba","funders":"","keywords":"Computer science; Data stream mining; Data mining; STREAMS; Tree (set theory); Data stream; Wireless sensor network; Computer network","score_opus":0.03794779456616829,"score_gpt":0.2669591683562896,"score_spread":0.2290113737901213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1559068944","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08384787,0.002124274,0.9084508,0.00037303436,0.00014768816,0.0003201023,0.0019192223,0.0018626255,0.0009544668],"genre_scores_gemma":[0.27932054,0.001344803,0.70779324,0.000108171735,0.00023403295,0.00030111472,0.008920152,0.00014413512,0.0018338799],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977842,0.0003655737,0.00038763997,0.00039719,0.00090449787,0.00016100568],"domain_scores_gemma":[0.9924516,0.0049939537,0.00054627744,0.0007323425,0.001107667,0.00016818466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00169348,0.0009317394,0.0022366098,0.00366581,0.0007917873,0.0022143724,0.0021751483,0.0011177085,0.00097043964],"category_scores_gemma":[0.010008363,0.00090139307,0.0015502844,0.0045056394,0.0003798534,0.0028434803,0.0012315384,0.0011783369,0.0009485783],"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":[0.00087472727,0.0004752833,0.015036706,0.0009847347,0.0004956568,0.0010191305,0.00035380013,0.053388286,0.016099118,0.005283578,0.008648721,0.8973402],"study_design_scores_gemma":[0.00009806847,0.00028547188,0.0041029677,0.000111496825,0.00020494734,0.001753572,0.0002434093,0.95076895,0.011585237,0.026005952,0.0047996007,0.000040367726],"about_ca_topic_score_codex":0.0010892662,"about_ca_topic_score_gemma":0.0015873798,"teacher_disagreement_score":0.00366581,"about_ca_system_score_codex":0.00036981926,"about_ca_system_score_gemma":0.0011034312,"threshold_uncertainty_score":0.008956134},"labels":[],"label_agreement":null},{"id":"W1559100584","doi":"10.1109/ihtc.2014.7147526","title":"Open data offers open opportunities: A case study on improving aid management","year":2014,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Open data; Computer science; Process (computing); Data science; Data management; Knowledge management; World Wide Web; Data mining","score_opus":0.2696111570302327,"score_gpt":0.3808838647789551,"score_spread":0.11127270774872239,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1559100584","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9312181,0.000955057,0.010904799,0.015938716,0.000105003426,0.0008005067,0.0006682153,0.00014555235,0.039264064],"genre_scores_gemma":[0.9730449,0.0009847564,0.02052973,0.00066879287,0.00004262308,0.0002307487,0.00028773613,0.00004522369,0.0041656927],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.985038,0.010740324,0.00044066997,0.0003699679,0.0020076516,0.0014033958],"domain_scores_gemma":[0.96791637,0.02184945,0.0019884298,0.0024859672,0.003339295,0.0024204762],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0142416395,0.00050606014,0.00043103308,0.0028484464,0.009557612,0.0048852367,0.0024330888,0.003886767,0.0025860192],"category_scores_gemma":[0.031017192,0.00034072823,0.0004724176,0.007936173,0.0044186297,0.0046380055,0.0058989376,0.0024138822,0.0004266595],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00082171743,0.006839263,0.091921225,0.0017840719,0.00023073597,0.03402289,0.36348245,0.02265452,0.0027990702,0.09238441,0.05528195,0.32777768],"study_design_scores_gemma":[0.0002470979,0.0012725892,0.03300607,0.0009230226,0.00013724003,0.0034947912,0.638424,0.021843396,0.005300977,0.021343028,0.27384707,0.0001606561],"about_ca_topic_score_codex":0.046541728,"about_ca_topic_score_gemma":0.12077107,"teacher_disagreement_score":0.046541728,"about_ca_system_score_codex":0.006008771,"about_ca_system_score_gemma":0.0082510095,"threshold_uncertainty_score":0.092541635},"labels":[],"label_agreement":null},{"id":"W1560603637","doi":"10.1007/978-3-540-45228-7_37","title":"Non-recursive Generation of Frequent K-itemsets from Frequent Pattern Tree Representations","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":32,"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; Association rule learning; Data mining; Tree (set theory); Tree structure; Dependency (UML); Process (computing); Data structure; Theoretical computer science; Artificial intelligence; Mathematics","score_opus":0.0323483048558167,"score_gpt":0.27265920035138413,"score_spread":0.24031089549556744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1560603637","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06004988,0.00028046762,0.9299806,0.00025908163,0.00009171476,0.0005378673,0.0015704724,0.0053216354,0.0019082604],"genre_scores_gemma":[0.15630223,0.00012460299,0.8346214,0.00008568503,0.000047725298,0.00034578983,0.0061740275,0.0003486804,0.0019497852],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987343,0.00026955202,0.00017005458,0.00023153464,0.00046629345,0.00012826348],"domain_scores_gemma":[0.99128485,0.005751005,0.0003184098,0.00089397543,0.0015908917,0.00016089954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011757403,0.0005065553,0.0011100041,0.0021483644,0.0006744813,0.0014725619,0.0021204029,0.00092439837,0.0049533085],"category_scores_gemma":[0.012726231,0.000594521,0.0014979687,0.002453448,0.00039656818,0.0019804868,0.0015339062,0.0011595048,0.003168796],"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":[0.00067850674,0.00039094343,0.0068355356,0.0007093706,0.00015831104,0.0014390602,0.00074129825,0.020844681,0.031080974,0.016460888,0.013248106,0.90741235],"study_design_scores_gemma":[0.00020862202,0.0003978154,0.004583714,0.00018254947,0.00018269803,0.0027289472,0.0005572281,0.8765431,0.034249973,0.0664465,0.01383946,0.00007946018],"about_ca_topic_score_codex":0.0009071672,"about_ca_topic_score_gemma":0.002500513,"teacher_disagreement_score":0.0049533085,"about_ca_system_score_codex":0.00040832037,"about_ca_system_score_gemma":0.001020231,"threshold_uncertainty_score":0.016570449},"labels":[],"label_agreement":null},{"id":"W1560982279","doi":"10.3233/ida-2011-0506","title":"Future trends in business analytics and optimization","year":2011,"lang":"en","type":"article","venue":"Intelligent Data Analysis","topic":"Data Mining Algorithms and Applications","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":"National Research Council Canada","funders":"","keywords":"Analytics; Business analytics; Data science; Business intelligence; Computer science; Business; Business model; Knowledge management; Business analysis; Marketing","score_opus":0.07903561137995375,"score_gpt":0.29939033646237545,"score_spread":0.2203547250824217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1560982279","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007002785,0.74304795,0.046192955,0.12243702,0.0048695914,0.00005141506,0.0004244733,0.0004853623,0.07548845],"genre_scores_gemma":[0.107697815,0.791069,0.051082525,0.013983424,0.015675792,0.00012811227,0.0009919658,0.00017096556,0.019200366],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99834824,0.0005529275,0.00008644532,0.00023532406,0.0006663408,0.00011080792],"domain_scores_gemma":[0.9915589,0.004723342,0.00043272163,0.0003514082,0.002368599,0.00056508335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036281734,0.0007894641,0.00096792745,0.0022868414,0.0004771995,0.004076196,0.0013669814,0.0023590894,0.016780721],"category_scores_gemma":[0.008391881,0.00032487785,0.0004650783,0.0048951632,0.0014816315,0.006981569,0.0011243615,0.0033488253,0.004708542],"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":[0.00013803114,0.00017735927,0.002349984,0.0016995333,0.000047975613,0.00007487488,0.0001489566,0.0027167196,0.00067279,0.20789494,0.096437566,0.68764126],"study_design_scores_gemma":[0.000031669126,0.00013848106,0.0030730944,0.0014284382,0.00004442516,0.00032802497,0.00068341504,0.016366366,0.00047022555,0.2516902,0.7256918,0.000053919975],"about_ca_topic_score_codex":0.0011155986,"about_ca_topic_score_gemma":0.0017406382,"teacher_disagreement_score":0.016780721,"about_ca_system_score_codex":0.0016468514,"about_ca_system_score_gemma":0.0020401555,"threshold_uncertainty_score":0.056137145},"labels":[],"label_agreement":null},{"id":"W1565903223","doi":"10.1007/3-540-44886-1_38","title":"Methods for Mining Frequent Sequential Patterns","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Trie; Prefix; Computer science; Heuristic; Algorithm; Data structure; Artificial intelligence","score_opus":0.042910758152290146,"score_gpt":0.33626521198040726,"score_spread":0.2933544538281171,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1565903223","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018980583,0.0017452564,0.9939797,0.00010014897,0.00010359465,0.00012614256,0.0003708093,0.00085545256,0.00082098425],"genre_scores_gemma":[0.031157386,0.0025324423,0.9586687,0.00012273794,0.00029564797,0.000722292,0.0018828482,0.00018092984,0.0044370615],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975509,0.0004364554,0.0002781801,0.000470815,0.0011857189,0.00007801645],"domain_scores_gemma":[0.9935142,0.0043593138,0.0003736794,0.0008016108,0.0008403911,0.00011079919],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025084943,0.0013714874,0.001937909,0.004534786,0.000707895,0.0017270879,0.0027409731,0.0009705229,0.005594496],"category_scores_gemma":[0.011816188,0.0009423654,0.0015078291,0.0054708333,0.00071803184,0.0032125055,0.0014719057,0.0014916792,0.0035959117],"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":[0.00020589934,0.00013710072,0.0019448794,0.0011587965,0.00028051037,0.00018426133,0.00016658947,0.01800297,0.0033582351,0.026626572,0.011728396,0.9362058],"study_design_scores_gemma":[0.00023005734,0.00022597089,0.0017300997,0.00030217174,0.00032220015,0.0015109386,0.0001827162,0.6781288,0.006869597,0.27074137,0.03968295,0.000073175375],"about_ca_topic_score_codex":0.0010538242,"about_ca_topic_score_gemma":0.0017103301,"teacher_disagreement_score":0.005594496,"about_ca_system_score_codex":0.00036592752,"about_ca_system_score_gemma":0.0008846548,"threshold_uncertainty_score":0.018715441},"labels":[],"label_agreement":null},{"id":"W1566767881","doi":"","title":"Tutorial notes of the sixth ACM SIGKDD international conference on Knowledge discovery and data mining","year":2000,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","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 British Columbia","funders":"","keywords":"Knowledge extraction; Computer science; Data science; Scientific discovery; World Wide Web; Information retrieval; Data mining; Psychology; Cognitive science","score_opus":0.08206034625641366,"score_gpt":0.33515065533331134,"score_spread":0.25309030907689767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1566767881","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008703237,0.14608538,0.26474825,0.058492914,0.31051826,0.0007710669,0.008015342,0.0033873646,0.1992782],"genre_scores_gemma":[0.016420718,0.10629329,0.069491975,0.0056627723,0.06430341,0.0003915732,0.015188329,0.0022875469,0.7199604],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985312,0.00022928692,0.00010654253,0.0002089147,0.0008154636,0.000108548404],"domain_scores_gemma":[0.9926906,0.0028349448,0.0002847005,0.00059117086,0.0021511782,0.0014473393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044517955,0.0016374314,0.0029976892,0.0025974212,0.0009853641,0.004293332,0.0013806104,0.0012406252,0.09287007],"category_scores_gemma":[0.006861838,0.00066437514,0.0012268599,0.0024446968,0.0008719836,0.0036567997,0.001493758,0.0036098128,0.04601692],"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":[0.00021679871,0.00012948668,0.00028982057,0.00025853547,0.0000435177,0.0000686038,0.000081722705,0.00061599,0.0007566838,0.0032345303,0.81720775,0.17709659],"study_design_scores_gemma":[0.00008177312,0.00018291968,0.0016565575,0.0003029855,0.00007425807,0.00029015623,0.00011843274,0.0038607628,0.00091137213,0.010111587,0.9823629,0.000046251724],"about_ca_topic_score_codex":0.0036163295,"about_ca_topic_score_gemma":0.0072959783,"teacher_disagreement_score":0.09287007,"about_ca_system_score_codex":0.00091208826,"about_ca_system_score_gemma":0.002171214,"threshold_uncertainty_score":0.31068134},"labels":[],"label_agreement":null},{"id":"W1566858089","doi":"10.1007/978-3-540-44918-8_7","title":"Statistical Methodologies for Mining Potentially Interesting Contrast Sets","year":2007,"lang":"en","type":"book-chapter","venue":"Studies in computational intelligence","topic":"Data Mining Algorithms and Applications","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 Regina","funders":"","keywords":"Contrast (vision); Computer science; Artificial intelligence; Data mining","score_opus":0.40000773488564073,"score_gpt":0.4790622480834785,"score_spread":0.0790545131978378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1566858089","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00795381,0.0018688325,0.9870068,0.0002292571,0.000034158897,0.00006474441,0.00024627292,0.00042120292,0.0021749742],"genre_scores_gemma":[0.1385525,0.0016888516,0.85612273,0.00018543904,0.00024196283,0.0003457376,0.0009934846,0.00013714672,0.0017321609],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985707,0.00038160075,0.000106618194,0.00029760168,0.0005971002,0.00004631992],"domain_scores_gemma":[0.98933053,0.008700758,0.0007109829,0.00065207476,0.00051675405,0.00008892631],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002803716,0.000969794,0.0010468918,0.0051596966,0.00060355087,0.001902244,0.0023720867,0.00073876814,0.0032562485],"category_scores_gemma":[0.014984574,0.0005788311,0.0010018031,0.0051146685,0.0012198798,0.0027535222,0.001583541,0.0015815481,0.0008654292],"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":[0.00012998481,0.00017825708,0.007977608,0.0008046774,0.00041889862,0.0003811408,0.00031526075,0.025900377,0.0093138525,0.2474624,0.0066772695,0.7004403],"study_design_scores_gemma":[0.000044270124,0.00011561473,0.0042559896,0.00014062818,0.0001919496,0.0010180449,0.00018887351,0.34142873,0.0065477565,0.6298298,0.016188074,0.00005019377],"about_ca_topic_score_codex":0.00038860142,"about_ca_topic_score_gemma":0.0009623634,"teacher_disagreement_score":0.0051596966,"about_ca_system_score_codex":0.00047182516,"about_ca_system_score_gemma":0.00070585206,"threshold_uncertainty_score":0.014827609},"labels":[],"label_agreement":null},{"id":"W1567542872","doi":"10.1007/11508069_16","title":"Mining Job Logs Using Incremental Attribute-Oriented Approach","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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","funders":"","keywords":"Computer science; Grid computing; Grid; Task (project management); Data mining; Resource (disambiguation); Power grid; Job scheduler; Distributed computing; Power (physics); Cloud computing; Operating system","score_opus":0.035586783335390317,"score_gpt":0.26928252533885655,"score_spread":0.23369574200346624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1567542872","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25781414,0.0021356228,0.7120733,0.00061637524,0.0005414055,0.0012779572,0.0073524876,0.01341625,0.004772425],"genre_scores_gemma":[0.4562028,0.0006995108,0.52923584,0.00024209147,0.00021923997,0.0004619139,0.00998966,0.00025053017,0.0026983868],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99815375,0.00017373824,0.00023560692,0.00040010456,0.0008752324,0.0001614872],"domain_scores_gemma":[0.9950895,0.002284869,0.00031766965,0.00071333756,0.0013228349,0.00027174965],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017080089,0.0010815468,0.0014278521,0.006241827,0.0009634886,0.0022827522,0.0026481887,0.00072520995,0.0010863935],"category_scores_gemma":[0.005141123,0.00056467013,0.0015346345,0.005536501,0.00035822674,0.0020550634,0.0010507591,0.0009893469,0.0008838132],"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":[0.00078878796,0.001987874,0.05923875,0.00062509486,0.0004307856,0.0006918547,0.00046883084,0.02592926,0.018362053,0.0022761167,0.010513979,0.87868667],"study_design_scores_gemma":[0.00015694465,0.00052561826,0.028415423,0.00014199525,0.0007180363,0.0012769334,0.00073077803,0.902793,0.027966678,0.022677029,0.014458599,0.00013900216],"about_ca_topic_score_codex":0.0043994132,"about_ca_topic_score_gemma":0.008101658,"teacher_disagreement_score":0.006241827,"about_ca_system_score_codex":0.00039436953,"about_ca_system_score_gemma":0.0016079955,"threshold_uncertainty_score":0.009032965},"labels":[],"label_agreement":null},{"id":"W1568047218","doi":"10.1023/a:1015014402846","title":"A Data Mining Approach to Characterizing Medical Code Usage Patterns","year":2002,"lang":"en","type":"article","venue":"Journal of Medical Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":11,"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":"Health informatics; Computer science; Code (set theory); Data mining; Data science; Programming language; Medicine; Public health","score_opus":0.11436576168669083,"score_gpt":0.3179121908718094,"score_spread":0.20354642918511856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1568047218","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26016268,0.0025868725,0.7171129,0.0029921888,0.00017574584,0.0012004621,0.008924272,0.003229634,0.0036151388],"genre_scores_gemma":[0.43308493,0.00069140136,0.55755955,0.0003787526,0.00011845076,0.000439331,0.006113495,0.00008373503,0.0015303727],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973436,0.00042569533,0.0005762429,0.00058160827,0.0009427024,0.00013015477],"domain_scores_gemma":[0.9910522,0.0049350895,0.0008890195,0.0006940265,0.0021179242,0.0003117367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002070134,0.00071816903,0.0009573546,0.0097316,0.0012062462,0.002146034,0.0015571446,0.0010556348,0.0010079345],"category_scores_gemma":[0.009053262,0.0003463218,0.0015615784,0.007881817,0.00064774044,0.0018352029,0.0009757041,0.001248296,0.00051693356],"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":[0.0007000393,0.001674023,0.13340768,0.000907446,0.0006793291,0.0012110183,0.0013323432,0.0118111195,0.02702607,0.009960075,0.008661141,0.80262977],"study_design_scores_gemma":[0.00023005571,0.001153353,0.07834328,0.0005618044,0.0013987445,0.007436299,0.0029664617,0.76624024,0.05114151,0.058423404,0.031869538,0.00023533124],"about_ca_topic_score_codex":0.0057027377,"about_ca_topic_score_gemma":0.010291413,"teacher_disagreement_score":0.0097316,"about_ca_system_score_codex":0.0008002265,"about_ca_system_score_gemma":0.0020657394,"threshold_uncertainty_score":0.011339068},"labels":[],"label_agreement":null},{"id":"W1569729202","doi":"10.1007/3-540-45571-x_47","title":"Mining Access Patterns Efficiently from Web Logs","year":2000,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":498,"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 mining; Data mining; Web mapping; Tree (set theory); Web modeling; World Wide Web; Information retrieval; Web service","score_opus":0.023285159835867267,"score_gpt":0.26845831841934226,"score_spread":0.245173158583475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1569729202","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35423136,0.0023034785,0.6025456,0.0011093827,0.00015475306,0.0006563626,0.012211707,0.022411613,0.004375703],"genre_scores_gemma":[0.5739632,0.0013723872,0.39532092,0.00017641345,0.00024415774,0.0003279865,0.021286568,0.0004650252,0.0068433955],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894303,0.00009156775,0.00013485967,0.00021436648,0.00050143537,0.000114733346],"domain_scores_gemma":[0.9969393,0.0015960383,0.0003211331,0.000519199,0.00049630605,0.0001280244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053517445,0.0010539949,0.0015903723,0.0048647067,0.0006777162,0.002148615,0.0012235495,0.00080373086,0.0014783294],"category_scores_gemma":[0.0047109136,0.00067491375,0.0011038902,0.0054544695,0.00031793254,0.0038288645,0.0009420459,0.0010602787,0.0020803309],"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":[0.00046885284,0.00073716673,0.044472534,0.0005716355,0.00022969923,0.0007373516,0.00034058752,0.017854584,0.033914175,0.0037422427,0.018934103,0.8779971],"study_design_scores_gemma":[0.00011336037,0.00025643743,0.016046304,0.000093706,0.0002887953,0.0023093526,0.0007513207,0.8928275,0.029174807,0.044102855,0.013976589,0.00005894445],"about_ca_topic_score_codex":0.004068955,"about_ca_topic_score_gemma":0.010935389,"teacher_disagreement_score":0.0048647067,"about_ca_system_score_codex":0.00039899166,"about_ca_system_score_gemma":0.0013077292,"threshold_uncertainty_score":0.008090496},"labels":[],"label_agreement":null},{"id":"W1570018751","doi":"10.1007/3-540-47922-8_13","title":"Mining Incremental Association Rules with Generalized FP-Tree","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":68,"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":"Association rule learning; Computer science; Database transaction; Apriori algorithm; Data mining; Tree (set theory); Database; A priori and a posteriori; Algorithm; Mathematics","score_opus":0.018521937659330405,"score_gpt":0.23551222168731673,"score_spread":0.2169902840279863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1570018751","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.080237,0.0033592107,0.9057315,0.00042953235,0.0002483047,0.0005116306,0.0026574659,0.004654859,0.002170417],"genre_scores_gemma":[0.1682047,0.0010085397,0.822373,0.00019602964,0.00013373044,0.00026925583,0.0065241125,0.00014593438,0.0011447931],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979054,0.00037795922,0.00029877503,0.0004887659,0.00079390506,0.00013510954],"domain_scores_gemma":[0.9928906,0.0046972847,0.0003197286,0.00090593356,0.0010518087,0.0001347831],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023845455,0.0012472479,0.002216315,0.005078129,0.0008273587,0.001739818,0.0028020325,0.0012929173,0.0017248433],"category_scores_gemma":[0.010843675,0.0009354869,0.0021222217,0.0050626732,0.00060192513,0.0034577865,0.0013512411,0.0016118484,0.0010389022],"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":[0.0006097951,0.00035636258,0.010250087,0.0008176311,0.0005892541,0.0021616041,0.00020256538,0.049579423,0.005977791,0.005628843,0.0105402395,0.91328645],"study_design_scores_gemma":[0.00020517275,0.0004538116,0.003991761,0.00023855697,0.00094365317,0.0044521815,0.00020374621,0.89686364,0.008019477,0.07427053,0.010282841,0.00007458091],"about_ca_topic_score_codex":0.0021224713,"about_ca_topic_score_gemma":0.0034876044,"teacher_disagreement_score":0.005078129,"about_ca_system_score_codex":0.00034985377,"about_ca_system_score_gemma":0.0012568544,"threshold_uncertainty_score":0.012610793},"labels":[],"label_agreement":null},{"id":"W1570326739","doi":"10.20381/ruor-13060","title":"Knowledge discovery for behavioral patterns in wireless sensor networks","year":2008,"lang":"en","type":"dissertation","venue":"uO Research (University of Ottawa)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Wireless sensor network; Behavioral pattern; Process (computing); Computer science; Wireless; Knowledge extraction; Set (abstract data type); Key distribution in wireless sensor networks; Data mining; Engineering; Wireless network; Distributed computing; Computer network; Telecommunications; Software engineering","score_opus":0.07448420202347159,"score_gpt":0.35573551975493267,"score_spread":0.28125131773146106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1570326739","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014269732,0.0004258717,0.9823124,0.000987773,0.000031656047,0.00022632547,0.00031216623,0.00025348723,0.0011806788],"genre_scores_gemma":[0.23343788,0.0013117855,0.76098907,0.00041227494,0.00007876096,0.00074027793,0.0018035324,0.000048347836,0.0011780489],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9935499,0.001886821,0.00097388163,0.0012162091,0.002099331,0.00027383698],"domain_scores_gemma":[0.97532237,0.018222507,0.002165524,0.0022922575,0.001737895,0.00025955812],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0053845597,0.0008379515,0.0010222256,0.0046408325,0.001072855,0.0029007047,0.0023652,0.0013833118,0.0009837688],"category_scores_gemma":[0.03563658,0.0007928038,0.0019646736,0.004143437,0.0022804942,0.0068323626,0.0026839096,0.0020163178,0.00031147167],"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":[0.00021433158,0.00036720862,0.016044537,0.0012863084,0.00037593534,0.0014159058,0.002812875,0.24998952,0.0040447647,0.38171792,0.0033797869,0.33835083],"study_design_scores_gemma":[0.000025597536,0.00006647339,0.0012757749,0.00020547661,0.00007785844,0.00044099,0.0004834723,0.69395643,0.0029507277,0.2943736,0.0061057387,0.00003781765],"about_ca_topic_score_codex":0.004894044,"about_ca_topic_score_gemma":0.0052943435,"teacher_disagreement_score":0.0053845597,"about_ca_system_score_codex":0.0014746716,"about_ca_system_score_gemma":0.0021756648,"threshold_uncertainty_score":0.028476655},"labels":[],"label_agreement":null},{"id":"W1570469335","doi":"10.1007/11766247_45","title":"Probabilistic Inference Trees for Classification and Ranking","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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 New Brunswick","funders":"","keywords":"Computer science; Ranking (information retrieval); Decision tree; Machine learning; Artificial intelligence; Ranking SVM; Probabilistic logic; Inference; Decision tree learning; Learning to rank; Data mining; Pattern recognition (psychology)","score_opus":0.032984000878324087,"score_gpt":0.27474496987325336,"score_spread":0.24176096899492927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1570469335","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00070206635,0.0020274986,0.9939958,0.00035274166,0.00015816813,0.00003484145,0.0004077267,0.00092625665,0.0013949301],"genre_scores_gemma":[0.053490035,0.0037591355,0.9252295,0.00046851576,0.0008740127,0.00043150294,0.0036835065,0.0006489937,0.011414765],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9952846,0.001806668,0.00036399672,0.0007403923,0.001585198,0.00021912312],"domain_scores_gemma":[0.9897138,0.0072453553,0.00036405795,0.0015608076,0.00096875883,0.00014718954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004248309,0.0013194977,0.0031252778,0.0026483776,0.0011943397,0.0034148782,0.0042371447,0.0023857686,0.011017487],"category_scores_gemma":[0.01897067,0.0012628891,0.0024239027,0.005544004,0.0014377567,0.0065993997,0.001930473,0.005002702,0.006467662],"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":[0.00010273562,0.00011901208,0.0005886086,0.000542899,0.00017414395,0.00010739631,0.00018034584,0.079852104,0.00075605046,0.2732399,0.05128323,0.5930536],"study_design_scores_gemma":[0.000020012674,0.000018919813,0.00019569963,0.00005265527,0.000034816818,0.000082783874,0.0000222044,0.31661555,0.00041111204,0.67099476,0.011530231,0.000021243572],"about_ca_topic_score_codex":0.003743076,"about_ca_topic_score_gemma":0.0050312444,"teacher_disagreement_score":0.011017487,"about_ca_system_score_codex":0.0018395232,"about_ca_system_score_gemma":0.0016650733,"threshold_uncertainty_score":0.036857188},"labels":[],"label_agreement":null},{"id":"W1570577635","doi":"10.1007/978-3-642-00887-0_33","title":"Multi-level Frequent Pattern Mining","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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":"Concordia University","funders":"","keywords":"Computer science; Exploit; Apriori algorithm; Data mining; Association rule learning; Focus (optics); Set (abstract data type); A priori and a posteriori; Tree (set theory); Raw data; Machine learning; Artificial intelligence; Computer security","score_opus":0.04595928257508384,"score_gpt":0.27563883082251656,"score_spread":0.22967954824743272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1570577635","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05468008,0.0038643763,0.9259507,0.00055103714,0.0003259551,0.00030007152,0.004691683,0.0029525189,0.0066835224],"genre_scores_gemma":[0.18743972,0.0020105406,0.792054,0.00019770655,0.00022562867,0.00020448104,0.009826929,0.0002038325,0.007837099],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875,0.00014132878,0.00024532122,0.0002831547,0.0005016298,0.00007864781],"domain_scores_gemma":[0.99677855,0.0015151433,0.0003211383,0.0006916242,0.0005901845,0.00010336712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00090919976,0.0006546314,0.0011920547,0.003421221,0.0005676334,0.0015140099,0.0016221605,0.0007758589,0.006483046],"category_scores_gemma":[0.0047954377,0.0005160612,0.0013765948,0.0051640137,0.0002492083,0.0024053266,0.0011117486,0.0009562219,0.0037584284],"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":[0.0002756302,0.0001710084,0.0071360446,0.00090609107,0.00022324047,0.0010658208,0.00011576008,0.0055170697,0.013923958,0.0076132286,0.0116016,0.9514505],"study_design_scores_gemma":[0.00015292194,0.00093226257,0.019233136,0.00048747545,0.00090988795,0.020034513,0.0004393105,0.6660996,0.054691177,0.13210687,0.104745336,0.00016748485],"about_ca_topic_score_codex":0.00020967149,"about_ca_topic_score_gemma":0.0005383937,"teacher_disagreement_score":0.006483046,"about_ca_system_score_codex":0.00020931712,"about_ca_system_score_gemma":0.00041728796,"threshold_uncertainty_score":0.021687984},"labels":[],"label_agreement":null},{"id":"W1571835199","doi":"10.1007/978-3-540-68123-6_33","title":"Effectiveness of Fuzzy Discretization for Class Association Rule-Based Classification","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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":"University of Calgary","funders":"","keywords":"Association rule learning; Classifier (UML); Data mining; Artificial intelligence; Fuzzy logic; Computer science; Machine learning; Discretization; Pattern recognition (psychology); Support vector machine; Fuzzy set; Feature vector; Fuzzy rule; Fuzzy classification; Mathematics","score_opus":0.019167794810366085,"score_gpt":0.2594617264196813,"score_spread":0.2402939316093152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1571835199","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14603533,0.004038007,0.83701384,0.0007583891,0.00037013987,0.0001233539,0.0005164421,0.00083847606,0.010306054],"genre_scores_gemma":[0.68955415,0.0009422242,0.30704588,0.00016798267,0.00014400377,0.00006558939,0.0004752109,0.000054600205,0.0015503267],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996932,0.00119806,0.00020951213,0.00031968454,0.0012364724,0.00010422518],"domain_scores_gemma":[0.98482186,0.012158605,0.0002710491,0.0013255137,0.0012608351,0.00016211203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003902969,0.00044230997,0.001067349,0.0013384082,0.0005583631,0.0018912058,0.0010073123,0.00091109244,0.0016782377],"category_scores_gemma":[0.014895598,0.00024196923,0.0005249467,0.0012012286,0.0005433526,0.0017135964,0.0007567966,0.0008199704,0.00037784895],"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":[0.0015639116,0.00032308523,0.005924676,0.0003678692,0.00021294311,0.00020765491,0.00028522397,0.15365218,0.009975153,0.030247,0.0051005534,0.79213977],"study_design_scores_gemma":[0.000056615456,0.000113693546,0.0014289868,0.00003676264,0.00007931422,0.0002276402,0.00009604125,0.9699358,0.004686109,0.022037638,0.0012836447,0.000017795486],"about_ca_topic_score_codex":0.0029779759,"about_ca_topic_score_gemma":0.0021110042,"teacher_disagreement_score":0.003902969,"about_ca_system_score_codex":0.00075563387,"about_ca_system_score_gemma":0.00074539473,"threshold_uncertainty_score":0.020641148},"labels":[],"label_agreement":null},{"id":"W1572996656","doi":"10.1007/978-3-540-72665-4_12","title":"ICS: An Interactive Classification System","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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 Regina","funders":"","keywords":"Computer science; Process (computing); Architecture; Human–computer interaction; Data mining; Operating system","score_opus":0.04069659745817585,"score_gpt":0.29741765279124693,"score_spread":0.2567210553330711,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1572996656","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01798188,0.00046948856,0.71201634,0.0005556058,0.00046373464,0.0006200471,0.0109768445,0.23166747,0.025248423],"genre_scores_gemma":[0.13949208,0.0005889024,0.7302491,0.0010892341,0.0005526296,0.0016443252,0.032460447,0.008631974,0.085291326],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992873,0.00009884969,0.000048251357,0.00019299088,0.00030290784,0.0000696791],"domain_scores_gemma":[0.9989982,0.00036330143,0.000041598032,0.00023463774,0.00026820914,0.00009407173],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096272427,0.0014421097,0.00089318346,0.003481796,0.0008462081,0.0021250148,0.00192843,0.0011129274,0.053997625],"category_scores_gemma":[0.0024340844,0.00058284414,0.0010538162,0.0022607236,0.00038426608,0.0020101995,0.0024694367,0.0010368604,0.02777249],"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":[0.0009741717,0.0001925176,0.0032799249,0.00026840024,0.00013414847,0.00021200055,0.00015814982,0.0044017825,0.01729656,0.007798987,0.23234937,0.732934],"study_design_scores_gemma":[0.00024495122,0.00041378866,0.0044894093,0.00013297093,0.0002730284,0.0007819866,0.00017950674,0.47503862,0.06265553,0.031752698,0.42390633,0.0001311352],"about_ca_topic_score_codex":0.0040007853,"about_ca_topic_score_gemma":0.005560132,"teacher_disagreement_score":0.053997625,"about_ca_system_score_codex":0.00072432373,"about_ca_system_score_gemma":0.0010068858,"threshold_uncertainty_score":0.18064004},"labels":[],"label_agreement":null},{"id":"W1573250459","doi":"10.1007/bf02949821","title":"A new classification method to overcome over-branching","year":2002,"lang":"en","type":"article","venue":"Journal of Computer Science and Technology","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; Branching (polymer chemistry); Decision tree; Data mining; Theory of computation; Decision tree learning; Node (physics); Incremental decision tree; Binary decision diagram; Artificial intelligence; Machine learning; Algorithm","score_opus":0.024238915323537544,"score_gpt":0.2958042842500415,"score_spread":0.27156536892650396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1573250459","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012179191,0.00068365474,0.97975326,0.00072723645,0.000719651,0.00020584418,0.0002778882,0.0024727038,0.0029805573],"genre_scores_gemma":[0.10464441,0.0004155682,0.8817555,0.0007193174,0.0006152994,0.0003544635,0.0009565459,0.00040862942,0.010130385],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997157,0.00037846484,0.00024667257,0.0006978841,0.001291231,0.00022874962],"domain_scores_gemma":[0.99374545,0.0019137659,0.00037933004,0.0009016777,0.002721037,0.00033878855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028614076,0.00096138136,0.0016752094,0.0035732158,0.0018757454,0.0026867124,0.0038529288,0.0025908474,0.0054583587],"category_scores_gemma":[0.0074244216,0.00048738904,0.0012125139,0.0034602042,0.00083210843,0.0034719757,0.002136635,0.002966017,0.002673104],"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":[0.0002219118,0.00028043962,0.0028160452,0.00014920592,0.000078373785,0.00010049036,0.00013872431,0.006372154,0.008853942,0.015677202,0.018410053,0.9469015],"study_design_scores_gemma":[0.00017029225,0.00022414466,0.0021424543,0.000097492455,0.0002141238,0.0008772739,0.00012699343,0.88675845,0.015937723,0.049721435,0.04361594,0.00011367757],"about_ca_topic_score_codex":0.0022976035,"about_ca_topic_score_gemma":0.0034442672,"teacher_disagreement_score":0.0054583587,"about_ca_system_score_codex":0.0008319166,"about_ca_system_score_gemma":0.0020762368,"threshold_uncertainty_score":0.018260002},"labels":[],"label_agreement":null},{"id":"W1574521024","doi":"10.1007/978-3-540-76928-6_33","title":"Constraint-Based Mining of Web Page Associations","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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":"University of Alberta","funders":"","keywords":"Heuristics; Association rule learning; Computer science; Data mining; Identification (biology); Process (computing); Key (lock); Ranking (information retrieval); Focus (optics); Resource (disambiguation); Constraint (computer-aided design); Machine learning; Data science; Artificial intelligence; Engineering","score_opus":0.03154203859856059,"score_gpt":0.27618510481201874,"score_spread":0.24464306621345816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1574521024","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13352984,0.002507367,0.8415077,0.0009210511,0.00015535246,0.0008113993,0.008933062,0.0034763273,0.008157878],"genre_scores_gemma":[0.34142005,0.001050763,0.6352097,0.00032681547,0.0001515256,0.00050444895,0.016799826,0.00036549586,0.0041713556],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967411,0.0005310725,0.0003276123,0.0006476003,0.0014981265,0.0002544886],"domain_scores_gemma":[0.98627234,0.008919791,0.0010839092,0.0012647167,0.0020869647,0.0003723276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017819876,0.00092018826,0.0019326701,0.0059860847,0.001457426,0.0026593846,0.0045296573,0.001329672,0.0046355953],"category_scores_gemma":[0.016268652,0.00069672853,0.0017779099,0.011798768,0.0009521487,0.002955675,0.0017132122,0.0014699796,0.0015884792],"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":[0.0012019314,0.0010698312,0.03778205,0.0019123284,0.0008667113,0.0019234708,0.00053264067,0.124591835,0.014886057,0.031183457,0.031039895,0.7530098],"study_design_scores_gemma":[0.00011674821,0.00012691379,0.007470944,0.00013353398,0.0002531735,0.0010708902,0.00025175177,0.9368503,0.007499545,0.036301505,0.009862658,0.0000620142],"about_ca_topic_score_codex":0.017026553,"about_ca_topic_score_gemma":0.03693156,"teacher_disagreement_score":0.017026553,"about_ca_system_score_codex":0.0009437739,"about_ca_system_score_gemma":0.0037604568,"threshold_uncertainty_score":0.0338549},"labels":[],"label_agreement":null},{"id":"W1578835529","doi":"","title":"Association Rules in Data Mining: An Application on a Clothing and Accessory Specialty Store","year":2014,"lang":"en","type":"article","venue":"Canadian social science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Association rule learning; Database transaction; Transaction data; Clothing; Product (mathematics); Apriori algorithm; Affinity analysis; Business; Lift (data mining); Value (mathematics); Set (abstract data type); Computer science; Marketing; Database; Advertising; Data mining","score_opus":0.03470362250395503,"score_gpt":0.29802585633070666,"score_spread":0.26332223382675163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1578835529","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33165625,0.0026207713,0.64335054,0.002677959,0.00023823736,0.0013343842,0.0051521715,0.008389671,0.0045799804],"genre_scores_gemma":[0.3210047,0.0014656708,0.67223597,0.00018728916,0.00007338603,0.0007200959,0.0024428775,0.00013496765,0.0017350224],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99657935,0.0014221657,0.0006408497,0.0004984308,0.0007233699,0.00013582098],"domain_scores_gemma":[0.984602,0.013237204,0.0004183524,0.00041229086,0.0011031167,0.00022713745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005316082,0.0008392036,0.0010458939,0.00370331,0.0009861746,0.0015406866,0.0010945345,0.0011934419,0.0021394326],"category_scores_gemma":[0.016251864,0.00060753804,0.0010603312,0.006000023,0.00043195506,0.0010794798,0.0011424567,0.0013015096,0.0007186873],"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":[0.00096840865,0.0015468001,0.06640309,0.0011237204,0.0006345525,0.0034167874,0.0018368425,0.10110201,0.004404667,0.0060695866,0.0109568145,0.80153674],"study_design_scores_gemma":[0.00021004726,0.000456002,0.028067494,0.00020646052,0.000262206,0.0013517942,0.0013504579,0.9349192,0.006451686,0.009822028,0.016813576,0.00008915785],"about_ca_topic_score_codex":0.008347596,"about_ca_topic_score_gemma":0.008182456,"teacher_disagreement_score":0.008347596,"about_ca_system_score_codex":0.0004632785,"about_ca_system_score_gemma":0.0013244168,"threshold_uncertainty_score":0.028114438},"labels":[],"label_agreement":null},{"id":"W1579524345","doi":"10.1007/978-3-642-40131-2_18","title":"Stream Mining of Frequent Patterns from Delayed Batches of Uncertain Data","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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 Manitoba","funders":"","keywords":"Data stream mining; Computer science; STREAMS; Sliding window protocol; Data mining; Data stream; Fading; Scheme (mathematics); Real-time computing; Window (computing); Telecommunications; Channel (broadcasting); Computer network; World Wide Web","score_opus":0.04259723588468572,"score_gpt":0.2723441762423638,"score_spread":0.22974694035767806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1579524345","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22250852,0.002072148,0.76949203,0.0004762319,0.0002587959,0.00029600156,0.0027931533,0.0009635638,0.0011395299],"genre_scores_gemma":[0.6716497,0.0014192986,0.31872168,0.000080817386,0.00037716713,0.00022449788,0.0052645276,0.00008683043,0.0021753954],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906546,0.000099428806,0.00012177869,0.0002234683,0.00040840654,0.000081482554],"domain_scores_gemma":[0.9950977,0.0031303326,0.00050493644,0.00042144084,0.0006909639,0.00015450163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015757948,0.00068860245,0.0012975131,0.0018384317,0.00046934257,0.0013471082,0.0015504254,0.0006724688,0.0009748877],"category_scores_gemma":[0.0071285022,0.0005041223,0.00096665113,0.0028983087,0.00029713212,0.001856709,0.00064389757,0.0010408469,0.00042196992],"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":[0.002474084,0.00066669064,0.039736543,0.0010676755,0.0004916973,0.002329055,0.00055783516,0.13668597,0.02617373,0.012405188,0.008512135,0.7688995],"study_design_scores_gemma":[0.0000483171,0.00025033054,0.004088849,0.00005343693,0.0001133706,0.00068752223,0.0001413689,0.96779424,0.0073577072,0.017099572,0.0023441466,0.0000212419],"about_ca_topic_score_codex":0.0011759128,"about_ca_topic_score_gemma":0.0015898916,"teacher_disagreement_score":0.0018384317,"about_ca_system_score_codex":0.00037603354,"about_ca_system_score_gemma":0.0006872421,"threshold_uncertainty_score":0.008333743},"labels":[],"label_agreement":null},{"id":"W1580093937","doi":"10.1007/3-540-44593-5_53","title":"Mining High-Quality Cases for Hypertext Prediction and Prefetching","year":2001,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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":"Simon Fraser University","funders":"","keywords":"Computer science; Hypertext; Quality (philosophy); Parallel computing; Data mining; Operating system","score_opus":0.04131834674854457,"score_gpt":0.28565945320756153,"score_spread":0.24434110645901697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1580093937","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6434335,0.0031052365,0.31273043,0.0025032214,0.00033751203,0.0009097043,0.015427266,0.014040837,0.0075123115],"genre_scores_gemma":[0.77054787,0.00066320953,0.20808081,0.00020049963,0.00031202481,0.00022105455,0.0156104695,0.00054721965,0.0038168316],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976146,0.00025734297,0.00028317963,0.00042091074,0.0011629224,0.00026099302],"domain_scores_gemma":[0.9887404,0.0055770855,0.0009787539,0.0019997896,0.0021619573,0.0005420402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012434627,0.0011709655,0.0011617739,0.007682374,0.0011274215,0.0023062804,0.002238197,0.0019171943,0.004666166],"category_scores_gemma":[0.018989155,0.00077311264,0.0011254648,0.005735299,0.0007857288,0.0037206747,0.0011626441,0.0013515423,0.002477853],"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":[0.0015647208,0.0010321137,0.20330647,0.000695204,0.00025091905,0.004114007,0.00054954085,0.044124298,0.030179529,0.005608153,0.052261923,0.65631306],"study_design_scores_gemma":[0.00015542768,0.00030572244,0.022493687,0.00014241113,0.000348733,0.0033775321,0.0006299743,0.88757133,0.043854777,0.029831516,0.01121757,0.00007122169],"about_ca_topic_score_codex":0.0043449453,"about_ca_topic_score_gemma":0.009242094,"teacher_disagreement_score":0.007682374,"about_ca_system_score_codex":0.00055217464,"about_ca_system_score_gemma":0.000957741,"threshold_uncertainty_score":0.01560992},"labels":[],"label_agreement":null},{"id":"W1581032865","doi":"10.1007/978-3-540-77048-0_10","title":"A Novel Method for Micro-Aggregation in Secure Statistical Databases Using Association and Interaction","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Cardinality (data modeling); Transitive closure; Mutual information; Association (psychology); Data mining; Set (abstract data type); Closure (psychology); Theoretical computer science; Transitive relation; Algorithm; Database; Artificial intelligence; Mathematics; Discrete mathematics; Combinatorics","score_opus":0.05896747598940669,"score_gpt":0.35839489233444605,"score_spread":0.29942741634503933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1581032865","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012519453,0.000082752995,0.99742293,0.000074902404,0.000055393088,0.00003840346,0.000043927073,0.00067390373,0.0003558546],"genre_scores_gemma":[0.05985659,0.00016807568,0.9356696,0.00015198962,0.00026313093,0.00021512383,0.0002702687,0.00022814385,0.0031770645],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99236906,0.001702833,0.0006370502,0.00119161,0.0037801543,0.00031928255],"domain_scores_gemma":[0.9903666,0.0033387227,0.0006082951,0.003723698,0.0016611215,0.00030159464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035736149,0.0009263494,0.0019849318,0.0025708007,0.0016413046,0.0032259799,0.0025388568,0.0011351861,0.0037709267],"category_scores_gemma":[0.010739696,0.0008426002,0.001686961,0.0037113181,0.0012400817,0.0037836563,0.0043952568,0.0026550966,0.0021990591],"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":[0.0005771889,0.00032403204,0.0031820044,0.00021950627,0.00034171244,0.00042057814,0.0005431201,0.035868436,0.018484307,0.1707082,0.016141828,0.75318915],"study_design_scores_gemma":[0.00006664174,0.00017561612,0.0009174682,0.0000333874,0.00013373031,0.001107729,0.00012056976,0.827796,0.017116793,0.12687333,0.025561545,0.000097207405],"about_ca_topic_score_codex":0.0011988893,"about_ca_topic_score_gemma":0.0018168273,"teacher_disagreement_score":0.0037709267,"about_ca_system_score_codex":0.00086782017,"about_ca_system_score_gemma":0.0020944292,"threshold_uncertainty_score":0.018899262},"labels":[],"label_agreement":null},{"id":"W1581468894","doi":"10.1007/978-3-540-30116-5_6","title":"Mining Positive and Negative Association Rules: An Approach for Confined Rules","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":197,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Association rule learning; Association (psychology); Associative property; Computer science; Process (computing); Data mining; Correlation; Complement (music); Affinity analysis; Space (punctuation); Artificial intelligence; Mathematics; Psychology","score_opus":0.01876755616653307,"score_gpt":0.25501796535937665,"score_spread":0.23625040919284357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1581468894","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021106115,0.0014564752,0.97303087,0.0003195213,0.00007942766,0.0004466411,0.0007816427,0.0015695549,0.0012097333],"genre_scores_gemma":[0.10292187,0.00067955226,0.89088887,0.0004308728,0.00016955797,0.00054342335,0.00217965,0.00019645858,0.0019897192],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9900087,0.0016066972,0.0015171728,0.0021553535,0.0043792217,0.00033292745],"domain_scores_gemma":[0.9742613,0.016846707,0.0012943991,0.004173562,0.0027530848,0.0006708881],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008058853,0.0014685567,0.0047906362,0.0063657206,0.0024597966,0.0046566017,0.0059726927,0.0025633627,0.0026413952],"category_scores_gemma":[0.03196687,0.0015184971,0.004310071,0.0068081478,0.0022778767,0.006290877,0.0061673196,0.0033334517,0.0012548496],"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":[0.0009668858,0.0008562336,0.014710819,0.001998806,0.0010955333,0.0022888642,0.0019943933,0.019157482,0.017050734,0.036254123,0.008521005,0.8951052],"study_design_scores_gemma":[0.00028822155,0.0008048496,0.006561678,0.00080940255,0.0018487396,0.0064410293,0.0017779036,0.62162215,0.01842772,0.30684838,0.034280974,0.00028905945],"about_ca_topic_score_codex":0.0022787254,"about_ca_topic_score_gemma":0.004185705,"teacher_disagreement_score":0.008058853,"about_ca_system_score_codex":0.0006402401,"about_ca_system_score_gemma":0.0023091766,"threshold_uncertainty_score":0.042619824},"labels":[],"label_agreement":null},{"id":"W1588921741","doi":"10.1007/978-3-642-37453-1_2","title":"PUF-Tree: A Compact Tree Structure for Frequent Pattern Mining of Uncertain Data","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":61,"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":"Tree (set theory); Computer science; Data mining; Tree structure; Uncertain data; K-ary tree; Algorithm; Mathematics; Binary tree","score_opus":0.04921570632610776,"score_gpt":0.29198430866385533,"score_spread":0.24276860233774758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1588921741","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013303653,0.0015503913,0.9644827,0.0004028047,0.00016737201,0.00024722773,0.009932318,0.008544936,0.0013685131],"genre_scores_gemma":[0.07486285,0.0013239054,0.90614223,0.00017123028,0.00013408704,0.00036556483,0.01470696,0.00057868205,0.0017143722],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910456,0.00016007354,0.00013930342,0.00015187825,0.00039286583,0.000051185027],"domain_scores_gemma":[0.9967796,0.001610283,0.00031135118,0.0005626605,0.00058924145,0.00014686388],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001354448,0.00066210714,0.0013098371,0.0028312383,0.0007792064,0.0015708131,0.001719761,0.0010562646,0.00530022],"category_scores_gemma":[0.010958595,0.0005336254,0.0010341041,0.0050884094,0.00037951424,0.0037789533,0.0014325859,0.001165284,0.0023855576],"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":[0.0008031389,0.00018287935,0.004160464,0.00140193,0.00021296614,0.00081308745,0.00053615327,0.028889913,0.009929457,0.031126445,0.05994149,0.862002],"study_design_scores_gemma":[0.00025368363,0.0004682561,0.002555156,0.00039923133,0.00023774849,0.002525632,0.00032978342,0.6675365,0.010467316,0.2111973,0.103906386,0.00012300094],"about_ca_topic_score_codex":0.0013633079,"about_ca_topic_score_gemma":0.0022781477,"teacher_disagreement_score":0.00530022,"about_ca_system_score_codex":0.0003915648,"about_ca_system_score_gemma":0.0013679992,"threshold_uncertainty_score":0.01773101},"labels":[],"label_agreement":null},{"id":"W1589379716","doi":"10.1109/icmla.2004.1383491","title":"Multi-dimensional sequential web mining by utilizing fuzzy interferencing","year":2005,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Inference; Data mining; Intuition; Web mining; Fuzzy logic; Web application; Domain (mathematical analysis); Machine learning; Artificial intelligence; Web service; World Wide Web; Mathematics","score_opus":0.03762111531358826,"score_gpt":0.28482422980585476,"score_spread":0.2472031144922665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1589379716","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08318215,0.0001531702,0.914609,0.000111922214,0.000023489456,0.0001436881,0.0002412665,0.0004173397,0.0011179971],"genre_scores_gemma":[0.51445806,0.00012323329,0.48425722,0.000048956255,0.000036313504,0.00013381208,0.00044291271,0.000018693267,0.00048087668],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981664,0.00026011732,0.00026906625,0.00039927065,0.0008066027,0.00009856889],"domain_scores_gemma":[0.99540836,0.0022745193,0.00068346295,0.00041846707,0.0010735133,0.00014161345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025304854,0.0005704576,0.0009752296,0.0036212073,0.0007710312,0.0011891717,0.0014984951,0.00052756665,0.0007026059],"category_scores_gemma":[0.008190752,0.00037192486,0.0011541793,0.0027871684,0.00058694324,0.001213571,0.0006763367,0.0006069107,0.00017245198],"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":[0.00082075415,0.00053010625,0.05055802,0.00038335694,0.0005121238,0.0010423395,0.00071962486,0.32678422,0.017419126,0.017362127,0.0015716613,0.5822965],"study_design_scores_gemma":[0.000020610025,0.000069805916,0.0025178504,0.000015176648,0.000052004292,0.000163612,0.000048410082,0.98363125,0.0038617977,0.008832327,0.00076417194,0.000022984845],"about_ca_topic_score_codex":0.0057210387,"about_ca_topic_score_gemma":0.00670192,"teacher_disagreement_score":0.0057210387,"about_ca_system_score_codex":0.0007517697,"about_ca_system_score_gemma":0.0009995402,"threshold_uncertainty_score":0.013382673},"labels":[],"label_agreement":null},{"id":"W1589918475","doi":"10.1007/978-3-540-27772-9_54","title":"Mining Web Sequential Patterns Incrementally with Revised PLWAP Tree","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms 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 Windsor","funders":"","keywords":"Computer science; Data mining; Tree (set theory); Web mining; Web page; Data stream mining; Point (geometry); Information retrieval; Database; World Wide Web","score_opus":0.019759765246205315,"score_gpt":0.24710461450956425,"score_spread":0.22734484926335893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1589918475","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11610786,0.0011258734,0.86186475,0.00055759493,0.0002348831,0.00078433973,0.0068354914,0.0094344765,0.0030548251],"genre_scores_gemma":[0.20926714,0.00045008303,0.7742953,0.00013497985,0.00010711269,0.0003238931,0.011667348,0.00032503367,0.0034291525],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989492,0.000103164835,0.00013962275,0.0002536629,0.00046261383,0.00009175127],"domain_scores_gemma":[0.9978777,0.0007059289,0.00015874601,0.0004402993,0.0007026823,0.000114656694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007166588,0.00055899465,0.0009673214,0.0039877756,0.000642865,0.0012939742,0.0015832018,0.0006453441,0.0022090457],"category_scores_gemma":[0.004872772,0.0005944584,0.0011952417,0.0041562007,0.0002644778,0.0024100968,0.0010230503,0.0008141277,0.0013038799],"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":[0.0005740265,0.00035789824,0.016301641,0.0005633505,0.00022752672,0.0009652485,0.0002133176,0.020074349,0.020734621,0.004042442,0.017531402,0.9184141],"study_design_scores_gemma":[0.0001251879,0.0003823242,0.00733787,0.000108686945,0.00042824526,0.0023093356,0.00027338255,0.9129747,0.022094028,0.030316005,0.02360146,0.000048803362],"about_ca_topic_score_codex":0.002639169,"about_ca_topic_score_gemma":0.0063349074,"teacher_disagreement_score":0.0039877756,"about_ca_system_score_codex":0.0002729253,"about_ca_system_score_gemma":0.0011588284,"threshold_uncertainty_score":0.0073899627},"labels":[],"label_agreement":null},{"id":"W1591220197","doi":"10.1007/978-3-642-29023-7_19","title":"Mining Social Networks for Significant Friend Groups","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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 Manitoba","funders":"","keywords":"Friendship; Computer science; Interdependence; World Wide Web; Social network (sociolinguistics); Social group; Tree (set theory); Internet privacy; Social network analysis; Data science; Social media; Sociology; Social science","score_opus":0.026763849917572108,"score_gpt":0.26129530314848376,"score_spread":0.23453145323091165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1591220197","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4620562,0.0064281155,0.49111912,0.0018278802,0.00033799713,0.00075776345,0.017071772,0.0026161943,0.017785003],"genre_scores_gemma":[0.8239718,0.001491768,0.14908428,0.00012182727,0.00051105313,0.00037824444,0.017176418,0.0001604246,0.0071041435],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992687,0.00014091891,0.000048796923,0.00027770142,0.00019160144,0.00007231436],"domain_scores_gemma":[0.99749506,0.0014283365,0.00032500076,0.00032645828,0.00027714297,0.00014807085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057984906,0.0009874603,0.0007147954,0.0054875384,0.0011582164,0.001305358,0.0013352202,0.0011320781,0.0034588678],"category_scores_gemma":[0.0068476647,0.00047544987,0.001481678,0.0030345598,0.00042562096,0.002734776,0.0011383529,0.00090471003,0.0018810334],"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":[0.00093973835,0.00088998437,0.14393693,0.0014392099,0.0011286958,0.0012468081,0.0015797685,0.049242143,0.0148265865,0.032046504,0.050753184,0.70197046],"study_design_scores_gemma":[0.00009397088,0.00032758297,0.04535734,0.00025641292,0.0005865204,0.0023087554,0.0016023143,0.8019473,0.007769185,0.116182044,0.023488669,0.000079831945],"about_ca_topic_score_codex":0.0018281083,"about_ca_topic_score_gemma":0.0052526165,"teacher_disagreement_score":0.0054875384,"about_ca_system_score_codex":0.0005142466,"about_ca_system_score_gemma":0.00044920668,"threshold_uncertainty_score":0.01157105},"labels":[],"label_agreement":null},{"id":"W1592291313","doi":"10.1007/11430919_30","title":"Considering Re-occurring Features in Associative Classifiers","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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 Alberta","funders":"","keywords":"Associative property; Computer science; Association rule learning; Artificial intelligence; Repetition (rhetorical device); Class (philosophy); Binary classification; Binary number; Association (psychology); Pattern recognition (psychology); Machine learning; Data mining; Support vector machine; Mathematics; Arithmetic","score_opus":0.024903828036657423,"score_gpt":0.27236170801453186,"score_spread":0.24745787997787444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1592291313","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21304835,0.0032830886,0.77072036,0.00076132966,0.0011583036,0.00027135236,0.000662411,0.0018873862,0.008207471],"genre_scores_gemma":[0.8138164,0.001250153,0.17322008,0.0003267691,0.00092136505,0.0001981471,0.0016105858,0.0003683905,0.008288124],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968856,0.0006503696,0.00034194515,0.0006554593,0.0011815056,0.00028516186],"domain_scores_gemma":[0.98538905,0.007808312,0.00061611214,0.0029292367,0.0029867347,0.00027061356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037145214,0.0009901333,0.0019802784,0.0027616117,0.0014080516,0.0026252177,0.0021718019,0.0021217775,0.004293056],"category_scores_gemma":[0.019770794,0.00054619653,0.0010657466,0.0034810167,0.0007524732,0.0070124003,0.0015885533,0.0021415998,0.0020152282],"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":[0.0011497756,0.0005034238,0.013784662,0.0005083617,0.00029200863,0.0008760255,0.0003004195,0.03324409,0.014756872,0.013168878,0.011152614,0.91026294],"study_design_scores_gemma":[0.000062073326,0.00040055445,0.0055318787,0.00019090668,0.000586458,0.0015583585,0.00035171662,0.88039094,0.021232048,0.08077689,0.008838256,0.00007984775],"about_ca_topic_score_codex":0.0015900672,"about_ca_topic_score_gemma":0.002919927,"teacher_disagreement_score":0.004293056,"about_ca_system_score_codex":0.00043460066,"about_ca_system_score_gemma":0.000939793,"threshold_uncertainty_score":0.019644499},"labels":[],"label_agreement":null},{"id":"W1592399994","doi":"10.4018/978-1-59140-057-8.ch005","title":"A Proposed Process for Performing Data Mining Projects","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada)","funders":"","keywords":"Process (computing); Data science; Computer science; Data mining; Knowledge management; Process management; Engineering","score_opus":0.10499023637669844,"score_gpt":0.31119780459149576,"score_spread":0.20620756821479733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1592399994","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006491544,0.00034897952,0.9505832,0.0047805314,0.00022595591,0.004672775,0.00024415844,0.001632965,0.031019758],"genre_scores_gemma":[0.013549261,0.0003110964,0.96510506,0.00021030652,0.00004323219,0.0014320146,0.0003698593,0.00013810916,0.018841125],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9818887,0.007978256,0.0016475662,0.0022633104,0.0056017754,0.00062032347],"domain_scores_gemma":[0.9798233,0.007903711,0.0014864767,0.0030527136,0.006201369,0.0015325258],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022154199,0.0013176491,0.0005194437,0.0037992029,0.0034723023,0.010429145,0.004421339,0.0035104423,0.012403956],"category_scores_gemma":[0.030911101,0.0012613414,0.0013802568,0.0041949493,0.0026304391,0.011284828,0.0053872904,0.004078105,0.009464242],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000077869256,0.0005773326,0.0028598593,0.0007053566,0.000026476602,0.0008992675,0.009179651,0.0072847097,0.005391505,0.5530701,0.026601307,0.3933266],"study_design_scores_gemma":[0.000103184066,0.00053428777,0.0017861002,0.0012332351,0.000045065917,0.0020535786,0.0052046687,0.06117668,0.011473094,0.28110024,0.6351116,0.00017831549],"about_ca_topic_score_codex":0.0015078131,"about_ca_topic_score_gemma":0.0018943876,"teacher_disagreement_score":0.022154199,"about_ca_system_score_codex":0.003218154,"about_ca_system_score_gemma":0.014021684,"threshold_uncertainty_score":0.117164016},"labels":[],"label_agreement":null},{"id":"W1592511765","doi":"10.1023/a:1008778107391","title":"Efficient Rule-Based Attribute-Oriented Induction for Data Mining","year":2000,"lang":"en","type":"article","venue":"Journal of Intelligent 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":"Simon Fraser University","funders":"","keywords":"Computer science; Generalization; Data mining; Rule induction; Backtracking; Knowledge extraction; Algorithm; Mathematics","score_opus":0.05392687639899999,"score_gpt":0.2939089391231826,"score_spread":0.23998206272418263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1592511765","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013331355,0.00069749786,0.9756806,0.0002560854,0.00010498254,0.00040361745,0.0010430517,0.006521692,0.0019611085],"genre_scores_gemma":[0.111227326,0.00046758787,0.88111514,0.00023064188,0.00009144783,0.00043541673,0.004027521,0.00024060253,0.0021643513],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99730515,0.0006347904,0.0003746135,0.00045720037,0.0010441818,0.00018398327],"domain_scores_gemma":[0.99334466,0.003959911,0.00027909986,0.0009030667,0.0013873935,0.00012593639],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002548057,0.000863224,0.0020593314,0.0030847522,0.0011672777,0.0018180002,0.0030920324,0.00083482417,0.0030992534],"category_scores_gemma":[0.008384484,0.0005999374,0.0013212438,0.0036399586,0.00052986166,0.0019458178,0.0016322721,0.0017500435,0.0033531568],"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":[0.00024311646,0.0004879603,0.0026836896,0.0003456901,0.00015236344,0.00021725275,0.00012492228,0.021957513,0.0071318927,0.005573401,0.0109000895,0.95018214],"study_design_scores_gemma":[0.00015800135,0.00020040097,0.0021027916,0.00009922385,0.0002472527,0.00055267406,0.0001153069,0.91607934,0.019555056,0.050832875,0.009994853,0.00006227291],"about_ca_topic_score_codex":0.003138729,"about_ca_topic_score_gemma":0.0048880004,"teacher_disagreement_score":0.003138729,"about_ca_system_score_codex":0.0006250458,"about_ca_system_score_gemma":0.0030462719,"threshold_uncertainty_score":0.013475537},"labels":[],"label_agreement":null},{"id":"W1594085708","doi":"10.1007/11875604_56","title":"Mining and Modeling Database User Access Patterns","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms 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":"York University","funders":"","keywords":"Computer science; TRACE (psycholinguistics); Database; Focus (optics); Data mining; Database design; Database model; Data modeling; Information retrieval","score_opus":0.041311983235184625,"score_gpt":0.28974080619172327,"score_spread":0.24842882295653865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1594085708","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45249742,0.0015369783,0.5360138,0.0010637812,0.00007523131,0.0002688156,0.003182311,0.0022988291,0.0030628922],"genre_scores_gemma":[0.8069661,0.0012211287,0.18404835,0.00011039114,0.00010473934,0.0002120111,0.00407878,0.00012515554,0.0031333365],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865353,0.00024826426,0.00015444789,0.00034165653,0.0004812912,0.00012081021],"domain_scores_gemma":[0.9948919,0.0029584148,0.00059929903,0.00067001244,0.0007303809,0.0001500479],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013930259,0.00062495645,0.0007928254,0.0040181363,0.0005584025,0.00221503,0.0015257319,0.0009375625,0.00097396126],"category_scores_gemma":[0.009024393,0.00059171655,0.0011814823,0.004627451,0.00049460016,0.0044612987,0.00076765544,0.0010244709,0.00051303994],"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":[0.0004936,0.00094253954,0.20472878,0.0006385051,0.0004054605,0.0009986857,0.0010198964,0.1187224,0.009857314,0.042582188,0.010280505,0.6093302],"study_design_scores_gemma":[0.000013073278,0.00006525583,0.0103901215,0.000037746904,0.00008731737,0.0004997714,0.00020843267,0.94959915,0.0033087428,0.033161335,0.0026095638,0.00001950941],"about_ca_topic_score_codex":0.0059928154,"about_ca_topic_score_gemma":0.010007479,"teacher_disagreement_score":0.0059928154,"about_ca_system_score_codex":0.00074061466,"about_ca_system_score_gemma":0.0009329573,"threshold_uncertainty_score":0.011915922},"labels":[],"label_agreement":null},{"id":"W1594281414","doi":"","title":"Product-Driven Data Mining","year":2003,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Product (mathematics); Preference; Data collection; Computer science; Data mining; Marketing; Information retrieval; Data science; Business; Mathematics; Statistics","score_opus":0.06860464979290952,"score_gpt":0.2950119074987205,"score_spread":0.226407257705811,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1594281414","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05319554,0.0022714296,0.76554537,0.0022797848,0.00041455394,0.0043717236,0.14457868,0.017811492,0.009531386],"genre_scores_gemma":[0.14475878,0.001171679,0.692854,0.0005267153,0.00011463738,0.0027888757,0.15336801,0.0004023184,0.004014997],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99565864,0.0008727111,0.00048778337,0.0010780321,0.0016942633,0.00020858206],"domain_scores_gemma":[0.99259853,0.0034111657,0.00049004116,0.0013089571,0.001993148,0.00019820403],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049183313,0.0015516195,0.001785037,0.0049133655,0.0007661752,0.002879995,0.0038018858,0.0013954943,0.004168607],"category_scores_gemma":[0.015503073,0.0007608805,0.0027447322,0.007558672,0.00055970775,0.0016416158,0.0018165333,0.0021593496,0.003944873],"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":[0.00070997776,0.0012468449,0.04844782,0.0031780782,0.00097620924,0.0008446066,0.0005619397,0.15854743,0.0046808063,0.022067716,0.10245981,0.6562788],"study_design_scores_gemma":[0.00013844474,0.00027531217,0.010972482,0.00024852343,0.00012786183,0.00058957847,0.00042796563,0.8503978,0.008531856,0.03441539,0.093793854,0.0000809569],"about_ca_topic_score_codex":0.008871833,"about_ca_topic_score_gemma":0.013867527,"teacher_disagreement_score":0.008871833,"about_ca_system_score_codex":0.0014546287,"about_ca_system_score_gemma":0.0033507566,"threshold_uncertainty_score":0.02601099},"labels":[],"label_agreement":null},{"id":"W1597513392","doi":"10.1109/ccece.1993.332373","title":"The symbolic classification of objects described by graphs: an aid to any process based on comparative discrimination","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Reuse; Process (computing); Graph; Domain (mathematical analysis); Symbolic execution; Artificial intelligence; Software; Data mining; Information retrieval; Theoretical computer science; Programming language; Mathematics","score_opus":0.06505733656002367,"score_gpt":0.3105003047490027,"score_spread":0.24544296818897904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1597513392","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0056297067,0.00046887185,0.9771394,0.00079278403,0.00015206856,0.00010644391,0.00027016754,0.0019187169,0.013521803],"genre_scores_gemma":[0.064416066,0.0005019609,0.9313859,0.00021344145,0.0001094706,0.00012296965,0.00057634606,0.00030318648,0.002370572],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967301,0.001584843,0.00025326866,0.00051207806,0.0008057517,0.00011396242],"domain_scores_gemma":[0.9917116,0.0045677037,0.0005973682,0.0020466615,0.0008291319,0.00024751268],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042087478,0.0011389903,0.0010568192,0.0088338675,0.0020350688,0.0057799565,0.0022325593,0.0014432095,0.016713722],"category_scores_gemma":[0.019040322,0.00047661873,0.001228944,0.0062568793,0.004941459,0.011594394,0.004021651,0.0023061014,0.004772814],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014814755,0.00008976088,0.0015664006,0.00043044172,0.00005102947,0.00023490352,0.0018221653,0.004220921,0.004629071,0.5326451,0.0076034525,0.44655854],"study_design_scores_gemma":[0.00003296265,0.00012313701,0.001520608,0.00037505256,0.000068911875,0.00097464264,0.0015058306,0.060992748,0.0058814245,0.8101627,0.118265115,0.00009677355],"about_ca_topic_score_codex":0.0018556896,"about_ca_topic_score_gemma":0.0020436593,"teacher_disagreement_score":0.016713722,"about_ca_system_score_codex":0.0012954966,"about_ca_system_score_gemma":0.0015861018,"threshold_uncertainty_score":0.055912912},"labels":[],"label_agreement":null},{"id":"W1598033829","doi":"10.48550/arxiv.1209.3089","title":"Pattern Detection with Rare Item-set Mining","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Algoma University","funders":"","keywords":"Set (abstract data type); Computer science; Data mining; Artificial intelligence; Information retrieval; Pattern recognition (psychology); Programming language","score_opus":0.07141462304812494,"score_gpt":0.18696320282228646,"score_spread":0.11554857977416151,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1598033829","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009891541,0.0007331504,0.98584574,0.00036121535,0.00011853568,0.00023838371,0.00054925936,0.0014985314,0.00076346577],"genre_scores_gemma":[0.117862776,0.00053817517,0.8779322,0.00030747638,0.00020859306,0.0004650596,0.0016015014,0.000092252056,0.0009919667],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9894469,0.0041151294,0.0011549698,0.0021666707,0.0027660085,0.00035033043],"domain_scores_gemma":[0.9792923,0.013395609,0.0015449957,0.0038509786,0.0016194991,0.00029662641],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008649725,0.001670255,0.0035160466,0.008659465,0.0011301995,0.0035460284,0.004969471,0.0031548818,0.0020978623],"category_scores_gemma":[0.03649712,0.0010474575,0.0027758558,0.0088634305,0.001459567,0.004233822,0.004302104,0.003453581,0.0027111832],"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":[0.000941814,0.0010099974,0.02785248,0.0012781806,0.0013740602,0.002094012,0.0006387171,0.08420633,0.010671602,0.044682335,0.012678189,0.81257236],"study_design_scores_gemma":[0.00010694818,0.0002112604,0.0019234366,0.00012377913,0.00016791599,0.0021096494,0.00017169697,0.87848943,0.007478993,0.102223985,0.006912051,0.00008074982],"about_ca_topic_score_codex":0.00090150296,"about_ca_topic_score_gemma":0.0008005686,"teacher_disagreement_score":0.008659465,"about_ca_system_score_codex":0.00052720547,"about_ca_system_score_gemma":0.0010539216,"threshold_uncertainty_score":0.045744658},"labels":[],"label_agreement":null},{"id":"W1599136575","doi":"10.1109/adl.1998.670376","title":"Discovering Web access patterns and trends by applying OLAP and data mining technology on Web logs","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":396,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Web mining; World Wide Web; Clickstream; Data Web; The Internet; Web page; Web development; Web intelligence; Online analytical processing; Web API; Database; Data warehouse","score_opus":0.05271091983902785,"score_gpt":0.30464539022079734,"score_spread":0.25193447038176947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1599136575","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30394682,0.0018539204,0.6458239,0.001875415,0.0001366389,0.0014381132,0.022855291,0.015849173,0.0062207617],"genre_scores_gemma":[0.39109334,0.0015868873,0.5842049,0.00019823562,0.000115268296,0.00081907696,0.020220555,0.00029867384,0.0014630673],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978446,0.0003677043,0.00040401678,0.0003773504,0.0008975642,0.00010884048],"domain_scores_gemma":[0.9909277,0.0047267633,0.0014057773,0.0011450752,0.0015098943,0.00028491163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024649748,0.0011095924,0.0010418404,0.015419136,0.00082527404,0.003222097,0.0011334762,0.0006806756,0.0008710705],"category_scores_gemma":[0.01097112,0.00051999214,0.0009882668,0.009561462,0.000422372,0.00377558,0.0010547703,0.0011753399,0.0009255581],"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":[0.00034031956,0.0010188674,0.15852198,0.0011591015,0.000331889,0.0008751893,0.0014821402,0.025775155,0.012243515,0.004625603,0.0069143577,0.78671193],"study_design_scores_gemma":[0.000090830894,0.00066126685,0.10683719,0.0005479518,0.00045263313,0.002283764,0.00399781,0.7519039,0.041627757,0.05133466,0.039968867,0.00029334472],"about_ca_topic_score_codex":0.0058849286,"about_ca_topic_score_gemma":0.009898797,"teacher_disagreement_score":0.015419136,"about_ca_system_score_codex":0.0007253101,"about_ca_system_score_gemma":0.0014525302,"threshold_uncertainty_score":0.013036191},"labels":[],"label_agreement":null},{"id":"W1601793508","doi":"10.1007/978-3-642-37574-3_8","title":"Discovering Frequent Patterns from Uncertain Data Streams with Time-Fading and Landmark Models","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":60,"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":"Landmark; Computer science; Data stream mining; Fading; STREAMS; Sliding window protocol; Data mining; Data stream; Window (computing); Artificial intelligence; Real-time computing; Telecommunications; Channel (broadcasting); Computer network; World Wide Web","score_opus":0.02964745347581408,"score_gpt":0.24281240655154315,"score_spread":0.21316495307572908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1601793508","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08656219,0.0012926064,0.9104338,0.00030478218,0.00006796706,0.000058178244,0.0004732752,0.0003730034,0.00043414687],"genre_scores_gemma":[0.8044301,0.001823619,0.18961827,0.00009020915,0.00032364964,0.00017296939,0.0019744043,0.00008556353,0.0014812391],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982527,0.00034163083,0.0001914145,0.0005442267,0.00048156673,0.00018834807],"domain_scores_gemma":[0.98526126,0.011092277,0.0015873209,0.0010471593,0.00076843926,0.00024347522],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002953739,0.0010451553,0.001894834,0.002180018,0.0004907652,0.0019041055,0.0025210658,0.0013400492,0.00091478793],"category_scores_gemma":[0.017871782,0.0007398764,0.0019587527,0.0032430473,0.00094580697,0.004503809,0.0013294055,0.0020494792,0.00039669205],"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":[0.0009136292,0.00021781199,0.029085698,0.0005664384,0.0005816434,0.0018004507,0.00065487734,0.69857126,0.0037012307,0.039947428,0.0033594198,0.22060013],"study_design_scores_gemma":[0.000014065094,0.00005159282,0.0011195614,0.000018212784,0.000051662588,0.00021089806,0.00006749623,0.9690027,0.00043278362,0.028520217,0.0004954132,0.00001538924],"about_ca_topic_score_codex":0.0025300991,"about_ca_topic_score_gemma":0.002139125,"teacher_disagreement_score":0.002953739,"about_ca_system_score_codex":0.0007071563,"about_ca_system_score_gemma":0.00060524675,"threshold_uncertainty_score":0.015621066},"labels":[],"label_agreement":null},{"id":"W1603563923","doi":"10.1023/a:1022419032620","title":"Extracting Share Frequent Itemsets with Infrequent Subsets","year":2003,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":77,"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 Regina","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Data mining; Association rule learning; Computer science; Measure (data warehouse); Property (philosophy); Database transaction; Heuristic; Set (abstract data type); Closure (psychology); Artificial intelligence; Database","score_opus":0.051266264070474,"score_gpt":0.2920698709287232,"score_spread":0.24080360685824923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1603563923","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47214955,0.001146708,0.5150251,0.00055619277,0.0003352791,0.00079550256,0.0034675384,0.0023096628,0.004214488],"genre_scores_gemma":[0.6072561,0.00056710304,0.37652043,0.00011800132,0.00041676767,0.000305962,0.011916996,0.00019684102,0.0027018206],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976024,0.00027365272,0.00038591112,0.00043721366,0.0010300428,0.00027088355],"domain_scores_gemma":[0.99241346,0.0029747623,0.00088459917,0.0016584645,0.0016899197,0.00037888088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015724883,0.0013630749,0.002251542,0.0073605594,0.0015574812,0.0027538536,0.0018697787,0.0014604478,0.0035796561],"category_scores_gemma":[0.010449158,0.00090428,0.0022170667,0.0076067112,0.00051878294,0.0039465725,0.0019480676,0.0011527818,0.0025788709],"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":[0.0030262708,0.0010735372,0.07644452,0.0009057978,0.0011655736,0.005128957,0.0010765893,0.010011311,0.05625634,0.0080619855,0.0090630995,0.827786],"study_design_scores_gemma":[0.00076539797,0.0037341153,0.07774067,0.0004411373,0.003893983,0.023755014,0.005566013,0.6074957,0.14326634,0.08531866,0.047760155,0.000262851],"about_ca_topic_score_codex":0.0007377396,"about_ca_topic_score_gemma":0.0014588654,"teacher_disagreement_score":0.0073605594,"about_ca_system_score_codex":0.0003702138,"about_ca_system_score_gemma":0.001306992,"threshold_uncertainty_score":0.01197511},"labels":[],"label_agreement":null},{"id":"W1606519679","doi":"","title":"Transactions on Computational Science V: Special Issue on Cognitive Knowledge Representation","year":2009,"lang":"en","type":"book","venue":"Springer eBooks","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":"University of Calgary","funders":"","keywords":"Computer science; Data science; Field (mathematics); Computational intelligence; Representation (politics); Computational model; Realm; Theory of computation; Knowledge representation and reasoning; Scale (ratio); Management science; Artificial intelligence; Engineering","score_opus":0.027975235972136206,"score_gpt":0.30519160778187504,"score_spread":0.27721637180973885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1606519679","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010682187,0.15279116,0.3518803,0.026440348,0.09895213,0.00039640412,0.0023612601,0.0029731975,0.3535229],"genre_scores_gemma":[0.08905113,0.1551006,0.1802435,0.005361897,0.032016113,0.0006691753,0.00740942,0.0021979709,0.52795017],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988073,0.00023375366,0.00009871161,0.00019358023,0.00059431675,0.00007234731],"domain_scores_gemma":[0.9976999,0.0009379702,0.00006467604,0.00059434946,0.00055608177,0.00014689578],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017231298,0.0010598364,0.0026418453,0.0016865066,0.0006138237,0.004847592,0.0015997224,0.0015738124,0.07147124],"category_scores_gemma":[0.005340702,0.00056815095,0.00093908986,0.004448065,0.0013742094,0.0056374697,0.002073052,0.0026038068,0.02154152],"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":[0.000071717615,0.00006799049,0.00033115243,0.0007834794,0.00010499436,0.00006884077,0.00011187533,0.0017247038,0.0012251958,0.05430721,0.41797253,0.5232303],"study_design_scores_gemma":[0.000039015744,0.000058381524,0.0014377984,0.00047825708,0.00012126364,0.0004975323,0.00020581462,0.013982073,0.0013589959,0.17719504,0.8045918,0.000033985543],"about_ca_topic_score_codex":0.0018149993,"about_ca_topic_score_gemma":0.0019788162,"teacher_disagreement_score":0.07147124,"about_ca_system_score_codex":0.0012799419,"about_ca_system_score_gemma":0.0016052847,"threshold_uncertainty_score":0.23909515},"labels":[],"label_agreement":null},{"id":"W1615499426","doi":"10.1109/ccece.2004.1349689","title":"Mammographic information analysis through association-rule mining","year":2004,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Association rule learning; Computer science; Atlas (anatomy); Data mining; K-optimal pattern discovery; Information retrieval; Scalability; Data science; Knowledge extraction; Database","score_opus":0.008667043931421599,"score_gpt":0.23439104529270233,"score_spread":0.22572400136128074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1615499426","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021404779,0.00082871085,0.9702219,0.00053332304,0.000055633693,0.00044407873,0.0013202843,0.003627728,0.0015636723],"genre_scores_gemma":[0.13184008,0.0005444601,0.86415595,0.00013545797,0.00006878319,0.00027110887,0.0023140328,0.00007270546,0.00059735915],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99513394,0.0014189698,0.0007692585,0.0008797083,0.0016437883,0.00015422754],"domain_scores_gemma":[0.9903522,0.0060621393,0.0010291527,0.0009905054,0.001437656,0.0001283749],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004676415,0.0011711501,0.0021974118,0.009784199,0.0007300305,0.0023606182,0.0025572802,0.0011019927,0.0015151773],"category_scores_gemma":[0.016453624,0.00049531186,0.0015554775,0.0065145874,0.0005693492,0.002331686,0.0011170125,0.001266006,0.0013813417],"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":[0.00034113845,0.0009898024,0.026988043,0.0007450587,0.00068773265,0.00083504786,0.00034063615,0.048535828,0.008427852,0.008325889,0.007929653,0.89585316],"study_design_scores_gemma":[0.00011678882,0.0003294816,0.009137882,0.00020293394,0.00040403655,0.0017062298,0.0003930941,0.90937203,0.022944657,0.04052427,0.014761542,0.000107126274],"about_ca_topic_score_codex":0.0022213608,"about_ca_topic_score_gemma":0.0024147723,"teacher_disagreement_score":0.009784199,"about_ca_system_score_codex":0.00048714102,"about_ca_system_score_gemma":0.0011196225,"threshold_uncertainty_score":0.024731576},"labels":[],"label_agreement":null},{"id":"W162107547","doi":"","title":"Evaluating Data Mining Models: A Pattern Language","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Data mining; Context (archaeology); Resolution (logic); Sequential Pattern Mining; Section (typography); Artificial intelligence; Geography","score_opus":0.29922702637863785,"score_gpt":0.3807078313623228,"score_spread":0.08148080498368493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W162107547","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002137433,0.00024576095,0.9917576,0.0027667694,0.000074606185,0.00019043148,0.00030762277,0.0007248462,0.0017949545],"genre_scores_gemma":[0.028442435,0.00037616488,0.96788263,0.00059684156,0.0001736913,0.0006117033,0.00058570073,0.00025016267,0.0010806106],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9811102,0.0074968324,0.0030141121,0.0025671497,0.0054374347,0.0003741928],"domain_scores_gemma":[0.96854067,0.019147914,0.0030388003,0.0050639454,0.0036213188,0.00058734615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017097125,0.0018617344,0.0013965633,0.0044292086,0.0015154601,0.008687653,0.003940171,0.003029835,0.0036381693],"category_scores_gemma":[0.056855414,0.0010728826,0.0024234902,0.005556526,0.005230245,0.02081414,0.004269256,0.005099402,0.0016811194],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012909951,0.0001077208,0.0025855508,0.00069376314,0.00014766648,0.00048134875,0.0017680359,0.011105023,0.002840826,0.79001904,0.016575672,0.17354624],"study_design_scores_gemma":[0.000054074335,0.00020314158,0.00046397245,0.0004807515,0.00009288674,0.0010972539,0.0007219596,0.15925524,0.0050808284,0.754355,0.07812064,0.000074277865],"about_ca_topic_score_codex":0.0012282857,"about_ca_topic_score_gemma":0.0010785403,"teacher_disagreement_score":0.017097125,"about_ca_system_score_codex":0.0017784009,"about_ca_system_score_gemma":0.0024654625,"threshold_uncertainty_score":0.09041935},"labels":[],"label_agreement":null},{"id":"W162707042","doi":"","title":"Calculating data warehouse aggregates using range-encoded bitmap index.","year":2002,"lang":"en","type":"article","venue":"Scholarship at UWindsor (University of Windsor)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Data warehouse; Bitmap; Index (typography); Range (aeronautics); Computer science; Data mining; Database; Statistics; Mathematics; Artificial intelligence; World Wide Web; Engineering","score_opus":0.09936808141982138,"score_gpt":0.26085577660449205,"score_spread":0.16148769518467065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W162707042","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.072565496,0.0010139433,0.9110244,0.00014889595,0.00012608815,0.000298796,0.0015142343,0.0067565637,0.0065515474],"genre_scores_gemma":[0.2661049,0.00073372404,0.7245404,0.00006411949,0.00004750745,0.00026293917,0.0048400466,0.00036977974,0.0030365794],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998874,0.0000705203,0.00012265168,0.00014351255,0.0007058285,0.00008346636],"domain_scores_gemma":[0.99855417,0.00020430463,0.0001962883,0.00019784874,0.0007963479,0.00005096157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005875035,0.00085346604,0.0007537262,0.0032104326,0.0006020318,0.0026332226,0.00095714664,0.00037970225,0.0020102225],"category_scores_gemma":[0.003343457,0.00032317513,0.00063562486,0.003870937,0.00022120094,0.0037470006,0.0011403299,0.00042823845,0.0012551502],"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":[0.0006587772,0.00019556655,0.02128391,0.0005220571,0.0001866981,0.00046204482,0.00056925893,0.0522569,0.09312042,0.019513732,0.012451814,0.7987788],"study_design_scores_gemma":[0.000060991777,0.00039892472,0.014236764,0.00008022939,0.00013676038,0.0009219515,0.0004862454,0.74586165,0.19444214,0.014354673,0.028864637,0.00015502865],"about_ca_topic_score_codex":0.0029678112,"about_ca_topic_score_gemma":0.0022811096,"teacher_disagreement_score":0.0032104326,"about_ca_system_score_codex":0.000827557,"about_ca_system_score_gemma":0.0009823069,"threshold_uncertainty_score":0.006724894},"labels":[],"label_agreement":null},{"id":"W1629982162","doi":"","title":"An Introduction to Data Structures with Applications","year":2001,"lang":"en","type":"book","venue":"CERN Document Server (European Organization for Nuclear Research)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":102,"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":"Computer science","score_opus":0.03376638287500426,"score_gpt":0.2924443787327042,"score_spread":0.2586779958576999,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1629982162","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013317047,0.070503,0.8526094,0.004284675,0.004393517,0.00033855057,0.00339839,0.01186816,0.05127263],"genre_scores_gemma":[0.013903002,0.07452257,0.7614756,0.004465336,0.0058804597,0.001101803,0.008192897,0.0057854806,0.12467288],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99711156,0.0003526013,0.00042195414,0.00045080847,0.0015489392,0.00011410622],"domain_scores_gemma":[0.99628794,0.002006009,0.0001616669,0.0008252623,0.0005724651,0.00014667067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016731189,0.0027544366,0.0029328638,0.0053789755,0.0013528997,0.0058375304,0.0031327843,0.0019544752,0.032793596],"category_scores_gemma":[0.0068639177,0.0026186996,0.0020801073,0.017748507,0.0023943502,0.0118638035,0.0032469805,0.0061291885,0.033852875],"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":[0.000039409948,0.000068878435,0.00019213608,0.0014590906,0.000031990963,0.0001212742,0.00019283567,0.002244338,0.001510415,0.16088854,0.22651637,0.6067347],"study_design_scores_gemma":[0.000020385145,0.000035565587,0.00020757264,0.000416575,0.000026726706,0.00085236033,0.000040677452,0.0057760477,0.0011611783,0.21005462,0.78136814,0.00004020849],"about_ca_topic_score_codex":0.0010677578,"about_ca_topic_score_gemma":0.0010709465,"teacher_disagreement_score":0.032793596,"about_ca_system_score_codex":0.0014754225,"about_ca_system_score_gemma":0.0017832869,"threshold_uncertainty_score":0.10970557},"labels":[],"label_agreement":null},{"id":"W1646633498","doi":"10.1007/978-3-319-22729-0_10","title":"Big Data Analytics of Social Networks for the Discovery of “Following” Patterns","year":2015,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":63,"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":"Big data; Computer science; Data science; Interdependence; Social network (sociolinguistics); Social network analysis; Analytics; Friendship; World Wide Web; Data mining; Social media; Sociology; Social science","score_opus":0.08719827100810508,"score_gpt":0.3050975525639662,"score_spread":0.21789928155586114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1646633498","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.111836575,0.011720605,0.82278633,0.004081416,0.0005208537,0.00044758816,0.030774008,0.004669452,0.01316318],"genre_scores_gemma":[0.46805173,0.0055599706,0.49188882,0.000513401,0.0005615606,0.0004261473,0.027321525,0.00024370622,0.0054331557],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991223,0.00019480636,0.000066780565,0.0002838993,0.0002773437,0.000054763146],"domain_scores_gemma":[0.9967548,0.0019471309,0.00041335472,0.00051031134,0.0002173747,0.00015697011],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000891328,0.0009744805,0.0009525052,0.0045003705,0.00059166545,0.0021557584,0.0015560064,0.0010068801,0.0035672637],"category_scores_gemma":[0.0067400625,0.000459694,0.0011587373,0.0063449764,0.000601158,0.0038503197,0.0013927447,0.0015144539,0.0026213038],"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":[0.00039737343,0.000616602,0.055439517,0.0020919242,0.00082221243,0.00051719876,0.0013092537,0.038727667,0.014844925,0.083207294,0.07147148,0.7305546],"study_design_scores_gemma":[0.00002650371,0.00014364548,0.018254934,0.00027974456,0.0001592859,0.00062606734,0.00075555313,0.5804129,0.007898652,0.35574177,0.035628993,0.00007185963],"about_ca_topic_score_codex":0.001895193,"about_ca_topic_score_gemma":0.0036332756,"teacher_disagreement_score":0.0045003705,"about_ca_system_score_codex":0.00056849513,"about_ca_system_score_gemma":0.00054158276,"threshold_uncertainty_score":0.011933744},"labels":[],"label_agreement":null},{"id":"W1647183428","doi":"10.1007/3-540-44886-1_62","title":"A Quick Look at Methods for Mining Long Subsequences","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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 Regina","funders":"","keywords":"Substring; Computer science; Sequence (biology); String (physics); Task (project management); Heuristic; String searching algorithm; Sequential Pattern Mining; Algorithm; Artificial intelligence; Data mining; Pattern matching; Data structure; Mathematics","score_opus":0.038905348153038075,"score_gpt":0.329222853790603,"score_spread":0.2903175056375649,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1647183428","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025627355,0.03502972,0.95177466,0.00095098146,0.00089680153,0.00012314034,0.0010070062,0.004131474,0.003523457],"genre_scores_gemma":[0.011948586,0.020803256,0.9366188,0.0008928018,0.0008266068,0.00019618995,0.0035322616,0.00094124716,0.024240203],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99913174,0.00008826627,0.000086889784,0.00022079397,0.00044015737,0.000032066608],"domain_scores_gemma":[0.9981804,0.0010859034,0.00007419274,0.00022235133,0.00037263092,0.00006438482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011549972,0.0019293131,0.0018298903,0.003649453,0.0008015678,0.0023392988,0.0025777514,0.0018201199,0.011919722],"category_scores_gemma":[0.0052527934,0.0011045224,0.0015614086,0.006223979,0.0006404424,0.005274702,0.0012066696,0.0022481582,0.0103146555],"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":[0.00013209034,0.00009596488,0.0008880597,0.0012382364,0.00019226492,0.00023656545,0.0000978341,0.00302673,0.01054682,0.011365391,0.043543637,0.92863643],"study_design_scores_gemma":[0.00020894383,0.00071788504,0.0057832734,0.0012219807,0.00046386864,0.006397106,0.0005222812,0.14602754,0.040826734,0.24459034,0.5528094,0.00043061722],"about_ca_topic_score_codex":0.0009759584,"about_ca_topic_score_gemma":0.0025917583,"teacher_disagreement_score":0.011919722,"about_ca_system_score_codex":0.00033985244,"about_ca_system_score_gemma":0.0005309947,"threshold_uncertainty_score":0.03987539},"labels":[],"label_agreement":null},{"id":"W165413397","doi":"","title":"Frequent Itemset Mining of Distributed Uncertain Data under User-Defined Constraints.","year":2012,"lang":"en","type":"article","venue":"Mspace (University of Manitoba)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Data mining; Computer science; Uncertain data; Tree (set theory); Wireless sensor network; Data stream mining; Distributed Computing Environment; Distributed computing; Computer network; Mathematics","score_opus":0.059842746764378583,"score_gpt":0.2510000747351413,"score_spread":0.1911573279707627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W165413397","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18077785,0.0038083973,0.806837,0.0013194925,0.00020074096,0.00040933897,0.0046132924,0.00091253774,0.0011212718],"genre_scores_gemma":[0.7090691,0.00083338615,0.28300142,0.00019531976,0.00021410169,0.00030912462,0.005616964,0.000070391,0.0006902863],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9942134,0.0018702274,0.0009991549,0.0009972162,0.0014901818,0.00042987772],"domain_scores_gemma":[0.9654438,0.025397228,0.0025252947,0.0027782298,0.0031517083,0.0007036631],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063764276,0.000973222,0.0024317282,0.0028692887,0.0010793554,0.0023828072,0.00279891,0.001769668,0.00082709495],"category_scores_gemma":[0.033825066,0.00084965647,0.0012393284,0.0043163537,0.0007710121,0.004232353,0.0014034965,0.0013342231,0.00031994455],"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":[0.003591862,0.0009239161,0.057752267,0.0017097234,0.0013643212,0.006615483,0.0007925493,0.51916397,0.012910502,0.01428267,0.015837455,0.36505526],"study_design_scores_gemma":[0.00007418514,0.00012919118,0.0038485809,0.00007220869,0.00011213175,0.0008577829,0.0003959702,0.9749213,0.003820605,0.013934515,0.0018019829,0.00003159749],"about_ca_topic_score_codex":0.003868314,"about_ca_topic_score_gemma":0.0059561967,"teacher_disagreement_score":0.0063764276,"about_ca_system_score_codex":0.00083118165,"about_ca_system_score_gemma":0.0015570571,"threshold_uncertainty_score":0.033722162},"labels":[],"label_agreement":null},{"id":"W167229317","doi":"10.1007/978-0-387-79420-4_3","title":"On Mining Maximal Pattern-Based Clusters","year":2008,"lang":"en","type":"book-chapter","venue":"","topic":"Data Mining Algorithms and Applications","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":"Simon Fraser University","funders":"","keywords":"Cluster analysis; Maple; Computer science; Data mining; Scalability; Heuristics; Pattern recognition (psychology); Artificial intelligence; Database","score_opus":0.027738766550003725,"score_gpt":0.23234926722953617,"score_spread":0.20461050067953243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W167229317","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008666955,0.00430685,0.9741255,0.0006919368,0.000284148,0.00021250368,0.0013952138,0.0014749765,0.0088418955],"genre_scores_gemma":[0.047447942,0.0038581474,0.9344071,0.00038267448,0.00033509597,0.0002994848,0.0043339357,0.0003421222,0.008593466],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988109,0.00015372319,0.00009621788,0.00032905274,0.00053969806,0.00007044547],"domain_scores_gemma":[0.997638,0.0013916589,0.000103043574,0.0005080401,0.00030438817,0.000054949232],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001047623,0.0012998985,0.001732925,0.003127987,0.0011742902,0.0020497865,0.0027710565,0.0010669775,0.004975445],"category_scores_gemma":[0.006519293,0.00076790754,0.0012639463,0.0075330855,0.0013329192,0.004789341,0.0025668887,0.0019053702,0.0030146744],"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":[0.00017473337,0.0001126003,0.0024272564,0.0011363337,0.00021503006,0.0002462531,0.00046296007,0.02738883,0.0044415668,0.09222635,0.043782547,0.82738554],"study_design_scores_gemma":[0.00005158815,0.00010590533,0.0019911553,0.00030184517,0.00015189406,0.001150757,0.00031355204,0.20307547,0.007123478,0.7292032,0.05646723,0.000063871004],"about_ca_topic_score_codex":0.0014566947,"about_ca_topic_score_gemma":0.002137787,"teacher_disagreement_score":0.004975445,"about_ca_system_score_codex":0.0006076344,"about_ca_system_score_gemma":0.0008433552,"threshold_uncertainty_score":0.016644478},"labels":[],"label_agreement":null},{"id":"W169165923","doi":"10.1007/978-3-642-54426-2_6","title":"Mining Multiple Related Data Sources Using Object-Oriented Model","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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":"University of Windsor","funders":"","keywords":"Computer science; Class hierarchy; Joins; Data mining; Database; Object (grammar); Inheritance (genetic algorithm); Theoretical computer science; Object-oriented programming; Artificial intelligence; Programming language","score_opus":0.0452442112778649,"score_gpt":0.27486780110831577,"score_spread":0.22962358983045086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W169165923","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04199513,0.0019700206,0.94687605,0.0006811846,0.0001656117,0.0006125614,0.0019443246,0.0035943605,0.002160712],"genre_scores_gemma":[0.13896821,0.0014433557,0.8502812,0.0003168283,0.000107720385,0.00035961042,0.006191548,0.00025725062,0.0020743043],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99662507,0.00037898045,0.00044115377,0.0006487843,0.0017540188,0.0001519312],"domain_scores_gemma":[0.99638355,0.0016606731,0.00046002772,0.00054174097,0.00081229233,0.00014164759],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028390249,0.0017150008,0.0018281197,0.010280574,0.0013246628,0.0044348324,0.003175794,0.0014343965,0.0011860004],"category_scores_gemma":[0.0066978238,0.00096835184,0.0034315474,0.012763279,0.00058371614,0.0047900407,0.0023739494,0.0012990594,0.00084179046],"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":[0.0006781153,0.0010674419,0.041056108,0.0014890685,0.0014754726,0.00368285,0.0009956363,0.034281302,0.014258649,0.025710708,0.013570413,0.86173415],"study_design_scores_gemma":[0.00018908372,0.00030036716,0.009753327,0.0004706226,0.0017973927,0.0025169984,0.0009827152,0.8249326,0.020404158,0.10583638,0.03266045,0.00015589272],"about_ca_topic_score_codex":0.004063056,"about_ca_topic_score_gemma":0.005796151,"teacher_disagreement_score":0.010280574,"about_ca_system_score_codex":0.0008945069,"about_ca_system_score_gemma":0.0019626066,"threshold_uncertainty_score":0.01501441},"labels":[],"label_agreement":null},{"id":"W1696171692","doi":"10.1007/s10601-015-9214-x","title":"On Algorithm Selection, with an application to combinatorial search problems","year":2015,"lang":"en","type":"article","venue":"Constraints","topic":"Data Mining Algorithms and Applications","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 British Columbia","funders":"","keywords":"Computer science; Machine learning; Selection (genetic algorithm); Artificial intelligence; De facto; Robustness (evolution); Field (mathematics); Constraint (computer-aided design); Algorithm; Mathematics","score_opus":0.02590515421391894,"score_gpt":0.28041833025471025,"score_spread":0.2545131760407913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1696171692","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030941106,0.0024162864,0.98474926,0.0011871915,0.00034090635,0.00016621484,0.00010794085,0.00017591786,0.0077622007],"genre_scores_gemma":[0.08566689,0.0052674804,0.8947274,0.000832376,0.0018149427,0.00093379716,0.00038042464,0.00044196637,0.009934723],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9921745,0.004970928,0.0002956125,0.0005884238,0.0016686992,0.0003019986],"domain_scores_gemma":[0.9459118,0.049172558,0.00094367214,0.0012626778,0.0020812775,0.000627995],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008430235,0.0031780517,0.003861267,0.006391045,0.0020833039,0.0042911917,0.0038167178,0.004328065,0.009839129],"category_scores_gemma":[0.051659934,0.0012792789,0.0022735244,0.017426694,0.0038087636,0.0059569334,0.0048243823,0.0059137708,0.001432907],"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":[0.00027478518,0.0003771399,0.0016735608,0.0009006603,0.00022730969,0.0005761398,0.0003328632,0.31254888,0.00092121336,0.38875726,0.027579302,0.26583087],"study_design_scores_gemma":[0.00012581775,0.00010708208,0.0003516619,0.000116953364,0.00006049653,0.0002381182,0.00007743309,0.713942,0.0003732944,0.27633974,0.008219623,0.00004782485],"about_ca_topic_score_codex":0.004523471,"about_ca_topic_score_gemma":0.0055703633,"teacher_disagreement_score":0.009839129,"about_ca_system_score_codex":0.0017376869,"about_ca_system_score_gemma":0.0023385787,"threshold_uncertainty_score":0.044583857},"labels":[],"label_agreement":null},{"id":"W170258093","doi":"","title":"A Unified Framework for Utility Based Measures for Mining Itemsets","year":2006,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":103,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Data mining; Computer science; Process (computing); Function (biology)","score_opus":0.053713182871785795,"score_gpt":0.3005510801555023,"score_spread":0.24683789728371652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W170258093","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000611325,0.0007217227,0.99723595,0.0002441836,0.00005685146,0.00010739626,0.00013957324,0.00012173051,0.00076136773],"genre_scores_gemma":[0.03799504,0.0018532377,0.9562419,0.00029560775,0.00043797394,0.0010674787,0.0006674488,0.000108722605,0.0013325997],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97976637,0.009034262,0.002739043,0.0022253762,0.0057263062,0.0005086381],"domain_scores_gemma":[0.9751012,0.01512012,0.0017015164,0.003485051,0.0040597566,0.0005324051],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021142514,0.0028364235,0.003668793,0.010290491,0.0014793525,0.008254201,0.005925688,0.0026650361,0.0028141502],"category_scores_gemma":[0.048953924,0.0012372843,0.0046189437,0.013742677,0.0031781797,0.011292082,0.0045345556,0.005422066,0.0018220372],"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":[0.000075315926,0.00018288537,0.001481741,0.0005445519,0.00030768808,0.00021864206,0.00042164224,0.043589998,0.0011188812,0.80741745,0.0057418477,0.13889939],"study_design_scores_gemma":[0.00004104071,0.00021614593,0.0007460488,0.00031562502,0.00014507698,0.0004993311,0.0001638758,0.3137647,0.001479177,0.65221244,0.030304829,0.00011169678],"about_ca_topic_score_codex":0.0018682701,"about_ca_topic_score_gemma":0.0015742998,"teacher_disagreement_score":0.021142514,"about_ca_system_score_codex":0.0028533032,"about_ca_system_score_gemma":0.0025562842,"threshold_uncertainty_score":0.111813605},"labels":[],"label_agreement":null},{"id":"W1728822304","doi":"10.1007/s00500-015-1876-1","title":"An agent-based algorithm exploiting multiple local dissimilarities for clusters mining and knowledge discovery","year":2015,"lang":"en","type":"article","venue":"Soft Computing","topic":"Data Mining Algorithms and Applications","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":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Knowledge extraction; Data mining; Artificial intelligence; Algorithm","score_opus":0.04851429484853851,"score_gpt":0.30124835046170645,"score_spread":0.2527340556131679,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1728822304","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021399751,0.00021915736,0.9751296,0.00031177042,0.00010162782,0.00022473527,0.00009583759,0.00088845874,0.0016290741],"genre_scores_gemma":[0.18973622,0.00012103488,0.80582815,0.00022853521,0.00007158179,0.00034917553,0.00037021755,0.00010847945,0.003186619],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985703,0.00037021292,0.00012462655,0.00034814124,0.00045044874,0.00013617708],"domain_scores_gemma":[0.9977894,0.0010630495,0.00016650379,0.0002661733,0.0005576867,0.00015715552],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002351485,0.0010025878,0.0021424692,0.0029216476,0.0019959935,0.0021022593,0.0037022932,0.0021425427,0.0028512366],"category_scores_gemma":[0.0053588287,0.0007199048,0.0012935996,0.0027989554,0.0010156734,0.0017594487,0.002566371,0.0014921423,0.00089194305],"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":[0.0007328369,0.00078056037,0.0065614604,0.00022702217,0.0006526545,0.0003412288,0.00028588972,0.34626162,0.0075456826,0.023725221,0.008217437,0.60466844],"study_design_scores_gemma":[0.00005249731,0.000043671767,0.00026069264,0.000007929591,0.000039094593,0.00006628243,0.000031172374,0.99216616,0.001112024,0.005171266,0.0010382837,0.000010903293],"about_ca_topic_score_codex":0.007868059,"about_ca_topic_score_gemma":0.0117377015,"teacher_disagreement_score":0.007868059,"about_ca_system_score_codex":0.0011794807,"about_ca_system_score_gemma":0.0028581684,"threshold_uncertainty_score":0.01564449},"labels":[],"label_agreement":null},{"id":"W1737158080","doi":"10.1007/s10707-016-0254-1","title":"On discovering co-location patterns in datasets: a case study of pollutants and child cancers","year":2016,"lang":"en","type":"article","venue":"GeoInformatica","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":67,"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":"Canadian Institutes of Health Research","keywords":"Association rule learning; Data mining; Computer science; Context (archaeology); Apriori algorithm; Database transaction; A priori and a posteriori; Domain (mathematical analysis); Geography; Database; Mathematics","score_opus":0.01219935380159732,"score_gpt":0.26967945318023745,"score_spread":0.25748009937864014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1737158080","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9506882,0.003627762,0.014303688,0.003564895,0.00008808994,0.00015418259,0.024024915,0.00023318472,0.0033151985],"genre_scores_gemma":[0.9237129,0.002043276,0.048087683,0.0004144767,0.00008060839,0.000083433384,0.024181353,0.000056344932,0.001340031],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969349,0.0012634246,0.00029767174,0.00056092395,0.0006987942,0.00024428617],"domain_scores_gemma":[0.9822044,0.013697312,0.0013015586,0.0013483077,0.001155762,0.00029265537],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036309855,0.00053994183,0.00056511,0.0039291633,0.0011598616,0.0019207681,0.0013667092,0.0019055714,0.0010614945],"category_scores_gemma":[0.016246438,0.0002518381,0.0014643938,0.008669705,0.00069965015,0.0016236177,0.001348054,0.0008188402,0.0003831513],"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":[0.0005477078,0.00051957805,0.8662353,0.0010399874,0.0008710975,0.0043142303,0.0018492297,0.020844454,0.0023372173,0.0033664869,0.0155440485,0.08253067],"study_design_scores_gemma":[0.00018412183,0.0005473641,0.6757019,0.00062286895,0.0014399878,0.0112371715,0.021504525,0.19376795,0.008803376,0.017289558,0.06871705,0.00018411745],"about_ca_topic_score_codex":0.038607683,"about_ca_topic_score_gemma":0.069793686,"teacher_disagreement_score":0.038607683,"about_ca_system_score_codex":0.0011547089,"about_ca_system_score_gemma":0.0013986742,"threshold_uncertainty_score":0.076765954},"labels":[],"label_agreement":null},{"id":"W1761817100","doi":"10.1007/978-3-540-68825-9_16","title":"Using Dependence Diagrams to Summarize Decision Rule Sets","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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 Regina; Lakehead University","funders":"","keywords":"Computer science; Set (abstract data type); Decision rule; Influence diagram; Data mining; Artificial intelligence; Machine learning; Rule-based system; Theoretical computer science; Decision tree; Programming language","score_opus":0.03946380529943017,"score_gpt":0.29260935656202497,"score_spread":0.2531455512625948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1761817100","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016564531,0.0010822456,0.9734673,0.00021421557,0.000112475755,0.00021908233,0.0028963499,0.0037448055,0.0016989447],"genre_scores_gemma":[0.21877263,0.0012099248,0.7660546,0.00015944308,0.00015897679,0.0004586848,0.010318412,0.00043368142,0.0024335885],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980312,0.00047429668,0.0003150609,0.00035114342,0.0007395149,0.000088793124],"domain_scores_gemma":[0.98234934,0.01303401,0.00079036376,0.0015578043,0.0020118097,0.00025670638],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002745001,0.0009957863,0.0012500111,0.0074530235,0.00078299246,0.0028631168,0.0012305311,0.0008439018,0.0041922247],"category_scores_gemma":[0.024151923,0.0008577687,0.0013593885,0.0041758046,0.0005086147,0.004995148,0.0011154052,0.0016612121,0.0011507816],"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":[0.00043517599,0.00027786993,0.007105171,0.0007751683,0.000360744,0.0003227965,0.00056629616,0.09855598,0.0043929704,0.058237318,0.015506466,0.81346387],"study_design_scores_gemma":[0.000059464837,0.00011957981,0.0016334867,0.00021411556,0.00030649645,0.00024205665,0.00011931439,0.7467445,0.005875345,0.22677518,0.017844616,0.00006588073],"about_ca_topic_score_codex":0.0043192157,"about_ca_topic_score_gemma":0.006260871,"teacher_disagreement_score":0.0074530235,"about_ca_system_score_codex":0.0010641898,"about_ca_system_score_gemma":0.0013555199,"threshold_uncertainty_score":0.0145171285},"labels":[],"label_agreement":null},{"id":"W177645602","doi":"10.1007/978-3-642-30217-6_29","title":"An Associative Classifier for Uncertain Datasets","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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":"","keywords":"Computer science; Associative property; Classifier (UML); Artificial intelligence; Machine learning; Artificial neural network; Uncertain data; Pruning; Decision tree; Pattern recognition (psychology); Data mining; Mathematics","score_opus":0.03891664597527363,"score_gpt":0.30842342463057865,"score_spread":0.26950677865530503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W177645602","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035209905,0.001867903,0.9526779,0.00064685836,0.00058602856,0.0002161223,0.00088110386,0.0027495348,0.005164696],"genre_scores_gemma":[0.31988242,0.0018261556,0.6569884,0.0005056568,0.0010202209,0.00054779655,0.004024466,0.00020160864,0.0150033645],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981273,0.0002363954,0.00022347573,0.00030300755,0.0010133064,0.00009654971],"domain_scores_gemma":[0.9956377,0.002132533,0.00017798568,0.00083901436,0.0010936342,0.00011913017],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028497793,0.00067630195,0.001489175,0.002289112,0.0011429089,0.0020661012,0.0019260407,0.0014445467,0.004150396],"category_scores_gemma":[0.009326048,0.00039824157,0.00081371353,0.002462043,0.0006161835,0.00484386,0.0020397312,0.0018859216,0.0026551282],"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":[0.0003775505,0.00025092473,0.0031928471,0.0002847928,0.00012574164,0.0003400421,0.00014070865,0.021288343,0.005818082,0.022665493,0.021273071,0.9242424],"study_design_scores_gemma":[0.000039260958,0.00013842531,0.0011691405,0.00009373331,0.00012686859,0.0008123032,0.000114393995,0.8952494,0.009486816,0.07702118,0.015708068,0.00004040164],"about_ca_topic_score_codex":0.0010227141,"about_ca_topic_score_gemma":0.0020056074,"teacher_disagreement_score":0.004150396,"about_ca_system_score_codex":0.0004993234,"about_ca_system_score_gemma":0.0013109928,"threshold_uncertainty_score":0.015071213},"labels":[],"label_agreement":null},{"id":"W1776761859","doi":"","title":"Aldrick, J. O., & Rodriguez, H. M. (2013). Building SPSS Graphs to Understand Data","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Mathematics","score_opus":0.17716966082276855,"score_gpt":0.3747928407452575,"score_spread":0.19762317992248893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1776761859","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029821035,0.006272926,0.89860153,0.01813833,0.0011543304,0.0010737039,0.010232938,0.009591249,0.025113925],"genre_scores_gemma":[0.0920774,0.0053452174,0.8872561,0.0013760369,0.00028894606,0.00071727706,0.004282008,0.0016769789,0.006980143],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99608624,0.0016123381,0.00042022744,0.00037016603,0.0014227673,0.000088204404],"domain_scores_gemma":[0.83774835,0.13615213,0.0051652323,0.006454943,0.013453463,0.0010258786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01373376,0.00093805214,0.00060520583,0.0075917267,0.0015991194,0.004672045,0.0012674067,0.00075346266,0.011227095],"category_scores_gemma":[0.13772383,0.0009809827,0.0010926547,0.0053244773,0.001982964,0.0053108297,0.0015162887,0.0037008775,0.0037938573],"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":[0.00040015197,0.00017895151,0.028647635,0.002122909,0.00032235673,0.00029435457,0.0068491567,0.0043155192,0.0048797163,0.056459364,0.16855507,0.72697484],"study_design_scores_gemma":[0.00025414443,0.0004478267,0.057548434,0.0026890214,0.001248708,0.0009845557,0.0074616186,0.03327293,0.012170333,0.36286736,0.5206197,0.00043536726],"about_ca_topic_score_codex":0.010637416,"about_ca_topic_score_gemma":0.023753526,"teacher_disagreement_score":0.01373376,"about_ca_system_score_codex":0.0010911818,"about_ca_system_score_gemma":0.0033978783,"threshold_uncertainty_score":0.072631955},"labels":[],"label_agreement":null},{"id":"W1785175716","doi":"10.1109/dexa.2006.78","title":"Invited Paper: Intelligent Data Mining Assistance via CBR and Ontologies","year":2006,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Computer science; Ontology; Realization (probability); Process (computing); Data mining; Process mining; Data stream mining; Data modeling; Data science; Database; Work in process; Engineering; Business process","score_opus":0.04137781113354955,"score_gpt":0.27407804264907526,"score_spread":0.2327002315155257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1785175716","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019294852,0.017135452,0.68209714,0.15132216,0.043494508,0.0007181883,0.0006647498,0.0028633852,0.08240956],"genre_scores_gemma":[0.21633844,0.022660369,0.3792759,0.045818202,0.06755533,0.00046793392,0.002385009,0.0012402397,0.26425847],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99821955,0.00070611987,0.00009627176,0.00032873283,0.0004928707,0.00015639569],"domain_scores_gemma":[0.9958995,0.0019588459,0.00008118733,0.0002138528,0.0014995949,0.0003470525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039655175,0.00055418804,0.0005194333,0.0009722683,0.0008444195,0.004043395,0.001177791,0.0028527349,0.015414439],"category_scores_gemma":[0.008257727,0.00024383748,0.0005532923,0.0014481216,0.0007621864,0.0044448483,0.0011100612,0.0014571998,0.006005961],"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":[0.0003698065,0.0002510549,0.0013401695,0.00073034404,0.000087104534,0.0009410193,0.0010260853,0.0038408767,0.00832963,0.054631982,0.5512188,0.37723315],"study_design_scores_gemma":[0.00022363589,0.00017457904,0.00088052585,0.00019894038,0.00014714396,0.0015760934,0.0009266771,0.028876295,0.009320749,0.053030323,0.90455025,0.0000948181],"about_ca_topic_score_codex":0.0012532591,"about_ca_topic_score_gemma":0.0011483933,"teacher_disagreement_score":0.015414439,"about_ca_system_score_codex":0.00061352155,"about_ca_system_score_gemma":0.0009053214,"threshold_uncertainty_score":0.05156648},"labels":[],"label_agreement":null},{"id":"W178558608","doi":"","title":"Real-time alert correlation using stream data mining techniques","year":2008,"lang":"en","type":"article","venue":"Innovative Applications of Artificial Intelligence","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Data mining; Intrusion detection system; Volume (thermodynamics); Correlation; Data stream mining; Scale (ratio)","score_opus":0.11685613468064328,"score_gpt":0.35740011008580913,"score_spread":0.24054397540516587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W178558608","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038040083,0.00041390455,0.9576837,0.00030695478,0.000073534095,0.00016836874,0.00032181287,0.0022821878,0.00070950616],"genre_scores_gemma":[0.43867406,0.000530057,0.5586825,0.000111681344,0.00016493679,0.0002058635,0.0009883818,0.000073010604,0.0005694828],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975521,0.00048807153,0.00027611092,0.00041901408,0.0011604246,0.000104302744],"domain_scores_gemma":[0.9931867,0.0028082805,0.0013310353,0.00082111394,0.0016313969,0.00022152736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026456334,0.0009623079,0.0012475004,0.004909117,0.00054453546,0.001986664,0.0014418666,0.00066935975,0.00056252116],"category_scores_gemma":[0.009413581,0.00041939737,0.0007013799,0.004409368,0.00033946987,0.002252981,0.0009963518,0.0009850655,0.0003188918],"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":[0.00044784174,0.0004819895,0.028434863,0.00028988248,0.00032816693,0.00069078425,0.00045970667,0.117671825,0.018194646,0.012344787,0.005795627,0.8148598],"study_design_scores_gemma":[0.00003114685,0.00011972338,0.002334004,0.000022785913,0.000058551195,0.0003007074,0.000088280685,0.97438836,0.0105773285,0.00837028,0.0036774746,0.000031390213],"about_ca_topic_score_codex":0.001578341,"about_ca_topic_score_gemma":0.001522974,"teacher_disagreement_score":0.004909117,"about_ca_system_score_codex":0.00056035013,"about_ca_system_score_gemma":0.0011933908,"threshold_uncertainty_score":0.013991594},"labels":[],"label_agreement":null},{"id":"W1794915560","doi":"10.1007/978-3-540-68125-0_61","title":"A Tree-Based Approach for Frequent Pattern Mining from Uncertain Data","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":224,"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; Database transaction; Data mining; Tree (set theory); Transaction data; Database; Mathematics","score_opus":0.06928100922740438,"score_gpt":0.28006681655450605,"score_spread":0.21078580732710167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1794915560","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022308398,0.0005532297,0.995732,0.00013031479,0.00006299346,0.000088666,0.00031438452,0.00050320936,0.00038433113],"genre_scores_gemma":[0.027264662,0.0007710917,0.96948797,0.00012607273,0.00011073207,0.00017904678,0.0010805258,0.000074446645,0.00090556033],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973277,0.00055955705,0.00033788435,0.000386112,0.0012852363,0.000103571525],"domain_scores_gemma":[0.9941757,0.0037315872,0.00021196317,0.00048033576,0.0012568209,0.00014360157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002232265,0.0008951187,0.001780954,0.0029776052,0.0009786004,0.0019155664,0.0023503576,0.0016794197,0.0029980268],"category_scores_gemma":[0.0112794135,0.000628568,0.0019172473,0.0063377954,0.00048915093,0.0034097605,0.0014300654,0.001766289,0.0019391543],"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":[0.00032647702,0.00027748322,0.001485008,0.0007249972,0.000359861,0.0006608374,0.00034494116,0.059506,0.009388476,0.02726307,0.014881518,0.8847813],"study_design_scores_gemma":[0.00006684085,0.00019124463,0.000636648,0.00011761054,0.00019376412,0.0010826349,0.00011746316,0.9045362,0.0036982545,0.07488728,0.014406244,0.00006585241],"about_ca_topic_score_codex":0.002819096,"about_ca_topic_score_gemma":0.0038361938,"teacher_disagreement_score":0.0029980268,"about_ca_system_score_codex":0.00043116004,"about_ca_system_score_gemma":0.0012635931,"threshold_uncertainty_score":0.011805534},"labels":[],"label_agreement":null},{"id":"W17956733","doi":"10.1007/978-3-642-30353-1_27","title":"Mining Sequential Rules Common to Several Sequences with the Window Size Constraint","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms 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":"Université du Québec à Montréal; Université de Moncton","funders":"","keywords":"Computer science; Constraint (computer-aided design); Window (computing); Data mining; Span (engineering); Sequential Pattern Mining; Algorithm; Sliding window protocol; Artificial intelligence; Mathematics","score_opus":0.020664498789227274,"score_gpt":0.2548446231237625,"score_spread":0.23418012433453522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W17956733","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29834357,0.00252018,0.6906331,0.00039901055,0.0001902962,0.0006027535,0.0036047322,0.001269718,0.0024366162],"genre_scores_gemma":[0.55394804,0.0012487499,0.43148512,0.00021347708,0.00033597025,0.00051642366,0.0096688075,0.00019867382,0.0023847804],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953275,0.00042151863,0.0008679259,0.0017021629,0.0013816393,0.00029928912],"domain_scores_gemma":[0.982028,0.011908778,0.002275517,0.0016884111,0.0015762257,0.00052309973],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002931581,0.0011531695,0.0023915388,0.0046455706,0.0008508806,0.0023255409,0.0022317297,0.0013040625,0.001790328],"category_scores_gemma":[0.018071087,0.0010019463,0.002551751,0.0045558345,0.00085837493,0.003928182,0.0013120663,0.0014458349,0.0006402462],"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":[0.0037504965,0.0012443105,0.08915705,0.0024464743,0.0020250732,0.0061931256,0.00070278195,0.10356129,0.058183737,0.022482237,0.007643217,0.70261025],"study_design_scores_gemma":[0.00025951525,0.0012246597,0.018995607,0.00043688848,0.0012427459,0.0050983033,0.00052276195,0.8644197,0.032495663,0.06383339,0.011353244,0.000117527066],"about_ca_topic_score_codex":0.0021535226,"about_ca_topic_score_gemma":0.0036303145,"teacher_disagreement_score":0.0046455706,"about_ca_system_score_codex":0.0004006036,"about_ca_system_score_gemma":0.0025635057,"threshold_uncertainty_score":0.015503883},"labels":[],"label_agreement":null},{"id":"W18036528","doi":"10.1007/978-3-642-23544-3_19","title":"Frequent Pattern Mining from Time-Fading Streams of Uncertain Data","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":53,"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":"Data stream mining; Computer science; STREAMS; Fading; Sliding window protocol; Data mining; Data stream; Real-time computing; Window (computing); Computer network; Telecommunications; Channel (broadcasting); World Wide Web","score_opus":0.050093446914141505,"score_gpt":0.2686092116487376,"score_spread":0.21851576473459608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W18036528","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11209912,0.0033588083,0.8810353,0.0004759872,0.00013934105,0.00011239987,0.0014161348,0.0005983444,0.00076464494],"genre_scores_gemma":[0.64047176,0.0034284054,0.3497498,0.000092011614,0.00037247298,0.00015013617,0.0041876207,0.00007541808,0.0014723487],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985948,0.00018854023,0.00019299035,0.00033076687,0.00058463024,0.00010822805],"domain_scores_gemma":[0.9941841,0.0042503793,0.0005406101,0.00046186976,0.00045884005,0.00010421999],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001413225,0.0007158731,0.0012458024,0.0019856167,0.00046392396,0.001372104,0.0015728837,0.00096086774,0.00065798877],"category_scores_gemma":[0.010197198,0.00041817655,0.0010809788,0.0034291137,0.0003982949,0.0025559233,0.0009240672,0.0012161256,0.0003477681],"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":[0.00096569303,0.00023320234,0.020110374,0.0010192036,0.00044978756,0.0031636506,0.00061122444,0.21004127,0.014081036,0.012309768,0.0043618553,0.7326529],"study_design_scores_gemma":[0.00002628066,0.00015565337,0.003921759,0.000080289545,0.0001203435,0.0016705103,0.0002126454,0.9527813,0.0059665986,0.031994592,0.0030350257,0.000035019617],"about_ca_topic_score_codex":0.0008645226,"about_ca_topic_score_gemma":0.0009688354,"teacher_disagreement_score":0.0019856167,"about_ca_system_score_codex":0.00034416004,"about_ca_system_score_gemma":0.00038190835,"threshold_uncertainty_score":0.0074739456},"labels":[],"label_agreement":null},{"id":"W1805869427","doi":"10.1007/978-3-540-44918-8_1","title":"Choosing the Right Lens: Finding What is Interesting in Data Mining","year":2007,"lang":"en","type":"book-chapter","venue":"Studies in computational intelligence","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":58,"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":"Lens (geology); Computer science; Data mining; Data science; Optics; Physics","score_opus":0.3746193807719971,"score_gpt":0.43494759794618215,"score_spread":0.06032821717418507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1805869427","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018665714,0.2196061,0.37326446,0.245932,0.0052310056,0.0003529552,0.00131064,0.0012017431,0.13443545],"genre_scores_gemma":[0.28880724,0.11622556,0.5206555,0.022593586,0.00804075,0.0005329511,0.0012196108,0.0010150255,0.040909775],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99523336,0.0021484555,0.00028188628,0.00056805566,0.0015970694,0.00017121827],"domain_scores_gemma":[0.9843917,0.012096386,0.0006551014,0.00064564345,0.0013438782,0.0008672718],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0057104323,0.0014040271,0.0017967895,0.006609586,0.003212037,0.015192031,0.00224823,0.0020703264,0.006992619],"category_scores_gemma":[0.026615769,0.0007399223,0.00094389124,0.00958089,0.010515468,0.025152065,0.004320335,0.0059535885,0.0020650034],"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":[0.00011042219,0.0001174256,0.0039797584,0.002473066,0.00013834653,0.00038215972,0.008117524,0.000473051,0.0013093915,0.41875196,0.13640681,0.42774016],"study_design_scores_gemma":[0.000019441391,0.000027278214,0.0009355263,0.0009886745,0.000054832908,0.00042414627,0.0059155393,0.0016825555,0.0008108858,0.85680366,0.13229263,0.00004485518],"about_ca_topic_score_codex":0.0019861741,"about_ca_topic_score_gemma":0.0043283836,"teacher_disagreement_score":0.015192031,"about_ca_system_score_codex":0.002572874,"about_ca_system_score_gemma":0.00322848,"threshold_uncertainty_score":0.030200064},"labels":[],"label_agreement":null},{"id":"W181032925","doi":"10.1007/978-3-319-06245-7_5","title":"Big Data Analysis","year":2014,"lang":"en","type":"book-chapter","venue":"SpringerBriefs in computer science","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 British Columbia","funders":"","keywords":"Big data; Computer science; Data science; Data mining; Software; Data analysis","score_opus":0.06409776620028236,"score_gpt":0.27650888267551427,"score_spread":0.21241111647523192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W181032925","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026560305,0.01851081,0.74110746,0.013751532,0.005997705,0.0005131467,0.009985595,0.019030865,0.18844682],"genre_scores_gemma":[0.04377089,0.025933977,0.5127539,0.007833019,0.007036884,0.0009627732,0.02761757,0.0073278267,0.36676314],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984428,0.00023175996,0.00009382667,0.00028832984,0.0008712156,0.000072007904],"domain_scores_gemma":[0.9967648,0.0011944777,0.0001138419,0.001196789,0.00058125437,0.00014885952],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024243041,0.0014568744,0.00122667,0.0036845396,0.0008637498,0.0039400826,0.0018786651,0.001168109,0.055714153],"category_scores_gemma":[0.005614438,0.0009598059,0.0012056102,0.0036402906,0.0009621457,0.004684436,0.00329799,0.0024291535,0.04730607],"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":[0.000051095776,0.00004095157,0.0005548301,0.00050878787,0.00008143471,0.00007257584,0.00012036819,0.0016781643,0.002210568,0.07326605,0.41175035,0.5096648],"study_design_scores_gemma":[0.000011796572,0.000019357238,0.00067550456,0.00018834275,0.00003185956,0.00025600326,0.00007322609,0.011116039,0.0036792238,0.21845214,0.76546603,0.00003055296],"about_ca_topic_score_codex":0.0005450319,"about_ca_topic_score_gemma":0.00084178406,"teacher_disagreement_score":0.055714153,"about_ca_system_score_codex":0.0007216422,"about_ca_system_score_gemma":0.0013386512,"threshold_uncertainty_score":0.18638241},"labels":[],"label_agreement":null},{"id":"W1813387235","doi":"10.1007/3-540-39963-1_13","title":"Rule Quality Measures Improve the Accuracy of Rule Induction: An Experimental Approach","year":2000,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":24,"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":"Rule induction; Computer science; Rule-based system; Quality (philosophy); Selection (genetic algorithm); Set (abstract data type); Data mining; Decision rule; Artificial intelligence; Machine learning","score_opus":0.04862834088733833,"score_gpt":0.3079711532364283,"score_spread":0.25934281234909,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1813387235","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8555215,0.00375989,0.12676282,0.0008503224,0.0006871105,0.0008551114,0.0030292592,0.0025582884,0.005975721],"genre_scores_gemma":[0.85193837,0.0005296703,0.13946125,0.00021921615,0.00021556288,0.00036361342,0.0040172143,0.0007410038,0.0025139644],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98365223,0.0065081813,0.0021690927,0.002218567,0.004945672,0.0005062791],"domain_scores_gemma":[0.7244005,0.2249413,0.0073970095,0.021120293,0.02071337,0.0014275531],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022229256,0.0016213568,0.0021863023,0.0030070867,0.0009957915,0.0029267846,0.0025146238,0.0023141736,0.0040170853],"category_scores_gemma":[0.10519464,0.00063137495,0.0014171455,0.0031444305,0.0013356451,0.0035968309,0.0016924903,0.0023419913,0.001261598],"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":[0.025414143,0.011928804,0.050092023,0.003171619,0.0025640333,0.00051118823,0.0014672652,0.07898052,0.06723789,0.004929427,0.011354194,0.74234885],"study_design_scores_gemma":[0.0027535362,0.015538344,0.03790887,0.00024080032,0.0030938426,0.0009878793,0.00088436884,0.75148356,0.16434702,0.016936164,0.0054907287,0.0003348673],"about_ca_topic_score_codex":0.0021848693,"about_ca_topic_score_gemma":0.002381435,"teacher_disagreement_score":0.022229256,"about_ca_system_score_codex":0.0012250072,"about_ca_system_score_gemma":0.0009809405,"threshold_uncertainty_score":0.11756092},"labels":[],"label_agreement":null},{"id":"W1841391047","doi":"10.1007/978-3-540-74553-2_20","title":"Selection and Pruning Algorithms for Bitmap Index Selection Problem Using Data Mining","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":22,"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 en Outaouais","funders":"","keywords":"Bitmap; Computer science; Data mining; Joins; Pruning; Join (topology); Data warehouse; Key (lock); Tuple; Dimension (graph theory); Search engine indexing; Selection (genetic algorithm); Information retrieval; Mathematics; Artificial intelligence","score_opus":0.07942153423394675,"score_gpt":0.3231942760796316,"score_spread":0.24377274184568481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1841391047","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031167703,0.0017915294,0.9624801,0.00045086915,0.00015830914,0.00020137626,0.00031179443,0.0014257377,0.0020127008],"genre_scores_gemma":[0.1090566,0.00088978023,0.88532007,0.00015430641,0.00015489734,0.0002180789,0.0008848106,0.0001573141,0.0031641107],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99860483,0.00031911186,0.0001315561,0.00017673727,0.00063731417,0.00013039571],"domain_scores_gemma":[0.996381,0.001826005,0.00022326375,0.0005532591,0.0008655901,0.00015094237],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002080048,0.00093158404,0.0019912443,0.0033399328,0.0010399579,0.00161468,0.0025204255,0.0013803921,0.0025473516],"category_scores_gemma":[0.0063221543,0.0005212404,0.0008976399,0.0051969406,0.00050374906,0.0024246236,0.0011893276,0.0016701189,0.00075232406],"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":[0.00039502225,0.00037988267,0.0025583105,0.000300751,0.00009680612,0.00017496556,0.00015579027,0.05697712,0.008185099,0.012160692,0.014948266,0.9036673],"study_design_scores_gemma":[0.00006755038,0.00011550894,0.0008594262,0.00004351156,0.00007303367,0.00028945078,0.00006310401,0.96744776,0.006348063,0.02093875,0.0037300189,0.000023853832],"about_ca_topic_score_codex":0.002283494,"about_ca_topic_score_gemma":0.0034729803,"teacher_disagreement_score":0.0033399328,"about_ca_system_score_codex":0.0006458844,"about_ca_system_score_gemma":0.0012879751,"threshold_uncertainty_score":0.011000514},"labels":[],"label_agreement":null},{"id":"W185053887","doi":"","title":"Proceedings of the 2006 international workshop on Mining software repositories","year":2006,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Blackberry (Canada)","funders":"","keywords":"Computer science; Software; Software engineering; Data science; Operating system","score_opus":0.010229537720551775,"score_gpt":0.23295906026636856,"score_spread":0.2227295225458168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W185053887","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10802867,0.022003746,0.795103,0.02672814,0.011377338,0.0011622527,0.0051453775,0.0075496454,0.022901813],"genre_scores_gemma":[0.17672293,0.013711813,0.69625485,0.003843905,0.003468682,0.000568418,0.031792518,0.0022385952,0.07139829],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99495924,0.0019243332,0.0005446072,0.0007815107,0.0015064315,0.00028385536],"domain_scores_gemma":[0.9863643,0.005030548,0.00046298013,0.0033554789,0.0034045973,0.0013820953],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011561648,0.0015525623,0.0029889527,0.0030945616,0.0014087437,0.009639255,0.0027144847,0.0019373917,0.008921472],"category_scores_gemma":[0.01773056,0.0011386495,0.0015531738,0.00246784,0.0011516617,0.008432284,0.0036454587,0.0036009247,0.0040182606],"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":[0.00089304545,0.001692242,0.010200276,0.0008324242,0.0005981802,0.00049460947,0.001544107,0.00430229,0.013057261,0.01179699,0.23728777,0.7173008],"study_design_scores_gemma":[0.0005224969,0.0012145642,0.02279765,0.0011814658,0.0014996807,0.0031450023,0.0026204805,0.15607107,0.055165786,0.088932216,0.6665563,0.00029334653],"about_ca_topic_score_codex":0.0038378849,"about_ca_topic_score_gemma":0.008537268,"teacher_disagreement_score":0.011561648,"about_ca_system_score_codex":0.0012037805,"about_ca_system_score_gemma":0.0038972523,"threshold_uncertainty_score":0.06114459},"labels":[],"label_agreement":null},{"id":"W1853932977","doi":"10.1504/ijbidm.2015.071324","title":"High performance framework for mining association rules from hierarchical data cubes","year":2015,"lang":"en","type":"article","venue":"International Journal of Business Intelligence and Data Mining","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Online analytical processing; Computer science; Data cube; Association rule learning; Data mining; Dimension (graph theory); Hierarchy; Cube (algebra); Data stream mining; Granularity; Data warehouse; Overhead (engineering); Database; Theoretical computer science; Information retrieval; Programming language","score_opus":0.13356226819405143,"score_gpt":0.35907357583464694,"score_spread":0.22551130764059552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1853932977","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0056549557,0.00042235598,0.9776383,0.00019101944,0.000040516697,0.00024555213,0.0007682539,0.014064965,0.00097408163],"genre_scores_gemma":[0.077079944,0.00036141166,0.9165578,0.00014361808,0.000049212835,0.0004239421,0.0039477893,0.00027931752,0.0011569894],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99691534,0.0005168405,0.0003667549,0.00040501094,0.0015271257,0.00026895668],"domain_scores_gemma":[0.9971213,0.0010910068,0.00018569395,0.0006370335,0.0007672784,0.00019765434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029405877,0.0013029925,0.0013404845,0.002500745,0.0013127865,0.003156538,0.0037075859,0.0010130884,0.0035125532],"category_scores_gemma":[0.0073798327,0.00085757294,0.0017723097,0.0040133437,0.00075303053,0.0031565737,0.0028313675,0.0018867278,0.0020697343],"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":[0.0019746977,0.00094209664,0.009716022,0.0011880903,0.00071211456,0.0014217111,0.0008708957,0.16316167,0.02736204,0.092881985,0.051946636,0.64782196],"study_design_scores_gemma":[0.00011583597,0.0001361091,0.000842787,0.000036995836,0.00007048793,0.0003144754,0.000108296255,0.9360194,0.007795372,0.035160813,0.019339738,0.000059794376],"about_ca_topic_score_codex":0.009798086,"about_ca_topic_score_gemma":0.010236251,"teacher_disagreement_score":0.009798086,"about_ca_system_score_codex":0.0010232067,"about_ca_system_score_gemma":0.0029499317,"threshold_uncertainty_score":0.019482076},"labels":[],"label_agreement":null},{"id":"W1854757958","doi":"","title":"The 3W Model and Algebra for Unified Data Mining","year":2000,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Dimension (graph theory); Process (computing); Process calculus; Task (project management); Relational algebra; Theoretical computer science; Extensional definition; Computation; Process mining; Knowledge extraction; Data mining; Algebra over a field; Work in process; Algorithm; Programming language; Mathematics; Relational database","score_opus":0.0608849545277844,"score_gpt":0.29342054888246083,"score_spread":0.23253559435467644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1854757958","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005176238,0.0010515663,0.9782137,0.001872172,0.00012452262,0.000084447995,0.00038091492,0.00034066962,0.012755731],"genre_scores_gemma":[0.14671552,0.0017693043,0.8383184,0.0011683296,0.00047396185,0.0007409744,0.001120108,0.00014796667,0.009545442],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9956664,0.0013312837,0.00053061673,0.0008231031,0.0013415242,0.0003069343],"domain_scores_gemma":[0.997672,0.0006516523,0.00028579237,0.0007791443,0.00038371768,0.00022764894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046971682,0.000685429,0.00090813875,0.0027309265,0.0016519229,0.0060984786,0.0021754764,0.001540986,0.0045179175],"category_scores_gemma":[0.0051840195,0.00054332206,0.002919422,0.0035464193,0.0052722106,0.011712108,0.003792241,0.0028965578,0.0019241276],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000063187026,0.000010474304,0.00013215473,0.000027070204,0.000009455953,0.000036659458,0.00009253971,0.0018387176,0.00016204389,0.98994166,0.0007185989,0.0070242262],"study_design_scores_gemma":[0.0000057605644,0.000010451357,0.00005254699,0.000020072837,0.0000064227897,0.00005234273,0.00003184195,0.014907553,0.0002099836,0.9731409,0.011549942,0.000012156123],"about_ca_topic_score_codex":0.0029588619,"about_ca_topic_score_gemma":0.0019945067,"teacher_disagreement_score":0.0060984786,"about_ca_system_score_codex":0.0019968117,"about_ca_system_score_gemma":0.0029259848,"threshold_uncertainty_score":0.024841309},"labels":[],"label_agreement":null},{"id":"W1857322730","doi":"10.1007/978-3-642-04985-9_12","title":"RBDT-1: A New Rule-Based Decision Tree Generation Technique","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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 Victoria","funders":"","keywords":"Incremental decision tree; Decision tree; Computer science; ID3 algorithm; Decision tree learning; Data mining; Tree (set theory); Decision rule; Machine learning; Decision stump; Decision tree model; Artificial intelligence; Set (abstract data type); Mathematics","score_opus":0.023713212876463177,"score_gpt":0.26454110393866065,"score_spread":0.24082789106219749,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1857322730","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004484043,0.00032528068,0.98617643,0.00014451392,0.00014732148,0.00029445405,0.0011635748,0.0058268528,0.0014375207],"genre_scores_gemma":[0.02662242,0.00016708502,0.96816385,0.00018943743,0.000064427455,0.00027853868,0.0023844026,0.0003272569,0.0018025564],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99843115,0.0003273592,0.00016782238,0.0003178604,0.0006920254,0.00006382229],"domain_scores_gemma":[0.997097,0.0016512009,0.00011938934,0.00033824815,0.0007120051,0.00008222492],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018892337,0.001052149,0.001305958,0.0022943518,0.0005376852,0.0010945366,0.003099523,0.0013947039,0.0074031046],"category_scores_gemma":[0.0068192678,0.0006932004,0.0015106271,0.0020798063,0.000335554,0.0015385718,0.0012910628,0.002234303,0.003789446],"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":[0.00020408763,0.00022448013,0.0010681583,0.00043026323,0.00012246725,0.0002058885,0.000078619116,0.025898816,0.012941999,0.0041598417,0.019221114,0.9354443],"study_design_scores_gemma":[0.00017528322,0.0003084136,0.00097346836,0.00012729962,0.00021825042,0.0007343872,0.000033196913,0.9183603,0.025548905,0.01735726,0.036092952,0.000070254675],"about_ca_topic_score_codex":0.0014939266,"about_ca_topic_score_gemma":0.0027016336,"teacher_disagreement_score":0.0074031046,"about_ca_system_score_codex":0.00045393608,"about_ca_system_score_gemma":0.0010306907,"threshold_uncertainty_score":0.02476585},"labels":[],"label_agreement":null},{"id":"W1858295406","doi":"10.1007/3-540-44886-1_50","title":"Fuzzy C-Means Clustering of Web Users for Educational Sites","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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":"Saint Mary's University","funders":"","keywords":"Computer science; Web mining; Cluster analysis; Data mining; Fuzzy clustering; Web intelligence; Fuzzy logic; Data Web; Web modeling; Web analytics; World Wide Web; Web page; Information retrieval; Machine learning; Artificial intelligence","score_opus":0.02448505845040658,"score_gpt":0.27102063153861455,"score_spread":0.24653557308820798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1858295406","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86186725,0.0008782715,0.12543125,0.00040642725,0.00008553883,0.00029822576,0.0032617026,0.0015385961,0.006232678],"genre_scores_gemma":[0.8883803,0.0001731646,0.102443114,0.000043634056,0.00003421308,0.00010793386,0.0037188495,0.00022238317,0.004876374],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986064,0.00019277223,0.00009241113,0.00029302982,0.0005501503,0.00026538406],"domain_scores_gemma":[0.9969037,0.0008910312,0.00022278391,0.00033101038,0.0013946235,0.00025683237],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016027953,0.0005592641,0.00067703513,0.0077241347,0.0019826575,0.0025071693,0.0015992861,0.0017257648,0.0035872634],"category_scores_gemma":[0.0066130715,0.00031435734,0.0014578063,0.005097835,0.00051648763,0.0011945058,0.0007881487,0.0007864191,0.0019603102],"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":[0.0027033428,0.00096080307,0.21829982,0.0005053448,0.00048961065,0.00035756003,0.003024375,0.079853624,0.02786279,0.0063064457,0.02785903,0.6317772],"study_design_scores_gemma":[0.000060486494,0.00022071006,0.15609603,0.00011514665,0.0003045344,0.000359479,0.0021377595,0.8031093,0.022770926,0.008683301,0.0059625003,0.00017984168],"about_ca_topic_score_codex":0.036490746,"about_ca_topic_score_gemma":0.053982157,"teacher_disagreement_score":0.036490746,"about_ca_system_score_codex":0.0020646458,"about_ca_system_score_gemma":0.0019789273,"threshold_uncertainty_score":0.072556674},"labels":[],"label_agreement":null},{"id":"W186018181","doi":"","title":"Pre-order linked WAP-tree mining of sequential patterns.","year":2002,"lang":"en","type":"article","venue":"Scholarship at UWindsor (University of Windsor)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Tree (set theory); Data mining; Mathematics; Combinatorics","score_opus":0.032575902894062314,"score_gpt":0.23032245697977716,"score_spread":0.19774655408571484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W186018181","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05494439,0.0010813948,0.92827433,0.0003236004,0.00012150259,0.0009678375,0.0058516716,0.004362163,0.0040730913],"genre_scores_gemma":[0.22432964,0.00068389944,0.75408566,0.00018243764,0.00006567911,0.00075536704,0.015566077,0.00024512003,0.004086129],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99870515,0.00018206416,0.00017521484,0.00030379306,0.0005092203,0.00012447873],"domain_scores_gemma":[0.9969902,0.0011951695,0.00041599173,0.00045439508,0.0008270388,0.00011715483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008913357,0.0007645295,0.0007615054,0.005478365,0.0011487155,0.0016538162,0.0013735835,0.0009261285,0.0031235416],"category_scores_gemma":[0.00776494,0.00049531943,0.001546762,0.0053441254,0.0005506987,0.0023030073,0.0011204077,0.0012503315,0.002110929],"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":[0.00050649873,0.00050142116,0.032081436,0.0011721692,0.0003997249,0.0020656094,0.00092423824,0.068421625,0.025758967,0.027436152,0.018159803,0.8225723],"study_design_scores_gemma":[0.000081111706,0.00043939994,0.011193053,0.0002757018,0.0001751787,0.0027445483,0.0006141419,0.838381,0.016177183,0.08451819,0.04532733,0.00007321077],"about_ca_topic_score_codex":0.002974621,"about_ca_topic_score_gemma":0.0062404578,"teacher_disagreement_score":0.005478365,"about_ca_system_score_codex":0.00052402436,"about_ca_system_score_gemma":0.001615842,"threshold_uncertainty_score":0.01044935},"labels":[],"label_agreement":null},{"id":"W1873820756","doi":"","title":"Static and dynamic overproduction and selection of classifier ensembles with genetic algorithms","year":2008,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Humanities; Selection (genetic algorithm); Philosophy; Computer science; Artificial intelligence","score_opus":0.011630962568971052,"score_gpt":0.22343088602575037,"score_spread":0.2117999234567793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1873820756","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.552482,0.0018049369,0.43268442,0.0008299057,0.00024273123,0.00018488211,0.00017024654,0.0013487821,0.01025206],"genre_scores_gemma":[0.9014911,0.00043942305,0.09361902,0.00013603814,0.000066378525,0.00011653304,0.00018058941,0.00012437785,0.0038264724],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987897,0.00035266293,0.000057271372,0.00025493407,0.00040060814,0.0001447312],"domain_scores_gemma":[0.9969379,0.001617476,0.00022411875,0.00046696418,0.00061057374,0.00014292162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022132683,0.00066220085,0.000873617,0.00092315645,0.0007519016,0.0017661436,0.0011583169,0.00092316436,0.0017768017],"category_scores_gemma":[0.0055446667,0.0002929494,0.0006527083,0.0008887703,0.0006214106,0.0015408773,0.00090850826,0.0006873204,0.00040647134],"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":[0.00036945374,0.00033321357,0.011089063,0.00014584578,0.00019085346,0.00021196184,0.00027016643,0.5653069,0.033462305,0.008033036,0.001493411,0.3790938],"study_design_scores_gemma":[0.00003350942,0.0002359791,0.0038107582,0.000022822582,0.00006593624,0.00012586944,0.000104047234,0.9717371,0.015302336,0.005756187,0.0027776088,0.000027866441],"about_ca_topic_score_codex":0.0025795395,"about_ca_topic_score_gemma":0.0043872097,"teacher_disagreement_score":0.0025795395,"about_ca_system_score_codex":0.0011493799,"about_ca_system_score_gemma":0.0008678458,"threshold_uncertainty_score":0.011705041},"labels":[],"label_agreement":null},{"id":"W188074206","doi":"10.1007/11516798_5","title":"Searching for a Black Hole in Tree Networks","year":2005,"lang":"en","type":"article","venue":"Lecture notes in computer science","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":"Université du Québec en Outaouais","funders":"","keywords":"Tree (set theory); Computer science; Mathematics; Combinatorics","score_opus":0.01867880802106293,"score_gpt":0.2854821865197181,"score_spread":0.26680337849865515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W188074206","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48425,0.0015689846,0.4925247,0.007146093,0.0003287544,0.0001871447,0.00033887464,0.00080472394,0.012850577],"genre_scores_gemma":[0.83660764,0.0005696726,0.15471698,0.00091178186,0.00011779866,0.00011001539,0.00029190362,0.00019716691,0.0064769275],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906343,0.00042756062,0.000035543224,0.00018174984,0.00014394827,0.00014777735],"domain_scores_gemma":[0.985926,0.010882649,0.0010067133,0.0008827694,0.0005702557,0.0007316762],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022491855,0.0005695647,0.0016042474,0.0014553942,0.0018832613,0.0018073063,0.002120537,0.004275199,0.004872247],"category_scores_gemma":[0.023002373,0.0011609404,0.0010435953,0.001142917,0.0026178067,0.0072756647,0.0030999708,0.0020732603,0.00052296504],"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":[0.001970446,0.0003401242,0.008791411,0.0007773161,0.00039555103,0.001056193,0.001851602,0.22184606,0.007100892,0.63741016,0.023726322,0.09473388],"study_design_scores_gemma":[0.00013009604,0.00013501929,0.00030362658,0.000069425725,0.00005876949,0.00017141801,0.00031650218,0.42595917,0.0016120626,0.56915635,0.0020668008,0.00002082164],"about_ca_topic_score_codex":0.0010340686,"about_ca_topic_score_gemma":0.001199352,"teacher_disagreement_score":0.004872247,"about_ca_system_score_codex":0.0007109857,"about_ca_system_score_gemma":0.00070251577,"threshold_uncertainty_score":0.016299248},"labels":[],"label_agreement":null},{"id":"W1884786007","doi":"","title":"Interval set clustering of web users using modified Kohonen self-organizing maps based on the properties of rough sets","year":2004,"lang":"en","type":"article","venue":"Saint Mary's University Institutional Repository (Saint Mary's University)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"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":"Cluster analysis; Data mining; Computer science; Self-organizing map; Web mining; Rough set; Set (abstract data type); Fuzzy clustering; Machine learning; Web page; World Wide Web","score_opus":0.027115376957776806,"score_gpt":0.19752431009847296,"score_spread":0.17040893314069616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1884786007","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.122414336,0.00016058407,0.8750954,0.000070274575,0.00002777287,0.00012591593,0.00009975296,0.00050297583,0.0015028765],"genre_scores_gemma":[0.6570121,0.00009921947,0.34182116,0.000017840719,0.000014078715,0.00013676377,0.00017965108,0.000047397953,0.00067178643],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99947256,0.00013171813,0.000040762916,0.00009005581,0.00022127452,0.000043695247],"domain_scores_gemma":[0.99904364,0.00047517417,0.000079877835,0.000100303674,0.00027150573,0.000029370785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009420558,0.0003822992,0.00073453505,0.0017818521,0.000555762,0.0011586981,0.0011769885,0.0004820704,0.000576695],"category_scores_gemma":[0.0034701976,0.0002812827,0.0009231028,0.0013514213,0.00038024632,0.0011403325,0.0006314294,0.00046857435,0.00014546936],"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":[0.0003073778,0.00015783253,0.0054151686,0.00020436896,0.00018987614,0.00019336442,0.001093147,0.6562058,0.00871667,0.010095273,0.0010583116,0.31636286],"study_design_scores_gemma":[0.00000639816,0.000025694451,0.0012658811,0.00000677906,0.000015440572,0.00003336433,0.00008673772,0.99213785,0.0019454793,0.00418137,0.00027362833,0.000021385878],"about_ca_topic_score_codex":0.0057485704,"about_ca_topic_score_gemma":0.0038411587,"teacher_disagreement_score":0.0057485704,"about_ca_system_score_codex":0.00062551297,"about_ca_system_score_gemma":0.00051631115,"threshold_uncertainty_score":0.011430204},"labels":[],"label_agreement":null},{"id":"W1888464276","doi":"10.1109/icde.2000.839450","title":"Efficient mining of constrained correlated sets","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":161,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Set (abstract data type); Computer science; Meaning (existential); Data mining; Mathematics; Algorithm; Theoretical computer science; Programming language","score_opus":0.023435587308256976,"score_gpt":0.23826341835949041,"score_spread":0.21482783105123343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1888464276","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07381917,0.0011825729,0.9215789,0.00050879194,0.00004689373,0.0003190778,0.0010049348,0.00034796257,0.0011918535],"genre_scores_gemma":[0.42247406,0.0010273204,0.570931,0.00034315052,0.00016322827,0.00054927496,0.0038014883,0.00011312941,0.0005972342],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98650694,0.005013568,0.0012550246,0.003199997,0.0033754236,0.00064904214],"domain_scores_gemma":[0.95682806,0.029270612,0.0047449972,0.005575967,0.0030890184,0.00049135496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0067596976,0.0020564506,0.003975282,0.00562707,0.0016274366,0.0032590337,0.0038372688,0.0020862303,0.0012900918],"category_scores_gemma":[0.05630355,0.0014186801,0.0020557872,0.010913316,0.0018285825,0.0057601565,0.0030846363,0.0021630824,0.0006826252],"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":[0.0008783665,0.0010700173,0.046084933,0.0020342371,0.001557879,0.0015251441,0.0010265694,0.42677367,0.008986099,0.09817309,0.011145412,0.40074453],"study_design_scores_gemma":[0.000053632924,0.0002008464,0.0030907255,0.0001346611,0.00010043829,0.00076480245,0.00029063807,0.8843546,0.005179349,0.10284326,0.0029174779,0.00006955638],"about_ca_topic_score_codex":0.0025644274,"about_ca_topic_score_gemma":0.0032370384,"teacher_disagreement_score":0.0067596976,"about_ca_system_score_codex":0.0012822626,"about_ca_system_score_gemma":0.0023652362,"threshold_uncertainty_score":0.035749137},"labels":[],"label_agreement":null},{"id":"W190049315","doi":"10.1007/978-3-642-30353-1_6","title":"Mining Top-K Association Rules","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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":"Université de Moncton","funders":"","keywords":"Association rule learning; Computer science; Data mining; Scalability; Task (project management); Set (abstract data type); Association (psychology); Algorithm; Database","score_opus":0.018313512452441,"score_gpt":0.25095015021367056,"score_spread":0.23263663776122956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W190049315","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18790185,0.014673414,0.75040436,0.0024858946,0.0015452628,0.0010000925,0.018931476,0.0077487538,0.015308897],"genre_scores_gemma":[0.3142402,0.00620406,0.626182,0.0007059005,0.0006628685,0.00041041014,0.041165404,0.00042606975,0.0100030145],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963973,0.00035641133,0.0006866225,0.0009695917,0.0013529017,0.00023713872],"domain_scores_gemma":[0.9930346,0.0036087104,0.0006402029,0.0010518951,0.0014045687,0.00026003848],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019309372,0.0018176076,0.002459634,0.0070381295,0.0019287034,0.0042828056,0.0036377923,0.001849336,0.0041359845],"category_scores_gemma":[0.013546433,0.0012028001,0.0033022482,0.0072211833,0.00063279486,0.005011404,0.0020117604,0.0023781531,0.0068119727],"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":[0.0006646999,0.0007750243,0.040166516,0.0017740559,0.0011287845,0.0032398175,0.0003686707,0.013132849,0.010843454,0.0056060716,0.03331873,0.8889814],"study_design_scores_gemma":[0.00035655315,0.0011576691,0.040816985,0.0019209494,0.004176087,0.023545608,0.002223778,0.60802466,0.046455894,0.17650945,0.09444804,0.00036437626],"about_ca_topic_score_codex":0.0015270791,"about_ca_topic_score_gemma":0.0038134106,"teacher_disagreement_score":0.0070381295,"about_ca_system_score_codex":0.00047654405,"about_ca_system_score_gemma":0.0020921612,"threshold_uncertainty_score":0.013836265},"labels":[],"label_agreement":null},{"id":"W1903505204","doi":"","title":"Using association patterns for discrete-valed data clustering","year":2007,"lang":"en","type":"article","venue":"Conference on Artificial Intelligence for Applications","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Computer science; Data mining; Association (psychology); Consensus clustering; CURE data clustering algorithm; Association rule learning; Correlation clustering; Cluster (spacecraft); Artificial intelligence","score_opus":0.29903905070245496,"score_gpt":0.43050299944391246,"score_spread":0.1314639487414575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1903505204","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029065066,0.00015186053,0.9955509,0.0001774585,0.00004656841,0.00006894065,0.00016706444,0.00051765476,0.00041306458],"genre_scores_gemma":[0.049617182,0.00022767577,0.94882345,0.00008145864,0.000044870558,0.00023279751,0.0005485351,0.00007151119,0.0003524926],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9916334,0.0028094933,0.0011220523,0.0017405208,0.0025004004,0.0001941107],"domain_scores_gemma":[0.9858943,0.00682463,0.0017061412,0.0030767866,0.0022253909,0.0002727187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0062432997,0.0011759133,0.0013332621,0.0051184185,0.0014471565,0.0031989145,0.0019820924,0.0019294884,0.0019541914],"category_scores_gemma":[0.02993696,0.0007260754,0.0015160533,0.0068758605,0.0017235202,0.0040927646,0.0027805404,0.002466198,0.0015466403],"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":[0.0003757836,0.00027609864,0.012195603,0.0009228161,0.0005663637,0.0008029594,0.0014395048,0.09781165,0.0077720773,0.11239304,0.008470995,0.7569731],"study_design_scores_gemma":[0.00006343983,0.0001203096,0.001959459,0.00014612266,0.00010587236,0.0011739578,0.00033329692,0.7585475,0.007486329,0.2106872,0.019271437,0.0001051207],"about_ca_topic_score_codex":0.0012405454,"about_ca_topic_score_gemma":0.0013821813,"teacher_disagreement_score":0.0062432997,"about_ca_system_score_codex":0.00078714854,"about_ca_system_score_gemma":0.0015487493,"threshold_uncertainty_score":0.033018112},"labels":[],"label_agreement":null},{"id":"W1904390369","doi":"","title":"Automatic New System in Intelligent Transport System by Using Knowledge Grid","year":2012,"lang":"en","type":"article","venue":"Journal of academic and applied studies","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Grid; Grid system; Distributed computing; Artificial intelligence; Geography","score_opus":0.05662122954348595,"score_gpt":0.3222780974291791,"score_spread":0.26565686788569315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1904390369","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12072772,0.00061709655,0.8428801,0.00062645104,0.00034938933,0.00045010177,0.0019654564,0.018892989,0.013490638],"genre_scores_gemma":[0.72815645,0.0003594866,0.26146474,0.00012894484,0.000053060958,0.00022229772,0.003373762,0.00022216907,0.006019129],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993074,0.000086373526,0.00008465341,0.00024386404,0.00019850147,0.000079191],"domain_scores_gemma":[0.99959606,0.00006842867,0.000035762492,0.0001117686,0.00015758397,0.00003043584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005082645,0.00056145625,0.0007243948,0.0017451273,0.0011537195,0.0016666568,0.00096108747,0.00060008385,0.0038086458],"category_scores_gemma":[0.0011416102,0.0003128779,0.0006792448,0.0016636732,0.0003322069,0.0024168189,0.00094683433,0.00045910434,0.0010475912],"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":[0.0011754462,0.000751279,0.024800438,0.00059833756,0.00028167103,0.0016545763,0.00049538823,0.112830825,0.028373275,0.021918466,0.046480305,0.76064],"study_design_scores_gemma":[0.00012204506,0.0001102987,0.005376647,0.000043188276,0.00021488094,0.00047714225,0.0002838361,0.9215988,0.02402195,0.021225765,0.026465392,0.000060053233],"about_ca_topic_score_codex":0.00857117,"about_ca_topic_score_gemma":0.0051612365,"teacher_disagreement_score":0.00857117,"about_ca_system_score_codex":0.0008895946,"about_ca_system_score_gemma":0.0016728777,"threshold_uncertainty_score":0.017042577},"labels":[],"label_agreement":null},{"id":"W1906561224","doi":"10.1109/pdis.1996.568665","title":"A fast distributed algorithm for mining association rules","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":439,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Association rule learning; Computer science; Scalability; Database transaction; Data mining; Distributed database; Distributed algorithm; Association (psychology); Algorithm design; Algorithm; Distributed computing; Database","score_opus":0.02193598178644724,"score_gpt":0.24397990882214524,"score_spread":0.222043927035698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1906561224","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015501027,0.0003075896,0.9964199,0.00013600908,0.00007356898,0.00012763681,0.00009399965,0.00092073466,0.00037042532],"genre_scores_gemma":[0.021235019,0.00022584973,0.9764371,0.00011171931,0.00007374202,0.00043063026,0.000412576,0.000059787406,0.0010137344],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962805,0.00087708834,0.000385674,0.0009908822,0.0012964715,0.00016950433],"domain_scores_gemma":[0.99494135,0.0028036118,0.0002995447,0.00085680874,0.00096556364,0.0001331264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004592292,0.0015593909,0.0021245535,0.004026335,0.001767337,0.001948495,0.0030453105,0.0018232239,0.0034913088],"category_scores_gemma":[0.0141743375,0.0008990695,0.0014628384,0.0056802323,0.0009520062,0.002976439,0.002289332,0.002121191,0.0024962137],"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":[0.00034413126,0.00019748192,0.0015401463,0.00031790385,0.00023021271,0.00022953378,0.00015570271,0.052333932,0.0049128016,0.015446283,0.011222368,0.9130694],"study_design_scores_gemma":[0.0005706827,0.00029139392,0.0007950916,0.00007460299,0.00016876508,0.001517933,0.00011758074,0.8765871,0.006412079,0.08524678,0.028146744,0.00007129946],"about_ca_topic_score_codex":0.0022578978,"about_ca_topic_score_gemma":0.0028905813,"teacher_disagreement_score":0.004592292,"about_ca_system_score_codex":0.0006767472,"about_ca_system_score_gemma":0.0027670288,"threshold_uncertainty_score":0.024286628},"labels":[],"label_agreement":null},{"id":"W191211215","doi":"","title":"Discovering Accurate and Interesting Classification Rules Using Genetic Algorithm.","year":2006,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Pruning; Task (project management); Data mining; Set (abstract data type); Genetic algorithm; Artificial intelligence; Rank (graph theory); Process (computing); Machine learning; Algorithm; Pattern recognition (psychology); Mathematics","score_opus":0.04052976808006323,"score_gpt":0.2810498314170712,"score_spread":0.24052006333700796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W191211215","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03459813,0.0006260984,0.9613059,0.00037778472,0.000037250218,0.0003590447,0.00014948066,0.0008676474,0.001678682],"genre_scores_gemma":[0.11076313,0.00031122874,0.88757443,0.00015029749,0.000023367513,0.0002658497,0.00033288306,0.000053035677,0.0005257543],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982223,0.0006113545,0.0001524786,0.00034603846,0.00057228655,0.000095612326],"domain_scores_gemma":[0.9942675,0.0040566646,0.00058478425,0.00044209766,0.0005725898,0.00007634378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035735606,0.0013861641,0.0016675354,0.0041121375,0.00077945594,0.0015705925,0.0015980896,0.0016743683,0.0008608908],"category_scores_gemma":[0.012030428,0.000593988,0.0013818712,0.002447033,0.0010653315,0.0013885339,0.00077509845,0.001551661,0.0005431279],"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":[0.00015241827,0.0003958364,0.013257652,0.0004383913,0.0005535142,0.00040450407,0.00039270017,0.43904296,0.014124607,0.0158495,0.0023858333,0.5130021],"study_design_scores_gemma":[0.00003879632,0.0000886007,0.001093672,0.00008154754,0.00011044457,0.00019539826,0.00007935452,0.97464037,0.0046143425,0.017235322,0.0018000039,0.000022129607],"about_ca_topic_score_codex":0.0041623805,"about_ca_topic_score_gemma":0.0046320017,"teacher_disagreement_score":0.0041623805,"about_ca_system_score_codex":0.0010130994,"about_ca_system_score_gemma":0.0014445473,"threshold_uncertainty_score":0.018899024},"labels":[],"label_agreement":null},{"id":"W19283389","doi":"10.1007/978-3-642-41218-9_35","title":"Recursive Profiles of Businesses and Reviewers on Yelp.com","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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":"Saint Mary's University; University of Saskatchewan","funders":"","keywords":"Computer science; Profiling (computer programming); Cluster analysis; Grading (engineering); Representation (politics); World Wide Web; Data science; Information retrieval; Data mining; Database; Artificial intelligence; Programming language","score_opus":0.019640891649529486,"score_gpt":0.2524847464374856,"score_spread":0.2328438547879561,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W19283389","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06245995,0.0037769675,0.03898723,0.008770962,0.001338923,0.00047403818,0.23698878,0.01882437,0.6283788],"genre_scores_gemma":[0.18299244,0.003166758,0.041944742,0.0012345086,0.00090683927,0.00039758958,0.16799413,0.0057455692,0.5956175],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990865,0.00017401855,0.00006662233,0.00018425671,0.00033025155,0.00015840595],"domain_scores_gemma":[0.9962919,0.0010021899,0.00044361627,0.0005013012,0.0009736772,0.00078735367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009650279,0.0005732283,0.00047610363,0.0061737094,0.0015698919,0.0036684894,0.0008279324,0.0006955383,0.11060059],"category_scores_gemma":[0.0072785956,0.0004092297,0.0003692234,0.008156446,0.00022768589,0.00486352,0.0015392026,0.00070045004,0.07083026],"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":[0.00023635413,0.000037733727,0.008736268,0.00017516756,0.000014747992,0.00020097295,0.0005572085,0.0008401138,0.0006068574,0.019438302,0.8282234,0.14093277],"study_design_scores_gemma":[0.000016664062,0.000020137384,0.008402677,0.000093319846,0.000008541411,0.0002953835,0.00052959495,0.0017324969,0.0007972215,0.008791128,0.9792793,0.000033490353],"about_ca_topic_score_codex":0.0065020854,"about_ca_topic_score_gemma":0.017724773,"teacher_disagreement_score":0.11060059,"about_ca_system_score_codex":0.0009232422,"about_ca_system_score_gemma":0.0014274884,"threshold_uncertainty_score":0.36999583},"labels":[],"label_agreement":null},{"id":"W1940847786","doi":"10.1007/3-540-45357-1_61","title":"Interactive Construction of Decision Trees","year":2001,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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 Waterloo","funders":"","keywords":"Computer science; Domain (mathematical analysis); Decision tree; Preference; Process (computing); Decision process; Human–computer interaction; Tree (set theory); Artificial intelligence; Management science; Programming language","score_opus":0.014567321842768497,"score_gpt":0.2646791023793548,"score_spread":0.25011178053658634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1940847786","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010881933,0.0002145127,0.977452,0.00022062473,0.00006301521,0.00012348115,0.00057007436,0.0024200852,0.0080543095],"genre_scores_gemma":[0.14283042,0.0002568321,0.84718,0.00012081388,0.00006769997,0.0002618187,0.0031584562,0.00065937894,0.005464635],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99743205,0.0008354764,0.00017778788,0.00047118176,0.00084068836,0.00024286058],"domain_scores_gemma":[0.9925869,0.0053010653,0.00013867633,0.0011176835,0.0006008839,0.0002548538],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019519383,0.0006847415,0.0011831102,0.0016482021,0.0010161274,0.0021378929,0.0020268075,0.0008135956,0.015476314],"category_scores_gemma":[0.010954756,0.0011030177,0.0022760178,0.001790137,0.001002606,0.0027953947,0.004808648,0.0024310655,0.0043360554],"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":[0.00055714784,0.00025831864,0.0025010481,0.00073972804,0.00018275935,0.00047902434,0.000854222,0.06607203,0.013259406,0.24952626,0.030432058,0.635138],"study_design_scores_gemma":[0.00011846775,0.00008617915,0.00075151416,0.00011510355,0.000098052995,0.00028180226,0.00019182854,0.4523085,0.012382693,0.49303964,0.040588927,0.000037258018],"about_ca_topic_score_codex":0.0010603272,"about_ca_topic_score_gemma":0.0023730958,"teacher_disagreement_score":0.015476314,"about_ca_system_score_codex":0.0008679773,"about_ca_system_score_gemma":0.0010294517,"threshold_uncertainty_score":0.05177343},"labels":[],"label_agreement":null},{"id":"W1943292826","doi":"10.1109/cig.2015.7317897","title":"Mining game logs to create a playbook for unit AIs","year":2015,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; State (computer science); Battle; Data mining; Cluster (spacecraft); Data science; Geography; Algorithm","score_opus":0.10328474107881794,"score_gpt":0.3238989060702502,"score_spread":0.22061416499143224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1943292826","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2530172,0.0013968077,0.55944777,0.0016354322,0.0006372168,0.0041245027,0.11085559,0.04902765,0.019857913],"genre_scores_gemma":[0.3596135,0.00050951535,0.52070487,0.00021199933,0.0001394482,0.0017425298,0.10457128,0.0009849314,0.011521947],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988237,0.00017310375,0.00012622315,0.00030229415,0.0004961613,0.00007851812],"domain_scores_gemma":[0.9966222,0.0013549295,0.0003827864,0.00051795,0.00080183,0.00032024787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009139312,0.0017632884,0.00066663086,0.0057625086,0.0005842925,0.0015837589,0.0015739062,0.00078609353,0.0055207103],"category_scores_gemma":[0.008257227,0.00048566062,0.0006826616,0.0027249749,0.00026232158,0.0024221889,0.0011273243,0.0013036198,0.005485098],"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":[0.0008798299,0.0018568836,0.09810461,0.0015216261,0.0004111189,0.0012144271,0.0015964833,0.034958497,0.016815891,0.0074744583,0.08880539,0.7463607],"study_design_scores_gemma":[0.00012540832,0.00065156765,0.048659448,0.00030781692,0.00014167973,0.00065410783,0.002333614,0.8035716,0.025384491,0.022676034,0.09534704,0.00014723021],"about_ca_topic_score_codex":0.0071608257,"about_ca_topic_score_gemma":0.021127542,"teacher_disagreement_score":0.0071608257,"about_ca_system_score_codex":0.0006193993,"about_ca_system_score_gemma":0.0013592279,"threshold_uncertainty_score":0.018468559},"labels":[],"label_agreement":null},{"id":"W1950860289","doi":"10.3233/ida-2008-12205","title":"Bridging the gap between data mining and decision support: A case-based reasoning and ontology approach","year":2008,"lang":"en","type":"article","venue":"Intelligent Data Analysis","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Bridging (networking); Ontology; Computer science; Decision support system; Data science; Data mining; Knowledge management; Epistemology","score_opus":0.15687912166084436,"score_gpt":0.34278105022392563,"score_spread":0.18590192856308127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1950860289","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0123876175,0.007000753,0.8955454,0.032613955,0.00044421345,0.00034737805,0.00019635454,0.00020536981,0.051258966],"genre_scores_gemma":[0.19470544,0.006317773,0.7918511,0.0017723297,0.00033777504,0.00047218354,0.00024266598,0.0000508382,0.00424982],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98885417,0.0070160287,0.0007848532,0.0004868874,0.002300445,0.0005576456],"domain_scores_gemma":[0.98742384,0.010183196,0.0006594376,0.0007209311,0.0006000058,0.00041267203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0150331715,0.001159386,0.0014688335,0.008482897,0.0027530799,0.012078266,0.005849223,0.005065547,0.004118749],"category_scores_gemma":[0.014458414,0.0010654492,0.001989542,0.0071570463,0.011337616,0.012718719,0.006605073,0.002966533,0.00063332275],"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":[0.00005015868,0.0001935761,0.0008611517,0.0002896097,0.00005228945,0.0011917845,0.0017094603,0.007484778,0.0003066181,0.9431674,0.0029427805,0.041750383],"study_design_scores_gemma":[0.00011005761,0.0000629599,0.00039740873,0.00081336807,0.00007975745,0.0013543768,0.002883456,0.069310255,0.0010353603,0.84054494,0.08333867,0.00006943021],"about_ca_topic_score_codex":0.007870259,"about_ca_topic_score_gemma":0.0066991784,"teacher_disagreement_score":0.0150331715,"about_ca_system_score_codex":0.004661876,"about_ca_system_score_gemma":0.0043177353,"threshold_uncertainty_score":0.07950395},"labels":[],"label_agreement":null},{"id":"W1956439169","doi":"10.3233/ifs-151936","title":"A fast Algorithm for mining fuzzy frequent itemsets","year":2015,"lang":"en","type":"article","venue":"Journal of Intelligent & Fuzzy Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"Harbin Institute of Technology; National Natural Science Foundation of China; Tencent","keywords":"Tree traversal; Data mining; Computer science; Pruning; Apriori algorithm; Fuzzy logic; Set (abstract data type); Process (computing); Tree (set theory); Fuzzy set; A priori and a posteriori; Algorithm; Association rule learning; Artificial intelligence; Mathematics","score_opus":0.05610564189806256,"score_gpt":0.2997849752522972,"score_spread":0.24367933335423464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1956439169","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041201226,0.0006914946,0.9923907,0.00010409004,0.00008697255,0.00023243965,0.0005254403,0.0011231903,0.00072556833],"genre_scores_gemma":[0.024211183,0.00042873458,0.97279155,0.000064827706,0.000042193613,0.00031805958,0.0012216266,0.000045855188,0.00087602047],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981007,0.00032552672,0.00025829914,0.0003965833,0.00080999837,0.00010889116],"domain_scores_gemma":[0.99712306,0.0015296247,0.00021078032,0.00023659487,0.0008443838,0.00005549687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022633064,0.001177123,0.0017552577,0.0047946344,0.0013766146,0.0013662154,0.0019522216,0.0014124742,0.003406505],"category_scores_gemma":[0.0074133086,0.0007303342,0.0014105056,0.004789702,0.00037372415,0.0024170775,0.001021891,0.0012692036,0.00255091],"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":[0.00032875652,0.00016228735,0.0022450197,0.0006624908,0.00020413073,0.00041516728,0.00017657771,0.031425573,0.008981599,0.012986227,0.009873156,0.9325391],"study_design_scores_gemma":[0.00024096826,0.0005051471,0.0022279334,0.0002486307,0.00017472362,0.0031856748,0.00023967953,0.8742188,0.018853374,0.050480466,0.04948248,0.00014204349],"about_ca_topic_score_codex":0.0013298367,"about_ca_topic_score_gemma":0.0016467787,"teacher_disagreement_score":0.0047946344,"about_ca_system_score_codex":0.0005370268,"about_ca_system_score_gemma":0.0014861362,"threshold_uncertainty_score":0.011969686},"labels":[],"label_agreement":null},{"id":"W1963747491","doi":"10.1109/icdmw.2011.177","title":"Visually Contrast Two Collections of Frequent Patterns","year":2011,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":8,"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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Contrast (vision); Computer science; Visualization; Representation (politics); Information retrieval; Color contrast; Artificial intelligence","score_opus":0.03579596834365949,"score_gpt":0.26633810913825157,"score_spread":0.23054214079459207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1963747491","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2343208,0.0017268808,0.70218945,0.0032666144,0.0005592208,0.0005742167,0.010696658,0.019822119,0.026844067],"genre_scores_gemma":[0.42896464,0.0013584731,0.55159914,0.00050451595,0.00022743546,0.00043469435,0.0076845796,0.0016445271,0.0075819236],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99937975,0.00013016292,0.00007202394,0.0001509221,0.00020017874,0.00006690846],"domain_scores_gemma":[0.9955859,0.0023520272,0.0005500019,0.00052264455,0.00077850645,0.00021080671],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009772372,0.0010998275,0.0005952048,0.00521293,0.00062239065,0.0026263264,0.0007770642,0.0009844637,0.011346176],"category_scores_gemma":[0.006292045,0.0005426772,0.0008360389,0.0030876687,0.0004452993,0.0039712302,0.002223411,0.0010319405,0.0014624777],"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":[0.003510416,0.00046354593,0.026437186,0.0034607146,0.0005694971,0.0058153276,0.015981846,0.018021405,0.13831152,0.06353407,0.09517534,0.6287192],"study_design_scores_gemma":[0.00070320524,0.0011673053,0.060710587,0.0012958148,0.0005899261,0.016255992,0.011946455,0.2102105,0.0948394,0.16294955,0.4386253,0.00070597976],"about_ca_topic_score_codex":0.0013472763,"about_ca_topic_score_gemma":0.0016211956,"teacher_disagreement_score":0.011346176,"about_ca_system_score_codex":0.00042851674,"about_ca_system_score_gemma":0.00054865074,"threshold_uncertainty_score":0.037956774},"labels":[],"label_agreement":null},{"id":"W1964492476","doi":"10.1109/icdm.2014.146","title":"Fast Algorithms for Frequent Itemset Mining from Uncertain Data","year":2014,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":64,"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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Data mining; Computer science; Tree (set theory); Uncertain data; Set (abstract data type); Tree structure; Data set; Data structure; Algorithm; Artificial intelligence; Mathematics; Binary tree","score_opus":0.0931108935228487,"score_gpt":0.32410135173307997,"score_spread":0.2309904582102313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964492476","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004916175,0.00084770704,0.99227774,0.00016634836,0.000045194956,0.00010744335,0.00026760495,0.00087387033,0.00049793336],"genre_scores_gemma":[0.055600516,0.0009056975,0.9408376,0.00011356981,0.00010967912,0.0004085502,0.0014565396,0.000097353695,0.00047042096],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99529725,0.0010020521,0.0006425652,0.0008335606,0.0019010566,0.00032347298],"domain_scores_gemma":[0.9800417,0.014134673,0.0010832367,0.0021848024,0.0023350033,0.0002205939],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004587425,0.0016154721,0.0022636412,0.003902648,0.00159482,0.0022229734,0.0032416312,0.0022067535,0.0025173402],"category_scores_gemma":[0.027957542,0.0010922711,0.0019188465,0.007065367,0.0007659412,0.006625748,0.0023980252,0.0027566694,0.0019036932],"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":[0.0005883625,0.00028242343,0.002944023,0.0007452144,0.00021200239,0.000363698,0.0004212072,0.1572576,0.0054935697,0.042489495,0.01001833,0.7791841],"study_design_scores_gemma":[0.00011662009,0.00017143351,0.00068309676,0.00008195348,0.000059697635,0.00067173236,0.00014070356,0.88185686,0.0052501895,0.10176278,0.009151103,0.00005377783],"about_ca_topic_score_codex":0.0015631156,"about_ca_topic_score_gemma":0.0017904752,"teacher_disagreement_score":0.004587425,"about_ca_system_score_codex":0.000979521,"about_ca_system_score_gemma":0.0016809346,"threshold_uncertainty_score":0.024260938},"labels":[],"label_agreement":null},{"id":"W1964786728","doi":"10.1016/j.procs.2014.08.043","title":"Visualizing Information for Electromyographic Characterization","year":2014,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Allison University","funders":"","keywords":"Computer science; Visualization; Data science; Human–computer interaction; Data visualization; Artificial intelligence","score_opus":0.006464410917255394,"score_gpt":0.23454342516808668,"score_spread":0.2280790142508313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964786728","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019770347,0.0046186736,0.94897383,0.0028931494,0.00022006866,0.00025214616,0.003376253,0.011587479,0.00830803],"genre_scores_gemma":[0.18674655,0.004026221,0.80316824,0.00028174595,0.00019105671,0.00032781414,0.0021765046,0.00090734113,0.0021744883],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991736,0.00037212484,0.00008761696,0.00008906159,0.00021832467,0.000059160855],"domain_scores_gemma":[0.99421126,0.004256771,0.0003019045,0.00049919775,0.0005464308,0.00018449],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018920988,0.0016791279,0.000758994,0.0048762434,0.00076375616,0.0040968074,0.0010831559,0.0017278534,0.016155306],"category_scores_gemma":[0.011678846,0.0005490899,0.0007907139,0.0035001673,0.00063700025,0.003411736,0.0026477505,0.0013583214,0.0019091661],"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":[0.001087242,0.00019013455,0.005493654,0.002852466,0.00016672237,0.0028808224,0.0057733995,0.029475184,0.0551018,0.064525284,0.048786517,0.78366673],"study_design_scores_gemma":[0.00023060663,0.00050254446,0.009607117,0.0024891377,0.00030727457,0.0063064825,0.0035839018,0.34923482,0.06288575,0.24613275,0.31823915,0.0004804367],"about_ca_topic_score_codex":0.0015499605,"about_ca_topic_score_gemma":0.0021789176,"teacher_disagreement_score":0.016155306,"about_ca_system_score_codex":0.00058041164,"about_ca_system_score_gemma":0.00069437135,"threshold_uncertainty_score":0.054044843},"labels":[],"label_agreement":null},{"id":"W1965269329","doi":"10.1145/1147234.1147235","title":"Introduction to the special issue on successful real-world data mining applications","year":2006,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Data science; Field (mathematics); Database transaction; Transaction data; Knowledge extraction; Data discovery; Data stream mining; Data mining; World Wide Web; Database; Metadata","score_opus":0.03975452893360564,"score_gpt":0.2972189779695197,"score_spread":0.25746444903591403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1965269329","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010028811,0.07082165,0.020917777,0.07909087,0.6991462,0.0007269252,0.0038137913,0.002623769,0.12185616],"genre_scores_gemma":[0.003426979,0.053577326,0.01030057,0.021508593,0.6522149,0.00039569067,0.0047387723,0.0019400266,0.25189713],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961204,0.00051231595,0.00039657496,0.0005080903,0.0022812502,0.00018130882],"domain_scores_gemma":[0.9813572,0.007568348,0.0011096868,0.001450196,0.0059007704,0.0026137382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040380945,0.0021474457,0.0021638903,0.005425847,0.0018374001,0.008494624,0.0019207598,0.0031195604,0.13330865],"category_scores_gemma":[0.013599206,0.00077248266,0.0013640819,0.005363408,0.001058865,0.007381915,0.0032153165,0.0038627011,0.099630095],"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":[0.000009217181,0.000022091688,0.00006741856,0.00016778421,0.000006405303,0.000028233046,0.000014487005,0.000044565277,0.000114506765,0.00060163013,0.9650856,0.033838045],"study_design_scores_gemma":[0.0000059943054,0.000031021755,0.00024642,0.0001570598,0.0000086548225,0.00013688994,0.000024440526,0.0001348304,0.00008125543,0.0015457697,0.9976192,0.000008440879],"about_ca_topic_score_codex":0.0003454486,"about_ca_topic_score_gemma":0.0010807918,"teacher_disagreement_score":0.13330865,"about_ca_system_score_codex":0.0009681179,"about_ca_system_score_gemma":0.0015584246,"threshold_uncertainty_score":0.44596183},"labels":[],"label_agreement":null},{"id":"W1966869280","doi":"10.1145/2037676.2037677","title":"Introduction to ACM multimedia 2010 best paper candidates","year":2011,"lang":"en","type":"article","venue":"ACM Transactions on Multimedia Computing Communications and Applications","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Multimedia","score_opus":0.03602298134847868,"score_gpt":0.28226026502377644,"score_spread":0.24623728367529776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966869280","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026682077,0.023401031,0.012750228,0.030304419,0.13730232,0.00096974755,0.018354554,0.0056531653,0.76859635],"genre_scores_gemma":[0.003405697,0.00739569,0.0024677294,0.0019431466,0.014081995,0.00016506697,0.0056484514,0.0010543577,0.9638379],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990809,0.00007823969,0.000058593225,0.00012791165,0.0005006676,0.00015370052],"domain_scores_gemma":[0.99465203,0.00044530333,0.00015409848,0.0002733758,0.0023378087,0.0021373297],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012768673,0.0012850551,0.0011948678,0.00678898,0.0016632202,0.0087975105,0.0014908158,0.0021190858,0.63920546],"category_scores_gemma":[0.0050042407,0.00053435226,0.00073964975,0.006498048,0.0003040707,0.0039713755,0.0018862492,0.0015041742,0.5155413],"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":[0.000046905592,0.000026632064,0.000065270135,0.00012239761,0.0000028716336,0.000038740374,0.000006487052,0.0000751795,0.00029228895,0.0009001748,0.92365825,0.074764736],"study_design_scores_gemma":[0.0000110894025,0.000028521052,0.00026109355,0.000099634395,0.000005435795,0.000058920286,0.000025713993,0.00016990701,0.00022998264,0.00077599974,0.9983235,0.000010277601],"about_ca_topic_score_codex":0.0022907516,"about_ca_topic_score_gemma":0.0070418124,"teacher_disagreement_score":0.63920546,"about_ca_system_score_codex":0.0014773885,"about_ca_system_score_gemma":0.0017914217,"threshold_uncertainty_score":0.5146296},"labels":[],"label_agreement":null},{"id":"W1966922244","doi":"10.1145/1376616.1376751","title":"DiMaC","year":2008,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Missing data; Computer science; Data mining; Information retrieval; Machine learning","score_opus":0.026135039105471623,"score_gpt":0.22987644217365183,"score_spread":0.2037414030681802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966922244","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008331456,0.004959492,0.7144677,0.002866973,0.004696287,0.0004212576,0.023513002,0.074689634,0.1660542],"genre_scores_gemma":[0.12897317,0.0029099644,0.5397557,0.003929801,0.001733759,0.00084190926,0.092165306,0.014045816,0.21564463],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99801457,0.00029453417,0.00008730209,0.0005995284,0.0007945994,0.00020935533],"domain_scores_gemma":[0.99822086,0.00016169934,0.000071064875,0.00073513715,0.0006528986,0.0001583368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018977453,0.0019228077,0.001759817,0.00295701,0.0020730214,0.0052429833,0.00364182,0.002784907,0.15224443],"category_scores_gemma":[0.0046702647,0.0008402446,0.0015047687,0.0023550526,0.0007687755,0.0031933584,0.0042736325,0.0023810894,0.12996686],"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":[0.0006675584,0.00013989628,0.0018720315,0.00041956457,0.0001510245,0.0002127623,0.00011675491,0.009031534,0.0055665527,0.048641913,0.43158275,0.5015977],"study_design_scores_gemma":[0.0001416479,0.00008402436,0.0014196159,0.00012292028,0.00005341596,0.0005821077,0.00015882964,0.12063453,0.013365241,0.057000842,0.8063271,0.00010974174],"about_ca_topic_score_codex":0.0044383374,"about_ca_topic_score_gemma":0.007100411,"teacher_disagreement_score":0.15224443,"about_ca_system_score_codex":0.0012205051,"about_ca_system_score_gemma":0.0020321067,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W1967387730","doi":"10.1016/j.patcog.2014.08.001","title":"Fuzzy rule based decision trees","year":2014,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":85,"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 Natural Science Foundation of China","keywords":"Decision tree; Node (physics); Incremental decision tree; Mathematics; ID3 algorithm; Fuzzy logic; Decision rule; Decision tree learning; Artificial intelligence; Decision stump; Data mining; Computer science; Hyperplane; Oblique case; Fuzzy classification; Fuzzy number; Feature (linguistics); Fuzzy rule; Fuzzy set; Combinatorics","score_opus":0.02359941041331809,"score_gpt":0.25175857148995734,"score_spread":0.22815916107663925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967387730","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024612619,0.0009904805,0.9654937,0.00028262645,0.00015289159,0.00021353347,0.00075281144,0.0009148823,0.006586518],"genre_scores_gemma":[0.39339295,0.0009870287,0.59656847,0.00023079562,0.00015811899,0.00028230206,0.0020525255,0.000095414485,0.0062324153],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99854857,0.00042897378,0.0001385373,0.0002400447,0.0005590976,0.00008468914],"domain_scores_gemma":[0.9968663,0.0021978961,0.0001106043,0.00022420974,0.0005333438,0.00006759596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017806996,0.00056186446,0.0012793313,0.0014939578,0.00056628464,0.0013079279,0.0009918234,0.00092113035,0.0059170797],"category_scores_gemma":[0.0061479146,0.00031241708,0.00097036513,0.0015478963,0.0003391991,0.0014224125,0.00046298432,0.001071695,0.0019176404],"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":[0.00036851107,0.00025603667,0.0020623102,0.00029452756,0.0001888973,0.00025647608,0.00010247353,0.17195222,0.0027207842,0.03097768,0.007489403,0.7833308],"study_design_scores_gemma":[0.000056075416,0.00016061841,0.0005790579,0.0000730892,0.000118561744,0.00016951536,0.00003436322,0.91442335,0.0029239643,0.07468625,0.006750229,0.000024927185],"about_ca_topic_score_codex":0.0011245318,"about_ca_topic_score_gemma":0.0014088704,"teacher_disagreement_score":0.0059170797,"about_ca_system_score_codex":0.0004192189,"about_ca_system_score_gemma":0.00084335124,"threshold_uncertainty_score":0.019794583},"labels":[],"label_agreement":null},{"id":"W1969134570","doi":"10.1088/1742-6596/256/1/012014","title":"CUDA-accelerated genetic feedforward-ANN training for data mining","year":2010,"lang":"en","type":"article","venue":"Journal of Physics Conference Series","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Speedup; Computer science; CUDA; Artificial neural network; Genetic algorithm; Lift (data mining); Genetic programming; Graphics; Context (archaeology); Set (abstract data type); Artificial intelligence; Feed forward; Machine learning; Data mining; Parallel computing; Computer engineering; Computer graphics (images)","score_opus":0.1484255488863258,"score_gpt":0.32663174132118233,"score_spread":0.17820619243485653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969134570","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05898281,0.00036642558,0.9184838,0.00045390538,0.00019100534,0.00013264046,0.0002777294,0.013045132,0.008066481],"genre_scores_gemma":[0.21269163,0.00012589237,0.78276086,0.00013489572,0.000023825476,0.00027158324,0.00048889226,0.0002552521,0.0032471537],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996277,0.00010313099,0.00002571924,0.00006567212,0.00013456283,0.000043249805],"domain_scores_gemma":[0.99901736,0.00033646132,0.00006149696,0.00017251693,0.00036462393,0.000047480586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000599657,0.0007320832,0.00044736787,0.00058464764,0.00062698993,0.000690656,0.0015964533,0.00070962345,0.0035745949],"category_scores_gemma":[0.0032502396,0.00032679076,0.00041018578,0.0012042107,0.00039568247,0.0005599102,0.0005177983,0.0011386952,0.0011504671],"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":[0.0002788219,0.00027195006,0.003922379,0.0001988011,0.00012398692,0.00028689703,0.00017353224,0.5449599,0.009961001,0.010683866,0.018447027,0.4106918],"study_design_scores_gemma":[0.000019612971,0.00001799602,0.0002295031,0.000005052568,0.00000540335,0.000021270178,0.000009503255,0.9935502,0.002749239,0.0014897814,0.0018974354,0.0000050487333],"about_ca_topic_score_codex":0.01479711,"about_ca_topic_score_gemma":0.021314804,"teacher_disagreement_score":0.01479711,"about_ca_system_score_codex":0.00089470984,"about_ca_system_score_gemma":0.0014902423,"threshold_uncertainty_score":0.029421985},"labels":[],"label_agreement":null},{"id":"W1971604907","doi":"10.1145/1189769.1189770","title":"Expressive power of an algebra for data mining","year":2006,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Tuple; Relational algebra; Data mining; Data model (GIS); Relational database; Information retrieval; Theoretical computer science; Algebra over a field; Artificial intelligence; Mathematics; Discrete mathematics","score_opus":0.04314760138777388,"score_gpt":0.2949769826758806,"score_spread":0.25182938128810667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971604907","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013123582,0.0012064434,0.96756905,0.0018655075,0.00011244695,0.00009486209,0.0005946875,0.00053223595,0.01490112],"genre_scores_gemma":[0.34035403,0.001831931,0.64685446,0.001277994,0.0006556034,0.00055812526,0.0016232902,0.0002194492,0.006625156],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99214995,0.0027262531,0.0011550802,0.0012846679,0.002368671,0.0003154164],"domain_scores_gemma":[0.99000376,0.0055053467,0.0006847448,0.0023470656,0.0010431268,0.00041590928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009194762,0.000659631,0.0008335595,0.0017388246,0.0016720496,0.00597976,0.0024840247,0.0013950055,0.0036022456],"category_scores_gemma":[0.012772937,0.00070165,0.002479599,0.0026664382,0.0054518934,0.012588185,0.00388147,0.0038782305,0.0011044861],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002137606,0.000021497495,0.00018275257,0.00007300366,0.000016524284,0.000052398747,0.00026806176,0.001991876,0.0008136031,0.9873696,0.0007066041,0.008482634],"study_design_scores_gemma":[0.000010319063,0.000017573586,0.00005582797,0.000020054205,0.0000104063565,0.00008412787,0.0000491363,0.012067114,0.0005956349,0.9794174,0.00765925,0.000013067641],"about_ca_topic_score_codex":0.0011675557,"about_ca_topic_score_gemma":0.0008031138,"teacher_disagreement_score":0.009194762,"about_ca_system_score_codex":0.00168777,"about_ca_system_score_gemma":0.0017387386,"threshold_uncertainty_score":0.04862714},"labels":[],"label_agreement":null},{"id":"W1972461429","doi":"10.5539/cis.v2n3p58","title":"The Design and Implementation of the Distributed Computing Platform for Bioinformatics","year":2009,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Bottleneck; Upload; Task (project management); Computation; Distributed computing; Process (computing); Decomposition; Operating system; Embedded system; Algorithm","score_opus":0.0208308790787428,"score_gpt":0.29078189788996006,"score_spread":0.26995101881121725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972461429","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007939922,0.00038502202,0.9823987,0.00048386946,0.00024633794,0.00047870356,0.000106894935,0.0034628757,0.0044977074],"genre_scores_gemma":[0.13358366,0.00061964797,0.85737914,0.00031308367,0.00014191712,0.0009806625,0.0006932188,0.00034705375,0.0059416555],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99861574,0.00034206416,0.00011724159,0.00026381647,0.00047481892,0.00018621044],"domain_scores_gemma":[0.9990808,0.00013270715,0.000042306718,0.00020179307,0.00042067637,0.000121757905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017604564,0.0005863349,0.0006236343,0.0007547555,0.001263823,0.002267197,0.0028252567,0.0010133098,0.0026142036],"category_scores_gemma":[0.002788087,0.00050618366,0.00067601487,0.0009552243,0.0007153221,0.0019665023,0.0013890278,0.0019381441,0.001419053],"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":[0.0009003068,0.0005943889,0.00494418,0.0009265812,0.0002225403,0.0011415604,0.00089914113,0.119113415,0.0748836,0.24783656,0.0363537,0.5121841],"study_design_scores_gemma":[0.00040066947,0.0005448252,0.0013297416,0.00018422281,0.00016600628,0.00074894575,0.0002541466,0.68332785,0.071511306,0.058420897,0.18294282,0.00016853595],"about_ca_topic_score_codex":0.002477054,"about_ca_topic_score_gemma":0.0014962151,"teacher_disagreement_score":0.0028252567,"about_ca_system_score_codex":0.0009885173,"about_ca_system_score_gemma":0.00368618,"threshold_uncertainty_score":0.009310305},"labels":[],"label_agreement":null},{"id":"W1972870286","doi":"10.1145/347090.347166","title":"Can we push more constraints into frequent pattern mining?","year":2000,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":191,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Citation; Computer science; Data science; Library science; World Wide Web","score_opus":0.013797217338656732,"score_gpt":0.2539804103553299,"score_spread":0.24018319301667318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972870286","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013002638,0.009926141,0.90298355,0.059687518,0.0026011404,0.00035013634,0.0026422483,0.0030100623,0.0057965633],"genre_scores_gemma":[0.1310818,0.010765234,0.8320078,0.011417066,0.004094565,0.0006477325,0.004121387,0.0011344542,0.0047299615],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9815974,0.007908004,0.0023711312,0.0028331997,0.004755954,0.00053433527],"domain_scores_gemma":[0.8777519,0.091659315,0.005038159,0.01253419,0.010750107,0.0022663393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02113976,0.0020753734,0.0030783082,0.00491877,0.0014692849,0.0067343153,0.0030832335,0.0032841023,0.015150752],"category_scores_gemma":[0.18030898,0.0018463974,0.0028594204,0.0066461256,0.0026492681,0.032177422,0.0059616873,0.006994996,0.007451232],"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":[0.0013078398,0.00041285518,0.009905577,0.0025850558,0.0008626205,0.0005429131,0.00095824734,0.021535033,0.0034967414,0.05187677,0.053141393,0.8533749],"study_design_scores_gemma":[0.0003658469,0.00038495832,0.002906358,0.0014999344,0.0004765161,0.0006752766,0.0010927408,0.1777503,0.0031884278,0.7194772,0.09194032,0.00024220852],"about_ca_topic_score_codex":0.0029679718,"about_ca_topic_score_gemma":0.0037254393,"teacher_disagreement_score":0.02113976,"about_ca_system_score_codex":0.000871788,"about_ca_system_score_gemma":0.0029491447,"threshold_uncertainty_score":0.11179906},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04077503,0.0011011845,0.9467171,0.0024782182,0.00017599875,0.00021099999,0.00036014372,0.00043766727,0.0077437046],"genre_scores_gemma":[0.79888046,0.00274831,0.176283,0.0004790736,0.00050459115,0.0007756779,0.00075149455,0.00024072776,0.019336723],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9951513,0.0020759262,0.00029720605,0.00103437,0.001012831,0.00042832174],"domain_scores_gemma":[0.98586607,0.009124485,0.0011723804,0.0015482573,0.0015458459,0.00074297184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056922375,0.0010651153,0.0026839734,0.0021260837,0.0025314835,0.0055704876,0.007922711,0.0043453495,0.00475095],"category_scores_gemma":[0.023942003,0.0013313605,0.0013347492,0.0039623925,0.003243704,0.008168394,0.0035086698,0.002215834,0.0014140084],"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":[0.00010423092,0.00008460171,0.0009936631,0.0001938781,0.000088393266,0.00026399083,0.00060769106,0.6990098,0.000530084,0.28388074,0.0028201095,0.01142274],"study_design_scores_gemma":[0.000034219902,0.000026929736,0.00015441286,0.000015909816,0.000030009476,0.000083780054,0.00009799179,0.87758243,0.00015059055,0.1203392,0.0014642058,0.000020335037],"about_ca_topic_score_codex":0.008759757,"about_ca_topic_score_gemma":0.0069611156,"teacher_disagreement_score":0.008759757,"about_ca_system_score_codex":0.003104671,"about_ca_system_score_gemma":0.001997167,"threshold_uncertainty_score":0.030103803},"labels":[],"label_agreement":null},{"id":"W1973724352","doi":"10.1145/1133905.1133909","title":"Implementing leap traversals of the itemset lattice","year":2005,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Tree traversal; Header; Computer science; Enumeration; Lattice (music); Traverse; Theoretical computer science; Tree (set theory); Algorithm; Combinatorics; Mathematics; Computer network; Physics","score_opus":0.018810049819788684,"score_gpt":0.27089864581936884,"score_spread":0.25208859599958017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973724352","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06690257,0.00024875245,0.9224256,0.00035538987,0.00006366171,0.0003140986,0.0009192631,0.005725343,0.0030453166],"genre_scores_gemma":[0.1625137,0.00010523839,0.8328347,0.00012528682,0.00002465275,0.00027995114,0.0018911441,0.00029166488,0.001933693],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994197,0.0019046373,0.0007357787,0.00080554606,0.0017670657,0.0005899011],"domain_scores_gemma":[0.9721839,0.017353427,0.001084026,0.0053852666,0.0033973376,0.00059607567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0059795054,0.0008818927,0.0013739399,0.0026883064,0.0013786067,0.004009802,0.003317568,0.0017327088,0.0049883956],"category_scores_gemma":[0.031140275,0.0010859728,0.001419349,0.0048146215,0.0009751362,0.0066890703,0.0033508234,0.0019738756,0.001795473],"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":[0.0014439903,0.00083486625,0.021715948,0.0006130902,0.0003337894,0.00076348335,0.0015243355,0.07894611,0.017278738,0.06530392,0.011768861,0.79947287],"study_design_scores_gemma":[0.00015039378,0.00040692347,0.0013683499,0.00006788418,0.00008866264,0.0007870863,0.0008179222,0.87840474,0.023108546,0.08268128,0.01204013,0.000078129226],"about_ca_topic_score_codex":0.0043089334,"about_ca_topic_score_gemma":0.0073790997,"teacher_disagreement_score":0.0059795054,"about_ca_system_score_codex":0.0010158869,"about_ca_system_score_gemma":0.0024502594,"threshold_uncertainty_score":0.031623065},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045206767,0.0031216904,0.9387853,0.0005631897,0.00040096662,0.00036489175,0.002099721,0.000668155,0.008789389],"genre_scores_gemma":[0.38833877,0.0022537503,0.59616053,0.00058709865,0.0007454078,0.000923077,0.0051826397,0.0001972318,0.005611462],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9895984,0.0018850401,0.0017623209,0.0025479877,0.0037802926,0.00042593863],"domain_scores_gemma":[0.98873156,0.004154519,0.0012577876,0.0026546153,0.0026630107,0.0005384806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047430717,0.0007437362,0.001874827,0.011698879,0.0013157311,0.0051156194,0.0025528811,0.0024731243,0.0038988981],"category_scores_gemma":[0.029129056,0.00035306226,0.0015616792,0.013081081,0.0024794303,0.009679774,0.0032459064,0.0019484857,0.0016329491],"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":[0.00053340464,0.00041827344,0.02348525,0.0016824107,0.00075393694,0.0005963148,0.001421844,0.012402196,0.03142103,0.4322059,0.010525889,0.48455352],"study_design_scores_gemma":[0.00007429229,0.0010050668,0.021629004,0.0005353868,0.0003416663,0.005960668,0.0011411818,0.12685825,0.009745094,0.780867,0.051603366,0.00023901316],"about_ca_topic_score_codex":0.00073313154,"about_ca_topic_score_gemma":0.00069553894,"teacher_disagreement_score":0.011698879,"about_ca_system_score_codex":0.0013687211,"about_ca_system_score_gemma":0.0012609899,"threshold_uncertainty_score":0.025084019},"labels":[],"label_agreement":null},{"id":"W1977379210","doi":"10.1145/1645953.1646148","title":"Diverging patterns","year":2009,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Data mining; Measure (data warehouse); Contrast (vision); Pattern recognition (psychology); Value (mathematics); Artificial intelligence; Algorithm; Machine learning","score_opus":0.010631948343244099,"score_gpt":0.24093961874643421,"score_spread":0.2303076704031901,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977379210","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18648523,0.003744759,0.78516775,0.0012695006,0.0003631094,0.0007123491,0.0037178644,0.001938656,0.016600806],"genre_scores_gemma":[0.58733124,0.0014132614,0.39868942,0.000722841,0.00025665414,0.00071917847,0.0059572635,0.0002726989,0.0046373736],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9940211,0.00071500026,0.0006880547,0.0020346667,0.002181233,0.00035974916],"domain_scores_gemma":[0.9877965,0.0054284753,0.0017136376,0.0022340755,0.002410643,0.00041662727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027673182,0.0011342511,0.0014459223,0.008403166,0.0014524569,0.0032897976,0.0024796464,0.0012809474,0.004406742],"category_scores_gemma":[0.020800512,0.0006143873,0.001155055,0.007394599,0.0015869319,0.005539558,0.0027260557,0.0014641791,0.0013730295],"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":[0.0007487787,0.00031211835,0.108216815,0.0015644677,0.0005660266,0.0040174234,0.0028711094,0.012221087,0.017162543,0.09385132,0.01033876,0.7481296],"study_design_scores_gemma":[0.00014575027,0.0006498568,0.08197591,0.00088161643,0.0006466103,0.018231656,0.0040519703,0.17632124,0.02200034,0.563297,0.13145804,0.00034006752],"about_ca_topic_score_codex":0.0010512638,"about_ca_topic_score_gemma":0.0012034624,"teacher_disagreement_score":0.008403166,"about_ca_system_score_codex":0.0006819012,"about_ca_system_score_gemma":0.0008213519,"threshold_uncertainty_score":0.014742076},"labels":[],"label_agreement":null},{"id":"W1978091735","doi":"10.1145/1809400.1809419","title":"Summary of the first ACM SIGKDD workshop on knowledge discovery from uncertain data (U'09)","year":2010,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Data science; Knowledge extraction; Information retrieval; Data mining","score_opus":0.07323755533522192,"score_gpt":0.30366766048651916,"score_spread":0.23043010515129725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978091735","genre_codex":"editorial","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006606672,0.24069871,0.11929248,0.088022,0.30168122,0.0019243228,0.052067343,0.0080090845,0.18169816],"genre_scores_gemma":[0.02243642,0.16239826,0.04778581,0.010394713,0.05506768,0.0009781147,0.10775742,0.003716509,0.5894651],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980003,0.0004329083,0.00016233599,0.00031334077,0.000924507,0.00016643816],"domain_scores_gemma":[0.988488,0.0019237124,0.00026183593,0.0008106786,0.006671367,0.0018444248],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0051959474,0.001423151,0.0017567496,0.00496995,0.0014150417,0.0055371965,0.001864083,0.0013744837,0.09000779],"category_scores_gemma":[0.008758026,0.00060887216,0.0012360546,0.005481289,0.0005320875,0.003903991,0.0021497633,0.0021303773,0.05761694],"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":[0.000103163795,0.00004323981,0.00013881185,0.00028874728,0.000015544509,0.000032124914,0.000022972943,0.00023726551,0.00025589255,0.00060574524,0.9040582,0.09419821],"study_design_scores_gemma":[0.000029615949,0.00007976595,0.0009775781,0.0003188518,0.000041656273,0.00008250884,0.000064265856,0.000820344,0.00089826906,0.002064766,0.9945912,0.000031192532],"about_ca_topic_score_codex":0.011372737,"about_ca_topic_score_gemma":0.022772761,"teacher_disagreement_score":0.09000779,"about_ca_system_score_codex":0.0018894091,"about_ca_system_score_gemma":0.0030574736,"threshold_uncertainty_score":0.30110604},"labels":[],"label_agreement":null},{"id":"W1979004204","doi":"10.1145/1557626.1557630","title":"Issues in pattern mining and their resolutions","year":2009,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Overfitting; Computer science; Data mining; Reliability (semiconductor); Anomaly detection; Sequential Pattern Mining; Anomaly (physics); Data science; Machine learning; Artificial neural network","score_opus":0.0181417059000252,"score_gpt":0.26754015289245453,"score_spread":0.24939844699242933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979004204","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011444314,0.071333066,0.79491556,0.09134134,0.003237999,0.00029739263,0.0007556944,0.0004936648,0.02618095],"genre_scores_gemma":[0.27117637,0.069645286,0.61717397,0.00824407,0.014602052,0.0010408653,0.0015823513,0.0002489484,0.016286027],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9716627,0.011326637,0.0029921965,0.0043522916,0.00869529,0.00097093766],"domain_scores_gemma":[0.9279494,0.054806843,0.0044711996,0.00707407,0.004739917,0.0009585955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02200253,0.0015027262,0.0025209864,0.0056880964,0.0035238857,0.0136274425,0.0048081665,0.0063772197,0.0052305185],"category_scores_gemma":[0.11425904,0.0021331597,0.0025344493,0.011536146,0.00935232,0.030482205,0.0071058455,0.011807906,0.0024039368],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007237873,0.000084936735,0.0018484584,0.00065146363,0.00011259074,0.00061003957,0.00070513913,0.004266202,0.00032482663,0.81230915,0.013470079,0.16554467],"study_design_scores_gemma":[0.000012450096,0.0000149227435,0.00029529244,0.00015609317,0.000016387834,0.00052553933,0.00033259313,0.008917524,0.0003043753,0.9672527,0.022147488,0.00002468483],"about_ca_topic_score_codex":0.0010829102,"about_ca_topic_score_gemma":0.00045412022,"teacher_disagreement_score":0.02200253,"about_ca_system_score_codex":0.0019425665,"about_ca_system_score_gemma":0.0017694329,"threshold_uncertainty_score":0.116361916},"labels":[],"label_agreement":null},{"id":"W1979516188","doi":"10.5539/cis.v5n1p32","title":"Research and Planning of Application Blueprint for Shanghai Airport Business Intelligence System","year":2011,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Blueprint; Computer science; Business intelligence; Gateway (web page); Architecture; Key (lock); Construct (python library); China; Engineering management; Process management; Knowledge management; Business; Computer security; Engineering; World Wide Web","score_opus":0.09823323312531215,"score_gpt":0.33654083957674025,"score_spread":0.2383076064514281,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979516188","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24732006,0.003237945,0.63969815,0.006999386,0.0002967614,0.001982849,0.0010461473,0.0075970516,0.09182164],"genre_scores_gemma":[0.58251315,0.0025137255,0.3864026,0.0006454205,0.0000946295,0.0006942145,0.003379497,0.00041897222,0.023337796],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99872226,0.0004399514,0.00008667718,0.00016087927,0.0003816907,0.00020846701],"domain_scores_gemma":[0.9984693,0.00021415592,0.00005820465,0.00020779837,0.0008435642,0.00020697345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002285259,0.00052795804,0.00035544572,0.0012466231,0.00063596567,0.0023470928,0.00090606057,0.0006272126,0.004881675],"category_scores_gemma":[0.0024029114,0.0003501669,0.00042169305,0.001586966,0.00036255983,0.0023350315,0.00062557025,0.00068100495,0.0017705187],"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":[0.00049925287,0.00044149053,0.032811146,0.00088732206,0.00008309534,0.0013893925,0.0015273207,0.0333317,0.06272957,0.07018616,0.04557559,0.75053793],"study_design_scores_gemma":[0.00017148585,0.0008156569,0.033528488,0.00035990064,0.000199466,0.0012670038,0.0019724492,0.5249943,0.08504837,0.020766433,0.33076224,0.000114175826],"about_ca_topic_score_codex":0.009100189,"about_ca_topic_score_gemma":0.0061231493,"teacher_disagreement_score":0.009100189,"about_ca_system_score_codex":0.0013331592,"about_ca_system_score_gemma":0.003817552,"threshold_uncertainty_score":0.01809448},"labels":[],"label_agreement":null},{"id":"W1979614540","doi":"","title":"Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining","year":2012,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Knowledge extraction; Data science; Construct (python library); Big data; Field (mathematics); Web mining; Inference; World Wide Web; Artificial intelligence; Web page; Data mining","score_opus":0.09907508012851189,"score_gpt":0.3369918420858378,"score_spread":0.23791676195732592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979614540","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021172391,0.25632656,0.30657718,0.08791807,0.11657178,0.0023392825,0.059554078,0.02692124,0.122619376],"genre_scores_gemma":[0.071633436,0.16946791,0.30948702,0.018740306,0.021436108,0.00203906,0.20276344,0.0041327863,0.20029998],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9916306,0.001911229,0.0010178708,0.0014429315,0.0035624963,0.0004347627],"domain_scores_gemma":[0.98762625,0.0042600473,0.0005925276,0.0026173894,0.0033507182,0.001553082],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007501374,0.0024227835,0.0047873543,0.0066272044,0.0020587093,0.013334467,0.004634887,0.00301936,0.04459837],"category_scores_gemma":[0.018494228,0.0014249791,0.0028880483,0.0056661996,0.0021481426,0.011140358,0.0051874407,0.006124267,0.027846154],"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":[0.00020643896,0.00023617476,0.001932688,0.0008050847,0.00029113502,0.00020407005,0.00018048614,0.0013319177,0.00069803634,0.005843324,0.7162257,0.272045],"study_design_scores_gemma":[0.000051789484,0.00006538312,0.0019236396,0.00045014176,0.00011657559,0.0003793912,0.00024152006,0.0058477633,0.0007040008,0.016288634,0.9738678,0.000063375664],"about_ca_topic_score_codex":0.009668733,"about_ca_topic_score_gemma":0.012257209,"teacher_disagreement_score":0.04459837,"about_ca_system_score_codex":0.0021288819,"about_ca_system_score_gemma":0.0068289437,"threshold_uncertainty_score":0.14919639},"labels":[],"label_agreement":null},{"id":"W1981778103","doi":"10.5430/air.v4n2p1","title":"Heavy path based super-sequence frequent pattern mining on web log dataset","year":2015,"lang":"en","type":"article","venue":"Artificial Intelligence Research","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Path (computing); Sequence (biology); Heuristic; Dynamic programming; Data mining; Graph; Algorithm; Theoretical computer science; Artificial intelligence; Biology","score_opus":0.44111280278568665,"score_gpt":0.4560858783839468,"score_spread":0.014973075598260166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981778103","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84669405,0.0014089694,0.07935067,0.00090452057,0.00018184014,0.0006917487,0.06090647,0.007470719,0.0023909414],"genre_scores_gemma":[0.6318888,0.0006259986,0.22927848,0.00017626472,0.00007457051,0.0007506351,0.13472454,0.00015993499,0.0023207588],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864095,0.00026303856,0.00016361369,0.00038190777,0.00038410097,0.00016648213],"domain_scores_gemma":[0.99673045,0.001577898,0.00035960204,0.0005719171,0.00056634395,0.00019391955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013009822,0.0011026185,0.00093218597,0.00481149,0.001118607,0.000711609,0.0015720804,0.0011734908,0.0012803229],"category_scores_gemma":[0.0045279395,0.00024420998,0.0010066566,0.005637782,0.00038995928,0.0018507413,0.00082170643,0.0012198222,0.00057434535],"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":[0.002184637,0.003498115,0.1129566,0.0020518282,0.0005898944,0.0035329708,0.0006422431,0.14414668,0.016191348,0.007091983,0.088994734,0.61811894],"study_design_scores_gemma":[0.00018775128,0.0003564931,0.022656959,0.000042246233,0.000075510834,0.0012323562,0.00046011747,0.9450179,0.008482644,0.007853728,0.013580362,0.000053959502],"about_ca_topic_score_codex":0.008879299,"about_ca_topic_score_gemma":0.01571134,"teacher_disagreement_score":0.008879299,"about_ca_system_score_codex":0.0007076943,"about_ca_system_score_gemma":0.0015138217,"threshold_uncertainty_score":0.017655253},"labels":[],"label_agreement":null},{"id":"W1982925244","doi":"10.1002/sam.10094","title":"Special issue on the best papers of SDM'10","year":2010,"lang":"en","type":"article","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","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":"Citation; Library science; Computer science; Information retrieval","score_opus":0.05194367942912519,"score_gpt":0.3425082124392971,"score_spread":0.2905645330101719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982925244","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013346015,0.044955537,0.015630016,0.04641785,0.79049426,0.00027127136,0.003501992,0.001420424,0.09597408],"genre_scores_gemma":[0.010435206,0.038281992,0.015575831,0.015777841,0.41266128,0.000334563,0.008466535,0.002651616,0.49581513],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99602354,0.00061613054,0.0003705468,0.0005594409,0.0021173966,0.00031294118],"domain_scores_gemma":[0.98478055,0.002701741,0.00080956594,0.0015945253,0.0071986564,0.0029149002],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005369399,0.0018590993,0.0024450598,0.0073137158,0.0017743567,0.009073788,0.0024868217,0.0025563098,0.12161495],"category_scores_gemma":[0.016767241,0.0006702429,0.001547108,0.0072542047,0.00092798553,0.003927201,0.0032256073,0.0032366966,0.0722213],"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":[0.000049106355,0.000032731357,0.00013400262,0.0002552406,0.00001815018,0.000032884796,0.000009103866,0.0001602401,0.00021834426,0.001933864,0.94016963,0.056986734],"study_design_scores_gemma":[0.000021812553,0.000050057162,0.0004528336,0.0002407441,0.00002267318,0.00009610502,0.000021163964,0.00049752754,0.0002740622,0.0048456746,0.99346185,0.000015439915],"about_ca_topic_score_codex":0.0015769198,"about_ca_topic_score_gemma":0.0041284026,"teacher_disagreement_score":0.12161495,"about_ca_system_score_codex":0.0032265256,"about_ca_system_score_gemma":0.0045278193,"threshold_uncertainty_score":0.40684253},"labels":[],"label_agreement":null},{"id":"W1983035395","doi":"10.1016/j.camwa.2012.01.045","title":"Max-FISM: Mining (recently) maximal frequent itemsets over data streams using the sliding window model","year":2012,"lang":"en","type":"article","venue":"Computers & Mathematics with Applications","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Sliding window protocol; Data stream mining; Data mining; Data stream; Computer science; Database transaction; Stock market prediction; Set (abstract data type); Trie; Data set; Prefix; Window (computing); Tree (set theory); Algorithm; Data structure; Stock market; Mathematics; Artificial intelligence; Database","score_opus":0.08426415759424052,"score_gpt":0.30745979556849545,"score_spread":0.22319563797425493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983035395","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04152128,0.0014390382,0.944104,0.00022409714,0.0001857106,0.00034918473,0.0032993704,0.008005005,0.00087220414],"genre_scores_gemma":[0.14834823,0.00045971296,0.8436146,0.00010533049,0.00013855021,0.00037838655,0.0052407742,0.0002734335,0.0014411154],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998692,0.0002348772,0.00020327761,0.0003780143,0.00038054152,0.00011146728],"domain_scores_gemma":[0.99704427,0.00162882,0.0002065344,0.0005415102,0.00046012786,0.00011869835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033712892,0.0013903208,0.0020179045,0.0052759657,0.00086264475,0.001620154,0.0030051544,0.0013393997,0.003489551],"category_scores_gemma":[0.0105952835,0.00076079095,0.002047862,0.004692852,0.00045872835,0.0033122338,0.0012906903,0.0010291835,0.0016513058],"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":[0.0017159401,0.00031580505,0.014507449,0.0011395137,0.0007272915,0.00069458305,0.00030706867,0.043425582,0.011228496,0.0071834866,0.012236185,0.90651864],"study_design_scores_gemma":[0.00012316834,0.0003828121,0.004265492,0.00010423397,0.00020705296,0.00086821476,0.00015542521,0.9511435,0.011889486,0.021728469,0.009080363,0.000051767336],"about_ca_topic_score_codex":0.0023192985,"about_ca_topic_score_gemma":0.0028088505,"teacher_disagreement_score":0.0052759657,"about_ca_system_score_codex":0.00043956336,"about_ca_system_score_gemma":0.0013744268,"threshold_uncertainty_score":0.01782924},"labels":[],"label_agreement":null},{"id":"W1983506100","doi":"10.1145/568574.568581","title":"Exploiting succinct constraints using FP-trees","year":2002,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":76,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Pruning; Focus (optics); Succinctness; Set (abstract data type); Constraint (computer-aided design); Tree (set theory); Data mining; Search tree; Theoretical computer science; Algorithm; Search algorithm; Programming language; Mathematics","score_opus":0.10287589201954778,"score_gpt":0.27695920445099,"score_spread":0.1740833124314422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983506100","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00737023,0.0003073197,0.989903,0.0002476,0.000029363111,0.00013334987,0.0003866487,0.0008555032,0.0007670429],"genre_scores_gemma":[0.08521721,0.0004970855,0.9115506,0.00016320622,0.000059341175,0.00029267807,0.0015436935,0.00012857986,0.0005476437],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99404573,0.001790674,0.00070102006,0.00069201563,0.0024791036,0.000291416],"domain_scores_gemma":[0.9775859,0.016517643,0.00151171,0.0017826247,0.0023685659,0.00023344714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046906765,0.0016737212,0.001810835,0.0043124147,0.0012742863,0.0028013894,0.0024691583,0.0016757279,0.0023379715],"category_scores_gemma":[0.031805936,0.00094399066,0.0015978158,0.005396755,0.0010135904,0.0067943516,0.002222359,0.0018919448,0.0010084267],"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":[0.000500514,0.00021639184,0.0050023748,0.00072677236,0.00021960548,0.0012306005,0.00047235077,0.1828321,0.006213338,0.07130087,0.009889776,0.7213953],"study_design_scores_gemma":[0.000070732865,0.00009748056,0.00033253443,0.00012705462,0.00006486352,0.0007152213,0.00010772121,0.8250488,0.007830206,0.15744247,0.0081114825,0.000051313415],"about_ca_topic_score_codex":0.0035741904,"about_ca_topic_score_gemma":0.0035394735,"teacher_disagreement_score":0.0046906765,"about_ca_system_score_codex":0.0008563449,"about_ca_system_score_gemma":0.0024009713,"threshold_uncertainty_score":0.024806976},"labels":[],"label_agreement":null},{"id":"W1983930501","doi":"10.1109/cicare.2013.6583073","title":"Activity pattern mining using temporal relationships in a smart home","year":2013,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Home automation; Computer science; Activities of daily living; Activity recognition; Real-time computing; Data mining; Machine learning; Medicine; Telecommunications","score_opus":0.06792001559255152,"score_gpt":0.2734992956173723,"score_spread":0.2055792800248208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983930501","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39500275,0.00085410586,0.598728,0.00038158655,0.000047035264,0.00016513112,0.0016553627,0.001399375,0.0017665792],"genre_scores_gemma":[0.75677687,0.0003878769,0.2402675,0.00006545448,0.000027073458,0.000105684674,0.0015256689,0.000021450922,0.0008225046],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999419,0.00009698457,0.000082772276,0.00019822699,0.00016667013,0.000036322283],"domain_scores_gemma":[0.9993648,0.00027542602,0.00014271657,0.000081438135,0.000091074704,0.000044559267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005143601,0.0002839145,0.000503421,0.0018678966,0.00029359836,0.0006027418,0.0005091541,0.00035220082,0.00058150245],"category_scores_gemma":[0.002098842,0.00021979386,0.00040753404,0.002126957,0.00023242741,0.0008889485,0.00041227782,0.00027695365,0.0002630542],"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":[0.0008846744,0.0008769116,0.07457278,0.00035314896,0.0002901123,0.0023843297,0.0007163277,0.12456101,0.036565743,0.00783131,0.0036583142,0.74730533],"study_design_scores_gemma":[0.000039384497,0.00022539884,0.018156031,0.000032967037,0.000092636445,0.0012528853,0.0002649184,0.95670265,0.009028687,0.010173619,0.0040052263,0.00002554207],"about_ca_topic_score_codex":0.0033831915,"about_ca_topic_score_gemma":0.004580723,"teacher_disagreement_score":0.0033831915,"about_ca_system_score_codex":0.0002115652,"about_ca_system_score_gemma":0.00051090715,"threshold_uncertainty_score":0.00672698},"labels":[],"label_agreement":null},{"id":"W1984606279","doi":"10.1145/380995.381002","title":"Mining frequent patterns by pattern-growth","year":2000,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":275,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Citation; Computer science; Data science; Library science","score_opus":0.021176622480086907,"score_gpt":0.24134360734380278,"score_spread":0.2201669848637159,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984606279","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025043061,0.0016388288,0.9662091,0.00079220696,0.000093214425,0.0005261056,0.0015344524,0.0019213783,0.0022416462],"genre_scores_gemma":[0.13158353,0.0015726336,0.86049795,0.00018635526,0.00009400722,0.0005125562,0.004078292,0.00015621894,0.0013184953],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958681,0.0009225828,0.00042128892,0.00073894486,0.0018359311,0.00021314566],"domain_scores_gemma":[0.98811394,0.006898399,0.0011147555,0.0013944535,0.0022594305,0.00021910683],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003352601,0.0010965745,0.0013067718,0.006404358,0.0008679016,0.0022410366,0.001899173,0.0010796053,0.0012786326],"category_scores_gemma":[0.018150112,0.00073991134,0.0018015167,0.007458903,0.0009778626,0.004002722,0.002000979,0.0016957959,0.0014638598],"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":[0.0002769898,0.00032199966,0.029028017,0.0011110074,0.00034141622,0.0015167544,0.00076330645,0.0817604,0.013803352,0.041906968,0.014282743,0.814887],"study_design_scores_gemma":[0.00005029027,0.0001738079,0.004046618,0.0001739515,0.000097859105,0.0017077613,0.00042963584,0.8662623,0.010301918,0.09585565,0.020836938,0.00006329585],"about_ca_topic_score_codex":0.0017568693,"about_ca_topic_score_gemma":0.00199644,"teacher_disagreement_score":0.006404358,"about_ca_system_score_codex":0.0006866153,"about_ca_system_score_gemma":0.0011202593,"threshold_uncertainty_score":0.017730415},"labels":[],"label_agreement":null},{"id":"W1985089860","doi":"10.1016/j.knosys.2012.08.010","title":"Context Based Positive and Negative Spatio-Temporal Association Rule Mining","year":2012,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":62,"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":"Association rule learning; Apriori algorithm; Data mining; Computer science; Context (archaeology); A priori and a posteriori; Association (psychology); Pruning; K-optimal pattern discovery; Geography","score_opus":0.0193485904430036,"score_gpt":0.25692828582641775,"score_spread":0.23757969538341414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985089860","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3536851,0.0033360287,0.6301355,0.0006204989,0.00048493466,0.00031236757,0.001320182,0.0009077882,0.0091976],"genre_scores_gemma":[0.8380749,0.00044218628,0.15795259,0.00015711176,0.00014665781,0.00011094472,0.000974818,0.000033114826,0.0021076594],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975236,0.00059842045,0.00027932567,0.0004917574,0.00095087494,0.00015607812],"domain_scores_gemma":[0.9938775,0.0034698509,0.0004052025,0.0005383852,0.0014763372,0.00023268201],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027475646,0.00057322776,0.0009257972,0.0022049116,0.0010703997,0.001588458,0.0013878722,0.00097111985,0.0018580244],"category_scores_gemma":[0.013137792,0.00031139623,0.0007817362,0.0018492119,0.0007091475,0.0019845548,0.0012975668,0.0008398252,0.0006139413],"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":[0.0046656644,0.001055725,0.09316422,0.0010617884,0.00067590666,0.0040465584,0.00087126484,0.041941922,0.031809475,0.036938254,0.008275295,0.7754939],"study_design_scores_gemma":[0.00015505325,0.0004867764,0.016043928,0.00014561863,0.00057943584,0.0042216494,0.0005132605,0.9126951,0.01669307,0.04010303,0.0082711475,0.000091959715],"about_ca_topic_score_codex":0.0017528005,"about_ca_topic_score_gemma":0.0050546383,"teacher_disagreement_score":0.0027475646,"about_ca_system_score_codex":0.00032228776,"about_ca_system_score_gemma":0.0008649449,"threshold_uncertainty_score":0.014530718},"labels":[],"label_agreement":null},{"id":"W1985318087","doi":"10.1145/1806338.1806411","title":"Mining online shopping patterns and communities","year":2009,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Association rule learning; Competitive advantage; Focus (optics); Computer science; Cluster analysis; Data science; Business; Data mining; Marketing; Artificial intelligence","score_opus":0.03972024582799476,"score_gpt":0.2817035417665,"score_spread":0.2419832959385052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985318087","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87273306,0.0017024698,0.100820415,0.00073809165,0.000119874276,0.0008154996,0.01209472,0.0015112491,0.0094646495],"genre_scores_gemma":[0.84610415,0.00061582,0.13675265,0.00012563165,0.00009136419,0.00033022097,0.0126044545,0.00010401362,0.0032717467],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998429,0.0002696547,0.00013008177,0.00048210216,0.000497971,0.00019111301],"domain_scores_gemma":[0.9964232,0.0014054108,0.0005140426,0.00043251982,0.00079658895,0.00042817526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093408464,0.00059074874,0.0008119483,0.01478231,0.0016340332,0.0020504205,0.0009787187,0.00116453,0.002312601],"category_scores_gemma":[0.0073271166,0.0004960766,0.0011250622,0.008981621,0.00059097423,0.0024174165,0.0017558619,0.00060991355,0.0011102146],"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":[0.0012064724,0.0020743099,0.34535414,0.0014816645,0.0009659887,0.0033964298,0.00483399,0.022342807,0.014693217,0.02287409,0.02583885,0.55493796],"study_design_scores_gemma":[0.00017664922,0.00056768145,0.2415382,0.00048195847,0.0005959128,0.006192396,0.010611444,0.5821031,0.010092404,0.095312975,0.05208855,0.0002388285],"about_ca_topic_score_codex":0.008671045,"about_ca_topic_score_gemma":0.015650384,"teacher_disagreement_score":0.01478231,"about_ca_system_score_codex":0.00055944506,"about_ca_system_score_gemma":0.0011986198,"threshold_uncertainty_score":0.01724112},"labels":[],"label_agreement":null},{"id":"W1985543266","doi":"10.1145/1620432.1620444","title":"Mining uncertain data for constrained frequent sets","year":2009,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Data mining; Association rule learning; Database transaction; Set (abstract data type); Casual; Uncertain data; Transaction data; Data stream mining; Process (computing); Information retrieval; Database","score_opus":0.08353128089340979,"score_gpt":0.34008053381014536,"score_spread":0.2565492529167356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985543266","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027265586,0.00063473603,0.970042,0.00033029498,0.000040534345,0.00012631595,0.00040342892,0.00045009094,0.00070691435],"genre_scores_gemma":[0.23994541,0.00061910547,0.7570932,0.0001843995,0.00011216492,0.00030480634,0.0013161136,0.00006253924,0.00036222494],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.994676,0.0015464302,0.0007003523,0.00075124146,0.0021285715,0.00019750273],"domain_scores_gemma":[0.9818287,0.013393462,0.0015181332,0.0014633213,0.0015795575,0.00021670265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041289595,0.00057259324,0.0015948693,0.0036500234,0.0011642539,0.0024098791,0.0016275878,0.0011740861,0.0014111579],"category_scores_gemma":[0.032498434,0.00058188115,0.0013531832,0.0039703194,0.00093585777,0.004172889,0.002302935,0.0011110657,0.00049685675],"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":[0.0010417677,0.00028769227,0.016270889,0.0011834436,0.00046788453,0.0040737134,0.002059392,0.23905595,0.013533091,0.15155023,0.008825668,0.5616503],"study_design_scores_gemma":[0.00006525285,0.00011212991,0.0012542557,0.00015366267,0.00007658907,0.0012090321,0.00030823468,0.83952695,0.004349366,0.14398175,0.008905998,0.000056785182],"about_ca_topic_score_codex":0.0010444297,"about_ca_topic_score_gemma":0.0011474098,"teacher_disagreement_score":0.0041289595,"about_ca_system_score_codex":0.0005127884,"about_ca_system_score_gemma":0.0010743416,"threshold_uncertainty_score":0.02183628},"labels":[],"label_agreement":null},{"id":"W1986244770","doi":"10.1155/2013/790160","title":"Data Mining and Knowledge Discovery in Industrial Engineering","year":2013,"lang":"en","type":"article","venue":"Mathematical Problems in Engineering","topic":"Data Mining Algorithms 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 Alberta","funders":"","keywords":"Knowledge extraction; Data science; Computer science; Engineering; Data mining","score_opus":0.04987662620668604,"score_gpt":0.2508070764253217,"score_spread":0.20093045021863565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986244770","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03322652,0.10928802,0.81079495,0.023397708,0.001173365,0.0001864123,0.0007611226,0.00038239214,0.020789461],"genre_scores_gemma":[0.4685547,0.072845995,0.43947834,0.0021167905,0.002060906,0.00038796285,0.0011989233,0.000086471075,0.013269917],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99782336,0.00076443213,0.00025341133,0.00034503255,0.0007329407,0.000080846345],"domain_scores_gemma":[0.9928173,0.005714396,0.00046042178,0.00042316402,0.00047312598,0.00011162564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031157874,0.0005855229,0.0012605673,0.0030257297,0.0008862034,0.0038397212,0.0016903807,0.0016001337,0.003330008],"category_scores_gemma":[0.013030445,0.00046712207,0.00089837326,0.004705531,0.0029804178,0.005776918,0.0016859712,0.0020031522,0.0010496781],"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":[0.00013420118,0.00025382388,0.005207758,0.0023546943,0.00014512007,0.00031261554,0.00042450317,0.038876407,0.0011565739,0.5206621,0.015355116,0.41511706],"study_design_scores_gemma":[0.000023021157,0.00003541782,0.0011750687,0.0002863834,0.000044421522,0.00016638916,0.00022349213,0.09584375,0.0013408652,0.8668266,0.034007195,0.000027322609],"about_ca_topic_score_codex":0.0022262756,"about_ca_topic_score_gemma":0.0016357898,"teacher_disagreement_score":0.0038397212,"about_ca_system_score_codex":0.0017971419,"about_ca_system_score_gemma":0.0022881266,"threshold_uncertainty_score":0.016478062},"labels":[],"label_agreement":null},{"id":"W1986684738","doi":"10.5539/cis.v1n3p112","title":"New Path Filling Method on Data Preprocessing in Web Mining","year":2008,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Font; Computer science; Preprocessor; Face (sociological concept); Artificial intelligence","score_opus":0.06100829919138898,"score_gpt":0.32150284737799073,"score_spread":0.2604945481866017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986684738","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042304527,0.00022727504,0.9841307,0.00017708083,0.00012508266,0.00019692231,0.0009221606,0.009202967,0.0007874767],"genre_scores_gemma":[0.020026041,0.00012031093,0.9751286,0.000087529894,0.000043620417,0.0002000637,0.0018295214,0.000507017,0.0020572266],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975236,0.0004955278,0.0003688991,0.00067388883,0.0008107152,0.00012728671],"domain_scores_gemma":[0.9955848,0.0020328257,0.0001972777,0.0010300514,0.0009950602,0.00016007498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022425342,0.0011935851,0.0014711939,0.004756195,0.0016019624,0.0021679169,0.0021807773,0.0013358174,0.010118866],"category_scores_gemma":[0.0077894786,0.00091116194,0.0019133777,0.0055778488,0.0007620353,0.0040228376,0.0022520304,0.002027614,0.004022788],"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":[0.00029161587,0.00023845727,0.0021897028,0.00037549133,0.00010918348,0.00030226645,0.0002790258,0.0075580417,0.008885931,0.011479581,0.019466244,0.9488244],"study_design_scores_gemma":[0.00022053641,0.00020378125,0.0023699861,0.00017216556,0.00018930087,0.0010575617,0.0004012255,0.79022914,0.042227842,0.07516078,0.087652445,0.00011525439],"about_ca_topic_score_codex":0.0036943902,"about_ca_topic_score_gemma":0.004107301,"teacher_disagreement_score":0.010118866,"about_ca_system_score_codex":0.0007049103,"about_ca_system_score_gemma":0.0024969212,"threshold_uncertainty_score":0.033851027},"labels":[],"label_agreement":null},{"id":"W1986871321","doi":"10.1145/362084.362142","title":"Knowledge discovery in data warehouses","year":2000,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Online analytical processing; Data warehouse; Automatic summarization; Terabyte; Knowledge extraction; Data mining; Process (computing); Data science; Information retrieval; Database","score_opus":0.06937896728329003,"score_gpt":0.3180131510689414,"score_spread":0.24863418378565139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986871321","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015636725,0.011949938,0.9507564,0.005821237,0.00027723509,0.00060711976,0.0034066807,0.0022765796,0.009268159],"genre_scores_gemma":[0.10384506,0.009233894,0.87621295,0.0013216918,0.00025523466,0.00045856403,0.0056927963,0.00017628861,0.0028034598],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98622257,0.0046819965,0.0018201215,0.0019953547,0.0047801565,0.00049977476],"domain_scores_gemma":[0.9754484,0.015392447,0.0013439809,0.0047803395,0.0024713958,0.00056336186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012709628,0.0010738703,0.002919577,0.012086702,0.0023036494,0.014161332,0.004637019,0.0022897068,0.0024289328],"category_scores_gemma":[0.039689656,0.0019351994,0.003017743,0.019263865,0.0028625492,0.017575229,0.0065029846,0.003447293,0.0018548851],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002697584,0.00034005602,0.008212704,0.0036792392,0.00092464976,0.0020725704,0.0034128346,0.05289418,0.00259275,0.45177203,0.02502171,0.44880757],"study_design_scores_gemma":[0.000051805782,0.000053456293,0.0009790881,0.0005878833,0.00017048279,0.0008758942,0.0014026276,0.16042301,0.003199575,0.7658007,0.06637292,0.00008244615],"about_ca_topic_score_codex":0.003744675,"about_ca_topic_score_gemma":0.00376621,"teacher_disagreement_score":0.014161332,"about_ca_system_score_codex":0.0021198038,"about_ca_system_score_gemma":0.0029144345,"threshold_uncertainty_score":0.06721574},"labels":[],"label_agreement":null},{"id":"W1987787956","doi":"10.1145/1281192.1281294","title":"Cleaning disguised missing data","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Missing data; Outlier; Anomaly detection; Computer science; Data mining; Data quality; Anomaly (physics); Statistics; Artificial intelligence; Mathematics; Machine learning; Engineering","score_opus":0.06706517474363113,"score_gpt":0.32922223021988334,"score_spread":0.26215705547625223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987787956","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059324704,0.0016598689,0.92499757,0.0010505536,0.000762786,0.00027580737,0.006985664,0.0036090938,0.0013338096],"genre_scores_gemma":[0.44230992,0.0012247121,0.5263528,0.0010537058,0.0004525523,0.0007502959,0.024034707,0.0011694095,0.0026518812],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97907877,0.0062817764,0.0031684202,0.0044424213,0.0059768315,0.001051654],"domain_scores_gemma":[0.89790595,0.04006054,0.012601304,0.03271887,0.015870253,0.0008431244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023671376,0.0015838321,0.0031167236,0.0060761687,0.0017727484,0.0025950305,0.003968583,0.0022685176,0.0027254245],"category_scores_gemma":[0.10556452,0.0009983825,0.0017879001,0.011175655,0.001675124,0.00375765,0.004274694,0.0038113534,0.0018221247],"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":[0.003220239,0.0005742772,0.12896432,0.0048494306,0.0011676989,0.0049745403,0.00626053,0.044032905,0.023830561,0.030411888,0.05486888,0.6968449],"study_design_scores_gemma":[0.00040015642,0.0010355104,0.07748143,0.002579334,0.0011590101,0.010973905,0.0059626834,0.34400785,0.10979168,0.25671804,0.18918185,0.0007084981],"about_ca_topic_score_codex":0.0020904974,"about_ca_topic_score_gemma":0.0022262777,"teacher_disagreement_score":0.023671376,"about_ca_system_score_codex":0.0008793615,"about_ca_system_score_gemma":0.002722136,"threshold_uncertainty_score":0.1251877},"labels":[],"label_agreement":null},{"id":"W1989568163","doi":"10.5626/jcse.2007.1.2.177","title":"A Data Mining Approach for Selecting Bitmap Join Indices","year":2007,"lang":"en","type":"article","venue":"Journal of Computing Science and Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec en Outaouais","funders":"","keywords":"Computer science; Bitmap; Data mining; Data warehouse; Joins; Pruning; Join (topology); Hash join; Selection (genetic algorithm); Star schema; Sort-merge join; Dimension (graph theory); Tuple; Search engine indexing; Database; Information retrieval; Relational database; Mathematics; Artificial intelligence; Database design","score_opus":0.036787878370733905,"score_gpt":0.29201758497302854,"score_spread":0.25522970660229466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989568163","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02147159,0.00056062744,0.9730166,0.00046065933,0.00006783699,0.0006974733,0.0004674574,0.0014457462,0.0018119415],"genre_scores_gemma":[0.05411412,0.00031444692,0.943619,0.00014789985,0.00003330659,0.00033038214,0.0008183832,0.0000646505,0.00055781106],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964281,0.0005083869,0.0004095762,0.0007277376,0.0017193456,0.00020680971],"domain_scores_gemma":[0.99490017,0.0014146065,0.00071735994,0.00072526175,0.0020765853,0.00016615297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028083634,0.0015095738,0.0015761639,0.004589629,0.0018203892,0.0031604501,0.0036285715,0.0014070187,0.0012013803],"category_scores_gemma":[0.009629663,0.0009875101,0.0014777243,0.0061497674,0.0007108905,0.0046551456,0.0018455224,0.0020500838,0.0010660315],"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":[0.0005671114,0.0008975325,0.015871162,0.00071049435,0.00020697773,0.00043152308,0.0006707463,0.07999743,0.058874242,0.038821634,0.011921115,0.79103],"study_design_scores_gemma":[0.00009375304,0.0003527997,0.002295959,0.00009731274,0.00009309001,0.0008581961,0.0002563585,0.934977,0.027209885,0.020881204,0.012803425,0.00008101186],"about_ca_topic_score_codex":0.0020829034,"about_ca_topic_score_gemma":0.0043841386,"teacher_disagreement_score":0.004589629,"about_ca_system_score_codex":0.0010348413,"about_ca_system_score_gemma":0.0032170408,"threshold_uncertainty_score":0.014852226},"labels":[],"label_agreement":null},{"id":"W1991263523","doi":"10.1007/s10664-009-9110-3","title":"Guest editors introduction: special issue on mining software repositories","year":2009,"lang":"en","type":"article","venue":"Empirical Software Engineering","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":"Queen's University","funders":"European Metrology Programme for Innovation and Research","keywords":"Computer science; Software engineering; Data science; World Wide Web","score_opus":0.010820047409559233,"score_gpt":0.25210937070345196,"score_spread":0.24128932329389274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991263523","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00045453454,0.0074629127,0.0028807605,0.026004761,0.95426404,0.000058868027,0.0004035886,0.0004639744,0.008006459],"genre_scores_gemma":[0.002245732,0.006553637,0.0014017546,0.0067590284,0.9222661,0.000056464476,0.00065735204,0.00048210987,0.059577834],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99791104,0.0002763702,0.00026809334,0.00045647335,0.0009027547,0.00018517795],"domain_scores_gemma":[0.98350936,0.003057927,0.0013153397,0.000869219,0.007769425,0.0034787436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003779316,0.0023250808,0.0027029738,0.006508915,0.0017188346,0.007010654,0.002161064,0.0032197484,0.080812156],"category_scores_gemma":[0.012247809,0.0008770917,0.001339563,0.0033141093,0.00068533816,0.005481078,0.0031442584,0.004880225,0.040135864],"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":[0.000028725985,0.000018334555,0.00012597951,0.00013256034,0.000009895297,0.00007192054,0.000009889287,0.000047354635,0.00019548707,0.00027850852,0.9787541,0.020327175],"study_design_scores_gemma":[0.000038284223,0.00009159163,0.0010495943,0.00018003046,0.000039400926,0.00035715345,0.000049923612,0.0004727038,0.00041097114,0.0017093752,0.995572,0.000028921691],"about_ca_topic_score_codex":0.00054485374,"about_ca_topic_score_gemma":0.002137423,"teacher_disagreement_score":0.080812156,"about_ca_system_score_codex":0.0009264868,"about_ca_system_score_gemma":0.0012325682,"threshold_uncertainty_score":0.2703436},"labels":[],"label_agreement":null},{"id":"W1992887625","doi":"10.1145/1014052.1014119","title":"A microeconomic data mining problem","year":2004,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Ministerio de Economía y Competitividad","keywords":"Computer science; Market segmentation; Segmentation; Greedy algorithm; Product (mathematics); Function (biology); Data mining; Algorithm; Artificial intelligence; Mathematics; Marketing","score_opus":0.040323895413509836,"score_gpt":0.27193510764522816,"score_spread":0.23161121223171832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992887625","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06445373,0.002923368,0.8805011,0.023507606,0.0004339842,0.00090541,0.003940755,0.0002795487,0.0230545],"genre_scores_gemma":[0.5865753,0.0026554042,0.38985628,0.0023972986,0.0009588101,0.0013579521,0.002849118,0.00010784767,0.013241944],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965417,0.0016338883,0.00021180848,0.0008767471,0.00051648077,0.0002192637],"domain_scores_gemma":[0.98512065,0.012809988,0.00072253915,0.00051307696,0.0005154817,0.0003182951],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052500833,0.0010844651,0.0024398689,0.0018788922,0.0013747246,0.0045070425,0.0031259984,0.004565607,0.006558505],"category_scores_gemma":[0.018161293,0.0009137266,0.0013177413,0.0041541443,0.0024424698,0.0050559547,0.001941523,0.0033649893,0.00074935355],"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":[0.00021147686,0.00037758096,0.004914127,0.00053471274,0.0002417024,0.0006673054,0.00025416593,0.43481946,0.00033387198,0.4765144,0.01990389,0.06122733],"study_design_scores_gemma":[0.00008105448,0.00003930363,0.00057440315,0.000048751073,0.00003479374,0.00018257825,0.00013976257,0.6309876,0.00022175837,0.35856423,0.0091030365,0.00002270604],"about_ca_topic_score_codex":0.003543608,"about_ca_topic_score_gemma":0.003087507,"teacher_disagreement_score":0.006558505,"about_ca_system_score_codex":0.0030582324,"about_ca_system_score_gemma":0.002737986,"threshold_uncertainty_score":0.027765393},"labels":[],"label_agreement":null},{"id":"W1993246951","doi":"10.1016/j.ins.2003.03.015","title":"CLIP4: Hybrid inductive machine learning algorithm that generates inequality rules","year":2003,"lang":"en","type":"article","venue":"Information Sciences","topic":"Data Mining Algorithms and Applications","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":"University of Alberta","funders":"","keywords":"Computer science; Pruning; Missing data; Algorithm; Feature (linguistics); Inductive bias; Tree (set theory); Data mining; Benchmarking; Machine learning; Artificial intelligence; Mathematics; Multi-task learning","score_opus":0.0490641143084704,"score_gpt":0.28807386267861396,"score_spread":0.23900974837014355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993246951","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0149208335,0.00014743519,0.96469694,0.00032098498,0.00012123212,0.00031416563,0.0022972547,0.0100969365,0.0070842328],"genre_scores_gemma":[0.11259694,0.00012512237,0.87076294,0.0003717808,0.00011612191,0.00071312813,0.007494273,0.00084812957,0.006971495],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998919,0.0002107998,0.00006253674,0.00020939924,0.0004971688,0.00010108827],"domain_scores_gemma":[0.9966407,0.0020612867,0.000093734525,0.00033542502,0.00076427794,0.00010457311],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018626623,0.0011520891,0.0011149463,0.003596855,0.0011271535,0.0011931033,0.0032470746,0.0012874784,0.02010374],"category_scores_gemma":[0.008301367,0.0005232969,0.0010837322,0.0022867739,0.00071706116,0.0014579298,0.0024301624,0.0019901462,0.0036416224],"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":[0.0005285636,0.0004340519,0.005317377,0.00056099985,0.00016554966,0.00046282684,0.00015491364,0.054554425,0.005096053,0.021451967,0.06041208,0.8508612],"study_design_scores_gemma":[0.00012843305,0.00011205838,0.0008894232,0.00006797656,0.000059279693,0.00020165333,0.00007300433,0.941636,0.011236803,0.028763553,0.016806033,0.000025746744],"about_ca_topic_score_codex":0.0034350127,"about_ca_topic_score_gemma":0.0070724026,"teacher_disagreement_score":0.02010374,"about_ca_system_score_codex":0.00084491534,"about_ca_system_score_gemma":0.002068986,"threshold_uncertainty_score":0.06725377},"labels":[],"label_agreement":null},{"id":"W1994599362","doi":"10.1016/j.ipl.2013.07.016","title":"P2P-FISM: Mining (recently) frequent item sets from distributed data streams over P2P network","year":2013,"lang":"en","type":"article","venue":"Information Processing Letters","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"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; Scalability; Asynchronous communication; Distributed computing; Data stream mining; Overhead (engineering); File sharing; Data stream; Distributed database; Computer network; Network topology; Peer-to-peer; Data mining; Database; The Internet; World Wide Web","score_opus":0.020568116366212537,"score_gpt":0.24554403671266442,"score_spread":0.2249759203464519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994599362","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061055183,0.0011156925,0.91288996,0.0007149157,0.00029083266,0.0005445084,0.0041342205,0.017363442,0.0018912298],"genre_scores_gemma":[0.32871443,0.00048376885,0.6625767,0.00020008707,0.00021203843,0.00040395313,0.0051271995,0.00024620804,0.0020357943],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99927825,0.00010785222,0.00007221284,0.00020453974,0.0002742819,0.00006285141],"domain_scores_gemma":[0.99778193,0.001158216,0.0001391336,0.00047885897,0.00035064018,0.000091222115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013997143,0.0013615335,0.0012918672,0.0031573556,0.0009910502,0.0013609119,0.0023860876,0.0011875271,0.002355558],"category_scores_gemma":[0.0064263274,0.0004957913,0.0007356107,0.0039450787,0.00047368472,0.0021649841,0.0012837761,0.001021637,0.0011547557],"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":[0.0016508913,0.0003981417,0.017991472,0.0006668127,0.00043148396,0.0015839619,0.0002620409,0.07076203,0.014516106,0.0059314654,0.028794982,0.85701054],"study_design_scores_gemma":[0.000072464856,0.00010472164,0.0018855127,0.000017981816,0.00005278053,0.00055821164,0.000093554605,0.97247654,0.006790015,0.013640796,0.0042889444,0.000018531173],"about_ca_topic_score_codex":0.003929589,"about_ca_topic_score_gemma":0.0045103896,"teacher_disagreement_score":0.003929589,"about_ca_system_score_codex":0.00042984827,"about_ca_system_score_gemma":0.0010535512,"threshold_uncertainty_score":0.007880092},"labels":[],"label_agreement":null},{"id":"W1994891592","doi":"10.1002/widm.31","title":"Mining uncertain data","year":2011,"lang":"en","type":"article","venue":"Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Association rule learning; Key (lock); Affinity analysis; Computer science; Uncertain data; Data mining; Associative property; Probabilistic logic; Database transaction; K-optimal pattern discovery; Task (project management); Process (computing); Knowledge extraction; Data science; Artificial intelligence; Database; Engineering; Mathematics","score_opus":0.2056452550767086,"score_gpt":0.37378523516306994,"score_spread":0.16813998008636133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994891592","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033491127,0.005203449,0.9452413,0.0053331433,0.00037889488,0.00028344296,0.0027442474,0.0004718639,0.0068524973],"genre_scores_gemma":[0.46142554,0.0063874973,0.517343,0.0014097461,0.0011626625,0.0006141305,0.008703843,0.00013785051,0.0028157681],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9872169,0.0033751607,0.0015692512,0.002289065,0.0050877645,0.0004618657],"domain_scores_gemma":[0.9706661,0.019318221,0.0027242738,0.0040086317,0.002855115,0.0004277183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007411716,0.0010689542,0.0022493857,0.0047208867,0.0015737946,0.0061303736,0.003655455,0.002234155,0.0029698296],"category_scores_gemma":[0.049195297,0.00097513164,0.0020105164,0.00725071,0.0022057153,0.00996181,0.0055826483,0.0024400975,0.0010845761],"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":[0.00045024877,0.00021504181,0.025995774,0.0024807367,0.001015943,0.004182295,0.0015904295,0.22137447,0.0026357966,0.2967042,0.01889362,0.42446136],"study_design_scores_gemma":[0.000043194745,0.00008939214,0.0019380514,0.00045797002,0.00014757218,0.0012574709,0.0006828505,0.47329903,0.0025219023,0.48571372,0.03377276,0.000076095756],"about_ca_topic_score_codex":0.0013670269,"about_ca_topic_score_gemma":0.0012582655,"teacher_disagreement_score":0.007411716,"about_ca_system_score_codex":0.00095319655,"about_ca_system_score_gemma":0.0013105945,"threshold_uncertainty_score":0.039197385},"labels":[],"label_agreement":null},{"id":"W1995221706","doi":"10.5539/cis.v6n4p88","title":"Data Mining Techniques and Preference Learning in Recommender Systems","year":2013,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Recommender system; Computer science; Component (thermodynamics); Preference; Set (abstract data type); Association rule learning; Order (exchange); Preference learning; Information retrieval; World Wide Web; Data mining","score_opus":0.060927878211622453,"score_gpt":0.27944789951514637,"score_spread":0.2185200213035239,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995221706","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0070052966,0.006597623,0.98197687,0.0013729957,0.00015994297,0.00020636113,0.00045401335,0.00034247985,0.0018845036],"genre_scores_gemma":[0.19453278,0.009202756,0.79096913,0.0005817072,0.0005548752,0.000609046,0.0011872033,0.000058957346,0.0023035936],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9927477,0.0037507531,0.0007472809,0.00084827753,0.0017461962,0.00015989764],"domain_scores_gemma":[0.9784828,0.01668125,0.00087345624,0.0015448761,0.0022184397,0.00019925326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0075647263,0.0012099232,0.0020256378,0.003614507,0.0007907987,0.0024580352,0.0020190647,0.0017981464,0.002131858],"category_scores_gemma":[0.026865648,0.00083649793,0.0016328231,0.005683406,0.0011106102,0.003355392,0.0012583984,0.0028568683,0.0012544045],"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":[0.0003095224,0.00068496825,0.013102273,0.0022375237,0.00091928156,0.0003678394,0.00057639804,0.150489,0.0019921549,0.08545921,0.008342159,0.7355197],"study_design_scores_gemma":[0.00013472047,0.00025121422,0.0035542347,0.00035216098,0.00019265543,0.00050320406,0.0002857266,0.77329683,0.0028701196,0.1997084,0.018728172,0.00012247104],"about_ca_topic_score_codex":0.0053572683,"about_ca_topic_score_gemma":0.0047859573,"teacher_disagreement_score":0.0075647263,"about_ca_system_score_codex":0.0011501433,"about_ca_system_score_gemma":0.0011833435,"threshold_uncertainty_score":0.040006578},"labels":[],"label_agreement":null},{"id":"W1995606590","doi":"10.5539/cis.v3n3p197","title":"Anomaly Detection of Clinical Behavior Sequences","year":2010,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Subsequence; Computer science; Anomaly detection; Similarity (geometry); Association rule learning; Anomaly (physics); Sequence (biology); Identification (biology); Pattern recognition (psychology); Data mining; Process (computing); Base (topology); Artificial intelligence; Algorithm; Mathematics; Biology","score_opus":0.02657666134097324,"score_gpt":0.32956803443532784,"score_spread":0.3029913730943546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995606590","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46755618,0.0007082966,0.5250982,0.00047024307,0.00011692105,0.00032107803,0.0015477908,0.0021594318,0.0020219118],"genre_scores_gemma":[0.8674001,0.00025475636,0.12982495,0.00006007181,0.00004302959,0.00012806497,0.0015923063,0.000033903725,0.00066280103],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99825495,0.00033014605,0.000252345,0.00045548117,0.0006015776,0.00010549807],"domain_scores_gemma":[0.9947857,0.0024739415,0.00083584286,0.0004009328,0.0012517745,0.00025185398],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012835322,0.00046495924,0.00061357627,0.0039275703,0.00038244593,0.0007303927,0.00071425433,0.00055910385,0.0007489085],"category_scores_gemma":[0.009607034,0.00017361299,0.00040938848,0.002221677,0.00037890908,0.0007793847,0.0005245221,0.00046210623,0.00024857707],"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":[0.0013723576,0.00043607573,0.2530044,0.0005333076,0.000295186,0.003779965,0.0010383648,0.040165093,0.048473638,0.009933872,0.0032184504,0.6377494],"study_design_scores_gemma":[0.00008413538,0.0007903607,0.08741665,0.00009094419,0.0002316917,0.007665349,0.0005791727,0.82756853,0.041916784,0.026190883,0.0073630908,0.000102379025],"about_ca_topic_score_codex":0.0022910282,"about_ca_topic_score_gemma":0.0016155567,"teacher_disagreement_score":0.0039275703,"about_ca_system_score_codex":0.0004123368,"about_ca_system_score_gemma":0.001056647,"threshold_uncertainty_score":0.0067880154},"labels":[],"label_agreement":null},{"id":"W1996324618","doi":"10.1109/cse.2013.129","title":"Topics and Terms Mining in Unstructured Data Stores","year":2013,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"NoSQL; Computer science; Unstructured data; Data mining; Schema (genetic algorithms); Database; Big data; Knowledge extraction; Semi-structured data; Data extraction; Data warehouse; Information retrieval; Relational database","score_opus":0.028138217890096923,"score_gpt":0.2605091579314912,"score_spread":0.23237094004139427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996324618","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.101046756,0.0017793253,0.8370946,0.0014765362,0.0002208879,0.0010379283,0.019393094,0.026763007,0.01118787],"genre_scores_gemma":[0.17402707,0.0009089041,0.7996187,0.00020548687,0.00008674067,0.0004134385,0.019781556,0.00078531366,0.0041727386],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99647886,0.00054564606,0.0005013563,0.00071960024,0.0015111291,0.00024332873],"domain_scores_gemma":[0.9926559,0.0028674235,0.0006018806,0.0021947015,0.0014499763,0.00023028928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002736424,0.00089398125,0.001285478,0.005756547,0.0014236362,0.0047536455,0.0017125697,0.0007720227,0.0021625317],"category_scores_gemma":[0.0160114,0.00065154297,0.001342048,0.007896693,0.0007921858,0.006767882,0.0031346285,0.0009698102,0.0022872395],"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":[0.0013385798,0.00035841143,0.026518201,0.0015506878,0.00023673651,0.0012636493,0.0038263276,0.034645043,0.036377583,0.0714937,0.047564518,0.77482665],"study_design_scores_gemma":[0.00020812885,0.00022903597,0.011105299,0.00028724986,0.00015494837,0.0015007067,0.004339011,0.50740814,0.08947921,0.2536166,0.13153209,0.00013969827],"about_ca_topic_score_codex":0.0047818823,"about_ca_topic_score_gemma":0.006685368,"teacher_disagreement_score":0.005756547,"about_ca_system_score_codex":0.0009043252,"about_ca_system_score_gemma":0.0020070558,"threshold_uncertainty_score":0.014471769},"labels":[],"label_agreement":null},{"id":"W1997009252","doi":"10.5555/777092.777246","title":"Student modeling for a web-based learning environment: a data mining approach","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Personalization; Web mining; Educational data mining; World Wide Web; Association rule learning; Cluster analysis; Web page; Data science; Artificial intelligence","score_opus":0.10457601303485353,"score_gpt":0.2836368207542535,"score_spread":0.17906080771939997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997009252","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09832912,0.00023654888,0.89396554,0.0020226191,0.000040898947,0.00042097093,0.0014613735,0.0012326414,0.0022902228],"genre_scores_gemma":[0.5841727,0.00043888242,0.4089986,0.00023964875,0.000084052364,0.0006802054,0.0023669023,0.00015941152,0.0028596192],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978623,0.0010337627,0.00014670323,0.00041885625,0.0004118598,0.00012659447],"domain_scores_gemma":[0.992728,0.0050691706,0.0005941072,0.00058246526,0.00068073167,0.0003456116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037341479,0.0008332617,0.0011598952,0.0032993692,0.0009515724,0.005180792,0.0030883292,0.0019204601,0.0027069114],"category_scores_gemma":[0.0126523925,0.00055126566,0.0015021826,0.0030165294,0.00067736366,0.005939887,0.0015861387,0.002586403,0.0010516734],"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":[0.00044575828,0.0022584642,0.13096374,0.0005148043,0.0006932542,0.0005543463,0.0020957894,0.5849169,0.002615386,0.046070848,0.006358768,0.22251196],"study_design_scores_gemma":[0.000008978048,0.00003514736,0.0017888403,0.000021508931,0.000032629858,0.00003907749,0.00024982548,0.98561573,0.0003913513,0.010644338,0.001154428,0.000018216482],"about_ca_topic_score_codex":0.010263762,"about_ca_topic_score_gemma":0.014878836,"teacher_disagreement_score":0.010263762,"about_ca_system_score_codex":0.0018205435,"about_ca_system_score_gemma":0.0019038954,"threshold_uncertainty_score":0.020408034},"labels":[],"label_agreement":null},{"id":"W1997024687","doi":"10.4018/jdm.2006070102","title":"A Framework for Efficient Association Rule Mining in XML Data","year":2006,"lang":"en","type":"article","venue":"Journal of Database Management","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; XML; Efficient XML Interchange; Association rule learning; Data mining; XML validation; Streaming XML; XML database; Generalization; Constraint (computer-aided design); Information retrieval; Task (project management); XML Schema (W3C); XML Encryption; World Wide Web","score_opus":0.03398456354941731,"score_gpt":0.3067758063708545,"score_spread":0.2727912428214372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997024687","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002473354,0.00017781327,0.99799985,0.00010919305,0.000016929811,0.00009161007,0.00015160807,0.0010868502,0.000118770084],"genre_scores_gemma":[0.004967404,0.0002446061,0.99369556,0.00008154963,0.000029508574,0.00025506498,0.00047611754,0.00004433912,0.00020585467],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99101967,0.003721913,0.0012696572,0.0011262025,0.002658103,0.0002044052],"domain_scores_gemma":[0.9919825,0.004614539,0.0006473734,0.0016779454,0.0008913914,0.00018628729],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012443932,0.0014833516,0.0023761888,0.0053311405,0.0012420008,0.003444904,0.004534073,0.001855807,0.002599518],"category_scores_gemma":[0.020054225,0.0015240961,0.004029792,0.0055076024,0.0011668669,0.0046436745,0.0033301155,0.003454239,0.0028168675],"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":[0.00028978015,0.00040190152,0.0024528194,0.0018285803,0.0009407421,0.0016512175,0.0006619276,0.1254844,0.009029647,0.20095685,0.022627387,0.6336747],"study_design_scores_gemma":[0.00016408354,0.0002467885,0.0007738914,0.0004168251,0.00018633466,0.0022087763,0.0001837545,0.7230161,0.007334835,0.18519308,0.08013634,0.00013923929],"about_ca_topic_score_codex":0.0021112524,"about_ca_topic_score_gemma":0.002935933,"teacher_disagreement_score":0.012443932,"about_ca_system_score_codex":0.00075219676,"about_ca_system_score_gemma":0.0020745913,"threshold_uncertainty_score":0.06581056},"labels":[],"label_agreement":null},{"id":"W1998319238","doi":"10.4018/jdwm.2005100103","title":"Preference-Based Frequent Pattern Mining","year":2005,"lang":"en","type":"article","venue":"International Journal of Data Warehousing and Mining","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Preference; Data mining; Sequential Pattern Mining; Constraint (computer-aided design); K-optimal pattern discovery; Machine learning; Artificial intelligence; Data stream mining; Mathematics","score_opus":0.11674474253513491,"score_gpt":0.3223307267655304,"score_spread":0.20558598423039548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998319238","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019642623,0.0004672334,0.9756438,0.0004345075,0.000057162477,0.0003085086,0.0008735943,0.00040208493,0.00217048],"genre_scores_gemma":[0.32661432,0.00077154615,0.66779375,0.00028135948,0.0001158234,0.00042047843,0.0021719635,0.00007252253,0.0017583192],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9911951,0.0028518548,0.00097249774,0.0012471777,0.003295554,0.00043779597],"domain_scores_gemma":[0.98398846,0.008134706,0.0014018416,0.0024123997,0.0037011637,0.00036133666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0057295673,0.0009413519,0.0015911403,0.0036553335,0.0010894954,0.0022316608,0.0021744394,0.0010458257,0.0024968963],"category_scores_gemma":[0.03222919,0.000482232,0.0015075813,0.00633175,0.0007197895,0.004739789,0.0013822977,0.0014179122,0.0011721172],"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":[0.00072907127,0.000438562,0.025208479,0.0013258287,0.0006025583,0.0012913579,0.00072133297,0.09507408,0.0071842656,0.13290288,0.013549258,0.72097236],"study_design_scores_gemma":[0.0001198025,0.00031357826,0.0034843804,0.00015937153,0.00019964368,0.002519821,0.0005462238,0.7011309,0.009271667,0.26389417,0.018236741,0.00012375369],"about_ca_topic_score_codex":0.0014936499,"about_ca_topic_score_gemma":0.001850491,"teacher_disagreement_score":0.0057295673,"about_ca_system_score_codex":0.00074498245,"about_ca_system_score_gemma":0.0015324842,"threshold_uncertainty_score":0.030301213},"labels":[],"label_agreement":null},{"id":"W2000444209","doi":"10.12957/cadinf.2009.6470","title":"Processo de Desenvolvimento do Sistema Multi-Agentes Monitor Glicêmico","year":2009,"lang":"pt","type":"article","venue":"Cadernos do IME - Série Informática","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science","score_opus":0.03145275467255462,"score_gpt":0.3055016043973951,"score_spread":0.27404884972484045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000444209","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24108379,0.0016951103,0.71179897,0.0014826203,0.00032289358,0.0007892729,0.0007062174,0.010772732,0.03134832],"genre_scores_gemma":[0.86146635,0.0007130927,0.12301076,0.00020889884,0.00007295831,0.00025588306,0.0004960635,0.00025668155,0.0135193765],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99895227,0.0002479897,0.000092862676,0.00022027358,0.00040348593,0.000083056315],"domain_scores_gemma":[0.99826694,0.00058091775,0.00020578613,0.0003052087,0.0005303588,0.00011080873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018638197,0.00057491736,0.00060987344,0.0014249872,0.00071511185,0.0032722575,0.00088175194,0.00075676624,0.004948608],"category_scores_gemma":[0.005177929,0.00032155518,0.00046931233,0.0008107608,0.0004050097,0.001534376,0.0010752083,0.0008248558,0.0014058803],"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":[0.0013291255,0.00080385763,0.036633704,0.0009804292,0.00025390353,0.0010179986,0.0035777076,0.07872345,0.11670154,0.03032737,0.009472159,0.7201787],"study_design_scores_gemma":[0.0001561666,0.0008618345,0.024688192,0.0002866009,0.00032101606,0.00057181256,0.0018084856,0.7497725,0.12653513,0.024849849,0.07001829,0.00013018638],"about_ca_topic_score_codex":0.004254918,"about_ca_topic_score_gemma":0.0031580718,"teacher_disagreement_score":0.004948608,"about_ca_system_score_codex":0.0006680902,"about_ca_system_score_gemma":0.0010943902,"threshold_uncertainty_score":0.016554773},"labels":[],"label_agreement":null},{"id":"W2004582297","doi":"10.4018/jdwm.2008100104","title":"Effectiveness of Fuzzy Classifier Rules in Capturing Correlations between Genes","year":2008,"lang":"en","type":"article","venue":"International Journal of Data Warehousing and Mining","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Classifier (UML); Computer science; Gene selection; Artificial intelligence; Fuzzy logic; Correlation; Fuzzy rule; Machine learning; Gene; Data mining; Pattern recognition (psychology); Fuzzy set; Mathematics; Genetics; Biology","score_opus":0.08223178487745361,"score_gpt":0.32237026324166423,"score_spread":0.24013847836421062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004582297","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20312995,0.0010584486,0.7882176,0.00043396468,0.000139495,0.00026109334,0.0004909482,0.001070109,0.005198459],"genre_scores_gemma":[0.63615775,0.00042469092,0.3616031,0.00018780812,0.00008762305,0.00014632945,0.00062750827,0.00007578581,0.0006893467],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9910088,0.002700069,0.0009626529,0.0013495646,0.0037060857,0.00027276154],"domain_scores_gemma":[0.9211777,0.062941484,0.0031248967,0.004812191,0.007547213,0.00039644373],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013103691,0.0010145148,0.0017917439,0.0035557447,0.0008123709,0.003338244,0.0012958137,0.0015386262,0.0008017409],"category_scores_gemma":[0.060839437,0.00047217542,0.0010978371,0.0017850456,0.0009696771,0.0042198757,0.00061814697,0.0013343799,0.00048283132],"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":[0.0011007972,0.00050760806,0.056915183,0.0004083472,0.0006065706,0.00081022724,0.0008933361,0.39953616,0.017637556,0.019351719,0.0020109878,0.50022143],"study_design_scores_gemma":[0.00004751833,0.00018403013,0.0069970367,0.00006693251,0.00015513155,0.00027708407,0.0001355878,0.9581244,0.012143737,0.020332795,0.0014524623,0.00008322962],"about_ca_topic_score_codex":0.0050377958,"about_ca_topic_score_gemma":0.0033130192,"teacher_disagreement_score":0.013103691,"about_ca_system_score_codex":0.0008812438,"about_ca_system_score_gemma":0.0015823955,"threshold_uncertainty_score":0.06929976},"labels":[],"label_agreement":null},{"id":"W2004607515","doi":"10.1145/1645953.1646202","title":"Using domain ontology for semantic web usage mining and next page prediction","year":2009,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Semantics (computer science); Web mining; Semantic Web; Ontology; Preprocessor; Information retrieval; Data mining; Social Semantic Web; Semantic Web Stack; Domain (mathematical analysis); Web page; Artificial intelligence; World Wide Web; Programming language","score_opus":0.05026632900114511,"score_gpt":0.29572018418263285,"score_spread":0.24545385518148774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004607515","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033535734,0.0002880404,0.9578498,0.00050342875,0.00005080212,0.00020233999,0.000996052,0.0025043495,0.0040694983],"genre_scores_gemma":[0.23710209,0.00046296165,0.757673,0.0001449137,0.000027387914,0.00028552895,0.0031198203,0.00018566306,0.0009985699],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99823254,0.0005690472,0.00017736758,0.00023311972,0.00069061737,0.00009728123],"domain_scores_gemma":[0.9978796,0.00091079436,0.0001906697,0.0005006279,0.0004290629,0.000089169625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016748648,0.0005897701,0.0006726124,0.0038515308,0.0010451364,0.0016188973,0.0010875863,0.00077725196,0.0011283363],"category_scores_gemma":[0.0071098367,0.0003755127,0.0010831718,0.003666026,0.00059904635,0.0048740483,0.0011090069,0.0009799686,0.00059938786],"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":[0.0003560756,0.000935496,0.023545397,0.00067537226,0.00026059023,0.0008518926,0.0011910505,0.05389117,0.020578537,0.11574856,0.011017824,0.77094793],"study_design_scores_gemma":[0.0000389012,0.0000805665,0.00485515,0.00017596768,0.0001229369,0.0006538816,0.0006441774,0.8084683,0.020420576,0.122943185,0.041516945,0.00007942779],"about_ca_topic_score_codex":0.0075460155,"about_ca_topic_score_gemma":0.010536914,"teacher_disagreement_score":0.0075460155,"about_ca_system_score_codex":0.000946856,"about_ca_system_score_gemma":0.0020252196,"threshold_uncertainty_score":0.015004158},"labels":[],"label_agreement":null},{"id":"W2004753031","doi":"10.1117/12.542509","title":"Experimental analysis of methods for imputation of missing values in databases","year":2004,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Imputation (statistics); Missing data; Computer science; Data mining; Decision tree; Naive Bayes classifier; Machine learning; Algorithm; Support vector machine","score_opus":0.02778216031126049,"score_gpt":0.3287805926909821,"score_spread":0.30099843237972157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004753031","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25969854,0.0029865638,0.72400033,0.0011363653,0.00055545627,0.0040484,0.00239798,0.0017314213,0.0034449536],"genre_scores_gemma":[0.27755412,0.001120668,0.7129759,0.00029815518,0.0001421195,0.005061569,0.0019288139,0.00023732767,0.0006812501],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.87126744,0.095861554,0.009755437,0.006096317,0.015763454,0.0012558118],"domain_scores_gemma":[0.47864795,0.44891864,0.012675226,0.03550573,0.023193281,0.0010591095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09231961,0.0017011832,0.0012077574,0.0027791548,0.0017691954,0.0020589014,0.0027986905,0.002392201,0.0021171626],"category_scores_gemma":[0.27087224,0.00088881084,0.0018595364,0.004079738,0.0022622654,0.0038664439,0.0020704651,0.002003604,0.0004960423],"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":[0.012521703,0.007964995,0.032241672,0.0075295027,0.004309816,0.00032426495,0.0021645753,0.2883814,0.02976062,0.028237807,0.0094156945,0.577148],"study_design_scores_gemma":[0.0021956002,0.0144040445,0.025167352,0.0010781748,0.0013978177,0.0010624279,0.0017306517,0.772096,0.1294063,0.037346266,0.013595,0.00052043085],"about_ca_topic_score_codex":0.0012686417,"about_ca_topic_score_gemma":0.0010687888,"teacher_disagreement_score":0.09231961,"about_ca_system_score_codex":0.0015277105,"about_ca_system_score_gemma":0.0019166816,"threshold_uncertainty_score":0.48823857},"labels":[],"label_agreement":null},{"id":"W2005499394","doi":"10.14778/2168651.2168658","title":"Dense subgraph maintenance under streaming edge weight updates for real-time story identification","year":2012,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":172,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Enhanced Data Rates for GSM Evolution; Identification (biology); Social media; Globe; Scale (ratio); Point (geometry); Data science; Edge device; Range (aeronautics); Social network (sociolinguistics); World Wide Web; Artificial intelligence; Geography; Mathematics; Engineering","score_opus":0.013209024702018898,"score_gpt":0.23841514356549856,"score_spread":0.22520611886347966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005499394","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15189083,0.00081494084,0.8400802,0.000516991,0.00005622228,0.0002299817,0.0010928966,0.0041688755,0.0011490996],"genre_scores_gemma":[0.60486597,0.00035701977,0.38903454,0.00014493465,0.00011444364,0.00026421418,0.0034517786,0.00030941545,0.0014576628],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988111,0.00028219342,0.00010371855,0.00036745885,0.00033142872,0.0001040963],"domain_scores_gemma":[0.991293,0.004996122,0.0011464787,0.0015155581,0.0007943123,0.00025446675],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015171234,0.0009236693,0.001450579,0.002850521,0.0007931802,0.0012188345,0.0030249315,0.0012411394,0.0010363597],"category_scores_gemma":[0.017366368,0.00072985416,0.0006752348,0.0032707648,0.0008244656,0.0041648597,0.0016468767,0.0010888033,0.00052569254],"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":[0.00077173987,0.0003907945,0.015224704,0.0003176146,0.00019636838,0.00044005134,0.0006669966,0.3944598,0.01724005,0.008579812,0.008912885,0.55279917],"study_design_scores_gemma":[0.000028873119,0.000053949596,0.0012391957,0.000008827959,0.000029339106,0.0001529856,0.00008766979,0.9860271,0.00385686,0.0075433035,0.0009612164,0.000010631149],"about_ca_topic_score_codex":0.006720096,"about_ca_topic_score_gemma":0.010211146,"teacher_disagreement_score":0.006720096,"about_ca_system_score_codex":0.0009957345,"about_ca_system_score_gemma":0.0010678744,"threshold_uncertainty_score":0.01336199},"labels":[],"label_agreement":null},{"id":"W2006062995","doi":"10.1142/s0219622007002368","title":"COMPARISON OF INTERESTINGNESS MEASURES FOR WEB USAGE MINING: AN EMPIRICAL STUDY","year":2007,"lang":"en","type":"article","venue":"International Journal of Information Technology & Decision Making","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Association rule learning; Data mining; Pruning; Web mining; The Internet; Information retrieval; Web page; World Wide Web","score_opus":0.06390906138059581,"score_gpt":0.4407990982195704,"score_spread":0.3768900368389746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006062995","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96791124,0.0040010572,0.024005428,0.0002985843,0.000036828227,0.00025451812,0.0011106699,0.00033176952,0.002049877],"genre_scores_gemma":[0.9738687,0.0004830703,0.02361762,0.00003127957,0.00005014078,0.00016687872,0.0015518188,0.00005992099,0.0001705197],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97263634,0.0113020055,0.0037415128,0.0017587501,0.010025807,0.00053557014],"domain_scores_gemma":[0.38939226,0.57162476,0.0126925325,0.01129361,0.013113363,0.001883435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.039458744,0.00084229716,0.0014386347,0.01445548,0.0009067834,0.0018021084,0.0015737085,0.0014515733,0.00077508186],"category_scores_gemma":[0.19388498,0.0002940401,0.0013734506,0.0097890375,0.0015159934,0.005014465,0.0012818072,0.0015140249,0.0001849009],"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":[0.0022469275,0.002572549,0.5843765,0.001693059,0.0016764409,0.00050609384,0.0022068494,0.034687176,0.003388426,0.0058128433,0.0037834095,0.35704973],"study_design_scores_gemma":[0.00041237017,0.005080208,0.5742931,0.000383524,0.000871837,0.0036104277,0.0028040903,0.3791753,0.010386283,0.018126687,0.004586497,0.00026967996],"about_ca_topic_score_codex":0.0008382246,"about_ca_topic_score_gemma":0.00094328803,"teacher_disagreement_score":0.039458744,"about_ca_system_score_codex":0.0010980729,"about_ca_system_score_gemma":0.00063186645,"threshold_uncertainty_score":0.20868021},"labels":[],"label_agreement":null},{"id":"W2006981561","doi":"10.1145/2351476.2351500","title":"Mining probabilistic datasets vertically","year":2012,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Probabilistic logic; Data mining; Uncertain data; Set (abstract data type); Database transaction; Data set; Representation (politics); A priori and a posteriori; Artificial intelligence; Database","score_opus":0.027978309331188937,"score_gpt":0.27640637180749933,"score_spread":0.24842806247631039,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006981561","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039077204,0.00046110747,0.9473745,0.0011287043,0.00012343064,0.0003034062,0.006475172,0.0012053603,0.0038510403],"genre_scores_gemma":[0.22927716,0.0008446868,0.74685824,0.00063160073,0.00019724494,0.00054076687,0.019397542,0.0001908832,0.002061862],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99492526,0.00075663533,0.00064837805,0.0013566726,0.0019966604,0.0003162945],"domain_scores_gemma":[0.99441457,0.0018955352,0.0006479494,0.0015175341,0.0013860707,0.00013821095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021025294,0.00075294153,0.0010893818,0.003046443,0.0010767689,0.0029123821,0.0017954978,0.0012268036,0.0022613637],"category_scores_gemma":[0.012960415,0.0010547633,0.0021082035,0.006752178,0.00051524036,0.006254917,0.005523955,0.0021450468,0.0010916964],"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":[0.00068038044,0.00039884413,0.04606729,0.000898492,0.000880191,0.0023220107,0.0011887447,0.10095883,0.033597868,0.12362762,0.024541818,0.66483796],"study_design_scores_gemma":[0.00009463283,0.00022907078,0.012197433,0.00021860798,0.00026451616,0.002167405,0.000989689,0.7037783,0.020566022,0.20182744,0.057562746,0.000104251194],"about_ca_topic_score_codex":0.0020288068,"about_ca_topic_score_gemma":0.0030990057,"teacher_disagreement_score":0.003046443,"about_ca_system_score_codex":0.0005527968,"about_ca_system_score_gemma":0.0015124292,"threshold_uncertainty_score":0.011119366},"labels":[],"label_agreement":null},{"id":"W2007076985","doi":"10.1016/j.ins.2004.12.007","title":"Temporal analysis of clusters of supermarket customers: conventional versus interval set approach","year":2005,"lang":"en","type":"article","venue":"Information Sciences","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":59,"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); Saint Mary's University","funders":"","keywords":"Computer science; Self-organizing map; Cluster analysis; Data mining; Abstraction; Dimension (graph theory); Interval (graph theory); Set (abstract data type); Data set; Cluster (spacecraft); Market segmentation; Temporal database; Sorting; Artificial intelligence; Mathematics; Marketing; Algorithm","score_opus":0.04789459233703726,"score_gpt":0.31517101400867553,"score_spread":0.2672764216716383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007076985","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.578396,0.00088161085,0.41617346,0.00024747124,0.000059916434,0.00008133262,0.0010436302,0.00025231222,0.00286424],"genre_scores_gemma":[0.95925397,0.00022924518,0.03923361,0.000019742172,0.00005845732,0.000042973206,0.00059170043,0.00001968795,0.0005507733],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994012,0.0001571442,0.00004347081,0.00016243599,0.00015979935,0.00007590783],"domain_scores_gemma":[0.9961904,0.0024467863,0.0005244217,0.00029908787,0.00040562873,0.0001335712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014895848,0.0003387554,0.0007145607,0.0023202787,0.0003928188,0.0012595179,0.0013413369,0.0004306753,0.0021577668],"category_scores_gemma":[0.0069399728,0.00015901952,0.00077130797,0.0031666637,0.00037179867,0.0015717706,0.0005909427,0.0005805278,0.0001592239],"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":[0.0025759272,0.0005975437,0.16609731,0.0006837779,0.000890217,0.0006865091,0.0017510523,0.31747591,0.011136193,0.06366348,0.003979473,0.43046263],"study_design_scores_gemma":[0.00003166041,0.00016894825,0.03448406,0.000027131277,0.00016704285,0.00023893669,0.0005816637,0.93266064,0.0019476567,0.028128048,0.0015240002,0.00004028924],"about_ca_topic_score_codex":0.003743455,"about_ca_topic_score_gemma":0.0025579322,"teacher_disagreement_score":0.003743455,"about_ca_system_score_codex":0.0007079965,"about_ca_system_score_gemma":0.00049480906,"threshold_uncertainty_score":0.007877767},"labels":[],"label_agreement":null},{"id":"W2009254877","doi":"10.1007/s10472-013-9372-8","title":"A fast compound algorithm for mining generators, closed itemsets, and computing links between equivalence classes","year":2013,"lang":"en","type":"article","venue":"Annals of Mathematics and Artificial Intelligence","topic":"Data Mining Algorithms and Applications","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":"Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Schema (genetic algorithms); Computer science; Computation; Data mining; Association rule learning; Scalability; Algorithm; Theoretical computer science; Machine learning; Database","score_opus":0.14313485498643166,"score_gpt":0.35577840393732607,"score_spread":0.2126435489508944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009254877","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032674015,0.00071392435,0.959201,0.00029776822,0.00009291397,0.00058083254,0.0023902312,0.002676859,0.0013723122],"genre_scores_gemma":[0.08069313,0.00026554574,0.90990907,0.00011207921,0.000090510206,0.0005303004,0.0064091505,0.00020044406,0.0017897753],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99755377,0.00039818737,0.00034980994,0.00072114356,0.0008071993,0.00016984339],"domain_scores_gemma":[0.98792076,0.00831047,0.00058227335,0.001523951,0.0012931316,0.000369428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00316399,0.001596178,0.0031611188,0.0073285517,0.0023688022,0.0032077162,0.0037106974,0.0020828876,0.008268352],"category_scores_gemma":[0.014582873,0.0010399865,0.0020562224,0.009417272,0.0012846354,0.007573527,0.0034718125,0.0023192402,0.0020626846],"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":[0.0016539335,0.0007660627,0.007227093,0.00073776324,0.00034925828,0.00058162434,0.0003290521,0.041906387,0.0069163535,0.04889,0.016624754,0.8740177],"study_design_scores_gemma":[0.0004369705,0.0005699164,0.0017576664,0.000109366876,0.00022427662,0.0009178798,0.0002106924,0.7176883,0.006495764,0.26061398,0.01090471,0.00007044649],"about_ca_topic_score_codex":0.0019786987,"about_ca_topic_score_gemma":0.004434176,"teacher_disagreement_score":0.008268352,"about_ca_system_score_codex":0.001049619,"about_ca_system_score_gemma":0.004323725,"threshold_uncertainty_score":0.02766043},"labels":[],"label_agreement":null},{"id":"W2009568892","doi":"10.1109/cidm.2013.6597230","title":"A hierarchy of independence assumptions for multi-relational Bayes net classifiers","year":2013,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Hierarchy; Naive Bayes classifier; Machine learning; Relational database; Classifier (UML); Artificial intelligence; Independence (probability theory); Class hierarchy; Net (polyhedron); Statistical relational learning; Data mining; Benchmark (surveying); Class (philosophy); Bayes' theorem; Bayesian probability; Mathematics; Object-oriented programming; Statistics; Support vector machine","score_opus":0.07172101457596379,"score_gpt":0.302775301285959,"score_spread":0.23105428670999517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009568892","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048376783,0.00039629027,0.9909446,0.0006104351,0.000037259066,0.00008180537,0.00016473747,0.0001694295,0.00275766],"genre_scores_gemma":[0.39277822,0.0014150294,0.5965528,0.0012122194,0.0007287203,0.0007077111,0.0014319762,0.00018214862,0.0049912673],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98115325,0.006408807,0.0011352788,0.0025410384,0.007876504,0.0008851747],"domain_scores_gemma":[0.9617592,0.024109077,0.0024272986,0.0049219197,0.0061012967,0.0006813174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01909697,0.001503976,0.00238663,0.0027527893,0.0020651212,0.0040186117,0.005209242,0.002554691,0.0036833617],"category_scores_gemma":[0.058636304,0.001780905,0.0023624294,0.002463397,0.0029398773,0.012152933,0.003530974,0.0066237836,0.0026867418],"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":[0.00053357997,0.0002530795,0.011380567,0.0005289868,0.0003905702,0.0006686251,0.0010036356,0.21468626,0.0034490456,0.5519892,0.009712378,0.20540407],"study_design_scores_gemma":[0.0000435528,0.000077597,0.0010983356,0.00011631594,0.000078380916,0.00024866595,0.000058162823,0.7374198,0.0011834177,0.25608832,0.0035324788,0.000055038785],"about_ca_topic_score_codex":0.0074988776,"about_ca_topic_score_gemma":0.00562912,"teacher_disagreement_score":0.01909697,"about_ca_system_score_codex":0.002413113,"about_ca_system_score_gemma":0.002120417,"threshold_uncertainty_score":0.10099566},"labels":[],"label_agreement":null},{"id":"W2009938851","doi":"10.1109/icdmw.2013.106","title":"Accelerating Frequent Itemsets Mining on the Cloud: A MapReduce -Based Approach","year":2013,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Cloud computing; Data mining; Overhead (engineering); Terabyte; Resource (disambiguation); Programming paradigm; Distributed computing","score_opus":0.05150657723462968,"score_gpt":0.24547473648372886,"score_spread":0.1939681592490992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009938851","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046630662,0.0005803263,0.9470167,0.0007880628,0.00012009443,0.00029772395,0.00032497023,0.0017124468,0.0025289794],"genre_scores_gemma":[0.24367717,0.00054032076,0.7529518,0.00016970391,0.000105848536,0.00017575671,0.00061990035,0.00009535644,0.0016641916],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990146,0.00021192504,0.0000763005,0.00016479981,0.00039551596,0.00013679542],"domain_scores_gemma":[0.99865997,0.00044025932,0.000084091254,0.0003034018,0.00040125306,0.00011112586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001234194,0.00056548504,0.0011456137,0.0019369491,0.0012816173,0.0012467531,0.002104364,0.00059575017,0.00092554494],"category_scores_gemma":[0.0022224963,0.00046848902,0.0012003324,0.0025562989,0.0004129542,0.001709757,0.0010673612,0.0006839588,0.00048331203],"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":[0.00095827447,0.0009615128,0.00817374,0.0004805114,0.0003930733,0.0010710408,0.00047227385,0.18131287,0.025846839,0.022316817,0.01878817,0.73922473],"study_design_scores_gemma":[0.00009847862,0.00011371935,0.0016569953,0.000015386777,0.00006068318,0.00055339094,0.0002678977,0.9549739,0.009780306,0.024926916,0.0075137783,0.000038610266],"about_ca_topic_score_codex":0.006820466,"about_ca_topic_score_gemma":0.0085702175,"teacher_disagreement_score":0.006820466,"about_ca_system_score_codex":0.0005660661,"about_ca_system_score_gemma":0.0019535506,"threshold_uncertainty_score":0.013561547},"labels":[],"label_agreement":null},{"id":"W2012908200","doi":"10.1145/1090193.1090197","title":"Mining relational databases with multi-view learning","year":2005,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Relational database; Table (database); Key (lock); Field (mathematics); Joins; Data mining; Representation (politics); Benchmark (surveying); Transformation (genetics); Database; Information retrieval; Machine learning","score_opus":0.05945742442819155,"score_gpt":0.2921118259925049,"score_spread":0.23265440156431336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012908200","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014080424,0.0010163558,0.9809157,0.0003317619,0.000040691622,0.00015943467,0.00065395515,0.002194575,0.0006070454],"genre_scores_gemma":[0.20478746,0.0006887803,0.7889834,0.00026833374,0.00008702122,0.00022722599,0.0042927214,0.0001244025,0.00054066535],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99460524,0.0013988008,0.00055103464,0.0014345908,0.00174389,0.00026648404],"domain_scores_gemma":[0.99321246,0.003035351,0.0005821963,0.001384178,0.0015684192,0.0002173529],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042994716,0.0014205532,0.002075164,0.0048968103,0.0007678552,0.0040135686,0.0041243443,0.0016103787,0.0012467977],"category_scores_gemma":[0.013336928,0.0009818858,0.0026973023,0.0042720092,0.00060481025,0.0056952992,0.003245794,0.0021518122,0.00078119664],"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":[0.00034403667,0.0004831577,0.0143613955,0.00043155122,0.00064291223,0.00053851045,0.0004712264,0.19527003,0.0050337333,0.015747191,0.012555306,0.754121],"study_design_scores_gemma":[0.000018403302,0.000055113767,0.00059776724,0.000027853846,0.000048622933,0.00013585754,0.00013676283,0.97817034,0.0025153193,0.016197402,0.0020771343,0.000019382947],"about_ca_topic_score_codex":0.004688097,"about_ca_topic_score_gemma":0.005580939,"teacher_disagreement_score":0.0048968103,"about_ca_system_score_codex":0.0011853374,"about_ca_system_score_gemma":0.0016859488,"threshold_uncertainty_score":0.0227381},"labels":[],"label_agreement":null},{"id":"W2013089647","doi":"10.1145/1816112.1816116","title":"CloseViz","year":2010,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Representation (politics); Data mining; Information retrieval; Visualization","score_opus":0.005910413621754661,"score_gpt":0.23523119386155494,"score_spread":0.2293207802398003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013089647","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0049857064,0.002913928,0.8333006,0.0015391894,0.0010470555,0.00052312703,0.007154364,0.09886853,0.049667485],"genre_scores_gemma":[0.061858147,0.0050256564,0.8205877,0.0015362389,0.0005190597,0.0012010713,0.035939272,0.018739311,0.05459355],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.997479,0.000414808,0.00018178567,0.00066226005,0.0010253437,0.00023677121],"domain_scores_gemma":[0.9980642,0.00058072445,0.00019794884,0.00049531966,0.0005133012,0.00014847671],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016789433,0.0024750447,0.0015126546,0.005408939,0.0016942282,0.005978111,0.00437722,0.0030642413,0.08619663],"category_scores_gemma":[0.008737141,0.0013559305,0.0025428617,0.0048418194,0.0009574221,0.0066205775,0.006225754,0.0023079375,0.04607075],"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":[0.00057766784,0.00013654958,0.001659705,0.0012704894,0.00013635829,0.00034754354,0.0005355047,0.0076564364,0.0062428843,0.10459979,0.2804285,0.59640855],"study_design_scores_gemma":[0.00018519085,0.00014487884,0.0010308746,0.00028256307,0.000055856515,0.0012331355,0.00024606628,0.076047435,0.013271761,0.087057166,0.8202778,0.0001674],"about_ca_topic_score_codex":0.0023187667,"about_ca_topic_score_gemma":0.0027413485,"teacher_disagreement_score":0.08619663,"about_ca_system_score_codex":0.001176088,"about_ca_system_score_gemma":0.0010865803,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W201367383","doi":"","title":"Proceedings of the 2nd SIGMOD PhD workshop on Innovative database research","year":2008,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Library science","score_opus":0.17405319926608798,"score_gpt":0.35865931969016973,"score_spread":0.18460612042408175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W201367383","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012218716,0.20068322,0.19627707,0.21007614,0.18133092,0.0017037145,0.009056138,0.006916034,0.18173806],"genre_scores_gemma":[0.06616177,0.14122385,0.19853404,0.026453529,0.109041646,0.0015551582,0.0305879,0.0041225026,0.42231965],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9874515,0.0044089532,0.0011493915,0.0013995211,0.004843591,0.00074708357],"domain_scores_gemma":[0.9811373,0.0042352853,0.0006990522,0.0029108305,0.0072110663,0.003806419],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02214314,0.0015319634,0.0021730454,0.004813212,0.0022521494,0.013119117,0.002994084,0.0025841135,0.048939697],"category_scores_gemma":[0.026226297,0.0012326181,0.0013983645,0.004082052,0.001847011,0.0127753485,0.0058686147,0.005794667,0.02650395],"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":[0.00015876719,0.00015662043,0.00075742725,0.00024463987,0.00005213877,0.000084910265,0.00035830948,0.00036756083,0.0007460433,0.008128597,0.8132045,0.17574054],"study_design_scores_gemma":[0.00002917811,0.0000640687,0.0006320303,0.00021541865,0.00002760979,0.00018130106,0.0002066556,0.0012560999,0.0006933506,0.009072903,0.9875914,0.00003004157],"about_ca_topic_score_codex":0.0027717643,"about_ca_topic_score_gemma":0.004979006,"teacher_disagreement_score":0.048939697,"about_ca_system_score_codex":0.002998457,"about_ca_system_score_gemma":0.0074658287,"threshold_uncertainty_score":0.1637196},"labels":[],"label_agreement":null},{"id":"W2014517001","doi":"10.1142/s0218213004001697","title":"TEMPORAL VERSUS LATEST SNAPSHOT WEB USAGE MINING USING KOHONEN SOM AND MODIFIED KOHONEN SOM BASED ON THE PROPERTIES OF ROUGH SETS THEORY","year":2004,"lang":"en","type":"article","venue":"International Journal of Artificial Intelligence Tools","topic":"Data Mining Algorithms and Applications","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":"Saint Mary's University","funders":"","keywords":"Self-organizing map; Computer science; Cluster analysis; Web mining; Data mining; Snapshot (computer storage); The Internet; Hierarchical clustering; Rough set; Artificial intelligence; Web page; Database; World Wide Web","score_opus":0.16912268507542091,"score_gpt":0.33207829162278074,"score_spread":0.16295560654735983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014517001","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23199086,0.00075593183,0.7610939,0.00017735393,0.00011181818,0.00008774927,0.00024008118,0.0005286934,0.0050135683],"genre_scores_gemma":[0.7774797,0.0003522057,0.22061186,0.000033707736,0.000029388748,0.000056277717,0.00019798633,0.000040039005,0.0011988373],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995906,0.00007940032,0.00004644388,0.000059208072,0.00018459387,0.000039795857],"domain_scores_gemma":[0.99911314,0.00035986645,0.00007129648,0.00010485723,0.00030831603,0.000042428015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089831237,0.0002549284,0.0004952566,0.0013056826,0.00028889248,0.001173673,0.00066144427,0.00043743008,0.0006483371],"category_scores_gemma":[0.003012637,0.00021252109,0.0008185008,0.0012520512,0.000312812,0.0015784708,0.00044720204,0.00038055924,0.00013369968],"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":[0.0008465285,0.00019969093,0.02342216,0.0004948732,0.0004433507,0.00050490425,0.00070308906,0.16805634,0.037625164,0.020215109,0.0016267856,0.74586195],"study_design_scores_gemma":[0.000023142014,0.00014742816,0.015735578,0.000048268914,0.00010763294,0.00042680872,0.00037863405,0.95108306,0.014319971,0.015393277,0.0022667672,0.000069444955],"about_ca_topic_score_codex":0.0021044721,"about_ca_topic_score_gemma":0.00304998,"teacher_disagreement_score":0.0021044721,"about_ca_system_score_codex":0.00035143993,"about_ca_system_score_gemma":0.0003278927,"threshold_uncertainty_score":0.004750788},"labels":[],"label_agreement":null},{"id":"W201498424","doi":"10.1007/978-3-642-37899-7_16","title":"Using Semantic-Based Association Rule Mining for Improving Clinical Text Retrieval","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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":"York University","funders":"","keywords":"Computer science; Information retrieval; Query expansion; Association rule learning; Ranking (information retrieval); Context (archaeology); Data mining; Unified Medical Language System; Ontology; Probabilistic logic; Artificial intelligence","score_opus":0.048396626243005496,"score_gpt":0.3171973309148056,"score_spread":0.2688007046718001,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W201498424","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13445202,0.012084754,0.8262753,0.0026204695,0.0018618152,0.0009464492,0.007302493,0.00642628,0.008030422],"genre_scores_gemma":[0.3316412,0.0033540535,0.64897126,0.0008869737,0.0011430882,0.00045402852,0.011208116,0.00022648564,0.0021147495],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955562,0.0009840546,0.0010112583,0.0007603847,0.0014718507,0.00021628337],"domain_scores_gemma":[0.9921823,0.004402131,0.00057229394,0.0005625223,0.0021188364,0.00016181727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038786745,0.0011841282,0.0023197245,0.0089161815,0.0008428869,0.0025122722,0.001512319,0.0014179143,0.0028208497],"category_scores_gemma":[0.01526421,0.00042027523,0.0023017225,0.007112153,0.00040030282,0.0030639702,0.0016511133,0.0015644365,0.0035137648],"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":[0.0008402731,0.0010300716,0.020266104,0.0010744284,0.0006950826,0.0006602166,0.0002180728,0.0064934613,0.021995157,0.003036892,0.018027961,0.92566216],"study_design_scores_gemma":[0.0005694176,0.0017079988,0.034167584,0.00088018354,0.0035881186,0.009067952,0.0009396296,0.7809162,0.06692608,0.059758004,0.041085627,0.00039325558],"about_ca_topic_score_codex":0.0012911655,"about_ca_topic_score_gemma":0.00231833,"teacher_disagreement_score":0.0089161815,"about_ca_system_score_codex":0.0003863171,"about_ca_system_score_gemma":0.001595707,"threshold_uncertainty_score":0.02051258},"labels":[],"label_agreement":null},{"id":"W2014995154","doi":"10.1016/s0898-1221(03)00034-8","title":"Learning classification rules from data","year":2003,"lang":"en","type":"article","venue":"Computers & Mathematics with Applications","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":32,"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":"Overfitting; Rule induction; Pruning; Classification rule; Heuristic; Artificial intelligence; Mathematics; Machine learning; Class (philosophy); Function (biology); Set (abstract data type); Relevance (law); Data mining; Process (computing); Computer science; Artificial neural network","score_opus":0.04934268682491376,"score_gpt":0.2748702871220373,"score_spread":0.22552760029712354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014995154","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.088929035,0.0027395908,0.88708854,0.0030632582,0.00088558765,0.00095325103,0.0039376323,0.004715876,0.007687181],"genre_scores_gemma":[0.44867396,0.002711156,0.5254516,0.00086524186,0.0005841263,0.00091218395,0.015752787,0.0002243418,0.0048246775],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969151,0.00048264122,0.00043740484,0.00080767093,0.0012086674,0.00014847246],"domain_scores_gemma":[0.99011153,0.006857823,0.00051230105,0.0011870265,0.0011709103,0.00016056448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002744094,0.0012034543,0.0016048019,0.005137398,0.00084252347,0.0034407992,0.0024148296,0.001467648,0.0026880326],"category_scores_gemma":[0.019137023,0.0005386154,0.0018112323,0.0029930763,0.0007795235,0.0035996449,0.0015712072,0.0031461706,0.0027063966],"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":[0.0002983906,0.0004777791,0.013002155,0.0006628642,0.00032460561,0.000904533,0.000329774,0.020387515,0.005737561,0.013476328,0.016633254,0.9277652],"study_design_scores_gemma":[0.00013333932,0.0003382539,0.004711265,0.00082037156,0.00070448837,0.0015575076,0.0004920816,0.75570023,0.022216458,0.17395392,0.039276104,0.00009595493],"about_ca_topic_score_codex":0.0014306036,"about_ca_topic_score_gemma":0.00189338,"teacher_disagreement_score":0.005137398,"about_ca_system_score_codex":0.0005792215,"about_ca_system_score_gemma":0.0014625787,"threshold_uncertainty_score":0.0145123005},"labels":[],"label_agreement":null},{"id":"W2015646334","doi":"10.1109/mis.2009.59","title":"Improving the Behavior of Intelligent Tutoring Agents with Data Mining","year":2009,"lang":"en","type":"article","venue":"IEEE Intelligent Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Université de Montpellier","keywords":"Computer science; Association rule learning; Data mining; K-optimal pattern discovery; Intelligent agent; Artificial intelligence; Sequential Pattern Mining; Intelligent decision support system; Machine learning; Knowledge extraction; Data science","score_opus":0.08249325113046038,"score_gpt":0.3094061991097688,"score_spread":0.22691294797930842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015646334","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48206547,0.00036429445,0.51002,0.0005928119,0.00005322023,0.0001978992,0.00031191256,0.0034167757,0.0029775626],"genre_scores_gemma":[0.80143017,0.00011167107,0.19683312,0.000080999125,0.000018892395,0.00010531213,0.00032179814,0.0000534619,0.0010445497],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990202,0.0004499075,0.000087874694,0.00017658195,0.0002162669,0.000049167178],"domain_scores_gemma":[0.99329007,0.0041837757,0.00049261324,0.0005335667,0.0013191112,0.00018084471],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021092694,0.00058607035,0.00065445673,0.0008905491,0.00031761627,0.0009917312,0.0008484821,0.0007551774,0.00076801516],"category_scores_gemma":[0.01862635,0.00021886826,0.00027035206,0.00066580606,0.00018945403,0.0012456131,0.00052430166,0.00067258,0.0005243846],"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":[0.0006967139,0.0013527098,0.091209315,0.00024987012,0.00022457931,0.00028493535,0.00069449225,0.14231916,0.01977328,0.0016872567,0.0033062235,0.7382015],"study_design_scores_gemma":[0.000026117024,0.00015365791,0.0048699537,0.000013730376,0.00004425757,0.00007623692,0.00009841734,0.9819292,0.008942219,0.002757533,0.0010748991,0.0000137287125],"about_ca_topic_score_codex":0.0023610822,"about_ca_topic_score_gemma":0.0026336336,"teacher_disagreement_score":0.0023610822,"about_ca_system_score_codex":0.00036695338,"about_ca_system_score_gemma":0.000768383,"threshold_uncertainty_score":0.011155069},"labels":[],"label_agreement":null},{"id":"W2016120275","doi":"10.1109/tevc.2013.2292181","title":"Guest Editorial: Special Issue on Advances in Multiobjective Evolutionary Algorithms for Data Mining","year":2014,"lang":"en","type":"editorial","venue":"IEEE Transactions on Evolutionary Computation","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Evolutionary algorithm; Snapshot (computer storage); Computer science; Evolutionary computation; Data science; Domain (mathematical analysis); Multi-objective optimization; Data mining; Machine learning; Artificial intelligence; Mathematics","score_opus":0.02128598396408002,"score_gpt":0.3156270003797391,"score_spread":0.29434101641565913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016120275","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007821077,0.0032291494,0.0004149619,0.015576052,0.978954,0.000018780413,0.0000644377,0.000055032553,0.0016093479],"genre_scores_gemma":[0.000556467,0.0032906663,0.00022056352,0.0051244935,0.9812758,0.000021362208,0.0000537009,0.00005504683,0.009401821],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969285,0.0003980684,0.00034969836,0.0004264879,0.0016342016,0.00026303262],"domain_scores_gemma":[0.9848453,0.0043451805,0.0010701888,0.00032915102,0.0071073133,0.0023027463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004653542,0.002710973,0.0028782578,0.0032831002,0.0019173694,0.006772111,0.002149876,0.0058435495,0.020547707],"category_scores_gemma":[0.015823351,0.00076344836,0.0022505203,0.0014506549,0.001205504,0.0027780016,0.0013199332,0.010159103,0.010707825],"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":[0.000055603905,0.000023174427,0.000058338337,0.00018566904,0.000025616842,0.000102942206,0.000006924629,0.000063109044,0.00011307898,0.00034189015,0.99056,0.008463702],"study_design_scores_gemma":[0.00008888483,0.00007144977,0.0005117189,0.00035372365,0.00008083329,0.00036458886,0.000034752768,0.00060149335,0.00036498703,0.0016142093,0.9958903,0.000023091661],"about_ca_topic_score_codex":0.0004457522,"about_ca_topic_score_gemma":0.0017058639,"teacher_disagreement_score":0.020547707,"about_ca_system_score_codex":0.0015491195,"about_ca_system_score_gemma":0.0018952938,"threshold_uncertainty_score":0.06873894},"labels":[],"label_agreement":null},{"id":"W2016981647","doi":"10.1145/1562849.1562853","title":"FpViz","year":2009,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Zoom; Process (computing); Representation (politics); Data mining; Visualization; Information retrieval; Knowledge extraction; Artificial intelligence","score_opus":0.00986806599778669,"score_gpt":0.24562149610843204,"score_spread":0.23575343011064534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016981647","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007457147,0.0027686614,0.36954206,0.002799958,0.0011853286,0.000527972,0.047104668,0.40256178,0.16605249],"genre_scores_gemma":[0.09910266,0.006164966,0.39644814,0.0021546597,0.0007433107,0.0018786698,0.18624805,0.0899678,0.21729167],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885595,0.00014859761,0.000068061694,0.0001993864,0.00058227545,0.00014573542],"domain_scores_gemma":[0.9986118,0.00044379287,0.000093721275,0.0002834992,0.0004476329,0.000119558856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013634241,0.0017310616,0.0008696988,0.0031186724,0.0008630768,0.003762626,0.0030102504,0.0017530175,0.13752398],"category_scores_gemma":[0.0065242485,0.0007590945,0.0013107356,0.0028108521,0.00052610534,0.0049751806,0.0035538597,0.0017517452,0.0680347],"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":[0.0005166849,0.0000713782,0.0010138287,0.0008018095,0.00005825196,0.0003458377,0.00042540228,0.0022259492,0.0056585125,0.028868983,0.6482261,0.3117873],"study_design_scores_gemma":[0.000121138284,0.00006191323,0.0011055857,0.00017397462,0.00003070761,0.0006764539,0.00009915223,0.012556007,0.0068666926,0.019459447,0.9587811,0.00006769653],"about_ca_topic_score_codex":0.0029299732,"about_ca_topic_score_gemma":0.0020044444,"teacher_disagreement_score":0.13752398,"about_ca_system_score_codex":0.0009099273,"about_ca_system_score_gemma":0.00096063607,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W2017386570","doi":"10.1145/2695664.2695823","title":"FOSHU","year":2015,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Database transaction; Data mining; Task (project management); Profit (economics); Execution time; Database; Distributed computing","score_opus":0.06242702842447991,"score_gpt":0.2752522185367186,"score_spread":0.2128251901122387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017386570","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026643582,0.0036487146,0.6022083,0.0022293853,0.0014996026,0.0009850524,0.036429085,0.09449752,0.23185879],"genre_scores_gemma":[0.15909299,0.0032062605,0.54874974,0.0019115225,0.00050282653,0.0011589316,0.096418194,0.005133435,0.18382609],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990638,0.00009443062,0.00008543146,0.00030604514,0.00035243723,0.00009796913],"domain_scores_gemma":[0.9990175,0.00019391219,0.00009538109,0.00030040782,0.00031863965,0.00007411368],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006450788,0.0010097206,0.0006915221,0.0027138614,0.0009150705,0.0018595443,0.0019349203,0.0009498101,0.08882043],"category_scores_gemma":[0.0035594467,0.00044880476,0.0008092052,0.0025754585,0.00044928203,0.0032495416,0.001985407,0.00078802364,0.05705954],"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":[0.00068005465,0.00013237886,0.002219769,0.0007367326,0.00008689023,0.00035841932,0.00016161927,0.006217753,0.010838732,0.03742132,0.16928294,0.7718633],"study_design_scores_gemma":[0.00010180892,0.00017350318,0.0012881329,0.00012807091,0.00003854227,0.0009891039,0.00014177118,0.044570908,0.022577692,0.048127927,0.88179237,0.00007017868],"about_ca_topic_score_codex":0.0017330701,"about_ca_topic_score_gemma":0.0021260139,"teacher_disagreement_score":0.91117954,"about_ca_system_score_codex":0.00085276004,"about_ca_system_score_gemma":0.0012082729,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W2017733008","doi":"10.1109/iit.2007.4430394","title":"Dynamic index selection in data warehouses","year":2007,"lang":"en","type":"preprint","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Search engine indexing; Data warehouse; Workload; Data mining; Selection (genetic algorithm); Overhead (engineering); Index (typography); Task (project management); Star schema; Set (abstract data type); Database index; Database; Information retrieval; Database design; Machine learning; Engineering","score_opus":0.05316115769001122,"score_gpt":0.3406875272513821,"score_spread":0.2875263695613709,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017733008","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16824459,0.0021789602,0.8165085,0.0005669932,0.00013266085,0.000231893,0.0007279049,0.009167525,0.002241019],"genre_scores_gemma":[0.5113572,0.00088211155,0.48317093,0.00019046298,0.00014464684,0.00022024373,0.0020126188,0.00045504252,0.0015667737],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964779,0.00077389774,0.00036421148,0.00069744745,0.0014470982,0.0002394318],"domain_scores_gemma":[0.99352723,0.0030826428,0.00047959803,0.0016074321,0.000974823,0.00032825547],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027859174,0.000757355,0.0014469636,0.0023427878,0.0011185836,0.00262522,0.00261439,0.0008043959,0.0007169563],"category_scores_gemma":[0.008871146,0.0011081579,0.000799432,0.0045720343,0.00069287873,0.0033237212,0.0016499779,0.0008106329,0.00069481024],"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":[0.0011036665,0.0006471695,0.020387527,0.00050870964,0.00021954627,0.0011910052,0.0012286894,0.09441779,0.069775075,0.013667007,0.01496539,0.78188837],"study_design_scores_gemma":[0.00014642504,0.00025720315,0.0059417146,0.000044032535,0.000105937776,0.0013048633,0.0004999066,0.8981431,0.04902509,0.030230531,0.014214339,0.00008686739],"about_ca_topic_score_codex":0.0015247863,"about_ca_topic_score_gemma":0.0013330824,"teacher_disagreement_score":0.0027859174,"about_ca_system_score_codex":0.00057499984,"about_ca_system_score_gemma":0.00078531896,"threshold_uncertainty_score":0.014733553},"labels":[],"label_agreement":null},{"id":"W2019503106","doi":"10.1504/ijgcrsis.2010.036981","title":"Associative classification using patterns from nested granules","year":2010,"lang":"en","type":"article","venue":"International Journal of Granular Computing Rough Sets and Intelligent Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Associative property; Computer science; Pattern recognition (psychology); Artificial intelligence; Mathematics; Pure mathematics","score_opus":0.034672428804420584,"score_gpt":0.3072841038350189,"score_spread":0.27261167503059835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019503106","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15819132,0.0005267407,0.83231175,0.0005463987,0.00013036745,0.00044431473,0.0011074245,0.0011911511,0.0055505545],"genre_scores_gemma":[0.64347625,0.0002348984,0.35252148,0.00010977164,0.00010617639,0.00038008438,0.0014109248,0.00007685882,0.001683626],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99783176,0.00035349827,0.00037236192,0.00045220857,0.0008150299,0.00017520072],"domain_scores_gemma":[0.9937191,0.0025360633,0.0009146151,0.0013792928,0.0012279131,0.00022293013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015635139,0.0005697933,0.00089367124,0.0036706917,0.000781257,0.0026255809,0.0010234583,0.00078660005,0.0021725295],"category_scores_gemma":[0.012470717,0.00027080817,0.00087104196,0.004477249,0.0010996447,0.0040074945,0.0016809938,0.0009820163,0.00052509265],"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":[0.0006684328,0.0002876022,0.03661733,0.0005993484,0.00020625858,0.001601853,0.0019239767,0.03701359,0.014857125,0.10514028,0.0058651716,0.7952191],"study_design_scores_gemma":[0.000081599654,0.00023916208,0.013615707,0.00019892595,0.00014364545,0.0013214858,0.0009337927,0.6257347,0.011063584,0.33310094,0.013469935,0.000096561766],"about_ca_topic_score_codex":0.0013248129,"about_ca_topic_score_gemma":0.0013301318,"teacher_disagreement_score":0.0036706917,"about_ca_system_score_codex":0.0005252015,"about_ca_system_score_gemma":0.0007732711,"threshold_uncertainty_score":0.008268774},"labels":[],"label_agreement":null},{"id":"W2020548986","doi":"10.1109/icmla.2012.187","title":"Extraction of Strong Associations in Classes of Similarities","year":2012,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Computer science; Exploit; Association rule learning; Process (computing); Data mining; Quality (philosophy); Artificial intelligence; Pattern recognition (psychology); Information retrieval; Machine learning","score_opus":0.041684373841672916,"score_gpt":0.3203470294649068,"score_spread":0.2786626556232339,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020548986","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19459221,0.0014147639,0.7838773,0.0007942144,0.00022535812,0.00091738964,0.0049546934,0.0031261912,0.010097958],"genre_scores_gemma":[0.46938902,0.0006397678,0.5192259,0.0001577259,0.00034449072,0.0008068818,0.006909641,0.0002615354,0.0022649402],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9920353,0.0006670503,0.0012535279,0.0020534217,0.0034631935,0.00052743923],"domain_scores_gemma":[0.9808524,0.009004164,0.0037244472,0.0025961732,0.003205412,0.0006173039],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030956506,0.00109952,0.0019471834,0.016557377,0.0020878073,0.004309592,0.0017623638,0.0017968734,0.0028168769],"category_scores_gemma":[0.022648603,0.00088739773,0.0021949105,0.011973739,0.0013778934,0.005065405,0.002546259,0.001963865,0.0016653974],"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":[0.00063526887,0.00066308177,0.061719783,0.0010484491,0.0005241318,0.0018798687,0.0023532538,0.006815625,0.023070881,0.043198764,0.008953043,0.84913784],"study_design_scores_gemma":[0.00026208637,0.00081317266,0.12397553,0.0010231396,0.0011037564,0.008925622,0.0038850056,0.3319252,0.057696953,0.38593653,0.08396876,0.00048430316],"about_ca_topic_score_codex":0.0014542483,"about_ca_topic_score_gemma":0.0020846743,"teacher_disagreement_score":0.016557377,"about_ca_system_score_codex":0.00092903833,"about_ca_system_score_gemma":0.002322715,"threshold_uncertainty_score":0.016371608},"labels":[],"label_agreement":null},{"id":"W202209444","doi":"10.1007/978-3-319-03410-2_3","title":"Clustering Items in Time-Stamped Databases Induced by Stability","year":2013,"lang":"en","type":"book-chapter","venue":"Intelligent systems reference library","topic":"Data Mining Algorithms and Applications","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 Alberta","funders":"","keywords":"Partition (number theory); Variation (astronomy); Cluster analysis; Stability (learning theory); Computer science; Cluster (spacecraft); Degree (music); Database; Data mining; Class (philosophy); Mathematics; Artificial intelligence; Machine learning","score_opus":0.084136961069966,"score_gpt":0.2619171409232814,"score_spread":0.1777801798533154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W202209444","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22222887,0.0022545268,0.7689727,0.0005444796,0.00019912218,0.00019567924,0.0024457166,0.0009720469,0.0021869135],"genre_scores_gemma":[0.6909378,0.0017141603,0.2962365,0.00016433581,0.00030317585,0.00022169926,0.0068154195,0.00016712665,0.003439845],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969908,0.00035544712,0.00040654585,0.0007441874,0.0013152654,0.00018765163],"domain_scores_gemma":[0.99036205,0.0043154154,0.001242002,0.0014366636,0.0022985893,0.00034528543],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001890386,0.0004877123,0.0014494143,0.005556798,0.0008269417,0.003187311,0.0025043874,0.00093020656,0.0015907994],"category_scores_gemma":[0.016309997,0.0005914696,0.0010103779,0.010921225,0.00094077934,0.0034238556,0.0018741632,0.0010193645,0.0007704132],"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":[0.0023750123,0.00030560023,0.04492767,0.0010682449,0.00056756847,0.001150737,0.0012577103,0.22995792,0.03160022,0.08395611,0.012449637,0.59038365],"study_design_scores_gemma":[0.00005092083,0.00024105806,0.007973152,0.000087254666,0.0001355914,0.0006749167,0.00041663964,0.8837916,0.0093266405,0.09194339,0.0053021396,0.000056621157],"about_ca_topic_score_codex":0.0019468728,"about_ca_topic_score_gemma":0.0021103353,"teacher_disagreement_score":0.005556798,"about_ca_system_score_codex":0.0010505414,"about_ca_system_score_gemma":0.00089820544,"threshold_uncertainty_score":0.009997487},"labels":[],"label_agreement":null},{"id":"W2025081659","doi":"10.5539/cis.v2n2p103","title":"Study on the Data Mining Algorithm Based on Positive and Negative Association Rules","year":2009,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Association rule learning; Computer science; Association (psychology); Data mining; Computation; Correlation; Measure (data warehouse); Algorithm; Apriori algorithm; Mathematics; Psychology","score_opus":0.029584073102321827,"score_gpt":0.2858691530126532,"score_spread":0.2562850799103314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025081659","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025627654,0.0031132228,0.9666899,0.0007057172,0.00018449253,0.0001220835,0.00005259185,0.00020688091,0.003297542],"genre_scores_gemma":[0.26995474,0.00544672,0.7206634,0.0005896218,0.0005747177,0.0002980841,0.00036911102,0.000074487674,0.0020291274],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99228066,0.0024406512,0.00079202803,0.0015043768,0.0028363748,0.00014585536],"domain_scores_gemma":[0.9836271,0.010871919,0.0005419344,0.0009916975,0.0038148542,0.00015248345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009300096,0.0008944631,0.0012281828,0.0025613336,0.0011692395,0.002502863,0.001908284,0.0012696517,0.0010376499],"category_scores_gemma":[0.030364716,0.00041957587,0.0009636883,0.0028457416,0.0012716068,0.006605251,0.0008713897,0.0017161873,0.00064882665],"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":[0.00027401996,0.0003178687,0.019303484,0.001068968,0.00027345816,0.0004546928,0.00072764617,0.0324434,0.0072401664,0.14821154,0.0040702545,0.7856145],"study_design_scores_gemma":[0.00015424867,0.0006131684,0.0048513734,0.00058520236,0.0004798627,0.004223521,0.0006461993,0.7417935,0.027416684,0.17352457,0.04554781,0.00016386007],"about_ca_topic_score_codex":0.00055905536,"about_ca_topic_score_gemma":0.00031535153,"teacher_disagreement_score":0.009300096,"about_ca_system_score_codex":0.0005788565,"about_ca_system_score_gemma":0.0011718442,"threshold_uncertainty_score":0.049184203},"labels":[],"label_agreement":null},{"id":"W2026176068","doi":"10.1007/s10489-007-0096-5","title":"Updating generalized association rules with evolving taxonomies","year":2007,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":9,"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":"Mitacs","keywords":"Computer science; Association rule learning; Association (psychology); Artificial intelligence; Data mining; Epistemology","score_opus":0.016192954368249263,"score_gpt":0.24776086061997635,"score_spread":0.23156790625172707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026176068","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23326336,0.0021219861,0.7530223,0.0012753347,0.0010254544,0.0004927307,0.001861997,0.0039288956,0.00300808],"genre_scores_gemma":[0.3998602,0.0006794545,0.59314823,0.0004089663,0.0003199146,0.00025233626,0.0029056375,0.00030928268,0.0021160364],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996024,0.0009347284,0.00053151953,0.0010556863,0.001256787,0.0001971689],"domain_scores_gemma":[0.9719811,0.015577546,0.0011756512,0.0052931183,0.0054561268,0.0005164422],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005694737,0.00096844044,0.0021582628,0.004602559,0.0008364314,0.0027638976,0.0046318257,0.0018662616,0.0032249144],"category_scores_gemma":[0.048843134,0.0010769895,0.0015548822,0.005443022,0.00075748784,0.0054974984,0.0022729684,0.0021804308,0.0009111662],"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":[0.00063921465,0.0005203384,0.023426235,0.000448236,0.0006517804,0.0005948195,0.0006592124,0.103697985,0.006434013,0.007059097,0.010357125,0.84551185],"study_design_scores_gemma":[0.00012683407,0.0001692051,0.0045084986,0.000120747616,0.00046849577,0.0006281784,0.0002556251,0.94650173,0.0041545746,0.035507552,0.0075021386,0.000056398334],"about_ca_topic_score_codex":0.0062564495,"about_ca_topic_score_gemma":0.01497426,"teacher_disagreement_score":0.0062564495,"about_ca_system_score_codex":0.0007361005,"about_ca_system_score_gemma":0.0016804338,"threshold_uncertainty_score":0.030116975},"labels":[],"label_agreement":null},{"id":"W2027440536","doi":"10.1007/s10707-006-9827-8","title":"Mining Co-Location Patterns with Rare Events from Spatial Data Sets","year":2006,"lang":"en","type":"article","venue":"GeoInformatica","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":156,"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); Data mining; Geography; Scale (ratio); Spatial ecology; Feature (linguistics); Scalability; Computer science; Measure (data warehouse); Common spatial pattern; Spatial analysis; Cartography; Pattern recognition (psychology); Artificial intelligence; Mathematics; Statistics; Remote sensing; Ecology; Database; Biology","score_opus":0.019559372552580914,"score_gpt":0.25377813719046366,"score_spread":0.23421876463788274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2027440536","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5034913,0.003053418,0.47557062,0.0014384704,0.00022027652,0.0003604033,0.01161135,0.0019262,0.00232795],"genre_scores_gemma":[0.8098085,0.00110291,0.16689092,0.00015774918,0.00031055947,0.0002696734,0.020284053,0.0000938624,0.0010817285],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967546,0.0004910897,0.0004749267,0.00096403924,0.0010960384,0.00021935217],"domain_scores_gemma":[0.9817386,0.011717777,0.0027980758,0.0020579011,0.0011646898,0.00052291836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020091217,0.0011388459,0.001749836,0.0085653365,0.00093772734,0.0022567797,0.0023348727,0.0015441425,0.0010257019],"category_scores_gemma":[0.017398149,0.0006433903,0.0017283561,0.008916751,0.00084991957,0.0029696373,0.0017190629,0.0016245221,0.00085428375],"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":[0.0019657412,0.0010294528,0.4223977,0.001574052,0.0020127788,0.008147472,0.0013852828,0.0807876,0.015545771,0.012808498,0.012172883,0.44017276],"study_design_scores_gemma":[0.00019036377,0.0004480361,0.07581015,0.00026497355,0.001084139,0.01146979,0.002189005,0.8229499,0.014078414,0.05795076,0.013442108,0.00012242273],"about_ca_topic_score_codex":0.0028768128,"about_ca_topic_score_gemma":0.005866559,"teacher_disagreement_score":0.0085653365,"about_ca_system_score_codex":0.00051299424,"about_ca_system_score_gemma":0.001254956,"threshold_uncertainty_score":0.010625362},"labels":[],"label_agreement":null},{"id":"W2028470267","doi":"10.1017/s0269888906000737","title":"A survey of Knowledge Discovery and Data Mining process models","year":2006,"lang":"en","type":"article","venue":"The Knowledge Engineering Review","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":388,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Data science; Process (computing); Business process discovery; Interoperability; Knowledge extraction; Process mining; Process modeling; Automation; Knowledge management; Data mining; Work in process; Engineering; Business process; Business process management; World Wide Web; Business process modeling","score_opus":0.06022485778747027,"score_gpt":0.31272350794040427,"score_spread":0.252498650152934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028470267","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005718871,0.2684447,0.6773576,0.010481763,0.0008264425,0.000398426,0.0018764855,0.0010598615,0.03383582],"genre_scores_gemma":[0.06520494,0.49088225,0.4250058,0.0025001992,0.0015911249,0.0009789361,0.003995808,0.0002517941,0.009589125],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9946496,0.0012170689,0.00069336244,0.0008353121,0.0024156675,0.00018894977],"domain_scores_gemma":[0.99293035,0.0049639903,0.00039097515,0.00053404784,0.0010711666,0.00010944149],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005959783,0.0016809073,0.00220777,0.007423976,0.0009979659,0.0060854335,0.0038721047,0.0025495964,0.0033852598],"category_scores_gemma":[0.011960473,0.0008168241,0.001744613,0.015939051,0.0014444202,0.008557822,0.0016221228,0.0022640636,0.0029029257],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010883587,0.00019905661,0.002887725,0.005439402,0.00018505237,0.00037810148,0.00043502433,0.025488507,0.0007138635,0.3943774,0.025139539,0.5446475],"study_design_scores_gemma":[0.00003369687,0.00013710972,0.0013145705,0.0024871314,0.00022079177,0.0014615228,0.00038068893,0.10244141,0.001653251,0.39795488,0.49179596,0.00011898459],"about_ca_topic_score_codex":0.0036236043,"about_ca_topic_score_gemma":0.0023996443,"teacher_disagreement_score":0.007423976,"about_ca_system_score_codex":0.0028841565,"about_ca_system_score_gemma":0.0044165077,"threshold_uncertainty_score":0.031518698},"labels":[],"label_agreement":null},{"id":"W2028572284","doi":"10.1145/846183.846208","title":"Discovering geographic knowledge in data rich environments","year":2000,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"City, University of London; University of Utah; University of Florida; Florida State University","keywords":"Data science; Identification (biology); Computer science; Geographic information system; Knowledge extraction; Data mining; Geography; Cartography","score_opus":0.05390222068445348,"score_gpt":0.2862366298714703,"score_spread":0.2323344091870168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028572284","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21038339,0.014947167,0.67418057,0.021293798,0.0017261382,0.00054514717,0.03311635,0.004486203,0.039321225],"genre_scores_gemma":[0.5976043,0.0103276735,0.34288597,0.0013835528,0.00041132295,0.00025706962,0.03137835,0.00021700078,0.015534799],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989304,0.00027743986,0.00006953018,0.00026229178,0.0003460106,0.0001142323],"domain_scores_gemma":[0.9979961,0.0011692488,0.0001426311,0.00028388205,0.00029010602,0.000118122836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011998524,0.00039760215,0.000814627,0.0032485072,0.0014871774,0.003877477,0.0010756904,0.001293856,0.0042831516],"category_scores_gemma":[0.006962259,0.0005834575,0.00066494936,0.0049819555,0.0013361851,0.005466469,0.0046564555,0.001232277,0.0014128118],"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":[0.0005830548,0.00021164995,0.020178815,0.0013621047,0.00021731223,0.0031682295,0.00504635,0.08456948,0.004602861,0.19400726,0.09891484,0.58713806],"study_design_scores_gemma":[0.0000683147,0.000101797734,0.009708973,0.00041988443,0.00012855094,0.0009594487,0.0071066306,0.12153248,0.006282609,0.26859343,0.58495563,0.00014233634],"about_ca_topic_score_codex":0.004602766,"about_ca_topic_score_gemma":0.013865982,"teacher_disagreement_score":0.004602766,"about_ca_system_score_codex":0.0010814989,"about_ca_system_score_gemma":0.0008717801,"threshold_uncertainty_score":0.014328599},"labels":[],"label_agreement":null},{"id":"W2029068068","doi":"10.1109/cason.2013.6622608","title":"Finding groups of friends who are significant across multiple domains in social networks","year":2013,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":15,"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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Social network (sociolinguistics); Computer science; World Wide Web; Internet privacy; Data science; Social group; Social network analysis; Social media; Social relationship; Psychology; Social psychology","score_opus":0.022165374121302935,"score_gpt":0.27385967385029336,"score_spread":0.25169429972899043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029068068","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7808893,0.0025311464,0.1939784,0.0028391106,0.00019377869,0.0010113626,0.0058877245,0.0009274018,0.011741846],"genre_scores_gemma":[0.845354,0.0007744331,0.14781961,0.00016737927,0.0001436893,0.0003503171,0.0031711068,0.000041044583,0.002178465],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979873,0.00041826002,0.00017975438,0.0006197848,0.00067140965,0.00012349944],"domain_scores_gemma":[0.99246615,0.0041650645,0.0013456363,0.0008875552,0.000734853,0.00040064982],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012839772,0.00074848044,0.00080910185,0.0065755094,0.0021601326,0.0013251803,0.001089306,0.0011230283,0.0017388503],"category_scores_gemma":[0.009598775,0.00037876877,0.0009306693,0.0052975765,0.0008650054,0.003479148,0.0019261688,0.00077027775,0.0007497697],"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":[0.0008525351,0.0009820587,0.45145747,0.0015233938,0.0012459437,0.0024189448,0.007993447,0.011985078,0.0161168,0.016770285,0.016092358,0.47256163],"study_design_scores_gemma":[0.00024466656,0.0014000663,0.37676674,0.0008062651,0.0022204244,0.014364083,0.029866336,0.29182026,0.0392134,0.13528629,0.10760993,0.00040154197],"about_ca_topic_score_codex":0.0019584368,"about_ca_topic_score_gemma":0.004852455,"teacher_disagreement_score":0.0065755094,"about_ca_system_score_codex":0.00045322956,"about_ca_system_score_gemma":0.0005769111,"threshold_uncertainty_score":0.0067903996},"labels":[],"label_agreement":null},{"id":"W2030468582","doi":"10.4018/jitwe.2010040102","title":"A Pattern Language for Knowledge Discovery in a Semantic Web context","year":2010,"lang":"en","type":"article","venue":"International Journal of Information Technology and Web Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Rimouski","funders":"","keywords":"Computer science; Ontology; Semantic Web; Information retrieval; Interpretability; Knowledge extraction; Domain knowledge; Domain (mathematical analysis); Context (archaeology); Data science; Social Semantic Web; Data mining; Artificial intelligence","score_opus":0.0035057044033288205,"score_gpt":0.22955875037814122,"score_spread":0.2260530459748124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030468582","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00077523093,0.0004895887,0.9897906,0.0012632303,0.00024309549,0.00041963975,0.0012599133,0.002447282,0.0033113665],"genre_scores_gemma":[0.011376621,0.00075794494,0.98057085,0.000702374,0.00013000614,0.0010650761,0.0021353438,0.0003101763,0.002951694],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99375546,0.0017871013,0.0016931685,0.00090983364,0.0015849004,0.00026940412],"domain_scores_gemma":[0.9950098,0.0024471306,0.0005280745,0.0011194072,0.0006663085,0.00022937976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0057884236,0.0015916858,0.0019967242,0.005174958,0.0021853496,0.0065419823,0.00368926,0.0032644037,0.007638045],"category_scores_gemma":[0.0107916,0.0015519889,0.0045117647,0.009144602,0.0035034134,0.01382288,0.004748279,0.0049744938,0.005578203],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000117418684,0.00009909952,0.00048782912,0.0008456355,0.00012716476,0.0009957039,0.0009855932,0.0032619457,0.0019803476,0.83166385,0.025387496,0.13404793],"study_design_scores_gemma":[0.00008970912,0.000082911145,0.00021852594,0.00038617873,0.00007498946,0.0015912943,0.00041813476,0.046552163,0.002725267,0.69175047,0.25603926,0.00007116183],"about_ca_topic_score_codex":0.0034958094,"about_ca_topic_score_gemma":0.0041139363,"teacher_disagreement_score":0.007638045,"about_ca_system_score_codex":0.001367161,"about_ca_system_score_gemma":0.0033045104,"threshold_uncertainty_score":0.030612528},"labels":[],"label_agreement":null},{"id":"W2030926509","doi":"10.1007/s10489-007-0099-2","title":"DRFP-tree: disk-resident frequent pattern tree","year":2007,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":39,"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; Bottleneck; Scalability; Auxiliary memory; Tree (set theory); Process (computing); Memory management; Data mining; Database; Computer hardware; Embedded system; Semiconductor memory; Operating system","score_opus":0.02120298499643358,"score_gpt":0.27410308120586263,"score_spread":0.25290009620942905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030926509","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038013387,0.0020945938,0.86403203,0.0009785541,0.00053055724,0.00069603557,0.029036561,0.060292922,0.004325327],"genre_scores_gemma":[0.15108906,0.001160659,0.79158795,0.00038375272,0.00021847792,0.00054304,0.048698798,0.0015957868,0.0047225063],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998979,0.00016035624,0.00015958976,0.00021137371,0.00040756678,0.00008225945],"domain_scores_gemma":[0.99652845,0.0011622512,0.00029333986,0.0011081727,0.0006917758,0.00021606845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011857473,0.0007867856,0.0013197918,0.002680718,0.0006872647,0.0017589569,0.0029169174,0.0010101892,0.0071881847],"category_scores_gemma":[0.010382507,0.0006820211,0.0007227303,0.0040689916,0.00036553724,0.0034539995,0.0014900699,0.0010007727,0.004663179],"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":[0.0015447122,0.0002944808,0.0059227585,0.0011908715,0.00020380053,0.00072155165,0.0002451575,0.017986951,0.012727304,0.010018685,0.10802682,0.8411169],"study_design_scores_gemma":[0.00089333113,0.00095219153,0.0042369557,0.00023937349,0.00033844335,0.004693124,0.0003497179,0.7002275,0.036831908,0.10121831,0.14985389,0.0001652439],"about_ca_topic_score_codex":0.0011347964,"about_ca_topic_score_gemma":0.0018436884,"teacher_disagreement_score":0.0071881847,"about_ca_system_score_codex":0.0003156553,"about_ca_system_score_gemma":0.0012973184,"threshold_uncertainty_score":0.024046838},"labels":[],"label_agreement":null},{"id":"W2031600655","doi":"10.1109/3pgcic.2012.38","title":"Large-Scale Mining of Co-occurrences: Challenges and Solutions","year":2012,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Set (abstract data type); Pruning; Field (mathematics); Hash function; Scale (ratio); Database transaction; Data mining; Principal (computer security); Word (group theory); Information retrieval; Association rule learning; Core (optical fiber); Data science; Theoretical computer science; Database; Computer security; Mathematics","score_opus":0.07059073906538048,"score_gpt":0.2994183145528519,"score_spread":0.2288275754874714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2031600655","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043089956,0.013641675,0.9200337,0.015600624,0.00044501817,0.00034172894,0.0015400368,0.0033522353,0.0019548615],"genre_scores_gemma":[0.1765267,0.0059174816,0.8085147,0.0012929683,0.0010497117,0.0005050181,0.0037430804,0.00048565236,0.0019645893],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9862641,0.0039787297,0.0012687325,0.0036341061,0.0043005054,0.00055384677],"domain_scores_gemma":[0.9174751,0.053980663,0.0066140364,0.010989297,0.009100981,0.0018398641],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009471351,0.0021050922,0.0060877474,0.0057814606,0.0036597454,0.007021959,0.008137885,0.0048319018,0.0015301126],"category_scores_gemma":[0.046502154,0.002390581,0.002386906,0.016441567,0.0027586047,0.01210546,0.006495235,0.004585633,0.0022491608],"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":[0.0005698631,0.00085447275,0.028152322,0.002016757,0.0006752329,0.0022221517,0.0017072865,0.07927552,0.0071346397,0.025666252,0.052339192,0.7993864],"study_design_scores_gemma":[0.00015227134,0.00015311332,0.007350957,0.0002551932,0.00015370686,0.0037282102,0.0040532127,0.73403376,0.006898703,0.21235964,0.030644955,0.00021640636],"about_ca_topic_score_codex":0.0042899367,"about_ca_topic_score_gemma":0.0047902158,"teacher_disagreement_score":0.009471351,"about_ca_system_score_codex":0.0013319004,"about_ca_system_score_gemma":0.003031754,"threshold_uncertainty_score":0.050089896},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011099182,0.0011142149,0.9371065,0.00036089084,0.00024840143,0.00059865456,0.011422102,0.035313714,0.0027363952],"genre_scores_gemma":[0.049336765,0.00066888914,0.9275955,0.00015667427,0.00007818708,0.00037731088,0.017496742,0.0016080376,0.00268185],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986927,0.00025012152,0.00016913483,0.00019097835,0.00059378066,0.00010325359],"domain_scores_gemma":[0.9958216,0.0017424977,0.0002051335,0.0009794168,0.0010076294,0.00024368105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015159169,0.0010606641,0.0015075727,0.004260251,0.0010099462,0.002600781,0.002450834,0.0010646568,0.0086219935],"category_scores_gemma":[0.0110673215,0.00089736417,0.0014359833,0.0054732054,0.00052272185,0.003007544,0.0015351088,0.0016473422,0.0037425216],"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":[0.0011303263,0.00036172007,0.0038665838,0.0013799357,0.00027318104,0.0006747421,0.0004561777,0.0217341,0.008582065,0.028379953,0.101332664,0.8318286],"study_design_scores_gemma":[0.0006083248,0.00047464864,0.0024623964,0.00035971726,0.00038773808,0.0015824201,0.00033671464,0.7047969,0.015611367,0.12110339,0.15204732,0.00022902263],"about_ca_topic_score_codex":0.006871248,"about_ca_topic_score_gemma":0.016837912,"teacher_disagreement_score":0.0086219935,"about_ca_system_score_codex":0.0006007674,"about_ca_system_score_gemma":0.0028870625,"threshold_uncertainty_score":0.028843403},"labels":[],"label_agreement":null},{"id":"W2032603905","doi":"10.1109/icws.2014.62","title":"Data Mining from NoSQL Document-Append Style Storages","year":2014,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"NoSQL; Computer science; Append; Big data; Database; Semi-structured data; Relational database; XML database; Data science; World Wide Web; Information retrieval; Data mining; XML","score_opus":0.03531886967117394,"score_gpt":0.2844406312017156,"score_spread":0.24912176153054166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032603905","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0835688,0.001227099,0.85121983,0.001405793,0.0002451666,0.00074455113,0.011915437,0.04287366,0.00679964],"genre_scores_gemma":[0.3617506,0.0012706663,0.6059369,0.00046993498,0.00013265581,0.0006558424,0.0253701,0.0007967741,0.0036165286],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99658847,0.0005240157,0.00062855263,0.0004679768,0.0016182258,0.000172775],"domain_scores_gemma":[0.99444276,0.0015389066,0.0005137553,0.0018512917,0.0015030357,0.0001501582],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029607,0.0006816734,0.0008198212,0.0020556403,0.00091890735,0.0037908577,0.0025279664,0.0006908973,0.0021214758],"category_scores_gemma":[0.014576851,0.00043774335,0.00089121045,0.004225923,0.0005830464,0.004971931,0.0026544565,0.00095913804,0.0012347125],"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":[0.0024281822,0.0008594314,0.022870163,0.0017862883,0.00040942393,0.002056822,0.0014937336,0.067720994,0.045497973,0.06651865,0.057143062,0.73121524],"study_design_scores_gemma":[0.00024137834,0.0003699003,0.004778298,0.00017395831,0.0001245012,0.0012854612,0.0011323737,0.73333865,0.1038542,0.09149728,0.06308086,0.0001231814],"about_ca_topic_score_codex":0.0016770014,"about_ca_topic_score_gemma":0.0019392706,"teacher_disagreement_score":0.0037908577,"about_ca_system_score_codex":0.00069234637,"about_ca_system_score_gemma":0.0015776219,"threshold_uncertainty_score":0.015657842},"labels":[],"label_agreement":null},{"id":"W2033172859","doi":"10.1109/cgc.2012.99","title":"Finding Popular Friends in Social Networks","year":2012,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":63,"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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Social computing; Social media; World Wide Web; Social network (sociolinguistics); Set (abstract data type); Data science; Social media optimization; Internet privacy; Software","score_opus":0.033355662558357806,"score_gpt":0.2941836583961544,"score_spread":0.2608279958377966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033172859","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8378362,0.0033168977,0.13431211,0.002201342,0.00015354124,0.0004321978,0.0020608415,0.0006578537,0.019029055],"genre_scores_gemma":[0.94589955,0.0009970219,0.047268413,0.00012669113,0.000137718,0.00014930355,0.001347805,0.00005496983,0.0040185256],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99743,0.0008850347,0.00014877516,0.0006815487,0.00064369227,0.00021086974],"domain_scores_gemma":[0.9926408,0.004324788,0.0011172895,0.0007387263,0.0007536111,0.0004247014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014849211,0.00062639354,0.0007726483,0.0058093416,0.0025567573,0.00218912,0.0011105303,0.0014689959,0.002965983],"category_scores_gemma":[0.012992321,0.00056102267,0.0007438616,0.0043721953,0.0011228455,0.0070533585,0.00238851,0.0007042146,0.0011458172],"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":[0.0010871701,0.0007608232,0.37273958,0.0013821237,0.001014339,0.0030500833,0.015682377,0.030395087,0.009753974,0.07444161,0.027169015,0.46252388],"study_design_scores_gemma":[0.0001729598,0.0006495343,0.14541027,0.0004822438,0.00095813297,0.007154423,0.025650874,0.5150537,0.016355189,0.20189285,0.08591894,0.00030099318],"about_ca_topic_score_codex":0.003603146,"about_ca_topic_score_gemma":0.0062596044,"teacher_disagreement_score":0.0058093416,"about_ca_system_score_codex":0.00060867,"about_ca_system_score_gemma":0.00040575457,"threshold_uncertainty_score":0.009922206},"labels":[],"label_agreement":null},{"id":"W2033367161","doi":"10.1117/12.509158","title":"&lt;title&gt;Information granulation for web-based information support systems&lt;/title&gt;","year":2003,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Granulation; Computer science; Information retrieval; Cluster analysis; Task (project management); Space (punctuation); Granulation tissue; Data mining; Artificial intelligence; Materials science; Engineering","score_opus":0.009434802964965364,"score_gpt":0.21750634717458484,"score_spread":0.20807154420961949,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033367161","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017074687,0.023164686,0.8189476,0.015120712,0.0076728933,0.000956388,0.003975557,0.007914585,0.10517291],"genre_scores_gemma":[0.18037131,0.023203846,0.5908864,0.0036375881,0.00590983,0.00094445114,0.012045379,0.0037330494,0.17926818],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99857354,0.00024237705,0.00016595855,0.00022223726,0.0007176514,0.00007817035],"domain_scores_gemma":[0.9967429,0.0013150256,0.0001961985,0.000649605,0.0009540815,0.00014215684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00165688,0.0005903443,0.00082281313,0.0020408467,0.00074555783,0.003909797,0.0011315893,0.0011202268,0.048105687],"category_scores_gemma":[0.005547302,0.00032787016,0.0005933786,0.0036463437,0.0009197141,0.003806264,0.0012244746,0.0012028344,0.024688605],"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":[0.00022210226,0.0000724038,0.0009341664,0.000857218,0.000039169965,0.00020669536,0.00018418401,0.0066053,0.01261248,0.06863556,0.16254584,0.7470849],"study_design_scores_gemma":[0.000060666327,0.00020778783,0.0035132181,0.00060131826,0.000055255343,0.00063894846,0.00020975531,0.102341965,0.022633342,0.1254775,0.74415493,0.00010528678],"about_ca_topic_score_codex":0.0019270639,"about_ca_topic_score_gemma":0.0014823822,"teacher_disagreement_score":0.048105687,"about_ca_system_score_codex":0.0014963355,"about_ca_system_score_gemma":0.0008051651,"threshold_uncertainty_score":0.16092956},"labels":[],"label_agreement":null},{"id":"W2033486966","doi":"10.14778/2095686.2095695","title":"Mining flipping correlations from large datasets with taxonomies","year":2011,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Abstraction; Computer science; Range (aeronautics); Correlation; Data mining; Abstraction layer; Pattern recognition (psychology); Algorithm; Artificial intelligence; Theoretical computer science; Mathematics; Programming language","score_opus":0.029882836731726446,"score_gpt":0.21506378199320536,"score_spread":0.1851809452614789,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033486966","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44331685,0.0034226095,0.53247297,0.0014617359,0.00022545665,0.0005371852,0.012051997,0.0033470034,0.0031642257],"genre_scores_gemma":[0.65563893,0.00080761896,0.3268916,0.00035227928,0.0001779879,0.00050220534,0.014771214,0.00018931487,0.0006688255],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99463814,0.0011804828,0.00075678417,0.0014130449,0.0016982189,0.00031328478],"domain_scores_gemma":[0.9691158,0.019024232,0.0045267697,0.0045862254,0.002112228,0.0006349121],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003354864,0.0012051315,0.0014932496,0.008330451,0.0012772243,0.0020216762,0.0014204044,0.0012281652,0.0014049199],"category_scores_gemma":[0.036938246,0.0007782503,0.0013157041,0.011049361,0.0011119621,0.004292661,0.0024500228,0.0018448541,0.0007479838],"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":[0.0009361564,0.0005311644,0.33186653,0.0020503704,0.0011265171,0.0059060273,0.0023682553,0.04372829,0.020935688,0.01867781,0.017807653,0.55406547],"study_design_scores_gemma":[0.00021802483,0.0005911396,0.12879652,0.0006830272,0.0006116425,0.008595135,0.00349083,0.55833715,0.017562319,0.24719535,0.033669528,0.0002493786],"about_ca_topic_score_codex":0.0016019014,"about_ca_topic_score_gemma":0.0037631248,"teacher_disagreement_score":0.008330451,"about_ca_system_score_codex":0.0005606584,"about_ca_system_score_gemma":0.0013839384,"threshold_uncertainty_score":0.017742395},"labels":[],"label_agreement":null},{"id":"W2036541533","doi":"10.1115/1.4002812","title":"Developing Data Mining-Based Prognostic Models for CF-18 Aircraft","year":2011,"lang":"en","type":"article","venue":"Journal of Engineering for Gas Turbines and Power","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Prognostics; Data pre-processing; Data mining; Aircraft maintenance; Computer science; Process (computing); Key (lock); Preprocessor; Variety (cybernetics); Data modeling; Data model (GIS); Systems engineering; Engineering; Artificial intelligence; Software engineering","score_opus":0.08781260246157194,"score_gpt":0.27842667758614537,"score_spread":0.19061407512457343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036541533","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17256454,0.0004280224,0.8166428,0.0008820637,0.00004508897,0.0006064575,0.0030731237,0.0030005097,0.0027574417],"genre_scores_gemma":[0.5963839,0.0005555254,0.3969412,0.0000862445,0.000027248929,0.00053256465,0.0040158457,0.00005620917,0.0014011908],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997135,0.00005718636,0.000037784717,0.000055512355,0.00009634102,0.000039748254],"domain_scores_gemma":[0.99873203,0.0007009778,0.00012136745,0.000058262234,0.00035084423,0.000036499685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014815355,0.00079362927,0.00065481017,0.0013667184,0.00056405424,0.0010390532,0.0010721812,0.00070916,0.0007505063],"category_scores_gemma":[0.003952183,0.00042050725,0.000794841,0.001023705,0.0002672032,0.0008241683,0.0005158586,0.0008531908,0.00019687673],"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":[0.000051250925,0.00006426154,0.004862896,0.00006084846,0.00004419775,0.000059968308,0.000052425345,0.95812386,0.0008474387,0.0015972063,0.00071662525,0.033519067],"study_design_scores_gemma":[0.000003930685,0.000011702036,0.0003741075,0.0000043083514,0.0000067357555,0.0000070522615,0.000010159316,0.99822634,0.0004976468,0.0005175394,0.0003373233,0.0000030927658],"about_ca_topic_score_codex":0.08513455,"about_ca_topic_score_gemma":0.083731644,"teacher_disagreement_score":0.08513455,"about_ca_system_score_codex":0.0020138188,"about_ca_system_score_gemma":0.0033515496,"threshold_uncertainty_score":0.16927803},"labels":[],"label_agreement":null},{"id":"W2036896422","doi":"10.5539/ies.v1n4p28","title":"Binary Coded Web Access Pattern Tree in Education Domain","year":2008,"lang":"en","type":"article","venue":"International Education Studies","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Trie; Tree (set theory); Sequence database; Data mining; Binary tree; Web log analysis software; Web mining; Sequence (biology); Information retrieval; Theoretical computer science; Data structure; Algorithm; World Wide Web; Web server; Web service; Mathematics; The Internet; Static web page","score_opus":0.07354948903731333,"score_gpt":0.39518153112784654,"score_spread":0.3216320420905332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036896422","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3904274,0.00057833025,0.59298223,0.0008018432,0.0000705366,0.00038355627,0.0050953454,0.0023600564,0.007300708],"genre_scores_gemma":[0.7290391,0.00029576453,0.2604404,0.0001226993,0.000020706002,0.00019922806,0.0053639305,0.00006140939,0.004456747],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995365,0.00006519209,0.000041198055,0.00010223929,0.00019298877,0.000061876635],"domain_scores_gemma":[0.99882466,0.00042552745,0.00013613151,0.00014106304,0.00038215693,0.00009037648],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024501345,0.00020033584,0.00031644717,0.0022621287,0.00049545214,0.0007657807,0.00058596197,0.00053315616,0.001256311],"category_scores_gemma":[0.002561307,0.00015100795,0.00029702758,0.003690196,0.0003184938,0.0012046167,0.000496808,0.0004958759,0.00036717454],"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":[0.0007608991,0.0004512073,0.054917395,0.000504983,0.000075515745,0.0023204256,0.00075622724,0.06810013,0.026727393,0.0391133,0.014825884,0.7914466],"study_design_scores_gemma":[0.00004011826,0.0001254207,0.020753898,0.000049244714,0.000035484725,0.0021303205,0.0004094715,0.9041283,0.01430486,0.04273857,0.015250283,0.00003406881],"about_ca_topic_score_codex":0.007208246,"about_ca_topic_score_gemma":0.007881038,"teacher_disagreement_score":0.007208246,"about_ca_system_score_codex":0.00050191843,"about_ca_system_score_gemma":0.0008906408,"threshold_uncertainty_score":0.0143325925},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84137416,0.0017052009,0.14843868,0.0005946215,0.00011522637,0.00064393994,0.0027364485,0.00052870996,0.0038630483],"genre_scores_gemma":[0.8315214,0.000734617,0.16029349,0.00008731737,0.00011065163,0.00023629487,0.0046861856,0.00013968,0.0021904418],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958727,0.0010701382,0.00051373465,0.0008317692,0.0014405831,0.0002711444],"domain_scores_gemma":[0.9785499,0.013466986,0.0016823998,0.0022305965,0.0033948468,0.000675387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037671386,0.00077274657,0.0012676222,0.009019513,0.0018565889,0.003934144,0.0015886705,0.0009962161,0.0028909636],"category_scores_gemma":[0.017470416,0.0003978365,0.0018204423,0.009930285,0.00077583635,0.0049205865,0.0012378431,0.0008558542,0.0010442153],"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":[0.0036901643,0.001196653,0.46611944,0.002171104,0.0017317445,0.0013789387,0.00539901,0.00937406,0.029235035,0.01199526,0.0054426165,0.46226606],"study_design_scores_gemma":[0.00063045777,0.003815452,0.44116873,0.0009087085,0.006551427,0.005321964,0.039979443,0.31372762,0.08118379,0.06303122,0.04326843,0.0004126662],"about_ca_topic_score_codex":0.0018961962,"about_ca_topic_score_gemma":0.002310748,"teacher_disagreement_score":0.009019513,"about_ca_system_score_codex":0.00062466227,"about_ca_system_score_gemma":0.0010848014,"threshold_uncertainty_score":0.019922733},"labels":[],"label_agreement":null},{"id":"W2038552044","doi":"10.1515/jisys.2008.17.1-3.247","title":"Range Similarity and Satisfaction Measures for Buyers and Sellers in E-marketplaces","year":2008,"lang":"en","type":"article","venue":"Journal of Intelligent Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Range (aeronautics); Similarity (geometry); Computer science; Artificial intelligence; Mathematics; Engineering","score_opus":0.04144229712915248,"score_gpt":0.26923465345755104,"score_spread":0.22779235632839856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038552044","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5152546,0.00094810623,0.47250924,0.0004165025,0.00007115274,0.00025903626,0.000454758,0.0003251858,0.009761512],"genre_scores_gemma":[0.9288806,0.000095773765,0.069812715,0.000045559504,0.00005634111,0.00013295081,0.00039804858,0.000028486655,0.0005495391],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9911703,0.0028982207,0.0010474978,0.0008923075,0.0036580905,0.00033358365],"domain_scores_gemma":[0.9832962,0.009949723,0.0025833338,0.0012734636,0.00213657,0.0007606614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004692422,0.00044104853,0.0008693069,0.0056177243,0.00089361926,0.0028968828,0.0014224112,0.0013219903,0.0030709286],"category_scores_gemma":[0.036632344,0.00028899635,0.000955655,0.004957296,0.0015735144,0.007458024,0.002341979,0.00077365397,0.0005891566],"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":[0.0030111168,0.0012215859,0.16146526,0.00086021214,0.00062976073,0.00087927637,0.00394898,0.09172786,0.014996788,0.17220762,0.0051166606,0.5439349],"study_design_scores_gemma":[0.00012326789,0.0011457044,0.05980181,0.00009662352,0.00015158813,0.0012399963,0.0031187467,0.7630761,0.007494073,0.15852185,0.005079538,0.0001506834],"about_ca_topic_score_codex":0.0007614067,"about_ca_topic_score_gemma":0.00054064096,"teacher_disagreement_score":0.0056177243,"about_ca_system_score_codex":0.000859585,"about_ca_system_score_gemma":0.0003600959,"threshold_uncertainty_score":0.024816215},"labels":[],"label_agreement":null},{"id":"W2039852163","doi":"10.1145/1774088.1774306","title":"A study on interestingness measures for associative classifiers","year":2010,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Association rule learning; Associative property; Computer science; Artificial intelligence; De facto; Machine learning; Class (philosophy); Data mining; Set (abstract data type); Association (psychology); Pattern recognition (psychology); Mathematics; Psychology","score_opus":0.0749619604693857,"score_gpt":0.34321929275355056,"score_spread":0.2682573322841649,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039852163","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20236914,0.015284114,0.75902504,0.0025981385,0.00045784796,0.00029877725,0.00049066497,0.00034354467,0.019132718],"genre_scores_gemma":[0.85018593,0.0034418884,0.13962041,0.00062438805,0.0019892661,0.00041825304,0.0007698763,0.00013722054,0.0028127048],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98738897,0.0033731647,0.0012299619,0.0018688564,0.005645937,0.0004931766],"domain_scores_gemma":[0.8017388,0.16953969,0.009131408,0.006267886,0.011459907,0.0018624021],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016199999,0.0011770771,0.001964221,0.008422258,0.0016343582,0.0042715915,0.0022179964,0.002090733,0.0024893545],"category_scores_gemma":[0.10944012,0.0006642935,0.0015951312,0.005852865,0.0038465136,0.01322411,0.0023616091,0.0034555527,0.00040662583],"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":[0.0004778356,0.00035940332,0.026179155,0.0007593686,0.00035811498,0.0006066652,0.00083579996,0.036908995,0.004906106,0.71858126,0.0035738794,0.20645338],"study_design_scores_gemma":[0.00006107203,0.00061003893,0.00801221,0.00033263885,0.00020158643,0.0015941045,0.00026874256,0.36790967,0.005908033,0.60798967,0.0070072063,0.000105032945],"about_ca_topic_score_codex":0.0003474369,"about_ca_topic_score_gemma":0.00019898589,"teacher_disagreement_score":0.016199999,"about_ca_system_score_codex":0.002110728,"about_ca_system_score_gemma":0.000693427,"threshold_uncertainty_score":0.08567476},"labels":[],"label_agreement":null},{"id":"W2041738807","doi":"10.1111/0824-7935.00154","title":"Rule Quality Measures for Rule Induction Systems: Description and Evaluation","year":2001,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":81,"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":"Government of Canada","keywords":"Rule induction; Generalization; Rule-based system; Computer science; Quality (philosophy); Selection (genetic algorithm); Learning rule; Set (abstract data type); Artificial intelligence; Mathematics; Machine learning; Data mining; Artificial neural network","score_opus":0.18695788751994588,"score_gpt":0.38607336659080627,"score_spread":0.19911547907086039,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041738807","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015488891,0.0025373776,0.97110724,0.00036667797,0.00014441027,0.0013577726,0.0021442096,0.0038922995,0.0029611532],"genre_scores_gemma":[0.09835405,0.0012617576,0.8936547,0.00012577958,0.00012081186,0.0016456428,0.003320852,0.0006261705,0.000890224],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9642103,0.0063395305,0.0064907284,0.0018270247,0.020375954,0.0007565354],"domain_scores_gemma":[0.9004384,0.059065674,0.007181399,0.009956014,0.022556666,0.0008018128],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024743984,0.0020020476,0.0022109014,0.007686778,0.00076426537,0.004307127,0.0037313725,0.0019306733,0.0037602906],"category_scores_gemma":[0.11431239,0.0007645375,0.0015915139,0.006998561,0.0011105632,0.0055101886,0.0015897668,0.0020414384,0.0015178858],"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":[0.00055907597,0.000642451,0.010262227,0.002559785,0.0003952564,0.000251148,0.0004363759,0.08027925,0.008387779,0.030170266,0.015030166,0.85102624],"study_design_scores_gemma":[0.00022559999,0.0012012479,0.0069053676,0.00061332743,0.0003233818,0.001267287,0.00028990742,0.8876242,0.03644769,0.04137087,0.023514481,0.00021663526],"about_ca_topic_score_codex":0.002355084,"about_ca_topic_score_gemma":0.002000919,"teacher_disagreement_score":0.024743984,"about_ca_system_score_codex":0.0022366215,"about_ca_system_score_gemma":0.0022197687,"threshold_uncertainty_score":0.13086027},"labels":[],"label_agreement":null},{"id":"W2042020602","doi":"10.1016/j.eswa.2013.12.043","title":"Multi-objective PSO algorithm for mining numerical association rules without a priori discretization","year":2014,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":87,"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 British Columbia","funders":"","keywords":"Discretization; Computer science; Particle swarm optimization; A priori and a posteriori; Association rule learning; Algorithm; Data mining; Apriori algorithm; Numerical analysis; Measure (data warehouse); Mathematical optimization; Machine learning; Mathematics","score_opus":0.013050005289703705,"score_gpt":0.27399422278141866,"score_spread":0.260944217491715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042020602","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011490691,0.00025270466,0.9867797,0.000109327724,0.00004337507,0.000042198662,0.00003770328,0.00020920785,0.0010350837],"genre_scores_gemma":[0.26269725,0.0002578059,0.7345892,0.00015390168,0.000072378265,0.0002496668,0.00021881267,0.00005056534,0.0017103897],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993579,0.00017562037,0.000068875466,0.0001303075,0.00021999764,0.000047354388],"domain_scores_gemma":[0.9982003,0.0012045036,0.00013067121,0.00013101487,0.0002766555,0.000056805366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014565511,0.0006061878,0.0014027896,0.0011250875,0.00044623905,0.0009656965,0.0012542277,0.001079194,0.001973173],"category_scores_gemma":[0.0052453266,0.00059552764,0.00094624044,0.0012856164,0.00054499006,0.00090804405,0.0009455384,0.0011111863,0.0004324076],"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":[0.00017422323,0.00015331058,0.0026134595,0.00019811919,0.00020768416,0.0001369535,0.000098614655,0.7346649,0.0027338325,0.009745214,0.0020744218,0.2471993],"study_design_scores_gemma":[0.000017164783,0.000021247874,0.00017189987,0.0000072792986,0.0000095160585,0.000025958814,0.0000046027094,0.9978897,0.00018237044,0.0014779551,0.00018901053,0.0000032971282],"about_ca_topic_score_codex":0.0032121742,"about_ca_topic_score_gemma":0.0031383962,"teacher_disagreement_score":0.0032121742,"about_ca_system_score_codex":0.00037954934,"about_ca_system_score_gemma":0.0010498461,"threshold_uncertainty_score":0.0077030063},"labels":[],"label_agreement":null},{"id":"W2043132313","doi":"10.1145/1062455.1062615","title":"MSR 2005 international workshop on mining software repositories","year":2005,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Software; Software engineering; World Wide Web; Data science; Operating system","score_opus":0.01865358661549979,"score_gpt":0.27501451720789466,"score_spread":0.25636093059239484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043132313","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08301345,0.01761701,0.7826237,0.011232515,0.0030333241,0.001528413,0.020455021,0.04236406,0.038132474],"genre_scores_gemma":[0.116264455,0.008165701,0.7171715,0.0014572653,0.0010511774,0.00082612113,0.060932625,0.0031437795,0.09098744],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99630284,0.0008350671,0.00046503913,0.00059377536,0.0016084892,0.00019472124],"domain_scores_gemma":[0.9887293,0.00367424,0.00080286764,0.0030107812,0.0030161554,0.00076659716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00631306,0.0013609333,0.0027238324,0.010234758,0.00097465655,0.0052111573,0.003392784,0.0017871046,0.019596204],"category_scores_gemma":[0.015170743,0.0008602959,0.0019566938,0.006912838,0.0006053039,0.007068342,0.002745809,0.001586876,0.012952872],"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":[0.00026689869,0.00036900066,0.004888882,0.0007791652,0.00020419052,0.00021888655,0.0002874072,0.0028411814,0.008835731,0.006628695,0.12408262,0.8505973],"study_design_scores_gemma":[0.00028068322,0.0014519948,0.019383596,0.0017636002,0.0010525405,0.0031084272,0.0011776421,0.1668617,0.07538409,0.06430447,0.6650254,0.00020577222],"about_ca_topic_score_codex":0.0018474109,"about_ca_topic_score_gemma":0.0035907812,"teacher_disagreement_score":0.019596204,"about_ca_system_score_codex":0.0008496337,"about_ca_system_score_gemma":0.002563931,"threshold_uncertainty_score":0.06555581},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019608561,0.15114613,0.089480124,0.73471314,0.0057799355,0.00020557428,0.00030338272,0.00050999434,0.01590085],"genre_scores_gemma":[0.16706468,0.3342386,0.36971208,0.08712785,0.02937904,0.0015021887,0.00087290193,0.0007580621,0.009344655],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9474573,0.03334611,0.004461061,0.002660342,0.01101732,0.0010579112],"domain_scores_gemma":[0.55890167,0.33576322,0.010106628,0.029420555,0.054944377,0.010863642],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13472348,0.003167832,0.0053270995,0.008756171,0.0037803324,0.02202194,0.007917255,0.015326348,0.010668081],"category_scores_gemma":[0.24473633,0.0023570633,0.0014619903,0.00889241,0.03702589,0.07013687,0.010910106,0.015485746,0.005318611],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019275506,0.00039409485,0.0048522945,0.004807663,0.0002354541,0.00022772372,0.0011621522,0.0015050026,0.00041009195,0.57316285,0.13382497,0.27922493],"study_design_scores_gemma":[0.00014041431,0.00012546808,0.00091501576,0.0040776827,0.000112712834,0.00034999702,0.0031747485,0.004298895,0.00045954718,0.8291125,0.1571601,0.00007293135],"about_ca_topic_score_codex":0.003501137,"about_ca_topic_score_gemma":0.0026669162,"teacher_disagreement_score":0.13472348,"about_ca_system_score_codex":0.0059383325,"about_ca_system_score_gemma":0.025028488,"threshold_uncertainty_score":0.7124944},"labels":[],"label_agreement":null},{"id":"W2044306058","doi":"10.1145/568574.568580","title":"Constrained frequent pattern mining","year":2002,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":133,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Data mining; Sequential Pattern Mining; Constraint (computer-aided design); K-optimal pattern discovery; Context (archaeology); Process (computing); Association rule learning; Mathematics","score_opus":0.06108663403363127,"score_gpt":0.2512890157389533,"score_spread":0.19020238170532203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044306058","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011723552,0.0022365502,0.97733843,0.0007698439,0.00023788183,0.0005609869,0.0023014622,0.0006671914,0.0041640257],"genre_scores_gemma":[0.17496449,0.0032336742,0.8063217,0.0007076478,0.00041334043,0.0010942535,0.0091111,0.00021229523,0.0039415807],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9903092,0.002818198,0.0012215798,0.0019026884,0.003350458,0.00039783347],"domain_scores_gemma":[0.9751687,0.01457816,0.0019232117,0.0037078424,0.004147016,0.00047493455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052519194,0.0012765123,0.0024557854,0.0055087307,0.001369036,0.003103514,0.0037668862,0.0018581968,0.0051526423],"category_scores_gemma":[0.03992119,0.0008629601,0.001759415,0.008675211,0.0011306653,0.0054031676,0.0025834218,0.0018689602,0.0023341463],"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":[0.0004916203,0.00036496055,0.012069325,0.002616185,0.00081826805,0.002889421,0.0005433671,0.10498316,0.006464588,0.175185,0.034748055,0.65882605],"study_design_scores_gemma":[0.00010947052,0.00013841262,0.0021214213,0.00031697194,0.00015053432,0.0030189943,0.00030537552,0.5641562,0.003941527,0.3787076,0.046944283,0.00008923117],"about_ca_topic_score_codex":0.0013770885,"about_ca_topic_score_gemma":0.0016207218,"teacher_disagreement_score":0.0055087307,"about_ca_system_score_codex":0.0006319402,"about_ca_system_score_gemma":0.0018814228,"threshold_uncertainty_score":0.027775109},"labels":[],"label_agreement":null},{"id":"W2044838388","doi":"10.1145/2361354.2361393","title":"Personalized document clustering with dual supervision","year":2012,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Cluster analysis; Personalization; Matching (statistics); Feature (linguistics); Ask price; Information retrieval; Document clustering; Data mining; Machine learning; Artificial intelligence; World Wide Web","score_opus":0.01932422136775616,"score_gpt":0.26078771744636037,"score_spread":0.2414634960786042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044838388","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031347763,0.0002626468,0.96209615,0.00020806439,0.000034054963,0.00018706721,0.00027739734,0.004016758,0.0015699421],"genre_scores_gemma":[0.387815,0.00015198135,0.60666037,0.00015743404,0.00007564653,0.0002487513,0.0012626009,0.00035031184,0.0032779546],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99482214,0.0018697634,0.00028604118,0.0016641419,0.001133018,0.0002248572],"domain_scores_gemma":[0.98998827,0.0029679483,0.00081621466,0.0041711093,0.0017517543,0.00030475872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040623574,0.0009878724,0.0016058488,0.0021966519,0.0011070837,0.0018764792,0.0022074275,0.0015301089,0.0023232433],"category_scores_gemma":[0.01387649,0.0008603885,0.0013022504,0.002121191,0.0010356008,0.0031116046,0.0022597902,0.001661019,0.0021373772],"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":[0.00097263005,0.00058885355,0.0076870234,0.000349934,0.00043448998,0.00012617251,0.0007639454,0.23264338,0.015085387,0.008161019,0.008180265,0.72500694],"study_design_scores_gemma":[0.000039755025,0.00010142531,0.0014337705,0.000017773986,0.000038139497,0.0001222724,0.00008762073,0.97572905,0.0075636865,0.012609012,0.0022231727,0.000034287223],"about_ca_topic_score_codex":0.0048379037,"about_ca_topic_score_gemma":0.008709313,"teacher_disagreement_score":0.0048379037,"about_ca_system_score_codex":0.001557189,"about_ca_system_score_gemma":0.0017251841,"threshold_uncertainty_score":0.021484017},"labels":[],"label_agreement":null},{"id":"W2046154557","doi":"10.4028/www.scientific.net/aef.2-3.706","title":"Fault Prediction Method Based on Data Mining in Semiconductor Test Line","year":2011,"lang":"en","type":"article","venue":"Advanced engineering forum","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Advanced Micro Devices (Canada)","funders":"Science and Technology Commission of Shanghai Municipality; National Natural Science Foundation of China","keywords":"Fault (geology); Reliability engineering; Test (biology); Computer science; Point (geometry); Line (geometry); Test data; Fault coverage; Data mining; Engineering; Electrical engineering; Software engineering","score_opus":0.03889166989183223,"score_gpt":0.2765252276831313,"score_spread":0.23763355779129908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046154557","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13364626,0.00067036255,0.8600025,0.0004175038,0.00013212879,0.00019287964,0.00083586015,0.0025111032,0.0015914612],"genre_scores_gemma":[0.82092875,0.00043062467,0.17547269,0.000116704294,0.00007392533,0.00018763467,0.0012509658,0.000039706374,0.0014990453],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999298,0.00009637577,0.000115025156,0.0001907045,0.00023950677,0.00006024689],"domain_scores_gemma":[0.99857926,0.0005836381,0.0001255376,0.00012075665,0.0005356656,0.000055126686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007587257,0.0005740607,0.0008861354,0.001980711,0.00052625005,0.0007872368,0.00095066655,0.00072587305,0.0007096951],"category_scores_gemma":[0.0033535585,0.000271457,0.0006475149,0.001399971,0.00020166261,0.0009652104,0.00039207484,0.000559106,0.00030804984],"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":[0.0004989455,0.00044641722,0.0323828,0.00026278317,0.00018863876,0.0006581274,0.00019557384,0.18441924,0.008401138,0.0023490002,0.006197488,0.76399994],"study_design_scores_gemma":[0.0000190436,0.00007533787,0.0030243646,0.000017195436,0.00003677218,0.00018201319,0.000038882077,0.9884692,0.005229771,0.0017266058,0.0011647639,0.00001603574],"about_ca_topic_score_codex":0.005080254,"about_ca_topic_score_gemma":0.0034466295,"teacher_disagreement_score":0.005080254,"about_ca_system_score_codex":0.00045242347,"about_ca_system_score_gemma":0.0006413932,"threshold_uncertainty_score":0.010101378},"labels":[],"label_agreement":null},{"id":"W2048032757","doi":"10.1145/1451940.1451967","title":"Efficient algorithms for stream mining of constrained frequent patterns in a limited memory environment","year":2008,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Data stream mining; Data mining; Process (computing); Focus (optics); Data stream; Machine learning","score_opus":0.03478426409996017,"score_gpt":0.24921129626098606,"score_spread":0.2144270321610259,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048032757","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015947757,0.00048255335,0.9818376,0.00016833411,0.00002702482,0.00014818602,0.00020564921,0.00074187684,0.00044103226],"genre_scores_gemma":[0.09280099,0.00046170506,0.9045728,0.0000752321,0.00006176656,0.0004605056,0.00082470855,0.00006826002,0.00067405344],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982681,0.000435265,0.00029278535,0.00035228452,0.00049831637,0.00015322994],"domain_scores_gemma":[0.99256647,0.005013114,0.00063366746,0.0008581213,0.0007746645,0.00015405382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002674602,0.001109168,0.0017222015,0.0020761667,0.00078873546,0.0019170447,0.0024092156,0.0010687765,0.0013601474],"category_scores_gemma":[0.015747558,0.0007610871,0.0009241165,0.0036222548,0.000616571,0.0040592547,0.0015935153,0.0012050334,0.00071635563],"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":[0.0006373759,0.0003981435,0.0053391834,0.00041090616,0.00021198679,0.000391418,0.0004141376,0.32216543,0.004906161,0.028508449,0.006742123,0.62987477],"study_design_scores_gemma":[0.00007770655,0.000048246427,0.00023917349,0.000018448934,0.00002607564,0.00014865652,0.000050220766,0.9631732,0.0013623191,0.033539772,0.0013059655,0.000010234084],"about_ca_topic_score_codex":0.001668389,"about_ca_topic_score_gemma":0.0020571856,"teacher_disagreement_score":0.002674602,"about_ca_system_score_codex":0.00061880867,"about_ca_system_score_gemma":0.0018642375,"threshold_uncertainty_score":0.014144778},"labels":[],"label_agreement":null},{"id":"W2048682322","doi":"10.1109/icsm.2013.90","title":"Mining Telecom System Logs to Facilitate Debugging Tasks","year":2013,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Troubleshooting; Computer science; Debugging; Focus (optics); Service (business); Software; Data mining; Quality (philosophy); Quality of service; Telecommunications; Data science; Operating system","score_opus":0.03590427364270893,"score_gpt":0.23631854070496433,"score_spread":0.2004142670622554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048682322","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55589724,0.0012405752,0.41356707,0.00112687,0.00014272923,0.0009846701,0.013098733,0.009200646,0.004741473],"genre_scores_gemma":[0.7650149,0.00065311015,0.21892878,0.00009047665,0.000047705722,0.00042603875,0.013080547,0.00025765097,0.0015008561],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9979571,0.0006084002,0.00027578475,0.00037871872,0.0006675109,0.00011249431],"domain_scores_gemma":[0.98807997,0.0060994904,0.0015524795,0.0020430093,0.0019669728,0.00025820613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001852033,0.0012486296,0.00065444235,0.006251749,0.00056440086,0.001275359,0.0011830836,0.0008614353,0.0012646556],"category_scores_gemma":[0.013163933,0.00041451643,0.0005608064,0.003995034,0.00025555014,0.0015284598,0.0007039064,0.00088022667,0.0007790691],"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":[0.0009211047,0.0017776038,0.17026033,0.0014746187,0.00034697296,0.0028829554,0.0019158038,0.06988698,0.035068125,0.0032469796,0.014977521,0.69724095],"study_design_scores_gemma":[0.00015488801,0.00066712155,0.08465747,0.00031638733,0.00023866935,0.0021992547,0.0016666994,0.8194018,0.054567546,0.0113230115,0.024702186,0.00010487505],"about_ca_topic_score_codex":0.0033647364,"about_ca_topic_score_gemma":0.0062128194,"teacher_disagreement_score":0.006251749,"about_ca_system_score_codex":0.0004519226,"about_ca_system_score_gemma":0.0010788871,"threshold_uncertainty_score":0.009794593},"labels":[],"label_agreement":null},{"id":"W2048976003","doi":"10.1145/1540276.1540299","title":"WebKDD 2008","year":2008,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Knowledge extraction; Las vegas; Conjunction (astronomy); Data science; Library science; World Wide Web; Data mining; History; Archaeology; Tourism","score_opus":0.05751956576975635,"score_gpt":0.2554444167508769,"score_spread":0.19792485098112056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048976003","genre_codex":"dataset","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020654376,0.014559869,0.109832086,0.016676806,0.005772306,0.0008737277,0.61289394,0.1760378,0.06128797],"genre_scores_gemma":[0.006576434,0.008628371,0.0863389,0.00368892,0.0006053533,0.0012929232,0.85877854,0.008541122,0.025549455],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9903261,0.0016724387,0.0010595185,0.0013788451,0.0050969347,0.0004660473],"domain_scores_gemma":[0.98890346,0.002732135,0.0005253476,0.0034786714,0.003530724,0.00082969485],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009461475,0.002605064,0.0043343096,0.0109142065,0.002458075,0.011936029,0.0068656923,0.0042408463,0.0514448],"category_scores_gemma":[0.031796105,0.0028013117,0.004313322,0.0073802765,0.00087144173,0.0069154277,0.0053914418,0.0066468026,0.118033305],"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":[0.00005105793,0.000039840215,0.00041969022,0.00038143957,0.00011142478,0.00003832971,0.000024616316,0.001100564,0.000083407394,0.0035796112,0.96241695,0.0317531],"study_design_scores_gemma":[0.00012409364,0.000015500444,0.00045229183,0.00018269902,0.000056131532,0.00020672088,0.000024046694,0.00771473,0.00075278344,0.019426355,0.97098774,0.000057001176],"about_ca_topic_score_codex":0.012069655,"about_ca_topic_score_gemma":0.016728954,"teacher_disagreement_score":0.94855523,"about_ca_system_score_codex":0.0026501603,"about_ca_system_score_gemma":0.008745913,"threshold_uncertainty_score":0.17210001},"labels":[],"label_agreement":null},{"id":"W2049222283","doi":"10.1145/2642937.2642960","title":"Constructing adaptive configuration dialogs using crowd data","year":2014,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Construct (python library); Solver; Markov decision process; Set (abstract data type); Process (computing); Dialog box; Software; Data mining; Human–computer interaction; Markov process; Machine learning; World Wide Web; Programming language","score_opus":0.09286127196892949,"score_gpt":0.30111899387711827,"score_spread":0.20825772190818878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049222283","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14841115,0.00024972204,0.8391777,0.0012339541,0.00005399547,0.0010804678,0.0016525016,0.0017247879,0.0064156903],"genre_scores_gemma":[0.60053027,0.00010158897,0.39404735,0.00023903015,0.000039737082,0.0010283957,0.0022356065,0.00013792705,0.0016401564],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9856192,0.008474236,0.0007404437,0.002434644,0.002235909,0.00049552356],"domain_scores_gemma":[0.9518828,0.03730012,0.002295821,0.0046375683,0.0024517905,0.0014319415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012314193,0.0018397857,0.0015213217,0.0035707785,0.0027645244,0.0032246707,0.0029153202,0.0025684594,0.0044735842],"category_scores_gemma":[0.040653177,0.0015558982,0.0017861029,0.0019484923,0.0024176075,0.0055307206,0.006143895,0.0030347232,0.00076386385],"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":[0.0018347336,0.0011656645,0.023714934,0.00094272755,0.0004645612,0.002186703,0.010443575,0.64431024,0.0118865175,0.07679867,0.009439961,0.21681167],"study_design_scores_gemma":[0.00008718691,0.00011786056,0.0015513193,0.000079339334,0.000040842104,0.00012222235,0.0019191462,0.90397096,0.0050668917,0.081185445,0.00576283,0.00009600198],"about_ca_topic_score_codex":0.0042448062,"about_ca_topic_score_gemma":0.008258848,"teacher_disagreement_score":0.012314193,"about_ca_system_score_codex":0.002672556,"about_ca_system_score_gemma":0.0033166176,"threshold_uncertainty_score":0.06512439},"labels":[],"label_agreement":null},{"id":"W2051402444","doi":"10.1145/2330784.2331011","title":"An evolutionary subspace clustering algorithm for high-dimensional data","year":2012,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Computer science; Subspace topology; Clustering high-dimensional data; Canopy clustering algorithm; Evolutionary algorithm; Artificial intelligence; Algorithm; Correlation clustering; Data mining","score_opus":0.0468221772716177,"score_gpt":0.30811432613238154,"score_spread":0.26129214886076385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051402444","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022619886,0.000107772285,0.99678695,0.00004167488,0.000023852577,0.000034526965,0.000033879758,0.00032324393,0.0003860843],"genre_scores_gemma":[0.03156528,0.00013008714,0.9664298,0.000051026484,0.000030825002,0.00019868655,0.0003209739,0.000103736864,0.0011695178],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983329,0.0004307238,0.00009437549,0.0003103861,0.0007321292,0.00009948143],"domain_scores_gemma":[0.9986909,0.0003777827,0.00009099307,0.00024105418,0.000523771,0.00007558324],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017799371,0.0010605054,0.001552589,0.002065418,0.001622519,0.0011612063,0.0018864503,0.0012746243,0.002237012],"category_scores_gemma":[0.004253195,0.0005598224,0.0011771029,0.003840805,0.0008801324,0.001628482,0.0018705755,0.0014674222,0.0013488651],"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":[0.000092696595,0.00012551145,0.0013188048,0.00014051361,0.00017914367,0.00014584625,0.00024697836,0.34432238,0.0070499443,0.023996811,0.0065837065,0.6157977],"study_design_scores_gemma":[0.000020607504,0.00004355541,0.00027286672,0.000010961495,0.000014404958,0.000111199945,0.00003612589,0.97698385,0.0019563485,0.015814167,0.004712547,0.000023436696],"about_ca_topic_score_codex":0.0040557957,"about_ca_topic_score_gemma":0.004676575,"teacher_disagreement_score":0.0040557957,"about_ca_system_score_codex":0.00058902375,"about_ca_system_score_gemma":0.0013359147,"threshold_uncertainty_score":0.009413362},"labels":[],"label_agreement":null},{"id":"W2051664277","doi":"10.1109/tkde.2011.100","title":"Discovery of Delta Closed Patterns and Noninduced Patterns from Sequences","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Substring; Computer science; Set (abstract data type); Sequence (biology); Data mining; Suffix tree; Pattern recognition (psychology); Artificial intelligence; Data structure","score_opus":0.04450856788129964,"score_gpt":0.2576284759502814,"score_spread":0.21311990806898173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051664277","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23123968,0.0005761514,0.76559037,0.00020427308,0.000032766296,0.00014973669,0.0004342442,0.0006380317,0.0011347748],"genre_scores_gemma":[0.40128404,0.00047708323,0.59484017,0.000092348964,0.000032975582,0.00013806514,0.0020479753,0.000075935284,0.0010114678],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988662,0.00022906721,0.00019490358,0.00023540012,0.00040317234,0.0000712792],"domain_scores_gemma":[0.9947078,0.0028835998,0.00075115234,0.0008035665,0.0006859981,0.00016785412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001274288,0.00043992052,0.00088992016,0.002038661,0.00045738916,0.0010884223,0.00093211053,0.00075881823,0.00088248064],"category_scores_gemma":[0.0074793524,0.0003381285,0.00083010434,0.0021004544,0.00062067545,0.0019377106,0.00093354814,0.000871457,0.00045426245],"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":[0.0007537596,0.0004616674,0.031964853,0.0008488065,0.00016552597,0.0014859536,0.0007645803,0.022858111,0.07069928,0.020140475,0.0013749485,0.8484821],"study_design_scores_gemma":[0.00013065626,0.0008147806,0.01873796,0.00018564917,0.00014241955,0.0046563125,0.0009085353,0.76355404,0.0814157,0.1200418,0.009317835,0.00009429782],"about_ca_topic_score_codex":0.00025020968,"about_ca_topic_score_gemma":0.00039054244,"teacher_disagreement_score":0.002038661,"about_ca_system_score_codex":0.00020057552,"about_ca_system_score_gemma":0.0006847173,"threshold_uncertainty_score":0.0067391396},"labels":[],"label_agreement":null},{"id":"W2051940511","doi":"10.1111/j.1467-8640.2008.00326.x","title":"AN INTERACTIVE SEARCH ASSISTANT ARCHITECTURE BASED ON INTRINSIC QUERY STREAM CHARACTERISTICS","year":2008,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Web search query; Information retrieval; Web query classification; Ranking (information retrieval); Search engine; Sargable; Phrase; Phrase search; Metric (unit); Query expansion; Data stream mining; Data stream; Query language; Data mining; Sequence (biology); Artificial intelligence","score_opus":0.03594127529118811,"score_gpt":0.30793452600318705,"score_spread":0.2719932507119989,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051940511","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07868833,0.0005873659,0.880187,0.00031808013,0.00008167427,0.00037663186,0.00041714162,0.034756046,0.0045876745],"genre_scores_gemma":[0.5297881,0.00047561273,0.45681822,0.00027233383,0.00012972574,0.00036019483,0.0012775885,0.00047780902,0.010400434],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99944955,0.00008156731,0.000041522748,0.00015132091,0.00022533207,0.000050632483],"domain_scores_gemma":[0.9985661,0.00053599296,0.00008837477,0.0002722462,0.00041039902,0.0001268852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009760118,0.0005290686,0.00083317637,0.0011057041,0.0004619036,0.0011778588,0.0017347927,0.00069803506,0.0033831466],"category_scores_gemma":[0.0034167625,0.00037297996,0.00039876183,0.0010630662,0.00028829294,0.0024207283,0.0008889536,0.0006479572,0.0018043383],"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":[0.0020865847,0.0007780054,0.010129464,0.0004449657,0.00019770021,0.00040949788,0.0005829159,0.01661196,0.09145075,0.00824573,0.016389873,0.8526726],"study_design_scores_gemma":[0.00016190714,0.00075228146,0.004117155,0.000026143523,0.00015770683,0.0010149478,0.00012710405,0.921125,0.042385213,0.0052603926,0.024783641,0.000088441724],"about_ca_topic_score_codex":0.0028559582,"about_ca_topic_score_gemma":0.003906736,"teacher_disagreement_score":0.0033831466,"about_ca_system_score_codex":0.00038333872,"about_ca_system_score_gemma":0.00080814905,"threshold_uncertainty_score":0.01131779},"labels":[],"label_agreement":null},{"id":"W2051980844","doi":"10.1016/j.eswa.2009.02.068","title":"Applications of web mining for marketing of online bookstores","year":2009,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Data Mining Algorithms and Applications","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":"Thompson Rivers University","funders":"","keywords":"Computer science; Association rule learning; Database transaction; Field (mathematics); Web mining; Key (lock); Transaction data; Data mining; Data science; Information retrieval; Order (exchange); World Wide Web; Web page; Database; Business","score_opus":0.014802555554104969,"score_gpt":0.278200047588135,"score_spread":0.26339749203403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051980844","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.590428,0.011923628,0.27529374,0.008187526,0.00094350596,0.0010872304,0.0067299535,0.009607017,0.095799334],"genre_scores_gemma":[0.8205243,0.0027194503,0.16371126,0.00033403217,0.0005196278,0.00015976984,0.0019074872,0.0003559408,0.009768155],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983241,0.00065632496,0.00011204565,0.0001690389,0.0006778223,0.0000606212],"domain_scores_gemma":[0.9892595,0.0077274204,0.0005718188,0.00077432994,0.001382149,0.0002847805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020493749,0.000711289,0.0006672728,0.006946298,0.0009819687,0.0029180187,0.0008544567,0.00096855575,0.0067864694],"category_scores_gemma":[0.013895588,0.0003237663,0.00079339184,0.0072990386,0.00027254462,0.0018687894,0.00064005156,0.0007993002,0.0020062611],"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":[0.00045630726,0.0012049987,0.08167325,0.0004496994,0.00037308084,0.0004148271,0.00053566374,0.015831722,0.0034626885,0.009344476,0.01864003,0.86761326],"study_design_scores_gemma":[0.00014950316,0.00035190373,0.08861884,0.00030572788,0.0004895377,0.0014163264,0.0015028374,0.76645124,0.017321842,0.06894607,0.05431478,0.00013134602],"about_ca_topic_score_codex":0.004605592,"about_ca_topic_score_gemma":0.006970559,"teacher_disagreement_score":0.006946298,"about_ca_system_score_codex":0.00079547026,"about_ca_system_score_gemma":0.0008173364,"threshold_uncertainty_score":0.022702992},"labels":[],"label_agreement":null},{"id":"W2052496634","doi":"10.1007/s10844-006-0006-z","title":"Constraint-based sequential pattern mining: the pattern-growth methods","year":2007,"lang":"en","type":"article","venue":"Journal of Intelligent Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":233,"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; University of British Columbia","funders":"Simon Fraser University; National Science Foundation","keywords":"Sequential Pattern Mining; Computer science; Constraint (computer-aided design); Data mining; Point (geometry); Artificial intelligence; Mathematics","score_opus":0.04073344562841342,"score_gpt":0.3292330749489349,"score_spread":0.2884996293205215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052496634","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00747499,0.0017947659,0.987452,0.0006003351,0.00009173618,0.0002421883,0.00069123256,0.00067774014,0.0009750847],"genre_scores_gemma":[0.09248449,0.0024758915,0.9001809,0.0002999555,0.00024567163,0.00051368313,0.0016408728,0.00024319648,0.0019154085],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99630356,0.0009912582,0.0003343472,0.0007489662,0.0014699976,0.00015184192],"domain_scores_gemma":[0.9845999,0.009689311,0.0010425636,0.0017655342,0.0025635215,0.0003391607],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045934794,0.0015437764,0.0026782725,0.0041611986,0.00097222015,0.0023566934,0.004278783,0.0013568747,0.003021284],"category_scores_gemma":[0.02172062,0.00088629156,0.0020532717,0.008666292,0.001209194,0.0040526767,0.0017826164,0.0029513654,0.0013364091],"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":[0.0004930506,0.00046324756,0.008692825,0.0013652251,0.00053022197,0.00040308878,0.00020496997,0.10482076,0.0048529855,0.039529894,0.012928508,0.82571524],"study_design_scores_gemma":[0.00006378006,0.00011175916,0.0010412168,0.0000766235,0.00011154407,0.00036829402,0.00005718877,0.94016117,0.0026509734,0.049124464,0.00619279,0.0000401099],"about_ca_topic_score_codex":0.0065875812,"about_ca_topic_score_gemma":0.008069252,"teacher_disagreement_score":0.0065875812,"about_ca_system_score_codex":0.0008071624,"about_ca_system_score_gemma":0.003552192,"threshold_uncertainty_score":0.024292946},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09135821,0.0017616424,0.8978154,0.0010837483,0.00014716004,0.00035763625,0.0025089746,0.0017212934,0.0032458869],"genre_scores_gemma":[0.6101188,0.0013985249,0.3744561,0.00033937258,0.0003208993,0.00051203865,0.008116314,0.000113889335,0.0046240995],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99648297,0.001098482,0.00031770763,0.00076330046,0.0009849096,0.00035260207],"domain_scores_gemma":[0.9875729,0.006105102,0.0012923805,0.0028637545,0.0019149428,0.00025085662],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034401584,0.00078998646,0.0023563101,0.0070870807,0.0010835428,0.0033421586,0.0022766364,0.0014000216,0.002261367],"category_scores_gemma":[0.014866972,0.00058085687,0.0017556555,0.0089424625,0.00090636325,0.0038804745,0.0019622853,0.0014188726,0.0018280691],"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":[0.00031276676,0.00042907422,0.08690983,0.00046543285,0.00032281585,0.00023602581,0.0005261197,0.025537256,0.002790309,0.014353046,0.012782644,0.85533464],"study_design_scores_gemma":[0.000051053426,0.00015547275,0.019215753,0.00019628236,0.00034646803,0.0005779616,0.0009903309,0.871932,0.0068319025,0.08171186,0.017929606,0.00006118715],"about_ca_topic_score_codex":0.005739502,"about_ca_topic_score_gemma":0.007566735,"teacher_disagreement_score":0.0070870807,"about_ca_system_score_codex":0.001003916,"about_ca_system_score_gemma":0.0018381062,"threshold_uncertainty_score":0.018193483},"labels":[],"label_agreement":null},{"id":"W2054773288","doi":"10.1145/2618243.2618261","title":"Mining statistically sound co-location patterns at multiple distances","year":2014,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Measure (data warehouse); Computer science; Data mining; Distance measures; Location data; Co-occurrence; Pattern recognition (psychology); Statistics; Artificial intelligence; Mathematics; Real-time computing","score_opus":0.02012134999052301,"score_gpt":0.27427764077496863,"score_spread":0.2541562907844456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054773288","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25699577,0.000698089,0.73444927,0.0006308712,0.00010739051,0.00033907976,0.0023049477,0.0019694243,0.0025051464],"genre_scores_gemma":[0.66263986,0.00026363504,0.33150283,0.00012505495,0.00007254426,0.00030175722,0.0037148858,0.00008073632,0.0012986972],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960122,0.0005558128,0.0004729329,0.0013908844,0.0012883068,0.00027995612],"domain_scores_gemma":[0.98243207,0.009632508,0.0025192252,0.0021863626,0.0027856654,0.0004441236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025935622,0.0010366135,0.0017248876,0.005809936,0.001273679,0.002089825,0.0025863159,0.001697602,0.0012434851],"category_scores_gemma":[0.019022053,0.00044490126,0.0014505009,0.006523158,0.0008336322,0.0025188518,0.0021798697,0.0014436123,0.0013387473],"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":[0.00097239285,0.0009978906,0.29951105,0.0010386404,0.000968491,0.0018448341,0.0011937043,0.09949074,0.017188953,0.011163264,0.008858633,0.55677146],"study_design_scores_gemma":[0.00008916397,0.000349114,0.034917723,0.00014432742,0.00023671941,0.0035266213,0.0014652652,0.9151309,0.015765762,0.021062758,0.0072040115,0.00010765993],"about_ca_topic_score_codex":0.0026963148,"about_ca_topic_score_gemma":0.0049037603,"teacher_disagreement_score":0.005809936,"about_ca_system_score_codex":0.0006165345,"about_ca_system_score_gemma":0.0014965443,"threshold_uncertainty_score":0.013716221},"labels":[],"label_agreement":null},{"id":"W2054860584","doi":"10.1109/cidm.2014.7008657","title":"Aggregating predictions vs. aggregating features for relational classification","year":2014,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Aggregate (composite); Computer science; Class (philosophy); Feature (linguistics); Artificial intelligence; Set (abstract data type); Probabilistic logic; Operator (biology); Machine learning; Data mining; Relational database; Information aggregation; Pattern recognition (psychology)","score_opus":0.02945382561680162,"score_gpt":0.26845529858302875,"score_spread":0.23900147296622712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054860584","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29018766,0.0010391442,0.6980416,0.0011353544,0.00025837784,0.0003970344,0.0012749176,0.0031515267,0.0045144293],"genre_scores_gemma":[0.84286237,0.00020774479,0.15426774,0.0001455011,0.00021054028,0.00013894141,0.0012469711,0.000113215036,0.0008070642],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99378395,0.0017163054,0.00059628044,0.0014271216,0.0020540985,0.00042217385],"domain_scores_gemma":[0.9820983,0.008280434,0.0015655487,0.0054155467,0.0021992691,0.00044094157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008829389,0.0015161372,0.0016040495,0.0023215185,0.00067408127,0.0020757369,0.0018671872,0.0011068069,0.0013951403],"category_scores_gemma":[0.026908115,0.0002656785,0.0010466693,0.0036238593,0.0009527644,0.005820001,0.0022906044,0.0023752407,0.00077610184],"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":[0.0008010003,0.0005755918,0.04392885,0.00018058205,0.00037414616,0.00014035392,0.00042526503,0.1635888,0.0059343963,0.013548066,0.005698205,0.7648048],"study_design_scores_gemma":[0.000052001873,0.00041254223,0.009801359,0.0000362615,0.00014337653,0.000114696624,0.00021964418,0.93764216,0.007171579,0.041615393,0.0027328215,0.000058218346],"about_ca_topic_score_codex":0.0023546438,"about_ca_topic_score_gemma":0.003359684,"teacher_disagreement_score":0.008829389,"about_ca_system_score_codex":0.00086953107,"about_ca_system_score_gemma":0.00097079936,"threshold_uncertainty_score":0.046694815},"labels":[],"label_agreement":null},{"id":"W2054885804","doi":"10.1504/ijbpim.2014.060604","title":"Analytics-as-a-service framework for terms association mining in unstructured data","year":2014,"lang":"en","type":"article","venue":"International Journal of Business Process Integration and Management","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Association rule learning; Computer science; Data mining; Unstructured data; Data science; Schema (genetic algorithms); Reliability (semiconductor); Analytics; Data warehouse; Data extraction; Service (business); Big data; Information retrieval","score_opus":0.02888492529035037,"score_gpt":0.3283027286669712,"score_spread":0.29941780337662083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054885804","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002141802,0.00017500271,0.9902981,0.00039331926,0.00004758503,0.0002651317,0.00038850086,0.005387372,0.0009031882],"genre_scores_gemma":[0.07576262,0.00032628793,0.92009276,0.00023547765,0.0000983355,0.0004926768,0.0015219705,0.00027924194,0.0011906576],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956863,0.0012090771,0.0006142363,0.00051089434,0.0017422594,0.00023733769],"domain_scores_gemma":[0.9946924,0.0020756477,0.00045529363,0.001227573,0.0011573385,0.0003917203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052785915,0.0010193862,0.001351487,0.0033933164,0.0016391923,0.004429707,0.0032558104,0.0016612587,0.002297739],"category_scores_gemma":[0.013152236,0.0006491653,0.0018100414,0.003941337,0.0012099567,0.0041807867,0.0041387705,0.0024304872,0.0021029958],"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":[0.0008166621,0.0006005533,0.008975042,0.0009834727,0.00042940935,0.0018809856,0.0017519477,0.12721519,0.015481847,0.3918504,0.037161537,0.41285294],"study_design_scores_gemma":[0.00003846226,0.00006953513,0.00044930738,0.00006405943,0.00004122473,0.00040120355,0.00022545716,0.87259287,0.004152972,0.088646024,0.03325826,0.00006060278],"about_ca_topic_score_codex":0.011444501,"about_ca_topic_score_gemma":0.012353048,"teacher_disagreement_score":0.011444501,"about_ca_system_score_codex":0.0016913667,"about_ca_system_score_gemma":0.005244528,"threshold_uncertainty_score":0.027916193},"labels":[],"label_agreement":null},{"id":"W2056806761","doi":"10.1007/s10844-006-9951-9","title":"Mining changing regions from access-constrained snapshots: a cluster-embedded decision tree approach","year":2006,"lang":"en","type":"article","venue":"Journal of Intelligent Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":11,"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 mining; Decision tree; Set (abstract data type); Tree (set theory); Spatial analysis; Simple (philosophy); Cluster (spacecraft); Data set; Artificial intelligence; Remote sensing","score_opus":0.029514702072971844,"score_gpt":0.27797311100323824,"score_spread":0.24845840893026638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056806761","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12953457,0.001133527,0.8646136,0.00047631396,0.00006791686,0.00020461115,0.0019227818,0.0010625251,0.00098417],"genre_scores_gemma":[0.6895126,0.0004526509,0.3052921,0.00010835436,0.00011021604,0.00015211843,0.0033859578,0.0001108485,0.0008751955],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871325,0.00023779261,0.00013151142,0.00043962782,0.00032171773,0.00015603792],"domain_scores_gemma":[0.9958429,0.0025758056,0.00041020007,0.00039102466,0.0006021833,0.00017789252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016425195,0.0010008147,0.0023564803,0.0040496774,0.00086777547,0.0018442228,0.0024949543,0.0014741177,0.0012399872],"category_scores_gemma":[0.0066737123,0.00067046523,0.0011914053,0.0058166333,0.0004732984,0.0026037325,0.0013273964,0.001186163,0.00043579275],"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":[0.00090943224,0.00056827866,0.035985526,0.00041726124,0.00062756747,0.00066819065,0.00044521235,0.6330989,0.0057016346,0.0062093027,0.005102747,0.31026602],"study_design_scores_gemma":[0.000015695476,0.000044743687,0.0018953432,0.000011994987,0.000070678194,0.00008087198,0.00009004043,0.9899312,0.0006174605,0.0067295637,0.00049772084,0.0000146548855],"about_ca_topic_score_codex":0.009156527,"about_ca_topic_score_gemma":0.011888733,"teacher_disagreement_score":0.009156527,"about_ca_system_score_codex":0.0005623962,"about_ca_system_score_gemma":0.0010672087,"threshold_uncertainty_score":0.018206477},"labels":[],"label_agreement":null},{"id":"W2057778735","doi":"10.1109/waina.2014.11","title":"Distributed Uncertain Data Mining for Frequent Patterns Satisfying Anti-monotonic Constraints","year":2014,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":15,"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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Task (project management); Exploit; Uncertain data; Monotonic function; Data mining; Distributed database; Distributed Computing Environment; Distributed computing; Computer security; Engineering","score_opus":0.06268958484812245,"score_gpt":0.3106310653976547,"score_spread":0.24794148054953227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057778735","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.072830945,0.0004201508,0.9250242,0.00033115628,0.000020002757,0.00012013312,0.0002328717,0.00021103694,0.0008095267],"genre_scores_gemma":[0.6452457,0.0003575627,0.35282892,0.00013392526,0.00007758513,0.00027700883,0.0004978654,0.000041316827,0.00054011267],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99659747,0.0010615762,0.00037879523,0.00075383706,0.0010340873,0.00017432675],"domain_scores_gemma":[0.9867643,0.009166343,0.001662341,0.001006554,0.0011515706,0.00024881482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039316854,0.0005033061,0.0011765996,0.0010499256,0.0008177797,0.0018266349,0.0014795356,0.0006044979,0.0007498215],"category_scores_gemma":[0.020213485,0.0005064573,0.00078755297,0.00203361,0.0007463177,0.0027025382,0.0012180273,0.0009759705,0.00017924301],"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":[0.0014521191,0.00035744347,0.016616225,0.00071293185,0.0004287643,0.003554062,0.001279541,0.60928077,0.026631417,0.101857916,0.0029788476,0.23485003],"study_design_scores_gemma":[0.000038437385,0.0000558311,0.00049289037,0.000015104133,0.000025258578,0.00028829,0.00010885353,0.9597666,0.0031550485,0.035154756,0.0008849751,0.0000139825015],"about_ca_topic_score_codex":0.0014943691,"about_ca_topic_score_gemma":0.0019709987,"teacher_disagreement_score":0.0039316854,"about_ca_system_score_codex":0.000588932,"about_ca_system_score_gemma":0.0012179931,"threshold_uncertainty_score":0.02079302},"labels":[],"label_agreement":null},{"id":"W2059054797","doi":"10.1109/tkde.2013.88","title":"Mining Statistically Significant Co-location and Segregation Patterns","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Data mining; Correlation; Artificial intelligence; Pattern recognition (psychology); Mathematics","score_opus":0.02346222270620061,"score_gpt":0.2662764905445469,"score_spread":0.24281426783834628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059054797","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49048126,0.0013715563,0.49700245,0.0008132793,0.000090699185,0.0003657822,0.0046725892,0.0017933425,0.0034091105],"genre_scores_gemma":[0.8360413,0.00026566949,0.15682217,0.000102705824,0.00007412263,0.00024279828,0.0053465157,0.0000940187,0.001010698],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964766,0.0005696064,0.00045597155,0.0011583127,0.0010018784,0.0003376984],"domain_scores_gemma":[0.982091,0.010556085,0.0028434207,0.0017972182,0.002235043,0.00047719578],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023948299,0.0011390054,0.0018991188,0.009241989,0.0013638994,0.0018286541,0.0021091388,0.0016808754,0.0017265002],"category_scores_gemma":[0.018306773,0.00049783854,0.0014217015,0.008087779,0.0008862258,0.0020967268,0.001925344,0.0011097948,0.0014161485],"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":[0.001078712,0.00088352035,0.5279152,0.0011240148,0.00104656,0.0029023634,0.001047757,0.04372813,0.016613191,0.009384167,0.010222231,0.38405418],"study_design_scores_gemma":[0.00017459618,0.0004211813,0.14154842,0.00019712528,0.00055501953,0.0048037088,0.002699974,0.7630833,0.022074979,0.052992467,0.0113082025,0.00014112247],"about_ca_topic_score_codex":0.0029249,"about_ca_topic_score_gemma":0.0051689153,"teacher_disagreement_score":0.009241989,"about_ca_system_score_codex":0.000629233,"about_ca_system_score_gemma":0.0013604894,"threshold_uncertainty_score":0.012665212},"labels":[],"label_agreement":null},{"id":"W2062921107","doi":"10.1145/2806416.2806524","title":"Associative Classification with Statistically Significant Positive and Negative Rules","year":2015,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Associative property; Association rule learning; Computer science; Classifier (UML); Artificial intelligence; Machine learning; Popularity; Data mining; Pattern recognition (psychology); Mathematics","score_opus":0.03491546422298477,"score_gpt":0.26670124939227596,"score_spread":0.2317857851692912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062921107","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15575546,0.0016976062,0.8220946,0.0010607332,0.00051020744,0.0004912161,0.00074182125,0.002681019,0.014967293],"genre_scores_gemma":[0.72876287,0.00070815743,0.26156804,0.000650796,0.0006754679,0.0004987823,0.0015326522,0.00010593408,0.0054972875],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9941519,0.00094355416,0.0008004118,0.0011076943,0.0026796225,0.00031670457],"domain_scores_gemma":[0.9784846,0.012721452,0.0017923116,0.0026873932,0.0039347983,0.00037943793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006318441,0.0012058181,0.0017721951,0.004495722,0.0014155498,0.0027007987,0.0026539238,0.0020836687,0.0039804303],"category_scores_gemma":[0.02623146,0.0004760653,0.0012878653,0.004222253,0.0015098815,0.0042225956,0.0018343305,0.0017374486,0.0023290883],"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":[0.00069246,0.0008051559,0.053374507,0.00057976943,0.00035718796,0.0019862892,0.0004745249,0.03919392,0.00974661,0.03181879,0.011498017,0.84947276],"study_design_scores_gemma":[0.00008827011,0.00030020325,0.008332521,0.00021036703,0.00043350153,0.0025769556,0.0002712959,0.8755482,0.015383663,0.08353317,0.013212862,0.00010898074],"about_ca_topic_score_codex":0.0009273391,"about_ca_topic_score_gemma":0.0015082569,"teacher_disagreement_score":0.006318441,"about_ca_system_score_codex":0.00055471726,"about_ca_system_score_gemma":0.0019561658,"threshold_uncertainty_score":0.033415496},"labels":[],"label_agreement":null},{"id":"W2063529879","doi":"10.1145/358108.358114","title":"Beyond intratransaction association analysis","year":2000,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":153,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Badan Riset dan Inovasi Nasional; Helsingin Yliopisto","keywords":"Association rule learning; Apriori algorithm; Database transaction; Computer science; Association (psychology); Transaction data; Affinity analysis; Data mining; Data science; Psychology; Database","score_opus":0.007761500766622136,"score_gpt":0.22556361950399387,"score_spread":0.21780211873737174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063529879","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041743524,0.002331823,0.94706273,0.00085884234,0.00020196429,0.0001958377,0.0011896086,0.001032099,0.0053835325],"genre_scores_gemma":[0.5820517,0.0016869123,0.40500385,0.0009091166,0.00061021664,0.00040938915,0.0049740407,0.00040899462,0.003945802],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9759803,0.005716295,0.0022951758,0.0064044804,0.008728353,0.00087539206],"domain_scores_gemma":[0.93066114,0.03607225,0.009458841,0.013144942,0.009642364,0.0010205079],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01113132,0.0018759372,0.002302752,0.008572572,0.0017142092,0.006259198,0.004534108,0.0019306072,0.003162001],"category_scores_gemma":[0.053748995,0.00076053216,0.0026025702,0.011217042,0.0021348626,0.0096499985,0.0048948308,0.003945418,0.0022049546],"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":[0.000577142,0.0004845112,0.13669473,0.0010624127,0.0017932756,0.002047279,0.0017174154,0.07279047,0.0037161238,0.1138321,0.00889225,0.65639234],"study_design_scores_gemma":[0.000054830893,0.00025756765,0.018463032,0.00035926912,0.00056552055,0.0025784597,0.0013398591,0.5614007,0.0074684634,0.3578354,0.049481455,0.00019538731],"about_ca_topic_score_codex":0.002621876,"about_ca_topic_score_gemma":0.0018159195,"teacher_disagreement_score":0.01113132,"about_ca_system_score_codex":0.0008298,"about_ca_system_score_gemma":0.0019511824,"threshold_uncertainty_score":0.058868706},"labels":[],"label_agreement":null},{"id":"W2064853889","doi":"10.1145/335191.335372","title":"Mining frequent patterns without candidate generation","year":2000,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":6360,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Data mining; Scalability; Set (abstract data type); Tree (set theory); GSP Algorithm; Trie; Apriori algorithm; Association rule learning; Database transaction; Data structure; Database; Mathematics","score_opus":0.02961243143666664,"score_gpt":0.2688342363591712,"score_spread":0.23922180492250456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064853889","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.092139326,0.0011316038,0.8995709,0.00043904272,0.00012886345,0.000554885,0.0017245291,0.0018245466,0.0024863668],"genre_scores_gemma":[0.31372544,0.00072446873,0.6758033,0.0002281819,0.00015492039,0.0006648764,0.0061734836,0.00013046637,0.0023949298],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961926,0.00071675074,0.00043328703,0.0008190486,0.0015685359,0.00026971198],"domain_scores_gemma":[0.9865072,0.007654811,0.0010216712,0.0023200556,0.0022599164,0.00023628607],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002773499,0.0010560468,0.0015197528,0.0033173126,0.0010026896,0.0020651596,0.0023299793,0.0013650684,0.0018598416],"category_scores_gemma":[0.020350711,0.0007856847,0.001484656,0.0049026296,0.0007125326,0.0044252025,0.0016331488,0.0010364935,0.0016855483],"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":[0.0010564004,0.00046187502,0.018379858,0.00074728165,0.00032900326,0.0018769072,0.00041830604,0.060169913,0.019364689,0.02295568,0.009558297,0.86468184],"study_design_scores_gemma":[0.0001956015,0.00081906974,0.003836875,0.0001240209,0.00024286074,0.002747715,0.00032901953,0.9142375,0.020698236,0.044000197,0.012703483,0.00006536376],"about_ca_topic_score_codex":0.0011205769,"about_ca_topic_score_gemma":0.0013202778,"teacher_disagreement_score":0.0033173126,"about_ca_system_score_codex":0.00040084432,"about_ca_system_score_gemma":0.0017851382,"threshold_uncertainty_score":0.014667809},"labels":[],"label_agreement":null},{"id":"W2065686347","doi":"10.1109/grc.2008.4664672","title":"NHOP: Detecting descriptive patterns using association pattern mining","year":2008,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Cluster analysis; Data mining; Tuple; Benchmark (surveying); Artificial intelligence; Set (abstract data type); Pattern recognition (psychology); Statistical hypothesis testing; Machine learning; Mathematics; Statistics","score_opus":0.053532880084292474,"score_gpt":0.2576343427580944,"score_spread":0.20410146267380191,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065686347","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03823088,0.00033829018,0.9532756,0.0003391396,0.000041834995,0.00048669142,0.0025026533,0.003416781,0.0013680725],"genre_scores_gemma":[0.1602577,0.00026098607,0.8326191,0.00020548327,0.000050853403,0.00050678215,0.005001551,0.00015331463,0.0009443689],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975067,0.00054793677,0.00032730505,0.0006707424,0.0008061319,0.00014130937],"domain_scores_gemma":[0.992599,0.0040130424,0.0010671061,0.0012859642,0.0008270857,0.0002077736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029400117,0.0010619734,0.001415665,0.004872573,0.0008354469,0.0016852451,0.0021299273,0.0011956994,0.0016434282],"category_scores_gemma":[0.012088307,0.0004419932,0.0011520222,0.004965396,0.00090757996,0.0026740804,0.0019833078,0.0011101469,0.00095784635],"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":[0.00041695844,0.0006405059,0.067966715,0.0014334262,0.0006069163,0.0017244171,0.0009616334,0.03202242,0.017004002,0.019130867,0.016814204,0.84127796],"study_design_scores_gemma":[0.00014907331,0.00033900837,0.018865025,0.00020538732,0.00023631347,0.0035098763,0.00097538787,0.81843746,0.022331765,0.11304832,0.021787738,0.000114644325],"about_ca_topic_score_codex":0.0020686009,"about_ca_topic_score_gemma":0.0027077715,"teacher_disagreement_score":0.004872573,"about_ca_system_score_codex":0.00037505405,"about_ca_system_score_gemma":0.001794704,"threshold_uncertainty_score":0.015548468},"labels":[],"label_agreement":null},{"id":"W2065715262","doi":"10.1007/s11047-013-9368-7","title":"Generation of classification trees from variable weighted features","year":2013,"lang":"en","type":"article","venue":"Natural Computing","topic":"Data Mining Algorithms and Applications","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":"Simon Fraser University","funders":"Fundação para a Ciência e a Tecnologia","keywords":"Phylogenetic tree; Trait; Constraint (computer-aided design); Tree (set theory); Consistency (knowledge bases); Computer science; Theory of computation; Family tree; Artificial intelligence; Machine learning; Theoretical computer science; Biology; Mathematics; Combinatorics; Algorithm; Genetics; Gene","score_opus":0.03415689047719922,"score_gpt":0.2655480904786237,"score_spread":0.2313912000014245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065715262","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06635781,0.00023120022,0.92665374,0.0003393436,0.00012195254,0.0002403827,0.0008682926,0.0029882279,0.0021990577],"genre_scores_gemma":[0.35731837,0.00017088327,0.6348016,0.00012235371,0.00006400341,0.00031518086,0.004166872,0.00031872964,0.00272191],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99952257,0.0000856712,0.000037541115,0.00012525299,0.00016998978,0.00005896957],"domain_scores_gemma":[0.9980627,0.0009761859,0.000100873774,0.00024445012,0.00055902015,0.000056715802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006987719,0.00049371395,0.0007142615,0.001312465,0.00050292216,0.00080847484,0.0011587925,0.00087906956,0.002793476],"category_scores_gemma":[0.0043445453,0.0003672015,0.0010237391,0.0011814305,0.00026959353,0.0010720335,0.0008318321,0.0012030641,0.0012500153],"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":[0.00033529228,0.0002531684,0.004956946,0.00026867262,0.00010096076,0.00047236285,0.00025483474,0.088514715,0.025668873,0.012577263,0.017299524,0.8492974],"study_design_scores_gemma":[0.000034824945,0.00008857363,0.0010296237,0.000031843145,0.000054653003,0.00015880022,0.000068008914,0.9541559,0.008707437,0.031639256,0.0040181284,0.000012967393],"about_ca_topic_score_codex":0.0011877347,"about_ca_topic_score_gemma":0.0024608043,"teacher_disagreement_score":0.002793476,"about_ca_system_score_codex":0.00044020658,"about_ca_system_score_gemma":0.00097360916,"threshold_uncertainty_score":0.009345055},"labels":[],"label_agreement":null},{"id":"W2066070009","doi":"10.1109/bigdata.congress.2014.53","title":"Reducing the Search Space for Big Data Mining for Interesting Patterns from Uncertain Data","year":2014,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Big data; Uncertain data; Data mining; Database transaction; Transaction data; Data stream mining; Probabilistic logic; Space (punctuation); Data science; Database; Artificial intelligence","score_opus":0.3019733450573061,"score_gpt":0.37437530883324105,"score_spread":0.07240196377593494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066070009","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09370959,0.0011855868,0.8958772,0.0021890833,0.00009468629,0.00032345322,0.0006641381,0.0023403103,0.0036159977],"genre_scores_gemma":[0.33767042,0.00057049916,0.65802544,0.00040513274,0.000070959424,0.00026938645,0.0012765774,0.00022791715,0.0014836532],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977884,0.0005868467,0.0002084883,0.0004084546,0.00082958175,0.00017816937],"domain_scores_gemma":[0.9941012,0.0039247647,0.0003005689,0.00093189685,0.0005529632,0.00018862275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018513446,0.00085207005,0.0012221088,0.0016468265,0.0011335689,0.00204687,0.0019616513,0.0010509078,0.0023013866],"category_scores_gemma":[0.009656863,0.0007262148,0.0016904667,0.0027492547,0.00083613617,0.004845844,0.0028704472,0.0015671835,0.000745734],"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":[0.001220192,0.0008214864,0.014388969,0.0009065596,0.00036533357,0.0008370416,0.0010556488,0.18733831,0.016186422,0.039043788,0.017138733,0.7206975],"study_design_scores_gemma":[0.00012193113,0.00016196456,0.0012911237,0.00004565659,0.00007120093,0.0005031043,0.0005979451,0.8926214,0.0068141595,0.09030134,0.0074290317,0.00004119705],"about_ca_topic_score_codex":0.002742003,"about_ca_topic_score_gemma":0.006118732,"teacher_disagreement_score":0.002742003,"about_ca_system_score_codex":0.0005867061,"about_ca_system_score_gemma":0.0024502454,"threshold_uncertainty_score":0.009791017},"labels":[],"label_agreement":null},{"id":"W2066881707","doi":"10.1016/j.fss.2004.09.014","title":"Genetic algorithm based framework for mining fuzzy association rules","year":2004,"lang":"en","type":"article","venue":"Fuzzy Sets and Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":133,"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":"Association rule learning; Data mining; Cluster analysis; Apriori algorithm; Fuzzy logic; Fuzzy clustering; Centroid; Computer science; Fuzzy set; Membership function; Mathematics; Fuzzy classification; Defuzzification; Fuzzy set operations; Midpoint; Algorithm; Artificial intelligence; Fuzzy number","score_opus":0.02101407464046413,"score_gpt":0.2648853785248908,"score_spread":0.24387130388442668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066881707","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00956544,0.00029089127,0.98842794,0.00013681993,0.000036676924,0.000090363734,0.00007759775,0.0004307918,0.00094338704],"genre_scores_gemma":[0.14155336,0.00036541824,0.8551487,0.00018487721,0.000054180065,0.0002924609,0.0004129169,0.00004215513,0.001945883],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989292,0.00029347307,0.000080746206,0.00022347533,0.00040950303,0.000063558495],"domain_scores_gemma":[0.99887353,0.0006116869,0.00008052623,0.00009733413,0.00030212276,0.000034877954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017276907,0.0007557167,0.0013784827,0.0028929901,0.0007857105,0.0013688182,0.0023768775,0.0015768462,0.0015691583],"category_scores_gemma":[0.0040833857,0.00041724675,0.0011569776,0.0029999288,0.0008352832,0.0010685179,0.0008154025,0.0013543668,0.00056974764],"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":[0.00015338688,0.00036936323,0.0045066234,0.00021348428,0.0005011143,0.0005300371,0.00027829345,0.44937736,0.006882809,0.048494294,0.0033267047,0.48536658],"study_design_scores_gemma":[0.00003475226,0.00009088978,0.0006351084,0.000034104996,0.00009392959,0.0002062662,0.000036974896,0.96719766,0.0016320695,0.028103668,0.0019140269,0.000020579275],"about_ca_topic_score_codex":0.007117502,"about_ca_topic_score_gemma":0.0057441597,"teacher_disagreement_score":0.007117502,"about_ca_system_score_codex":0.00077535183,"about_ca_system_score_gemma":0.0018344388,"threshold_uncertainty_score":0.014152169},"labels":[],"label_agreement":null},{"id":"W2067393160","doi":"10.4018/ijirr.2013100107","title":"Interactive Visual Analytics of Databases and Frequent Sets","year":2013,"lang":"en","type":"article","venue":"International Journal of Information Retrieval Research","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Visual analytics; Database transaction; Set (abstract data type); Database; Visualization; Information retrieval; Analytics; Data mining; Interactive visual analysis","score_opus":0.06121063490723716,"score_gpt":0.4204395344302275,"score_spread":0.35922889952299036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067393160","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019673692,0.0023846251,0.9473962,0.0018269566,0.0002634757,0.0002710027,0.0023681219,0.010496113,0.015319791],"genre_scores_gemma":[0.20823258,0.0032459905,0.77786374,0.00053008465,0.00043482965,0.0005725373,0.0029624286,0.0009700294,0.0051877806],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987446,0.0004371557,0.0001000155,0.00019793461,0.000448126,0.000072140625],"domain_scores_gemma":[0.9938524,0.0045071007,0.00037808434,0.0004416268,0.00064641907,0.00017445859],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018030395,0.0011478203,0.00062501,0.0048691593,0.00056167896,0.0039233994,0.0012227631,0.00088786834,0.0135949785],"category_scores_gemma":[0.010003289,0.00050465117,0.000829249,0.0032796832,0.0010203131,0.004470275,0.0035991748,0.0011031339,0.001937387],"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":[0.0013868256,0.00019405484,0.0036084251,0.0031545153,0.00018515077,0.0015078417,0.0074101603,0.02800692,0.027694592,0.19305651,0.07004885,0.6637461],"study_design_scores_gemma":[0.00022246792,0.0002626773,0.004215691,0.0010340211,0.00011054061,0.002523681,0.0035179453,0.28106323,0.018159868,0.46915564,0.21951821,0.00021604136],"about_ca_topic_score_codex":0.0013120901,"about_ca_topic_score_gemma":0.001108624,"teacher_disagreement_score":0.0135949785,"about_ca_system_score_codex":0.0005910838,"about_ca_system_score_gemma":0.00050213205,"threshold_uncertainty_score":0.045479774},"labels":[],"label_agreement":null},{"id":"W2068826480","doi":"10.5539/mas.v2n2p35","title":"Electric Power Customer Positioning Model Based on Decision Tree","year":2008,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Decision tree; Electric power; Computer science; Construct (python library); ID3 algorithm; Power (physics); ID3; Process (computing); Tree (set theory); Segmentation; Decision tree model; Data mining; Artificial intelligence; Incremental decision tree; Decision tree learning; Mathematics","score_opus":0.01618573663611076,"score_gpt":0.24608781062998256,"score_spread":0.2299020739938718,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068826480","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07056111,0.0005734335,0.91077495,0.0009831669,0.00014180472,0.00013685628,0.0013672838,0.0007162022,0.014745212],"genre_scores_gemma":[0.9075574,0.00085809466,0.0803208,0.000112589085,0.00009267785,0.00020860533,0.0016818858,0.000051692215,0.009116139],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988262,0.00029965167,0.00008578068,0.00028863014,0.00032720462,0.00017253065],"domain_scores_gemma":[0.99916327,0.0003985443,0.000100349556,0.00003797882,0.00024020963,0.000059661328],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011287605,0.0006237306,0.00081664976,0.0014142118,0.0005185758,0.0016870189,0.0019610855,0.0009538756,0.004842178],"category_scores_gemma":[0.0024659447,0.0003853126,0.00084106,0.0027726186,0.0003549698,0.0019341396,0.0005318497,0.00089877174,0.0011128373],"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":[0.0001214055,0.000080923484,0.0047641457,0.0000962532,0.00006657436,0.0002701932,0.0001411729,0.8983294,0.00054690364,0.037233055,0.0032310225,0.055118915],"study_design_scores_gemma":[0.000008363323,0.000019875919,0.0003943993,0.000005679284,0.000014404076,0.000042083382,0.000014616473,0.9913521,0.00010229349,0.0072034574,0.00083330425,0.000009515729],"about_ca_topic_score_codex":0.014501452,"about_ca_topic_score_gemma":0.009127755,"teacher_disagreement_score":0.014501452,"about_ca_system_score_codex":0.0012365167,"about_ca_system_score_gemma":0.00091555226,"threshold_uncertainty_score":0.028834105},"labels":[],"label_agreement":null},{"id":"W2069255081","doi":"10.1002/widm.40","title":"Fuzzy association rule mining framework and its application to effective fuzzy associative classification","year":2011,"lang":"en","type":"article","venue":"Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Western University","funders":"","keywords":"Association rule learning; Data mining; Fuzzy classification; Artificial intelligence; Fuzzy set operations; Fuzzy logic; Computer science; Neuro-fuzzy; Defuzzification; Machine learning; Fuzzy rule; Fuzzy set; Classifier (UML); Fuzzy number; Fuzzy clustering; Pattern recognition (psychology); Fuzzy control system","score_opus":0.06305845491350742,"score_gpt":0.3417930014364239,"score_spread":0.27873454652291646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069255081","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00776189,0.00050219643,0.98987234,0.00018413014,0.000036136174,0.00007199076,0.000036277233,0.00013094231,0.0014041053],"genre_scores_gemma":[0.22393078,0.0005188477,0.77381456,0.00009996346,0.000102726706,0.00020329357,0.00014496101,0.000025280555,0.0011596158],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966456,0.0011488666,0.00028863433,0.00049190054,0.0012842031,0.00014077032],"domain_scores_gemma":[0.9973477,0.0013028343,0.00022757343,0.00017404852,0.0008675726,0.000080278485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004993999,0.0006029322,0.0011087486,0.0031820978,0.0010270479,0.001650505,0.0016151344,0.0009727199,0.0016694806],"category_scores_gemma":[0.0081509845,0.0002921155,0.0011942409,0.0026810393,0.0011465352,0.001696626,0.0011238283,0.001072831,0.00043466347],"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":[0.00013409306,0.0002909097,0.0031379259,0.0003057903,0.00021077147,0.0006918834,0.0006837372,0.26260164,0.0052158805,0.32253385,0.0034952855,0.40069827],"study_design_scores_gemma":[0.000009295232,0.000032134296,0.00026713655,0.00002443257,0.00002318417,0.00010439461,0.000032242624,0.95720637,0.0011329923,0.038270917,0.002882792,0.000014083369],"about_ca_topic_score_codex":0.004776614,"about_ca_topic_score_gemma":0.0026739964,"teacher_disagreement_score":0.004993999,"about_ca_system_score_codex":0.0009465434,"about_ca_system_score_gemma":0.0015102884,"threshold_uncertainty_score":0.026411116},"labels":[],"label_agreement":null},{"id":"W2069318033","doi":"10.1109/icde.2010.5447820","title":"Efficient identification of coupled entities in document collections","year":2010,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Identification (biology); Information retrieval; Core (optical fiber); Pace; Value (mathematics); Data science; Data mining; World Wide Web; Geography","score_opus":0.006950176333583624,"score_gpt":0.24722710925159874,"score_spread":0.2402769329180151,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069318033","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2609639,0.0018301838,0.72752917,0.0005015182,0.000051983196,0.0007174738,0.0028259233,0.0036734957,0.0019063498],"genre_scores_gemma":[0.26567233,0.00056579127,0.7273602,0.00006136469,0.000057514666,0.00021189895,0.0047556087,0.00021897173,0.0010963569],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99615675,0.00077507575,0.000540364,0.0010725592,0.0011976158,0.00025773808],"domain_scores_gemma":[0.9889408,0.005243048,0.0018279505,0.0021568132,0.0014264891,0.0004049327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031232075,0.0010636152,0.0019867688,0.0074387975,0.0018132516,0.0048011485,0.002800128,0.001412111,0.00083709636],"category_scores_gemma":[0.020007372,0.0012849058,0.0013999483,0.008830023,0.0012860321,0.007291189,0.003762812,0.0012473334,0.0006827358],"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":[0.00078398205,0.00041720763,0.06572029,0.0016992177,0.00071897206,0.0012479238,0.0039007235,0.07818832,0.04386374,0.021363555,0.008627829,0.77346826],"study_design_scores_gemma":[0.00009740516,0.00035568723,0.028989298,0.00021103617,0.000521371,0.00238694,0.0036826378,0.7968583,0.05721187,0.087087035,0.02239923,0.0001991381],"about_ca_topic_score_codex":0.0038702956,"about_ca_topic_score_gemma":0.0077557536,"teacher_disagreement_score":0.0074387975,"about_ca_system_score_codex":0.0009887825,"about_ca_system_score_gemma":0.001960439,"threshold_uncertainty_score":0.016517282},"labels":[],"label_agreement":null},{"id":"W2071386504","doi":"10.1145/1982185.1982399","title":"Equivalence class transformation based mining of frequent itemsets from uncertain data","year":2011,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Probabilistic logic; Data mining; Transformation (genetics); Equivalence (formal languages); Computer science; Equivalence class (music); Class (philosophy); Uncertain data; Data transformation; Mathematics; Artificial intelligence; Data warehouse; Discrete mathematics","score_opus":0.17545549848142186,"score_gpt":0.3027612175957297,"score_spread":0.12730571911430785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071386504","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038715035,0.00023030242,0.95880103,0.0001739983,0.00003852379,0.00010273,0.00024467125,0.0005627226,0.0011309816],"genre_scores_gemma":[0.50182426,0.00035948522,0.49473742,0.00012347999,0.000096477444,0.00022438972,0.0017239911,0.000068311834,0.0008421648],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975333,0.00050915027,0.0002461095,0.00046254773,0.0010961407,0.0001527043],"domain_scores_gemma":[0.99583924,0.0024843607,0.00041987532,0.0005499884,0.0006247276,0.00008192658],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001462536,0.00037160306,0.0009070863,0.0023337544,0.0004755861,0.001051713,0.0012481795,0.000592632,0.0012843473],"category_scores_gemma":[0.008867805,0.00019091398,0.0009074364,0.0024985669,0.0006298354,0.0022790441,0.0013180658,0.00093479815,0.00032152818],"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":[0.0004250721,0.00030578772,0.006699707,0.00022144146,0.00013238103,0.00072090444,0.00041806194,0.05692696,0.012352368,0.035037648,0.0031792482,0.8835804],"study_design_scores_gemma":[0.000082703285,0.0002719179,0.0037766953,0.00003590547,0.00007006357,0.0011505978,0.0002840003,0.87078696,0.020867119,0.09494301,0.007683109,0.000047822097],"about_ca_topic_score_codex":0.0007311514,"about_ca_topic_score_gemma":0.0004960471,"teacher_disagreement_score":0.0023337544,"about_ca_system_score_codex":0.00031843974,"about_ca_system_score_gemma":0.0004959979,"threshold_uncertainty_score":0.007734716},"labels":[],"label_agreement":null},{"id":"W2072065544","doi":"10.1145/1923947.1923983","title":"An introduction to data mining and predictive analytics","year":2010,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada)","funders":"","keywords":"Computer science; Analytics; Data science; Process (computing); Data mining; Predictive analytics; Data analysis; Artificial intelligence","score_opus":0.02519771867409121,"score_gpt":0.29814220958508597,"score_spread":0.27294449091099476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072065544","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014289712,0.3323549,0.57603586,0.029832141,0.009755742,0.000377225,0.0029112282,0.0023597812,0.04494417],"genre_scores_gemma":[0.031537995,0.33105767,0.56791264,0.012829734,0.020559678,0.0010477342,0.0035058153,0.00048223513,0.031066522],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953122,0.0011475101,0.0005456802,0.0007565074,0.0021020968,0.00013588431],"domain_scores_gemma":[0.99139434,0.006616007,0.0002729577,0.0007941238,0.0006980959,0.00022437496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00390797,0.0017161178,0.0023032802,0.0042217094,0.00087700604,0.0059068617,0.0025610267,0.002884564,0.011789393],"category_scores_gemma":[0.009153239,0.000845647,0.0015523954,0.009350381,0.0031467255,0.008853186,0.0023610923,0.005992571,0.008866878],"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":[0.00007868393,0.00011549332,0.0011998868,0.0033953066,0.00018702864,0.0003466631,0.00047565522,0.0043580784,0.0012958888,0.31154534,0.15775552,0.51924646],"study_design_scores_gemma":[0.000019025476,0.00006401831,0.000576211,0.000815622,0.000030635405,0.0005710768,0.00013073605,0.005969284,0.00039505668,0.32490003,0.66647047,0.000057795703],"about_ca_topic_score_codex":0.0010918208,"about_ca_topic_score_gemma":0.0010900617,"teacher_disagreement_score":0.011789393,"about_ca_system_score_codex":0.0012519492,"about_ca_system_score_gemma":0.0020996581,"threshold_uncertainty_score":0.03943944},"labels":[],"label_agreement":null},{"id":"W2073184692","doi":"10.1007/s10618-005-1359-6","title":"Data Mining for Inventory Item Selection with Cross-Selling Considerations","year":2005,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Data Mining Algorithms and Applications","field":"Computer Science","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","funders":"","keywords":"Association rule learning; Computer science; Data mining; Profit (economics); Selection (genetic algorithm); Greedy algorithm; Machine learning; Algorithm; Economics","score_opus":0.10575153970874877,"score_gpt":0.3499721572955075,"score_spread":0.24422061758675873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073184692","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25291735,0.0042956676,0.7220311,0.0019450964,0.00027138088,0.000606527,0.004077391,0.001141816,0.012713704],"genre_scores_gemma":[0.75691193,0.0008123646,0.23362523,0.00021523908,0.0002921006,0.0003090598,0.003915254,0.00007253004,0.0038462454],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99669755,0.00083998754,0.00040959808,0.000725933,0.0011591386,0.0001678758],"domain_scores_gemma":[0.9888958,0.0076374584,0.0007471894,0.0012475009,0.0012764344,0.00019567701],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004446562,0.0009305151,0.0019039387,0.0042691766,0.0011163482,0.0031139038,0.0018607157,0.0009561267,0.005448673],"category_scores_gemma":[0.019926373,0.00068119966,0.0019267687,0.0059620263,0.00057748676,0.003994374,0.001203365,0.0013000935,0.0010608946],"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":[0.001990671,0.0012145969,0.12547451,0.0011520879,0.0011734884,0.0020015733,0.00040730563,0.102244444,0.0044379835,0.038259387,0.012708386,0.7089356],"study_design_scores_gemma":[0.00012496562,0.00054847397,0.023921179,0.00022489607,0.0005565143,0.0019230465,0.00042682028,0.8859912,0.006802899,0.068363704,0.011050297,0.00006610526],"about_ca_topic_score_codex":0.0011605578,"about_ca_topic_score_gemma":0.001762806,"teacher_disagreement_score":0.005448673,"about_ca_system_score_codex":0.00075936154,"about_ca_system_score_gemma":0.0011196289,"threshold_uncertainty_score":0.023516},"labels":[],"label_agreement":null},{"id":"W2074432012","doi":"10.1145/1610555.1610557","title":"Efficient algorithms for mining constrained frequent patterns from uncertain data","year":2009,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":42,"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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Association rule learning; Data mining; K-optimal pattern discovery; Database transaction; Data stream mining; Geodetic datum; Uncertain data; Knowledge extraction; Sequential Pattern Mining; Database","score_opus":0.07913958170490928,"score_gpt":0.32447663181875375,"score_spread":0.24533705011384446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074432012","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0070557534,0.0006232621,0.99112225,0.00015077637,0.000029858604,0.00014091616,0.00020339103,0.00032167096,0.00035224957],"genre_scores_gemma":[0.04953276,0.00050080114,0.94817835,0.00007555586,0.000066408866,0.00037660912,0.00085969584,0.000037215064,0.00037257167],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99738175,0.0005456693,0.00040852022,0.00051540957,0.0009816353,0.00016700593],"domain_scores_gemma":[0.9929516,0.0048075924,0.0005934074,0.0006911365,0.00084302155,0.00011327106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00269286,0.0011736652,0.0022906044,0.003273169,0.0011754049,0.0019027212,0.0030197303,0.0015916267,0.0013180295],"category_scores_gemma":[0.013902856,0.0009122403,0.0013664034,0.005493371,0.00069445005,0.004072363,0.0022423312,0.0015470763,0.00072070304],"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":[0.00026367154,0.000266223,0.0030439948,0.00050970825,0.0002360796,0.0005498461,0.0003632864,0.2157964,0.003011413,0.023558358,0.0057799607,0.7466211],"study_design_scores_gemma":[0.0000868669,0.000078840545,0.0005063928,0.000051542527,0.000050763665,0.0005698729,0.00012587372,0.93637633,0.0017971,0.056145586,0.00418197,0.000028831124],"about_ca_topic_score_codex":0.0015886092,"about_ca_topic_score_gemma":0.0020531367,"teacher_disagreement_score":0.003273169,"about_ca_system_score_codex":0.00055687065,"about_ca_system_score_gemma":0.0014476251,"threshold_uncertainty_score":0.014241397},"labels":[],"label_agreement":null},{"id":"W2074741303","doi":"10.1145/1276958.1277329","title":"Discovering rules in the poker hand dataset","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Artificial intelligence; Information retrieval; Data science","score_opus":0.02079449577083023,"score_gpt":0.28830016884704784,"score_spread":0.26750567307621764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074741303","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45010903,0.005827602,0.0153128365,0.0030574107,0.0009917599,0.0009151319,0.48138538,0.005134402,0.037266485],"genre_scores_gemma":[0.24584873,0.0015482131,0.03686353,0.00036846404,0.00019287024,0.00047883892,0.69797784,0.000282505,0.016439037],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989675,0.00015190711,0.0001198155,0.00025286662,0.00039611943,0.00011185621],"domain_scores_gemma":[0.99619764,0.0022132464,0.00018550885,0.00068617234,0.00035538134,0.0003619732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010408375,0.0007371433,0.0009201443,0.0042726523,0.0009971063,0.0011085554,0.0014174781,0.0016769144,0.014779269],"category_scores_gemma":[0.0054583475,0.00024767785,0.00076324685,0.0033317902,0.000488294,0.0012258932,0.0010541395,0.0012066035,0.0050277174],"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":[0.0029218472,0.0017234172,0.046386994,0.0026181017,0.00045759502,0.0038033512,0.00029455384,0.009109718,0.0061661107,0.0029988156,0.46147877,0.46204072],"study_design_scores_gemma":[0.0017476591,0.0016979052,0.21758322,0.001471442,0.0008211551,0.0051118354,0.002739977,0.107548304,0.030019647,0.023151917,0.6077424,0.00036443485],"about_ca_topic_score_codex":0.006892954,"about_ca_topic_score_gemma":0.022149093,"teacher_disagreement_score":0.014779269,"about_ca_system_score_codex":0.0004450114,"about_ca_system_score_gemma":0.0012364668,"threshold_uncertainty_score":0.049441576},"labels":[],"label_agreement":null},{"id":"W2074837969","doi":"10.1145/1992896.1992902","title":"Fastest association rule mining algorithm predictor (FARM-AP)","year":2011,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Association rule learning; Computer science; Implementation; Partition (number theory); Data mining; Block (permutation group theory); Field (mathematics); Partition problem; Algorithm design; Algorithm; Programming language","score_opus":0.02382052414332731,"score_gpt":0.22939507028550798,"score_spread":0.20557454614218068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074837969","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.057959925,0.0037973092,0.9094031,0.0017903687,0.0011585734,0.0004769813,0.0022363227,0.01304591,0.010131447],"genre_scores_gemma":[0.19466032,0.0013356718,0.7882769,0.0006555708,0.00040071338,0.00059111346,0.004012151,0.0005312839,0.009536367],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972366,0.0006533824,0.00023366956,0.00082886324,0.00072526385,0.0003220924],"domain_scores_gemma":[0.9928773,0.0027591642,0.00046654302,0.0015750093,0.0020407967,0.00028122115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034733023,0.0009904158,0.0018309165,0.0020241202,0.0013404033,0.0026595641,0.003123139,0.0015999684,0.008550298],"category_scores_gemma":[0.01450302,0.0007271015,0.0009599576,0.0031144798,0.0005335695,0.003513139,0.0022647218,0.0021784564,0.007098303],"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":[0.00132962,0.000572336,0.016910784,0.0005373708,0.00024352968,0.00033963754,0.00014163337,0.04895878,0.004598351,0.010801794,0.04962903,0.8659371],"study_design_scores_gemma":[0.00045745913,0.0009274293,0.0039518573,0.00012710465,0.00019925438,0.0017681813,0.00016121761,0.8941438,0.013642855,0.03622116,0.048322167,0.00007751892],"about_ca_topic_score_codex":0.0018516752,"about_ca_topic_score_gemma":0.0024986393,"teacher_disagreement_score":0.008550298,"about_ca_system_score_codex":0.00048534872,"about_ca_system_score_gemma":0.004097862,"threshold_uncertainty_score":0.028603554},"labels":[],"label_agreement":null},{"id":"W2075772152","doi":"10.1145/1774088.1774305","title":"Mining uncertain data for frequent itemsets that satisfy aggregate constraints","year":2010,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Aggregate (composite); Computer science; Database transaction; Constraint (computer-aided design); Data mining; Uncertain data; Process (computing); Computation; Tree (set theory); Database; Algorithm; Engineering; Mathematics","score_opus":0.07917583322538332,"score_gpt":0.3226308264401625,"score_spread":0.24345499321477918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075772152","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07245844,0.0005563544,0.9238222,0.00031233532,0.000030774823,0.0001863099,0.0012202845,0.00047600863,0.00093720434],"genre_scores_gemma":[0.3203015,0.000517957,0.6743665,0.00018658568,0.000075493044,0.0003371999,0.0037123717,0.00007354815,0.00042889564],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961145,0.00072564813,0.00060308125,0.00069749303,0.0016760471,0.00018316523],"domain_scores_gemma":[0.98398095,0.011403448,0.0015666841,0.0011301365,0.0016855663,0.00023322018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037016792,0.0007216656,0.0018352265,0.0027341647,0.0009804085,0.002423308,0.0015517671,0.0010616852,0.0012751063],"category_scores_gemma":[0.024426827,0.00057374104,0.0016377721,0.004137835,0.00059342326,0.004472429,0.0014899777,0.0010108284,0.00048974203],"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":[0.0012607714,0.0004711062,0.04752462,0.0015563578,0.00082668144,0.00363794,0.001887629,0.25675273,0.028824886,0.06653176,0.010115716,0.58060986],"study_design_scores_gemma":[0.00007355858,0.00021750336,0.003422002,0.00018022531,0.00017652416,0.0015854816,0.00058887555,0.8986856,0.010127557,0.07750015,0.0073753935,0.0000671436],"about_ca_topic_score_codex":0.0011125798,"about_ca_topic_score_gemma":0.001528946,"teacher_disagreement_score":0.0037016792,"about_ca_system_score_codex":0.0003870925,"about_ca_system_score_gemma":0.0013004942,"threshold_uncertainty_score":0.01957655},"labels":[],"label_agreement":null},{"id":"W2077020471","doi":"10.1007/s00778-005-0179-z","title":"Special issue: Best papers of VLDB 2004","year":2005,"lang":"en","type":"article","venue":"The VLDB Journal","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":"University of Toronto; University of Waterloo","funders":"","keywords":"Very large database; Computer science; Data science; Data mining","score_opus":0.014589702295020011,"score_gpt":0.2587781872719452,"score_spread":0.24418848497692516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077020471","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021549922,0.07485902,0.008321708,0.06555553,0.71407217,0.0005572876,0.021022966,0.0032234713,0.11023279],"genre_scores_gemma":[0.008721948,0.058674376,0.0065004476,0.012327414,0.27241293,0.00031653172,0.04004293,0.0024774561,0.59852594],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976109,0.00032915428,0.0002844732,0.00037090929,0.001155444,0.00024907358],"domain_scores_gemma":[0.98408115,0.002626786,0.00080467813,0.0012956235,0.007856855,0.0033349576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033222116,0.0023950043,0.0043371837,0.010889002,0.0020562361,0.014219285,0.0029410867,0.0027878697,0.1888429],"category_scores_gemma":[0.012046314,0.0008465702,0.0013775011,0.011314165,0.00083075167,0.0051495316,0.0019778165,0.0028413665,0.12121795],"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":[0.00006614758,0.000021354912,0.00009013212,0.00015941316,0.000009846363,0.000025114143,0.0000040095347,0.00006974428,0.00013408248,0.0004149133,0.97924316,0.019762157],"study_design_scores_gemma":[0.000036365516,0.00003679166,0.00056666415,0.00018615497,0.000037017362,0.00010200655,0.000017998529,0.00033178052,0.00037411303,0.0014419741,0.9968541,0.000015048147],"about_ca_topic_score_codex":0.003996015,"about_ca_topic_score_gemma":0.006116969,"teacher_disagreement_score":0.1888429,"about_ca_system_score_codex":0.00366304,"about_ca_system_score_gemma":0.003953946,"threshold_uncertainty_score":0.6317424},"labels":[],"label_agreement":null},{"id":"W2077155372","doi":"10.1006/aama.2001.0758","title":"A Structured Family of Clustering and Tree Construction Methods","year":2001,"lang":"en","type":"article","venue":"Advances in Applied Mathematics","topic":"Data Mining Algorithms and Applications","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":"McGill University","funders":"","keywords":"Mathematics; Disjoint sets; Cluster analysis; Hierarchical clustering; Cluster (spacecraft); Tree (set theory); Theoretical computer science; Combinatorics; Set (abstract data type); Computer science; Statistics","score_opus":0.018972937093347356,"score_gpt":0.3204450755155659,"score_spread":0.30147213842221854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077155372","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003604842,0.00028684924,0.9983864,0.00007060981,0.00005948052,0.00003678357,0.00007407103,0.00026829372,0.00045705072],"genre_scores_gemma":[0.009235804,0.000771397,0.98614144,0.0002088141,0.00019169424,0.00027405328,0.0005836345,0.00032141377,0.0022716252],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99565166,0.0015211531,0.00026431034,0.00083320006,0.0016034069,0.00012633656],"domain_scores_gemma":[0.9912794,0.003273517,0.00037157146,0.00236419,0.0023686676,0.0003425864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044999155,0.0016328838,0.00203902,0.0037264146,0.0017071319,0.002058336,0.0034767666,0.0021280048,0.006616101],"category_scores_gemma":[0.016297983,0.0012427529,0.0033879993,0.0055167275,0.0012604527,0.003759305,0.0043170913,0.0043765856,0.006721159],"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":[0.000117516756,0.00016055162,0.0010708083,0.0006440637,0.00023547628,0.0000977306,0.00034409028,0.031006796,0.005130019,0.131764,0.022081451,0.80734754],"study_design_scores_gemma":[0.000120945486,0.0002630816,0.0009434901,0.00027770997,0.00019031188,0.0007872426,0.00015874713,0.49456006,0.0058923583,0.42760766,0.06910126,0.00009718474],"about_ca_topic_score_codex":0.0010857297,"about_ca_topic_score_gemma":0.002036495,"teacher_disagreement_score":0.006616101,"about_ca_system_score_codex":0.00073422474,"about_ca_system_score_gemma":0.001957466,"threshold_uncertainty_score":0.023798108},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008779426,0.0002639309,0.9865739,0.00019838371,0.0000783022,0.00040622393,0.0011407597,0.0012905154,0.0012685151],"genre_scores_gemma":[0.087221764,0.00028271854,0.9078753,0.00010793413,0.000041068448,0.0005440522,0.002225805,0.00006854393,0.00163277],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99668014,0.0008990314,0.0005351149,0.00063592027,0.0011263686,0.00012346607],"domain_scores_gemma":[0.9915455,0.005728547,0.00046825517,0.0003976678,0.0016492457,0.00021071202],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028497824,0.0007054725,0.0011481505,0.004950769,0.0009336949,0.002582649,0.0013437119,0.0012767226,0.005750876],"category_scores_gemma":[0.01289001,0.0005311655,0.0011711105,0.0038055985,0.0006068251,0.0027355107,0.0009251632,0.0010808078,0.0015777234],"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":[0.0016688128,0.00079754245,0.016397556,0.0023484125,0.00040133003,0.0010882638,0.00070283335,0.057766594,0.02440337,0.08915106,0.011152012,0.7941223],"study_design_scores_gemma":[0.00032757668,0.000701722,0.003866563,0.00033945646,0.0004982288,0.0015005086,0.00029996096,0.84523046,0.021229744,0.089700565,0.03615619,0.00014906634],"about_ca_topic_score_codex":0.0037951896,"about_ca_topic_score_gemma":0.0041584945,"teacher_disagreement_score":0.005750876,"about_ca_system_score_codex":0.00079399126,"about_ca_system_score_gemma":0.0019808684,"threshold_uncertainty_score":0.019238532},"labels":[],"label_agreement":null},{"id":"W2077981172","doi":"10.1109/bdcloud.2014.136","title":"A Data Science Solution for Mining Interesting Patterns from Uncertain Big Data","year":2014,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":65,"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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Big data; Computer science; Uncertain data; Database transaction; Data mining; Transaction data; Focus (optics); Computation; Tree (set theory); Data science; Data stream mining; Database; Algorithm; Mathematics","score_opus":0.26748523354361164,"score_gpt":0.3601249488761387,"score_spread":0.09263971533252707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077981172","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051426543,0.0002462773,0.99168736,0.0009703551,0.00005976747,0.00013132347,0.00038650527,0.0005212582,0.000854466],"genre_scores_gemma":[0.061416168,0.00031599682,0.93606025,0.00026637097,0.000095461866,0.00022578429,0.00077283604,0.0000498342,0.0007973077],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984352,0.00023113839,0.00015060672,0.0003741053,0.0007259417,0.00008302869],"domain_scores_gemma":[0.99769646,0.0011279996,0.00023398407,0.00038168358,0.0004354561,0.00012451322],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017308614,0.00084032223,0.0009854912,0.0023470414,0.0012461768,0.0020841723,0.0020739054,0.0014624553,0.0019551327],"category_scores_gemma":[0.008297678,0.0006524962,0.0021022994,0.003876022,0.00094639556,0.00359094,0.0024288844,0.0019430621,0.00078349584],"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":[0.000440115,0.0005434513,0.005854717,0.0014083222,0.00047146127,0.0012599089,0.00097638,0.209248,0.011709154,0.17579621,0.02717092,0.56512135],"study_design_scores_gemma":[0.000056011657,0.00007836946,0.00045760852,0.000052952084,0.00005266813,0.00041461395,0.0002496007,0.78780794,0.0034866184,0.19536138,0.0119530335,0.000029266716],"about_ca_topic_score_codex":0.0023024674,"about_ca_topic_score_gemma":0.0031965189,"teacher_disagreement_score":0.0023470414,"about_ca_system_score_codex":0.0005861424,"about_ca_system_score_gemma":0.0020211106,"threshold_uncertainty_score":0.009153783},"labels":[],"label_agreement":null},{"id":"W2078064242","doi":"10.1023/b:dami.0000023674.74932.4c","title":"Pushing Convertible Constraints in Frequent Itemset Mining","year":2004,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":134,"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 British Columbia","funders":"","keywords":"Constraint (computer-aided design); Computer science; Data mining; Context (archaeology); Association rule learning; Convertible; A priori and a posteriori; Class (philosophy); Apriori algorithm; Monotonic function; Sequential Pattern Mining; Artificial intelligence; Mathematics; Engineering; Geography","score_opus":0.04812423122534112,"score_gpt":0.2999252304469889,"score_spread":0.2518009992216478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078064242","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061209988,0.0031864594,0.92396307,0.0022040133,0.00044184053,0.00039710946,0.0015404589,0.0014474405,0.0056095864],"genre_scores_gemma":[0.3256478,0.0022440637,0.6614846,0.000805379,0.00044455964,0.0003639216,0.0034773964,0.00033877513,0.0051934184],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9913293,0.002363333,0.0010018512,0.001404176,0.0034825986,0.0004185825],"domain_scores_gemma":[0.9512032,0.037253078,0.0020197388,0.005807577,0.0030127044,0.0007036111],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007770571,0.0011203683,0.0024950386,0.005193333,0.0017461644,0.005434884,0.0043817377,0.002693982,0.0057859956],"category_scores_gemma":[0.07125326,0.0019642464,0.002228376,0.0071308315,0.002327159,0.013502907,0.005022739,0.005739216,0.0011916584],"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":[0.0012552697,0.0006220003,0.009343117,0.0016320517,0.00043886446,0.0030670112,0.001541019,0.107940264,0.0049430314,0.25365418,0.013216594,0.6023466],"study_design_scores_gemma":[0.00013414597,0.00020466292,0.0013239052,0.00034459884,0.00019795036,0.0012686057,0.0004854435,0.428769,0.0046202815,0.5465281,0.016034681,0.00008863499],"about_ca_topic_score_codex":0.003388511,"about_ca_topic_score_gemma":0.0037205575,"teacher_disagreement_score":0.007770571,"about_ca_system_score_codex":0.000814135,"about_ca_system_score_gemma":0.0016011738,"threshold_uncertainty_score":0.041095197},"labels":[],"label_agreement":null},{"id":"W2078645062","doi":"10.2991/ijcis.2011.4.1.2","title":"Experimental Comparison of Iterative Versus Evolutionary Crisp and Rough Clustering","year":2011,"lang":"en","type":"article","venue":"International Journal of Computational Intelligence Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint Mary's University","funders":"","keywords":"Cluster analysis; Mathematics; Computer science; Artificial intelligence; Pattern recognition (psychology); Data mining","score_opus":0.09646447562586563,"score_gpt":0.3715459763866903,"score_spread":0.27508150076082466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078645062","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7691313,0.0018268398,0.20393385,0.00037957274,0.0003039012,0.00052296073,0.0012442173,0.0037189757,0.01893834],"genre_scores_gemma":[0.7651031,0.00042125312,0.22928406,0.000062567844,0.00003107659,0.00027353232,0.0018349516,0.00035662513,0.002632811],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966594,0.0010125894,0.00032383937,0.00047248462,0.0013631139,0.00016853973],"domain_scores_gemma":[0.98396677,0.008650471,0.0004843636,0.0019066633,0.0047816695,0.0002101462],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041633095,0.0007010892,0.0008333919,0.0029319252,0.0010204955,0.0015197897,0.0013777207,0.0009909945,0.0025057753],"category_scores_gemma":[0.017573211,0.0002664004,0.00048432712,0.0032404002,0.000719415,0.0013797074,0.00082772254,0.0004821031,0.0006628645],"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":[0.004956667,0.0014120095,0.0060565625,0.0018553745,0.00047466924,0.00026700465,0.0010217838,0.33927605,0.07649172,0.0073491265,0.005375503,0.5554636],"study_design_scores_gemma":[0.00028237482,0.0019815543,0.017638652,0.0001084086,0.00016157597,0.00036058025,0.00093996036,0.8582055,0.109886885,0.0044749146,0.00579994,0.00015959184],"about_ca_topic_score_codex":0.0033856104,"about_ca_topic_score_gemma":0.0031191646,"teacher_disagreement_score":0.0041633095,"about_ca_system_score_codex":0.0006947757,"about_ca_system_score_gemma":0.000513139,"threshold_uncertainty_score":0.022017956},"labels":[],"label_agreement":null},{"id":"W2079695515","doi":"10.1145/2351476.2351479","title":"A constrained frequent pattern mining system for handling aggregate constraints","year":2012,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Aggregate (composite); Computer science; Data mining; Range (aeronautics); Value (mathematics); Machine learning; Engineering","score_opus":0.030248318801918146,"score_gpt":0.2656152109575963,"score_spread":0.2353668921556782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079695515","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0067576277,0.00025348924,0.97817594,0.00026117792,0.000082394065,0.00046241478,0.0021742245,0.010674005,0.0011586468],"genre_scores_gemma":[0.042327754,0.00020761513,0.95131594,0.00023630164,0.000058578236,0.00057064305,0.003557921,0.00024720002,0.0014780612],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970197,0.00054213183,0.0006422338,0.0007564528,0.0009091027,0.00013031083],"domain_scores_gemma":[0.99492586,0.0019197694,0.0004949675,0.001110168,0.0013663195,0.00018289975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033344163,0.0009945839,0.001725731,0.003433547,0.0019458428,0.0022745542,0.0029236125,0.0015889716,0.0067664273],"category_scores_gemma":[0.012849828,0.0008049112,0.0013507206,0.0053719007,0.00051943975,0.004253264,0.0022378028,0.0015889292,0.003542347],"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":[0.0012200391,0.00058934756,0.011820814,0.0015830507,0.0006494931,0.0030718588,0.0010851185,0.04438415,0.029748337,0.0424445,0.06370344,0.79969984],"study_design_scores_gemma":[0.00034418848,0.00033951513,0.0035621317,0.0001866152,0.0003435742,0.0036503575,0.0002304889,0.8197648,0.020004634,0.051974464,0.099376075,0.00022313325],"about_ca_topic_score_codex":0.0034806398,"about_ca_topic_score_gemma":0.0047173705,"teacher_disagreement_score":0.0067664273,"about_ca_system_score_codex":0.0005521859,"about_ca_system_score_gemma":0.0024859502,"threshold_uncertainty_score":0.022635996},"labels":[],"label_agreement":null},{"id":"W2080533345","doi":"10.1007/s10844-006-2618-8","title":"An efficient approach to mining indirect associations","year":2006,"lang":"en","type":"article","venue":"Journal of Intelligent Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":25,"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; Association rule learning; Data mining; struct; Set (abstract data type); Efficient algorithm; Algorithm","score_opus":0.02252393769148645,"score_gpt":0.2616728185588945,"score_spread":0.23914888086740807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080533345","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031944294,0.0012830676,0.95989853,0.00043101623,0.00012045473,0.0003372825,0.0014231033,0.0023206116,0.0022415852],"genre_scores_gemma":[0.15745753,0.00063283055,0.8329218,0.00017151803,0.00016475124,0.00034772753,0.0036704028,0.000112271635,0.0045210687],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99693334,0.00047715713,0.0003598729,0.0005330103,0.0015210008,0.00017569792],"domain_scores_gemma":[0.99288565,0.0039899107,0.0004019902,0.0012094633,0.0013425639,0.00017045083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019153749,0.0011185234,0.002108886,0.0062995534,0.0017782756,0.0027945389,0.0029725924,0.0013124669,0.0034643945],"category_scores_gemma":[0.010782055,0.0008748615,0.001564426,0.006367627,0.0008341443,0.0034983666,0.00287042,0.0018342824,0.0018132776],"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":[0.0005114841,0.0006336015,0.01006617,0.00037078746,0.00037887244,0.0005444264,0.00032190155,0.019757092,0.008724493,0.025912415,0.011915239,0.9208635],"study_design_scores_gemma":[0.00022310884,0.0002721995,0.0047595445,0.00012026114,0.0004925171,0.0020402204,0.0003865475,0.81729597,0.010518755,0.1451983,0.018600317,0.000092189824],"about_ca_topic_score_codex":0.003121452,"about_ca_topic_score_gemma":0.008400929,"teacher_disagreement_score":0.0062995534,"about_ca_system_score_codex":0.00058964954,"about_ca_system_score_gemma":0.0028954134,"threshold_uncertainty_score":0.011589587},"labels":[],"label_agreement":null},{"id":"W2080706130","doi":"10.1145/347090.347139","title":"<i>RuleViz</i>","year":2000,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science","score_opus":0.006996232053514642,"score_gpt":0.21499089057654455,"score_spread":0.2079946585230299,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080706130","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030717647,0.0008272444,0.3107721,0.007834245,0.0037308973,0.001368012,0.1034555,0.30636805,0.26257223],"genre_scores_gemma":[0.04576258,0.0023022254,0.31810313,0.005454669,0.0020879763,0.0023370325,0.19937839,0.112969756,0.31160417],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987483,0.00022073029,0.00010733187,0.00018897753,0.0006252537,0.000109427296],"domain_scores_gemma":[0.9936552,0.002632507,0.0003262783,0.0016274756,0.0011781229,0.00058042025],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018001864,0.0010668111,0.0009867117,0.0034700194,0.00089696795,0.0063919113,0.0033718403,0.0023460623,0.31729388],"category_scores_gemma":[0.014089205,0.00078800827,0.0013840563,0.0042992453,0.0009223985,0.0059059993,0.0031446503,0.001850359,0.14083223],"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":[0.00015970341,0.000048988535,0.00054237596,0.00038332053,0.000023819339,0.00018901422,0.00018539952,0.0013170897,0.0013041632,0.012215098,0.9071814,0.076449804],"study_design_scores_gemma":[0.000070021146,0.00004072865,0.00071091496,0.00015684657,0.000015769148,0.00019215941,0.00006190799,0.012102937,0.0024759227,0.014610816,0.9695143,0.000047692378],"about_ca_topic_score_codex":0.006338862,"about_ca_topic_score_gemma":0.009956244,"teacher_disagreement_score":0.31729388,"about_ca_system_score_codex":0.0010195441,"about_ca_system_score_gemma":0.0016603565,"threshold_uncertainty_score":0.97379744},"labels":[],"label_agreement":null},{"id":"W2080792813","doi":"10.1145/1401890.1402023","title":"DiMaC","year":2008,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Missing data; Computer science; Data mining; Information retrieval; Machine learning","score_opus":0.026135039105471623,"score_gpt":0.22987644217365183,"score_spread":0.2037414030681802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080792813","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008331456,0.004959492,0.7144677,0.002866973,0.004696287,0.0004212576,0.023513002,0.074689634,0.1660542],"genre_scores_gemma":[0.12897317,0.0029099644,0.5397557,0.003929801,0.001733759,0.00084190926,0.092165306,0.014045816,0.21564463],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99801457,0.00029453417,0.00008730209,0.0005995284,0.0007945994,0.00020935533],"domain_scores_gemma":[0.99822086,0.00016169934,0.000071064875,0.00073513715,0.0006528986,0.0001583368],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018977453,0.0019228077,0.001759817,0.00295701,0.0020730214,0.0052429833,0.00364182,0.002784907,0.15224443],"category_scores_gemma":[0.0046702647,0.0008402446,0.0015047687,0.0023550526,0.0007687755,0.0031933584,0.0042736325,0.0023810894,0.12996686],"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":[0.0006675584,0.00013989628,0.0018720315,0.00041956457,0.0001510245,0.0002127623,0.00011675491,0.009031534,0.0055665527,0.048641913,0.43158275,0.5015977],"study_design_scores_gemma":[0.0001416479,0.00008402436,0.0014196159,0.00012292028,0.00005341596,0.0005821077,0.00015882964,0.12063453,0.013365241,0.057000842,0.8063271,0.00010974174],"about_ca_topic_score_codex":0.0044383374,"about_ca_topic_score_gemma":0.007100411,"teacher_disagreement_score":0.84775555,"about_ca_system_score_codex":0.0012205051,"about_ca_system_score_gemma":0.0020321067,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W2081024207","doi":"10.1016/j.datak.2007.05.006","title":"A tree-projection-based algorithm for multi-label recurrent-item associative-classification rule generation","year":2007,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Association rule learning; Associative property; Computer science; Data mining; Apriori algorithm; Artificial intelligence; Classifier (UML); Pattern recognition (psychology); Machine learning; Projection (relational algebra); Algorithm; Mathematics","score_opus":0.15268889256032656,"score_gpt":0.35595682947668167,"score_spread":0.2032679369163551,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081024207","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003464374,0.00018940135,0.9913722,0.00011511199,0.00006046235,0.00023038441,0.00020942761,0.0037585795,0.000600033],"genre_scores_gemma":[0.029622817,0.00010245468,0.9674339,0.00012718096,0.00003891646,0.00037235022,0.00068611366,0.00013933118,0.0014769164],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983784,0.00034891415,0.00017026998,0.0004370304,0.0005524334,0.000112820126],"domain_scores_gemma":[0.9967759,0.0015805507,0.000104758896,0.00033345117,0.0010901885,0.000115063696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023487625,0.0013643703,0.0024497234,0.0027624392,0.0012894174,0.001711335,0.0033288288,0.0019954,0.009301401],"category_scores_gemma":[0.0062562414,0.000819456,0.0012310112,0.0036500876,0.0007325072,0.0019654506,0.0021385867,0.0028420545,0.0046919812],"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":[0.00015034695,0.0002081701,0.0005802533,0.000106909254,0.00009872235,0.00008923143,0.000078656696,0.014125084,0.0036020454,0.0033017774,0.00700027,0.9706585],"study_design_scores_gemma":[0.00010973221,0.00012458408,0.0005454697,0.000039356266,0.00008862577,0.00031061613,0.000058200523,0.97463834,0.007766826,0.012102611,0.004176777,0.00003882274],"about_ca_topic_score_codex":0.007556651,"about_ca_topic_score_gemma":0.012727309,"teacher_disagreement_score":0.009301401,"about_ca_system_score_codex":0.0007422748,"about_ca_system_score_gemma":0.0030993226,"threshold_uncertainty_score":0.031116247},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2081335906","doi":"10.1145/1620432.1620457","title":"Mining very long sequences in large databases with PLWAPLong","year":2009,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"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 Windsor","funders":"Natural Sciences and Engineering Research Council of Canada; University of Windsor","keywords":"Computer science; Suffix tree; Data mining; Tree (set theory); Event (particle physics); Set (abstract data type); Database; Node (physics); Trie; Algorithm; Theoretical computer science; Data structure; Mathematics; Programming language","score_opus":0.027820600833755225,"score_gpt":0.28128468282872343,"score_spread":0.2534640819949682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081335906","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12032191,0.0006464161,0.8598489,0.0004902526,0.000056844998,0.00039312628,0.00255737,0.014132232,0.0015530107],"genre_scores_gemma":[0.278281,0.0002726301,0.71324337,0.00017575832,0.000067802444,0.0004096327,0.0054921214,0.00024063488,0.0018170123],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837923,0.0002471853,0.00025139152,0.0003619638,0.0006518167,0.000108430286],"domain_scores_gemma":[0.99455416,0.0026868877,0.0007114026,0.0010631598,0.000804566,0.00017992273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014317884,0.00070254185,0.00080702774,0.004336982,0.0010192513,0.001720543,0.0015451926,0.0009300285,0.0017846684],"category_scores_gemma":[0.010729077,0.0006279519,0.00070025783,0.006051215,0.00055770355,0.0033719493,0.0014983182,0.000962471,0.0015283863],"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":[0.00084409927,0.00041596583,0.023349242,0.00041986268,0.00016277056,0.0014779856,0.00057345396,0.044178307,0.020034613,0.008215665,0.009904385,0.8904237],"study_design_scores_gemma":[0.00010269308,0.00029800707,0.0044223615,0.000055610337,0.000065267035,0.0013557279,0.00045164902,0.92339087,0.022839008,0.036802422,0.010167717,0.0000485911],"about_ca_topic_score_codex":0.002663897,"about_ca_topic_score_gemma":0.004399716,"teacher_disagreement_score":0.004336982,"about_ca_system_score_codex":0.0004318906,"about_ca_system_score_gemma":0.0016405899,"threshold_uncertainty_score":0.0075721145},"labels":[],"label_agreement":null},{"id":"W2081464336","doi":"10.1007/s00500-005-0018-6","title":"Mining fuzzy sequential patterns from quantitative transactions","year":2005,"lang":"en","type":"article","venue":"Soft Computing","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"New York Institute of Technology","funders":"National Science Council","keywords":"Computer science; Fuzzy logic; Data mining; Artificial intelligence","score_opus":0.03403399933309804,"score_gpt":0.2933859879958488,"score_spread":0.2593519886627508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081464336","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5534785,0.0009149375,0.4385867,0.00045423134,0.00012273062,0.00029140015,0.0019971374,0.00082188647,0.0033325406],"genre_scores_gemma":[0.8593988,0.0003648223,0.1369381,0.000038576058,0.00007397479,0.00014548626,0.0015611406,0.000031103158,0.0014480158],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99928683,0.000085929896,0.000086534754,0.00012738566,0.0003574299,0.00005604667],"domain_scores_gemma":[0.99697936,0.0013957,0.00050203287,0.00025852863,0.0007180229,0.0001464763],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006804622,0.0005824504,0.0006049809,0.0033833429,0.00033724672,0.0008479192,0.0006067846,0.0004157408,0.0018804094],"category_scores_gemma":[0.0056392183,0.0002406539,0.00056089944,0.003346959,0.0003822405,0.0014586666,0.00038376142,0.0005478034,0.00049652724],"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":[0.0021690917,0.0004624049,0.095795624,0.0012026692,0.0004645801,0.0027134118,0.00065866875,0.048236046,0.043052096,0.026015123,0.00491227,0.77431804],"study_design_scores_gemma":[0.00016115962,0.000780349,0.025300862,0.00015977515,0.00035354248,0.0025167763,0.00078403996,0.8339567,0.02448573,0.103682265,0.0077507826,0.000068028756],"about_ca_topic_score_codex":0.00084186305,"about_ca_topic_score_gemma":0.0014022432,"teacher_disagreement_score":0.0033833429,"about_ca_system_score_codex":0.00027588895,"about_ca_system_score_gemma":0.0005723703,"threshold_uncertainty_score":0.0062906146},"labels":[],"label_agreement":null},{"id":"W2081892160","doi":"10.3166/isi.19.3.93-105","title":"Big data analytics – Retour vers le futur 3. De statisticien à data scientist","year":2014,"lang":"fr","type":"preprint","venue":"Ingénierie des systèmes d information","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Statistician; Big data; Data science; Completeness (order theory); Variety (cybernetics); Computer science; Analytics; Data analysis; Order (exchange); Volume (thermodynamics); Data mining; Statistics; Mathematics; Business; Artificial intelligence; Physics","score_opus":0.09202070383690884,"score_gpt":0.29543726563077527,"score_spread":0.2034165617938664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081892160","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004407914,0.36153796,0.08349187,0.501253,0.024168607,0.000037994425,0.00043896446,0.00068596285,0.023977745],"genre_scores_gemma":[0.21845086,0.37481737,0.12062743,0.094819106,0.14965244,0.00028316164,0.00059386605,0.0023715065,0.038384274],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.977768,0.011854088,0.0011963176,0.0019765312,0.006632169,0.0005727571],"domain_scores_gemma":[0.96420604,0.025913944,0.001002743,0.0034376509,0.004290308,0.0011493191],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031434435,0.0015317388,0.0018827395,0.005201918,0.0024300087,0.015012582,0.0017708938,0.0064052413,0.003606784],"category_scores_gemma":[0.037040584,0.0008393128,0.001867893,0.004786896,0.024918979,0.028176893,0.005686017,0.01612914,0.0025068126],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000703499,0.000033036104,0.0006434063,0.0004676784,0.000051773477,0.00012676527,0.0013032313,0.0008345049,0.00044600232,0.8952202,0.037520315,0.0632827],"study_design_scores_gemma":[0.000022805092,0.000049750986,0.00050526595,0.00085666525,0.000017132821,0.00027299186,0.00061279826,0.002383015,0.0004306199,0.5806704,0.41410184,0.00007671356],"about_ca_topic_score_codex":0.0043617007,"about_ca_topic_score_gemma":0.0023854827,"teacher_disagreement_score":0.031434435,"about_ca_system_score_codex":0.0070135356,"about_ca_system_score_gemma":0.0053025107,"threshold_uncertainty_score":0.16624314},"labels":[],"label_agreement":null},{"id":"W2082914115","doi":"10.1007/s10462-007-9055-0","title":"Just enough learning (of association rules): the TAR2 “Treatment” learner","year":2006,"lang":"en","type":"article","venue":"Artificial Intelligence Review","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"University of British Columbia; West Virginia University; National Aeronautics and Space Administration","keywords":"Pruning; Computer science; Set (abstract data type); Association rule learning; Contrast (vision); Class (philosophy); Association (psychology); Simple (philosophy); Machine learning; Domain (mathematical analysis); Artificial intelligence; Controller (irrigation); Psychology; Mathematics; Programming language","score_opus":0.06132035250675822,"score_gpt":0.3248625355230162,"score_spread":0.263542183016258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082914115","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00676245,0.00946199,0.9652786,0.009360678,0.0007942133,0.00005764496,0.00028409692,0.00060401694,0.0073962314],"genre_scores_gemma":[0.33048782,0.014549775,0.6193068,0.0075817704,0.0045537087,0.00047522466,0.0018260638,0.0005995026,0.020619296],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946944,0.0028839859,0.00029053746,0.0007360134,0.001203513,0.000191484],"domain_scores_gemma":[0.98217976,0.012334244,0.00043963525,0.002745947,0.0019115654,0.00038881],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010418387,0.0009344465,0.0019546463,0.0021634405,0.00090968027,0.0026761338,0.004301832,0.0026638792,0.0052782684],"category_scores_gemma":[0.033098824,0.0005306739,0.0014687973,0.002756352,0.0025028668,0.009644149,0.0036579724,0.0071186777,0.0018267618],"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":[0.0004388533,0.00018453364,0.0023115736,0.00065615494,0.00023646685,0.00020586194,0.00028949848,0.021652194,0.0006503264,0.4362719,0.036339115,0.5007635],"study_design_scores_gemma":[0.00007753568,0.00015540898,0.00039560607,0.00015314558,0.00007845586,0.00045471964,0.00009161622,0.20090432,0.001379795,0.7720352,0.024238167,0.000035991237],"about_ca_topic_score_codex":0.0010155356,"about_ca_topic_score_gemma":0.0009976674,"teacher_disagreement_score":0.010418387,"about_ca_system_score_codex":0.00077579304,"about_ca_system_score_gemma":0.001903637,"threshold_uncertainty_score":0.055098355},"labels":[],"label_agreement":null},{"id":"W2083152120","doi":"10.1109/cibcb.2014.6845530","title":"Using associators to generate ensemble biclustering from multiple evolved biclusterings","year":2014,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Biclustering; Computer science; Cluster analysis; Block matrix; Data mining; Evolutionary algorithm; Hierarchical clustering; Algorithm; Data Matrix; Artificial intelligence; Pattern recognition (psychology); Canopy clustering algorithm; Correlation clustering","score_opus":0.0429895785078126,"score_gpt":0.26937461566451404,"score_spread":0.22638503715670144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083152120","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05173012,0.000102470425,0.9446937,0.00009503737,0.000053550117,0.00007854156,0.00009217929,0.0015942312,0.0015600866],"genre_scores_gemma":[0.32592216,0.00009823787,0.6702655,0.00013384873,0.000034151308,0.0004302081,0.00064418017,0.00049244263,0.001979265],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993119,0.00017770354,0.000059350856,0.00016552152,0.00022551256,0.000059989216],"domain_scores_gemma":[0.9972838,0.001188006,0.00018690333,0.00038072644,0.0008657591,0.00009486173],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024599675,0.00086839,0.00112303,0.0016383872,0.00077208044,0.0008619468,0.0011869469,0.0008610171,0.0020788496],"category_scores_gemma":[0.0070265518,0.00049643114,0.0010879833,0.0013415931,0.00047536285,0.00092065084,0.0015729481,0.0011350153,0.0006777227],"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":[0.00014384325,0.00013434338,0.005638876,0.00011716856,0.00017604993,0.00017149579,0.00033366153,0.70800215,0.016725857,0.009734862,0.0023731897,0.2564485],"study_design_scores_gemma":[0.000008975767,0.000034250585,0.00031175447,0.000008633763,0.000016293006,0.000035076726,0.00002234975,0.992466,0.0035641936,0.0027172097,0.0008051498,0.000010132335],"about_ca_topic_score_codex":0.0012419984,"about_ca_topic_score_gemma":0.0016504562,"teacher_disagreement_score":0.0024599675,"about_ca_system_score_codex":0.0005267067,"about_ca_system_score_gemma":0.00067654817,"threshold_uncertainty_score":0.013009727},"labels":[],"label_agreement":null},{"id":"W2083723332","doi":"10.1145/2331042.2351917","title":"The secret behind the Luhn-ie","year":2012,"lang":"en","type":"article","venue":"XRDS Crossroads The ACM Magazine for Students","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Algoma University","funders":"","keywords":"Computer science; Arithmetic; Algorithm; History; Mathematics","score_opus":0.027502909950692146,"score_gpt":0.3629187966781577,"score_spread":0.33541588672746553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083723332","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006300847,0.03563147,0.60176146,0.27142692,0.024820728,0.00015057561,0.000754017,0.0051566698,0.05399726],"genre_scores_gemma":[0.22135729,0.031121029,0.50367224,0.11263961,0.025669936,0.00059947436,0.0014050273,0.0049308664,0.098604485],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9853049,0.005181074,0.0006912682,0.0021185784,0.005733611,0.0009706615],"domain_scores_gemma":[0.95015407,0.021736488,0.0009242567,0.013819083,0.012090035,0.0012760776],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021694368,0.0013748537,0.0018038969,0.0022951367,0.0039062314,0.009126617,0.0029922952,0.0073058205,0.01029088],"category_scores_gemma":[0.08611944,0.0011959876,0.0010694187,0.0027330234,0.013120834,0.031923678,0.0067491345,0.0195495,0.013495629],"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":[0.00042943645,0.00010074322,0.0015083775,0.00025943381,0.00007576512,0.00012367661,0.00051957247,0.003069433,0.0016874878,0.42766377,0.23468548,0.32987678],"study_design_scores_gemma":[0.00006763,0.00016017357,0.00044219944,0.00062180916,0.000037235983,0.0004523618,0.00051540503,0.020793706,0.005180671,0.65384114,0.3177069,0.00018071421],"about_ca_topic_score_codex":0.0025907664,"about_ca_topic_score_gemma":0.00234554,"teacher_disagreement_score":0.021694368,"about_ca_system_score_codex":0.0019768444,"about_ca_system_score_gemma":0.0042652157,"threshold_uncertainty_score":0.114732146},"labels":[],"label_agreement":null},{"id":"W2083786854","doi":"10.1145/2492517.2500301","title":"Efficient mining of frequent itemsets in social network data based on MapReduce framework","year":2013,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Terabyte; Cloud computing; Overhead (engineering); Data mining; Big data; Resource (disambiguation); Programming paradigm; Data science; Computer network","score_opus":0.040163805697533896,"score_gpt":0.29503326160512283,"score_spread":0.2548694559075889,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083786854","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14738972,0.00079223176,0.84571004,0.00063498144,0.00008082813,0.00042333186,0.0010764676,0.0021087092,0.0017837015],"genre_scores_gemma":[0.49614528,0.0004489201,0.50012964,0.00008499542,0.00005359751,0.00024887073,0.0018012599,0.000059302653,0.0010282167],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99872094,0.00026709418,0.00012602302,0.00029004083,0.00043460427,0.00016120219],"domain_scores_gemma":[0.9989177,0.00042604507,0.00010603063,0.00016995595,0.0002858759,0.000094372255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016236479,0.0006174163,0.0012209638,0.0022541496,0.0014038099,0.0011661068,0.0018426813,0.0004970557,0.0004116583],"category_scores_gemma":[0.0025195458,0.00043705333,0.0016506033,0.002076471,0.00043482633,0.0016808442,0.0009123698,0.000581023,0.00021461786],"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":[0.0008580608,0.000916329,0.034422502,0.0007914082,0.0010075049,0.0021838418,0.0013279693,0.32927522,0.022860745,0.024447374,0.014480564,0.56742847],"study_design_scores_gemma":[0.000041600208,0.0001096424,0.0034376024,0.000015099048,0.000065959175,0.0006043274,0.00038665632,0.9661314,0.005230176,0.019954542,0.003990277,0.000032677046],"about_ca_topic_score_codex":0.008287192,"about_ca_topic_score_gemma":0.010069413,"teacher_disagreement_score":0.008287192,"about_ca_system_score_codex":0.00065133156,"about_ca_system_score_gemma":0.0019458085,"threshold_uncertainty_score":0.016477883},"labels":[],"label_agreement":null},{"id":"W2083930755","doi":"10.1109/cicare.2014.7007836","title":"New frequent pattern mining algorithm tested for activities models creation","year":2014,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Computer science; Process (computing); Data mining; Algorithm; Relation (database); Algorithm design; Temporal database; Data modeling; Simple (philosophy); Machine learning; Database","score_opus":0.025267312740044866,"score_gpt":0.2628804952110622,"score_spread":0.23761318247101734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083930755","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021381555,0.00058363035,0.97206974,0.00020693782,0.00019052428,0.00028607738,0.000938251,0.0029659157,0.0013773303],"genre_scores_gemma":[0.0792655,0.0003067049,0.91568106,0.000069692294,0.00006184437,0.00035066303,0.002230352,0.0001145548,0.001919745],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997701,0.0002630427,0.0003543021,0.0008038236,0.0007612939,0.000116553405],"domain_scores_gemma":[0.9976708,0.0006921747,0.00017181644,0.00029268969,0.001080727,0.00009168473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013639013,0.00092089956,0.0011035547,0.0026706578,0.000828946,0.001640119,0.0018203469,0.0011330384,0.0024675943],"category_scores_gemma":[0.0045994334,0.00038667078,0.0010712612,0.002510354,0.0002979099,0.0024661582,0.0007053441,0.001109176,0.0012400723],"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":[0.00072104717,0.00051260355,0.009331903,0.00071586965,0.00034098435,0.0007709885,0.00023323004,0.031882156,0.021638693,0.01005377,0.009332322,0.9144665],"study_design_scores_gemma":[0.0002532261,0.00039098007,0.0050697676,0.00010362964,0.00020939832,0.003363451,0.00016666645,0.9103691,0.03438458,0.012282289,0.03333095,0.00007584838],"about_ca_topic_score_codex":0.0016416393,"about_ca_topic_score_gemma":0.0015672267,"teacher_disagreement_score":0.0026706578,"about_ca_system_score_codex":0.0005211912,"about_ca_system_score_gemma":0.0015014425,"threshold_uncertainty_score":0.008254945},"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":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006247621,0.18005398,0.060323354,0.1023885,0.51295567,0.00071832875,0.013536625,0.0026188865,0.12115704],"genre_scores_gemma":[0.016912114,0.1131637,0.035564832,0.010437516,0.08561319,0.0002891276,0.021765323,0.0020308301,0.7142233],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969393,0.0003206395,0.00028296176,0.0004302604,0.0017963225,0.00023053099],"domain_scores_gemma":[0.98790866,0.0015744581,0.00042874867,0.0008911379,0.0065895338,0.0026073386],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005463561,0.0015226883,0.0028307026,0.00575458,0.0014046918,0.0075998395,0.0024317168,0.0019334494,0.14412726],"category_scores_gemma":[0.0099070305,0.0005193435,0.0016865693,0.0068457033,0.0005958132,0.0044774255,0.0026782446,0.002411497,0.07318584],"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":[0.00015429998,0.0000762238,0.0003740527,0.0005493392,0.00004620972,0.00008916727,0.000033882217,0.0003540347,0.00084486464,0.0012247798,0.7882355,0.20801756],"study_design_scores_gemma":[0.000036986516,0.000088307504,0.0012775618,0.00034031927,0.000077613724,0.00022864674,0.00007168417,0.0009828996,0.0014201752,0.003493043,0.9919492,0.00003357095],"about_ca_topic_score_codex":0.0023865143,"about_ca_topic_score_gemma":0.005526237,"teacher_disagreement_score":0.14412726,"about_ca_system_score_codex":0.0017976544,"about_ca_system_score_gemma":0.0038143871,"threshold_uncertainty_score":0.4821537},"labels":[],"label_agreement":null},{"id":"W2084228012","doi":"10.1109/bigdata.congress.2014.99","title":"Terms Mining in Document-Based NoSQL: Response to Unstructured Data","year":2014,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"NoSQL; Computer science; Relational database management system; Unstructured data; Database; Big data; Relational database; Cluster analysis; SQL; Analytics; Data science; Information retrieval; Data mining; Artificial intelligence","score_opus":0.0221982600746082,"score_gpt":0.29123149068350235,"score_spread":0.26903323060889417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084228012","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.075163305,0.00078679016,0.88315976,0.002052091,0.00024082922,0.0007091245,0.002857355,0.03128862,0.0037421554],"genre_scores_gemma":[0.49111402,0.00058773044,0.4949737,0.000673296,0.00018145586,0.0004512297,0.0066703367,0.0009136984,0.0044346265],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960504,0.00088642095,0.00050468533,0.0006059627,0.0016546118,0.00029798766],"domain_scores_gemma":[0.9947818,0.0016217704,0.0003335816,0.0015114927,0.0015273071,0.00022401678],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034176218,0.0005722157,0.0010033714,0.001639717,0.0011027482,0.002653886,0.0026659463,0.0009571572,0.0017058288],"category_scores_gemma":[0.013693393,0.00033653897,0.0006821273,0.0024888797,0.0005292123,0.0030362685,0.0028743192,0.0012711423,0.001189345],"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":[0.0027217814,0.0008727311,0.03237738,0.0011959375,0.0003573172,0.0013367404,0.0036853438,0.051692996,0.076692216,0.03728855,0.042529684,0.7492492],"study_design_scores_gemma":[0.000113066184,0.00014809257,0.004345333,0.000058061563,0.00008604444,0.0006350419,0.0012110114,0.8613609,0.052711792,0.050460495,0.028792014,0.00007811785],"about_ca_topic_score_codex":0.006404996,"about_ca_topic_score_gemma":0.005649058,"teacher_disagreement_score":0.006404996,"about_ca_system_score_codex":0.00090104656,"about_ca_system_score_gemma":0.0016936145,"threshold_uncertainty_score":0.018074334},"labels":[],"label_agreement":null},{"id":"W2085169145","doi":"10.1155/2014/973750","title":"Negative and Positive Association Rules Mining from Text Using Frequent and Infrequent Itemsets","year":2014,"lang":"en","type":"article","venue":"The Scientific World JOURNAL","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Association rule learning; Association (psychology); Computer science; Data mining; Data science; Medicine; Psychology","score_opus":0.01610229892552416,"score_gpt":0.24601185808130027,"score_spread":0.2299095591557761,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2085169145","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044525683,0.0020313363,0.94493324,0.0008271834,0.00029133508,0.00076335354,0.0020299759,0.0014689713,0.00312892],"genre_scores_gemma":[0.15397826,0.0012692922,0.83775824,0.00031660468,0.00030224954,0.00051526004,0.0041200677,0.00009045108,0.0016496042],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9923666,0.0015035848,0.001632578,0.0016153578,0.0026363567,0.00024558822],"domain_scores_gemma":[0.98233885,0.01188529,0.0017556201,0.0012194143,0.0024924814,0.00030839123],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055739093,0.001429855,0.0021265198,0.00807651,0.0012311038,0.0033334438,0.0023751527,0.0014449051,0.0017204719],"category_scores_gemma":[0.02532092,0.0006341255,0.0022163612,0.0056605334,0.0010736554,0.0038589141,0.0016794341,0.0017500586,0.0017260303],"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":[0.0004959514,0.000736319,0.037686825,0.0016854958,0.00059202174,0.0033194844,0.0008393683,0.026383413,0.011977486,0.020443462,0.010366452,0.8854737],"study_design_scores_gemma":[0.00018683691,0.00074742397,0.016501138,0.0010204604,0.0008370292,0.00977944,0.0016544588,0.69844043,0.028404081,0.19533442,0.046846684,0.00024756073],"about_ca_topic_score_codex":0.0008254758,"about_ca_topic_score_gemma":0.0013856324,"teacher_disagreement_score":0.00807651,"about_ca_system_score_codex":0.00038428712,"about_ca_system_score_gemma":0.0013019684,"threshold_uncertainty_score":0.029478014},"labels":[],"label_agreement":null},{"id":"W2085995514","doi":"10.1145/772862.772888","title":"WEBKDD 2002","year":2002,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Conjunction (astronomy); Theme (computing); Knowledge extraction; Data science; Web mining; Data mining; Information retrieval; World Wide Web; Web service","score_opus":0.061081370656482024,"score_gpt":0.2461904553370433,"score_spread":0.18510908468056128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2085995514","genre_codex":"dataset","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036374233,0.015810598,0.19205558,0.020928511,0.008032216,0.0011635148,0.55526674,0.16015731,0.042948153],"genre_scores_gemma":[0.012255161,0.00993473,0.12939861,0.0047014127,0.00074239913,0.0018134863,0.8075586,0.007987105,0.02560854],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99085134,0.0017070688,0.001269858,0.0011323718,0.0046865465,0.0003527501],"domain_scores_gemma":[0.9868537,0.0037577634,0.0005820954,0.003962881,0.00382758,0.0010159618],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009158089,0.0021146175,0.00431655,0.008350158,0.0023231315,0.010128183,0.0059408327,0.003657967,0.027852349],"category_scores_gemma":[0.03009435,0.00271893,0.003165991,0.0072922665,0.00076637784,0.0051030223,0.003918403,0.0053297905,0.055288155],"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":[0.000120318306,0.00007616068,0.00068863836,0.0007788946,0.00019587729,0.00009822108,0.000034490615,0.002502848,0.00017492742,0.004592247,0.9365782,0.05415916],"study_design_scores_gemma":[0.00024118823,0.000023608907,0.0007189346,0.00018461795,0.00008690448,0.00036715067,0.000029757573,0.014707522,0.0015955737,0.018609619,0.9633626,0.000072511764],"about_ca_topic_score_codex":0.011893584,"about_ca_topic_score_gemma":0.016142948,"teacher_disagreement_score":0.97214764,"about_ca_system_score_codex":0.0021550683,"about_ca_system_score_gemma":0.008490472,"threshold_uncertainty_score":0.09317541},"labels":[],"label_agreement":null},{"id":"W2086051422","doi":"10.1109/wi.2004.140","title":"TMS: Targeted Marketing System Based on Market Value Functions","year":2004,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Marketing research; Marketing management; Profit (economics); Database marketing; Information system; Marketing strategy; Presentation (obstetrics); Marketing; Knowledge management; Business; Relationship marketing; Engineering","score_opus":0.008323684985471876,"score_gpt":0.21190546239680616,"score_spread":0.2035817774113343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086051422","genre_codex":"software","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01669421,0.00058467477,0.40885067,0.00047122495,0.00019535763,0.0007596983,0.013991828,0.5350738,0.023378555],"genre_scores_gemma":[0.41883692,0.0017101993,0.42547566,0.0014801394,0.0006045837,0.0023707892,0.06056425,0.029766837,0.059190646],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99940646,0.00010788776,0.0000694689,0.0001233623,0.00022959626,0.00006322755],"domain_scores_gemma":[0.9987888,0.0004672544,0.00012438543,0.0001663815,0.00035996514,0.00009321175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012007145,0.0013183339,0.0009842883,0.003573688,0.00043164776,0.0023419543,0.0017071521,0.0012810889,0.05648608],"category_scores_gemma":[0.0047830106,0.00069911155,0.00078401604,0.0018604766,0.00026059235,0.0029655795,0.0011542125,0.0007983939,0.021498494],"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":[0.0031948406,0.0005856264,0.0061976146,0.0010784608,0.00027065768,0.00070218294,0.0004111192,0.019800004,0.02410898,0.025131298,0.4618168,0.45670238],"study_design_scores_gemma":[0.0011924359,0.0005012668,0.0061438144,0.00020313091,0.00033675838,0.0012580797,0.00010153035,0.6342862,0.045528077,0.040818173,0.2692988,0.00033176722],"about_ca_topic_score_codex":0.0019111981,"about_ca_topic_score_gemma":0.0011006953,"teacher_disagreement_score":0.05648608,"about_ca_system_score_codex":0.00079877867,"about_ca_system_score_gemma":0.0008611505,"threshold_uncertainty_score":0.18896478},"labels":[],"label_agreement":null},{"id":"W2086997861","doi":"10.1145/2076623.2076659","title":"A landmark-model based system for mining frequent patterns from uncertain data streams","year":2011,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Data stream mining; Landmark; Sliding window protocol; Computer science; STREAMS; Data mining; Streaming data; Process (computing); Window (computing); Data modeling; Real-time computing; Data stream; Artificial intelligence; Computer network; Database; Telecommunications","score_opus":0.13920775530637192,"score_gpt":0.2918751412455623,"score_spread":0.15266738593919038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086997861","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00842557,0.0001559694,0.9833803,0.00021317253,0.000062887,0.00007577234,0.00024530367,0.00688648,0.00055434724],"genre_scores_gemma":[0.2840206,0.00027148105,0.7119476,0.00019382735,0.000104573875,0.00036826226,0.0011784639,0.00020420535,0.0017110433],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989489,0.00021021326,0.00010392654,0.0003292492,0.00031656882,0.00009123818],"domain_scores_gemma":[0.99778533,0.0008428264,0.00026103097,0.000432618,0.00052914646,0.00014891902],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017249221,0.0006284985,0.0014807605,0.0014586924,0.0007705406,0.0018140847,0.0022961306,0.0013556567,0.002331393],"category_scores_gemma":[0.007354235,0.0004032264,0.000823099,0.0019275281,0.0006064594,0.0028917333,0.0018472861,0.0013002284,0.0015904208],"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":[0.0023393224,0.0004160772,0.012658492,0.00050789356,0.00042401464,0.0016853112,0.0009400163,0.18031651,0.036673483,0.04539347,0.02949755,0.6891479],"study_design_scores_gemma":[0.000090685455,0.00021654375,0.0006211234,0.000015575248,0.000074611184,0.00033951973,0.000058947433,0.97144914,0.0075922394,0.011071096,0.008409171,0.000061466446],"about_ca_topic_score_codex":0.0033228793,"about_ca_topic_score_gemma":0.0034787185,"teacher_disagreement_score":0.0033228793,"about_ca_system_score_codex":0.00065511104,"about_ca_system_score_gemma":0.0017720433,"threshold_uncertainty_score":0.009122431},"labels":[],"label_agreement":null},{"id":"W2087758886","doi":"10.2165/00822942-200504020-00002","title":"A Multiple-Pattern Biosequence Analysis Method for Diverse Source Association Mining","year":2005,"lang":"en","type":"article","venue":"Applied Bioinformatics","topic":"Data Mining Algorithms and Applications","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 Guelph","funders":"","keywords":"Computer science; Representation (politics); Sequence (biology); Matching (statistics); Task (project management); Data mining; Identification (biology); Computational biology; Association rule learning; Pattern recognition (psychology); Biology; Artificial intelligence; Mathematics; Genetics; Statistics","score_opus":0.018390743711956533,"score_gpt":0.2717366685490165,"score_spread":0.25334592483706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087758886","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0053371377,0.00013753034,0.98752856,0.00012559931,0.000051943094,0.00013943951,0.0006625486,0.0056417026,0.0003755117],"genre_scores_gemma":[0.030234493,0.000094366485,0.96660376,0.000071850794,0.000049377282,0.00020187059,0.0012389008,0.00028309016,0.0012223256],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982114,0.00030275807,0.00020321757,0.00045425058,0.00074986456,0.00007849746],"domain_scores_gemma":[0.9965503,0.0015434407,0.00020813967,0.00061622425,0.0009189835,0.00016284571],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025998938,0.0011572189,0.0013714104,0.005207747,0.0014276855,0.0017173176,0.0022400261,0.0012694111,0.0056075845],"category_scores_gemma":[0.008311266,0.00060173986,0.0016386213,0.0043434086,0.00045227684,0.0018010872,0.0018147411,0.0016892353,0.00327698],"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":[0.0004453105,0.00031869826,0.005848714,0.00027588347,0.0003509233,0.00041532368,0.0001526316,0.0052133743,0.020832041,0.0047369185,0.0107568875,0.9506534],"study_design_scores_gemma":[0.00043756008,0.00030598752,0.0057857228,0.00007614713,0.0005454447,0.0040377276,0.0002199515,0.8846519,0.040643908,0.03266156,0.030439435,0.00019464557],"about_ca_topic_score_codex":0.0018808945,"about_ca_topic_score_gemma":0.0039424677,"teacher_disagreement_score":0.0056075845,"about_ca_system_score_codex":0.00034189475,"about_ca_system_score_gemma":0.0014663348,"threshold_uncertainty_score":0.018759191},"labels":[],"label_agreement":null},{"id":"W2088163015","doi":"10.1145/347090.347163","title":"Efficient algorithms for constructing decision trees with constraints","year":2000,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada)","funders":"","keywords":"Computer science; Citation; Information technology; Algorithm; Data science; Library science","score_opus":0.01847771564887421,"score_gpt":0.2692755089854428,"score_spread":0.2507977933365686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2088163015","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063137813,0.00081457506,0.9834273,0.00050573825,0.000105234496,0.0004535551,0.0016552687,0.00328296,0.0034416774],"genre_scores_gemma":[0.045278408,0.00045439022,0.94755334,0.0001728819,0.00006834818,0.0005940308,0.0033571785,0.00025729448,0.0022641653],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99641573,0.0010792485,0.00032049068,0.00088149105,0.00097162486,0.00033143573],"domain_scores_gemma":[0.98963577,0.008282104,0.00035599933,0.0008435754,0.0006633775,0.00021913329],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00301774,0.0026317078,0.0029809377,0.0038955107,0.0016967463,0.0037496432,0.0039131227,0.0023271258,0.014168869],"category_scores_gemma":[0.01620139,0.0023199078,0.004238988,0.006052856,0.0013091206,0.0053705685,0.0034636392,0.0050854916,0.0035365818],"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":[0.00028946504,0.00034851776,0.0009797501,0.0009063688,0.0002098117,0.00019212684,0.00021099739,0.24889378,0.0011579932,0.05148732,0.024233976,0.67108995],"study_design_scores_gemma":[0.00015573222,0.00006547639,0.0002256962,0.000110851586,0.00010008744,0.00010124368,0.00013423088,0.823586,0.0011063899,0.16725479,0.0071346415,0.000024960917],"about_ca_topic_score_codex":0.0067506786,"about_ca_topic_score_gemma":0.011897593,"teacher_disagreement_score":0.014168869,"about_ca_system_score_codex":0.0025073956,"about_ca_system_score_gemma":0.0037904473,"threshold_uncertainty_score":0.04739958},"labels":[],"label_agreement":null},{"id":"W2090143015","doi":"10.1016/s0304-3975(02)00183-4","title":"A simple greedy algorithm for finding functional relations: efficient implementation and average case analysis","year":2003,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":14,"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":"Ministry of Education, Culture, Sports, Science and Technology; Alberta Innovates - Health Solutions","keywords":"Simple (philosophy); Greedy algorithm; Bounded function; Algorithm; Computer science; Domain (mathematical analysis); Mathematics; Function (biology); Relational database; Constant (computer programming); Theoretical computer science; Mathematical optimization; Data mining","score_opus":0.01779435933608195,"score_gpt":0.2961311114551869,"score_spread":0.2783367521191049,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090143015","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048567113,0.00008135678,0.99215055,0.00010334752,0.000025010433,0.00022732043,0.00015501093,0.0014080572,0.0009925342],"genre_scores_gemma":[0.034800176,0.00004860008,0.9634746,0.000048604987,0.000029103549,0.00024402521,0.00029707002,0.0001337,0.00092422735],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976786,0.00052092463,0.00020377887,0.00050053996,0.00082043896,0.0002758098],"domain_scores_gemma":[0.9959341,0.0023274838,0.00021444129,0.00071316527,0.0006670338,0.00014377848],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024225402,0.0018259248,0.0019806705,0.00383775,0.001549261,0.0019967915,0.0039355024,0.0018703707,0.011994504],"category_scores_gemma":[0.009039155,0.0010357532,0.0016841447,0.0042741396,0.0013133122,0.0029483107,0.0022353162,0.0016712786,0.004265532],"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":[0.0005469926,0.000726975,0.0028589754,0.00040968807,0.00016891788,0.00034063566,0.00024317448,0.07563968,0.013004443,0.04352626,0.015358821,0.8471754],"study_design_scores_gemma":[0.00022981901,0.00015705556,0.0008438459,0.000031652522,0.00011932033,0.0007437687,0.00012348128,0.90075976,0.0052586733,0.08721052,0.004470092,0.000051991552],"about_ca_topic_score_codex":0.0048357463,"about_ca_topic_score_gemma":0.009641367,"teacher_disagreement_score":0.011994504,"about_ca_system_score_codex":0.0010952752,"about_ca_system_score_gemma":0.003393747,"threshold_uncertainty_score":0.04012561},"labels":[],"label_agreement":null},{"id":"W2090882202","doi":"10.1016/j.procs.2013.05.016","title":"Supervised Discretization with GK − τ","year":2013,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Categorical variable; Discretization; Computer science; Discretization of continuous features; Maximization; Variable (mathematics); Probabilistic logic; Executable; Data mining; Machine learning; Loan; Artificial intelligence; Variables; Mathematical optimization; Mathematics; Discretization error","score_opus":0.007077395900725657,"score_gpt":0.20528238814462343,"score_spread":0.1982049922438978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090882202","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014057437,0.00009871667,0.9846283,0.00009989118,0.000030905027,0.0000343878,0.00008347119,0.00040385616,0.0005629488],"genre_scores_gemma":[0.33909523,0.00016347502,0.6572466,0.00018823183,0.00009406364,0.00022779017,0.00069156504,0.00020064211,0.0020923603],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885917,0.0004794251,0.00011407371,0.00025324558,0.00020653244,0.00008766293],"domain_scores_gemma":[0.99735045,0.0013633156,0.00025432018,0.00052629644,0.00041691185,0.00008860876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018940298,0.00050504046,0.0010509132,0.0005874128,0.00043465002,0.0010294719,0.0010958157,0.0009694217,0.001709705],"category_scores_gemma":[0.0056586363,0.00033170084,0.0008459364,0.0008049986,0.0007897622,0.0011908041,0.0010151477,0.0011573159,0.0005171825],"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":[0.00062090566,0.00015760383,0.0039553815,0.00034487294,0.00017246237,0.00019829815,0.00035164677,0.5726272,0.017155005,0.041947298,0.0048664,0.35760292],"study_design_scores_gemma":[0.000014139139,0.000048379814,0.00029429473,0.00001008889,0.000008542265,0.000040988798,0.000022621425,0.98326194,0.0027528424,0.012684081,0.00085335865,0.000008799442],"about_ca_topic_score_codex":0.0016392533,"about_ca_topic_score_gemma":0.0024016018,"teacher_disagreement_score":0.0018940298,"about_ca_system_score_codex":0.0006766349,"about_ca_system_score_gemma":0.0010126657,"threshold_uncertainty_score":0.01001668},"labels":[],"label_agreement":null},{"id":"W2090996319","doi":"10.1142/s0218001402002180","title":"USING MARKET VALUE FUNCTIONS FOR TARGETED MARKETING DATA MINING","year":2002,"lang":"en","type":"article","venue":"International Journal of Pattern Recognition and Artificial Intelligence","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Rank (graph theory); Computer science; Identification (biology); Value (mathematics); Data mining; Set (abstract data type); Function (biology); Object (grammar); Basis (linear algebra); Artificial intelligence; Machine learning; Mathematics","score_opus":0.2820522918434763,"score_gpt":0.35811021958621786,"score_spread":0.07605792774274156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090996319","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038862593,0.000874561,0.9567158,0.0004130866,0.000026112182,0.00021326792,0.00064269727,0.00075607235,0.0014956974],"genre_scores_gemma":[0.46994346,0.0009508607,0.5252387,0.00019233704,0.000095754505,0.0005636146,0.0019430523,0.000091418486,0.0009808524],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99628735,0.0021011806,0.00023146659,0.00042689664,0.0008030002,0.00015005474],"domain_scores_gemma":[0.98872364,0.0087216655,0.0008287924,0.0006921799,0.0008937446,0.000139983],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005672016,0.0014481974,0.0019396215,0.00698592,0.0006445002,0.0027182577,0.0014843874,0.0015471418,0.0011668362],"category_scores_gemma":[0.021945665,0.0005016214,0.0013666117,0.0064206817,0.00081795186,0.0039208974,0.0011404711,0.0013830542,0.0008878265],"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":[0.0003107112,0.00084324897,0.01581767,0.0005373229,0.0005039644,0.000377894,0.0002842038,0.43747833,0.0037498951,0.042399872,0.0055679996,0.4921289],"study_design_scores_gemma":[0.000017300647,0.00007262169,0.0010420863,0.000023491413,0.000027287833,0.00006674756,0.00004552344,0.9693755,0.001565105,0.026297478,0.001440889,0.00002612853],"about_ca_topic_score_codex":0.0023599581,"about_ca_topic_score_gemma":0.002016051,"teacher_disagreement_score":0.00698592,"about_ca_system_score_codex":0.0011934378,"about_ca_system_score_gemma":0.0010804016,"threshold_uncertainty_score":0.029996872},"labels":[],"label_agreement":null},{"id":"W2091083222","doi":"10.5539/cis.v3n2p86","title":"Research and Design of Hongqiao Airport Water Management Information System","year":2010,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Function (biology); Management system; Management information systems; Information system; Information management; Process management; Knowledge management; Business; Operations management","score_opus":0.03111830395205222,"score_gpt":0.2834335438756714,"score_spread":0.25231523992361915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091083222","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30562642,0.0021606532,0.62438893,0.0032261102,0.0002472503,0.002944817,0.0008791236,0.0022018608,0.058324765],"genre_scores_gemma":[0.78766644,0.0012300088,0.19888201,0.0002500538,0.00006267504,0.00085495436,0.0012545569,0.000048674792,0.009750783],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989177,0.00030307172,0.00010155562,0.0002016426,0.00033157377,0.0001445661],"domain_scores_gemma":[0.99940336,0.000090793066,0.000042629526,0.000056137727,0.00032400896,0.00008304431],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001257052,0.00028497484,0.00029471875,0.0011800892,0.00090120896,0.0023068355,0.0008616721,0.00040724222,0.0018689301],"category_scores_gemma":[0.0014367377,0.00033762035,0.00046783322,0.001216344,0.00041340615,0.0023318292,0.000588138,0.0003744503,0.00046661694],"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":[0.00070805213,0.00057395664,0.045349743,0.0019576065,0.00023278465,0.0019311183,0.0060271383,0.071972,0.10464478,0.19018082,0.023401277,0.5530208],"study_design_scores_gemma":[0.00029929963,0.0008847639,0.023017775,0.00034705625,0.00046282174,0.0009642144,0.0031622762,0.6872931,0.07286723,0.014900104,0.19565305,0.00014835819],"about_ca_topic_score_codex":0.018214067,"about_ca_topic_score_gemma":0.009449961,"teacher_disagreement_score":0.018214067,"about_ca_system_score_codex":0.001910277,"about_ca_system_score_gemma":0.004704544,"threshold_uncertainty_score":0.03621614},"labels":[],"label_agreement":null},{"id":"W2091140227","doi":"10.4018/jdwm.2010070102","title":"Exploring Disease Association from the NHANES Data","year":2010,"lang":"en","type":"article","venue":"International Journal of Data Warehousing and Mining","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Automatic summarization; Disease; Association rule learning; Data mining; Association (psychology); Data science; Artificial intelligence; Medicine; Pathology; Psychology","score_opus":0.21387985509449203,"score_gpt":0.33851251238262725,"score_spread":0.12463265728813522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091140227","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77439255,0.0031258252,0.10325328,0.0033294943,0.00009506314,0.00051637454,0.10549586,0.0010374376,0.008754094],"genre_scores_gemma":[0.8005784,0.0023525243,0.10457839,0.00043631333,0.00013570869,0.0004921577,0.08987291,0.000053485353,0.001500164],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987532,0.00041777804,0.0001581177,0.00022122578,0.00037926887,0.0000703118],"domain_scores_gemma":[0.99460727,0.003831688,0.0006669826,0.00033725012,0.00040306294,0.0001538921],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015580129,0.00034579987,0.00038445953,0.004525099,0.0003960814,0.00054319366,0.00032682036,0.00037297513,0.0019259957],"category_scores_gemma":[0.0077025536,0.0001343653,0.00091078866,0.005140696,0.00017682707,0.0005061887,0.00085353845,0.00062191096,0.00044361938],"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":[0.00070335396,0.00039011007,0.77219206,0.0008650387,0.00092087453,0.0020716053,0.0008577901,0.012602004,0.007932324,0.0043057045,0.009530779,0.18762843],"study_design_scores_gemma":[0.00014758957,0.0005608925,0.8426622,0.00020878058,0.0010459961,0.0029511412,0.0021468657,0.061737113,0.008290506,0.026644489,0.05350668,0.00009773027],"about_ca_topic_score_codex":0.010068462,"about_ca_topic_score_gemma":0.022867855,"teacher_disagreement_score":0.010068462,"about_ca_system_score_codex":0.00032899049,"about_ca_system_score_gemma":0.0009563964,"threshold_uncertainty_score":0.02001977},"labels":[],"label_agreement":null},{"id":"W2091633850","doi":"10.1145/1645953.1646161","title":"Mining frequent itemsets in time-varying data streams","year":2009,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Data stream mining; Computer science; Data mining; STREAMS; Task (project management); Execution time; Distributed computing; Engineering","score_opus":0.0407907442065405,"score_gpt":0.2950595553225094,"score_spread":0.2542688111159689,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091633850","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3108062,0.0012007965,0.6840077,0.00059249776,0.00014314099,0.00019857813,0.0009847281,0.0014642401,0.000602146],"genre_scores_gemma":[0.70458686,0.00048880104,0.292147,0.00015005516,0.0001157466,0.00013974665,0.0018546985,0.000066908986,0.00045021254],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954686,0.0009695721,0.00079442264,0.0009368079,0.001534009,0.0002966047],"domain_scores_gemma":[0.968096,0.020928998,0.0043295803,0.0021066065,0.0039206687,0.0006181085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005208654,0.0010359209,0.001959411,0.0050666933,0.0011134752,0.0022731447,0.0023039125,0.0016991097,0.00028531306],"category_scores_gemma":[0.029118218,0.0006719697,0.0009929574,0.004820467,0.0007212101,0.0033638314,0.00089521846,0.0011760455,0.00025369762],"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":[0.001897279,0.00084200484,0.15108512,0.00072094635,0.0009145334,0.004999179,0.0013058736,0.1751051,0.021144055,0.006521008,0.0049402774,0.63052464],"study_design_scores_gemma":[0.00005726935,0.00024677688,0.010208397,0.00007119473,0.00016539448,0.001932558,0.00053008896,0.9552511,0.013062892,0.016373463,0.0020477702,0.000053020474],"about_ca_topic_score_codex":0.0017075724,"about_ca_topic_score_gemma":0.0017547566,"teacher_disagreement_score":0.005208654,"about_ca_system_score_codex":0.00055840035,"about_ca_system_score_gemma":0.00072083704,"threshold_uncertainty_score":0.027546346},"labels":[],"label_agreement":null},{"id":"W2091837657","doi":"10.1007/s10618-010-0199-1","title":"Improving constrained pattern mining with first-fail-based heuristics","year":2010,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Data Mining Algorithms and Applications","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":"HEC Montréal; Polytechnique Montréal; École de Technologie Supérieure","funders":"","keywords":"Heuristics; Data mining; Computer science; Process (computing); Data stream mining; State (computer science); Sequential Pattern Mining; Machine learning; Artificial intelligence; Algorithm","score_opus":0.02107824697066401,"score_gpt":0.2557087373958644,"score_spread":0.2346304904252004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091837657","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04539374,0.0015678367,0.94533557,0.00067141,0.00022946502,0.0004083736,0.00054734567,0.0031888082,0.0026574722],"genre_scores_gemma":[0.29242668,0.0004775158,0.7002919,0.00091683335,0.00019478296,0.0003770455,0.001914073,0.00054534175,0.0028558227],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9944722,0.0019679104,0.00060905865,0.0009725585,0.0014676873,0.00051051384],"domain_scores_gemma":[0.96221054,0.027298525,0.0012787184,0.0051980377,0.0033332352,0.0006810351],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005993431,0.002234811,0.004463254,0.004747842,0.0016994155,0.0032963005,0.0046669166,0.002602617,0.0057356777],"category_scores_gemma":[0.037839267,0.0013233369,0.0027406563,0.0046231877,0.0015018893,0.005825853,0.0032710293,0.0034601667,0.0015358223],"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":[0.002134752,0.0013283639,0.014083554,0.000910112,0.0010377562,0.00083398615,0.0004028815,0.24189776,0.0051918724,0.022482838,0.01971238,0.6899837],"study_design_scores_gemma":[0.00019355025,0.0002473155,0.000850538,0.00005622533,0.00023034977,0.000311142,0.000091996044,0.96678424,0.00220951,0.026731811,0.002255814,0.000037427788],"about_ca_topic_score_codex":0.00839112,"about_ca_topic_score_gemma":0.014048917,"teacher_disagreement_score":0.00839112,"about_ca_system_score_codex":0.0010018918,"about_ca_system_score_gemma":0.0041619237,"threshold_uncertainty_score":0.031696618},"labels":[],"label_agreement":null},{"id":"W2092358235","doi":"10.1016/j.dam.2007.08.004","title":"A framework for incremental generation of closed itemsets","year":2007,"lang":"en","type":"article","venue":"Discrete Applied Mathematics","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":36,"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 en Outaouais; Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Association rule learning; Database transaction; Data mining; Computer science; Lattice (music); Implementation; Closed set; Limit (mathematics); Set (abstract data type); Mathematics; Theoretical computer science; Database; Discrete mathematics; Programming language","score_opus":0.052337768151854445,"score_gpt":0.31925921598017054,"score_spread":0.2669214478283161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2092358235","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002478718,0.00017465393,0.99420726,0.00013271709,0.000042293672,0.0001841398,0.00039987147,0.0018517672,0.0005286437],"genre_scores_gemma":[0.04406742,0.00018036888,0.95211583,0.000103043916,0.0000569624,0.00032426682,0.0020536056,0.0002097128,0.0008888025],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962243,0.00087866466,0.00039215002,0.0006611871,0.0016081707,0.0002355636],"domain_scores_gemma":[0.98556626,0.008901025,0.0004034775,0.0024351412,0.002399578,0.00029453944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004150406,0.00094729185,0.0017060839,0.0036629636,0.0011454026,0.002692923,0.005020171,0.0015354493,0.005477368],"category_scores_gemma":[0.026647225,0.0009812247,0.0024712991,0.004169076,0.0009784834,0.0044188756,0.003895953,0.0025134399,0.0019834416],"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":[0.00047973928,0.00036686228,0.0021189114,0.000655048,0.00024175362,0.00074838335,0.00050393416,0.101477526,0.005603537,0.0809308,0.021043653,0.78582984],"study_design_scores_gemma":[0.00010904606,0.00012104891,0.0003121166,0.00008931897,0.00011086399,0.00048568597,0.000109713226,0.84139806,0.005080581,0.140273,0.011864605,0.000046003785],"about_ca_topic_score_codex":0.0031436621,"about_ca_topic_score_gemma":0.0057230056,"teacher_disagreement_score":0.005477368,"about_ca_system_score_codex":0.0008637987,"about_ca_system_score_gemma":0.0022379286,"threshold_uncertainty_score":0.021949708},"labels":[],"label_agreement":null},{"id":"W2092463048","doi":"10.1016/j.im.2004.02.008","title":"The language of quarterly reports as an indicator of change in the company’s financial status","year":2004,"lang":"en","type":"article","venue":"Information & Management","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Order (exchange); Quarter (Canadian coin); Qualitative property; Business; Finance; Period (music); Accounting; Data science; Computer science; Geography","score_opus":0.014801510916158288,"score_gpt":0.27054627756432864,"score_spread":0.25574476664817036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2092463048","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9716181,0.001013824,0.002020663,0.0024138913,0.000589309,0.00006254992,0.009986941,0.00021514676,0.012079648],"genre_scores_gemma":[0.9905599,0.0004565069,0.002234447,0.0002405363,0.00037475032,0.000089941015,0.0040379236,0.000046412428,0.0019594994],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9935821,0.0022878028,0.001204544,0.0004136503,0.0022176334,0.00029425215],"domain_scores_gemma":[0.855012,0.06172612,0.05932497,0.0034737345,0.016753005,0.0037102583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055119344,0.00029661728,0.00033532744,0.008191791,0.000503763,0.004067676,0.000590595,0.00080482755,0.0028747672],"category_scores_gemma":[0.06835133,0.00014030261,0.00031985977,0.007609822,0.000846792,0.0021215666,0.0011863135,0.0011550664,0.0013671233],"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":[0.0010668231,0.00032992178,0.91509277,0.0003901724,0.00015473757,0.00037196424,0.004147102,0.0005644393,0.0057071513,0.0027249102,0.013572562,0.05587752],"study_design_scores_gemma":[0.0000534772,0.00095117686,0.95851064,0.00024183028,0.00017663246,0.0009605414,0.0062313206,0.0037827755,0.0048864526,0.001784013,0.022313157,0.000107918175],"about_ca_topic_score_codex":0.0014751422,"about_ca_topic_score_gemma":0.0014760633,"teacher_disagreement_score":0.008191791,"about_ca_system_score_codex":0.0006452045,"about_ca_system_score_gemma":0.0007912665,"threshold_uncertainty_score":0.029150248},"labels":[],"label_agreement":null},{"id":"W2093055460","doi":"10.1109/iri.2014.7051923","title":"Analyzing immediate correlations between names and pop culture of North America in the 21st century","year":2014,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Set (abstract data type); Computer science; Estimation; Rough set; Artificial intelligence; Data mining; Information retrieval; Engineering","score_opus":0.010579793683123454,"score_gpt":0.23914032651859937,"score_spread":0.22856053283547592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2093055460","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99790835,0.00014554511,0.00014602032,0.000056490964,0.0000072335115,0.000002210032,0.00025310492,0.0000025291356,0.0014785122],"genre_scores_gemma":[0.9989349,0.0001385621,0.00020582175,0.000013502438,0.0000068814575,0.000003381251,0.0002772856,0.0000026568107,0.00041686755],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99949384,0.00015681861,0.000048294936,0.00011034272,0.00013634724,0.000054476437],"domain_scores_gemma":[0.99244964,0.002932352,0.0027423964,0.00041039806,0.0009007227,0.00056453847],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008397451,0.00012023388,0.0001820919,0.0014946487,0.00045047828,0.0010895614,0.00024962277,0.00022025159,0.0016466194],"category_scores_gemma":[0.007246404,0.00009677825,0.0002090094,0.0032164138,0.00047513025,0.0006997091,0.0007828522,0.00048595233,0.00019627846],"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":[0.00002343528,0.00001047409,0.995249,0.000008609165,0.000027447548,0.00007085729,0.0008173946,0.00009198851,0.00018301097,0.000115570285,0.00006780394,0.003334574],"study_design_scores_gemma":[3.7595328e-7,0.000017103726,0.9974107,0.000003796986,0.000009847853,0.00006176359,0.0015791497,0.00017059004,0.00014411639,0.00004953217,0.00054909295,0.000003969811],"about_ca_topic_score_codex":0.021403097,"about_ca_topic_score_gemma":0.051660545,"teacher_disagreement_score":0.021403097,"about_ca_system_score_codex":0.00052550447,"about_ca_system_score_gemma":0.00033062426,"threshold_uncertainty_score":0.04255706},"labels":[],"label_agreement":null},{"id":"W2093214280","doi":"10.3166/isi.9.3-4.211-240","title":"Découverte de motifs fréquents dans les bases de données. Un cadre formel pour les méthodes","year":2004,"lang":"fr","type":"article","venue":"Ingénierie des systèmes d information","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Philosophy","score_opus":0.038838978412465516,"score_gpt":0.26126979557658375,"score_spread":0.22243081716411822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2093214280","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011272677,0.000540332,0.99728966,0.00018668352,0.000030083513,0.00008982974,0.00015992516,0.00036615663,0.0002100349],"genre_scores_gemma":[0.012651679,0.0005823274,0.98444504,0.00008049399,0.00006308533,0.00027251162,0.0005347237,0.00016729656,0.0012028319],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98864263,0.0038483771,0.0012428396,0.0023853655,0.0035814624,0.0002993296],"domain_scores_gemma":[0.9762397,0.017722357,0.0012430084,0.002518718,0.0019906408,0.00028554382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0095371045,0.0027472444,0.0027291363,0.0072785686,0.0012624243,0.0061194855,0.0029725528,0.0023696814,0.0055176355],"category_scores_gemma":[0.04746942,0.0023292934,0.00449892,0.0057938653,0.0026487391,0.0054165246,0.0032791921,0.0065184524,0.0043277526],"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":[0.0002002852,0.00016982267,0.0025950996,0.0017819647,0.0006888853,0.00037670947,0.0012403792,0.029891528,0.012363438,0.10437256,0.0048065605,0.84151274],"study_design_scores_gemma":[0.00013848195,0.00025650187,0.0024856308,0.0011627408,0.00034635534,0.0017460583,0.0009161871,0.526669,0.016115628,0.3846329,0.065370254,0.00016024268],"about_ca_topic_score_codex":0.0033547427,"about_ca_topic_score_gemma":0.005345337,"teacher_disagreement_score":0.0095371045,"about_ca_system_score_codex":0.0016613835,"about_ca_system_score_gemma":0.002294783,"threshold_uncertainty_score":0.05043763},"labels":[],"label_agreement":null},{"id":"W2093446553","doi":"10.1007/s10618-005-0022-6","title":"An Erratum on #x201C;Pushing Convertible Constraints in Frequent Itemset Mining#x201D;","year":2006,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","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":"University of British Columbia; Simon Fraser University","funders":"","keywords":"Prefix; Order (exchange); Combinatorics; Convertible; Function (biology); Mathematics; Physics; Philosophy; Linguistics; Biology; Business; Genetics","score_opus":0.03631538169184479,"score_gpt":0.29980017754183547,"score_spread":0.2634847958499907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2093446553","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00046527822,0.0020234282,0.008980656,0.16712935,0.80919164,0.00009499825,0.0016271045,0.00084518705,0.00964231],"genre_scores_gemma":[0.012728968,0.008806128,0.05266488,0.25600886,0.44776735,0.00049899414,0.0049591926,0.0019381713,0.21462737],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9915079,0.0012612502,0.0010690661,0.0008664301,0.0047802636,0.0005151304],"domain_scores_gemma":[0.9519758,0.017213985,0.0015558802,0.0032758904,0.024074009,0.001904448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049505266,0.0022400175,0.0022748369,0.0054654707,0.0071383845,0.0065911175,0.004811122,0.010287471,0.02493144],"category_scores_gemma":[0.061696175,0.0014873453,0.0017915735,0.0049467133,0.0033277012,0.0040147793,0.0024486564,0.013317502,0.016445769],"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":[0.000023111752,0.000011858239,0.000049484166,0.000053921343,0.000007245251,0.00008787886,0.000014748531,0.00006759068,0.00008394413,0.0013038567,0.9921515,0.006144894],"study_design_scores_gemma":[0.00004484392,0.000035745463,0.0006525701,0.00019990833,0.0000529155,0.00033243946,0.00008069881,0.0016606777,0.00080483884,0.0068121194,0.9892615,0.00006176333],"about_ca_topic_score_codex":0.04665974,"about_ca_topic_score_gemma":0.06422651,"teacher_disagreement_score":0.04665974,"about_ca_system_score_codex":0.00517638,"about_ca_system_score_gemma":0.006817111,"threshold_uncertainty_score":0.0927763},"labels":[],"label_agreement":null},{"id":"W2093485636","doi":"10.1145/1120687.1120691","title":"A framework for representing navigational patterns as full temporal objects","year":2004,"lang":"en","type":"article","venue":"ACM SIGecom Exchanges","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Profiling (computer programming); Personalization; Representation (politics); Temporal database; Cluster analysis; Data mining; Artificial intelligence; World Wide Web","score_opus":0.04643712198875068,"score_gpt":0.3320409715437025,"score_spread":0.2856038495549518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2093485636","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018716455,0.00017739845,0.99567634,0.00020835991,0.000028327828,0.00006404275,0.00044885167,0.0004947227,0.0010301932],"genre_scores_gemma":[0.04705608,0.00039664216,0.94983655,0.00010358451,0.00005151961,0.00032453745,0.0010698013,0.000084767176,0.0010764345],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99773884,0.0006167415,0.0004108276,0.0005934602,0.0005003234,0.00013976221],"domain_scores_gemma":[0.9962286,0.0015502832,0.0005983832,0.00085085054,0.00059593836,0.00017592568],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030786712,0.0011366025,0.0008743506,0.004159796,0.0011961204,0.004162149,0.0022798574,0.0015620333,0.0023579975],"category_scores_gemma":[0.009455103,0.00071831106,0.0029673227,0.0060822163,0.0016907462,0.008242126,0.0018819144,0.0022748099,0.001176761],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015262052,0.00015407916,0.0061943824,0.00046914804,0.0002290441,0.0004609281,0.002486995,0.057401393,0.005881714,0.6990104,0.008421211,0.2191382],"study_design_scores_gemma":[0.000039981933,0.00012965628,0.0019676036,0.000192329,0.0001554597,0.0008268114,0.0005424276,0.39926708,0.0021297205,0.52352124,0.07109775,0.00012994224],"about_ca_topic_score_codex":0.014179709,"about_ca_topic_score_gemma":0.012837731,"teacher_disagreement_score":0.014179709,"about_ca_system_score_codex":0.0014044063,"about_ca_system_score_gemma":0.0022244311,"threshold_uncertainty_score":0.028194368},"labels":[],"label_agreement":null},{"id":"W2093843477","doi":"10.1145/1150402.1150469","title":"Mining relational data through correlation-based multiple view validation","year":2006,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Relational database; Relation (database); Data mining; Joins; Key (lock); Process (computing)","score_opus":0.07068702858844765,"score_gpt":0.2889045827647962,"score_spread":0.21821755417634853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2093843477","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021244405,0.00015093766,0.9777648,0.000076310425,0.000008938562,0.000059190963,0.000074338874,0.0004403891,0.00018065787],"genre_scores_gemma":[0.35134095,0.00021249063,0.64699656,0.00008758855,0.000026366908,0.00016882233,0.0008975527,0.000079883794,0.0001898135],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98930955,0.0047001136,0.00076558796,0.0013298852,0.0035429155,0.00035193344],"domain_scores_gemma":[0.9710977,0.016128542,0.0035052085,0.0043432736,0.0045601106,0.00036516297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01133768,0.0010611502,0.0017989537,0.0039677448,0.0007369828,0.0033537704,0.0025963627,0.0013435296,0.0004146996],"category_scores_gemma":[0.036200844,0.00065376883,0.0016048171,0.0027424803,0.0010724942,0.0036039008,0.0023434456,0.0018687405,0.00029826854],"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":[0.000691563,0.0005195795,0.047451995,0.00034997947,0.00082444487,0.0006197951,0.0009536014,0.28014022,0.029926732,0.022736821,0.0029975611,0.6127877],"study_design_scores_gemma":[0.000020122256,0.000080099424,0.002101599,0.000033235407,0.000053386575,0.00017280466,0.000105386855,0.975977,0.012078803,0.008391926,0.00095683016,0.00002883777],"about_ca_topic_score_codex":0.0020876345,"about_ca_topic_score_gemma":0.0020050206,"teacher_disagreement_score":0.01133768,"about_ca_system_score_codex":0.00091241935,"about_ca_system_score_gemma":0.0017613759,"threshold_uncertainty_score":0.059960127},"labels":[],"label_agreement":null},{"id":"W2096281132","doi":"10.1145/1460797.1460799","title":"Mining frequent cross-graph quasi-cliques","year":2009,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":91,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Division of Information and Intelligent Systems","keywords":"Heuristics; Computer science; Clique; Data mining; Vertex (graph theory); Graph; Theoretical computer science; Combinatorics; Mathematics","score_opus":0.05441437221485232,"score_gpt":0.33723344906684105,"score_spread":0.2828190768519887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096281132","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44646245,0.0010824013,0.540214,0.002123375,0.000069744725,0.00041356977,0.0055886367,0.0008243404,0.00322147],"genre_scores_gemma":[0.76084507,0.00050477544,0.22623183,0.0003565323,0.00015229362,0.00029880836,0.009530523,0.00015131265,0.0019289217],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99693906,0.00079344714,0.00016901024,0.0012256051,0.0005564271,0.00031642008],"domain_scores_gemma":[0.98242927,0.01115739,0.002299686,0.0019144521,0.0015028333,0.0006963699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022631083,0.00079741504,0.0016308151,0.002742835,0.001765262,0.0019662038,0.0025695893,0.0015008379,0.0022961632],"category_scores_gemma":[0.013560224,0.0011167311,0.0018599418,0.003231357,0.001189523,0.005258562,0.0021433746,0.0014420863,0.00039546977],"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":[0.0013328213,0.0012165959,0.10233593,0.0019564366,0.001693472,0.0054636216,0.0021719935,0.47891745,0.020222723,0.18495709,0.028088203,0.1716437],"study_design_scores_gemma":[0.00007655209,0.00008587109,0.0063406895,0.000058563466,0.00009082631,0.0009850245,0.0005107828,0.8424877,0.0024945722,0.14205584,0.00477494,0.000038529608],"about_ca_topic_score_codex":0.0038569188,"about_ca_topic_score_gemma":0.0054404153,"teacher_disagreement_score":0.0038569188,"about_ca_system_score_codex":0.0009719478,"about_ca_system_score_gemma":0.0012210057,"threshold_uncertainty_score":0.011968613},"labels":[],"label_agreement":null},{"id":"W2096692332","doi":"10.1007/978-3-642-23199-5_11","title":"GENCCS: A Correlated Group Difference Approach to Contrast Set Mining","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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 Regina","funders":"","keywords":"Contrast (vision); Computer science; Set (abstract data type); Data mining; Group (periodic table); Property (philosophy); Task (project management); Artificial intelligence; Space (punctuation); Value (mathematics); Machine learning","score_opus":0.0331577624955423,"score_gpt":0.2398708847056504,"score_spread":0.2067131222101081,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096692332","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008056972,0.00020269224,0.9875767,0.000098992634,0.00009343109,0.00020358164,0.00048981904,0.0023943565,0.0008833797],"genre_scores_gemma":[0.073342405,0.00011715218,0.9219626,0.00015040128,0.00010956847,0.00038722082,0.0017472204,0.00041961632,0.0017639091],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99804235,0.00062670885,0.000108470434,0.00045833513,0.00063974404,0.0001244049],"domain_scores_gemma":[0.99702114,0.0014964339,0.00011791867,0.00067317754,0.00057121593,0.000120154305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026187566,0.0010814922,0.0019675414,0.002540473,0.0010309677,0.0016493929,0.0040313387,0.001193883,0.0060276203],"category_scores_gemma":[0.00746538,0.0005989076,0.0017088312,0.0028954602,0.00081289164,0.0013975365,0.0031190473,0.0021440163,0.0018723498],"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":[0.00087640557,0.00053963234,0.0039578285,0.0002798425,0.0004992573,0.00023945948,0.00028930337,0.042820927,0.014793295,0.026666243,0.019086866,0.8899508],"study_design_scores_gemma":[0.00013383258,0.00027131604,0.002379969,0.000031673277,0.00011556185,0.00023571872,0.00012318448,0.924838,0.008859265,0.05216856,0.010788374,0.000054522206],"about_ca_topic_score_codex":0.0033233943,"about_ca_topic_score_gemma":0.0064358637,"teacher_disagreement_score":0.0060276203,"about_ca_system_score_codex":0.00060581206,"about_ca_system_score_gemma":0.0016986026,"threshold_uncertainty_score":0.02016437},"labels":[],"label_agreement":null},{"id":"W2097718994","doi":"10.1109/ccece.2002.1013039","title":"Multilayer perceptron discrimination of software quality in a biomedical data analysis system","year":2003,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Institute for Biodiagnostics","funders":"Larner College of Medicine, University of Vermont","keywords":"Computer science; Extensibility; Software; CLARITY; Supervisor; Software engineering; Software quality; Visualization; Software visualization; Reusability; Software development; Software construction; Data mining; Operating system","score_opus":0.06898670555010881,"score_gpt":0.35219427381735585,"score_spread":0.283207568267247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097718994","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8314851,0.00018721726,0.16539279,0.00027475832,0.00003628033,0.00007861117,0.00015120365,0.0010491291,0.0013448755],"genre_scores_gemma":[0.97727406,0.000033074197,0.02212273,0.000040585386,0.000009055997,0.000024129826,0.0001623877,0.000036662732,0.00029728765],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9911891,0.003050209,0.0013175645,0.00090779085,0.002794468,0.0007407715],"domain_scores_gemma":[0.9659307,0.01989821,0.0036688594,0.0027818282,0.0065923436,0.0011280213],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019117221,0.0006692197,0.00079198263,0.0030077728,0.00046921778,0.0020821888,0.00069379184,0.0014303835,0.000702051],"category_scores_gemma":[0.06689456,0.00028719121,0.0007758215,0.0015848541,0.0009519155,0.001779345,0.001411348,0.0009395633,0.00037303896],"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":[0.006736284,0.00075256795,0.35308015,0.0003184348,0.0006750983,0.00067120825,0.0012187022,0.186432,0.05201045,0.0049860845,0.0029324386,0.39018655],"study_design_scores_gemma":[0.000042529926,0.00042856138,0.07176703,0.000030806532,0.00009427788,0.00020376591,0.00019232374,0.911462,0.012154088,0.0032678796,0.00029667505,0.000060145205],"about_ca_topic_score_codex":0.003695173,"about_ca_topic_score_gemma":0.0026627064,"teacher_disagreement_score":0.019117221,"about_ca_system_score_codex":0.0010987258,"about_ca_system_score_gemma":0.0007068565,"threshold_uncertainty_score":0.10110271},"labels":[],"label_agreement":null},{"id":"W2097807244","doi":"10.1142/s021962201240007x","title":"TOP-10 DATA MINING CASE STUDIES","year":2012,"lang":"en","type":"article","venue":"International Journal of Information Technology & Decision Making","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Simon Fraser University","funders":"National Science Foundation","keywords":"Snapshot (computer storage); Computer science; Knowledge extraction; Data science; Unstructured data; Data mining; Domain knowledge; Information extraction; Big data; Knowledge management; Artificial intelligence; Database","score_opus":0.05060423209022588,"score_gpt":0.38867010242500777,"score_spread":0.33806587033478186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097807244","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66800165,0.022908615,0.14172989,0.036469497,0.0019102477,0.0045044976,0.038572136,0.0021127725,0.083790705],"genre_scores_gemma":[0.6967524,0.009779167,0.23633653,0.0040155365,0.00038925966,0.0019113447,0.034962986,0.0002827849,0.015569867],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98910856,0.003561952,0.0010314578,0.000744798,0.0044667,0.0010865178],"domain_scores_gemma":[0.9771533,0.014436589,0.0009596796,0.0017702101,0.0045145475,0.0011656749],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009735806,0.0008142797,0.00082883664,0.004797591,0.0042510573,0.004097613,0.0030710953,0.0033479817,0.0049221837],"category_scores_gemma":[0.023131497,0.00043269066,0.001965332,0.013187249,0.0012211005,0.0023816535,0.0026768618,0.0022607967,0.001489843],"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":[0.001752859,0.003193028,0.17703101,0.0074176993,0.0007377849,0.036494333,0.005339119,0.037137467,0.006867841,0.061722636,0.25297582,0.40933037],"study_design_scores_gemma":[0.00059718656,0.0013455156,0.059436135,0.0021312898,0.0005557252,0.033610187,0.018055087,0.08173946,0.03190513,0.047522612,0.72280234,0.0002993744],"about_ca_topic_score_codex":0.00878968,"about_ca_topic_score_gemma":0.021928573,"teacher_disagreement_score":0.009735806,"about_ca_system_score_codex":0.0026777505,"about_ca_system_score_gemma":0.0030485857,"threshold_uncertainty_score":0.05148846},"labels":[],"label_agreement":null},{"id":"W2098162950","doi":"10.1023/b:dami.0000023675.04946.f1","title":"Building Association-Rule Based Sequential Classifiers for Web-Document Prediction","year":2004,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":60,"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; Association rule learning; Data mining; Web application; Predictive modelling; Web server; Association (psychology); Web mining; Machine learning; Web page; Information retrieval; World Wide Web; The Internet","score_opus":0.03959326074880023,"score_gpt":0.3087525581662589,"score_spread":0.2691592974174587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098162950","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11026667,0.0011919198,0.87741244,0.00044128048,0.00031954344,0.0005861175,0.0014947813,0.006149533,0.0021377904],"genre_scores_gemma":[0.29582405,0.0006145509,0.6944715,0.00020073283,0.0003006115,0.00052050996,0.003836523,0.00016947529,0.0040620575],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99781466,0.00033501277,0.00032347877,0.00058457087,0.0007595075,0.00018281728],"domain_scores_gemma":[0.9902829,0.005532743,0.0005306698,0.0007653629,0.0025494585,0.00033898136],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040832986,0.0011567165,0.0021999236,0.0047894316,0.0010792849,0.0019538705,0.0021364437,0.0019452549,0.0026173487],"category_scores_gemma":[0.011140641,0.00076865545,0.0014221822,0.0029262379,0.00044997683,0.0030622226,0.0009944532,0.0020316415,0.0028812303],"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":[0.00078092783,0.0009576234,0.026639368,0.00029823964,0.00032606535,0.00047702782,0.00013987705,0.047960147,0.011798053,0.0024552594,0.00864098,0.8995265],"study_design_scores_gemma":[0.00005050786,0.0002488537,0.0022747135,0.000034989145,0.0001723718,0.00030862578,0.000052954205,0.97819203,0.009758197,0.0061448663,0.0027331545,0.000028659755],"about_ca_topic_score_codex":0.006652573,"about_ca_topic_score_gemma":0.008279706,"teacher_disagreement_score":0.006652573,"about_ca_system_score_codex":0.0006365745,"about_ca_system_score_gemma":0.0022782278,"threshold_uncertainty_score":0.021594822},"labels":[],"label_agreement":null},{"id":"W2098309258","doi":"10.1109/ccece.2002.1013116","title":"A fast algorithm for mining association rules in medical image data","year":2003,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Association rule learning; Computer science; Data mining; Image (mathematics); Apriori algorithm; Association (psychology); Algorithm design; Algorithm; Artificial intelligence","score_opus":0.02915397153413349,"score_gpt":0.30848967765327256,"score_spread":0.27933570611913905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098309258","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027301318,0.0008130971,0.9930599,0.0002096425,0.00011670488,0.00023535476,0.00043713299,0.0020255635,0.00037240752],"genre_scores_gemma":[0.0120105175,0.00041915462,0.9854139,0.000116634495,0.00007161418,0.000396666,0.00093329535,0.00007933305,0.000558921],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99590766,0.0007567622,0.0006113084,0.0007269332,0.0018397382,0.00015767639],"domain_scores_gemma":[0.99229616,0.0048396424,0.00062799844,0.00072155654,0.0013754066,0.00013919002],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005393347,0.0015240308,0.0020046197,0.006679145,0.0013063798,0.002245017,0.0024014579,0.0022560959,0.0032013832],"category_scores_gemma":[0.019655503,0.0011589576,0.0017521707,0.006379767,0.00078669563,0.0030211348,0.0016060752,0.0023488465,0.0042985003],"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":[0.00032858382,0.00020969386,0.0027822754,0.0005412536,0.00033490325,0.00054757006,0.0001729055,0.0155506935,0.010354812,0.006595819,0.013094942,0.9494865],"study_design_scores_gemma":[0.0007127974,0.00078639947,0.0061347005,0.00044014218,0.0005697995,0.008182647,0.00024189067,0.7735437,0.04311089,0.07716269,0.08881195,0.00030234575],"about_ca_topic_score_codex":0.0015540377,"about_ca_topic_score_gemma":0.0020680607,"teacher_disagreement_score":0.006679145,"about_ca_system_score_codex":0.00044209685,"about_ca_system_score_gemma":0.0019488315,"threshold_uncertainty_score":0.028523028},"labels":[],"label_agreement":null},{"id":"W2099098003","doi":"10.1007/978-3-642-21590-2_1","title":"Subsumption of Vertical Viewpoint Patterns","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms 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":"McGill University; Centre for Interdisciplinary Research in Music Media and Technology","funders":"","keywords":"Computer science; Pattern matching; Representation (politics); Polyphony; Semantics (computer science); Matching (statistics); Artificial intelligence; Inference; Translation (biology); Relational database; Natural language processing; Relational calculus; Theoretical computer science; Programming language; Relational model; Data mining; Mathematics","score_opus":0.030069267441165063,"score_gpt":0.2556152944534851,"score_spread":0.22554602701232002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099098003","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26639232,0.0025665406,0.65749174,0.00068367954,0.00017600271,0.00021300677,0.0034205173,0.0016822115,0.06737398],"genre_scores_gemma":[0.72886664,0.0013718656,0.23746946,0.00021233417,0.00013495893,0.0001403332,0.009078377,0.00046832775,0.022257643],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982222,0.0002235166,0.00014388139,0.00035736282,0.00082509086,0.0002279692],"domain_scores_gemma":[0.99739635,0.00093031715,0.00025340656,0.0007109464,0.00058289454,0.00012616377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069300155,0.00053592125,0.00057780003,0.0029920791,0.000845481,0.0022360554,0.0009816716,0.0005592795,0.0054517793],"category_scores_gemma":[0.004588958,0.00059134525,0.000994351,0.0045841467,0.00076147163,0.0042223693,0.0016025191,0.0009824815,0.0010503363],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032336934,0.0001061754,0.0153897805,0.0003750966,0.00020910558,0.0015777879,0.0017387773,0.0053486554,0.01769348,0.4917606,0.00951661,0.4559606],"study_design_scores_gemma":[0.000046574307,0.00013572801,0.012701588,0.00026486613,0.0002798515,0.002883783,0.0016422253,0.06902544,0.02146764,0.8182986,0.07319201,0.00006184155],"about_ca_topic_score_codex":0.005810603,"about_ca_topic_score_gemma":0.0082901865,"teacher_disagreement_score":0.005810603,"about_ca_system_score_codex":0.0008761287,"about_ca_system_score_gemma":0.00067265664,"threshold_uncertainty_score":0.018238008},"labels":[],"label_agreement":null},{"id":"W2099349620","doi":"10.1145/1081870.1081929","title":"Learning to predict train wheel failures","year":2005,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":74,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Prognostics; Train; Computer science; Feature extraction; Data modeling; Feature (linguistics); Engineering; Machine learning; Artificial intelligence; Data mining; Database","score_opus":0.01103356435586418,"score_gpt":0.24798554144303017,"score_spread":0.236951977087166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099349620","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2365624,0.00058023527,0.75520474,0.0007795025,0.00010198029,0.0001332341,0.0019680653,0.002401661,0.0022681358],"genre_scores_gemma":[0.92831045,0.00025739588,0.06639047,0.000104502404,0.000056150322,0.0001603282,0.002812313,0.000048390804,0.0018600783],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99963236,0.00006609837,0.000028128346,0.00012616906,0.00009731095,0.000049893955],"domain_scores_gemma":[0.99845755,0.0008816348,0.00019460342,0.00014704518,0.00025794437,0.00006124946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007008657,0.00081874186,0.0007501499,0.0010556022,0.000312142,0.0007610165,0.0007659953,0.0008113119,0.001342101],"category_scores_gemma":[0.0046564797,0.00036064643,0.00054705207,0.00078279997,0.00025864973,0.0009831534,0.0006069017,0.0009881845,0.00075399276],"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":[0.0001783651,0.0003995951,0.024511619,0.00008389794,0.00013398353,0.00009471327,0.000064498054,0.73265785,0.002099518,0.001817516,0.0047945236,0.23316391],"study_design_scores_gemma":[0.000009255879,0.00004322098,0.0012971713,0.000005386055,0.000014381385,0.000017449502,0.000012193467,0.99386144,0.0010762535,0.0030035363,0.0006528184,0.0000069132857],"about_ca_topic_score_codex":0.006764697,"about_ca_topic_score_gemma":0.009026112,"teacher_disagreement_score":0.006764697,"about_ca_system_score_codex":0.00054081925,"about_ca_system_score_gemma":0.00078908657,"threshold_uncertainty_score":0.013450682},"labels":[],"label_agreement":null},{"id":"W2099367269","doi":"10.1023/b:mach.0000035516.74817.51","title":"Introduction: Lessons Learned from Data Mining Applications and Collaborative Problem Solving","year":2004,"lang":"en","type":"article","venue":"Machine Learning","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":45,"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; Ministrstvo za Izobraževanje, Znanost in Šport; Ministry of Education, Culture, Sports, Science and Technology","keywords":"Computer science; Data science; Data mining","score_opus":0.037539201725950364,"score_gpt":0.30025338922856964,"score_spread":0.26271418750261927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099367269","genre_codex":"methods","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0071565453,0.13472953,0.46913013,0.28882223,0.027628936,0.00014358762,0.001713332,0.0015426063,0.06913319],"genre_scores_gemma":[0.1483361,0.14330858,0.41399705,0.10784244,0.07923656,0.00047984865,0.003585101,0.0012651078,0.10194917],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981621,0.0005348391,0.000106248706,0.00044988218,0.0006647838,0.00008218316],"domain_scores_gemma":[0.9763435,0.016756715,0.00042684513,0.0017569497,0.0039326996,0.00078327034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004184429,0.0009593597,0.0008863921,0.001478706,0.0011757733,0.0047910046,0.002480938,0.0035764535,0.012356503],"category_scores_gemma":[0.02043543,0.0004934434,0.0006795161,0.0029662861,0.00284051,0.009217152,0.0020444405,0.006869127,0.0065719904],"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":[0.00011226775,0.0001626719,0.0011954756,0.0014711887,0.00006799441,0.00016480194,0.0006783473,0.0032973026,0.0008438506,0.18147726,0.46722308,0.34330577],"study_design_scores_gemma":[0.000030800227,0.00005913855,0.00097283284,0.00061767467,0.00003342817,0.00040971598,0.0003959568,0.007587659,0.001213519,0.46952632,0.5190845,0.00006845506],"about_ca_topic_score_codex":0.0024178848,"about_ca_topic_score_gemma":0.0020496128,"teacher_disagreement_score":0.012356503,"about_ca_system_score_codex":0.0015262135,"about_ca_system_score_gemma":0.0016239369,"threshold_uncertainty_score":0.041336596},"labels":[],"label_agreement":null},{"id":"W2099464320","doi":"10.1145/1107499.1107507","title":"An apples-to-apples comparison of two database journals","year":2005,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Database; Information retrieval; World Wide Web","score_opus":0.06868933506628278,"score_gpt":0.39365361095319384,"score_spread":0.32496427588691107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099464320","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67279464,0.027124783,0.058298137,0.009973531,0.013653671,0.0013081328,0.020843316,0.004853982,0.19114977],"genre_scores_gemma":[0.91211396,0.0036782941,0.055460297,0.0013255904,0.002686883,0.0005346321,0.010270983,0.0017379815,0.0121913785],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9529158,0.012804044,0.0061562154,0.001996337,0.024829546,0.0012980036],"domain_scores_gemma":[0.67890537,0.1307683,0.043596826,0.01604848,0.11973731,0.010943646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022460813,0.0006125753,0.0013539993,0.047731884,0.00185725,0.00978656,0.0008375396,0.0009793045,0.009220402],"category_scores_gemma":[0.220461,0.00027878265,0.0010703865,0.030052518,0.001700874,0.009164975,0.0043409416,0.0012074054,0.003016908],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003764472,0.00051130744,0.19375613,0.0026380967,0.0014792972,0.00046384474,0.005504593,0.0020598196,0.015010394,0.041554447,0.08337661,0.64988106],"study_design_scores_gemma":[0.0003371421,0.0043943673,0.53362155,0.0010764579,0.0012387297,0.0021668642,0.01564019,0.010493718,0.015741026,0.035976898,0.37875256,0.0005604422],"about_ca_topic_score_codex":0.0014830522,"about_ca_topic_score_gemma":0.0034039288,"teacher_disagreement_score":0.047731884,"about_ca_system_score_codex":0.0027615854,"about_ca_system_score_gemma":0.0016659446,"threshold_uncertainty_score":0.11878556},"labels":[],"label_agreement":null},{"id":"W2100111509","doi":"10.5430/air.v2n3p70","title":"A new web based data mining exploration and reporting tool for decision makers","year":2013,"lang":"en","type":"article","venue":"Artificial Intelligence Research","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Web mining; Computer science; Association rule learning; Data science; Decision tree; Data mining; Cluster analysis; Scalability; Decision support system; Data stream mining; World Wide Web; Database; Machine learning; Web service","score_opus":0.5174205066787242,"score_gpt":0.48821820317275366,"score_spread":0.029202303505970528,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100111509","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005141798,0.0002825502,0.87406445,0.0008145905,0.0001133125,0.00043058,0.0026502842,0.11174786,0.0047546756],"genre_scores_gemma":[0.039074894,0.0004292839,0.9442203,0.000683711,0.00012817192,0.00059418834,0.0053685415,0.0025895366,0.0069113006],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9951245,0.0010827607,0.0005764341,0.0005401171,0.002538638,0.00013759891],"domain_scores_gemma":[0.98393595,0.009286334,0.0011092843,0.0025431807,0.0024508617,0.0006744455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0074752234,0.0012449903,0.0013729052,0.004564287,0.0006503558,0.0035242992,0.0023762702,0.0016137088,0.010687938],"category_scores_gemma":[0.01650751,0.0009432458,0.00091050833,0.0032251517,0.0004732966,0.0052415556,0.002786225,0.0024289826,0.00550103],"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":[0.0008468624,0.00076534937,0.004953198,0.0009561978,0.00025249523,0.0013045454,0.00079275813,0.008023838,0.025408939,0.014184503,0.08766546,0.8548458],"study_design_scores_gemma":[0.0005415216,0.0006844329,0.006916498,0.0008469498,0.00028549726,0.00385623,0.00048155087,0.3726356,0.06644395,0.046713214,0.49999726,0.00059731986],"about_ca_topic_score_codex":0.0006588302,"about_ca_topic_score_gemma":0.00086310814,"teacher_disagreement_score":0.010687938,"about_ca_system_score_codex":0.00046236443,"about_ca_system_score_gemma":0.0018214372,"threshold_uncertainty_score":0.039533257},"labels":[],"label_agreement":null},{"id":"W2100499323","doi":"10.1007/978-3-642-03730-6_11","title":"TidFP: Mining Frequent Patterns in Different Databases with Transaction ID","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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 Windsor","funders":"","keywords":"Computer science; Database transaction; Identifier; Database; Data mining; Bitmap; Online analytical processing; Online transaction processing; Apriori algorithm; Transaction processing; Association rule learning; Set (abstract data type); Transaction data; Information retrieval; Data warehouse; Artificial intelligence","score_opus":0.023951022885895765,"score_gpt":0.2522751124825563,"score_spread":0.22832408959666053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100499323","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04594909,0.002207649,0.8985549,0.00049690844,0.00035878492,0.0005166995,0.015407575,0.03353709,0.0029711667],"genre_scores_gemma":[0.088388175,0.0007574588,0.8859338,0.00015649467,0.000105667146,0.000402253,0.02050093,0.0007618915,0.0029932873],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989274,0.00009301511,0.00016136748,0.00030179063,0.00044483118,0.000071512906],"domain_scores_gemma":[0.9986014,0.0006404431,0.00010049927,0.00031949813,0.00026200817,0.00007622619],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011375254,0.0012152421,0.0015192522,0.004479315,0.0007705729,0.0023053368,0.0024841619,0.0010148701,0.0050889235],"category_scores_gemma":[0.0049880366,0.00089639897,0.001335273,0.0062351017,0.00042147667,0.0036591091,0.0016684644,0.0009562447,0.0034214014],"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":[0.0006988779,0.0002006417,0.007982616,0.0011350294,0.00027188432,0.0007220081,0.00025858558,0.0072893403,0.011342741,0.0063735326,0.04330806,0.9204166],"study_design_scores_gemma":[0.000514028,0.00090129935,0.012930934,0.00041762847,0.0007050994,0.007204947,0.00081208814,0.7263708,0.0514005,0.090090044,0.1084499,0.00020276828],"about_ca_topic_score_codex":0.0015344329,"about_ca_topic_score_gemma":0.0015802362,"teacher_disagreement_score":0.0050889235,"about_ca_system_score_codex":0.00040646904,"about_ca_system_score_gemma":0.00083813514,"threshold_uncertainty_score":0.01702416},"labels":[],"label_agreement":null},{"id":"W2101249915","doi":"10.1109/tsmcb.2006.876163","title":"Customized Generalization of Support Patterns for Classification","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Generalization; Computer science; Artificial intelligence; Pattern recognition (psychology); Mathematics","score_opus":0.024899944962103012,"score_gpt":0.25060230510369846,"score_spread":0.22570236014159545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101249915","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025364406,0.00026924015,0.97085315,0.0003134711,0.000037526075,0.000113530084,0.0003574514,0.0017131508,0.000978022],"genre_scores_gemma":[0.42202657,0.00029011088,0.5721723,0.0004866215,0.00019057024,0.00057033973,0.0020974276,0.0002191238,0.0019469536],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99709785,0.00073161616,0.00019539752,0.0007686329,0.0010257066,0.00018079022],"domain_scores_gemma":[0.9904677,0.004797586,0.00077382417,0.0019880417,0.0017027543,0.00027005858],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038236282,0.0011537127,0.0017634606,0.0031441613,0.00058118196,0.0013458194,0.0032297494,0.0016058153,0.0027621936],"category_scores_gemma":[0.016068144,0.00061364117,0.0014261778,0.0028957906,0.0009006728,0.0036558234,0.002435933,0.0028359648,0.0016972271],"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":[0.00035127424,0.000509039,0.014594305,0.0002812757,0.00024794883,0.00039073298,0.00025043343,0.10367685,0.006227886,0.012407147,0.010102372,0.8509607],"study_design_scores_gemma":[0.000041824303,0.00012703073,0.0008260519,0.000025392628,0.000026213022,0.00024024353,0.00003738274,0.96420527,0.0028930444,0.029220935,0.002335221,0.00002140169],"about_ca_topic_score_codex":0.00080890564,"about_ca_topic_score_gemma":0.0009243403,"teacher_disagreement_score":0.0038236282,"about_ca_system_score_codex":0.00044535656,"about_ca_system_score_gemma":0.00112656,"threshold_uncertainty_score":0.020221472},"labels":[],"label_agreement":null},{"id":"W2102297485","doi":"10.1145/1132960.1132963","title":"Interestingness measures for data mining","year":2006,"lang":"en","type":"review","venue":"ACM Computing Surveys","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1125,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Ranking (information retrieval); Data mining; Process (computing); Data science; Measure (data warehouse); Information retrieval","score_opus":0.295248331531593,"score_gpt":0.4196157088055408,"score_spread":0.12436737727394775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102297485","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004497429,0.25944796,0.6963258,0.005523076,0.0017674222,0.00080347137,0.0024408377,0.0011885482,0.02800545],"genre_scores_gemma":[0.10692071,0.19015692,0.6730881,0.003736886,0.009052588,0.0035514294,0.005359794,0.00052431365,0.007609311],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9837714,0.004522714,0.0019651232,0.0022362084,0.007219137,0.00028535567],"domain_scores_gemma":[0.9643875,0.027608147,0.00219629,0.0024377229,0.0030025481,0.00036783583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0118294805,0.0021021613,0.0032009403,0.015716266,0.0011832437,0.005336717,0.0031402837,0.0023923465,0.004353996],"category_scores_gemma":[0.041789677,0.00070012774,0.0022525662,0.017662141,0.0039162706,0.012443799,0.0023845525,0.004199994,0.0029827864],"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":[0.00009031595,0.000114339935,0.0031976972,0.005828315,0.0003505194,0.0002774609,0.0004287259,0.009012241,0.0013982627,0.45411554,0.03452443,0.49066213],"study_design_scores_gemma":[0.000046587294,0.00014286906,0.0027163466,0.0017869007,0.0001605591,0.0015027417,0.00027829318,0.023243176,0.001417747,0.761216,0.20737004,0.00011884599],"about_ca_topic_score_codex":0.0007485713,"about_ca_topic_score_gemma":0.00046394762,"teacher_disagreement_score":0.015716266,"about_ca_system_score_codex":0.0023549674,"about_ca_system_score_gemma":0.0018493368,"threshold_uncertainty_score":0.062561035},"labels":[],"label_agreement":null},{"id":"W2102423866","doi":"10.1145/775047.775144","title":"Item selection by \"hub-authority\" profit ranking","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Analogy; Ranking (information retrieval); Profit (economics); Computer science; Selection (genetic algorithm); Operations research; Microeconomics; Information retrieval; Machine learning; Economics; Mathematics","score_opus":0.021689267872572388,"score_gpt":0.23895414273861112,"score_spread":0.21726487486603874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102423866","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09970934,0.0015777218,0.8890104,0.0007353119,0.00013981026,0.00060743786,0.00046144603,0.0013476727,0.006410899],"genre_scores_gemma":[0.7034537,0.0007081532,0.28679532,0.00025367053,0.0003765149,0.00044453677,0.0011044878,0.00018388672,0.0066797407],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9948201,0.0023724989,0.00027185233,0.0006715601,0.0014913116,0.00037266457],"domain_scores_gemma":[0.99032587,0.0055556027,0.0007547042,0.0015740737,0.0013694839,0.00042023306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041195275,0.0015381596,0.0035875924,0.004854592,0.0012720381,0.0021385665,0.002224081,0.0017013047,0.0041571856],"category_scores_gemma":[0.016136391,0.00068939704,0.0012938066,0.005552565,0.0010602747,0.003151273,0.0012811482,0.0011834444,0.0014822198],"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":[0.0009555484,0.0007265773,0.012243711,0.00062542007,0.000677501,0.000583153,0.0002761158,0.29347456,0.0056507355,0.04861015,0.019037275,0.6171392],"study_design_scores_gemma":[0.00017076584,0.00033176955,0.0024077757,0.000032140528,0.00016740545,0.00039332273,0.000098041535,0.9310679,0.0031101946,0.057742327,0.0044078506,0.00007055359],"about_ca_topic_score_codex":0.0020465225,"about_ca_topic_score_gemma":0.0034418867,"teacher_disagreement_score":0.004854592,"about_ca_system_score_codex":0.0009566097,"about_ca_system_score_gemma":0.0015780329,"threshold_uncertainty_score":0.021786392},"labels":[],"label_agreement":null},{"id":"W2102589938","doi":"10.1109/icdm.2001.989600","title":"Fast parallel association rule mining without candidacy generation","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":154,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Association rule learning; Computer science; Candidacy; Data mining; Process (computing); Parallel algorithm; Tree (set theory); Parallel computing; Mathematics; Operating system","score_opus":0.03154291050930846,"score_gpt":0.246651509559753,"score_spread":0.21510859905044455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102589938","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021053322,0.00051891047,0.9699533,0.00029845504,0.0001260565,0.00022467333,0.00022888886,0.005691119,0.0019053465],"genre_scores_gemma":[0.13361236,0.00030813206,0.8597295,0.0002177144,0.00013246339,0.0005022484,0.0011991787,0.00043853326,0.0038598347],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99749327,0.0005080865,0.00021694427,0.000564003,0.0010368621,0.00018088052],"domain_scores_gemma":[0.9944931,0.0027884275,0.00027375837,0.001439094,0.00085117255,0.0001543898],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023775457,0.0011568519,0.0017534748,0.0017490793,0.0012063794,0.001764253,0.002564358,0.0008078903,0.0045594885],"category_scores_gemma":[0.0095999,0.0007774171,0.0009108959,0.002751606,0.0006931872,0.002817019,0.0017912902,0.0013320367,0.003170575],"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":[0.0007280348,0.00022136129,0.0033466136,0.00020725219,0.00013218944,0.00027393762,0.00015637519,0.04783426,0.011119128,0.006962092,0.0070882584,0.92193043],"study_design_scores_gemma":[0.0004152693,0.0002576605,0.001355015,0.000028558372,0.00013623059,0.0010876809,0.00010561052,0.92000496,0.023885366,0.036343638,0.016328577,0.000051552495],"about_ca_topic_score_codex":0.002785875,"about_ca_topic_score_gemma":0.004483517,"teacher_disagreement_score":0.0045594885,"about_ca_system_score_codex":0.00052453333,"about_ca_system_score_gemma":0.0018758775,"threshold_uncertainty_score":0.015253007},"labels":[],"label_agreement":null},{"id":"W2102676521","doi":"10.1142/s0219265908002266","title":"CHRONOLOGICAL TREE — A COMPRESSED STRUCTURE FOR MINING BEHAVIORAL PATTERNS FROM WIRELESS SENSOR NETWORKS","year":2008,"lang":"en","type":"article","venue":"Journal of Interconnection Networks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Wireless sensor network; Behavioral pattern; Tree (set theory); Set (abstract data type); Wireless; Quality of service; Data mining; Representation (politics); Variety (cybernetics); Distributed computing; Machine learning; Computer network; Artificial intelligence; Telecommunications","score_opus":0.032687725082573414,"score_gpt":0.268443296980625,"score_spread":0.2357555718980516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102676521","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058384232,0.00073410914,0.9315714,0.0005927323,0.0000799576,0.0003453462,0.0052438905,0.0015529564,0.0014952777],"genre_scores_gemma":[0.2231961,0.00085735705,0.7613223,0.00019287434,0.00008452244,0.0006564622,0.012284792,0.00011852685,0.0012870121],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988557,0.00021170409,0.0001614381,0.00024990173,0.00042093272,0.00010029237],"domain_scores_gemma":[0.99648273,0.0013930871,0.0005333499,0.00066332996,0.0007607234,0.00016671016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009957246,0.0005403159,0.0007224875,0.0038476505,0.0008759879,0.0010596829,0.0014841041,0.0007017978,0.0012042113],"category_scores_gemma":[0.007859119,0.00031570016,0.0009609863,0.005186381,0.0005685989,0.002371526,0.0009606283,0.0009027756,0.00043934616],"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":[0.0007907821,0.0005288821,0.025484126,0.0010336691,0.0002179056,0.0009909421,0.0015026127,0.104361095,0.019213878,0.048417687,0.0153317,0.7821267],"study_design_scores_gemma":[0.00007439723,0.00033412967,0.0059797587,0.00016871469,0.0000988525,0.0011385283,0.00059871277,0.8875562,0.010040351,0.06872498,0.025205694,0.00007962923],"about_ca_topic_score_codex":0.005371256,"about_ca_topic_score_gemma":0.00868528,"teacher_disagreement_score":0.005371256,"about_ca_system_score_codex":0.00070473365,"about_ca_system_score_gemma":0.0018547218,"threshold_uncertainty_score":0.01067996},"labels":[],"label_agreement":null},{"id":"W2103304233","doi":"10.1142/s0219649210002498","title":"Comparison of Matrix Dimensionality Reduction Methods in Uncovering Latent Structures in the Data","year":2010,"lang":"en","type":"article","venue":"Journal of Information & Knowledge Management","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Singular value decomposition; Dimensionality reduction; Computer science; Curse of dimensionality; Matrix (chemical analysis); Decomposition; Reduction (mathematics); Matrix decomposition; Data mining; Pattern recognition (psychology); Artificial intelligence; Mathematics; Eigenvalues and eigenvectors; Physics","score_opus":0.05824730027405066,"score_gpt":0.4241836645208491,"score_spread":0.36593636424679843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103304233","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35326925,0.07259138,0.5529057,0.0025038018,0.0008419535,0.00090707204,0.001495094,0.001449486,0.014036286],"genre_scores_gemma":[0.40744546,0.022068907,0.5643558,0.00019650647,0.0003023186,0.0006465044,0.0021708366,0.00027005677,0.00254369],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9913742,0.0036911515,0.00086518796,0.00062470546,0.0032573943,0.00018734517],"domain_scores_gemma":[0.97732645,0.016665015,0.00085203233,0.0015280738,0.0033412923,0.0002871738],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012152543,0.0013555423,0.0011676847,0.006312414,0.0006188411,0.0021229773,0.00077761005,0.0011823169,0.0012477731],"category_scores_gemma":[0.02666467,0.0003118722,0.0014300864,0.0058498,0.00061254326,0.0029060096,0.0015218699,0.0010045484,0.00057386846],"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":[0.0019317013,0.00063292065,0.011202766,0.0026677328,0.0016041927,0.000091114365,0.0006609122,0.040128194,0.0060210144,0.010612018,0.0042198957,0.9202275],"study_design_scores_gemma":[0.0011314631,0.0053741136,0.06954958,0.0009472368,0.0015663668,0.0012157856,0.00194322,0.82449657,0.024767378,0.04149078,0.02703334,0.0004842513],"about_ca_topic_score_codex":0.0017243056,"about_ca_topic_score_gemma":0.0024145953,"teacher_disagreement_score":0.012152543,"about_ca_system_score_codex":0.0007128427,"about_ca_system_score_gemma":0.0009758473,"threshold_uncertainty_score":0.06426954},"labels":[],"label_agreement":null},{"id":"W2103600656","doi":"10.1109/icsmc.1995.537924","title":"Discovery of high order patterns","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Set (abstract data type); Event (particle physics); Data mining; Class (philosophy); Artificial intelligence; Task (project management); Data set; Machine learning; Engineering","score_opus":0.018547926681089327,"score_gpt":0.2266577472956555,"score_spread":0.20810982061456618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103600656","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16781622,0.0009908965,0.8232088,0.0008341903,0.00008141527,0.00033793517,0.0018175163,0.0010677151,0.0038452467],"genre_scores_gemma":[0.5724897,0.0005570506,0.42150605,0.00022040741,0.0000858822,0.00030632858,0.0027896857,0.00011365938,0.001931258],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961402,0.0006332403,0.00041660017,0.0009650331,0.001600419,0.0002446335],"domain_scores_gemma":[0.98070794,0.010758382,0.0026605255,0.0031855137,0.002308918,0.0003786941],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029877536,0.0006491499,0.0011346055,0.0036899105,0.000777396,0.0019980767,0.0013982593,0.0008497184,0.0019630503],"category_scores_gemma":[0.0196214,0.00041199476,0.0010366614,0.0029162476,0.0009978946,0.003045839,0.0015509614,0.0014153247,0.0009736426],"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":[0.00075204385,0.000621407,0.11696594,0.002056491,0.00054148317,0.0026549965,0.0025491517,0.023998281,0.06418749,0.0930279,0.007195631,0.6854491],"study_design_scores_gemma":[0.00013463898,0.00068425736,0.0668617,0.0003339734,0.0004516376,0.0043225777,0.002160682,0.41366005,0.044093426,0.43516102,0.031950586,0.00018552167],"about_ca_topic_score_codex":0.000727175,"about_ca_topic_score_gemma":0.00088711496,"teacher_disagreement_score":0.0036899105,"about_ca_system_score_codex":0.00041060775,"about_ca_system_score_gemma":0.0009498517,"threshold_uncertainty_score":0.015800953},"labels":[],"label_agreement":null},{"id":"W2103662135","doi":"10.1109/icnc.2011.6022588","title":"A dynamic composite approach for evaluating association rules","year":2011,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Association rule learning; Association (psychology); Computer science; Task (project management); Process (computing); Set (abstract data type); Data mining; Measure (data warehouse); Property (philosophy); Artificial neural network; Machine learning; Artificial intelligence; Engineering","score_opus":0.061657267090387206,"score_gpt":0.30808992636654114,"score_spread":0.24643265927615393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103662135","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028534815,0.0004968112,0.9678803,0.00023437392,0.000056236702,0.00020541616,0.0001414879,0.0005932825,0.0018573721],"genre_scores_gemma":[0.30498752,0.0002989033,0.69296676,0.00013619795,0.00006709535,0.00034192944,0.00026389924,0.00008234521,0.0008553516],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9859535,0.0041948473,0.0016158134,0.002450385,0.005456273,0.00032901016],"domain_scores_gemma":[0.9601794,0.025874687,0.0041372227,0.0028026744,0.006244723,0.000761345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01747608,0.0017043524,0.0021502594,0.009513117,0.0011337186,0.0036248337,0.0022069393,0.0016091741,0.0014628683],"category_scores_gemma":[0.05178765,0.0006042214,0.001205042,0.0053835358,0.0017274069,0.0059162015,0.0018761052,0.0024708395,0.00037672906],"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":[0.00075148017,0.0005500865,0.030964626,0.0005608742,0.00097523205,0.00033105531,0.0006235413,0.21702377,0.0142785,0.033632208,0.00211648,0.6981921],"study_design_scores_gemma":[0.000034233977,0.00046236062,0.0059279716,0.000083506086,0.0002220721,0.00030173679,0.00013581676,0.9420701,0.007582461,0.04066914,0.0024123131,0.00009821458],"about_ca_topic_score_codex":0.0019573504,"about_ca_topic_score_gemma":0.0033355514,"teacher_disagreement_score":0.01747608,"about_ca_system_score_codex":0.0015841599,"about_ca_system_score_gemma":0.0013364569,"threshold_uncertainty_score":0.09242344},"labels":[],"label_agreement":null},{"id":"W2103800269","doi":"10.1145/1982185.1982417","title":"Mining uncertain web log sequences with access history probabilities","year":2011,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Traverse; Session (web analytics); Path (computing); A priori and a posteriori; Suffix; Data mining; Web mining; Theoretical computer science; Web page; Algorithm; World Wide Web; Computer network","score_opus":0.10535775471393305,"score_gpt":0.2688354839739381,"score_spread":0.16347772926000503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103800269","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20866103,0.00058529474,0.7865611,0.00026242962,0.000023884908,0.00013414936,0.0016245021,0.0013090309,0.0008386495],"genre_scores_gemma":[0.8389689,0.00035616965,0.15728977,0.00007178886,0.000059800434,0.00013405965,0.0024515558,0.00006410562,0.0006040163],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977704,0.00038627768,0.00029032963,0.00058755063,0.00083501457,0.00013048471],"domain_scores_gemma":[0.9884552,0.007734256,0.0017147247,0.0010294801,0.00084337214,0.0002230883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016498247,0.0008365924,0.0011527857,0.0030845308,0.00051853945,0.0012966625,0.0013886159,0.0007305288,0.0006732813],"category_scores_gemma":[0.015143594,0.00075988524,0.00087073824,0.0031281714,0.00053066073,0.004263991,0.0011331738,0.0009476286,0.00033143183],"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":[0.0010291374,0.00034544282,0.11286248,0.0006267767,0.0003512115,0.0025366743,0.0008053654,0.50142264,0.013952704,0.016719092,0.0023254543,0.3470231],"study_design_scores_gemma":[0.000011843668,0.00006436942,0.003793988,0.00002274495,0.00003757454,0.000456406,0.00009467162,0.9725911,0.003758872,0.018013924,0.0011337675,0.00002072085],"about_ca_topic_score_codex":0.0024275156,"about_ca_topic_score_gemma":0.0033652498,"teacher_disagreement_score":0.0030845308,"about_ca_system_score_codex":0.00050622993,"about_ca_system_score_gemma":0.0009841354,"threshold_uncertainty_score":0.008725226},"labels":[],"label_agreement":null},{"id":"W2103806412","doi":"10.1109/tai.1995.479846","title":"Performance evaluation of attribute-oriented algorithms for knowledge discovery from databases","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Knowledge extraction; Data mining; Database; Algorithm","score_opus":0.13889654948253907,"score_gpt":0.33326669534984527,"score_spread":0.1943701458673062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103806412","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7710208,0.0117875915,0.18053807,0.0015823721,0.0005339881,0.0005536244,0.0026586037,0.017847888,0.01347692],"genre_scores_gemma":[0.69498485,0.0028131898,0.29178828,0.000246967,0.00015023627,0.0003143703,0.0067444057,0.00068688305,0.0022709083],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98953307,0.0034679568,0.0016243759,0.0013022759,0.0033383758,0.00073402293],"domain_scores_gemma":[0.955418,0.033599358,0.0012268228,0.0027158034,0.0061127557,0.0009272382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012271437,0.0013298145,0.0013903381,0.0031163148,0.0010473821,0.0028823512,0.0030539336,0.0016565078,0.0018094874],"category_scores_gemma":[0.033383586,0.0004569207,0.0006959514,0.005841949,0.0007552994,0.003713394,0.001198686,0.0009652067,0.0011465613],"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":[0.008621794,0.0019392794,0.020467501,0.0014089746,0.00071062334,0.00017418609,0.00037743227,0.25901526,0.009203458,0.009080266,0.014287756,0.6747135],"study_design_scores_gemma":[0.00050166505,0.0008194907,0.0040112524,0.00004790102,0.00013900796,0.00019522071,0.00018349996,0.9716314,0.015430659,0.0037040804,0.0032836557,0.00005212093],"about_ca_topic_score_codex":0.008439228,"about_ca_topic_score_gemma":0.003189113,"teacher_disagreement_score":0.012271437,"about_ca_system_score_codex":0.0025011091,"about_ca_system_score_gemma":0.0024192836,"threshold_uncertainty_score":0.06489831},"labels":[],"label_agreement":null},{"id":"W2103986443","doi":"10.1145/564376.564412","title":"Document clustering with committees","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":174,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Cluster analysis; Information retrieval; Artificial intelligence","score_opus":0.018399226671570082,"score_gpt":0.21974579563819918,"score_spread":0.2013465689666291,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103986443","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005525586,0.00059293554,0.9872634,0.00014238148,0.00010159731,0.0003529771,0.00042027625,0.002164887,0.0034359787],"genre_scores_gemma":[0.07907792,0.00046812298,0.9120487,0.00013503572,0.00023215997,0.0006482719,0.0023067996,0.000647557,0.00443537],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9838816,0.008081938,0.001405824,0.002474466,0.0037171368,0.00043903646],"domain_scores_gemma":[0.9791988,0.008494368,0.0012960299,0.005504679,0.0050453646,0.0004606616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011010683,0.0014110873,0.0018501678,0.00524215,0.0018299451,0.0039226096,0.0022039132,0.0019410186,0.0050178417],"category_scores_gemma":[0.04172497,0.00081468414,0.002098172,0.0072405366,0.001158686,0.0041312696,0.0028736372,0.0018809645,0.004063326],"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":[0.0006019738,0.00015607545,0.0027323097,0.0006054219,0.00042447718,0.00013216033,0.00055951753,0.13520767,0.006054404,0.061025277,0.026040213,0.76646054],"study_design_scores_gemma":[0.00013952475,0.00033402038,0.0018191393,0.000117204894,0.00019689322,0.00052115537,0.00022580505,0.80352205,0.018968396,0.11579387,0.058250457,0.00011152382],"about_ca_topic_score_codex":0.0021791293,"about_ca_topic_score_gemma":0.0021015923,"teacher_disagreement_score":0.011010683,"about_ca_system_score_codex":0.001181089,"about_ca_system_score_gemma":0.0015502616,"threshold_uncertainty_score":0.058230698},"labels":[],"label_agreement":null},{"id":"W2104142344","doi":"","title":"Discovering and understanding change using multivariate trees: the RECPAM approach","year":2005,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Visitor pattern; Computer science; Multivariate statistics; Change detection; Tree (set theory); Data mining; Variable (mathematics); Data science; Machine learning; Artificial intelligence; Mathematics","score_opus":0.2119133288941466,"score_gpt":0.3099608054708215,"score_spread":0.0980474765766749,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104142344","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03842343,0.00077636295,0.9564217,0.0009858349,0.00004250948,0.00015850911,0.00074478047,0.00097142684,0.0014756108],"genre_scores_gemma":[0.42806774,0.0005615464,0.56820136,0.0002024268,0.00015065623,0.00026946852,0.0015697574,0.00015894057,0.00081805105],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996271,0.0019380708,0.00022322826,0.0007964756,0.00057702715,0.00019410136],"domain_scores_gemma":[0.98409235,0.011134935,0.0018439512,0.0016128139,0.00106889,0.00024715642],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049837683,0.0009714762,0.0015426596,0.0055107893,0.00085421494,0.0022697041,0.0024332926,0.0013575061,0.0018908333],"category_scores_gemma":[0.02413088,0.00062320236,0.0020127133,0.0051343185,0.0007994484,0.004535266,0.0017372031,0.002237854,0.000843881],"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":[0.00034438196,0.0006989405,0.07506574,0.00065740524,0.0009112496,0.0007395781,0.0022068114,0.1908416,0.0020288865,0.048886944,0.00735271,0.67026573],"study_design_scores_gemma":[0.000015171402,0.00007197473,0.006482043,0.000082762184,0.00009763688,0.00025878072,0.00040960853,0.9318018,0.0005534171,0.056040928,0.0041575157,0.000028353212],"about_ca_topic_score_codex":0.004530651,"about_ca_topic_score_gemma":0.0051943506,"teacher_disagreement_score":0.0055107893,"about_ca_system_score_codex":0.00080620963,"about_ca_system_score_gemma":0.0010182206,"threshold_uncertainty_score":0.026356995},"labels":[],"label_agreement":null},{"id":"W2105197992","doi":"10.1109/tai.1997.632290","title":"Data visualization in the DB-Discover system","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Visualization; Data visualization; Generalization; Data mining; Software; Knowledge extraction; Tree (set theory); Software visualization; Software system; Data science; Information retrieval; Programming language","score_opus":0.09015075838898043,"score_gpt":0.3029520327859268,"score_spread":0.21280127439694638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105197992","genre_codex":"software","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017667903,0.0006440606,0.47236145,0.0011301665,0.00023162235,0.00038234607,0.016517969,0.47591937,0.015145082],"genre_scores_gemma":[0.14496385,0.0014537823,0.77298737,0.0012640246,0.00026025498,0.0011823692,0.04206667,0.022116065,0.0137056485],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981469,0.00036512775,0.0002314936,0.0003438423,0.00080934865,0.000103259175],"domain_scores_gemma":[0.9948953,0.0022791137,0.00025905477,0.0014632696,0.00079112547,0.0003122179],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038433105,0.0009839874,0.0012459239,0.0027849877,0.00083543494,0.0042134607,0.0019898317,0.0009332462,0.012916775],"category_scores_gemma":[0.009373049,0.0010815845,0.0007296285,0.0028169027,0.0004225735,0.0038473145,0.0028118787,0.0016130398,0.0060042073],"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":[0.0034008746,0.0005516328,0.011056096,0.0013207452,0.0003800727,0.0011947931,0.0019590214,0.015783744,0.028735558,0.038633645,0.4493552,0.4476287],"study_design_scores_gemma":[0.0008644936,0.0003228595,0.0054396777,0.00029919966,0.00028665835,0.0016587304,0.00057303824,0.32273433,0.06945166,0.071106866,0.5268628,0.00039972787],"about_ca_topic_score_codex":0.002009859,"about_ca_topic_score_gemma":0.0019201392,"teacher_disagreement_score":0.012916775,"about_ca_system_score_codex":0.00071668235,"about_ca_system_score_gemma":0.0014012353,"threshold_uncertainty_score":0.043210924},"labels":[],"label_agreement":null},{"id":"W2105323064","doi":"10.5539/cis.v1n2p17","title":"Research on Decision Forest Learning Algorithm","year":2008,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Overfitting; Computer science; Decision tree; Machine learning; Artificial intelligence; Tree (set theory); Root (linguistics); Tree structure; Incremental decision tree; Decision tree learning; Algorithm; Alternating decision tree; Data mining; Mathematics; Artificial neural network; Binary tree","score_opus":0.05377590464561675,"score_gpt":0.3408806680468781,"score_spread":0.28710476340126134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105323064","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010455198,0.027824191,0.9506558,0.0013897317,0.0005135685,0.00010730547,0.0001360173,0.00032464258,0.008593538],"genre_scores_gemma":[0.23665102,0.036465712,0.71746355,0.0011754376,0.0016081778,0.00026206192,0.0007588869,0.00012509896,0.0054901186],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99639976,0.0012813811,0.0002454353,0.0007923361,0.0011019427,0.0001791408],"domain_scores_gemma":[0.9938432,0.004208451,0.0001813538,0.0003390611,0.0013358636,0.00009212431],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049046376,0.001083469,0.0016303594,0.002139229,0.00086118246,0.002247888,0.0018268009,0.0018071188,0.0022439696],"category_scores_gemma":[0.013288954,0.00051551644,0.0011150371,0.0043398575,0.0009633762,0.005037129,0.0008077283,0.0022767554,0.0013036465],"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":[0.00012155746,0.0001837845,0.0033032524,0.0008857839,0.00018631265,0.00014420638,0.00016027095,0.10029204,0.001924524,0.10417176,0.0063501517,0.7822763],"study_design_scores_gemma":[0.000057435456,0.00019791127,0.0013965059,0.00042379196,0.00011800701,0.00042809494,0.000108988876,0.74957496,0.0049138186,0.19582069,0.046890948,0.000068812275],"about_ca_topic_score_codex":0.002654069,"about_ca_topic_score_gemma":0.0015448924,"teacher_disagreement_score":0.0049046376,"about_ca_system_score_codex":0.0009431428,"about_ca_system_score_gemma":0.001586987,"threshold_uncertainty_score":0.02593851},"labels":[],"label_agreement":null},{"id":"W2105347536","doi":"10.1109/icdm.2006.62","title":"DSTree: A Tree Structure for the Mining of Frequent Sets from Data Streams","year":2006,"lang":"en","type":"article","venue":"Proceedings","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":165,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Data stream mining; Computer science; STREAMS; Data mining; Tree (set theory); Flood myth; Data stream; Tree structure; Data structure; Computer network; Mathematics","score_opus":0.031559548625875095,"score_gpt":0.26912972924114803,"score_spread":0.23757018061527294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105347536","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008527115,0.0010803575,0.9759679,0.0004829606,0.00012629406,0.00043114147,0.008415407,0.004146759,0.0008219958],"genre_scores_gemma":[0.04499452,0.0009979475,0.9390578,0.0002020817,0.00009359829,0.00062540616,0.013200891,0.0002611717,0.00056652864],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99806327,0.00045792924,0.0003688622,0.0003331144,0.0006794645,0.00009740916],"domain_scores_gemma":[0.9945767,0.002556811,0.00063122314,0.0007811853,0.0011825681,0.0002715788],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026851643,0.0009806827,0.00144402,0.0060158726,0.0013877684,0.0020093808,0.0020582557,0.0012522157,0.001988641],"category_scores_gemma":[0.014716807,0.00073981617,0.0015858208,0.00785032,0.00067642116,0.004718186,0.0018295689,0.0015709866,0.0014368868],"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":[0.0008231459,0.00032288377,0.012275206,0.002203172,0.00061636703,0.0011927644,0.0017332349,0.05621209,0.013538929,0.057679296,0.05990762,0.7934954],"study_design_scores_gemma":[0.0002843834,0.0005395743,0.004157865,0.0005510325,0.00028451552,0.0024430347,0.0006499967,0.6300499,0.012189255,0.21554917,0.13309321,0.0002079877],"about_ca_topic_score_codex":0.0027467508,"about_ca_topic_score_gemma":0.0050839577,"teacher_disagreement_score":0.0060158726,"about_ca_system_score_codex":0.00070077495,"about_ca_system_score_gemma":0.0020202028,"threshold_uncertainty_score":0.014200628},"labels":[],"label_agreement":null},{"id":"W2105564121","doi":"","title":"Privacy preserving frequent itemset mining","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":286,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Data mining; Database transaction; Set (abstract data type); Process (computing); Database","score_opus":0.046678222893395134,"score_gpt":0.25063001995182144,"score_spread":0.2039517970584263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105564121","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05636937,0.000745524,0.9370478,0.0010178251,0.000075588294,0.00019142075,0.0008899931,0.0015599917,0.0021024991],"genre_scores_gemma":[0.54113114,0.0008001415,0.45287237,0.00041350143,0.0002409553,0.00022738546,0.002336557,0.00015903618,0.0018189864],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98348236,0.0059343055,0.002271809,0.0023669584,0.0050979923,0.0008466653],"domain_scores_gemma":[0.915818,0.03293405,0.006341335,0.03793606,0.0063282885,0.00064229866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012572186,0.00074527046,0.002247817,0.0026699353,0.001601629,0.0043621045,0.0029768127,0.0018146096,0.0010263993],"category_scores_gemma":[0.06270926,0.0006689395,0.0015396278,0.0044869212,0.0017298342,0.0069194697,0.002832348,0.0020806685,0.0011287916],"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":[0.0017928916,0.00063405896,0.031261988,0.00068845163,0.0006358859,0.0009761049,0.0010484348,0.120191954,0.040938936,0.067411035,0.009743424,0.7246768],"study_design_scores_gemma":[0.00012949064,0.00055162125,0.0037910151,0.000110303736,0.0002579427,0.0026611395,0.000515132,0.68117154,0.08099169,0.21435365,0.0153470505,0.00011938512],"about_ca_topic_score_codex":0.0006114056,"about_ca_topic_score_gemma":0.0005940087,"teacher_disagreement_score":0.012572186,"about_ca_system_score_codex":0.00075264927,"about_ca_system_score_gemma":0.0022845056,"threshold_uncertainty_score":0.06648886},"labels":[],"label_agreement":null},{"id":"W2106859889","doi":"10.1109/icsmc.2007.4413722","title":"Pre-shaped fuzzy c-means algorithm (PFCM) for transparent membership function generation","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Alberta; National Aeronautics and Space Administration","keywords":"Fuzzy logic; Membership function; Transparency (behavior); Algorithm; Cluster analysis; Computer science; Fuzzy set; Process (computing); Function (biology); Data mining; Artificial intelligence","score_opus":0.066554402513894,"score_gpt":0.2997982292466215,"score_spread":0.23324382673272748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106859889","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019257148,0.000054496937,0.9972882,0.000038943486,0.000022342709,0.00003629794,0.000010176189,0.00029836167,0.00032534113],"genre_scores_gemma":[0.042950016,0.00007013438,0.95599145,0.00006840728,0.000020843274,0.00016101405,0.000057132118,0.00008021454,0.0006008814],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984289,0.0003616516,0.00010420721,0.00034856514,0.00067028357,0.00008632723],"domain_scores_gemma":[0.9971916,0.0012121279,0.0001928828,0.0003581163,0.0009694804,0.000075752],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022885327,0.0012076428,0.0011055024,0.0015506395,0.0013226407,0.0009850885,0.0023097708,0.0018731172,0.0017533905],"category_scores_gemma":[0.0076097036,0.00059887336,0.0012691208,0.0015443137,0.0010738745,0.0014499257,0.0011487369,0.0021568595,0.00067054445],"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":[0.0002725535,0.00012059739,0.00087292213,0.00023642018,0.000105913976,0.00016618398,0.00037371606,0.2837772,0.019599043,0.024269054,0.0055271885,0.6646792],"study_design_scores_gemma":[0.000025175095,0.000062287334,0.00023620726,0.000017632734,0.00001420995,0.0001361959,0.00001995944,0.979768,0.009778757,0.006574021,0.003328692,0.000038918133],"about_ca_topic_score_codex":0.005105468,"about_ca_topic_score_gemma":0.0042453953,"teacher_disagreement_score":0.005105468,"about_ca_system_score_codex":0.0011252569,"about_ca_system_score_gemma":0.0021784576,"threshold_uncertainty_score":0.012103081},"labels":[],"label_agreement":null},{"id":"W2107197725","doi":"","title":"DATA MINING UNTUK KLASIFIKASI PELANGGAN DENGAN ANT COLONY OPTIMIZATION","year":2007,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Encana (Canada)","funders":"","keywords":"Ant colony optimization algorithms; Computer science; Artificial intelligence","score_opus":0.3462147573934887,"score_gpt":0.5636145785336187,"score_spread":0.21739982114013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107197725","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10535931,0.0017690301,0.87635386,0.0010849144,0.00020737683,0.00035069243,0.00055508723,0.002264247,0.012055509],"genre_scores_gemma":[0.58564794,0.0012995848,0.39876017,0.00034139317,0.000069992406,0.00037448644,0.0010781594,0.000204111,0.01222418],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988783,0.0001670523,0.00010782746,0.00031541038,0.00045000922,0.00008133509],"domain_scores_gemma":[0.9987576,0.0005294319,0.00013578165,0.000107153886,0.00043357696,0.000036457273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009215012,0.00088364386,0.0010232598,0.0013039011,0.00046984633,0.0020407098,0.0009851247,0.0006751106,0.0022584542],"category_scores_gemma":[0.0026890733,0.000418412,0.000791415,0.0014088583,0.0004299011,0.0010901645,0.00054371834,0.000988806,0.00093356636],"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":[0.00035241578,0.00031229365,0.013183972,0.0008032045,0.00036426663,0.00045472206,0.00046022655,0.2583404,0.025714394,0.007744572,0.0059597604,0.6863098],"study_design_scores_gemma":[0.000030400093,0.0001517474,0.004495163,0.000070650516,0.00010649897,0.0002923714,0.00023502135,0.96337223,0.014255767,0.006421895,0.010526194,0.000042115116],"about_ca_topic_score_codex":0.0044360724,"about_ca_topic_score_gemma":0.003996875,"teacher_disagreement_score":0.0044360724,"about_ca_system_score_codex":0.00059256115,"about_ca_system_score_gemma":0.0009341866,"threshold_uncertainty_score":0.008820534},"labels":[],"label_agreement":null},{"id":"W2107309265","doi":"10.5539/cis.v7n4p74","title":"Prototyping Data Warehouse System for Ministry of Higher Education in Saudi Arabia","year":2014,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Christian ministry; Data warehouse; Computer science; Higher education; Institution; Stakeholder; World Wide Web; Engineering management; Knowledge management; Database; Public relations; Political science; Engineering","score_opus":0.029324182756130617,"score_gpt":0.29919267311621034,"score_spread":0.2698684903600797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107309265","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5903592,0.001481547,0.31605414,0.0026954447,0.00028569758,0.002129003,0.023341551,0.047403384,0.016250003],"genre_scores_gemma":[0.50413144,0.0011270833,0.45209908,0.00031438709,0.000029897834,0.0005491347,0.033475082,0.0007265859,0.0075474926],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99924016,0.00013227304,0.00014803089,0.00016987532,0.0002371092,0.00007244606],"domain_scores_gemma":[0.9980155,0.00044260887,0.00014361979,0.0004116499,0.0007629209,0.00022359376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019960601,0.00039445638,0.00039404503,0.001127704,0.0008069136,0.002897077,0.0012177235,0.0006279617,0.0025283585],"category_scores_gemma":[0.002471767,0.00044379744,0.00070394395,0.0016623645,0.00019412447,0.0023160009,0.0011745772,0.0007565983,0.0011781933],"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":[0.003009221,0.0026115833,0.06967234,0.0034998478,0.00046467458,0.00851813,0.013437525,0.026523983,0.19417638,0.023267407,0.09856557,0.5562534],"study_design_scores_gemma":[0.000747919,0.0011795955,0.060034603,0.00071585743,0.0005363043,0.0048030317,0.011988848,0.22214499,0.28652486,0.009042738,0.40190163,0.0003796028],"about_ca_topic_score_codex":0.0046653394,"about_ca_topic_score_gemma":0.0045453715,"teacher_disagreement_score":0.0046653394,"about_ca_system_score_codex":0.00072049873,"about_ca_system_score_gemma":0.0015367658,"threshold_uncertainty_score":0.010556281},"labels":[],"label_agreement":null},{"id":"W2107415975","doi":"10.1007/11527503_10","title":"Finding All Frequent Patterns Starting from the Closure","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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 Alberta","funders":"","keywords":"Computer science; Closure (psychology)","score_opus":0.031212176330043133,"score_gpt":0.26666680672615317,"score_spread":0.23545463039611003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107415975","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4092728,0.0024790268,0.5612596,0.0013197401,0.0005941725,0.001185592,0.011818127,0.0030544952,0.009016464],"genre_scores_gemma":[0.41319838,0.0010796405,0.55553436,0.00023307191,0.00036383208,0.0005522847,0.022854507,0.0004464105,0.005737546],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988475,0.00008964408,0.0001621487,0.00042463702,0.00034058088,0.00013553588],"domain_scores_gemma":[0.9952578,0.0022248398,0.00051639683,0.00061154715,0.0010500478,0.0003394197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008974492,0.001153787,0.00168975,0.0040474106,0.0012357851,0.0020015675,0.0014108274,0.0010697092,0.0056976243],"category_scores_gemma":[0.008600613,0.0006974709,0.0021703464,0.002528362,0.0006582324,0.0039878855,0.0010914407,0.001656809,0.0025430552],"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":[0.0025889648,0.0011977613,0.03784191,0.0026530335,0.00043640853,0.0070997374,0.001398395,0.0050752354,0.071712375,0.04113267,0.021274474,0.807589],"study_design_scores_gemma":[0.000842428,0.0036361546,0.034615546,0.0016512378,0.0012217844,0.022421576,0.0040275403,0.2063213,0.09967477,0.54081297,0.084481776,0.00029298058],"about_ca_topic_score_codex":0.00056282955,"about_ca_topic_score_gemma":0.0007850695,"teacher_disagreement_score":0.0056976243,"about_ca_system_score_codex":0.0003147787,"about_ca_system_score_gemma":0.0014945106,"threshold_uncertainty_score":0.019060493},"labels":[],"label_agreement":null},{"id":"W2110116143","doi":"10.1109/icc.2007.648","title":"An Efficient Data Extraction Mechanism for Mining Association Rules from Wireless Sensor Networks","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Wireless sensor network; Computer science; Association rule learning; Data mining; Process (computing); Data stream mining; Knowledge extraction; Distributed computing; Computation; Computer network; Algorithm","score_opus":0.03380474071331885,"score_gpt":0.30953858612964186,"score_spread":0.275733845416323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110116143","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0068716514,0.00028125604,0.9903137,0.0001686012,0.000043788437,0.00019030989,0.00043484545,0.0014829225,0.00021293807],"genre_scores_gemma":[0.093466036,0.00044785868,0.90203965,0.0001862118,0.00009101275,0.00073957746,0.002073068,0.00006440354,0.0008922036],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957301,0.00078665453,0.0007842684,0.0009314,0.0016097416,0.00015787878],"domain_scores_gemma":[0.99018353,0.0051139835,0.0011493478,0.0018014746,0.0016028112,0.0001488724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005332405,0.0012060934,0.002499128,0.004074396,0.0012192474,0.0019912906,0.0030246812,0.001478176,0.0011011154],"category_scores_gemma":[0.017617341,0.0008578909,0.0016839964,0.0054294197,0.0006363838,0.0038929435,0.0018091627,0.0017836118,0.0008844778],"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":[0.0006587866,0.0005819618,0.005442814,0.0006986766,0.0005827121,0.0010644498,0.00039457539,0.081463635,0.02174473,0.018873028,0.0079400325,0.8605545],"study_design_scores_gemma":[0.0002515131,0.00044713868,0.002691541,0.0001514171,0.00039021295,0.0017423283,0.00019414807,0.89859647,0.032349855,0.04427885,0.018782945,0.00012355004],"about_ca_topic_score_codex":0.001012532,"about_ca_topic_score_gemma":0.0014478333,"teacher_disagreement_score":0.005332405,"about_ca_system_score_codex":0.00046238687,"about_ca_system_score_gemma":0.0017703873,"threshold_uncertainty_score":0.028200805},"labels":[],"label_agreement":null},{"id":"W2110439290","doi":"10.1142/s0218001402002179","title":"IMPROVING ENCARTA SEARCH ENGINE PERFORMANCE BY MINING USER LOGS","year":2002,"lang":"en","type":"article","venue":"International Journal of Pattern Recognition and Artificial Intelligence","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick; Western University","funders":"","keywords":"Computer science; Web query classification; Web search query; Information retrieval; Search engine; Query expansion; Search-oriented architecture; Sargable; Query language; Query optimization; Spatial query; Web search engine; Cache; Data mining; World Wide Web","score_opus":0.0828712349594512,"score_gpt":0.2874540315330467,"score_spread":0.20458279657359552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110439290","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56718093,0.0030449873,0.32020006,0.0011691786,0.00013309704,0.0004136391,0.0033664366,0.09865392,0.0058376486],"genre_scores_gemma":[0.70297533,0.0005611709,0.2867676,0.00018407598,0.00008969085,0.00015843181,0.005731916,0.0008116416,0.0027201802],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99779946,0.00043403514,0.0002292343,0.00041247046,0.0009880229,0.00013685372],"domain_scores_gemma":[0.9891159,0.004173558,0.0007671859,0.0030763268,0.0024869912,0.00038010484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029645902,0.0013805743,0.0019386174,0.0036507535,0.00059871614,0.002300179,0.0020422437,0.0006106892,0.0010814834],"category_scores_gemma":[0.013900745,0.000640948,0.0006097543,0.0036676775,0.00041747474,0.0051018344,0.0011038554,0.0009794515,0.0014095898],"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":[0.002505938,0.0013122207,0.086767584,0.00062455767,0.000582668,0.00040802098,0.0006663686,0.043424968,0.044625737,0.0036545098,0.017068587,0.79835886],"study_design_scores_gemma":[0.00009945459,0.0004092969,0.010640553,0.000024301651,0.0001321725,0.00038058506,0.00016065515,0.94591415,0.033834424,0.0028289885,0.0054868213,0.00008862596],"about_ca_topic_score_codex":0.009829563,"about_ca_topic_score_gemma":0.014839775,"teacher_disagreement_score":0.009829563,"about_ca_system_score_codex":0.00056489324,"about_ca_system_score_gemma":0.001734057,"threshold_uncertainty_score":0.019544661},"labels":[],"label_agreement":null},{"id":"W2110624414","doi":"10.1109/ideas.2007.28","title":"Feature Space Enrichment by Incorporation of Implicit Features for Effective Classification","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Classifier (UML); Pattern recognition (psychology); Discriminative model; Feature extraction; Artificial intelligence; Feature vector; Computer science; Unison; Linear classifier; Feature (linguistics); Data mining","score_opus":0.009552854389385785,"score_gpt":0.27831299669707427,"score_spread":0.26876014230768847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110624414","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019617574,0.0005263217,0.97768855,0.00018696478,0.00004506393,0.00007490537,0.00009990617,0.00069143175,0.0010693235],"genre_scores_gemma":[0.24231178,0.00045448047,0.75481325,0.00010179258,0.000085883155,0.00020488499,0.00040875148,0.000076904296,0.0015421839],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99853575,0.0004899836,0.00012196651,0.00024860835,0.0005263958,0.00007723123],"domain_scores_gemma":[0.9964259,0.0018098673,0.00025970212,0.000885471,0.000565264,0.000053823926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015175685,0.0005991034,0.00072687084,0.0014171764,0.000323492,0.0015354888,0.0008245728,0.0007018483,0.0016546975],"category_scores_gemma":[0.007304441,0.00026336586,0.0005285096,0.0019492815,0.00079936575,0.0024935566,0.0013052181,0.0012683722,0.0011584786],"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":[0.00018063217,0.00017710564,0.0031032348,0.00029261588,0.000069969225,0.00018050456,0.00025617293,0.017579801,0.037804645,0.028210122,0.0031842177,0.9089612],"study_design_scores_gemma":[0.00006807128,0.00053255545,0.006063728,0.00013416326,0.00012175961,0.00095493725,0.00015189196,0.82709616,0.06181332,0.06841135,0.03454625,0.000105836436],"about_ca_topic_score_codex":0.00032469796,"about_ca_topic_score_gemma":0.0004839122,"teacher_disagreement_score":0.0016546975,"about_ca_system_score_codex":0.0002769814,"about_ca_system_score_gemma":0.00042742156,"threshold_uncertainty_score":0.008025765},"labels":[],"label_agreement":null},{"id":"W2110834019","doi":"10.1109/icdm.2005.35","title":"Bifold Constraint-Based Mining by Simultaneous Monotone and Anti-Monotone Checking","year":2006,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Monotone polygon; Constraint (computer-aided design); Computer science; Overhead (engineering); Set (abstract data type); Exploit; Data mining; Process (computing); Set operations; Mathematics","score_opus":0.007690496117258246,"score_gpt":0.22429573944284417,"score_spread":0.21660524332558592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110834019","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028400851,0.00016701016,0.96502787,0.00029386795,0.00002921958,0.00029256206,0.00027858382,0.003948292,0.0015617266],"genre_scores_gemma":[0.20377845,0.00008169153,0.79325694,0.00027069447,0.000029142182,0.00030142878,0.00066241866,0.00028203274,0.0013372084],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.993651,0.0016209406,0.0006153802,0.00092899345,0.0026053546,0.0005784516],"domain_scores_gemma":[0.9789069,0.013455708,0.0013315607,0.0032093092,0.0027435366,0.0003529242],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008090255,0.001017899,0.001482402,0.0032056188,0.001157177,0.0031054635,0.00443702,0.0015862436,0.004107219],"category_scores_gemma":[0.026068518,0.001070922,0.0019856424,0.0028264257,0.0016781035,0.005429765,0.004260538,0.0016855219,0.0010689304],"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":[0.0018075175,0.0007125534,0.017252656,0.00072520884,0.00034842288,0.0011769877,0.000663069,0.08350264,0.034122173,0.08055854,0.0074544316,0.7716758],"study_design_scores_gemma":[0.0001355389,0.00019532423,0.0007629912,0.00006683962,0.00006145006,0.0005436096,0.00008311918,0.91729903,0.0221289,0.054759417,0.0038998662,0.000063920386],"about_ca_topic_score_codex":0.004098609,"about_ca_topic_score_gemma":0.0069942838,"teacher_disagreement_score":0.008090255,"about_ca_system_score_codex":0.0010484298,"about_ca_system_score_gemma":0.0032493067,"threshold_uncertainty_score":0.042785883},"labels":[],"label_agreement":null},{"id":"W2112154958","doi":"10.1109/tkde.2009.59","title":"Discovering Transitional Patterns and Their Significant Milestones in Transaction Databases","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Database; Database transaction; Transaction processing; Transaction log; Distributed database; Information retrieval; Data science","score_opus":0.02862650924382022,"score_gpt":0.26474186092001395,"score_spread":0.23611535167619374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112154958","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3945386,0.0027671251,0.5931224,0.00074288715,0.00008689811,0.00035803553,0.003344891,0.0012746699,0.0037644848],"genre_scores_gemma":[0.7138617,0.0012225878,0.2796689,0.000117712814,0.000060203874,0.00032545876,0.0034733335,0.000083824125,0.0011863986],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997512,0.00037898935,0.00047199198,0.0006024358,0.000817434,0.0002172556],"domain_scores_gemma":[0.99128586,0.004013802,0.001771474,0.0010864998,0.0014099285,0.00043242262],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018746858,0.00056500983,0.0007834533,0.00529917,0.001014439,0.0024784787,0.0013758943,0.00082541595,0.0010396527],"category_scores_gemma":[0.015359477,0.0005913836,0.000874859,0.007846926,0.00080783566,0.005282489,0.0017629787,0.001009484,0.00063046213],"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":[0.0012922519,0.00046818866,0.19340944,0.0013652819,0.00048968423,0.004846871,0.0047280327,0.048180122,0.021519227,0.07274156,0.0069821905,0.6439772],"study_design_scores_gemma":[0.000108858556,0.0006383157,0.06763569,0.0004866188,0.00041219871,0.005485123,0.005025877,0.516828,0.026438626,0.34075987,0.035940457,0.00024038547],"about_ca_topic_score_codex":0.0015817959,"about_ca_topic_score_gemma":0.0014582139,"teacher_disagreement_score":0.00529917,"about_ca_system_score_codex":0.00049398956,"about_ca_system_score_gemma":0.00079696684,"threshold_uncertainty_score":0.009914398},"labels":[],"label_agreement":null},{"id":"W2112289227","doi":"10.1109/tsmcb.2009.2020213","title":"A Multifaceted Perspective at Data Analysis: A Study in Collaborative Intelligent Agents $^{\\ast}$","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Perspective (graphical); Computer science; Data science; Psychology; Artificial intelligence","score_opus":0.04637901439065827,"score_gpt":0.3147114452960959,"score_spread":0.2683324309054376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112289227","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014826929,0.010025211,0.94347066,0.018263537,0.00014995711,0.00010911922,0.00004674314,0.00009810877,0.01300974],"genre_scores_gemma":[0.2606975,0.0057172207,0.7289037,0.0014160429,0.00047776345,0.00033822263,0.000064968415,0.00009043537,0.0022940477],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97643584,0.016100436,0.0010942483,0.0027071878,0.0031586727,0.00050360383],"domain_scores_gemma":[0.9494832,0.043214228,0.001820155,0.0029522006,0.0016294973,0.0009007267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024404895,0.000975073,0.0013554881,0.004996416,0.0038464826,0.011696945,0.0035598474,0.006213776,0.0014919377],"category_scores_gemma":[0.034960434,0.0009131982,0.0021739646,0.006092302,0.020679133,0.0154632125,0.0053738044,0.0054695704,0.00034709985],"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":[0.00001755004,0.000047023175,0.0009100493,0.0002274427,0.000065230444,0.00022467568,0.00555175,0.008287836,0.00047978573,0.9590607,0.000776852,0.024351101],"study_design_scores_gemma":[0.000021344154,0.00006390281,0.0007603507,0.00023745056,0.000045509103,0.00030052112,0.002196481,0.083916165,0.0006527382,0.8904008,0.021347623,0.000057038273],"about_ca_topic_score_codex":0.004843134,"about_ca_topic_score_gemma":0.0031517672,"teacher_disagreement_score":0.024404895,"about_ca_system_score_codex":0.004309525,"about_ca_system_score_gemma":0.0027932276,"threshold_uncertainty_score":0.129067},"labels":[],"label_agreement":null},{"id":"W2112971308","doi":"10.1007/978-3-319-06608-0_4","title":"Fast Vertical Mining of Sequential Patterns Using Co-occurrence Information","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":242,"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":"European Regional Development Fund; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Pruning; Bottleneck; Data mining; Representation (politics); Sequential Pattern Mining; Information bottleneck method; State (computer science); Pattern recognition (psychology); Artificial intelligence; Algorithm; Cluster analysis","score_opus":0.028075066088250885,"score_gpt":0.2794808825966699,"score_spread":0.25140581650841903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112971308","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1411406,0.003559109,0.8349794,0.00034311315,0.0002556377,0.00036571853,0.008043376,0.006679707,0.004633316],"genre_scores_gemma":[0.3204465,0.0012847338,0.65488195,0.000082693914,0.00016329048,0.00021520555,0.017736776,0.000292523,0.004896363],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989889,0.00007849128,0.00012807686,0.00022743178,0.0004574138,0.000119720986],"domain_scores_gemma":[0.9974541,0.0011436443,0.00029566465,0.00030915317,0.00064835994,0.00014898746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005802197,0.0010399746,0.001231359,0.00585938,0.00082747807,0.0015113393,0.0012211151,0.0006289563,0.0026076238],"category_scores_gemma":[0.0031809348,0.0005523649,0.0012016452,0.0074207857,0.00026224207,0.0017907013,0.0010584424,0.00083382044,0.0020608676],"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":[0.0005458505,0.0002932385,0.014686032,0.0006352427,0.00024387814,0.0005987593,0.00020011723,0.008186978,0.027609084,0.0038590736,0.012011942,0.9311298],"study_design_scores_gemma":[0.00014811177,0.00059878844,0.017095933,0.0002398156,0.000460945,0.0029962272,0.00053861446,0.8784603,0.037863966,0.036297046,0.025202129,0.000098082426],"about_ca_topic_score_codex":0.0041108,"about_ca_topic_score_gemma":0.007662056,"teacher_disagreement_score":0.00585938,"about_ca_system_score_codex":0.00033158323,"about_ca_system_score_gemma":0.0012489686,"threshold_uncertainty_score":0.008723319},"labels":[],"label_agreement":null},{"id":"W2113516501","doi":"10.1109/tsmcb.2004.843278","title":"Fuzzy OLAP Association Rules Mining-Based Modular Reinforcement Learning Approach for Multiagent Systems","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Online analytical processing; Computer science; Modular design; Association rule learning; Reinforcement learning; Fuzzy logic; Data mining; Artificial intelligence; Machine learning; Data warehouse; Programming language","score_opus":0.022201967909970022,"score_gpt":0.23933210750748174,"score_spread":0.2171301395975117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113516501","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012764073,0.00013744562,0.9859936,0.000111644724,0.000014299398,0.00006415834,0.00003821575,0.00022224536,0.00065434206],"genre_scores_gemma":[0.6810333,0.00023169628,0.31665143,0.00011421116,0.000039253122,0.00029986916,0.00018517909,0.000040947638,0.0014040793],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882287,0.0003093363,0.00011037712,0.00032502462,0.00032726282,0.0001050325],"domain_scores_gemma":[0.9977708,0.001006659,0.00033094175,0.0002066457,0.0005802434,0.00010478807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019051796,0.00093149085,0.0013169986,0.0011112647,0.00062770385,0.0011642865,0.0020287489,0.00079197704,0.0014233711],"category_scores_gemma":[0.0037080452,0.0004306349,0.001030898,0.0009843047,0.00065774017,0.0014045495,0.0015069311,0.001216059,0.0002382428],"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":[0.000067192836,0.00011115477,0.0019614846,0.000106061176,0.00013118307,0.00017123831,0.0001544344,0.88431716,0.0018555942,0.011571127,0.0006973043,0.098856054],"study_design_scores_gemma":[0.0000036262218,0.0000123510135,0.00006456883,0.0000021649007,0.000005568254,0.000009531889,0.000007802883,0.9965534,0.00024744798,0.002944668,0.00014570041,0.0000031475308],"about_ca_topic_score_codex":0.004984653,"about_ca_topic_score_gemma":0.0033977684,"teacher_disagreement_score":0.004984653,"about_ca_system_score_codex":0.0010279024,"about_ca_system_score_gemma":0.0012977151,"threshold_uncertainty_score":0.010075629},"labels":[],"label_agreement":null},{"id":"W2113998358","doi":"10.1109/ccece.2008.4564627","title":"Research on intelligent decision-making operation modes in Modern Commerce Service Value Chain Model","year":2008,"lang":"en","type":"article","venue":"Conference proceedings - Canadian Conference on Electrical and Computer Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Service (business); Computer science; Service-oriented architecture; Process management; Architecture; Supply chain; Engineering management; Knowledge management; Web service; Business; Engineering; World Wide Web; Marketing","score_opus":0.06955463404174575,"score_gpt":0.29635692717292633,"score_spread":0.22680229313118058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113998358","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08535527,0.0008295665,0.8839719,0.0012560998,0.00006734035,0.0001255061,0.00010468951,0.00026300698,0.028026676],"genre_scores_gemma":[0.8823028,0.0008161067,0.11270936,0.00009786226,0.000049981772,0.000106575724,0.00012447363,0.0000291289,0.0037637155],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891055,0.00036692934,0.00006834608,0.00021475238,0.0002986755,0.00014080259],"domain_scores_gemma":[0.998662,0.0006478324,0.00012980735,0.00016186616,0.0002921635,0.00010636044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019294497,0.00055730715,0.0004315507,0.0011170986,0.00067985326,0.0029357488,0.0013217793,0.0010508157,0.0028110258],"category_scores_gemma":[0.0035322944,0.0003328663,0.000788843,0.002000684,0.0017669862,0.0057895924,0.00075053744,0.001426563,0.0004996255],"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":[0.000086484506,0.00010201393,0.0033274137,0.000101202284,0.000047683687,0.00019607892,0.00075155497,0.15865517,0.0017612219,0.78763837,0.0012641657,0.04606865],"study_design_scores_gemma":[0.000015063105,0.000045829715,0.00045911956,0.00002753823,0.000016316297,0.00007115033,0.00013460113,0.72538644,0.00067796715,0.27009562,0.003046677,0.000023739574],"about_ca_topic_score_codex":0.005215849,"about_ca_topic_score_gemma":0.0018822037,"teacher_disagreement_score":0.005215849,"about_ca_system_score_codex":0.0020953196,"about_ca_system_score_gemma":0.0014948061,"threshold_uncertainty_score":0.015202761},"labels":[],"label_agreement":null},{"id":"W2114506861","doi":"10.1109/icdm.2005.38","title":"CanTree: A Tree Structure for Efficient Incremental Mining of Frequent Patterns","year":2006,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":101,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Tree (set theory); Data mining; Database transaction; Tree structure; Fractal tree index; GSP Algorithm; Interval tree; Search tree; A priori and a posteriori; Segment tree; Incremental decision tree; Apriori algorithm; Association rule learning; Database; Decision tree; Decision tree learning; Algorithm; Binary tree; Mathematics; Search algorithm","score_opus":0.010621176732323021,"score_gpt":0.23705300987513508,"score_spread":0.22643183314281207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114506861","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009507622,0.0014199691,0.9741866,0.00044796185,0.00016282253,0.00045968094,0.0038924573,0.008597882,0.001324908],"genre_scores_gemma":[0.048537824,0.0009926354,0.938879,0.00018923957,0.000118221345,0.00058518094,0.00927007,0.00039175822,0.0010360883],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99806935,0.0004891015,0.00024701672,0.0002792222,0.00079268037,0.00012265693],"domain_scores_gemma":[0.99254555,0.0032972037,0.00071516307,0.0013511786,0.0017242007,0.00036676548],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023904035,0.0009350156,0.0015704071,0.0059168106,0.0012266687,0.0021368088,0.002811455,0.0010317301,0.0023977263],"category_scores_gemma":[0.014482086,0.0009605258,0.0015712304,0.0073280004,0.00064758555,0.004081542,0.0020912564,0.0015221374,0.0017655459],"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":[0.0008049444,0.0003265263,0.005678713,0.0013935927,0.00042800079,0.0010965957,0.0008543167,0.04739581,0.014186178,0.03794434,0.071632765,0.8182582],"study_design_scores_gemma":[0.00043469598,0.00058435556,0.0030792933,0.00026938107,0.00035554825,0.002714154,0.00036930165,0.7341862,0.016206956,0.12064697,0.12091545,0.00023772298],"about_ca_topic_score_codex":0.0041552554,"about_ca_topic_score_gemma":0.008506114,"teacher_disagreement_score":0.0059168106,"about_ca_system_score_codex":0.0007323554,"about_ca_system_score_gemma":0.0027571847,"threshold_uncertainty_score":0.0126417875},"labels":[],"label_agreement":null},{"id":"W2115482638","doi":"10.1023/b:dami.0000005258.31418.83","title":"Mining Frequent Patterns without Candidate Generation: A Frequent-Pattern Tree Approach","year":2003,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2615,"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 mining; Computer science; Scalability; Tree (set theory); Set (abstract data type); Apriori algorithm; GSP Algorithm; Association rule learning; Trie; Tree structure; Pattern recognition (psychology); Data structure; Artificial intelligence; Database; Mathematics","score_opus":0.06223377143017436,"score_gpt":0.29063549100603664,"score_spread":0.22840171957586228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115482638","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015540487,0.0007677517,0.9811126,0.00036274185,0.0000735874,0.00025755877,0.0005567197,0.0007541402,0.0005744072],"genre_scores_gemma":[0.09764457,0.0006919973,0.89796776,0.00020486343,0.00015232248,0.00023687597,0.0019381226,0.000117852265,0.0010457486],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9948336,0.0012880629,0.0005897361,0.001057398,0.001971786,0.0002594239],"domain_scores_gemma":[0.9828394,0.011822382,0.0009671408,0.0019243362,0.0021089658,0.00033776354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005180415,0.0013000112,0.0032327133,0.004975306,0.0014235725,0.0034171168,0.0043475204,0.0025914365,0.002064071],"category_scores_gemma":[0.022039149,0.0010614758,0.0026218898,0.0060721207,0.0010220045,0.0061683636,0.0019202031,0.0022507547,0.0018815331],"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":[0.0010310683,0.001224696,0.013310004,0.0013528459,0.00077918754,0.0021127616,0.0004719143,0.038808662,0.0124722095,0.023623649,0.0089901965,0.89582276],"study_design_scores_gemma":[0.0002655924,0.00060924364,0.0023457075,0.00016885977,0.0007396905,0.0036782988,0.00032303424,0.8846376,0.008669051,0.0908212,0.007629762,0.00011199995],"about_ca_topic_score_codex":0.0010077553,"about_ca_topic_score_gemma":0.0015396416,"teacher_disagreement_score":0.005180415,"about_ca_system_score_codex":0.00040257652,"about_ca_system_score_gemma":0.0018241032,"threshold_uncertainty_score":0.027396977},"labels":[],"label_agreement":null},{"id":"W2115866740","doi":"10.1145/1008694.1008705","title":"An associative classifier based on positive and negative rules","year":2004,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":106,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Associative property; Association rule learning; Classifier (UML); Computer science; Negation; Artificial intelligence; Correlation; Data mining; Machine learning; Pattern recognition (psychology); Mathematics","score_opus":0.013254721964891894,"score_gpt":0.26462933096591834,"score_spread":0.25137460900102643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115866740","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05965774,0.0010775031,0.92437583,0.0011425314,0.0006157666,0.00047745628,0.0006010299,0.0019627842,0.010089479],"genre_scores_gemma":[0.400057,0.00072640524,0.58488417,0.000995758,0.0007829133,0.0006193856,0.0015692433,0.00016260559,0.0102024805],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.994822,0.00084296643,0.0005311761,0.00091842527,0.002594553,0.00029084005],"domain_scores_gemma":[0.9867606,0.006343564,0.00084802357,0.0014014939,0.0042126398,0.00043370365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006198284,0.0010858052,0.0020123397,0.004335983,0.0016481047,0.0027832016,0.0025936957,0.002225543,0.0025908486],"category_scores_gemma":[0.019581277,0.00044202796,0.0010717656,0.002814491,0.0012933655,0.0047539636,0.001403352,0.0021401779,0.0020809844],"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":[0.00048395916,0.00068350043,0.023076592,0.00037386626,0.00025715283,0.000675532,0.00026252953,0.032529857,0.009630866,0.0390249,0.020424917,0.87257636],"study_design_scores_gemma":[0.00009479286,0.0003671423,0.0033037323,0.00013314473,0.0002832403,0.0016533785,0.00014023752,0.8888863,0.017480051,0.06825415,0.019292044,0.000111894355],"about_ca_topic_score_codex":0.0018984571,"about_ca_topic_score_gemma":0.0029823852,"teacher_disagreement_score":0.006198284,"about_ca_system_score_codex":0.000802714,"about_ca_system_score_gemma":0.002282409,"threshold_uncertainty_score":0.03278005},"labels":[],"label_agreement":null},{"id":"W2116064560","doi":"10.1007/s10618-005-0248-3","title":"Mining Web Log Sequential Patterns with Position Coded Pre-Order Linked WAP-Tree","year":2005,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":131,"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":"Computer science; Web log analysis software; Tree (set theory); Trie; Suffix tree; Prefix; Data mining; Subsequence; Web mining; Node (physics); Web server; Fractal tree index; Tree structure; Interval tree; Web page; Data structure; Algorithm; The Internet; World Wide Web; Mathematics; Binary tree; Static web page","score_opus":0.03043223887843423,"score_gpt":0.2874098398765441,"score_spread":0.2569776009981099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116064560","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5177175,0.00056133926,0.45766583,0.00047686562,0.00014078627,0.0006583247,0.010545723,0.007308394,0.004925318],"genre_scores_gemma":[0.7005172,0.00019770915,0.28464252,0.000082408464,0.000044670018,0.00027089263,0.011100974,0.00018437025,0.0029592593],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993704,0.000074171476,0.00007431507,0.00012425223,0.00027375732,0.00008307207],"domain_scores_gemma":[0.997134,0.0011070856,0.0003126317,0.00050053734,0.00078559556,0.00016017385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005223575,0.00040836495,0.0005828464,0.004766338,0.0008250256,0.001168149,0.0009660025,0.0007547274,0.0019632874],"category_scores_gemma":[0.0053360937,0.00033619313,0.0007076811,0.004870439,0.00032884185,0.0016362119,0.00067967025,0.00075847376,0.0010580372],"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":[0.001794458,0.0012917713,0.1252399,0.00078961236,0.00029643154,0.0027029128,0.00059119245,0.07023752,0.027731208,0.01470895,0.017101133,0.737515],"study_design_scores_gemma":[0.00007652842,0.0003251839,0.014477587,0.00008038871,0.00014697514,0.0011535183,0.00040841402,0.93617,0.013842741,0.02474358,0.008537252,0.00003790231],"about_ca_topic_score_codex":0.0038287025,"about_ca_topic_score_gemma":0.008566475,"teacher_disagreement_score":0.004766338,"about_ca_system_score_codex":0.00041369058,"about_ca_system_score_gemma":0.0013111613,"threshold_uncertainty_score":0.0076128244},"labels":[],"label_agreement":null},{"id":"W2116316066","doi":"10.1109/icde.2009.157","title":"Mining of Frequent Itemsets from Streams of Uncertain Data","year":2009,"lang":"en","type":"article","venue":"Proceedings - International Conference on Data Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":97,"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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data stream mining; Data mining; Database transaction; Uncertain data; Flood myth; Tree (set theory); Transaction data; Database; Mathematics","score_opus":0.11409841460705344,"score_gpt":0.32357743779976694,"score_spread":0.2094790231927135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116316066","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08341703,0.0010155215,0.9126935,0.0003912872,0.000086216154,0.00021186964,0.0011834125,0.0004655737,0.00053566816],"genre_scores_gemma":[0.48404828,0.0011401793,0.5100845,0.00012513115,0.00017783645,0.00033055502,0.0036602893,0.000048949376,0.00038422915],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99661213,0.0007514214,0.0006709694,0.0006062409,0.0011285595,0.00023067278],"domain_scores_gemma":[0.98590904,0.009822315,0.0015314382,0.00084514543,0.0016365069,0.0002556141],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030915341,0.0009749802,0.0021268083,0.004329746,0.0010757538,0.0020960446,0.0017361871,0.001558174,0.00044299394],"category_scores_gemma":[0.019183,0.00060643913,0.0015260144,0.004682029,0.00052393746,0.0033179214,0.0011571276,0.0011443387,0.00030139004],"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":[0.0015785302,0.00054892857,0.049124587,0.0011417557,0.0010430269,0.0064692027,0.0015967367,0.3677591,0.01634936,0.020132782,0.005882692,0.52837324],"study_design_scores_gemma":[0.00004323221,0.00013283176,0.0029181144,0.00007636431,0.00010899996,0.0010097004,0.00037009266,0.96316165,0.0052155484,0.024777256,0.002141156,0.0000451528],"about_ca_topic_score_codex":0.0012354184,"about_ca_topic_score_gemma":0.0010858523,"teacher_disagreement_score":0.004329746,"about_ca_system_score_codex":0.00048715447,"about_ca_system_score_gemma":0.0009031977,"threshold_uncertainty_score":0.016349792},"labels":[],"label_agreement":null},{"id":"W2117039206","doi":"10.1109/wi.2005.77","title":"Information Domain Modeling for Adaptive Web Systems","year":2005,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Domain (mathematical analysis); Data mining; Sequence (biology); Adaptive system; Domain model; Web application; Web page; Information retrieval; World Wide Web; Artificial intelligence; Domain knowledge","score_opus":0.023512140977256245,"score_gpt":0.24661499290537978,"score_spread":0.22310285192812354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117039206","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034362006,0.00027649725,0.990182,0.00039529387,0.000046320274,0.00011046697,0.00034940997,0.0009151839,0.0042887265],"genre_scores_gemma":[0.24198857,0.0016050257,0.74716675,0.00030381986,0.00014139139,0.00078855286,0.0022892808,0.0002814863,0.005435113],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988205,0.0004159065,0.000115132694,0.00018482159,0.00038745164,0.000076162105],"domain_scores_gemma":[0.998323,0.0008037601,0.00013164911,0.00038401093,0.00028878034,0.0000687126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014797604,0.00069593947,0.0006417992,0.0016087183,0.00071791856,0.0025942496,0.0014563799,0.0010567347,0.0032154603],"category_scores_gemma":[0.0050482466,0.00040737653,0.0012756239,0.0013246168,0.0006626889,0.0033040314,0.0013070486,0.0017007435,0.0013532941],"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":[0.00007217856,0.00011118683,0.0017535463,0.00022249734,0.00008030107,0.000335902,0.000401296,0.45809895,0.0018621908,0.42468792,0.009076941,0.10329711],"study_design_scores_gemma":[0.00000963079,0.000011773981,0.00011485591,0.000033737604,0.0000142228155,0.000068488494,0.000052040083,0.8925458,0.0005177966,0.089454226,0.017165333,0.000012013166],"about_ca_topic_score_codex":0.0071714986,"about_ca_topic_score_gemma":0.004627453,"teacher_disagreement_score":0.0071714986,"about_ca_system_score_codex":0.0014190767,"about_ca_system_score_gemma":0.0016094261,"threshold_uncertainty_score":0.014259517},"labels":[],"label_agreement":null},{"id":"W2117247700","doi":"","title":"Mining Multi-Dimensional Constrained Gradients in Data Cubes","year":2001,"lang":"en","type":"article","venue":"Journal of Bioresource Management","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computation; Computer science; Scalability; Pruning; Tree (set theory); Measure (data warehouse); Big data; Algorithm; Process (computing); Data mining; Mathematics; Combinatorics; Database","score_opus":0.048030887544727424,"score_gpt":0.28894505973409984,"score_spread":0.24091417218937242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117247700","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0447672,0.0029748182,0.94801325,0.001219626,0.00008413152,0.00014658936,0.0011921196,0.0008820208,0.00072024285],"genre_scores_gemma":[0.28407902,0.002778054,0.70776844,0.00031278454,0.00023371518,0.00037932443,0.0030045535,0.00017690283,0.0012672016],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99788123,0.00043119868,0.00027292507,0.00034772832,0.0009459978,0.000120974706],"domain_scores_gemma":[0.99408036,0.0034112544,0.0007468696,0.0005789448,0.00095247483,0.00022991921],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021835463,0.001283275,0.0028674353,0.0024613135,0.0006035494,0.0027816165,0.002771813,0.0017438403,0.0014320879],"category_scores_gemma":[0.009325916,0.00097209186,0.0014258913,0.0065605994,0.0012286935,0.0032967676,0.0025755358,0.0018892625,0.00037745526],"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":[0.00031793484,0.00032268974,0.01538274,0.0011578711,0.00034024403,0.0004077531,0.00032922562,0.5790897,0.005515006,0.03157277,0.008566523,0.35699755],"study_design_scores_gemma":[0.000012963224,0.00004968,0.00084090274,0.000044724984,0.000020279645,0.0000870776,0.000066963534,0.96821904,0.0013580811,0.027638715,0.0016448108,0.000016840626],"about_ca_topic_score_codex":0.0030808377,"about_ca_topic_score_gemma":0.0036214618,"teacher_disagreement_score":0.0030808377,"about_ca_system_score_codex":0.00064846314,"about_ca_system_score_gemma":0.0010992676,"threshold_uncertainty_score":0.011547804},"labels":[],"label_agreement":null},{"id":"W2117302875","doi":"10.1109/icde.2005.127","title":"Scrutinizing Frequent Pattern Discovery Performance","year":2005,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Benchmarking; Testbed; Computer science; Implementation; Software deployment; Data science; Performance improvement; Data mining; Software engineering; World Wide Web; Engineering","score_opus":0.016506591423710783,"score_gpt":0.23484229663420791,"score_spread":0.21833570521049714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117302875","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8692591,0.0023955242,0.11240661,0.0023019235,0.00028447757,0.00030001663,0.001854693,0.0036485149,0.0075490484],"genre_scores_gemma":[0.9342997,0.0005084882,0.061095532,0.00014804697,0.00012906114,0.00015846266,0.0028102067,0.00026480315,0.0005856597],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9648353,0.01418182,0.003614583,0.0047414484,0.011233678,0.0013932562],"domain_scores_gemma":[0.83439946,0.119627565,0.0056124907,0.019753912,0.01935218,0.0012543736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.029803082,0.0010731596,0.0012278417,0.005085757,0.0012498249,0.0037009956,0.0019274958,0.0016167007,0.0012364468],"category_scores_gemma":[0.16161086,0.00037905198,0.00075624214,0.0070032515,0.0012204488,0.006079181,0.0017285034,0.0012617907,0.00094103086],"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":[0.0026279585,0.001538875,0.18310805,0.0013247398,0.0011897198,0.0005139547,0.0013856513,0.18733832,0.028718235,0.020454347,0.011524432,0.5602758],"study_design_scores_gemma":[0.00024026663,0.0028749174,0.086574905,0.00016157064,0.00022050375,0.0010969247,0.002114309,0.811298,0.05624291,0.028304514,0.010669213,0.00020200801],"about_ca_topic_score_codex":0.0023084306,"about_ca_topic_score_gemma":0.001219852,"teacher_disagreement_score":0.029803082,"about_ca_system_score_codex":0.0014582034,"about_ca_system_score_gemma":0.001724111,"threshold_uncertainty_score":0.15761566},"labels":[],"label_agreement":null},{"id":"W2117423052","doi":"10.1109/icdm.2002.1183881","title":"Text document categorization by term association","year":2003,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":224,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Classifier (UML); Categorization; Artificial intelligence; Text categorization; Association rule learning; Machine learning; Natural language processing; Data mining; Information retrieval; Pattern recognition (psychology)","score_opus":0.005463032048834978,"score_gpt":0.22543330126779562,"score_spread":0.21997026921896065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117423052","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025315357,0.004801477,0.947479,0.0006406003,0.00056370115,0.0020409557,0.0059087877,0.0072418633,0.006008335],"genre_scores_gemma":[0.043516263,0.0013632723,0.94361585,0.00011439679,0.00025541778,0.00090653566,0.0068492163,0.00021731855,0.0031616814],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969261,0.00045661186,0.000495104,0.0008055436,0.0011519804,0.00016464706],"domain_scores_gemma":[0.996585,0.0013248369,0.00047819014,0.0005127912,0.000969644,0.00012953627],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019659176,0.0012888593,0.0021043771,0.018878058,0.0013598436,0.003091806,0.0016305752,0.0013453241,0.003847195],"category_scores_gemma":[0.008328383,0.0003848431,0.0019523537,0.01496377,0.00091729156,0.003989653,0.0014708688,0.001343699,0.0065180296],"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":[0.00018509678,0.00023424595,0.002929035,0.0008393743,0.00016793219,0.00019792117,0.00022773417,0.003810916,0.016873462,0.008394107,0.019697167,0.94644296],"study_design_scores_gemma":[0.0002499652,0.00092317804,0.016448963,0.0007967952,0.000677807,0.0056775985,0.0011930838,0.4947587,0.07439812,0.1688602,0.23558979,0.00042579064],"about_ca_topic_score_codex":0.0020967259,"about_ca_topic_score_gemma":0.0020861044,"teacher_disagreement_score":0.018878058,"about_ca_system_score_codex":0.00081521715,"about_ca_system_score_gemma":0.0016451159,"threshold_uncertainty_score":0.012870133},"labels":[],"label_agreement":null},{"id":"W2119043676","doi":"","title":"Using Heuristics to Speed Up Frequent Pattern Mining","year":2008,"lang":"fr","type":"article","venue":"Les Cahiers du GERAD","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Heuristics; Data mining; Computer science; Subgraph isomorphism problem; Simple (philosophy); Heuristic; Space (punctuation); Machine learning; Artificial intelligence; Theoretical computer science","score_opus":0.0880807771086874,"score_gpt":0.2864859583849585,"score_spread":0.1984051812762711,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119043676","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022995569,0.00088162476,0.9682095,0.00032693087,0.00018849572,0.0004708905,0.00040502925,0.004831808,0.0016901015],"genre_scores_gemma":[0.06021503,0.00042731882,0.936504,0.00020899622,0.000089221736,0.00029281172,0.0011358492,0.00028229872,0.0008445399],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99644524,0.0012493704,0.00037539582,0.0005054621,0.0011895053,0.00023510274],"domain_scores_gemma":[0.9761872,0.018412514,0.0009548619,0.0020074144,0.0021912397,0.00024684146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042616045,0.0017801302,0.001831701,0.0056046387,0.00083880505,0.0019822943,0.0024545908,0.0013734448,0.004273107],"category_scores_gemma":[0.036489006,0.0010779338,0.0010746501,0.005000445,0.0006192839,0.0036883892,0.0013143996,0.002014116,0.0029380373],"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":[0.0005348856,0.0005066243,0.006893758,0.0009976638,0.00038945128,0.00060537,0.00042569157,0.05819403,0.0115549015,0.023345577,0.013879939,0.88267213],"study_design_scores_gemma":[0.00048953894,0.0005248426,0.0029106608,0.00030769777,0.00035101536,0.0017807985,0.0004531482,0.8417721,0.020897144,0.09548169,0.034887683,0.0001437619],"about_ca_topic_score_codex":0.0021609622,"about_ca_topic_score_gemma":0.0031938155,"teacher_disagreement_score":0.0056046387,"about_ca_system_score_codex":0.0005885681,"about_ca_system_score_gemma":0.0019036153,"threshold_uncertainty_score":0.022537768},"labels":[],"label_agreement":null},{"id":"W2119639303","doi":"10.20381/ruor-6141","title":"Location Aware Multi-criteria Recommender System for Intelligent Data Mining","year":2012,"lang":"en","type":"dissertation","venue":"uO Research (University of Ottawa)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Recommender system; Computer science; Data mining; Data science; Information retrieval","score_opus":0.2539884411384292,"score_gpt":0.41043835260390504,"score_spread":0.15644991146547582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119639303","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012599206,0.0030112523,0.9778256,0.00066872215,0.00022475029,0.0002387547,0.0005317911,0.0011270904,0.0037729028],"genre_scores_gemma":[0.31433618,0.0027727268,0.67297196,0.00041703382,0.00023598978,0.0005691076,0.0015131184,0.000071391,0.0071124407],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99786735,0.00064804836,0.0002371803,0.00063356804,0.0004777882,0.00013596396],"domain_scores_gemma":[0.9982705,0.0006250821,0.00014408417,0.00025051628,0.0006356528,0.000074202835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021459095,0.0008217543,0.0019850575,0.0016685971,0.000981653,0.0015476297,0.0025857696,0.0018029681,0.0027703147],"category_scores_gemma":[0.00423864,0.00048092284,0.0017755387,0.0025089493,0.00030926603,0.0015362597,0.0012048561,0.001356967,0.0018045418],"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":[0.0004704308,0.0004854625,0.01093141,0.0011817706,0.0007643207,0.0011902449,0.0005909484,0.35930395,0.018952882,0.024684962,0.023846254,0.5575974],"study_design_scores_gemma":[0.0000309843,0.000105898456,0.0012596244,0.000065375374,0.0000820778,0.00026208223,0.00009737151,0.9820618,0.0016816667,0.005398195,0.008912041,0.000042841886],"about_ca_topic_score_codex":0.013775062,"about_ca_topic_score_gemma":0.015634121,"teacher_disagreement_score":0.013775062,"about_ca_system_score_codex":0.0008374258,"about_ca_system_score_gemma":0.0011845456,"threshold_uncertainty_score":0.027389765},"labels":[],"label_agreement":null},{"id":"W2119940294","doi":"10.1109/itcc.2004.1286666","title":"Mining user navigational patterns in dynamically changing environments","year":2004,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Web mining; Semantics (computer science); Domain (mathematical analysis); Information retrieval; Data mining; Web page; World Wide Web; Human–computer interaction; Programming language","score_opus":0.009425187136717873,"score_gpt":0.23375339301944548,"score_spread":0.22432820588272762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119940294","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86383975,0.0004467864,0.13047579,0.00048960006,0.000022705062,0.00012423865,0.002167144,0.0009969969,0.0014370331],"genre_scores_gemma":[0.9054003,0.00028343298,0.09067724,0.000049318503,0.000016049993,0.00007093119,0.0027602282,0.00004495086,0.0006974323],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989492,0.00025546915,0.00010677005,0.0002904493,0.00028957694,0.00010849995],"domain_scores_gemma":[0.99600285,0.0020966278,0.0006213318,0.0004448668,0.00061293226,0.00022147477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008359171,0.0004587701,0.00059843203,0.0032334512,0.00068102474,0.0014192327,0.0009543424,0.00092268514,0.00038649666],"category_scores_gemma":[0.005593022,0.00036842944,0.00051800936,0.003591624,0.00053041393,0.0018554474,0.000788743,0.00063673506,0.0003312884],"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":[0.00066812255,0.00062902254,0.6068461,0.00041692064,0.00033128101,0.0012007195,0.0024093955,0.05824607,0.015069361,0.007972372,0.0038255637,0.3023851],"study_design_scores_gemma":[0.000043847598,0.00030597905,0.13514481,0.00007589203,0.00018685815,0.001334163,0.0028258592,0.8161836,0.014472297,0.022644592,0.006696729,0.00008535944],"about_ca_topic_score_codex":0.007849421,"about_ca_topic_score_gemma":0.016236205,"teacher_disagreement_score":0.007849421,"about_ca_system_score_codex":0.00041747652,"about_ca_system_score_gemma":0.00078379724,"threshold_uncertainty_score":0.015607476},"labels":[],"label_agreement":null},{"id":"W2120557245","doi":"10.1007/978-3-642-01091-0_8","title":"Multi-value Association Patterns and Data Mining","year":2009,"lang":"en","type":"book-chapter","venue":"Studies in computational intelligence","topic":"Data Mining Algorithms 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 Guelph","funders":"","keywords":"Null hypothesis; Null (SQL); Tuple; Statistical hypothesis testing; Value (mathematics); Null model; Set (abstract data type); Event (particle physics); p-value; Mathematics; Alternative hypothesis; Data mining; Association (psychology); Statistics; Computer science; Pattern recognition (psychology); Artificial intelligence; Combinatorics; Discrete mathematics; Psychology","score_opus":0.1787754505042847,"score_gpt":0.4013187604246597,"score_spread":0.222543309920375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120557245","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011423261,0.08224364,0.85530263,0.005784102,0.0022074135,0.00012273299,0.0005855359,0.00073455437,0.04159609],"genre_scores_gemma":[0.15992938,0.08268143,0.70001423,0.0017712013,0.0031530033,0.00035745095,0.0017900025,0.0002549688,0.050048288],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99892265,0.00023181694,0.000101690544,0.00020867257,0.0004971929,0.00003797478],"domain_scores_gemma":[0.9963188,0.0027235732,0.00019920472,0.0003736856,0.00032381056,0.00006092755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014188557,0.0008160107,0.0009286728,0.0019659596,0.00045369874,0.0020952956,0.0014945129,0.00092284335,0.0060970597],"category_scores_gemma":[0.0073660347,0.0005318193,0.0005776098,0.007982378,0.0013705734,0.0061663757,0.0012219499,0.0020088253,0.0027566315],"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":[0.000058485435,0.0000735717,0.0018213938,0.00095583906,0.000091552545,0.0003211571,0.00028031383,0.004089346,0.00084510405,0.29868037,0.025990993,0.6667919],"study_design_scores_gemma":[0.000012649848,0.000043275864,0.00095965527,0.00030471614,0.000045676526,0.0014699348,0.00017130896,0.026475715,0.001052342,0.88004375,0.08939596,0.000024985766],"about_ca_topic_score_codex":0.0003079127,"about_ca_topic_score_gemma":0.00035805788,"teacher_disagreement_score":0.0060970597,"about_ca_system_score_codex":0.0004359629,"about_ca_system_score_gemma":0.00059184287,"threshold_uncertainty_score":0.02039665},"labels":[],"label_agreement":null},{"id":"W2120610831","doi":"10.1109/icdm.2003.1250942","title":"MPIS: maximal-profit item selection with cross-selling considerations","year":2004,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Association rule learning; Profit (economics); Computer science; Selection (genetic algorithm); Quadratic equation; Heuristic; Quadratic programming; Mathematical optimization; Data mining; Artificial intelligence; Mathematics; Economics; Microeconomics","score_opus":0.0219841248234083,"score_gpt":0.2702095731798626,"score_spread":0.2482254483564543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120610831","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034654967,0.0008908169,0.9561667,0.0012079591,0.00012356638,0.00034592708,0.00033075397,0.001064795,0.0052145887],"genre_scores_gemma":[0.48611197,0.00059061317,0.5029255,0.00068534026,0.00045986168,0.00045658552,0.0010199243,0.00014737292,0.0076028174],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962799,0.0014781948,0.00022349224,0.0005132658,0.0012462098,0.0002589158],"domain_scores_gemma":[0.99393374,0.0038889064,0.000503022,0.0007984763,0.00063230307,0.00024350944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00508553,0.0011546324,0.0027122458,0.0019607514,0.0010615016,0.0017001713,0.0034411063,0.0015298292,0.0055229496],"category_scores_gemma":[0.011439016,0.0009021616,0.0013415446,0.003993592,0.0011346148,0.0031814717,0.0020029969,0.0017420581,0.001253597],"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":[0.0011099736,0.00087856484,0.009707157,0.0007051618,0.00041596667,0.0013060711,0.00020695853,0.3792818,0.004357841,0.047818203,0.022213884,0.5319984],"study_design_scores_gemma":[0.0000996744,0.00029551116,0.0011110955,0.00003100605,0.00006136096,0.0006517929,0.000058191035,0.9443521,0.0025354645,0.04670358,0.004076226,0.000024065923],"about_ca_topic_score_codex":0.0011069656,"about_ca_topic_score_gemma":0.0013683302,"teacher_disagreement_score":0.0055229496,"about_ca_system_score_codex":0.0009182618,"about_ca_system_score_gemma":0.0018458649,"threshold_uncertainty_score":0.026895165},"labels":[],"label_agreement":null},{"id":"W2120676662","doi":"10.1145/1008694.1008706","title":"COFI approach for mining frequent itemsets revisited","year":2004,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Oracle; Computer science; Data mining; Algorithm","score_opus":0.030746748873414515,"score_gpt":0.2726599395540408,"score_spread":0.24191319068062625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120676662","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022905054,0.001640569,0.9688673,0.00038072228,0.00013218113,0.00022402724,0.0008340158,0.0028377865,0.0021783572],"genre_scores_gemma":[0.108229935,0.000523834,0.88609535,0.000208677,0.00013828294,0.0002981689,0.0022243133,0.00013265607,0.0021488604],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961428,0.0006192394,0.00034290963,0.0010747281,0.0015171106,0.00030313822],"domain_scores_gemma":[0.99119776,0.0043794625,0.0006705599,0.0014636487,0.00203143,0.0002570804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033642438,0.0011303314,0.0015815625,0.008249343,0.0013250173,0.0026333868,0.0036322381,0.0024950018,0.002774461],"category_scores_gemma":[0.01553698,0.0006728374,0.001536779,0.008513005,0.0008108025,0.0031614858,0.0014992116,0.0023293553,0.0017340818],"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":[0.00058658747,0.00025935922,0.01350188,0.0005907762,0.00039358044,0.00065535895,0.00043314538,0.023941113,0.0107071325,0.022727791,0.011472488,0.9147308],"study_design_scores_gemma":[0.00013268836,0.00047323428,0.006536861,0.00018848569,0.00028242913,0.005622865,0.00044998413,0.85596234,0.032038145,0.048107713,0.050045677,0.00015961584],"about_ca_topic_score_codex":0.0029964535,"about_ca_topic_score_gemma":0.0038396537,"teacher_disagreement_score":0.008249343,"about_ca_system_score_codex":0.0010282226,"about_ca_system_score_gemma":0.002083051,"threshold_uncertainty_score":0.017792046},"labels":[],"label_agreement":null},{"id":"W2120896220","doi":"10.1109/icnc.2011.6022593","title":"Towards an optimal classification model against imbalanced data for Customer Relationship Management","year":2011,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Customer relationship management; Computer science; Data mining; Task (project management); Identification (biology); Domain (mathematical analysis); CONTEST; Data quality; Quality (philosophy); Data modeling; Data science; Database; Engineering; Systems engineering; Mathematics; Operations management","score_opus":0.20631776086197628,"score_gpt":0.3370690664338736,"score_spread":0.1307513055718973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120896220","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04023984,0.00072805147,0.9549641,0.0013611616,0.00013564894,0.00013004872,0.00036380906,0.0011471938,0.00093011506],"genre_scores_gemma":[0.558202,0.00075823057,0.4339129,0.0007345408,0.00047826,0.00048691905,0.002672228,0.00026940662,0.0024855072],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99637127,0.0015218701,0.00028778703,0.0007892124,0.0007088833,0.00032100588],"domain_scores_gemma":[0.9912237,0.0049618734,0.00087309687,0.0008588053,0.0018526929,0.00022986361],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012095239,0.0011197851,0.0024477874,0.0032745805,0.000998556,0.002972885,0.0031488636,0.0024458682,0.0013535885],"category_scores_gemma":[0.02017664,0.0006030357,0.0011517779,0.0031708677,0.00081427355,0.0049282084,0.001715058,0.0033892905,0.0016066135],"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":[0.000579382,0.0005618404,0.011274077,0.00014581629,0.0002445583,0.00010960462,0.0002532464,0.47787508,0.0021408214,0.0115394145,0.011573401,0.4837028],"study_design_scores_gemma":[0.000006706222,0.00002151727,0.00030833695,0.0000091272395,0.000008037427,0.000010872564,0.000023075681,0.9936724,0.00023974612,0.0053317146,0.0003640342,0.0000044651265],"about_ca_topic_score_codex":0.005026823,"about_ca_topic_score_gemma":0.0032286043,"teacher_disagreement_score":0.012095239,"about_ca_system_score_codex":0.0016091234,"about_ca_system_score_gemma":0.0016719206,"threshold_uncertainty_score":0.06396651},"labels":[],"label_agreement":null},{"id":"W2120943353","doi":"10.1007/3-540-47922-8_29","title":"RFCT: An Association-Based Causality Miner","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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 Regina","funders":"","keywords":"Causality (physics); Computer science; Association rule learning; Association (psychology); Raw data; Causal model; Data mining; Artificial intelligence; Granger causality; Causal analysis; Data science; Machine learning; Econometrics; Programming language; Statistics; Psychology; Mathematics","score_opus":0.02304092670617294,"score_gpt":0.2579760302973366,"score_spread":0.23493510359116368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120943353","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0059605124,0.00078149943,0.96599233,0.00029502102,0.00019044938,0.0003602027,0.0049204887,0.019950543,0.0015489636],"genre_scores_gemma":[0.058769975,0.0006577783,0.9256589,0.0002833372,0.00016043306,0.00043563155,0.007595296,0.00090186734,0.005536739],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979388,0.00040818864,0.00021195297,0.00046506213,0.0008812218,0.000094708645],"domain_scores_gemma":[0.99556667,0.002377321,0.00031243096,0.0008240547,0.00076187745,0.0001574726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032521884,0.001767151,0.0020649238,0.0054841465,0.00093435525,0.0020964195,0.0038081992,0.0016413485,0.01120153],"category_scores_gemma":[0.013519984,0.0012136764,0.0020272445,0.0037818647,0.0005622003,0.0028416677,0.002323797,0.00232113,0.005787151],"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":[0.00078378397,0.00049010845,0.0110716885,0.0010872785,0.0008265428,0.00070813403,0.00017458748,0.048595436,0.0077372314,0.011553177,0.055067644,0.86190444],"study_design_scores_gemma":[0.000438085,0.00040798433,0.0026856263,0.0002394339,0.00070388237,0.001942442,0.00009774625,0.8633172,0.01600048,0.06264774,0.051389564,0.00012981967],"about_ca_topic_score_codex":0.0033061914,"about_ca_topic_score_gemma":0.0077234074,"teacher_disagreement_score":0.01120153,"about_ca_system_score_codex":0.0003411594,"about_ca_system_score_gemma":0.0029432673,"threshold_uncertainty_score":0.037472844},"labels":[],"label_agreement":null},{"id":"W2121550967","doi":"10.1007/s10619-006-0445-0","title":"Parallel Bifold: Large-scale parallel pattern mining with constraints","year":2006,"lang":"en","type":"article","venue":"Distributed and Parallel Databases","topic":"Data Mining Algorithms and Applications","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 Alberta","funders":"","keywords":"Computer science; Data mining; Set (abstract data type); Scale (ratio); Cluster (spacecraft); Space (punctuation); Geography","score_opus":0.01781232993566086,"score_gpt":0.2489065911592234,"score_spread":0.23109426122356252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121550967","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019468617,0.0008050703,0.9437988,0.0006642881,0.00019621196,0.0004731791,0.0038345319,0.02704843,0.003710785],"genre_scores_gemma":[0.110424764,0.00040448748,0.8775632,0.00024410782,0.00009568212,0.00063596136,0.006436954,0.0013270769,0.0028677096],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986268,0.00028451154,0.00014897497,0.00027066434,0.00054857566,0.00012048103],"domain_scores_gemma":[0.99631953,0.0015542813,0.00020480377,0.0010275074,0.0006662662,0.00022757701],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019613293,0.0017196579,0.0016444339,0.002001039,0.001206923,0.0024106037,0.004040366,0.0007619838,0.010435264],"category_scores_gemma":[0.009506075,0.0010920162,0.0009877778,0.0041488,0.0006855054,0.0034221772,0.0024251381,0.0017678519,0.0026872645],"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":[0.0022353253,0.0005070019,0.0052324906,0.0012375221,0.00036473095,0.00044202304,0.00015020896,0.09284389,0.012479699,0.024504054,0.09135471,0.7686483],"study_design_scores_gemma":[0.00043839813,0.0001251833,0.0006974468,0.000035681667,0.00008355484,0.0002540932,0.0000601481,0.9346517,0.011299043,0.037888125,0.014425162,0.000041527706],"about_ca_topic_score_codex":0.0064712507,"about_ca_topic_score_gemma":0.012514701,"teacher_disagreement_score":0.010435264,"about_ca_system_score_codex":0.0006957521,"about_ca_system_score_gemma":0.003569142,"threshold_uncertainty_score":0.034909427},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01438856,0.00088106876,0.9580609,0.00025127575,0.0001759569,0.0002345753,0.0020679582,0.022282215,0.0016574081],"genre_scores_gemma":[0.08911966,0.00045252586,0.9009691,0.00023536972,0.00012629229,0.00044586588,0.004239587,0.0007699828,0.0036416184],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987141,0.0002449017,0.00015833213,0.00025620675,0.00055089116,0.0000755943],"domain_scores_gemma":[0.9978886,0.0011380079,0.00013920755,0.00045389243,0.000289117,0.00009127304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010314083,0.0011404803,0.0016696063,0.004487724,0.0007601981,0.0017723166,0.0023994548,0.0009681152,0.00789005],"category_scores_gemma":[0.0057793283,0.00085657986,0.0010423523,0.004902567,0.00045834915,0.0030681125,0.002471954,0.0011623717,0.0037253331],"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":[0.0010417092,0.00023318763,0.0026804805,0.0006447144,0.0002740172,0.00030765217,0.00013067911,0.008301948,0.015638484,0.0053025954,0.028524535,0.93692],"study_design_scores_gemma":[0.00089753215,0.0007380916,0.0027541765,0.00012330033,0.0005138077,0.002203855,0.0003142006,0.8152127,0.04202738,0.06030845,0.07475117,0.00015531333],"about_ca_topic_score_codex":0.0010151762,"about_ca_topic_score_gemma":0.0022993411,"teacher_disagreement_score":0.00789005,"about_ca_system_score_codex":0.0003044397,"about_ca_system_score_gemma":0.0015245068,"threshold_uncertainty_score":0.026394844},"labels":[],"label_agreement":null},{"id":"W2121897210","doi":"10.1109/tai.2002.1180827","title":"TimeSleuth: a tool for discovering causal and temporal rules","year":2003,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Causality (physics); Association rule learning; Bayesian network; Artificial intelligence; Data mining; Tree (set theory); Preprocessor; Machine learning; Data science; Mathematics","score_opus":0.02023488657022956,"score_gpt":0.2633571375755482,"score_spread":0.24312225100531862,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121897210","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033299343,0.00025101204,0.93508863,0.00031592706,0.000081737475,0.00039854267,0.0065996367,0.050424557,0.0035099727],"genre_scores_gemma":[0.030467184,0.00036628288,0.9540748,0.00015829927,0.0000434935,0.0007150355,0.008677642,0.0019101823,0.0035872164],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976628,0.0004758059,0.0003725745,0.0004687255,0.0008997702,0.00012028853],"domain_scores_gemma":[0.9885422,0.007988709,0.0013244861,0.0010587394,0.00089343404,0.00019241306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035682383,0.0021191773,0.0009604302,0.0061474247,0.0014626497,0.002520977,0.0024902166,0.0016285512,0.021686152],"category_scores_gemma":[0.018561395,0.001609728,0.002791549,0.003324056,0.0011071496,0.005816777,0.0023466048,0.0023044792,0.0047227712],"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":[0.00073875993,0.0003019837,0.010370826,0.004202999,0.00064905925,0.0029353797,0.0022474946,0.070170835,0.009272088,0.13091671,0.14010952,0.62808436],"study_design_scores_gemma":[0.0002474384,0.00022717204,0.002355322,0.0007326122,0.00026554038,0.0018051622,0.00046706526,0.52510285,0.022130381,0.16209745,0.28431994,0.0002491283],"about_ca_topic_score_codex":0.0066900244,"about_ca_topic_score_gemma":0.01215658,"teacher_disagreement_score":0.021686152,"about_ca_system_score_codex":0.0009542497,"about_ca_system_score_gemma":0.0035949892,"threshold_uncertainty_score":0.072547436},"labels":[],"label_agreement":null},{"id":"W2122509399","doi":"","title":"Data Driven Research at LIS: the Laboratory of Information Systems at UNICAMP","year":2011,"lang":"en","type":"article","venue":"Cadernos de Linguística e Teoria da Literatura (Universidade Federal de Minas Gerais)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Library science; Multidisciplinary approach; Information system; Information science; Computer science; Sociology; Engineering; Social science","score_opus":0.07584052084699909,"score_gpt":0.3016183514608213,"score_spread":0.22577783061382217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122509399","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02965483,0.143463,0.28938654,0.17051591,0.008305854,0.0008180951,0.012002159,0.020042386,0.32581127],"genre_scores_gemma":[0.40802383,0.0889217,0.27671918,0.011103,0.00551144,0.0029327855,0.011823416,0.009587412,0.18537721],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9737716,0.011912148,0.0019815618,0.005229046,0.0056305537,0.0014750686],"domain_scores_gemma":[0.9347789,0.035655554,0.003649523,0.008998591,0.012525614,0.0043918206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010903994,0.0016294251,0.0025373755,0.009415062,0.0038053077,0.018010128,0.0030850144,0.0037677668,0.043751765],"category_scores_gemma":[0.05629737,0.0014329848,0.0011512055,0.014058338,0.0063844933,0.015097998,0.009470049,0.0042696674,0.020090096],"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":[0.00043831236,0.000121692785,0.004883537,0.0047059185,0.00015805542,0.0014370778,0.015128417,0.0020645703,0.0050126617,0.3901741,0.1811585,0.3947172],"study_design_scores_gemma":[0.00003857606,0.000103644175,0.002257914,0.0017985745,0.0000412274,0.001230713,0.0017427669,0.00360851,0.005175004,0.03546741,0.9484487,0.000086964166],"about_ca_topic_score_codex":0.010813893,"about_ca_topic_score_gemma":0.0036549552,"teacher_disagreement_score":0.043751765,"about_ca_system_score_codex":0.008776686,"about_ca_system_score_gemma":0.011572043,"threshold_uncertainty_score":0.14636427},"labels":[],"label_agreement":null},{"id":"W2123255899","doi":"10.1080/09332480.2001.10542284","title":"On the Edge: Statistics &amp; Computing","year":2001,"lang":"en","type":"article","venue":"CHANCE","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Computational statistics; Enhanced Data Rates for GSM Evolution; Statistics; Mathematics; Artificial intelligence","score_opus":0.04397246498573638,"score_gpt":0.29069031230481357,"score_spread":0.2467178473190772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123255899","genre_codex":"methods","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037941313,0.0012889777,0.5826116,0.007103742,0.0029035497,0.0007670809,0.029135404,0.27454036,0.09785507],"genre_scores_gemma":[0.03485967,0.001725835,0.68765587,0.0051470236,0.0019384571,0.0019382418,0.034198936,0.080118135,0.15241784],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981694,0.000302992,0.00017169358,0.0003305796,0.00082068454,0.00020461189],"domain_scores_gemma":[0.98345965,0.0076500215,0.00070791325,0.0032712668,0.0031567372,0.0017544011],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023554023,0.002407379,0.0023959752,0.0047413325,0.0013228202,0.00571834,0.002567476,0.0017949757,0.29309246],"category_scores_gemma":[0.041496743,0.0020341065,0.0011960372,0.0061894837,0.0012763268,0.006041265,0.0036305338,0.0048179007,0.25393736],"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":[0.00012101357,0.000061523635,0.0007271271,0.00022869358,0.000021611702,0.000080115926,0.00006214967,0.0004939004,0.0012867124,0.0077578374,0.82149076,0.16766842],"study_design_scores_gemma":[0.0003695184,0.00014207415,0.0041141952,0.0004431917,0.00008731524,0.00044652863,0.00016314625,0.04013096,0.020223532,0.1565556,0.77706766,0.00025625565],"about_ca_topic_score_codex":0.0033768967,"about_ca_topic_score_gemma":0.006254256,"teacher_disagreement_score":0.29309246,"about_ca_system_score_codex":0.0010512888,"about_ca_system_score_gemma":0.0027213308,"threshold_uncertainty_score":0.98049194},"labels":[],"label_agreement":null},{"id":"W2123405451","doi":"10.1109/cidm.2007.368862","title":"SSM : A Frequent Sequential Data Stream Patterns Miner","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Data stream mining; Computer science; Data stream; Data mining; Tree (set theory); Process (computing); Clickstream; Web server; The Internet","score_opus":0.06005905097074067,"score_gpt":0.3194850300245604,"score_spread":0.25942597905381976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123405451","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040376585,0.0005143321,0.9284793,0.00049868855,0.00013111322,0.00068985816,0.006472085,0.020789698,0.002048237],"genre_scores_gemma":[0.13166928,0.00026453106,0.85814697,0.00017892616,0.00005325692,0.0005588625,0.0066003855,0.00035340758,0.0021743968],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990332,0.00019506094,0.00013270692,0.00019022645,0.00038722937,0.0000616551],"domain_scores_gemma":[0.99814034,0.0007715317,0.00018692082,0.0003252588,0.0004705831,0.00010533687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017328284,0.000778682,0.00091844733,0.0030623612,0.0006441591,0.0011430673,0.0019467153,0.00089948974,0.0025248842],"category_scores_gemma":[0.0064996243,0.0005146455,0.00087350584,0.002800333,0.0003339018,0.0020753765,0.001396643,0.0008896489,0.0014258139],"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":[0.0011134251,0.0005266133,0.022701172,0.00069678156,0.0004366007,0.0005726018,0.00032505862,0.044076096,0.01341023,0.00783558,0.03368662,0.8746192],"study_design_scores_gemma":[0.00020776421,0.00033417172,0.002625383,0.000052726315,0.00006995881,0.0007540831,0.00012516153,0.9381098,0.017824797,0.014326895,0.025533877,0.000035241705],"about_ca_topic_score_codex":0.0016737968,"about_ca_topic_score_gemma":0.0027789753,"teacher_disagreement_score":0.0030623612,"about_ca_system_score_codex":0.00040583097,"about_ca_system_score_gemma":0.0019161262,"threshold_uncertainty_score":0.0091641545},"labels":[],"label_agreement":null},{"id":"W2123581730","doi":"10.1109/ictai.2007.86","title":"Exploratory Quantitative Contrast Set Mining: A Discretization Approach","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Contrast (vision); Categorical variable; Discretization; Ranking (information retrieval); Set (abstract data type); Association rule learning; Computer science; Data mining; Measure (data warehouse); Interval (graph theory); Mathematics; Artificial intelligence; Machine learning","score_opus":0.05002360354283416,"score_gpt":0.3009474250412551,"score_spread":0.25092382149842096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123581730","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026463179,0.00019194628,0.9713757,0.00014616296,0.000017229622,0.00013230198,0.00024206132,0.0002496606,0.0011818184],"genre_scores_gemma":[0.306785,0.00016067406,0.6915385,0.000104674116,0.000039756116,0.00027159593,0.0006359741,0.000045946166,0.000417749],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99770254,0.00075336563,0.0001988726,0.00034828746,0.00087122986,0.00012574537],"domain_scores_gemma":[0.9921325,0.0056346995,0.0005593631,0.00086044567,0.0006831358,0.00012992062],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031368032,0.0006060289,0.0011198816,0.0036041974,0.00053451094,0.001973593,0.0016970201,0.00087411946,0.0013555482],"category_scores_gemma":[0.015574287,0.0004272319,0.0009984899,0.003002511,0.0008312418,0.0019474631,0.0018894091,0.0012774592,0.00022086018],"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":[0.00064694084,0.00051691046,0.024922749,0.0006712896,0.0003469019,0.00070593675,0.0013225778,0.19901744,0.029165668,0.12216737,0.0040759095,0.6164403],"study_design_scores_gemma":[0.000058603993,0.00016751899,0.0027484722,0.000080328595,0.000059715298,0.0005549253,0.0002764356,0.9041517,0.0075327535,0.08049281,0.003827765,0.000048968923],"about_ca_topic_score_codex":0.0005667128,"about_ca_topic_score_gemma":0.00082565355,"teacher_disagreement_score":0.0036041974,"about_ca_system_score_codex":0.00068816915,"about_ca_system_score_gemma":0.00061175355,"threshold_uncertainty_score":0.016589165},"labels":[],"label_agreement":null},{"id":"W2124137508","doi":"10.1109/icdm.2006.163","title":"Turning Clusters into Patterns: Rectangle-Based Discriminative Data Description","year":2006,"lang":"en","type":"article","venue":"Proceedings","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Interpretability; Computer science; Cluster analysis; Discriminative model; Heuristic; Rectangle; Data mining; Artificial intelligence; Expressive power; Heuristics; Knowledge extraction; Machine learning; Theoretical computer science; Mathematics","score_opus":0.035933610408936105,"score_gpt":0.26433892791066943,"score_spread":0.22840531750173332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124137508","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011420306,0.00014390233,0.98591214,0.0002706663,0.000018559644,0.00008733446,0.00041101806,0.00059907517,0.0011369832],"genre_scores_gemma":[0.18430465,0.00043963603,0.8087576,0.0002692754,0.000039739003,0.00036130552,0.0028106468,0.0003886077,0.0026284747],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997118,0.0011171722,0.0002880101,0.0005936081,0.00072741136,0.00015581763],"domain_scores_gemma":[0.9910076,0.0042629205,0.0008462219,0.002767485,0.0009006972,0.00021512403],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031104302,0.00070194225,0.00070895354,0.0017191758,0.00057805894,0.0018612763,0.002488907,0.0010796629,0.003010036],"category_scores_gemma":[0.017198328,0.0006963859,0.0011026064,0.003945971,0.001816408,0.006692122,0.0026012312,0.0015643769,0.0010231691],"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":[0.0005561039,0.00015311586,0.005116382,0.0004483777,0.00007105646,0.00044602115,0.0018319386,0.1429694,0.007863881,0.42721125,0.012948173,0.40038443],"study_design_scores_gemma":[0.00005609695,0.0001352951,0.0005419168,0.000087213906,0.000034607427,0.00048182308,0.00048373587,0.7357721,0.007557037,0.23445687,0.020341022,0.00005237675],"about_ca_topic_score_codex":0.0022180714,"about_ca_topic_score_gemma":0.0020526699,"teacher_disagreement_score":0.0031104302,"about_ca_system_score_codex":0.00093747536,"about_ca_system_score_gemma":0.00095434475,"threshold_uncertainty_score":0.01644969},"labels":[],"label_agreement":null},{"id":"W2124300031","doi":"10.1109/tsmcb.2009.2024949","title":"On Utilizing Association and Interaction Concepts for Enhancing Microaggregation in Secure Statistical Databases","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Association (psychology); Database; Computer science; Association rule learning; Information retrieval; Data mining; Psychology","score_opus":0.024928359286228944,"score_gpt":0.2984764440105066,"score_spread":0.27354808472427766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124300031","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016390553,0.0005317517,0.9817063,0.000263015,0.000027677777,0.00004977009,0.000038023936,0.00019686575,0.0007959927],"genre_scores_gemma":[0.43176627,0.0012145287,0.5644923,0.00034836924,0.00029839718,0.00019993405,0.00025193053,0.00007942901,0.0013488741],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9921928,0.002547954,0.00083779957,0.00088023307,0.0032439074,0.0002973081],"domain_scores_gemma":[0.9842329,0.008612474,0.002460311,0.0031031987,0.0012938969,0.00029724374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0077068745,0.0010661945,0.0014392171,0.0028756643,0.0011046381,0.0032727197,0.0015739617,0.00088176917,0.001118784],"category_scores_gemma":[0.016823629,0.0004740375,0.0011816645,0.0046916027,0.0024748105,0.009656353,0.005829417,0.0023238952,0.0005103117],"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":[0.0005895489,0.0003327465,0.009405143,0.00032596348,0.0002505818,0.00031658477,0.0012921493,0.19438656,0.012875029,0.16780895,0.0016944173,0.6107223],"study_design_scores_gemma":[0.000030773077,0.00039093668,0.002143189,0.000061707164,0.000091710455,0.0006280037,0.00030576246,0.8712802,0.012697765,0.10469991,0.0075964397,0.000073667885],"about_ca_topic_score_codex":0.000861299,"about_ca_topic_score_gemma":0.0008407027,"teacher_disagreement_score":0.0077068745,"about_ca_system_score_codex":0.00093848165,"about_ca_system_score_gemma":0.0014251474,"threshold_uncertainty_score":0.04075837},"labels":[],"label_agreement":null},{"id":"W2124322287","doi":"10.1111/j.1467-9574.2011.00490.x","title":"Bayesian clustering with priors on partitions","year":2011,"lang":"en","type":"article","venue":"Statistica Neerlandica","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Prior probability; Bayesian probability; Partition (number theory); Posterior probability; Computer science; Stylometry; Data mining; Mathematics; Artificial intelligence; Algorithm; Machine learning","score_opus":0.025334773401883143,"score_gpt":0.23339167957134108,"score_spread":0.20805690616945793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124322287","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0064657703,0.00035407644,0.98989534,0.0004106133,0.000042038297,0.000094022726,0.00032461496,0.00021373988,0.0021997208],"genre_scores_gemma":[0.20053135,0.0010628577,0.79064447,0.00049321604,0.00035786763,0.00078215776,0.002371864,0.00031249036,0.0034436793],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98120373,0.009741288,0.0010305652,0.0047631296,0.0026606575,0.00060055126],"domain_scores_gemma":[0.9630858,0.024257576,0.0022543524,0.006661537,0.0031947717,0.00054601114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018586334,0.0016134061,0.0028569794,0.005543778,0.0029400773,0.0075551528,0.0049472977,0.0038794354,0.004192719],"category_scores_gemma":[0.07882878,0.0022276868,0.0027834387,0.005766856,0.0055964096,0.008987025,0.005925418,0.0056516137,0.0021797067],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029174495,0.000080379425,0.0041626436,0.00035252224,0.00030655102,0.00013214743,0.001221507,0.28352967,0.0009766013,0.60829383,0.0068740672,0.09377839],"study_design_scores_gemma":[0.000041402098,0.000024832838,0.0008845239,0.00011852271,0.00004269426,0.000065800254,0.000121743,0.30820423,0.0005449336,0.6853018,0.0045945775,0.000054974233],"about_ca_topic_score_codex":0.0043213507,"about_ca_topic_score_gemma":0.005977709,"teacher_disagreement_score":0.018586334,"about_ca_system_score_codex":0.0036179414,"about_ca_system_score_gemma":0.0030179538,"threshold_uncertainty_score":0.09829515},"labels":[],"label_agreement":null},{"id":"W2124422284","doi":"10.1007/3-540-44886-1_45","title":"Explanation-Oriented Association Mining Using a Combination of Unsupervised and Supervised Learning Algorithms","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Association rule learning; Association (psychology); Machine learning; Artificial intelligence; Unsupervised learning; Focus (optics); Task (project management); Simple (philosophy); Supervised learning; Process (computing); Data mining; Artificial neural network","score_opus":0.01959039365315557,"score_gpt":0.24910181309963952,"score_spread":0.22951141944648396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124422284","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005693422,0.00017952635,0.9920168,0.0001208463,0.000027607559,0.0001257382,0.00011975502,0.0009951392,0.00072114734],"genre_scores_gemma":[0.056584038,0.00018930492,0.94057286,0.00014698664,0.00008300683,0.00024350273,0.0008161755,0.00011574627,0.0012484931],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968695,0.0009826088,0.0003834573,0.00071234984,0.0009383221,0.0001137692],"domain_scores_gemma":[0.99132043,0.005543087,0.00046270931,0.0011668532,0.0013435952,0.0001633507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038194892,0.0011876571,0.0020568685,0.0037643546,0.0010322025,0.002180461,0.0027543486,0.0012709305,0.0029060843],"category_scores_gemma":[0.009175702,0.0007524058,0.001994972,0.003868191,0.00077336683,0.0031378847,0.0021902067,0.0018216218,0.0013482396],"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":[0.00022366368,0.00071450433,0.009645027,0.00043466265,0.0007082223,0.00023558953,0.00027834676,0.037096865,0.004933965,0.013479587,0.0077878754,0.9244616],"study_design_scores_gemma":[0.00008886002,0.00016084625,0.0025993283,0.000075118645,0.0003735706,0.00063009956,0.00010948121,0.9373665,0.005204046,0.048428707,0.00490075,0.00006264336],"about_ca_topic_score_codex":0.0014348507,"about_ca_topic_score_gemma":0.0039391005,"teacher_disagreement_score":0.0038194892,"about_ca_system_score_codex":0.00040677568,"about_ca_system_score_gemma":0.0017535099,"threshold_uncertainty_score":0.020199656},"labels":[],"label_agreement":null},{"id":"W2125852123","doi":"10.1109/icdm.2007.87","title":"Transitional Patterns and Their Significant Milestones","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Database transaction; Computer science; Data mining; Set (abstract data type); Database; Transaction data; Transaction log; Timestamp; Real-time computing","score_opus":0.013529732999485823,"score_gpt":0.23396273429864292,"score_spread":0.2204330012991571,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125852123","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6273693,0.0036973045,0.3488831,0.001439725,0.00017995069,0.00033975972,0.0035223481,0.0009276465,0.013640952],"genre_scores_gemma":[0.87449473,0.0009598396,0.11964756,0.00013253841,0.000091322996,0.0002607678,0.0021460066,0.00006263413,0.0022046403],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984946,0.00022599226,0.00024877695,0.00040221756,0.00045799348,0.00017035332],"domain_scores_gemma":[0.9922895,0.003355055,0.0016498049,0.0009747327,0.001283333,0.0004476409],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012676374,0.0003808353,0.0004883477,0.0034372003,0.0009786199,0.0021543477,0.000928545,0.00065085624,0.0027252857],"category_scores_gemma":[0.013209526,0.0003836555,0.00056403916,0.004355437,0.0012449572,0.0039104233,0.0016722989,0.00078586396,0.00071787514],"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":[0.0013123649,0.00029052337,0.16419521,0.0011765669,0.00033431384,0.00405814,0.0055389698,0.021307958,0.017687216,0.23478389,0.008459883,0.54085505],"study_design_scores_gemma":[0.00009939203,0.0004228585,0.084996216,0.0004290255,0.00025398587,0.0061811195,0.004383043,0.11467143,0.012524965,0.70354545,0.072304666,0.00018786755],"about_ca_topic_score_codex":0.0008323257,"about_ca_topic_score_gemma":0.00072391564,"teacher_disagreement_score":0.0034372003,"about_ca_system_score_codex":0.00038253143,"about_ca_system_score_gemma":0.00058076746,"threshold_uncertainty_score":0.009116948},"labels":[],"label_agreement":null},{"id":"W2125999281","doi":"10.1007/s11280-010-0094-0","title":"Mining discriminative items in multiple data streams","year":2010,"lang":"en","type":"article","venue":"World Wide Web","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":11,"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; Discriminative model; Data stream; Data stream mining; Heuristic; Information retrieval; Volume (thermodynamics); Space (punctuation); Data mining; Reading (process); Streaming data; Raw data; STREAMS; Artificial intelligence","score_opus":0.04568083920431813,"score_gpt":0.2889493389425767,"score_spread":0.24326849973825854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125999281","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.51000386,0.0029180388,0.479204,0.0012597027,0.00039855295,0.00039901197,0.0028397846,0.0013736277,0.0016033754],"genre_scores_gemma":[0.83063364,0.001313401,0.15773894,0.00023276215,0.00046173754,0.00024688174,0.0068877307,0.00012584245,0.0023591244],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817,0.00025449446,0.0002580216,0.00042996003,0.0006917329,0.00019588745],"domain_scores_gemma":[0.9935866,0.0032859223,0.0008648501,0.00068489363,0.0011949464,0.0003827544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021844432,0.0010491192,0.0020771557,0.0065904777,0.0009488654,0.0024288981,0.0016398169,0.0016249121,0.00093794795],"category_scores_gemma":[0.009572321,0.000874779,0.0011696568,0.0074519343,0.00057420164,0.004323403,0.0015625852,0.001764007,0.00071769767],"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":[0.0022963737,0.0017942166,0.31931388,0.00083050766,0.0010763565,0.003934217,0.00073024485,0.042486772,0.018812513,0.009074314,0.010248274,0.5894023],"study_design_scores_gemma":[0.000098175566,0.00035052764,0.040019587,0.00012105734,0.00049638405,0.002122072,0.0006936755,0.9144445,0.010092635,0.026034126,0.0054710666,0.000056147026],"about_ca_topic_score_codex":0.0016929962,"about_ca_topic_score_gemma":0.0029699889,"teacher_disagreement_score":0.0065904777,"about_ca_system_score_codex":0.00050677336,"about_ca_system_score_gemma":0.0008703724,"threshold_uncertainty_score":0.011552513},"labels":[],"label_agreement":null},{"id":"W2126046032","doi":"","title":"SPMF: a Java open-source pattern mining library","year":2014,"lang":"en","type":"article","venue":"Journal of Machine Learning Research","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":417,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Java; Source code; License; Interface (matter); MIT License; Open source; Documentation; Database transaction; Implementation; Data mining; Database; Programming language; Information retrieval; World Wide Web; Operating system; Software","score_opus":0.05115801282898343,"score_gpt":0.35700697144061744,"score_spread":0.305848958611634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126046032","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029102103,0.00083012163,0.649344,0.00034843065,0.00020330439,0.0004698611,0.0550875,0.2852024,0.0056041474],"genre_scores_gemma":[0.011630879,0.00093620166,0.8173952,0.0004749344,0.000118597396,0.0013193496,0.13848923,0.019465825,0.010169804],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99806744,0.00014748507,0.00034401464,0.0005070489,0.0007903407,0.0001437532],"domain_scores_gemma":[0.9972995,0.0011168094,0.0002865419,0.00042032698,0.0007168239,0.00016008863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001503976,0.0024224229,0.0015759583,0.00640036,0.0009745544,0.0027548857,0.004373354,0.001179383,0.029925544],"category_scores_gemma":[0.008411132,0.0017220557,0.0027279283,0.0055305106,0.00040516243,0.004108985,0.0021540842,0.0016448676,0.031749774],"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":[0.00037549398,0.00024465105,0.0054694344,0.0024685268,0.0003552765,0.00056327105,0.00024023112,0.0038666308,0.00868571,0.0058636116,0.38710243,0.5847647],"study_design_scores_gemma":[0.00033854533,0.00018911494,0.008706733,0.0005702608,0.00026914102,0.0030961165,0.00017944633,0.07574019,0.031025892,0.032677248,0.84691906,0.00028822964],"about_ca_topic_score_codex":0.0030374192,"about_ca_topic_score_gemma":0.004064546,"teacher_disagreement_score":0.029925544,"about_ca_system_score_codex":0.0006285683,"about_ca_system_score_gemma":0.0027230382,"threshold_uncertainty_score":0.10011095},"labels":[],"label_agreement":null},{"id":"W2126680566","doi":"10.1109/iat.2003.1241150","title":"Multiagent reinforcement learning using OLAP-based association rules mining","year":2004,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Online analytical processing; Computer science; Association rule learning; Cube (algebra); Data cube; Reinforcement learning; Data mining; Association (psychology); State (computer science); Domain (mathematical analysis); Action (physics); Architecture; Artificial intelligence; Machine learning; Data warehouse; Algorithm","score_opus":0.02654640116779461,"score_gpt":0.2693319855613973,"score_spread":0.2427855843936027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126680566","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030151485,0.00009286318,0.9681363,0.00022523195,0.000024839712,0.00008905103,0.000035587895,0.00039952094,0.0008450404],"genre_scores_gemma":[0.7193286,0.00010638916,0.27887416,0.00013949639,0.000034542205,0.0002402039,0.00013037883,0.00003466761,0.0011115075],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987698,0.00053585984,0.00008677825,0.00023255708,0.0002866602,0.00008829726],"domain_scores_gemma":[0.9959389,0.002541548,0.00042433993,0.00041923308,0.0004995152,0.00017659017],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022910535,0.00063137524,0.001086998,0.00057009235,0.00043369184,0.00093704095,0.0018413749,0.0007581938,0.0009347074],"category_scores_gemma":[0.0070690215,0.0003743778,0.00052782416,0.0005672351,0.00078425225,0.0015059083,0.0013963458,0.0012059204,0.00024109046],"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":[0.00015546835,0.00043395383,0.004589193,0.00010519615,0.00017857848,0.00019252083,0.00015772908,0.8331994,0.0024117215,0.012030144,0.001002415,0.14554377],"study_design_scores_gemma":[0.000009038585,0.000021948028,0.000095141695,0.0000022093886,0.00000479354,0.000010971308,0.000009059815,0.9956703,0.00040381288,0.0035920676,0.00017680049,0.0000038019746],"about_ca_topic_score_codex":0.0030489175,"about_ca_topic_score_gemma":0.0024516117,"teacher_disagreement_score":0.0030489175,"about_ca_system_score_codex":0.00062919676,"about_ca_system_score_gemma":0.00103726,"threshold_uncertainty_score":0.012116373},"labels":[],"label_agreement":null},{"id":"W2128248047","doi":"10.1007/3-540-44886-1_17","title":"Efficient Mining of Indirect Associations Using HI-Mine","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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":"York University","funders":"","keywords":"Computer science; Association rule learning; Data mining; struct; Set (abstract data type)","score_opus":0.030633662295016437,"score_gpt":0.26933802142846597,"score_spread":0.23870435913344953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128248047","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13082261,0.0027212875,0.84691554,0.0005529391,0.00021442852,0.000354298,0.0058746138,0.0068970197,0.005647293],"genre_scores_gemma":[0.35803503,0.00078099227,0.6157052,0.00030300848,0.0002452255,0.00030212238,0.01667356,0.00028400938,0.0076707737],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984831,0.00028535642,0.00018171738,0.00035467485,0.0005563564,0.00013874016],"domain_scores_gemma":[0.9939499,0.0033501415,0.00040339702,0.0011547443,0.00093964697,0.00020218527],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018162376,0.001057353,0.0018843433,0.004041276,0.0011490503,0.002159434,0.00251183,0.001068177,0.0036057045],"category_scores_gemma":[0.008191101,0.00075433054,0.0012167542,0.0040780394,0.00057756086,0.0030525024,0.0023704648,0.001478102,0.0025422086],"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":[0.0011530566,0.0007145024,0.044112947,0.000845358,0.0007129169,0.0012177636,0.00045456097,0.01653666,0.013279736,0.01255416,0.026093094,0.8823253],"study_design_scores_gemma":[0.00028379925,0.0007235363,0.018855786,0.00035975923,0.0012482917,0.0038593882,0.0009227049,0.7983101,0.035470292,0.10498256,0.03483568,0.00014806686],"about_ca_topic_score_codex":0.0012934209,"about_ca_topic_score_gemma":0.003968939,"teacher_disagreement_score":0.004041276,"about_ca_system_score_codex":0.00023287282,"about_ca_system_score_gemma":0.0015504047,"threshold_uncertainty_score":0.012062252},"labels":[],"label_agreement":null},{"id":"W2128309988","doi":"10.1109/icdmw.2007.84","title":"Efficient Mining of Frequent Patterns from Uncertain Data","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":93,"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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Database transaction; Data mining; Focus (optics); Transaction data; Uncertain data; Tree (set theory); Efficient algorithm; Association rule learning; Database; Algorithm; Mathematics","score_opus":0.05931962622228517,"score_gpt":0.3104257172430666,"score_spread":0.25110609102078146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128309988","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033943996,0.0009269303,0.9634467,0.00031860528,0.000032978503,0.00009573456,0.000494294,0.00036750434,0.00037319132],"genre_scores_gemma":[0.22571701,0.0012324983,0.7696295,0.00011763044,0.00011314437,0.0002027069,0.002503213,0.000056138815,0.00042823903],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965754,0.0008048242,0.000517982,0.000606248,0.0012868004,0.00020870763],"domain_scores_gemma":[0.9861624,0.009940765,0.0012930053,0.0010454189,0.0013888216,0.00016948645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002371164,0.00081089017,0.0021848266,0.002857027,0.00086829497,0.001550613,0.0019517137,0.0011652036,0.0005033931],"category_scores_gemma":[0.018274575,0.00064905704,0.0012821992,0.004336152,0.0005744351,0.0035919773,0.0014159556,0.0010903733,0.0004340316],"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":[0.0006357612,0.00029754677,0.016451553,0.0012954656,0.0005844494,0.0030658038,0.000956864,0.19403428,0.01655779,0.02174863,0.0069064917,0.7374654],"study_design_scores_gemma":[0.000049594328,0.00012365548,0.0018431116,0.00007149666,0.000104493934,0.0014738144,0.00027131801,0.9238284,0.005987061,0.06235138,0.003861267,0.00003435862],"about_ca_topic_score_codex":0.0010031483,"about_ca_topic_score_gemma":0.001111601,"teacher_disagreement_score":0.002857027,"about_ca_system_score_codex":0.00030697798,"about_ca_system_score_gemma":0.00096326927,"threshold_uncertainty_score":0.012540042},"labels":[],"label_agreement":null},{"id":"W2128360831","doi":"10.1109/cbms.1992.245017","title":"A probabilistic inductive learning approach to the acquisition of knowledge in medical expert systems","year":2003,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Probabilistic logic; Computer science; Knowledge acquisition; Artificial intelligence; Machine learning; Expert system; Probabilistic classification; Inference; Data mining; Support vector machine","score_opus":0.029978358029708652,"score_gpt":0.28419959335259504,"score_spread":0.2542212353228864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128360831","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00033406098,0.00021258685,0.9980761,0.00017415336,0.000015484904,0.00003229037,0.000025905987,0.00010996963,0.0010194505],"genre_scores_gemma":[0.051951915,0.0009291827,0.94457585,0.00021479475,0.00018785542,0.0003637554,0.0001536371,0.000042546053,0.0015805073],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99396175,0.0029462944,0.00034941465,0.0005635887,0.002004891,0.00017411476],"domain_scores_gemma":[0.98967135,0.008364123,0.00044777783,0.00067542534,0.00071654085,0.00012472531],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006122952,0.000780366,0.00087089837,0.0031210391,0.0008703923,0.0026665004,0.0034480796,0.0012865927,0.0039610756],"category_scores_gemma":[0.01635393,0.0007532771,0.0013731223,0.0031020876,0.0031044376,0.0039592944,0.0028753374,0.00244726,0.0010064605],"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":[0.000056519988,0.0001327519,0.0010474079,0.0007719371,0.00019138862,0.00033452993,0.0006888125,0.14103958,0.0019846833,0.49244428,0.0055678813,0.35574028],"study_design_scores_gemma":[0.000025119229,0.000054080392,0.0003381211,0.00016324947,0.000047201207,0.00028663856,0.00006920643,0.46726024,0.002211999,0.513925,0.015566148,0.00005301709],"about_ca_topic_score_codex":0.0015291418,"about_ca_topic_score_gemma":0.0018859986,"teacher_disagreement_score":0.006122952,"about_ca_system_score_codex":0.0013708953,"about_ca_system_score_gemma":0.0017739944,"threshold_uncertainty_score":0.032381654},"labels":[],"label_agreement":null},{"id":"W2128721204","doi":"10.1109/ideas.2004.34","title":"Incremental mining of Web sequential patterns using PLWAP tree on tolerance MinSupport","year":2004,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Tree (set theory); Data mining; Database; Fractal tree index; Incremental decision tree; Decision tree; Decision tree learning; Mathematics","score_opus":0.03985169507216933,"score_gpt":0.28707303580120763,"score_spread":0.24722134072903829,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128721204","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1167602,0.0007117374,0.8745376,0.00035965245,0.000069120135,0.00047102568,0.001374632,0.004256219,0.0014597841],"genre_scores_gemma":[0.25810027,0.00025148297,0.73711425,0.00012844555,0.000055125012,0.00032962498,0.0028930474,0.00015400858,0.00097368454],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985057,0.00021232877,0.00017139864,0.00028891364,0.0006931484,0.00012860348],"domain_scores_gemma":[0.99641716,0.0016414302,0.00044283574,0.0005873724,0.000741814,0.00016942415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010657599,0.0005609393,0.0010845487,0.0034728253,0.00068294303,0.0011828893,0.0019807469,0.000651692,0.0010241098],"category_scores_gemma":[0.008829393,0.0005980087,0.00087172026,0.0036406782,0.0004016648,0.0031735,0.0013491997,0.00085021806,0.00061753637],"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":[0.0005689049,0.00024097829,0.018089639,0.0003712619,0.00015913373,0.0007817711,0.00048673936,0.060235318,0.015387177,0.006143877,0.0064135063,0.8911218],"study_design_scores_gemma":[0.00007668386,0.00026761083,0.0036170091,0.000060122384,0.00009392205,0.0011746393,0.00026364965,0.94981354,0.014283307,0.020653505,0.009654091,0.00004195009],"about_ca_topic_score_codex":0.0028566346,"about_ca_topic_score_gemma":0.0043543084,"teacher_disagreement_score":0.0034728253,"about_ca_system_score_codex":0.0003592315,"about_ca_system_score_gemma":0.0011029005,"threshold_uncertainty_score":0.005679965},"labels":[],"label_agreement":null},{"id":"W2128723273","doi":"10.1145/775047.775081","title":"Mining frequent item sets by opportunistic projection","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":189,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Scalability; Set (abstract data type); Tree (set theory); Data mining; Database transaction; Projection (relational algebra); Algorithm; Database; Mathematics","score_opus":0.05014063780212529,"score_gpt":0.25913997932862065,"score_spread":0.20899934152649535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128723273","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03188948,0.0003071237,0.9649445,0.000112303635,0.000019061825,0.0001890848,0.00035875972,0.0014336936,0.0007458855],"genre_scores_gemma":[0.20995423,0.0003075005,0.78636134,0.00008661348,0.00004133215,0.00049914705,0.0019095151,0.0000866862,0.00075364177],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99781126,0.0006080067,0.00019862017,0.00038653208,0.00086856796,0.00012708163],"domain_scores_gemma":[0.9958759,0.0024205009,0.00032010055,0.0006836969,0.00059717393,0.00010269161],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014470195,0.00078486896,0.0011717489,0.002552874,0.0007563852,0.0015321414,0.0015276805,0.00062140764,0.0012143158],"category_scores_gemma":[0.008033784,0.000706648,0.00088681956,0.0030496581,0.0005443969,0.0027653016,0.0018432313,0.0007406863,0.00083763135],"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":[0.00042082093,0.00029408702,0.012174094,0.00038856082,0.0002651931,0.0006453535,0.0004937842,0.06641503,0.011491529,0.010825148,0.0042726877,0.8923138],"study_design_scores_gemma":[0.00007319939,0.00034809395,0.0032245063,0.00008153407,0.00010443316,0.0019378262,0.00037021574,0.926689,0.014102114,0.042129353,0.010878704,0.00006099368],"about_ca_topic_score_codex":0.00080594386,"about_ca_topic_score_gemma":0.0011134959,"teacher_disagreement_score":0.002552874,"about_ca_system_score_codex":0.00024856144,"about_ca_system_score_gemma":0.0010101147,"threshold_uncertainty_score":0.0076527},"labels":[],"label_agreement":null},{"id":"W2128933128","doi":"10.1109/tkde.2008.38","title":"Simultaneous Pattern and Data Clustering for Pattern Cluster Analysis","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data mining; Cluster analysis; Categorical variable; Relation (database); Cluster (spacecraft); Data set; Set (abstract data type); Pattern recognition (psychology); Consensus clustering; Measure (data warehouse); Artificial intelligence; Fuzzy clustering; CURE data clustering algorithm; Machine learning","score_opus":0.039446023589009414,"score_gpt":0.28539766762821617,"score_spread":0.24595164403920675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128933128","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00091333885,0.00038809274,0.99670863,0.0001382165,0.000070086746,0.00012153916,0.0001258526,0.0009001699,0.00063402276],"genre_scores_gemma":[0.023654105,0.00045078545,0.97347623,0.00014050177,0.000098762604,0.00052400754,0.0006247838,0.00022548679,0.0008053708],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9891651,0.0039779367,0.0007816641,0.002444285,0.0032920998,0.00033885316],"domain_scores_gemma":[0.9919435,0.0033569282,0.0006361281,0.002329498,0.0015751322,0.0001588444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0053750025,0.00257738,0.0023552151,0.0059525953,0.0022379393,0.002918095,0.0032491214,0.002132346,0.0059254407],"category_scores_gemma":[0.018429881,0.0009902064,0.0029088268,0.012492417,0.0021075779,0.0047043185,0.004339161,0.00391329,0.0030100802],"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":[0.0003539117,0.00023920728,0.0027660537,0.0015645023,0.0007248315,0.0004305415,0.0010851305,0.06390357,0.009194709,0.14778422,0.01842519,0.7535281],"study_design_scores_gemma":[0.00006922565,0.00015176077,0.0015437745,0.0001648066,0.00018557115,0.00075490883,0.00030241956,0.68095964,0.012876722,0.234316,0.06850021,0.00017497638],"about_ca_topic_score_codex":0.0029423118,"about_ca_topic_score_gemma":0.003081787,"teacher_disagreement_score":0.0059525953,"about_ca_system_score_codex":0.001336112,"about_ca_system_score_gemma":0.0025906183,"threshold_uncertainty_score":0.028426051},"labels":[],"label_agreement":null},{"id":"W2129671388","doi":"10.1007/s101090100069","title":"Deriving rules from activity diary data: A learning algorithm and results of computer experiments","year":2001,"lang":"en","type":"article","venue":"Journal of Geographical 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":"Ministry of Transportation of Ontario","funders":"","keywords":"Computer science; Formalism (music); Decision rule; Scheduling (production processes); Data mining; Machine learning; Artificial intelligence; Mathematical optimization; Mathematics","score_opus":0.030934817272593833,"score_gpt":0.28028829228174723,"score_spread":0.2493534750091534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129671388","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6605015,0.0015357387,0.32263514,0.0007985629,0.00026368917,0.0012808727,0.003608971,0.0030242882,0.0063512255],"genre_scores_gemma":[0.6493512,0.0006598512,0.33887115,0.00015921707,0.000083972176,0.0006949231,0.0076465174,0.00021688035,0.0023163175],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954857,0.0021268188,0.0005912454,0.0008647192,0.0007356954,0.00019579468],"domain_scores_gemma":[0.9111312,0.079293914,0.00076744653,0.005011262,0.0034488423,0.0003472681],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008282789,0.0013853975,0.001631513,0.002023892,0.0011037508,0.0024882285,0.0024443376,0.0022357756,0.003508878],"category_scores_gemma":[0.05439646,0.00047889852,0.0016549692,0.002695834,0.0007415893,0.0033969497,0.0011721597,0.0019066483,0.0017193077],"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":[0.0030172626,0.0035206205,0.025807504,0.00082137214,0.0006743919,0.00026761205,0.0009907291,0.15133499,0.003114594,0.003193675,0.006924525,0.8003327],"study_design_scores_gemma":[0.00043396794,0.000539898,0.0054602395,0.00007274138,0.0004056894,0.00026322994,0.0006400768,0.9735118,0.0070863394,0.009067089,0.002458638,0.00006038426],"about_ca_topic_score_codex":0.009285091,"about_ca_topic_score_gemma":0.0067492556,"teacher_disagreement_score":0.009285091,"about_ca_system_score_codex":0.0010620306,"about_ca_system_score_gemma":0.0018588755,"threshold_uncertainty_score":0.04380411},"labels":[],"label_agreement":null},{"id":"W2129827556","doi":"10.5539/ijsp.v4n2p1","title":"Model Selection for Poisson Regression via Association Rules Analysis","year":2015,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Poisson regression; Poisson distribution; Regression analysis; Selection (genetic algorithm); Computer science; Model selection; Regression; Regression diagnostic; Mathematics; Econometrics; Statistics; Machine learning; Polynomial regression; Population","score_opus":0.03726347752418733,"score_gpt":0.3225111672697547,"score_spread":0.28524768974556736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129827556","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034467326,0.00019796223,0.9954254,0.00015140197,0.000027548298,0.00010734411,0.00011692934,0.00019108236,0.0003356433],"genre_scores_gemma":[0.1555955,0.00079693546,0.8393282,0.0002646508,0.000197296,0.0013691218,0.001170977,0.00022038336,0.0010569054],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98029596,0.01374897,0.00085035537,0.0018881815,0.0027319358,0.0004845627],"domain_scores_gemma":[0.9592606,0.03536572,0.0016127725,0.001203691,0.0022555182,0.0003018192],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0194526,0.0017866582,0.003014459,0.004793044,0.0012450259,0.0027462598,0.0037552745,0.0015442042,0.0031379964],"category_scores_gemma":[0.05430163,0.0011141984,0.0044868914,0.0039803283,0.00089989306,0.0021538094,0.0026178367,0.0036894614,0.0010675453],"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":[0.00027234622,0.00029280578,0.0135322325,0.00054204446,0.0010145104,0.000789944,0.00029632822,0.6830171,0.0011099626,0.0873181,0.005698804,0.20611587],"study_design_scores_gemma":[0.000026977665,0.00004298739,0.0003475387,0.00003531335,0.00006909576,0.00008484411,0.000033656896,0.9654269,0.00036027623,0.0322846,0.0012694955,0.000018283357],"about_ca_topic_score_codex":0.0048485696,"about_ca_topic_score_gemma":0.004236923,"teacher_disagreement_score":0.0194526,"about_ca_system_score_codex":0.0012007613,"about_ca_system_score_gemma":0.0033055,"threshold_uncertainty_score":0.102876425},"labels":[],"label_agreement":null},{"id":"W2129968705","doi":"10.1109/ideas.2007.23","title":"Contrasting the Contrast Sets: An Alternative Approach","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Contrast (vision); Computer science; Association rule learning; Set (abstract data type); Focus (optics); Data mining; Value (mathematics); Artificial intelligence; Machine learning","score_opus":0.03204471525812842,"score_gpt":0.2907036345068925,"score_spread":0.2586589192487641,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129968705","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020802485,0.0006798416,0.9678247,0.0012308158,0.0001916828,0.0002804331,0.0003797521,0.00050009816,0.0081102485],"genre_scores_gemma":[0.1915976,0.0002855561,0.8038692,0.00058280135,0.00020358486,0.0003170979,0.0004647386,0.00014622067,0.0025332088],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9933563,0.0022216938,0.0004065499,0.0018433643,0.0018794679,0.00029258212],"domain_scores_gemma":[0.9832109,0.010635728,0.0008357422,0.0031903412,0.0017474309,0.00037990927],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0057130726,0.0013381611,0.0022686406,0.0071963253,0.0018112693,0.0059667253,0.00480006,0.002970876,0.008966985],"category_scores_gemma":[0.03350768,0.0007690562,0.0027048525,0.0059178057,0.0034979496,0.0079432195,0.0044544083,0.003462772,0.0018109056],"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":[0.0009657768,0.00036358347,0.01492419,0.0006083537,0.00056232006,0.0006910549,0.0019510466,0.014708923,0.009404148,0.44419575,0.005613249,0.50601166],"study_design_scores_gemma":[0.0002243846,0.00067253615,0.005808314,0.00024895862,0.00046259954,0.0034768896,0.0012360093,0.23140179,0.009766102,0.6942539,0.052241284,0.00020721825],"about_ca_topic_score_codex":0.0010796043,"about_ca_topic_score_gemma":0.0013148893,"teacher_disagreement_score":0.008966985,"about_ca_system_score_codex":0.000994107,"about_ca_system_score_gemma":0.0015607822,"threshold_uncertainty_score":0.030214012},"labels":[],"label_agreement":null},{"id":"W2130025037","doi":"10.1145/2245276.2245314","title":"A new class of constraints for constrained frequent pattern mining","year":2012,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Monotone polygon; Property (philosophy); Class (philosophy); Computer science; Exploit; Data mining; Constraint (computer-aided design); Sequential Pattern Mining; Theoretical computer science; Mathematics; Artificial intelligence","score_opus":0.033559258363863816,"score_gpt":0.28135701995397,"score_spread":0.2477977615901062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130025037","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008319385,0.0012680067,0.98358154,0.00081270625,0.00028216906,0.0002843881,0.0018319578,0.00036719537,0.003252617],"genre_scores_gemma":[0.108474076,0.0018134858,0.8806947,0.001162411,0.0007118861,0.0010706375,0.003530758,0.00020514212,0.002336989],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99240994,0.0020763746,0.0009651914,0.0011494257,0.0031079424,0.00029108103],"domain_scores_gemma":[0.984377,0.009286254,0.0014481682,0.0012931612,0.003185291,0.00041014684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044524297,0.0012442109,0.0012650429,0.002606177,0.0009295842,0.0030947058,0.0023884475,0.0015223549,0.0036693262],"category_scores_gemma":[0.026108412,0.00050410384,0.001480487,0.0048769517,0.0010395908,0.005744857,0.0015720177,0.0027677906,0.00085306686],"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":[0.0006961376,0.00040423326,0.009845739,0.0016646667,0.0004708313,0.0018232717,0.00056624686,0.061142765,0.016519397,0.29331797,0.036595777,0.57695305],"study_design_scores_gemma":[0.00019279112,0.00040787656,0.0026986338,0.000427037,0.0001759236,0.003242647,0.00028032812,0.58531284,0.010858566,0.285726,0.11046667,0.00021057135],"about_ca_topic_score_codex":0.0015374098,"about_ca_topic_score_gemma":0.0017305524,"teacher_disagreement_score":0.0044524297,"about_ca_system_score_codex":0.0006094978,"about_ca_system_score_gemma":0.0020035668,"threshold_uncertainty_score":0.023546934},"labels":[],"label_agreement":null},{"id":"W2131225292","doi":"10.1109/ride.1997.583715","title":"Generalization and decision tree induction: efficient classification in data mining","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":118,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Scalability; Decision tree; Data mining; Abstraction; Generalization; Relevance (law); Machine learning; Artificial intelligence; Database; Mathematics","score_opus":0.11375942199519888,"score_gpt":0.29908879285565126,"score_spread":0.18532937086045237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131225292","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048897355,0.001206194,0.99131536,0.00041290186,0.000092446215,0.00009331659,0.00010478547,0.000728648,0.0011566163],"genre_scores_gemma":[0.118890546,0.0017256978,0.8753523,0.00037889343,0.00040995347,0.00035163295,0.00057978707,0.00015610972,0.0021550867],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99593157,0.001843526,0.00022909643,0.0006286651,0.0011789771,0.00018820603],"domain_scores_gemma":[0.9952112,0.002928444,0.00026487326,0.0008848792,0.00060075306,0.000109806344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00579642,0.0008039897,0.0017866394,0.0018562089,0.00068113866,0.0012559892,0.002137853,0.0012070766,0.0015613589],"category_scores_gemma":[0.010903469,0.0004915234,0.0011236131,0.0041595646,0.0011746589,0.0031410544,0.0019401688,0.002192922,0.001232911],"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":[0.00014704771,0.00014529783,0.002335729,0.0003876797,0.00011973139,0.00017508205,0.00023687471,0.06207373,0.0036131192,0.07778572,0.011552584,0.8414273],"study_design_scores_gemma":[0.000057927,0.00009443378,0.0010191095,0.000085257365,0.000062332154,0.0002632428,0.00005132469,0.7903185,0.0042347116,0.19143535,0.012339478,0.000038318132],"about_ca_topic_score_codex":0.0014045133,"about_ca_topic_score_gemma":0.0015770872,"teacher_disagreement_score":0.00579642,"about_ca_system_score_codex":0.00067583995,"about_ca_system_score_gemma":0.0012865247,"threshold_uncertainty_score":0.030654728},"labels":[],"label_agreement":null},{"id":"W2131781085","doi":"10.1109/fuzz.2002.1006632","title":"An OLAM framework for Web usage mining and business intelligence reporting","year":2003,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Clickstream; Web mining; Business intelligence; Computer science; Web intelligence; Data science; World Wide Web; Web analytics; Online analytical processing; Web page; Data mining; Data warehouse; Web modeling; Web API","score_opus":0.05356395959585923,"score_gpt":0.3351425518602231,"score_spread":0.2815785922643639,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131781085","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00055221765,0.00042151124,0.98959047,0.00038159906,0.00006390933,0.00043966188,0.001082324,0.0049104015,0.0025578483],"genre_scores_gemma":[0.009617285,0.0004962458,0.9843344,0.00029297554,0.0001225165,0.0009989485,0.0023033125,0.00024189932,0.0015924415],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9859751,0.0042718803,0.0023010576,0.0012477193,0.0057185013,0.00048571895],"domain_scores_gemma":[0.9855703,0.0058101327,0.0019202379,0.003170604,0.0031191763,0.00040944899],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010353806,0.0019584824,0.0019084521,0.0095560495,0.0016147862,0.00950016,0.004993025,0.001854862,0.005130026],"category_scores_gemma":[0.026080547,0.0012264029,0.0031020052,0.011119307,0.00133132,0.0075084916,0.0039910367,0.0032712577,0.0046768454],"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":[0.00012748958,0.00033081273,0.0046407063,0.0013311896,0.00034691067,0.00082396425,0.00073381414,0.021760501,0.002887766,0.3853357,0.059654687,0.52202654],"study_design_scores_gemma":[0.00006177184,0.00011864249,0.0023064925,0.00067243684,0.00016892064,0.0014816831,0.0004001916,0.27671698,0.005861171,0.3218159,0.39021376,0.0001820942],"about_ca_topic_score_codex":0.0056890403,"about_ca_topic_score_gemma":0.0060407645,"teacher_disagreement_score":0.010353806,"about_ca_system_score_codex":0.0016315535,"about_ca_system_score_gemma":0.0042123687,"threshold_uncertainty_score":0.05475682},"labels":[],"label_agreement":null},{"id":"W2132965194","doi":"10.1016/j.ejor.2011.04.022","title":"Mining axiomatic fuzzy set association rules for classification problems","year":2011,"lang":"en","type":"article","venue":"European Journal of Operational Research","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":32,"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":"Interpretability; Association rule learning; Computer science; Data mining; Axiom; Classifier (UML); Fuzzy logic; Fuzzy rule; Artificial intelligence; Fuzzy set; Rough set; Machine learning; Class (philosophy); Mathematics","score_opus":0.27293754368649475,"score_gpt":0.377612287166583,"score_spread":0.10467474348008826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132965194","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07875371,0.0014327756,0.91382116,0.0012976965,0.00022297302,0.0003150778,0.0009813937,0.0005216601,0.002653487],"genre_scores_gemma":[0.3683444,0.0010672393,0.62396646,0.0005583554,0.00028068808,0.00043817295,0.0038312331,0.000036435362,0.001477079],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9899649,0.0030454712,0.0015760494,0.0016473392,0.003428389,0.00033782577],"domain_scores_gemma":[0.9728617,0.018908389,0.0018934165,0.002175002,0.0038346914,0.00032679224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006653761,0.0010616983,0.0015417124,0.004599558,0.0013430511,0.0032653857,0.0029110736,0.0018872243,0.0021011722],"category_scores_gemma":[0.0375576,0.0007486067,0.0022516276,0.003471997,0.0015209733,0.004336502,0.0019849506,0.0032193854,0.0007904578],"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":[0.0009005882,0.0014185547,0.04187623,0.0020416854,0.0017091638,0.0038178847,0.001313922,0.078177616,0.009569101,0.17135441,0.0120586585,0.6757622],"study_design_scores_gemma":[0.00020676028,0.00036221847,0.005359607,0.00037057666,0.00066430063,0.002908393,0.00052758795,0.56740594,0.007700972,0.40732518,0.0070579452,0.00011047851],"about_ca_topic_score_codex":0.00085933245,"about_ca_topic_score_gemma":0.0019770167,"teacher_disagreement_score":0.006653761,"about_ca_system_score_codex":0.0006831058,"about_ca_system_score_gemma":0.0022846882,"threshold_uncertainty_score":0.035188854},"labels":[],"label_agreement":null},{"id":"W2133901639","doi":"10.1109/icpads.2006.77","title":"Parallel leap: large-scale maximal pattern mining in a distributed environment","year":2006,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Data mining; Set (abstract data type); Scale (ratio); Cluster (spacecraft); Space (punctuation); Geography","score_opus":0.009984837463231585,"score_gpt":0.21469892225454712,"score_spread":0.20471408479131553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133901639","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033117946,0.00050260214,0.94677657,0.0004951093,0.00009875515,0.00032162346,0.00082186545,0.015973752,0.0018917855],"genre_scores_gemma":[0.18478143,0.00030507092,0.80917907,0.00017612037,0.000093981136,0.00045961692,0.0021334086,0.00045974363,0.002411553],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99843866,0.0003795318,0.00014588419,0.00042357016,0.00045511077,0.00015715344],"domain_scores_gemma":[0.9963469,0.0013227223,0.00030846504,0.0013547774,0.00042903126,0.00023821923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024356432,0.0011408738,0.0013400684,0.0016142381,0.0012128449,0.0017672519,0.0035532992,0.00086404453,0.002928579],"category_scores_gemma":[0.0057993913,0.0007463376,0.0009503124,0.0026769738,0.0008413847,0.0035934593,0.0027476493,0.0011799268,0.0019847467],"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":[0.0023365756,0.00092828635,0.013702551,0.00084082066,0.0005024501,0.0014285285,0.0006491203,0.09348964,0.031877544,0.012365342,0.036378715,0.80550045],"study_design_scores_gemma":[0.000390559,0.00031093802,0.0019409874,0.000030889056,0.00009636381,0.0010489906,0.00028126992,0.92168385,0.018903868,0.038704794,0.016550997,0.000056416884],"about_ca_topic_score_codex":0.0016798067,"about_ca_topic_score_gemma":0.002755178,"teacher_disagreement_score":0.0035532992,"about_ca_system_score_codex":0.00037418513,"about_ca_system_score_gemma":0.0016569076,"threshold_uncertainty_score":0.012881041},"labels":[],"label_agreement":null},{"id":"W2135085701","doi":"","title":"CMRULES: An Efficient Algorithm for Mining Sequential Rules Common to Several Sequences","year":2010,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Association rule learning; Computer science; Sequence (biology); Sequential Pattern Mining; Sliding window protocol; Scalability; Data mining; Algorithm; Algorithm design; Efficient algorithm; Window (computing); Database","score_opus":0.02192218344860776,"score_gpt":0.27109259432932875,"score_spread":0.249170410880721,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135085701","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014818939,0.00071102043,0.96738964,0.00023985901,0.00011165911,0.0005411741,0.002186397,0.012759894,0.0012414923],"genre_scores_gemma":[0.04570651,0.00020017993,0.9463139,0.00020308327,0.000073177915,0.00048303674,0.0046697306,0.00048854697,0.0018618444],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99691224,0.0005782946,0.00033763843,0.0009908143,0.0010011942,0.00017981505],"domain_scores_gemma":[0.99242014,0.00528206,0.00039302884,0.00083949126,0.00084880146,0.00021642444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035702984,0.0019288403,0.0020532424,0.0066823475,0.0011765441,0.0027197576,0.0035875598,0.0022714508,0.005826679],"category_scores_gemma":[0.016553573,0.0011121718,0.0023268291,0.0035250077,0.00095656863,0.002981404,0.002012154,0.0020709047,0.0030263413],"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":[0.00081587455,0.00038666875,0.006135228,0.00087546464,0.00042811516,0.0005715758,0.00027452467,0.026991876,0.013828976,0.009466346,0.021245621,0.91897976],"study_design_scores_gemma":[0.0004603,0.00064784806,0.0030606133,0.00031218582,0.00034484413,0.001764985,0.00024661073,0.87466687,0.023980707,0.052400827,0.04198774,0.00012642036],"about_ca_topic_score_codex":0.0035108726,"about_ca_topic_score_gemma":0.0075211916,"teacher_disagreement_score":0.0066823475,"about_ca_system_score_codex":0.0008251286,"about_ca_system_score_gemma":0.0036746957,"threshold_uncertainty_score":0.019492209},"labels":[],"label_agreement":null},{"id":"W2135135089","doi":"10.1109/iv.2008.35","title":"ARC-UI: Visualization Tool for Associative Classifiers","year":2008,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Classifier (UML); Visualization; Associative property; Artificial intelligence; Machine learning; Data mining; Data visualization; Pattern recognition (psychology)","score_opus":0.04334740996045065,"score_gpt":0.3012809472802954,"score_spread":0.25793353731984475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135135089","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0056048017,0.0006485889,0.5928439,0.0006314741,0.00025306767,0.00033136975,0.014719248,0.3762189,0.00874863],"genre_scores_gemma":[0.08229242,0.001047308,0.8612962,0.0004649076,0.00023264108,0.001449817,0.021091131,0.022717392,0.00940829],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987997,0.00027344684,0.00016617037,0.00016151066,0.00050449785,0.000094605384],"domain_scores_gemma":[0.9946919,0.0033041257,0.00027516412,0.0006023179,0.00085041265,0.00027593353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002373813,0.0022593408,0.0013190497,0.00534732,0.00077069335,0.0027411557,0.0023346206,0.0018145578,0.05074341],"category_scores_gemma":[0.011101312,0.00083107664,0.0011506074,0.002893125,0.00035933373,0.0034979144,0.0023552275,0.002055527,0.012177487],"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":[0.0010351836,0.00038756427,0.004869462,0.001795592,0.00021508196,0.0007278017,0.0012237618,0.011681733,0.016215688,0.01798745,0.43662974,0.5072309],"study_design_scores_gemma":[0.0004831097,0.00023321425,0.005156434,0.00061901944,0.0001515496,0.0013757057,0.00032684676,0.41083828,0.03910418,0.04662378,0.49481174,0.00027603615],"about_ca_topic_score_codex":0.0028637825,"about_ca_topic_score_gemma":0.0037597138,"teacher_disagreement_score":0.05074341,"about_ca_system_score_codex":0.00052805163,"about_ca_system_score_gemma":0.0011596655,"threshold_uncertainty_score":0.16975361},"labels":[],"label_agreement":null},{"id":"W2135754018","doi":"10.1109/icpr.2008.4761258","title":"Three related types of multi-value association patterns","year":2008,"lang":"en","type":"article","venue":"Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Tuple; Null hypothesis; Association (psychology); Computer science; Value (mathematics); Statistical hypothesis testing; Statistics; Pattern recognition (psychology); Event (particle physics); Data mining; Null (SQL); Mathematics; Artificial intelligence; Psychology","score_opus":0.0975866222858241,"score_gpt":0.29916258520079525,"score_spread":0.20157596291497115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135754018","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17264716,0.0023328783,0.8024294,0.0027708875,0.00035247844,0.0011320162,0.0035354146,0.0013296378,0.013470163],"genre_scores_gemma":[0.59747845,0.0009882466,0.39108124,0.000885232,0.00022457496,0.00087821495,0.0025380796,0.00009580658,0.005830134],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99279153,0.0012108864,0.0009837275,0.0015258468,0.003028068,0.00045989855],"domain_scores_gemma":[0.963304,0.016970996,0.007947405,0.005309479,0.0056861793,0.0007820323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031043638,0.000771695,0.0008494824,0.0027209362,0.0011360693,0.0023811813,0.0018203288,0.0016558289,0.0030393794],"category_scores_gemma":[0.030290099,0.00046466704,0.0009859223,0.006235964,0.0017171295,0.0043618395,0.0018481215,0.0015706933,0.0008079127],"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":[0.0010967129,0.0006478905,0.15920402,0.0020481723,0.0005623905,0.0058943504,0.0023111508,0.015318912,0.012480788,0.19451149,0.0146287875,0.5912953],"study_design_scores_gemma":[0.00022309282,0.00043697408,0.05966196,0.0005108134,0.0003796086,0.015934175,0.0025213745,0.16687597,0.019624645,0.6732322,0.06025486,0.00034428676],"about_ca_topic_score_codex":0.00080566626,"about_ca_topic_score_gemma":0.0012074284,"teacher_disagreement_score":0.0031043638,"about_ca_system_score_codex":0.00056217273,"about_ca_system_score_gemma":0.0010641123,"threshold_uncertainty_score":0.016417623},"labels":[],"label_agreement":null},{"id":"W2136278857","doi":"10.1109/grc.2005.1547372","title":"Compact transaction database for efficient frequent pattern mining","year":2005,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Database transaction; Apriori algorithm; Data mining; Association rule learning; GSP Algorithm; A priori and a posteriori; Database; Transaction data; Tree (set theory); Mathematics","score_opus":0.03264285611169323,"score_gpt":0.2876708239333178,"score_spread":0.25502796782162457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136278857","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01563548,0.0018122048,0.9726398,0.00047238448,0.00021151248,0.00026952403,0.0029398021,0.003278343,0.0027409794],"genre_scores_gemma":[0.12885481,0.0014945302,0.85745376,0.00023720162,0.00019091649,0.0005738829,0.009082681,0.00019938845,0.0019128965],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99763584,0.0005902034,0.00038728636,0.00034225456,0.00095532474,0.00008914835],"domain_scores_gemma":[0.99410546,0.0019557292,0.00041835097,0.0018913342,0.0014942078,0.00013490606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016808473,0.0006719352,0.0011367963,0.0025334142,0.0005800851,0.0020926401,0.0015932453,0.0007424785,0.0059819263],"category_scores_gemma":[0.012186031,0.0004963914,0.00063967594,0.0061054938,0.00034590357,0.0039043818,0.0011323121,0.0010378872,0.0030955593],"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":[0.0009786655,0.00023782432,0.0033902202,0.0008648412,0.00019601609,0.0010862447,0.00037882093,0.041331243,0.027566746,0.068928674,0.044163674,0.810877],"study_design_scores_gemma":[0.00036762503,0.0006051712,0.002318872,0.00020904308,0.00019197896,0.00417384,0.00038529234,0.68581533,0.037884023,0.12663631,0.14128079,0.0001318124],"about_ca_topic_score_codex":0.0007536828,"about_ca_topic_score_gemma":0.00074257085,"teacher_disagreement_score":0.0059819263,"about_ca_system_score_codex":0.0003400782,"about_ca_system_score_gemma":0.00083796104,"threshold_uncertainty_score":0.020011544},"labels":[],"label_agreement":null},{"id":"W2136309879","doi":"10.1109/fuzz.2002.1005076","title":"Automated mining of granular database scheme","year":2003,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Scheme (mathematics); Computer science; Construct (python library); Data mining; Granular computing; Database design; Database; Functional dependency; Database theory; Relation (database); Database model; Relational database; Mathematics; Rough set","score_opus":0.02228329152129546,"score_gpt":0.27244032067624774,"score_spread":0.2501570291549523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136309879","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039439443,0.00042182754,0.95361185,0.00024100539,0.00004329886,0.0002731212,0.001121195,0.0026395267,0.0022087325],"genre_scores_gemma":[0.26186854,0.0003150188,0.7335247,0.000103632534,0.00003060072,0.0002714349,0.0028854872,0.00013005661,0.0008705512],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99630153,0.00048873364,0.00048433314,0.0006850392,0.001775035,0.0002652869],"domain_scores_gemma":[0.99430686,0.0017337337,0.00070756435,0.0020737546,0.00097605237,0.00020206586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002145254,0.00063730264,0.0013481587,0.0042343955,0.0010855203,0.003058369,0.0019992075,0.00096185005,0.0016395468],"category_scores_gemma":[0.0125384545,0.0007226873,0.0012001758,0.004385544,0.00083480706,0.003920179,0.0027505832,0.0011172412,0.00070617977],"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":[0.00069064985,0.00029111476,0.022193866,0.0007896712,0.00024192191,0.0016508258,0.0010166137,0.07518707,0.028905405,0.13458848,0.013176521,0.7212678],"study_design_scores_gemma":[0.00009288769,0.0001236188,0.004944398,0.0001284921,0.00012907671,0.0011744607,0.00026940895,0.76366115,0.022891585,0.17963678,0.026868574,0.00007953429],"about_ca_topic_score_codex":0.0017684897,"about_ca_topic_score_gemma":0.0019639558,"teacher_disagreement_score":0.0042343955,"about_ca_system_score_codex":0.0007521703,"about_ca_system_score_gemma":0.0013446651,"threshold_uncertainty_score":0.0113453865},"labels":[],"label_agreement":null},{"id":"W2136898966","doi":"10.1145/1081870.1081964","title":"Pattern lattice traversal by selective jumps","year":2005,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Tree traversal; Computer science; Lattice (music); Graph traversal; Theoretical computer science; Set (abstract data type); Algorithm; Physics","score_opus":0.008858889178993358,"score_gpt":0.23732043382276433,"score_spread":0.22846154464377097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136898966","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12705985,0.0003639855,0.8644946,0.0003769489,0.00004818763,0.00030905285,0.00036592782,0.002693252,0.0042881537],"genre_scores_gemma":[0.4361302,0.00022823332,0.55625737,0.0001748922,0.00003087446,0.0004547176,0.0013310346,0.0003375031,0.0050552087],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99815196,0.0005068632,0.00017161395,0.0003270143,0.00060317444,0.00023936175],"domain_scores_gemma":[0.99345,0.0041367123,0.00035978295,0.0011662549,0.0006617357,0.00022555709],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015885826,0.0004904332,0.00083661743,0.0016820768,0.0007852381,0.001471713,0.0014131994,0.00090897887,0.0039030656],"category_scores_gemma":[0.010581376,0.0005292529,0.0008467581,0.0020401506,0.0008426179,0.0024746612,0.0025536693,0.0013563114,0.00092697114],"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":[0.0013743526,0.0005806699,0.011657567,0.00070628244,0.00019532241,0.0010927996,0.0016240593,0.11536093,0.06258165,0.09877683,0.010534653,0.69551504],"study_design_scores_gemma":[0.00014973222,0.00041496527,0.00091456925,0.000064309424,0.000079945035,0.00083391456,0.0004528999,0.86364096,0.028316302,0.09329966,0.011783588,0.0000491358],"about_ca_topic_score_codex":0.0009875854,"about_ca_topic_score_gemma":0.0017583208,"teacher_disagreement_score":0.0039030656,"about_ca_system_score_codex":0.00045359498,"about_ca_system_score_gemma":0.0010178302,"threshold_uncertainty_score":0.013057053},"labels":[],"label_agreement":null},{"id":"W2139422684","doi":"10.1145/335191.336572","title":"Towards data mining benchmarking","year":2000,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Data mining; Benchmarking; Data stream mining; Database transaction; Association rule learning; Apriori algorithm; Set (abstract data type); GSP Algorithm; Database; Relational database","score_opus":0.05942132737752803,"score_gpt":0.2999806763587709,"score_spread":0.24055934898124287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139422684","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0127102975,0.008093272,0.904648,0.02819348,0.0026669954,0.0014120243,0.0023988665,0.0091613205,0.030715713],"genre_scores_gemma":[0.1305668,0.0060761445,0.8335759,0.0072931326,0.0013268857,0.002414981,0.011137007,0.0022373828,0.0053717145],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9033338,0.048775017,0.008951464,0.009044292,0.027283413,0.0026119724],"domain_scores_gemma":[0.8826397,0.038210843,0.0038993736,0.04006594,0.031718552,0.003465533],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08084901,0.002452552,0.0036637764,0.006299605,0.0021011953,0.017717518,0.008426043,0.004187661,0.0061568916],"category_scores_gemma":[0.19353804,0.001373507,0.0022828782,0.011315529,0.0036101767,0.023646332,0.012806977,0.010353582,0.006223383],"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":[0.000494394,0.0009710113,0.009077013,0.001994987,0.00033869475,0.00023880045,0.0010002431,0.045109514,0.0041297763,0.3878365,0.08371024,0.4650989],"study_design_scores_gemma":[0.00016906341,0.0007037732,0.0026139244,0.0017192086,0.000113422706,0.0004603865,0.0014112898,0.22657391,0.0117822215,0.4658794,0.28840753,0.00016582545],"about_ca_topic_score_codex":0.0015298664,"about_ca_topic_score_gemma":0.00087495486,"teacher_disagreement_score":0.919151,"about_ca_system_score_codex":0.0047153383,"about_ca_system_score_gemma":0.0074580163,"threshold_uncertainty_score":0.42757553},"labels":[],"label_agreement":null},{"id":"W2139473768","doi":"10.5539/mas.v3n8p9","title":"Study on the Material Requisition System Based on Data Mining","year":2009,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Shanghai Leading Academic Discipline Project","keywords":"Requisition; Production (economics); Computer science; Process (computing); Quality (philosophy); Data mining; Risk analysis (engineering); Business","score_opus":0.06633616815029349,"score_gpt":0.29334655168058155,"score_spread":0.22701038353028807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139473768","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23068324,0.0013562279,0.75016916,0.0011784012,0.0001462548,0.0008329434,0.00042592094,0.0028557726,0.0123521425],"genre_scores_gemma":[0.72844416,0.0010951734,0.2634173,0.0002589991,0.00006923802,0.00028018426,0.00081770157,0.00011596823,0.0055013592],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986706,0.00027146286,0.00012776795,0.00030524214,0.0005346795,0.00009031489],"domain_scores_gemma":[0.9975949,0.0012194447,0.0001605235,0.00030755988,0.00064236287,0.00007508469],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018556303,0.00043252326,0.00058842875,0.0014796561,0.0010815638,0.0020620683,0.0009978389,0.0006590981,0.0021000728],"category_scores_gemma":[0.0050990055,0.00040208508,0.0007759162,0.001760086,0.0004350052,0.002768678,0.00054217357,0.0006633578,0.00041334014],"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":[0.00092601054,0.0010285607,0.045878045,0.001425648,0.0002841292,0.001748062,0.0020239726,0.062259942,0.04863967,0.07387042,0.008506376,0.75340915],"study_design_scores_gemma":[0.00009563959,0.0005104469,0.013874268,0.00016669837,0.00028598052,0.0010119996,0.0005233231,0.866676,0.05863031,0.02153712,0.03659193,0.00009635477],"about_ca_topic_score_codex":0.0035647813,"about_ca_topic_score_gemma":0.002082277,"teacher_disagreement_score":0.0035647813,"about_ca_system_score_codex":0.0010025392,"about_ca_system_score_gemma":0.0018251913,"threshold_uncertainty_score":0.009813607},"labels":[],"label_agreement":null},{"id":"W2139501711","doi":"10.71781/9668","title":"Intégration des connaissances ontologiques dans la fouille de motifs séquentiels avec application à la personnalisation Web","year":2008,"lang":"fr","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Abstraction; Ontology; Semantics (computer science); Set (abstract data type); Object (grammar); Scalability; Syntax; Artificial intelligence; Natural language processing; Programming language; Database","score_opus":0.024777495704895538,"score_gpt":0.24837688435230434,"score_spread":0.2235993886474088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139501711","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11789857,0.0018745548,0.8641361,0.0006674186,0.00019197051,0.00022379932,0.0016627604,0.0062975963,0.0070472844],"genre_scores_gemma":[0.35847452,0.0014673715,0.61666167,0.00016282465,0.00014253528,0.00019371879,0.0036586828,0.0018058154,0.017432973],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982187,0.00037880824,0.00013807428,0.00049984804,0.00067852833,0.00008608284],"domain_scores_gemma":[0.9959382,0.0020259304,0.00024680796,0.00053090684,0.0010587099,0.00019951545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018250385,0.0006311204,0.0007758718,0.002572233,0.0007654221,0.0036712897,0.0008499119,0.0009859927,0.0068107564],"category_scores_gemma":[0.007982427,0.00054996205,0.0013719623,0.0019237706,0.0009329092,0.0031249109,0.0012130458,0.0012907302,0.0016600167],"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":[0.0010801535,0.00043646514,0.02466518,0.00094797136,0.0003068861,0.0012998917,0.0040054494,0.052636795,0.09743247,0.07121865,0.0064937156,0.7394764],"study_design_scores_gemma":[0.00007286735,0.00028526163,0.02885593,0.00027763814,0.00022446371,0.0011593105,0.001310344,0.78861624,0.04897318,0.0520151,0.07806524,0.00014445717],"about_ca_topic_score_codex":0.016715312,"about_ca_topic_score_gemma":0.023554271,"teacher_disagreement_score":0.016715312,"about_ca_system_score_codex":0.0009099398,"about_ca_system_score_gemma":0.0015593576,"threshold_uncertainty_score":0.033236027},"labels":[],"label_agreement":null},{"id":"W2140168239","doi":"10.1109/cse.2009.51","title":"Scalable APRIORI-Based Frequent Pattern Discovery","year":2009,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Scalability; Benchmark (surveying); A priori and a posteriori; Data mining; sort; Task (project management); Field (mathematics); Machine learning; Implementation; Contrast (vision); Artificial intelligence; Pattern recognition (psychology); Information retrieval; Database","score_opus":0.014413921653244894,"score_gpt":0.24576069880235824,"score_spread":0.23134677714911334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140168239","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0656898,0.002832782,0.8967103,0.0014706941,0.00033392335,0.00045259265,0.0039979406,0.022450883,0.0060610943],"genre_scores_gemma":[0.19497891,0.000981108,0.79262644,0.0002679176,0.00022226572,0.00030321526,0.007700912,0.00025809306,0.0026611811],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99755895,0.0004349962,0.00023501247,0.0005378688,0.0010787916,0.00015437296],"domain_scores_gemma":[0.992125,0.0031398907,0.00050304504,0.0024717122,0.0014881439,0.00027223848],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031542806,0.0010863463,0.0021103283,0.0024511956,0.0008245702,0.0021826946,0.00334126,0.00082474377,0.0033359844],"category_scores_gemma":[0.010038057,0.0007861122,0.0010390888,0.0051744767,0.00050749286,0.00439824,0.0019068976,0.0013174019,0.0028435127],"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":[0.001378192,0.000591659,0.007516371,0.0006376455,0.00035978935,0.0006601195,0.00020478452,0.07970773,0.018803984,0.010239099,0.033904113,0.84599644],"study_design_scores_gemma":[0.00027991744,0.00026554347,0.0018832202,0.000033460205,0.00009893096,0.00078982546,0.00014760984,0.9502656,0.011323841,0.024880044,0.00998096,0.000051100433],"about_ca_topic_score_codex":0.0030215885,"about_ca_topic_score_gemma":0.004310034,"teacher_disagreement_score":0.00334126,"about_ca_system_score_codex":0.0005175008,"about_ca_system_score_gemma":0.0020349217,"threshold_uncertainty_score":0.016681612},"labels":[],"label_agreement":null},{"id":"W2140511449","doi":"10.1007/978-3-540-24840-8_37","title":"Distributed Data Mining vs. Sampling Techniques: A Comparison","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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":"Université Laval","funders":"","keywords":"Computer science; Data mining; Download; Aggregate (composite); Sampling (signal processing); Distributed database; Set (abstract data type); Volume (thermodynamics); Database; World Wide Web","score_opus":0.060641999652649735,"score_gpt":0.3188307178509959,"score_spread":0.2581887181983462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140511449","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09874184,0.0726612,0.80178046,0.0034997303,0.0013337147,0.0009914399,0.00077008386,0.0038635603,0.016357968],"genre_scores_gemma":[0.5125848,0.03688411,0.43923393,0.0010918077,0.0017461785,0.0006004991,0.001383286,0.00097306323,0.0055023553],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99048877,0.00360014,0.00051910855,0.0010121166,0.0040841214,0.00029580793],"domain_scores_gemma":[0.94836855,0.039089534,0.0011211935,0.0052565155,0.00533995,0.0008243406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011896611,0.0011878886,0.0033671951,0.004035045,0.0007454573,0.0026243788,0.0036372808,0.0018367987,0.0043053445],"category_scores_gemma":[0.033876363,0.00063348905,0.0015387455,0.005981235,0.0008989126,0.0049174097,0.001749856,0.0015728769,0.0012879224],"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":[0.0032793866,0.0005141418,0.005910326,0.0018725473,0.0006967035,0.000052218787,0.00023864598,0.014980315,0.0028661548,0.011139917,0.00545691,0.95299274],"study_design_scores_gemma":[0.002849925,0.006186087,0.0364757,0.001569163,0.0028413034,0.002864637,0.0020806629,0.7391214,0.020421488,0.13338959,0.051958073,0.00024197531],"about_ca_topic_score_codex":0.0019348033,"about_ca_topic_score_gemma":0.0036228143,"teacher_disagreement_score":0.011896611,"about_ca_system_score_codex":0.001336495,"about_ca_system_score_gemma":0.0018186434,"threshold_uncertainty_score":0.06291604},"labels":[],"label_agreement":null},{"id":"W2140617045","doi":"","title":"Application of data mining techniques for medical image classification","year":2001,"lang":"en","type":"article","venue":"ACM Multimedia","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":311,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Association rule learning; Computer science; Categorization; Mammography; Data mining; Breast cancer; Artificial intelligence; Artificial neural network; Anomaly detection; Contextual image classification; Pattern recognition (psychology); Image (mathematics); Machine learning; Cancer; Medicine","score_opus":0.06693477581833332,"score_gpt":0.36358705227625665,"score_spread":0.29665227645792336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140617045","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04780476,0.009684786,0.92880684,0.0031368968,0.0005855324,0.0005056557,0.0015376236,0.0025844772,0.0053534815],"genre_scores_gemma":[0.3086364,0.0058455025,0.67927086,0.0005727809,0.00042200394,0.00033147456,0.0019959195,0.00012445859,0.0028005894],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983589,0.0002889301,0.000256691,0.00019950204,0.0008323081,0.00006372383],"domain_scores_gemma":[0.9952055,0.0026420737,0.0003887445,0.00045814208,0.0011935025,0.00011199473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024666896,0.0006650204,0.000994207,0.0055020107,0.00063771853,0.0021827423,0.0012877806,0.0011276309,0.001796026],"category_scores_gemma":[0.008841845,0.00034502667,0.0011424322,0.0045428695,0.0005483444,0.001156868,0.0008992943,0.0014023561,0.001075799],"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":[0.0002914564,0.00033235992,0.011259779,0.0007634738,0.00029241468,0.0004234319,0.0001856722,0.009678897,0.01670489,0.0040058773,0.0068323687,0.9492294],"study_design_scores_gemma":[0.00016719966,0.0006328303,0.019938014,0.00057745114,0.00086050294,0.0058757565,0.0006005303,0.7408517,0.1042798,0.05108702,0.07499322,0.00013596761],"about_ca_topic_score_codex":0.0012933114,"about_ca_topic_score_gemma":0.001454806,"teacher_disagreement_score":0.0055020107,"about_ca_system_score_codex":0.0004961986,"about_ca_system_score_gemma":0.0008512942,"threshold_uncertainty_score":0.013045251},"labels":[],"label_agreement":null},{"id":"W2140677665","doi":"10.1080/713827182","title":"Web-log cleaning for constructing sequential classifiers","year":2003,"lang":"en","type":"article","venue":"Applied Artificial Intelligence","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Association rule learning; Data mining; Feature selection; Machine learning; Web server; Construct (python library); Information retrieval; Artificial intelligence; World Wide Web; The Internet","score_opus":0.07602961379321414,"score_gpt":0.3056663072595603,"score_spread":0.22963669346634613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140677665","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036588922,0.00014634476,0.9567222,0.00015786756,0.000063838605,0.0002851468,0.00081592327,0.004397353,0.000822385],"genre_scores_gemma":[0.250254,0.00015038409,0.74282426,0.00011159494,0.0001027114,0.0007093362,0.0039700833,0.00022777701,0.0016498389],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9981353,0.00034556183,0.00019467331,0.0004901888,0.00069251214,0.00014177732],"domain_scores_gemma":[0.99333596,0.0031128367,0.00047363396,0.0014978318,0.0014014593,0.00017826632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028968153,0.0011564691,0.0017960535,0.0029691064,0.0011202109,0.0011576909,0.0018224542,0.0013009538,0.0026687928],"category_scores_gemma":[0.01492979,0.000891938,0.0013392511,0.0020679848,0.00041156064,0.0027461932,0.0011226577,0.0017158883,0.0021790038],"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":[0.0003952886,0.000647286,0.024082545,0.00024957146,0.00019541058,0.00040746763,0.00022780916,0.19848311,0.009164783,0.0077070366,0.009982267,0.7484575],"study_design_scores_gemma":[0.000013333716,0.00004944608,0.0009888938,0.000013239065,0.00002424424,0.000081356055,0.000024634204,0.98542386,0.003626819,0.007929966,0.001812915,0.000011222333],"about_ca_topic_score_codex":0.00632715,"about_ca_topic_score_gemma":0.0071003945,"teacher_disagreement_score":0.00632715,"about_ca_system_score_codex":0.0007734487,"about_ca_system_score_gemma":0.0026529713,"threshold_uncertainty_score":0.015320003},"labels":[],"label_agreement":null},{"id":"W2141008330","doi":"10.1145/1982185.1982393","title":"Frequent itemset mining of uncertain data streams using the damped window model","year":2011,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Data mining; Computer science; Window (computing); Data stream mining; STREAMS; Data modeling; Database","score_opus":0.3111343591625202,"score_gpt":0.3358582583869379,"score_spread":0.0247238992244177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141008330","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03411274,0.00056429044,0.96452045,0.00014864598,0.000042213916,0.00005902362,0.00021999565,0.00018383357,0.00014876993],"genre_scores_gemma":[0.50844085,0.0010968436,0.48810583,0.00009949111,0.00015290033,0.00025429516,0.0010717623,0.00004039954,0.0007376498],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973043,0.0007629147,0.0004958067,0.0006500161,0.0006425029,0.00014452435],"domain_scores_gemma":[0.9899479,0.0072632427,0.0010147112,0.00070833066,0.00082599913,0.00023992505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004586101,0.0006929513,0.0023293344,0.0021711139,0.0005473329,0.0017437803,0.0019200615,0.0011271917,0.0006451301],"category_scores_gemma":[0.015337994,0.0006196234,0.0015652551,0.0028570462,0.0006065429,0.004332458,0.0008854424,0.0012311713,0.00023011322],"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":[0.0009433635,0.0003166036,0.011531588,0.0005047898,0.00070589833,0.0009941091,0.0005557372,0.7559486,0.008287518,0.032370187,0.0022005944,0.18564099],"study_design_scores_gemma":[0.0000149137295,0.000050889244,0.00037486624,0.00000940668,0.00002298867,0.00007799858,0.000019117091,0.99035233,0.0005830423,0.008196179,0.0002893997,0.000008852295],"about_ca_topic_score_codex":0.0020510284,"about_ca_topic_score_gemma":0.0014541576,"teacher_disagreement_score":0.004586101,"about_ca_system_score_codex":0.00048878015,"about_ca_system_score_gemma":0.00072818465,"threshold_uncertainty_score":0.024253905},"labels":[],"label_agreement":null},{"id":"W2141035746","doi":"10.3141/1886-04","title":"Using Decision Trees to Improve the Accuracy of Vehicle Signature Reidentification","year":2004,"lang":"en","type":"article","venue":"Transportation Research Record Journal of the Transportation Research Board","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Windsor","funders":"","keywords":"Induction loop; Decision tree; Signature (topology); Vehicle tracking system; Computer science; Tree (set theory); Detector; Process (computing); Tracking (education); Work (physics); Data mining; Artificial intelligence; Engineering; Mathematics; Segmentation; Telecommunications","score_opus":0.10733580649659219,"score_gpt":0.41561695408306437,"score_spread":0.3082811475864722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141035746","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16069415,0.0027234335,0.82447666,0.00084002333,0.00036386526,0.00025833375,0.0014291187,0.004750489,0.0044639097],"genre_scores_gemma":[0.6263163,0.0008558299,0.36665374,0.00027584258,0.00023642843,0.00016734099,0.0033375972,0.00026539832,0.0018915718],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9949502,0.0021476508,0.0005379139,0.00080932805,0.0011817267,0.00037325555],"domain_scores_gemma":[0.96554095,0.026158422,0.0011033139,0.0018642488,0.0049527045,0.0003803566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008775678,0.0018189913,0.0022432148,0.0044131815,0.0010729751,0.0017787403,0.0020304043,0.0018101601,0.00161286],"category_scores_gemma":[0.03580555,0.0006446271,0.0012988206,0.0034129152,0.00040832325,0.00319735,0.001326513,0.0024164577,0.0016486956],"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":[0.00064706523,0.00045845303,0.01564703,0.00024499776,0.0003097186,0.0002354429,0.00026634053,0.35355312,0.0035217302,0.0030159894,0.009050423,0.6130497],"study_design_scores_gemma":[0.00003595728,0.00008122587,0.0013462041,0.0000321907,0.0000613799,0.000063735155,0.00004878502,0.9890484,0.0025513107,0.0051257936,0.0015830408,0.00002187685],"about_ca_topic_score_codex":0.0058727833,"about_ca_topic_score_gemma":0.0051842234,"teacher_disagreement_score":0.008775678,"about_ca_system_score_codex":0.0008529868,"about_ca_system_score_gemma":0.0013242624,"threshold_uncertainty_score":0.0464108},"labels":[],"label_agreement":null},{"id":"W2142103633","doi":"10.1109/tkde.2006.172","title":"Discovering Frequent Closed Partial Orders from Strings","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; National Science Foundation","keywords":"Computer science; Multiset; Data mining; String (physics); Pruning; Set (abstract data type); Knowledge extraction; Order (exchange); Theoretical computer science; Mathematics","score_opus":0.017260913842518027,"score_gpt":0.24542276892658657,"score_spread":0.22816185508406855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142103633","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27222303,0.001294818,0.71563655,0.00068417593,0.00006437194,0.00043840907,0.005819207,0.0019859548,0.001853438],"genre_scores_gemma":[0.41132307,0.00078748417,0.5706759,0.00019535249,0.000081608756,0.00040109822,0.015236661,0.00014945013,0.0011494062],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9971616,0.00046726078,0.00041012443,0.0005759661,0.0011708846,0.00021424454],"domain_scores_gemma":[0.9869489,0.008455784,0.0014018129,0.0013166936,0.0015332801,0.00034353998],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014858709,0.00082628714,0.0016507729,0.004723179,0.0010166237,0.0019181719,0.0010986144,0.00096252654,0.0009231555],"category_scores_gemma":[0.015011779,0.0005743806,0.001394089,0.004411127,0.00089753006,0.0034320334,0.0011923896,0.0011497282,0.00044516154],"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":[0.001060183,0.00074955804,0.053015396,0.0016234518,0.00044575753,0.0043911524,0.0016661453,0.14089273,0.03525902,0.05267023,0.008462062,0.6997643],"study_design_scores_gemma":[0.00009789277,0.0003136003,0.009357158,0.00015384665,0.00011783261,0.002682037,0.00069113466,0.7034766,0.019036468,0.25361317,0.010365211,0.00009503088],"about_ca_topic_score_codex":0.0015371002,"about_ca_topic_score_gemma":0.0026196726,"teacher_disagreement_score":0.004723179,"about_ca_system_score_codex":0.0005395763,"about_ca_system_score_gemma":0.0019184019,"threshold_uncertainty_score":0.007858098},"labels":[],"label_agreement":null},{"id":"W2142807487","doi":"10.1109/dexa.2003.1232075","title":"Parallel association rule mining with minimum inter-processor communication","year":2004,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Association rule learning; Apriori algorithm; Scalability; Data mining; Node (physics); Parallel algorithm; Distributed computing; Parallel computing; Database","score_opus":0.014345585813829807,"score_gpt":0.24780350635039755,"score_spread":0.23345792053656775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142807487","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031501815,0.0004426677,0.9593432,0.00042071054,0.00005840982,0.00023735476,0.00021217117,0.0043883864,0.003395354],"genre_scores_gemma":[0.17016926,0.00035226738,0.8239071,0.00014604315,0.00013181473,0.0006446301,0.00092132995,0.00021123438,0.0035163201],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99779177,0.0005752324,0.00024402185,0.0005023164,0.000720006,0.00016666671],"domain_scores_gemma":[0.9948427,0.0019382106,0.00035304468,0.0018560094,0.0008615653,0.00014849087],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016617364,0.0010450861,0.0014346875,0.0014583493,0.0009310809,0.0016512234,0.002537045,0.0006761907,0.002613141],"category_scores_gemma":[0.008289615,0.000728864,0.000816314,0.0028667797,0.0005667612,0.002855426,0.0015317949,0.0009187011,0.00241546],"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":[0.0014718382,0.00055555045,0.004537369,0.0003783233,0.00024763547,0.0005126247,0.0002794221,0.10571893,0.02309317,0.013577259,0.01094002,0.83868784],"study_design_scores_gemma":[0.00043849324,0.0004558141,0.0014227002,0.000032660995,0.00016806374,0.0010821729,0.00016153116,0.8989502,0.025779366,0.05525649,0.016205309,0.00004722492],"about_ca_topic_score_codex":0.0014270582,"about_ca_topic_score_gemma":0.0021011152,"teacher_disagreement_score":0.002613141,"about_ca_system_score_codex":0.00043087325,"about_ca_system_score_gemma":0.001808257,"threshold_uncertainty_score":0.008788168},"labels":[],"label_agreement":null},{"id":"W2142996119","doi":"10.1109/icppw.2006.63","title":"PLT- Positional Lexicographic Tree: A New Structure for Mining Frequent Itemsets","year":2006,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Lexicographical order; Computer science; Correctness; Data mining; Association rule learning; Representation (politics); Set (abstract data type); Tree structure; Tree (set theory); Database; Data structure; Search engine indexing; Theoretical computer science; Information retrieval; Algorithm; Mathematics; Programming language","score_opus":0.01153421255386396,"score_gpt":0.24037075264575627,"score_spread":0.2288365400918923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142996119","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010810059,0.0005801192,0.97981066,0.00057123153,0.00013108911,0.0003700629,0.0031304292,0.0024521337,0.002144245],"genre_scores_gemma":[0.042005878,0.0004861833,0.9505106,0.00017756433,0.00007789407,0.0003833024,0.0052480586,0.00014994269,0.000960537],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986368,0.00032837156,0.00024997638,0.00021628577,0.0004912753,0.00007724272],"domain_scores_gemma":[0.9969537,0.0013135105,0.0003414613,0.0005570831,0.0007332188,0.00010108402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001669491,0.00051628903,0.0008965164,0.004301268,0.0009256265,0.0018475297,0.0014746183,0.0011007127,0.0029550341],"category_scores_gemma":[0.009683285,0.0005294275,0.001033434,0.0066609574,0.0008555517,0.0045017507,0.001513648,0.0009839832,0.0018898363],"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":[0.000508656,0.00019920492,0.008648311,0.0014640306,0.00017850006,0.0011630047,0.0009827892,0.027375242,0.01755578,0.109876804,0.02982764,0.80222005],"study_design_scores_gemma":[0.00026234947,0.00076101633,0.0039604944,0.0005445311,0.00024191772,0.006509966,0.0009095512,0.5205091,0.029124929,0.30708003,0.12989287,0.00020318592],"about_ca_topic_score_codex":0.0010930186,"about_ca_topic_score_gemma":0.0014136699,"teacher_disagreement_score":0.004301268,"about_ca_system_score_codex":0.000567492,"about_ca_system_score_gemma":0.0018730994,"threshold_uncertainty_score":0.00988555},"labels":[],"label_agreement":null},{"id":"W2143317258","doi":"10.1109/tsmcb.2005.852983","title":"Highly scalable and robust rule learner: performance evaluation and comparison","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Scalability; Data mining; Missing data; Set (abstract data type); Business intelligence; Simplicity; State (computer science); Knowledge extraction; Artificial intelligence; Machine learning; Algorithm; Database","score_opus":0.0260826067644924,"score_gpt":0.2476861809748204,"score_spread":0.221603574210328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143317258","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45616147,0.02326797,0.4539287,0.0025417695,0.0017404008,0.0018437223,0.0077770134,0.03742441,0.015314484],"genre_scores_gemma":[0.6376303,0.004674929,0.33386526,0.0005989633,0.00042955732,0.0009028223,0.014529449,0.0012738619,0.0060949023],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98940724,0.0032613308,0.0011691103,0.0019726132,0.003688354,0.00050145254],"domain_scores_gemma":[0.9673661,0.022524403,0.0008796877,0.0033834416,0.0050257556,0.0008206394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015088104,0.002169662,0.0032125758,0.0032048603,0.00085911097,0.0021017932,0.0047909613,0.0034007244,0.004078977],"category_scores_gemma":[0.036708932,0.00059286447,0.0011429802,0.004004532,0.00087257003,0.0044333125,0.002268794,0.0024661252,0.0025091316],"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":[0.004727763,0.0016769762,0.009076509,0.00086144253,0.0010965967,0.00043772766,0.00013357885,0.38529754,0.002989774,0.0017898666,0.01894886,0.57296336],"study_design_scores_gemma":[0.0004939095,0.0008344757,0.0021093094,0.00004785321,0.00014494183,0.00027591377,0.00010327592,0.98300296,0.0076316437,0.0024142878,0.0028845323,0.00005696551],"about_ca_topic_score_codex":0.012348138,"about_ca_topic_score_gemma":0.0057204557,"teacher_disagreement_score":0.015088104,"about_ca_system_score_codex":0.0016856005,"about_ca_system_score_gemma":0.0024325266,"threshold_uncertainty_score":0.07979441},"labels":[],"label_agreement":null},{"id":"W2144393799","doi":"","title":"METODOLOGÍA PARA UN SCORING DE CLIENTES SIN REFERENCIAS CREDITICIAS","year":2013,"lang":"es","type":"article","venue":"Redalyc (Universidad Autónoma del Estado de México)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Balanced scorecard; CHAID; Humanities; Geography; Political science; Business; Computer science; Philosophy; Process management; Artificial intelligence; Decision tree","score_opus":0.037575713336762656,"score_gpt":0.26750639022627204,"score_spread":0.22993067688950938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144393799","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21969368,0.0005114562,0.76043385,0.0019196765,0.00009425388,0.0016740538,0.0033102925,0.00069155724,0.011671186],"genre_scores_gemma":[0.7383127,0.0005774149,0.24791104,0.00013683086,0.00006725702,0.0013691029,0.0021023185,0.00005389692,0.009469382],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966474,0.0017491061,0.00029329205,0.0004937671,0.0006037369,0.00021250799],"domain_scores_gemma":[0.99556255,0.0020057196,0.0005819102,0.0004246082,0.0012815725,0.00014356455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050569624,0.00089376874,0.0013791523,0.0021505204,0.00097242487,0.0030128232,0.001428611,0.0011228931,0.008071347],"category_scores_gemma":[0.015783664,0.0003880955,0.0008641059,0.0036769034,0.00055947946,0.0015964843,0.0013993843,0.001320406,0.001080887],"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":[0.00096224505,0.00075019844,0.2075633,0.00076227327,0.0003797675,0.00045574407,0.002367233,0.15925275,0.0041395654,0.05466151,0.011505249,0.5572002],"study_design_scores_gemma":[0.00014275419,0.0004266716,0.052940387,0.0001772624,0.0001707708,0.00037941796,0.002835909,0.8736307,0.0048448807,0.04794619,0.01641944,0.00008557057],"about_ca_topic_score_codex":0.017950317,"about_ca_topic_score_gemma":0.01372132,"teacher_disagreement_score":0.017950317,"about_ca_system_score_codex":0.0026371654,"about_ca_system_score_gemma":0.003053225,"threshold_uncertainty_score":0.03569168},"labels":[],"label_agreement":null},{"id":"W2144839111","doi":"10.1109/bibm.2009.51","title":"Discovering Temporal Associations among Significant Changes in Gene Expression","year":2009,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Multivariate statistics; Computer science; Data mining; Multivariate analysis; Change detection; False discovery rate; Expression (computer science); Artificial intelligence; Gene; Machine learning; Computational biology; Biology; Genetics","score_opus":0.018934607723844882,"score_gpt":0.2561674505588383,"score_spread":0.23723284283499343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144839111","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52323294,0.0019056457,0.46794966,0.0009895661,0.000088281275,0.00010323548,0.0024615175,0.0010992698,0.0021698],"genre_scores_gemma":[0.9106133,0.0005530675,0.086190134,0.00011014805,0.00009551593,0.000088151304,0.0017954992,0.000054592954,0.0004995583],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989754,0.00019606776,0.000093927316,0.00035580125,0.00029453222,0.00008426667],"domain_scores_gemma":[0.9912021,0.005413591,0.0019000391,0.0005515931,0.0007262332,0.00020642528],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019134504,0.00035843684,0.0006027734,0.003376505,0.00048805343,0.0009163177,0.00067577715,0.00047905173,0.00087694207],"category_scores_gemma":[0.010877853,0.00030333872,0.0007127139,0.003278145,0.0005733002,0.0012201326,0.00059317704,0.0008559337,0.0002654547],"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":[0.00089322624,0.00050690497,0.46025795,0.0006463149,0.0006520864,0.0021154312,0.0010752947,0.05202468,0.044706106,0.022988668,0.0042310585,0.40990233],"study_design_scores_gemma":[0.00009175748,0.00048141368,0.26438633,0.00014968438,0.00054960087,0.001970207,0.0011267709,0.5778255,0.023215497,0.115495086,0.014542982,0.00016524727],"about_ca_topic_score_codex":0.0029162783,"about_ca_topic_score_gemma":0.004384043,"teacher_disagreement_score":0.003376505,"about_ca_system_score_codex":0.00042980257,"about_ca_system_score_gemma":0.0008689744,"threshold_uncertainty_score":0.010119379},"labels":[],"label_agreement":null},{"id":"W2145034657","doi":"","title":"Predicting UNIX Command Lines: Adjusting to User Patterns","year":2000,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Personalization; User interface; Human–computer interaction; Unix; User modeling; Simple (philosophy); Macro; Interface (matter); Process (computing); Natural user interface; User interface design; Variety (cybernetics); User experience design; Artificial intelligence; Operating system; World Wide Web; Software; Programming language","score_opus":0.01762623480869171,"score_gpt":0.258106695062692,"score_spread":0.2404804602540003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145034657","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71042675,0.0003935128,0.27197528,0.0010053504,0.00006585258,0.00030052065,0.0019062901,0.00975845,0.0041679833],"genre_scores_gemma":[0.89367956,0.00015033186,0.10270854,0.00012218807,0.000025519459,0.00010069894,0.001189724,0.00029644748,0.001726878],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984901,0.00043113233,0.00011157352,0.0005763939,0.0002949751,0.00009584835],"domain_scores_gemma":[0.9927406,0.0039829747,0.0007560193,0.0011865473,0.0010850389,0.00024881135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002090789,0.0007540168,0.0007172443,0.0017244321,0.0005256209,0.0014792708,0.0010468075,0.0007711161,0.0019159145],"category_scores_gemma":[0.019163383,0.00035222902,0.0003307453,0.001620961,0.0003787498,0.0023595619,0.0006622476,0.00090891134,0.0015257405],"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":[0.0006990534,0.00037937998,0.37701637,0.00014603599,0.00009877361,0.00024782593,0.0013319098,0.03354349,0.0076446603,0.0012955661,0.007279686,0.57031727],"study_design_scores_gemma":[0.0000335852,0.00023383622,0.08077525,0.000039547875,0.000056332334,0.00033498273,0.0005925882,0.8975807,0.011014185,0.004488977,0.004765594,0.00008446016],"about_ca_topic_score_codex":0.007797126,"about_ca_topic_score_gemma":0.009953786,"teacher_disagreement_score":0.007797126,"about_ca_system_score_codex":0.0005302226,"about_ca_system_score_gemma":0.0005311617,"threshold_uncertainty_score":0.015503466},"labels":[],"label_agreement":null},{"id":"W2145050101","doi":"10.1109/cnsr.2007.5","title":"A Novel Approach for Frequent Phrase Mining in Web Search Engine Query Streams","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":16,"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 New Brunswick","funders":"Atlantic Canada Opportunities Agency","keywords":"Computer science; Phrase; Set (abstract data type); Data stream mining; Data mining; Information retrieval; Recommender system; Phrase search; Data stream; Web query classification; Web search query; Search engine; Artificial intelligence","score_opus":0.04000222621762329,"score_gpt":0.2943553656368082,"score_spread":0.2543531394191849,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145050101","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003564347,0.00021526145,0.995275,0.00009940123,0.000026526071,0.00009168219,0.00014678505,0.00030489438,0.00027605976],"genre_scores_gemma":[0.057708915,0.00043194997,0.93989635,0.00012456339,0.00014139563,0.00023107104,0.00067676976,0.000064446256,0.000724636],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99635077,0.0009132443,0.00042749743,0.0007925654,0.0013894311,0.00012654577],"domain_scores_gemma":[0.99483335,0.0026907376,0.0005381696,0.0007049847,0.0011056117,0.0001270454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029317944,0.0009556494,0.001398011,0.0035285018,0.0007843183,0.0022129714,0.0019155061,0.0010863163,0.0011811677],"category_scores_gemma":[0.011263042,0.00052670646,0.0014210138,0.0043156403,0.00067629997,0.0041637877,0.0012944062,0.0015215114,0.0008819969],"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":[0.00054738135,0.00039476325,0.008114827,0.00084443117,0.00027477535,0.0006295678,0.00088280794,0.03768753,0.027876794,0.061655384,0.0069645112,0.8541273],"study_design_scores_gemma":[0.00007151407,0.0002759579,0.0018491009,0.000066078544,0.00011246429,0.0014645054,0.00024397975,0.9210138,0.01240061,0.045525312,0.016887812,0.000089001296],"about_ca_topic_score_codex":0.001495713,"about_ca_topic_score_gemma":0.0014927272,"teacher_disagreement_score":0.0035285018,"about_ca_system_score_codex":0.0006021905,"about_ca_system_score_gemma":0.0011662046,"threshold_uncertainty_score":0.015504956},"labels":[],"label_agreement":null},{"id":"W2146606092","doi":"10.1145/1824795.1824798","title":"A taxonomy of sequential pattern mining algorithms","year":2010,"lang":"en","type":"review","venue":"ACM Computing Surveys","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":396,"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 Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Taxonomy (biology); Tree traversal; Sequential Pattern Mining; Key (lock); Data mining; Web mining; Information retrieval; Artificial intelligence; Machine learning; Algorithm; Web page; World Wide Web","score_opus":0.12317318612398061,"score_gpt":0.3469654630301945,"score_spread":0.2237922769062139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146606092","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036801652,0.19116078,0.7796493,0.004159501,0.00091108587,0.000892119,0.001177805,0.0014406609,0.016928466],"genre_scores_gemma":[0.022255018,0.16638611,0.80091184,0.0010761674,0.0010279571,0.0009242094,0.0023983223,0.00015314916,0.004867184],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99440444,0.0011186973,0.0009690289,0.0010208173,0.0023223625,0.00016459389],"domain_scores_gemma":[0.9894288,0.005581796,0.00059567665,0.0007946815,0.003428592,0.00017047375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0059046387,0.0020099871,0.0022541936,0.011279891,0.0011234414,0.004337171,0.0040127775,0.002146513,0.0033803373],"category_scores_gemma":[0.015699243,0.00096109434,0.0017564804,0.019934941,0.0012800246,0.008406404,0.0013475489,0.0025316363,0.004808785],"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":[0.00006199003,0.00015051896,0.002503383,0.003979444,0.00013682537,0.00019652727,0.0002445334,0.0070048473,0.0011199511,0.075721405,0.016704103,0.89217657],"study_design_scores_gemma":[0.00008593519,0.00046530837,0.0031547486,0.0040734224,0.0002493643,0.004602333,0.00046634566,0.10402314,0.0046239784,0.33546734,0.54258335,0.00020470063],"about_ca_topic_score_codex":0.0022440646,"about_ca_topic_score_gemma":0.0016849067,"teacher_disagreement_score":0.011279891,"about_ca_system_score_codex":0.0015504756,"about_ca_system_score_gemma":0.0037711402,"threshold_uncertainty_score":0.031227112},"labels":[],"label_agreement":null},{"id":"W2147646759","doi":"10.1145/1822327.1822338","title":"Estimation of the number of cliques in a random graph","year":2010,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Exponential random graph models; Random graph; Mathematics; Combinatorics; Induced subgraph isomorphism problem; Vertex (graph theory); Clique; Clique graph; Graph; Discrete mathematics; Line graph; Graph power; Voltage graph","score_opus":0.0077685051943247796,"score_gpt":0.27690162447108735,"score_spread":0.2691331192767626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147646759","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04840439,0.00037267964,0.9489064,0.0003027348,0.000022153064,0.000085538944,0.00030825066,0.00080724515,0.0007906666],"genre_scores_gemma":[0.44209257,0.0005656774,0.5545599,0.00012161753,0.00010956633,0.00020213098,0.001379388,0.00018595604,0.0007832657],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974699,0.00089264446,0.00013516088,0.00071508327,0.00062213687,0.00016510143],"domain_scores_gemma":[0.9522134,0.037970796,0.003049767,0.0039884564,0.0021582923,0.0006192941],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037966534,0.00084088295,0.0015473496,0.004070161,0.00082342845,0.0014728275,0.0022524719,0.0016354377,0.0012954546],"category_scores_gemma":[0.044918757,0.00064257707,0.0010511075,0.0021085027,0.0015715348,0.005072338,0.001197348,0.0013979132,0.0006048215],"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":[0.00044609958,0.00024757514,0.057864495,0.0004742971,0.00028988693,0.00022755547,0.00045821455,0.6556274,0.009662866,0.065094896,0.0038999605,0.20570672],"study_design_scores_gemma":[0.000018563644,0.00003930995,0.0032125139,0.000028481916,0.00001896409,0.00013073985,0.00006811871,0.95399624,0.0033466448,0.03757952,0.0015257475,0.000035077417],"about_ca_topic_score_codex":0.0025819603,"about_ca_topic_score_gemma":0.0023755378,"teacher_disagreement_score":0.004070161,"about_ca_system_score_codex":0.0009980891,"about_ca_system_score_gemma":0.00081477105,"threshold_uncertainty_score":0.020078838},"labels":[],"label_agreement":null},{"id":"W2147840212","doi":"10.1007/978-3-540-39935-3_22","title":"Enhanced phrase-based document clustering using Self-Organizing Map (SOM) architectures","year":2004,"lang":"en","type":"book-chapter","venue":"Studies in fuzziness and soft computing","topic":"Data Mining Algorithms and Applications","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 Waterloo","funders":"","keywords":"Self-organizing map; Phrase; Cluster analysis; Computer science; Artificial intelligence; Natural language processing; Document clustering","score_opus":0.035314826928261024,"score_gpt":0.2978583838462532,"score_spread":0.26254355691799214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147840212","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030242411,0.0009903006,0.962436,0.000116614996,0.0001437621,0.00008776284,0.0004471751,0.0030157592,0.0025201635],"genre_scores_gemma":[0.13886724,0.0006098635,0.8530227,0.000087248045,0.00011801047,0.000115037146,0.001383789,0.0002217754,0.005574328],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99951744,0.000081237864,0.000041884283,0.0000938238,0.0002296419,0.00003600009],"domain_scores_gemma":[0.9989868,0.00030845287,0.000045792887,0.00012738082,0.0004946854,0.000036832484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006141935,0.0005531576,0.0010194426,0.0014676277,0.00050744525,0.001182891,0.0012707065,0.00074758544,0.0025241985],"category_scores_gemma":[0.0019949917,0.0002833939,0.000750732,0.003156238,0.00029209544,0.0015313347,0.0009192962,0.00072087103,0.001771618],"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":[0.00032083585,0.00017725574,0.0008116447,0.00026513083,0.00013087406,0.00009579097,0.00018842988,0.02659554,0.03882381,0.0033420278,0.007186589,0.92206204],"study_design_scores_gemma":[0.00005143921,0.00015054166,0.0025083555,0.000031528234,0.00012938007,0.00031816043,0.0001246778,0.93542844,0.04314125,0.010048111,0.0080014095,0.00006666213],"about_ca_topic_score_codex":0.0034341982,"about_ca_topic_score_gemma":0.00525732,"teacher_disagreement_score":0.0034341982,"about_ca_system_score_codex":0.00040703086,"about_ca_system_score_gemma":0.00060582766,"threshold_uncertainty_score":0.008444309},"labels":[],"label_agreement":null},{"id":"W2148900457","doi":"10.1109/icdm.2008.43","title":"SCS: A New Similarity Measure for Categorical Sequences","year":2008,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","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":"Université de Sherbrooke","funders":"","keywords":"Categorical variable; Similarity (geometry); Computer science; Matching (statistics); Task (project management); Data mining; Artificial intelligence; Pattern recognition (psychology); Range (aeronautics); Sequence (biology); Measure (data warehouse); Similarity measure; Noise (video); Process (computing); Natural language processing; Machine learning; Mathematics; Statistics; Image (mathematics)","score_opus":0.07981175858382283,"score_gpt":0.2826599722391048,"score_spread":0.20284821365528194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148900457","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13491929,0.003861274,0.8459577,0.00043345278,0.00044193186,0.0006233507,0.0056322166,0.0018376567,0.006293056],"genre_scores_gemma":[0.5070941,0.0011418427,0.47865275,0.00027952399,0.0004866923,0.0009601855,0.00888536,0.00020741815,0.0022921478],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9945257,0.00075402466,0.00096926955,0.000722228,0.0028338812,0.00019492411],"domain_scores_gemma":[0.9880953,0.005378303,0.0017305865,0.0011477647,0.0031721974,0.0004758859],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002262893,0.0007095902,0.0014018827,0.014709465,0.0008942795,0.0018357596,0.0016326506,0.0012565952,0.002567466],"category_scores_gemma":[0.017725686,0.00020441452,0.0010892743,0.014356403,0.0014243727,0.005240633,0.002117217,0.001013613,0.0010901915],"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":[0.0010653705,0.00035379082,0.058420483,0.0017606197,0.0006281713,0.00044521087,0.0013004802,0.04058157,0.025341019,0.05424673,0.015838725,0.8000178],"study_design_scores_gemma":[0.00020528836,0.0019386422,0.04745434,0.00044899652,0.00032292667,0.0029821547,0.0018281804,0.65696955,0.02227236,0.20400098,0.061220754,0.0003558924],"about_ca_topic_score_codex":0.0019157451,"about_ca_topic_score_gemma":0.0017834515,"teacher_disagreement_score":0.014709465,"about_ca_system_score_codex":0.0011303631,"about_ca_system_score_gemma":0.0016657265,"threshold_uncertainty_score":0.01196748},"labels":[],"label_agreement":null},{"id":"W2149495447","doi":"10.1109/icdm.2005.99","title":"Mining Patterns That Respond to Actions","year":2006,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Focus (optics); Data science; State (computer science); Data mining","score_opus":0.041331504845930934,"score_gpt":0.28510241678512327,"score_spread":0.24377091193919234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149495447","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5183361,0.0039508627,0.4388779,0.0072074067,0.0006342784,0.0011828502,0.013597809,0.0033256307,0.012887094],"genre_scores_gemma":[0.7601293,0.0020280967,0.21984534,0.0011324988,0.0002937525,0.00053454406,0.01222904,0.00022346659,0.0035839588],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964438,0.0005990116,0.00039617895,0.0012194363,0.0010816483,0.00025999796],"domain_scores_gemma":[0.98858684,0.0054525244,0.002468428,0.0016272861,0.0014669988,0.00039788688],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021537368,0.0010613222,0.0011414689,0.0049389573,0.0009505819,0.0023498489,0.0018072702,0.0017287395,0.0021148417],"category_scores_gemma":[0.016860288,0.0005682146,0.0013678285,0.004425986,0.0009817007,0.0047256523,0.0014116344,0.0015454347,0.0013616016],"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":[0.0012807375,0.0010859712,0.26940638,0.0024286506,0.0014653344,0.003176027,0.002509164,0.03245209,0.032734983,0.029653553,0.022366647,0.60144037],"study_design_scores_gemma":[0.0003429729,0.0014430536,0.1573039,0.0011750463,0.0021129474,0.0055425228,0.006226612,0.4072786,0.053040255,0.27550644,0.08959678,0.00043097403],"about_ca_topic_score_codex":0.0014533361,"about_ca_topic_score_gemma":0.002022544,"teacher_disagreement_score":0.0049389573,"about_ca_system_score_codex":0.0005036216,"about_ca_system_score_gemma":0.0011355268,"threshold_uncertainty_score":0.011390209},"labels":[],"label_agreement":null},{"id":"W2150433972","doi":"10.1145/958942.958944","title":"Efficient dynamic mining of constrained frequent sets","year":2003,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":85,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; University of British Columbia","funders":"","keywords":"Computer science; Context (archaeology); Computation; Exploit; Process (computing); Set (abstract data type); Data mining; Function (biology); Component (thermodynamics); Association rule learning; Algorithm","score_opus":0.02206422575661429,"score_gpt":0.26971647157293405,"score_spread":0.24765224581631975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150433972","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04971014,0.00038001023,0.94725746,0.00022965914,0.000023387862,0.00015698417,0.00048364908,0.0009351385,0.00082351547],"genre_scores_gemma":[0.29939854,0.00032274693,0.6969597,0.00008380792,0.000056314508,0.00027906537,0.0021218404,0.000117662246,0.00066037953],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976305,0.00054825394,0.00020891384,0.000454629,0.0009604961,0.00019722624],"domain_scores_gemma":[0.988818,0.007849645,0.0007416127,0.0011988475,0.0011973148,0.00019469649],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020639924,0.00074351515,0.0015004713,0.003555853,0.0008334368,0.0014380915,0.0020157585,0.00087687024,0.0012586927],"category_scores_gemma":[0.020683946,0.00068254385,0.0008662645,0.0041895485,0.00055737305,0.0030653367,0.0015723222,0.0009170439,0.0004948013],"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":[0.00056158117,0.00022768886,0.008264381,0.00041677148,0.00018451946,0.00068065216,0.0004820435,0.19733585,0.012072898,0.022943018,0.0052801226,0.75155044],"study_design_scores_gemma":[0.000032010346,0.00008248608,0.000979432,0.000030153013,0.000031146745,0.00046057752,0.00015743398,0.9518961,0.005587383,0.03748089,0.0032409367,0.000021441721],"about_ca_topic_score_codex":0.0020089927,"about_ca_topic_score_gemma":0.0024419727,"teacher_disagreement_score":0.003555853,"about_ca_system_score_codex":0.0005963174,"about_ca_system_score_gemma":0.0013893018,"threshold_uncertainty_score":0.010915577},"labels":[],"label_agreement":null},{"id":"W2150564254","doi":"10.1109/anss.2007.6","title":"A Performance Evaluation of Distributed Framework for Mining Wireless Sensor Networks","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Data mining; Partition (number theory); Wireless sensor network; Association rule learning; Process (computing); Knowledge extraction; Representation (politics); Lexicographical order; Distributed database; Process mining; Data stream mining; Tree (set theory); Compressed sensing; Distributed computing; Machine learning; Work in process; Computer network; Engineering","score_opus":0.040137381660700314,"score_gpt":0.3176173248066985,"score_spread":0.2774799431459982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150564254","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31818908,0.0026346594,0.6606047,0.0007760465,0.00026036752,0.0003917422,0.0005747783,0.011555056,0.0050135083],"genre_scores_gemma":[0.7556339,0.0004614535,0.24127725,0.00008312019,0.000050092356,0.00019580367,0.0011405508,0.00014563333,0.0010121854],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960751,0.0012658589,0.00023020332,0.00059827627,0.0016039923,0.0002266],"domain_scores_gemma":[0.9924604,0.0040880446,0.00032070023,0.0012343342,0.0016543583,0.00024206661],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005931735,0.0008663726,0.0012868446,0.0015710734,0.0009028986,0.0010065003,0.0021453826,0.0009584735,0.0010643187],"category_scores_gemma":[0.014523413,0.00029327357,0.00045939806,0.0023529083,0.00055210147,0.002963136,0.0013184443,0.0006602734,0.00034402357],"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":[0.002543258,0.00050220574,0.008338277,0.00045599777,0.0003037491,0.00025451783,0.00023821065,0.5074285,0.013168934,0.008381921,0.006217843,0.4521666],"study_design_scores_gemma":[0.00007216864,0.0002237268,0.0007017569,0.000006427292,0.00002025886,0.000101643825,0.00005826653,0.992603,0.003948776,0.0013451847,0.00090805854,0.000010741437],"about_ca_topic_score_codex":0.006501223,"about_ca_topic_score_gemma":0.0047624786,"teacher_disagreement_score":0.006501223,"about_ca_system_score_codex":0.0014626726,"about_ca_system_score_gemma":0.0016133562,"threshold_uncertainty_score":0.0313704},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007803008,0.0015858274,0.9851151,0.001056134,0.00020160111,0.00009105446,0.00031163814,0.00048249596,0.0033531508],"genre_scores_gemma":[0.31451404,0.001873411,0.6765507,0.00062722,0.00063514384,0.00025066308,0.0015774913,0.00030085188,0.0036705115],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99187297,0.0032289317,0.000484297,0.0014076887,0.002538481,0.00046757807],"domain_scores_gemma":[0.9912418,0.004168655,0.0006740282,0.0017087483,0.0018398099,0.0003669517],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006538544,0.0011364558,0.0021955653,0.005617841,0.0015398778,0.0081944065,0.0035864557,0.0022258137,0.0051287822],"category_scores_gemma":[0.014912399,0.00083687744,0.0036286318,0.0051946067,0.0012463809,0.008015023,0.003057084,0.002801332,0.0017424187],"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":[0.00056620105,0.000517417,0.010096086,0.0007786528,0.0013179367,0.0005707039,0.001053694,0.02499255,0.010515593,0.16699712,0.021252496,0.7613415],"study_design_scores_gemma":[0.000058812777,0.00018277572,0.0037646207,0.00025423383,0.0007292874,0.0007526894,0.0008893063,0.6755484,0.005668349,0.2910421,0.020980924,0.00012843784],"about_ca_topic_score_codex":0.0026960047,"about_ca_topic_score_gemma":0.0030484363,"teacher_disagreement_score":0.0081944065,"about_ca_system_score_codex":0.0011783683,"about_ca_system_score_gemma":0.0015567398,"threshold_uncertainty_score":0.034579515},"labels":[],"label_agreement":null},{"id":"W2151827974","doi":"10.1109/ideas.2006.20","title":"Efficient Mining of Constrained Frequent Patterns from Streams","year":2006,"lang":"en","type":"article","venue":"Proceedings - International Database Engineering and Applications Symposium","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":16,"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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data stream mining; Focus (optics); Flood myth; Data mining; Web mining; Process (computing); STREAMS; Streaming data; Tree (set theory); Process mining; Data science; Work in process; World Wide Web; Web page; Computer network","score_opus":0.0051417285826871805,"score_gpt":0.20385736106929778,"score_spread":0.1987156324866106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151827974","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10597612,0.00073893275,0.8896286,0.00046414285,0.00005662291,0.00025371593,0.0013973813,0.00082218385,0.00066237507],"genre_scores_gemma":[0.43676677,0.000626539,0.5560045,0.00014264642,0.00013044845,0.0004182713,0.005132191,0.000089664805,0.00068898464],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99658823,0.0008507397,0.0005173124,0.00062007015,0.0011631628,0.00026052215],"domain_scores_gemma":[0.9840745,0.011411755,0.0014631368,0.0010272269,0.0017491743,0.0002742637],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030367668,0.00088896335,0.0020366663,0.003298104,0.0007514818,0.0018224076,0.0018046476,0.0011778701,0.0006443482],"category_scores_gemma":[0.021814968,0.0006912912,0.0010849936,0.003883914,0.00051778276,0.0032944602,0.0013598657,0.001192417,0.00033891402],"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":[0.0013739743,0.00073303434,0.03635221,0.0009865199,0.00063749234,0.0023290496,0.0013195196,0.27354136,0.018893788,0.023785764,0.010436225,0.629611],"study_design_scores_gemma":[0.000043393204,0.000070883776,0.0016174176,0.000035532474,0.000037357866,0.00030929895,0.0001861779,0.96681297,0.002468278,0.026986722,0.0014142268,0.00001775227],"about_ca_topic_score_codex":0.0018806601,"about_ca_topic_score_gemma":0.0024486633,"teacher_disagreement_score":0.003298104,"about_ca_system_score_codex":0.00040668223,"about_ca_system_score_gemma":0.0014332557,"threshold_uncertainty_score":0.016060174},"labels":[],"label_agreement":null},{"id":"W2151953639","doi":"10.1109/tkde.2005.166","title":"Fast algorithms for frequent itemset mining using FP-trees","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":552,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Data mining; Traverse; Association rule learning; Algorithm; Tree (set theory); Data structure; Tree structure; Trie; Prefix; Binary tree; Mathematics","score_opus":0.05517782314487753,"score_gpt":0.3067297556925058,"score_spread":0.2515519325476283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151953639","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004194064,0.0012566178,0.990008,0.00021948286,0.00011942866,0.00022719498,0.0004799875,0.0027604613,0.0007347819],"genre_scores_gemma":[0.024912206,0.0008922489,0.9714082,0.00008709006,0.00011184272,0.00055577,0.0013231467,0.00013815185,0.00057141786],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99528545,0.0011284762,0.0007426538,0.00076596654,0.0017806708,0.00029686195],"domain_scores_gemma":[0.98015,0.013016299,0.0013235909,0.0015650648,0.003760589,0.00018442806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063311206,0.0027101818,0.003150566,0.0074423607,0.002156128,0.0025594938,0.003521581,0.002636136,0.0043886886],"category_scores_gemma":[0.028531963,0.0017480087,0.0024248923,0.010387564,0.00077285303,0.006881258,0.0015517059,0.0026306754,0.005217967],"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":[0.00048198685,0.00026383516,0.0032428857,0.0008821056,0.00037620874,0.00036204892,0.00030725548,0.0569064,0.0044092834,0.017650485,0.01712701,0.8979905],"study_design_scores_gemma":[0.00033407198,0.00037995778,0.0016548272,0.00027508003,0.0002647925,0.001877789,0.00022775008,0.83985066,0.014175682,0.11238606,0.028409906,0.00016345677],"about_ca_topic_score_codex":0.0024232964,"about_ca_topic_score_gemma":0.0021189374,"teacher_disagreement_score":0.0074423607,"about_ca_system_score_codex":0.0010136531,"about_ca_system_score_gemma":0.002183775,"threshold_uncertainty_score":0.03348255},"labels":[],"label_agreement":null},{"id":"W2152320416","doi":"10.1109/bibm.2013.6732718","title":"Regrouping of pattern clusters to reveal characteristics of distinct classes and related classes","year":2013,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Pattern recognition (psychology); Entropy (arrow of time); Computer science; Artificial intelligence; Class (philosophy); Separable space; Data mining; Measure (data warehouse); Subspace topology; Mathematics","score_opus":0.01347225624646124,"score_gpt":0.241153297404486,"score_spread":0.22768104115802476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152320416","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23406714,0.00026279793,0.7604468,0.00024044572,0.0000573327,0.00043518256,0.0004583804,0.002233938,0.0017980204],"genre_scores_gemma":[0.3191013,0.00013288247,0.67702305,0.00007493589,0.00003100039,0.00022646121,0.0017112907,0.0002849749,0.0014140862],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904317,0.000113576665,0.000097558375,0.00040108827,0.0002531662,0.000091426926],"domain_scores_gemma":[0.996424,0.0008307227,0.0004557471,0.00122406,0.00092728005,0.0001380328],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013850525,0.0006927321,0.0010100049,0.0026828505,0.00087800686,0.0010249789,0.0007590012,0.0005397908,0.0011536238],"category_scores_gemma":[0.0055789095,0.00035491074,0.0010770023,0.0020005237,0.00064489746,0.0014426976,0.0011880284,0.00075944763,0.00068201136],"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":[0.0006621511,0.0004127268,0.027641697,0.0003353889,0.00029129867,0.000194804,0.001450082,0.03617255,0.09532703,0.0059272847,0.0035903943,0.8279945],"study_design_scores_gemma":[0.00014653878,0.00080018217,0.03841863,0.000113182294,0.00043934243,0.00097570923,0.002204076,0.7655838,0.13386056,0.037185606,0.020117566,0.00015479041],"about_ca_topic_score_codex":0.0015284445,"about_ca_topic_score_gemma":0.0024522382,"teacher_disagreement_score":0.0026828505,"about_ca_system_score_codex":0.0004243024,"about_ca_system_score_gemma":0.0009447816,"threshold_uncertainty_score":0.007324934},"labels":[],"label_agreement":null},{"id":"W2152322132","doi":"10.1109/icdm.2006.139","title":"Searching for Pattern Rules","year":2006,"lang":"en","type":"article","venue":"Proceedings","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Suffix tree; Data mining; Traverse; Computation; Set (abstract data type); Association rule learning; Metric (unit); Suffix; Algorithm; Artificial intelligence; Pattern recognition (psychology); Data structure","score_opus":0.015091992137644847,"score_gpt":0.2543717560116975,"score_spread":0.23927976387405264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152322132","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10160116,0.0022339383,0.8807653,0.0014642117,0.00019261507,0.0007186769,0.007233406,0.0024633603,0.0033273268],"genre_scores_gemma":[0.14333147,0.0011722367,0.8401422,0.00038184415,0.00015796981,0.000623625,0.012797327,0.00024056094,0.0011528275],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946649,0.000641346,0.0007266176,0.0018293489,0.001933632,0.00020423874],"domain_scores_gemma":[0.9851517,0.008893413,0.0018327697,0.0018621447,0.0019523596,0.0003077326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027856776,0.0013350873,0.0023663908,0.006788337,0.0014059693,0.0032692868,0.0037412734,0.001902351,0.0035919247],"category_scores_gemma":[0.025353443,0.00096799346,0.002323965,0.0065693725,0.0009088521,0.0061024535,0.0016204756,0.0016740152,0.0024550674],"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":[0.00040653566,0.00071659905,0.03797659,0.0025468862,0.00069651473,0.003046387,0.00080170116,0.025475793,0.0192348,0.022124974,0.013448714,0.87352455],"study_design_scores_gemma":[0.00020015542,0.0009871011,0.00964258,0.00085770973,0.00087299483,0.007237102,0.0017086437,0.65165526,0.03630713,0.24421333,0.046139166,0.00017889483],"about_ca_topic_score_codex":0.0010082455,"about_ca_topic_score_gemma":0.0015861434,"teacher_disagreement_score":0.006788337,"about_ca_system_score_codex":0.00044980354,"about_ca_system_score_gemma":0.0020913938,"threshold_uncertainty_score":0.014732301},"labels":[],"label_agreement":null},{"id":"W2152831615","doi":"10.1007/978-3-642-39712-7_6","title":"Improving the Efficiency of Distributed Data Mining Using an Adjustment Work Flow","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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","funders":"","keywords":"Computer science; Data mining; Work (physics); Work flow; Set (abstract data type); Data flow diagram; Cluster analysis; Extension (predicate logic); Data set; Information flow; Flow (mathematics); Industrial engineering; Artificial intelligence; Database","score_opus":0.04298936272471931,"score_gpt":0.26897268766176474,"score_spread":0.22598332493704543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152831615","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024093142,0.00026877763,0.9688693,0.0002765653,0.000120515746,0.00014424878,0.00009521087,0.004784632,0.0013476242],"genre_scores_gemma":[0.22084329,0.00015343071,0.7747217,0.00015874211,0.00011528685,0.00021008446,0.00034255415,0.00043912543,0.0030157864],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99708956,0.0007929523,0.0002775388,0.0007497333,0.00082812284,0.0002621415],"domain_scores_gemma":[0.99125624,0.003972102,0.00037320136,0.0029053728,0.0012096175,0.00028338507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031694255,0.0012654924,0.0017391391,0.001804973,0.0016863967,0.0021704102,0.003926324,0.0010602382,0.0049775466],"category_scores_gemma":[0.01585899,0.00079506857,0.0011787394,0.0032773302,0.0009300205,0.004382328,0.003136866,0.0017345877,0.001785224],"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":[0.0015845484,0.00070647,0.003828394,0.00023618856,0.00012268174,0.00013036806,0.0003701539,0.071487255,0.018741237,0.010767132,0.008250472,0.8837751],"study_design_scores_gemma":[0.00022995418,0.00019941514,0.0009221232,0.00002158252,0.00007189372,0.00011943389,0.00010426642,0.95631003,0.01517867,0.02252085,0.0042875493,0.000034333807],"about_ca_topic_score_codex":0.003918362,"about_ca_topic_score_gemma":0.0032174613,"teacher_disagreement_score":0.0049775466,"about_ca_system_score_codex":0.00090479496,"about_ca_system_score_gemma":0.0028717825,"threshold_uncertainty_score":0.01676178},"labels":[],"label_agreement":null},{"id":"W2153360418","doi":"10.1007/978-3-540-77018-3_19","title":"Translation and Rotation Invariant Mining of Frequent Trajectories: Application to Protein Unfolding Pathways","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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":"York University","funders":"","keywords":"Translation (biology); Invariant (physics); Wavelet; Rotation (mathematics); Computer science; Transformation (genetics); Artificial intelligence; Data mining; Noisy data; Pattern recognition (psychology); Algorithm; Mathematics","score_opus":0.03614689279289869,"score_gpt":0.2617671007059255,"score_spread":0.22562020791302684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153360418","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17127807,0.0016046923,0.81858015,0.00035627637,0.00010713503,0.00014939721,0.0011575887,0.0056557506,0.0011109826],"genre_scores_gemma":[0.3863139,0.0009633506,0.60832304,0.00006046242,0.000105229235,0.00011209662,0.0022463573,0.0003852265,0.0014903678],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994048,0.000112480586,0.000072376846,0.00017910385,0.00016859961,0.00006258541],"domain_scores_gemma":[0.99795747,0.0010621599,0.00024017294,0.00026321074,0.00034804837,0.00012882779],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011815605,0.00078231713,0.0013333288,0.0025109225,0.0009363962,0.001236087,0.0011501493,0.0007915372,0.001932717],"category_scores_gemma":[0.004175676,0.00043766954,0.001285546,0.00439188,0.00052213424,0.0006611349,0.00096623955,0.0007992556,0.00090276357],"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":[0.00089337997,0.00026998634,0.011382347,0.00043848713,0.00024853006,0.0007615061,0.00034469794,0.06527737,0.038866565,0.0054427655,0.0047591184,0.8713153],"study_design_scores_gemma":[0.000056023746,0.00014446709,0.0062265354,0.000020653668,0.000082182865,0.0006964158,0.0001458182,0.96710134,0.012796763,0.009947955,0.0027405028,0.00004136719],"about_ca_topic_score_codex":0.0037361854,"about_ca_topic_score_gemma":0.0044694724,"teacher_disagreement_score":0.0037361854,"about_ca_system_score_codex":0.00041067705,"about_ca_system_score_gemma":0.00085500855,"threshold_uncertainty_score":0.0074288845},"labels":[],"label_agreement":null},{"id":"W2153688520","doi":"10.1109/icdm.2005.44","title":"CoLe: A Cooperative Data Mining Approach and Its Application to Early Diabetes Detection","year":2006,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Data mining; Knowledge extraction; Data science; Machine learning","score_opus":0.021527686195547967,"score_gpt":0.24921825941635267,"score_spread":0.22769057322080472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153688520","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027943587,0.0014288424,0.9608585,0.0012265685,0.00010830681,0.00068226573,0.0007921044,0.0037507731,0.0032091918],"genre_scores_gemma":[0.14957751,0.0008829469,0.84473175,0.0004143798,0.00009609738,0.0006161668,0.0010233171,0.00023249658,0.0024252462],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963754,0.0011189014,0.0002714047,0.0006896357,0.0013332503,0.00021137888],"domain_scores_gemma":[0.9885992,0.006736605,0.000913282,0.0014922852,0.0018203045,0.00043824533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007600616,0.0015843691,0.002128345,0.008965176,0.0017127017,0.0028169493,0.0026269422,0.0015529505,0.0021038533],"category_scores_gemma":[0.025146466,0.0008884142,0.002044487,0.0062758,0.0011401703,0.0033810346,0.0044444934,0.0018625942,0.00087977137],"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":[0.0012875668,0.0007963919,0.04807969,0.0014083567,0.0010636376,0.001044247,0.0025575939,0.05942822,0.013271357,0.026106972,0.022016045,0.82293993],"study_design_scores_gemma":[0.0003201688,0.000844128,0.013190658,0.00033934854,0.00081244984,0.0019005508,0.0012224496,0.8585,0.021152072,0.05393485,0.047295313,0.00048796317],"about_ca_topic_score_codex":0.008414967,"about_ca_topic_score_gemma":0.0148896165,"teacher_disagreement_score":0.008965176,"about_ca_system_score_codex":0.00092548283,"about_ca_system_score_gemma":0.0022508157,"threshold_uncertainty_score":0.04019642},"labels":[],"label_agreement":null},{"id":"W2154217032","doi":"10.1007/s10618-009-0133-6","title":"Fast incremental mining of web sequential patterns with PLWAP tree","year":2009,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":22,"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":"Computer science; Data mining; Tree (set theory); Metadata; Web mining; Database; Web log analysis software; Web page; Information retrieval; Web navigation; World Wide Web; Static web page","score_opus":0.0352025202348579,"score_gpt":0.2851548256075449,"score_spread":0.249952305372687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154217032","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10378817,0.0011707183,0.8797337,0.00032760898,0.00016238498,0.00044847245,0.003385322,0.008791653,0.0021921282],"genre_scores_gemma":[0.27908906,0.00044870545,0.7112548,0.00009837242,0.00007398587,0.00030447874,0.0062989187,0.00024229714,0.0021894085],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991241,0.00011004627,0.00009772813,0.00016554123,0.00041132915,0.00009108273],"domain_scores_gemma":[0.997486,0.0010919488,0.00020693097,0.00040751306,0.0006813127,0.00012624695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008474107,0.0005587126,0.00096313574,0.003480332,0.0007403493,0.0011950828,0.0015350919,0.00059853814,0.0018568397],"category_scores_gemma":[0.0055308226,0.00054113485,0.0009366437,0.003947287,0.00026154966,0.0022466916,0.0010791122,0.00080368377,0.0011561778],"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":[0.00061900495,0.00029772156,0.014442552,0.0005609684,0.0001986943,0.0008946408,0.0002249265,0.020826148,0.017367166,0.004538511,0.014292613,0.9257371],"study_design_scores_gemma":[0.00011608323,0.00028011124,0.0050521344,0.00005567854,0.00018734107,0.0014392851,0.0001957757,0.9434766,0.0155340005,0.021471404,0.012157874,0.00003369222],"about_ca_topic_score_codex":0.0031526694,"about_ca_topic_score_gemma":0.005857447,"teacher_disagreement_score":0.003480332,"about_ca_system_score_codex":0.0002513818,"about_ca_system_score_gemma":0.0011770187,"threshold_uncertainty_score":0.0062686205},"labels":[],"label_agreement":null},{"id":"W2154535371","doi":"10.1145/956750.956766","title":"Inverted matrix","year":2003,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Association rule learning; Data mining; Process (computing); Tree (set theory); Dependency (UML); Data structure; Artificial intelligence","score_opus":0.016641721870403744,"score_gpt":0.2656214936836532,"score_spread":0.24897977181324943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154535371","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021950228,0.0036425677,0.79736775,0.002126279,0.002872376,0.0011932686,0.03515008,0.015905792,0.11979163],"genre_scores_gemma":[0.15940262,0.0033973686,0.67707884,0.0015426297,0.0011435635,0.00093089853,0.055374652,0.00119071,0.09993875],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987801,0.00012228663,0.00011758339,0.00027058483,0.00056942913,0.0001399657],"domain_scores_gemma":[0.9980817,0.0002992901,0.00014983621,0.00038130023,0.0010201171,0.000067834626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056494307,0.0011361885,0.00077754527,0.0036055706,0.0012186656,0.0030842551,0.0014156894,0.0009244305,0.047914166],"category_scores_gemma":[0.0044512777,0.00042448667,0.0006973775,0.0044774273,0.00042470742,0.0030961435,0.0016708736,0.00080136466,0.0352525],"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":[0.00039410993,0.00010394603,0.002642939,0.00073239906,0.00009425941,0.0006459982,0.00014388959,0.007159863,0.012043265,0.0547747,0.13013317,0.79113144],"study_design_scores_gemma":[0.00014125767,0.0003979045,0.0028484713,0.00023313185,0.00011421245,0.0035803642,0.0005418173,0.12387842,0.029234853,0.14316086,0.69568974,0.00017898141],"about_ca_topic_score_codex":0.0031712053,"about_ca_topic_score_gemma":0.0039467057,"teacher_disagreement_score":0.047914166,"about_ca_system_score_codex":0.0005231278,"about_ca_system_score_gemma":0.0017288943,"threshold_uncertainty_score":0.16028887},"labels":[],"label_agreement":null},{"id":"W2154888737","doi":"10.1109/greencom-cpscom.2010.134","title":"An Intelligent RFID System for Consumer Businesses","year":2010,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Purchasing; Product (mathematics); Computer science; Phone; Customer satisfaction; Radio-frequency identification; Service (business); Identification (biology); Smart phone; Business; Consumer behaviour; Marketing; Telecommunications; Computer security","score_opus":0.019898555988177836,"score_gpt":0.2860731929655712,"score_spread":0.26617463697739335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154888737","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.094241396,0.002838662,0.83709085,0.0010262143,0.0005460891,0.00061659334,0.0012095959,0.03398683,0.028443778],"genre_scores_gemma":[0.5151563,0.0011262954,0.45971695,0.0008257334,0.00014919524,0.00034067986,0.0015621466,0.00025716453,0.020865586],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999516,0.00009468732,0.000049832084,0.00012914285,0.00017659109,0.0000337732],"domain_scores_gemma":[0.9995858,0.00011232106,0.00003797333,0.000092993105,0.00014111858,0.00002974881],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059621653,0.0005189518,0.00043700624,0.00074514654,0.0005373804,0.0011048865,0.0008602668,0.0010309921,0.0052027595],"category_scores_gemma":[0.0012414828,0.00026977298,0.00035319474,0.00093455333,0.00025203123,0.0015179139,0.0005470711,0.0005014488,0.0034730993],"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":[0.000846563,0.00045668654,0.008110735,0.0004827218,0.00010583759,0.0010337676,0.0005132951,0.014228675,0.07837201,0.013336788,0.032715317,0.8497976],"study_design_scores_gemma":[0.00037007124,0.0012158663,0.012816292,0.00023456046,0.00045368116,0.003394341,0.0005043886,0.56479126,0.115590945,0.017731702,0.28263775,0.00025917238],"about_ca_topic_score_codex":0.0011310929,"about_ca_topic_score_gemma":0.0008570746,"teacher_disagreement_score":0.0052027595,"about_ca_system_score_codex":0.00040124782,"about_ca_system_score_gemma":0.00045360514,"threshold_uncertainty_score":0.017404974},"labels":[],"label_agreement":null},{"id":"W2155568874","doi":"10.1057/palgrave.ivs.9500045","title":"A Visualization Model of Interactive Knowledge Discovery Systems and Its Implementations","year":2003,"lang":"en","type":"article","venue":"Information Visualization","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Visualization; Association rule learning; Data mining; Preprocessor; Discretization; Set (abstract data type); Implementation; Interactive visualization; Knowledge extraction; Information visualization; Data visualization; Component (thermodynamics); Data pre-processing; Theoretical computer science; Data science; Artificial intelligence; Software engineering; Programming language","score_opus":0.031133258885594203,"score_gpt":0.3432125757204657,"score_spread":0.3120793168348715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155568874","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00087608217,0.00013820997,0.99372214,0.00038214365,0.000028966184,0.000052853742,0.00010241549,0.0024773409,0.00221968],"genre_scores_gemma":[0.046691906,0.00055475644,0.9484125,0.00027918033,0.00008763586,0.0005856569,0.00056703837,0.00038058628,0.0024408458],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996917,0.0010182526,0.0002942939,0.00052294414,0.0010685278,0.00017906501],"domain_scores_gemma":[0.9946866,0.0028004358,0.0002571658,0.0013295291,0.0007367068,0.0001894604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029769072,0.0011774662,0.0010437747,0.0021877424,0.0012389666,0.0067775077,0.0038750083,0.0024030232,0.008616525],"category_scores_gemma":[0.011537015,0.0011521297,0.0016848631,0.0026041893,0.00215274,0.0076851156,0.0029107165,0.0030346885,0.0027081063],"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":[0.00023485265,0.0001593188,0.0013972356,0.0005926577,0.00013802378,0.00046114606,0.0018134036,0.07285276,0.006204505,0.6978036,0.017465668,0.20087674],"study_design_scores_gemma":[0.00006836269,0.00009680264,0.00027183612,0.0001386212,0.000047810132,0.0005011078,0.000166551,0.512439,0.0054587815,0.40409094,0.07665101,0.00006917718],"about_ca_topic_score_codex":0.0034959652,"about_ca_topic_score_gemma":0.0016569826,"teacher_disagreement_score":0.008616525,"about_ca_system_score_codex":0.0011236473,"about_ca_system_score_gemma":0.0016979083,"threshold_uncertainty_score":0.028825164},"labels":[],"label_agreement":null},{"id":"W2155709205","doi":"10.1145/846183.846209","title":"WEBKDD'99","year":2000,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University; DePaul University","keywords":"Computer science; Profiling (computer programming); Knowledge extraction; Data science; World Wide Web; Information retrieval; Data mining","score_opus":0.027504247362564814,"score_gpt":0.25488755574249206,"score_spread":0.22738330837992723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155709205","genre_codex":"dataset","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035845572,0.016199807,0.26065108,0.01805268,0.010185373,0.0015771608,0.3695178,0.2479245,0.07230699],"genre_scores_gemma":[0.016159061,0.011708355,0.19690529,0.0047806767,0.0009781393,0.002696942,0.7118547,0.014782295,0.04013462],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9862482,0.0024692959,0.0015146155,0.0017636846,0.0074620126,0.00054208894],"domain_scores_gemma":[0.98264354,0.0049120765,0.00052888494,0.0060737436,0.0045573427,0.0012844092],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012427366,0.002564441,0.0049830307,0.012685178,0.0036367138,0.014764848,0.0073517812,0.0042032856,0.034463704],"category_scores_gemma":[0.03654352,0.002892656,0.004261038,0.00886555,0.00119494,0.0066892887,0.0073416373,0.006464954,0.076417446],"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":[0.000105751955,0.000099648016,0.0006273994,0.0005657977,0.00019196195,0.00009563291,0.000056326055,0.002290422,0.00017419044,0.006618697,0.9157326,0.07344157],"study_design_scores_gemma":[0.00022511113,0.00002655597,0.00071793736,0.0001788008,0.000074853604,0.0002712271,0.00005099546,0.01895625,0.0016051708,0.032886837,0.94492364,0.00008252347],"about_ca_topic_score_codex":0.012633856,"about_ca_topic_score_gemma":0.016697312,"teacher_disagreement_score":0.034463704,"about_ca_system_score_codex":0.0023055596,"about_ca_system_score_gemma":0.008189315,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W2157161149","doi":"10.1109/icdm.2006.97","title":"Learning to Use a Learned Model: A Two-Stage Approach to Classification","year":2006,"lang":"en","type":"article","venue":"Proceedings","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Stage (stratigraphy); Artificial intelligence; Natural language processing; Machine learning; Geology","score_opus":0.06055412454060583,"score_gpt":0.28731790906693633,"score_spread":0.2267637845263305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157161149","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028917133,0.00010575899,0.9956462,0.00027664375,0.00002566123,0.00012545915,0.000057619665,0.00041869996,0.00045219468],"genre_scores_gemma":[0.13867337,0.0002982046,0.85622996,0.00032863487,0.0001518169,0.00055423856,0.0005311625,0.0001536009,0.0030790223],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99498206,0.0018416481,0.00037559087,0.0011114194,0.0013669102,0.00032237967],"domain_scores_gemma":[0.9904236,0.0062077255,0.00041661892,0.0014018953,0.0013597072,0.0001903537],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063330405,0.001751682,0.00208482,0.0022052922,0.0008554506,0.0033655295,0.0052675996,0.0033460634,0.0030927013],"category_scores_gemma":[0.016586114,0.0013034417,0.0019993645,0.0020940367,0.0012590806,0.0061338004,0.0031035773,0.0041680867,0.0017213508],"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":[0.00034063894,0.00081486785,0.005467869,0.0004592284,0.0004041775,0.0003076366,0.00054514734,0.2716701,0.006478315,0.047196075,0.0075704544,0.65874547],"study_design_scores_gemma":[0.00001440681,0.00006892843,0.00022993,0.000020578158,0.000026932079,0.00006717963,0.000023271634,0.9764574,0.0013636245,0.02053344,0.0011607433,0.00003352247],"about_ca_topic_score_codex":0.0034320494,"about_ca_topic_score_gemma":0.0050679217,"teacher_disagreement_score":0.0063330405,"about_ca_system_score_codex":0.0014772599,"about_ca_system_score_gemma":0.0021378337,"threshold_uncertainty_score":0.033492684},"labels":[],"label_agreement":null},{"id":"W2157169143","doi":"10.1109/icdm.2012.20","title":"Direct Discovery of High Utility Itemsets without Candidate Generation","year":2012,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":179,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Simon Fraser University","funders":"","keywords":"Computer science; Scalability; Data mining; Pruning; Bounding overwatch; Property (philosophy); Artificial intelligence; Database","score_opus":0.027122081516313064,"score_gpt":0.2701453798814657,"score_spread":0.24302329836515263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157169143","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.073522516,0.0005431063,0.92253757,0.0002578428,0.000034852987,0.00045830844,0.00029083696,0.0010384943,0.001316487],"genre_scores_gemma":[0.35804686,0.0003348658,0.6377784,0.00017659336,0.00006663569,0.00041464862,0.0013017354,0.00009319644,0.00178703],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99781007,0.00065675325,0.00018354424,0.00040415462,0.00075878866,0.00018668121],"domain_scores_gemma":[0.98263484,0.012664735,0.0010535754,0.0020691426,0.0012896125,0.00028811747],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038572815,0.0009950185,0.0022556775,0.0034575777,0.00089240854,0.0016261518,0.0029054102,0.0013522995,0.0014765419],"category_scores_gemma":[0.018803023,0.0006861231,0.0014355097,0.0042801383,0.0008839745,0.0029467917,0.0019211922,0.0013947404,0.00096456823],"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":[0.00084116997,0.00084589695,0.02396401,0.00065757346,0.00024364746,0.0010059208,0.0005525041,0.117427126,0.012650853,0.031240733,0.0048934193,0.8056771],"study_design_scores_gemma":[0.00011777055,0.00033951658,0.002494989,0.00008563579,0.00010332348,0.0008598744,0.00018172094,0.9443722,0.009081717,0.03915498,0.0031729713,0.00003522848],"about_ca_topic_score_codex":0.00089225295,"about_ca_topic_score_gemma":0.0019276747,"teacher_disagreement_score":0.0038572815,"about_ca_system_score_codex":0.00053246296,"about_ca_system_score_gemma":0.0013317956,"threshold_uncertainty_score":0.02039951},"labels":[],"label_agreement":null},{"id":"W2157408109","doi":"10.1145/1370175.1370235","title":"MSR 2008 - 5th working conference on mining software repositories","year":2008,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Software; Software engineering; World Wide Web; Operating system","score_opus":0.06864099992213862,"score_gpt":0.27454620093881094,"score_spread":0.2059052010166723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157408109","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0681199,0.048421104,0.59932643,0.05200668,0.0122940475,0.004470867,0.065055765,0.06347109,0.08683409],"genre_scores_gemma":[0.09888361,0.023209367,0.51732314,0.0037525059,0.004334098,0.0017372165,0.19376205,0.008011134,0.14898683],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99290246,0.0018982594,0.000942255,0.0010530945,0.0027099343,0.00049393263],"domain_scores_gemma":[0.9696796,0.008726645,0.0015541911,0.0072853863,0.010042003,0.002712285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016791953,0.001992432,0.0034615593,0.014955456,0.0017296853,0.008585766,0.0050622504,0.0028528625,0.03999013],"category_scores_gemma":[0.027478617,0.0012079265,0.0025053048,0.007421225,0.0013208701,0.012357208,0.0046904674,0.0027687068,0.026712762],"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":[0.0004967532,0.00038047144,0.005310931,0.0012755609,0.00023302723,0.00015975392,0.00035253842,0.0027268508,0.005607907,0.008833105,0.36628044,0.60834265],"study_design_scores_gemma":[0.00030858858,0.0012820574,0.013509946,0.0024441078,0.0005309406,0.0011763906,0.0010662376,0.051117446,0.037102897,0.045172255,0.84603137,0.00025792298],"about_ca_topic_score_codex":0.0039412077,"about_ca_topic_score_gemma":0.0064607896,"teacher_disagreement_score":0.03999013,"about_ca_system_score_codex":0.0019184082,"about_ca_system_score_gemma":0.007557173,"threshold_uncertainty_score":0.1337803},"labels":[],"label_agreement":null},{"id":"W2159328231","doi":"10.1007/s10618-007-0083-9","title":"Mining functional dependencies from data","year":2007,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":90,"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":"Correctness; Pruning; Computer science; Data mining; Information loss; Process (computing); Functional dependency; Series (stratigraphy); Axiom; Algorithm; Artificial intelligence; Mathematics; Relational database","score_opus":0.10341483207346523,"score_gpt":0.31561346603796997,"score_spread":0.21219863396450472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159328231","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24997446,0.003117688,0.7079066,0.0026007008,0.0002769143,0.00069006084,0.018919712,0.006621375,0.009892497],"genre_scores_gemma":[0.6248855,0.0020416498,0.32478815,0.00041642404,0.00024979975,0.0006180092,0.04115873,0.0006147268,0.0052270116],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977489,0.00035756934,0.00020972159,0.0005019616,0.001018464,0.00016332683],"domain_scores_gemma":[0.9883692,0.007944746,0.0008204216,0.0012817462,0.001312535,0.00027129406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018071919,0.0011451287,0.00081957784,0.006528472,0.0011752757,0.0013366847,0.0015119936,0.0008547136,0.0031583644],"category_scores_gemma":[0.016114263,0.0007398302,0.0015864763,0.0037671512,0.00077601266,0.0039151506,0.0014565518,0.0017284252,0.0013751731],"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":[0.00070918363,0.00075340224,0.0774849,0.002092498,0.0006063586,0.004297322,0.0010999952,0.034306947,0.024551248,0.05972816,0.033872556,0.7604974],"study_design_scores_gemma":[0.00011806195,0.00047751068,0.036195688,0.00070646516,0.0011484068,0.0046278876,0.0010533922,0.54163086,0.04005851,0.30494916,0.06888306,0.00015105323],"about_ca_topic_score_codex":0.0028739145,"about_ca_topic_score_gemma":0.0063235504,"teacher_disagreement_score":0.006528472,"about_ca_system_score_codex":0.0006388622,"about_ca_system_score_gemma":0.0019920233,"threshold_uncertainty_score":0.010565758},"labels":[],"label_agreement":null},{"id":"W2162121999","doi":"10.1109/ride.2005.11","title":"Maintaining Knowledge-Bases of Navigational Patterns from Streams of Navigational Sequences","year":2005,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Sliding window protocol; Window (computing); Data mining; Computation; Sequential Pattern Mining; Data stream mining; Real-time computing; Algorithm","score_opus":0.01759193110172354,"score_gpt":0.28179296627984857,"score_spread":0.26420103517812504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162121999","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08222151,0.00072250626,0.91025025,0.0004342061,0.00003531202,0.0002113307,0.0024086726,0.0028420303,0.000874113],"genre_scores_gemma":[0.342654,0.000656449,0.64740664,0.00012257915,0.00005808912,0.00024842634,0.007855682,0.00015712884,0.0008410481],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99847263,0.00015121598,0.00018878037,0.00049752614,0.0005723673,0.00011746561],"domain_scores_gemma":[0.9919565,0.00333712,0.0011411778,0.002105401,0.001223407,0.00023629353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018187116,0.0009498622,0.0015654967,0.0045546694,0.0008257059,0.0032790613,0.0031802575,0.00096448103,0.00090540765],"category_scores_gemma":[0.01673268,0.000938703,0.0009419077,0.0052834386,0.0006324002,0.006283825,0.0017681682,0.0014930591,0.0008677614],"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":[0.0006564517,0.0004906519,0.029397156,0.00083364366,0.00034524797,0.000780547,0.0011577413,0.0808445,0.021149492,0.012045502,0.004732659,0.8475664],"study_design_scores_gemma":[0.000058596866,0.00023454199,0.007854873,0.00016490984,0.00024506156,0.000794319,0.0006335863,0.89388275,0.031521946,0.054762993,0.009759825,0.00008657249],"about_ca_topic_score_codex":0.005975955,"about_ca_topic_score_gemma":0.0079715485,"teacher_disagreement_score":0.005975955,"about_ca_system_score_codex":0.00071121205,"about_ca_system_score_gemma":0.0022440965,"threshold_uncertainty_score":0.011882365},"labels":[],"label_agreement":null},{"id":"W2163024037","doi":"10.1109/icdmw.2010.145","title":"Evaluating Association Rules by Quantitative Pairwise Property Comparisons","year":2010,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pairwise comparison; Association rule learning; Computer science; Analytic hierarchy process; Data mining; Property (philosophy); Task (project management); Measure (data warehouse); Association (psychology); Selection (genetic algorithm); Domain (mathematical analysis); Process (computing); Set (abstract data type); Machine learning; Artificial intelligence; Mathematics; Operations research; Engineering","score_opus":0.06888549084155006,"score_gpt":0.359598028990325,"score_spread":0.29071253814877496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163024037","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09633336,0.0010458095,0.89650583,0.0004313966,0.00009032992,0.00065573334,0.00089653605,0.0009085439,0.0031324308],"genre_scores_gemma":[0.36510628,0.00034871875,0.6321658,0.00007893703,0.000087442844,0.00061424944,0.0011953023,0.00008504237,0.0003182291],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9542303,0.020111404,0.0059435093,0.0041162088,0.014993082,0.0006054629],"domain_scores_gemma":[0.8236708,0.14064832,0.012904833,0.00822396,0.013426252,0.0011257314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03996407,0.0019302233,0.002597211,0.016997017,0.0012386575,0.0051164567,0.002160629,0.0013832065,0.0023923793],"category_scores_gemma":[0.1298741,0.00048590347,0.0020578708,0.0086498475,0.0018401037,0.006814141,0.002438458,0.001689442,0.000666797],"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":[0.0010967469,0.0008240489,0.070003085,0.0024123774,0.0017292948,0.00069500087,0.0011354611,0.100157976,0.025687817,0.040796056,0.0032561831,0.7522059],"study_design_scores_gemma":[0.00024565106,0.0030739957,0.024538573,0.00043878655,0.0010623431,0.0016970123,0.0021055206,0.70789695,0.037827417,0.21271044,0.008039513,0.00036378796],"about_ca_topic_score_codex":0.0004607453,"about_ca_topic_score_gemma":0.00064696715,"teacher_disagreement_score":0.03996407,"about_ca_system_score_codex":0.0009727213,"about_ca_system_score_gemma":0.0017448107,"threshold_uncertainty_score":0.2113527},"labels":[],"label_agreement":null},{"id":"W2163463784","doi":"","title":"Using the k-Means Clustering Algorithm to Classify Features for Choropleth Maps","year":2014,"lang":"en","type":"article","venue":"Cartographica The International Journal for Geographic Information and Geovisualization","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cluster analysis; Artificial intelligence; k-means clustering; Computer science; Pattern recognition (psychology); Cartography; Algorithm; Geography","score_opus":0.021065513704491945,"score_gpt":0.31237866032438616,"score_spread":0.2913131466198942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163463784","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02472354,0.0002855936,0.965967,0.00017867984,0.00012481419,0.00041207607,0.00072785706,0.0029936945,0.0045867213],"genre_scores_gemma":[0.07899041,0.00023763231,0.91461796,0.000043302647,0.000037942456,0.00032860943,0.0016676646,0.0003799123,0.0036965783],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99813384,0.00021900056,0.00015714351,0.00053522654,0.00076988066,0.00018489845],"domain_scores_gemma":[0.9979044,0.0005020815,0.00015593771,0.0003075254,0.0010667979,0.00006315728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011835492,0.0013782359,0.0009841842,0.006221298,0.0022655097,0.0031760521,0.0012838434,0.0011462332,0.003801909],"category_scores_gemma":[0.0049585896,0.0005813041,0.0017039817,0.005452604,0.0009652504,0.0018759167,0.0013682377,0.001450916,0.003175815],"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":[0.0002107934,0.00011969447,0.010357884,0.00048660542,0.00027546127,0.00027422232,0.0016616767,0.031426664,0.022588115,0.009548848,0.015114849,0.90793514],"study_design_scores_gemma":[0.00008677509,0.00028016965,0.04501659,0.00040036312,0.00029248497,0.0014075661,0.004793371,0.6762449,0.08966652,0.04634064,0.13492732,0.00054334785],"about_ca_topic_score_codex":0.023924552,"about_ca_topic_score_gemma":0.02610168,"teacher_disagreement_score":0.023924552,"about_ca_system_score_codex":0.0014397084,"about_ca_system_score_gemma":0.0020176317,"threshold_uncertainty_score":0.047570586},"labels":[],"label_agreement":null},{"id":"W2163966399","doi":"10.1109/icdew.2010.5452736","title":"Constrained frequent itemset mining from uncertain data streams","year":2010,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Association rule learning; Data stream mining; Database transaction; Data mining; Uncertain data; Tree (set theory); Task (project management); Database; Engineering; Mathematics","score_opus":0.048222877722301695,"score_gpt":0.29853124148375254,"score_spread":0.2503083637614508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163966399","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020803327,0.0008339582,0.9762415,0.00027720604,0.00005658652,0.00018554466,0.00078891276,0.00036123878,0.0004517419],"genre_scores_gemma":[0.27329233,0.0016422372,0.7187282,0.00023168368,0.0002525451,0.0005438879,0.00443825,0.00009632587,0.0007745182],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996077,0.00090913393,0.0007039279,0.00074492226,0.001337739,0.00022724533],"domain_scores_gemma":[0.98419386,0.011149781,0.0013823782,0.0011756396,0.0018358782,0.00026254228],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040844237,0.0011516765,0.00299999,0.0033508982,0.00091003394,0.0026091596,0.0026435633,0.00163662,0.0009796587],"category_scores_gemma":[0.023062993,0.00083962874,0.0015965437,0.005898756,0.0006216677,0.0046780864,0.0016609391,0.0016010801,0.00050873373],"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":[0.001142468,0.00037334664,0.012767505,0.0011533055,0.00053739565,0.0023650213,0.0007080683,0.5247921,0.007862167,0.030334847,0.007737391,0.41022643],"study_design_scores_gemma":[0.000029189601,0.00006364387,0.00061605126,0.000043952878,0.0000403382,0.00035349024,0.00010626646,0.96575123,0.0020597924,0.028879011,0.0020341657,0.000022851],"about_ca_topic_score_codex":0.001487176,"about_ca_topic_score_gemma":0.0015548051,"teacher_disagreement_score":0.0040844237,"about_ca_system_score_codex":0.00054768886,"about_ca_system_score_gemma":0.0011207978,"threshold_uncertainty_score":0.021600723},"labels":[],"label_agreement":null},{"id":"W2164379666","doi":"10.1109/icdm.2014.51","title":"Heavyweight Pattern Mining in Attributed Flow Graphs","year":2014,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; IBM (Canada)","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Compiler; Enhanced Data Rates for GSM Evolution; Path (computing); Set (abstract data type); Flow (mathematics); Data mining; Theoretical computer science; Algorithm; Mathematics; Artificial intelligence; Programming language","score_opus":0.013525456646100838,"score_gpt":0.2310836326789239,"score_spread":0.21755817603282307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164379666","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.062265188,0.0005041619,0.9293174,0.00061610236,0.00006085771,0.00029131165,0.0033269038,0.0026164183,0.0010016382],"genre_scores_gemma":[0.3698764,0.00066164706,0.61902815,0.0003723478,0.00010910026,0.00041225247,0.007227539,0.00035135171,0.0019611465],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9944891,0.0009574757,0.0006453307,0.0015679465,0.0019307161,0.00040944555],"domain_scores_gemma":[0.98295754,0.009478511,0.0025474648,0.0026546419,0.0018557749,0.0005061066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029666782,0.0010874253,0.0013894261,0.0082523795,0.0014717424,0.002361136,0.0026786549,0.0015584483,0.0010513619],"category_scores_gemma":[0.018766658,0.00072859006,0.0018332169,0.007352488,0.0013687883,0.0058910795,0.002354134,0.0019978846,0.00042361795],"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":[0.00066862087,0.0008223644,0.07357821,0.0014625026,0.00061047863,0.0025019909,0.0012009963,0.21937248,0.0139953885,0.06423949,0.013665971,0.6078816],"study_design_scores_gemma":[0.00005079364,0.00010563109,0.00475597,0.00013211305,0.00012294084,0.0010087444,0.0004903059,0.73104924,0.011995501,0.2381498,0.012083946,0.000055033746],"about_ca_topic_score_codex":0.0042011323,"about_ca_topic_score_gemma":0.00542986,"teacher_disagreement_score":0.0082523795,"about_ca_system_score_codex":0.0010880434,"about_ca_system_score_gemma":0.0018956249,"threshold_uncertainty_score":0.015689433},"labels":[],"label_agreement":null},{"id":"W2164832447","doi":"10.1109/tsmcb.2010.2048900","title":"A Bounded and Adaptive Memory-Based Approach to Mine Frequent Patterns From Very Large Databases","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Thrashing; Computer science; Demand paging; Physical address; Interleaved memory; Flat memory model; Virtual memory; Memory management; Memory map; Paging; Extended memory; Auxiliary memory; Block (permutation group theory); Page fault; Registered memory; Data structure; Shared memory; Parallel computing; Operating system; Overlay","score_opus":0.028074208801518157,"score_gpt":0.24433049619443922,"score_spread":0.21625628739292108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164832447","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014477799,0.00053540536,0.98337656,0.00015179977,0.00002787567,0.00008087398,0.00012787369,0.0008229294,0.0003988937],"genre_scores_gemma":[0.3416553,0.00065393985,0.6543651,0.00026832597,0.00013588699,0.0004057028,0.00062712695,0.000110212786,0.0017784509],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980483,0.0004100427,0.00022911091,0.0006520774,0.0005045882,0.0001558258],"domain_scores_gemma":[0.9969651,0.0016747513,0.00029945493,0.00051844795,0.00043144956,0.00011080225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015769011,0.0008699147,0.0014972513,0.0030562284,0.00065163703,0.0015746669,0.003734615,0.0012220464,0.0011422276],"category_scores_gemma":[0.006410302,0.00066922896,0.001377749,0.0027220324,0.00077661744,0.0020669184,0.0016398677,0.0011760236,0.00060456706],"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":[0.00063470635,0.000503644,0.006928874,0.00042151022,0.00048619878,0.0007495955,0.00041477825,0.33854473,0.017084626,0.014178538,0.0039109336,0.6161418],"study_design_scores_gemma":[0.000014365173,0.00007978122,0.00046148404,0.000018853261,0.00003609576,0.00016838635,0.00004478766,0.98828715,0.0014874989,0.008278705,0.0011090774,0.000013918821],"about_ca_topic_score_codex":0.0031494864,"about_ca_topic_score_gemma":0.0034258526,"teacher_disagreement_score":0.003734615,"about_ca_system_score_codex":0.0005305738,"about_ca_system_score_gemma":0.0010763156,"threshold_uncertainty_score":0.008339524},"labels":[],"label_agreement":null},{"id":"W2165427642","doi":"10.1109/icmla.2013.87","title":"An Incremental Parallel Particle Swarm Approach for Classification Rule Discovery from Dynamic Data","year":2013,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Particle swarm optimization; Data mining; Artificial intelligence; Population; Classification rule; Set (abstract data type); Machine learning; Construct (python library)","score_opus":0.06307491343824,"score_gpt":0.30536527002960334,"score_spread":0.24229035659136333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165427642","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011275002,0.00017294558,0.98710746,0.000110410845,0.00003980689,0.00007786775,0.000035891437,0.00041097202,0.000769697],"genre_scores_gemma":[0.30322096,0.00029406734,0.6937559,0.00014465374,0.000100363584,0.00036826122,0.00031495074,0.00007510809,0.0017257127],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992409,0.00015398955,0.00006437827,0.00018422473,0.0002951848,0.00006142596],"domain_scores_gemma":[0.99876106,0.0006392438,0.0001252464,0.0001597442,0.0002730214,0.00004172012],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012391147,0.00082724035,0.0013577563,0.0013228215,0.0004584147,0.0008989477,0.0016058871,0.0006919071,0.0007494286],"category_scores_gemma":[0.0032293855,0.00049785775,0.0009969681,0.0010007756,0.0004918974,0.001061846,0.00073440454,0.0010499416,0.00022979903],"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":[0.00016057333,0.00024035014,0.0038962634,0.00015186824,0.00023290137,0.00023799547,0.00017474976,0.56443584,0.0073680673,0.009458242,0.002522645,0.4111205],"study_design_scores_gemma":[0.000012818432,0.000029331277,0.00021026457,0.000002696963,0.000013371151,0.00002740188,0.000006840684,0.9960531,0.00078755955,0.0022002624,0.000651314,0.000004979129],"about_ca_topic_score_codex":0.0046045473,"about_ca_topic_score_gemma":0.0047270814,"teacher_disagreement_score":0.0046045473,"about_ca_system_score_codex":0.0005472041,"about_ca_system_score_gemma":0.0010446372,"threshold_uncertainty_score":0.009155512},"labels":[],"label_agreement":null},{"id":"W2165804133","doi":"10.1109/ccece.1997.608243","title":"Applications of data mining for power systems","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Knowledge extraction; Field (mathematics); Data science; Data mining; Data visualization; Visualization; Data stream mining; Machine learning","score_opus":0.07900683330359647,"score_gpt":0.3040695030414044,"score_spread":0.22506266973780792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165804133","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004891979,0.05451419,0.8732956,0.014501175,0.0022616354,0.00036342503,0.0015000709,0.0015227806,0.047149118],"genre_scores_gemma":[0.20153752,0.090386465,0.68735653,0.0026551988,0.0029602132,0.000763607,0.0025959874,0.00032932183,0.011415061],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99793375,0.00075219973,0.00019175303,0.00021774143,0.00085371174,0.00005082384],"domain_scores_gemma":[0.9960349,0.0026483934,0.00019664413,0.00039435286,0.00063775195,0.00008797305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022910992,0.0010913871,0.0009753838,0.003647633,0.00094625354,0.0028417623,0.0013326324,0.0017935683,0.008662987],"category_scores_gemma":[0.013853027,0.00044249572,0.0010172742,0.0070214933,0.0009222917,0.002430254,0.001918725,0.0028698535,0.0034192218],"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":[0.00009090353,0.00009670211,0.003737704,0.0017489052,0.00024970467,0.000738671,0.00040403346,0.05355546,0.0014456355,0.2837499,0.051923744,0.60225856],"study_design_scores_gemma":[0.000036522484,0.000060271934,0.001331157,0.00072661176,0.00007705979,0.00075505895,0.00029603872,0.13161063,0.0020509954,0.5016453,0.36135662,0.00005383233],"about_ca_topic_score_codex":0.0017709748,"about_ca_topic_score_gemma":0.0014543412,"teacher_disagreement_score":0.008662987,"about_ca_system_score_codex":0.0010827596,"about_ca_system_score_gemma":0.0011714163,"threshold_uncertainty_score":0.028980613},"labels":[],"label_agreement":null},{"id":"W2167681385","doi":"10.1109/icdm.2001.989541","title":"CMAR: accurate and efficient classification based on multiple class-association rules","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1209,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Association rule learning; Associative property; Overfitting; Computer science; Data mining; Class (philosophy); Artificial intelligence; Scalability; Flexibility (engineering); Classification rule; Set (abstract data type); Statistical classification; Decision tree; Tree (set theory); One-class classification; Pattern recognition (psychology); Machine learning; Database; Support vector machine; Mathematics; Artificial neural network; Statistics","score_opus":0.03426440388287782,"score_gpt":0.24369401877160032,"score_spread":0.2094296148887225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167681385","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035864472,0.0014213163,0.94809896,0.00046561344,0.00025192328,0.00031959498,0.0012641534,0.0083784135,0.0039355266],"genre_scores_gemma":[0.16730016,0.0006069697,0.8265057,0.00028718644,0.0002294796,0.00031544932,0.0019177332,0.0001744098,0.002662919],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9951385,0.000786809,0.0004902168,0.0007456743,0.0025443116,0.00029450856],"domain_scores_gemma":[0.9896019,0.0046862066,0.0012301501,0.0016768952,0.002579033,0.00022579673],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037748413,0.0011620915,0.0016806354,0.006523139,0.0009755706,0.0025599587,0.0029567035,0.0016226403,0.0028133804],"category_scores_gemma":[0.012352064,0.0005526382,0.0011846246,0.00735356,0.00081211654,0.004264732,0.0017122567,0.0017270228,0.003128091],"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":[0.00025161912,0.00023528327,0.01053027,0.00025273766,0.00016459353,0.00030929322,0.00013723585,0.016211865,0.005394375,0.006606535,0.014215403,0.94569075],"study_design_scores_gemma":[0.000088781315,0.0003514351,0.007936626,0.00012865428,0.00018900119,0.0022142278,0.00026143002,0.9138779,0.020409347,0.02870301,0.02572107,0.00011858791],"about_ca_topic_score_codex":0.0022825545,"about_ca_topic_score_gemma":0.0026571595,"teacher_disagreement_score":0.006523139,"about_ca_system_score_codex":0.0004965828,"about_ca_system_score_gemma":0.001300857,"threshold_uncertainty_score":0.019963503},"labels":[],"label_agreement":null},{"id":"W2168846201","doi":"10.1109/icdm.2008.93","title":"WiFIsViz: Effective Visualization of Frequent Itemsets","year":2008,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Visualization; Representation (politics); Data mining; Information retrieval; Association rule learning; Data visualization; Creative visualization","score_opus":0.016221547384068818,"score_gpt":0.2695666566170058,"score_spread":0.25334510923293696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168846201","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0229101,0.0012025316,0.8562868,0.00091720175,0.0002842451,0.00031784552,0.010619761,0.103148706,0.0043128678],"genre_scores_gemma":[0.11889279,0.0017062296,0.8610197,0.00030159828,0.00019860177,0.00067181466,0.010646493,0.0038164647,0.0027463783],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99932194,0.00018458701,0.000078501565,0.00009832996,0.00025050956,0.000066140325],"domain_scores_gemma":[0.9970386,0.0017101499,0.00026050946,0.00032169602,0.00048182392,0.00018725607],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013926466,0.0022602645,0.001130738,0.004291035,0.0004941351,0.002169766,0.0016750211,0.001359902,0.015763003],"category_scores_gemma":[0.007644745,0.0006765766,0.0011040185,0.0023828582,0.00028885886,0.0030863774,0.0026763985,0.0014311743,0.002347364],"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":[0.0025036072,0.00027763005,0.006002569,0.0029748043,0.00038443538,0.0017969604,0.0025833277,0.02025081,0.06460795,0.016714465,0.18277994,0.69912356],"study_design_scores_gemma":[0.001187991,0.0008075946,0.013403876,0.00086498767,0.00036048837,0.0041297907,0.0011670659,0.53839934,0.109532975,0.057035044,0.2725239,0.00058700045],"about_ca_topic_score_codex":0.0013285999,"about_ca_topic_score_gemma":0.0011351482,"teacher_disagreement_score":0.015763003,"about_ca_system_score_codex":0.00026945295,"about_ca_system_score_gemma":0.0004345922,"threshold_uncertainty_score":0.052732527},"labels":[],"label_agreement":null},{"id":"W2169290919","doi":"10.1109/coginf.2006.365532","title":"User-centered Interactive Data Mining","year":2006,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Focus (optics); Selection (genetic algorithm); Automation; User modeling; Data science; Human–computer interaction; User interface; Artificial intelligence; Engineering","score_opus":0.041845712651434795,"score_gpt":0.29763392318737425,"score_spread":0.2557882105359395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169290919","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009292431,0.00034177137,0.9753983,0.0004342903,0.000037343914,0.00034431432,0.00042738253,0.006630506,0.007093629],"genre_scores_gemma":[0.2695384,0.0005050828,0.7175707,0.0006289421,0.00015470978,0.0010190358,0.002147562,0.0007881448,0.0076473225],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98003596,0.010313226,0.0008260331,0.0028216646,0.0053588115,0.0006443136],"domain_scores_gemma":[0.960303,0.024366504,0.0010887064,0.008577648,0.0045849965,0.0010791257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012934145,0.0017802217,0.0019423871,0.0022954338,0.0011326056,0.005228703,0.004784168,0.0018045151,0.012202889],"category_scores_gemma":[0.03585254,0.0008946779,0.0014689057,0.0027355305,0.0014337957,0.0047296463,0.0068715313,0.0020262194,0.0054423995],"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":[0.0026643132,0.0015934905,0.019279696,0.0016937645,0.0006932955,0.0013061033,0.011049967,0.030579563,0.028258365,0.0891485,0.040835608,0.7728974],"study_design_scores_gemma":[0.0003269072,0.00068624807,0.0064161476,0.00037063033,0.00035259157,0.0020977433,0.0022862668,0.6060831,0.05145987,0.16201955,0.16753343,0.0003675036],"about_ca_topic_score_codex":0.0016304897,"about_ca_topic_score_gemma":0.0030787413,"teacher_disagreement_score":0.012934145,"about_ca_system_score_codex":0.00069920026,"about_ca_system_score_gemma":0.0018921456,"threshold_uncertainty_score":0.068403125},"labels":[],"label_agreement":null},{"id":"W2169474320","doi":"10.1109/ideas.2003.1214917","title":"Incremental mining of frequent patterns without candidate generation or support constraint","year":2003,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":216,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Constraint (computer-aided design); Data mining; Tree (set theory); Tree structure; Binary tree; Algorithm; Engineering; Mathematics","score_opus":0.0403410905032692,"score_gpt":0.284965270308043,"score_spread":0.24462417980477377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169474320","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11013839,0.00089308305,0.88387674,0.0003322701,0.00010574633,0.00033398884,0.00095219276,0.0015465831,0.0018211163],"genre_scores_gemma":[0.28481117,0.00044712372,0.70948327,0.00016440317,0.000112469614,0.00030628967,0.003328128,0.00009485344,0.0012523456],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99853206,0.0002527769,0.00016394648,0.00023482369,0.0007153237,0.00010114735],"domain_scores_gemma":[0.99093974,0.0055196583,0.0005312313,0.0011220066,0.0016896694,0.00019768851],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014320763,0.0004723834,0.0010199575,0.0022462916,0.0005970101,0.0011821537,0.0021266534,0.00069246284,0.0012555843],"category_scores_gemma":[0.011869937,0.00047406575,0.0008609847,0.0026726513,0.00037813885,0.0032760315,0.0011276352,0.0007380983,0.0006882698],"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":[0.0008434816,0.00041103817,0.0147226015,0.0006692452,0.00026675846,0.0016676373,0.0003613333,0.029275553,0.025995322,0.012158926,0.0067495103,0.90687853],"study_design_scores_gemma":[0.0002490384,0.0009551772,0.006432623,0.0001454426,0.0004595139,0.0035796436,0.000386375,0.8815486,0.04092842,0.04427118,0.020944234,0.00009987576],"about_ca_topic_score_codex":0.0010815376,"about_ca_topic_score_gemma":0.0019636846,"teacher_disagreement_score":0.0022462916,"about_ca_system_score_codex":0.0002678097,"about_ca_system_score_gemma":0.0012262003,"threshold_uncertainty_score":0.0075736046},"labels":[],"label_agreement":null},{"id":"W2169781627","doi":"10.1109/grc.2006.1635775","title":"Efficient indirect association discovery using compact transaction databases","year":2006,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Association rule learning; Database transaction; Computer science; Association (psychology); Database; Data mining; Transaction processing; Distributed database","score_opus":0.029336021478138203,"score_gpt":0.27311686800390556,"score_spread":0.24378084652576734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169781627","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.069768436,0.0009862733,0.9248483,0.00036480313,0.000056328496,0.00017999299,0.0006874579,0.001789429,0.0013189603],"genre_scores_gemma":[0.26519275,0.00051883777,0.7303684,0.000106714804,0.0000739421,0.00023616992,0.0019350406,0.00008767269,0.0014804647],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974661,0.0006519354,0.0003301769,0.00045037156,0.0009765658,0.00012482743],"domain_scores_gemma":[0.9912354,0.0047095865,0.0008920862,0.0016034704,0.0013903121,0.00016906112],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025817868,0.0007422164,0.0018852332,0.003034778,0.0006723269,0.002551785,0.0020467367,0.00069415726,0.002128181],"category_scores_gemma":[0.012590596,0.0007190131,0.00070948206,0.0041921674,0.0005633241,0.003654983,0.002284811,0.0011603937,0.000837165],"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":[0.0009039938,0.00036836162,0.017713116,0.0004246582,0.0003455324,0.00058919337,0.0003141684,0.07970467,0.011412203,0.017672999,0.0074302596,0.8631209],"study_design_scores_gemma":[0.00008549718,0.00015342525,0.0017604859,0.00005840396,0.00009139903,0.00097010157,0.00017579024,0.9560833,0.013995099,0.020245926,0.0063516363,0.000028930508],"about_ca_topic_score_codex":0.0009177598,"about_ca_topic_score_gemma":0.001152773,"teacher_disagreement_score":0.003034778,"about_ca_system_score_codex":0.00036938762,"about_ca_system_score_gemma":0.0009890844,"threshold_uncertainty_score":0.013653994},"labels":[],"label_agreement":null},{"id":"W2169939867","doi":"10.5772/6461","title":"Data Mining Applied to the Instrumentation Data Analysis of a Large Dam","year":2009,"lang":"en","type":"book-chapter","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"College of Family Physicians of Canada","keywords":"Instrumentation (computer programming); Computer science; Data science; Operating system","score_opus":0.07821821716239924,"score_gpt":0.32353399223895024,"score_spread":0.245315775076551,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169939867","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35298267,0.0012102667,0.6229956,0.0010398579,0.00013811613,0.0012580523,0.013421554,0.0040564304,0.0028973985],"genre_scores_gemma":[0.5121221,0.00049354084,0.47434393,0.00008669196,0.000050115978,0.00080443296,0.011060495,0.000060709597,0.0009780085],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817157,0.00028663524,0.00036622348,0.00043688132,0.0006187862,0.00011984043],"domain_scores_gemma":[0.9976197,0.001053843,0.00030662626,0.00028768965,0.0006117411,0.00012041417],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016514079,0.0008445687,0.0010455567,0.004989849,0.0008202501,0.0014977775,0.0010667122,0.00070252415,0.0007985294],"category_scores_gemma":[0.0048132003,0.00028013246,0.0013659311,0.0048643877,0.00046879792,0.00082495954,0.0008586539,0.000787251,0.00051421544],"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":[0.00088902836,0.0015948957,0.0992447,0.0017260959,0.0006210408,0.002575636,0.0019611286,0.08438228,0.048861135,0.0037546863,0.007637225,0.7467521],"study_design_scores_gemma":[0.00007920721,0.0012617186,0.11853484,0.0003097889,0.00035522899,0.0020847325,0.003039801,0.7807716,0.055203293,0.012078511,0.026139215,0.0001420086],"about_ca_topic_score_codex":0.0035147853,"about_ca_topic_score_gemma":0.0030044701,"teacher_disagreement_score":0.004989849,"about_ca_system_score_codex":0.000551452,"about_ca_system_score_gemma":0.0015302852,"threshold_uncertainty_score":0.008733571},"labels":[],"label_agreement":null},{"id":"W2170138277","doi":"10.1109/icde.2009.59","title":"GuruMine: A Pattern Mining System for Discovering Leaders and Tribes","year":2009,"lang":"en","type":"article","venue":"Proceedings - International Conference on Data Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Set (abstract data type); Social media; Process (computing); Social network (sociolinguistics); Interface (matter); World Wide Web; Graphical user interface; Data science; Information retrieval","score_opus":0.0736423980785224,"score_gpt":0.29960727302705753,"score_spread":0.22596487494853512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170138277","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008260519,0.0005291521,0.80547535,0.0006322567,0.00022889594,0.0004604648,0.0142383035,0.16441616,0.0057588136],"genre_scores_gemma":[0.051776007,0.0004921566,0.9065801,0.00058133714,0.000056438967,0.0007220572,0.028200852,0.0041767615,0.0074143],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904484,0.00015987511,0.00011116381,0.0003390743,0.0002781287,0.000066948895],"domain_scores_gemma":[0.9983937,0.0006507901,0.00014851979,0.0004540057,0.00024057049,0.000112458234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015110257,0.0014081327,0.0012047953,0.0033813287,0.0009924127,0.0021650016,0.0027274056,0.0010056769,0.010097829],"category_scores_gemma":[0.006025306,0.00092825084,0.0012196754,0.0024094046,0.0005293932,0.0042017866,0.0025754073,0.0014281219,0.0057379236],"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":[0.0013239965,0.00035505145,0.017130136,0.0018647755,0.00040215495,0.0015781953,0.0015803069,0.020657077,0.015351709,0.036896944,0.26239994,0.6404598],"study_design_scores_gemma":[0.0003154965,0.0002546967,0.00662839,0.00032024278,0.00015014244,0.0015333636,0.00055644143,0.51337063,0.026569905,0.0705538,0.37955278,0.00019399473],"about_ca_topic_score_codex":0.0036131057,"about_ca_topic_score_gemma":0.0067173173,"teacher_disagreement_score":0.010097829,"about_ca_system_score_codex":0.0007663406,"about_ca_system_score_gemma":0.0010797257,"threshold_uncertainty_score":0.033780634},"labels":[],"label_agreement":null},{"id":"W2170530489","doi":"10.1111/coin.12049","title":"Creating Decision Trees from Rules using RBDT‐1","year":2014,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"George Mason University","keywords":"Decision tree; ID3 algorithm; Incremental decision tree; Computer science; Decision tree learning; Decision stump; Decision rule; Machine learning; Artificial intelligence; Data mining; Alternating decision tree; ID3; Set (abstract data type); Tree (set theory); Mathematics","score_opus":0.046232399762322685,"score_gpt":0.320815491402463,"score_spread":0.27458309164014033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170530489","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051710773,0.00020038866,0.98699653,0.00016665009,0.000055404984,0.00030894965,0.00063450955,0.003516188,0.0029502737],"genre_scores_gemma":[0.040656917,0.00018561498,0.9546927,0.00016336376,0.000027869699,0.00036990116,0.002192333,0.00029429718,0.0014171022],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975604,0.00075647695,0.00029644213,0.0004388269,0.00084178016,0.00010602054],"domain_scores_gemma":[0.99134606,0.0058898954,0.00035359245,0.0009695573,0.0012818752,0.00015905712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033223047,0.0010121969,0.0007075887,0.0019027167,0.0005520194,0.0015870928,0.0018237602,0.0009080859,0.006245567],"category_scores_gemma":[0.014489724,0.0006195419,0.0018671206,0.0013871383,0.00060774304,0.0018362865,0.0013730321,0.0023112218,0.0033809512],"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":[0.0002803567,0.0003236783,0.0031286182,0.0009279143,0.0001667051,0.00027802645,0.00039214766,0.0933869,0.007585314,0.041868813,0.019594355,0.83206713],"study_design_scores_gemma":[0.00014193896,0.00018143418,0.0006598811,0.00020555167,0.00008422921,0.00042142646,0.000093592425,0.8553998,0.019714667,0.07347231,0.04956841,0.000056800352],"about_ca_topic_score_codex":0.0015117157,"about_ca_topic_score_gemma":0.0025063334,"teacher_disagreement_score":0.006245567,"about_ca_system_score_codex":0.0007677093,"about_ca_system_score_gemma":0.0015957252,"threshold_uncertainty_score":0.020893455},"labels":[],"label_agreement":null},{"id":"W2171206798","doi":"10.1109/icmla.2009.37","title":"Discretization Techniques and Genetic Algorithm for Learning the Classification Method PROAFTN","year":2009,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint John Regional Hospital; University of New Brunswick","funders":"","keywords":"Discretization; Computer science; One-class classification; Statistical classification; Artificial intelligence; Machine learning; Genetic algorithm; Class (philosophy); Algorithm; Multiclass classification; Data classification; Data mining; Pattern recognition (psychology); Mathematics; Support vector machine","score_opus":0.021201518184099263,"score_gpt":0.3115964511052302,"score_spread":0.29039493292113094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171206798","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037407053,0.00022124754,0.9950911,0.00008437322,0.000033162312,0.000023495559,0.000014376552,0.00009274339,0.0006988114],"genre_scores_gemma":[0.102446884,0.00043263758,0.89542544,0.00011334942,0.000061576015,0.00023430014,0.0001540992,0.000040197378,0.0010913808],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986879,0.0004569634,0.00010170786,0.00024879404,0.00044536326,0.00005928184],"domain_scores_gemma":[0.9983323,0.0010386636,0.00014381853,0.00015096433,0.0003002061,0.000034003744],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021220874,0.00049628544,0.0008031333,0.0014082299,0.00049015536,0.0007921926,0.0009923928,0.00090249476,0.0010924658],"category_scores_gemma":[0.0054303394,0.00028788476,0.0007629079,0.0013978487,0.0009321505,0.0011561953,0.0006796878,0.0016797435,0.0003524104],"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":[0.00008426338,0.00009492292,0.0023062027,0.0001822872,0.00011736494,0.00008853537,0.00026992816,0.39110324,0.007272623,0.07134742,0.0019366805,0.52519655],"study_design_scores_gemma":[0.000015207619,0.000046332723,0.00040768032,0.000030133006,0.0000161223,0.00007332191,0.00002509724,0.9698027,0.0019828707,0.024300776,0.003279234,0.00002046612],"about_ca_topic_score_codex":0.0026977179,"about_ca_topic_score_gemma":0.0020579414,"teacher_disagreement_score":0.0026977179,"about_ca_system_score_codex":0.00093297416,"about_ca_system_score_gemma":0.0007565053,"threshold_uncertainty_score":0.011222839},"labels":[],"label_agreement":null},{"id":"W2178542274","doi":"10.4018/jcini.2008010105","title":"User-Centered Interactive Data Mining","year":2008,"lang":"en","type":"article","venue":"International Journal of Cognitive Informatics and Natural Intelligence","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Focus (optics); User modeling; Selection (genetic algorithm); Automation; Data mining; User requirements document; Data stream mining; Data science; User interface; Human–computer interaction; Machine learning; Software engineering","score_opus":0.05587008671700552,"score_gpt":0.3388465204695839,"score_spread":0.2829764337525784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2178542274","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0068706633,0.0001607198,0.9851703,0.000375526,0.000017803019,0.00029783428,0.00026582347,0.00379065,0.0030507303],"genre_scores_gemma":[0.22118554,0.00026611093,0.77251005,0.00043156723,0.000064197906,0.00076031534,0.001303891,0.0003804538,0.00309782],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9767969,0.011317731,0.0014032845,0.0030933074,0.0065259235,0.0008627895],"domain_scores_gemma":[0.9594395,0.022424584,0.0016441145,0.0093747815,0.005993823,0.0011232713],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017499782,0.0017350295,0.0018765016,0.0026945753,0.0012938516,0.0068681836,0.005378909,0.0018934375,0.006128898],"category_scores_gemma":[0.042519532,0.0009814318,0.0020418968,0.0030550805,0.0017825655,0.006693317,0.0071809636,0.0023557397,0.0027842503],"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":[0.0022823391,0.0014535405,0.03315875,0.0017493754,0.0008461657,0.001582757,0.015743539,0.04014287,0.027828213,0.14943944,0.025595948,0.70017713],"study_design_scores_gemma":[0.00020415286,0.0004965267,0.00650081,0.00037477945,0.00033438916,0.0017615156,0.0020530776,0.68204206,0.04200174,0.1692638,0.09461063,0.00035647157],"about_ca_topic_score_codex":0.0021855982,"about_ca_topic_score_gemma":0.0029053742,"teacher_disagreement_score":0.017499782,"about_ca_system_score_codex":0.001048771,"about_ca_system_score_gemma":0.0029228758,"threshold_uncertainty_score":0.09254885},"labels":[],"label_agreement":null},{"id":"W2180880586","doi":"10.1007/s10586-015-0477-1","title":"A distributed frequent itemset mining algorithm using Spark for Big Data analytics","year":2015,"lang":"en","type":"article","venue":"Cluster Computing","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":85,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"National Natural Science Foundation of China","keywords":"Computer science; SPARK (programming language); Pruning; Scalability; Data mining; Association rule learning; Big data; Benchmark (surveying); GSP Algorithm; Computation; Process (computing); Algorithm; Apriori algorithm; Database","score_opus":0.256721916407233,"score_gpt":0.34482071353202187,"score_spread":0.08809879712478885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2180880586","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025723642,0.0003693204,0.95938665,0.00033882842,0.00027992832,0.00030228205,0.00090365193,0.011412805,0.0012829613],"genre_scores_gemma":[0.09833704,0.00015787079,0.89602256,0.00012276712,0.00012210252,0.00027580856,0.0025616372,0.00042647807,0.001973806],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985098,0.00018734022,0.00017085492,0.0004260218,0.0005816038,0.00012435415],"domain_scores_gemma":[0.9976533,0.0006126609,0.000101918384,0.00060349784,0.0007906689,0.0002379656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017911318,0.0010505875,0.0024002574,0.0020306644,0.0016768355,0.0016261775,0.003363443,0.00082075683,0.0031595568],"category_scores_gemma":[0.0045116404,0.0007699398,0.0013969517,0.0038581644,0.00042042648,0.0019955568,0.0017533111,0.0012095643,0.001940976],"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":[0.0022690836,0.0012305431,0.0065235808,0.00052216795,0.000670569,0.00077846885,0.00031256097,0.07169991,0.025128078,0.008766173,0.04796354,0.83413535],"study_design_scores_gemma":[0.0004897538,0.0003033849,0.0015418667,0.000016626049,0.00013894835,0.00071482995,0.00015428514,0.95880926,0.008574192,0.017978502,0.011219678,0.00005872591],"about_ca_topic_score_codex":0.0029105006,"about_ca_topic_score_gemma":0.0048303474,"teacher_disagreement_score":0.003363443,"about_ca_system_score_codex":0.00052421,"about_ca_system_score_gemma":0.0021590188,"threshold_uncertainty_score":0.010569751},"labels":[],"label_agreement":null},{"id":"W2186571714","doi":"","title":"Dat a Mining Strategies and Methods to Develop Microfinance Market - Use Case Currency Exchange","year":2009,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Currency; Microfinance; Foreign exchange market; Market data; Economics; Virtual currency; Recession; Exchange rate; Business; Finance; Monetary economics; Macroeconomics","score_opus":0.05289198102714368,"score_gpt":0.35764489783136577,"score_spread":0.3047529168042221,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2186571714","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019984335,0.00040671654,0.96627533,0.0008610563,0.00009793244,0.00092081307,0.0019189004,0.0019742341,0.0075606178],"genre_scores_gemma":[0.14924315,0.00032352042,0.84033906,0.00012276259,0.000063743566,0.0009311875,0.0034908394,0.00016233802,0.0053234305],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975821,0.00048399117,0.00038506064,0.00047805355,0.0009355747,0.00013521734],"domain_scores_gemma":[0.99552935,0.0020036604,0.0005651207,0.0006083247,0.0011138197,0.00017971639],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027796347,0.0010560323,0.00081830315,0.008346996,0.0014134019,0.004020213,0.0030455391,0.0014939493,0.009912303],"category_scores_gemma":[0.011872914,0.00071214564,0.0022085495,0.004380641,0.00072966877,0.0039502634,0.001737638,0.0014085262,0.0021821877],"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":[0.00019017015,0.00059806346,0.028519893,0.00077058777,0.00027299183,0.001568446,0.00083678536,0.10137731,0.0045938524,0.1439781,0.019122958,0.6981707],"study_design_scores_gemma":[0.000040110754,0.000065441825,0.0023428167,0.00009441254,0.000057967518,0.00082132244,0.0005669598,0.88912416,0.005497448,0.0687879,0.032570675,0.000030746618],"about_ca_topic_score_codex":0.0032626865,"about_ca_topic_score_gemma":0.004142424,"teacher_disagreement_score":0.009912303,"about_ca_system_score_codex":0.0012586399,"about_ca_system_score_gemma":0.001707669,"threshold_uncertainty_score":0.03315997},"labels":[],"label_agreement":null},{"id":"W2187801270","doi":"10.4018/978-1-60566-404-0.ch001","title":"Association Rules","year":2009,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Association rule learning; Lift (data mining); Association (psychology); Analogy; Computer science; K-optimal pattern discovery; Data mining; Artificial intelligence; Psychology; Epistemology","score_opus":0.01568686122016129,"score_gpt":0.24486356012017918,"score_spread":0.2291766989000179,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2187801270","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010080589,0.05992382,0.5269481,0.017805014,0.010262333,0.0080630155,0.10122588,0.012459754,0.25323153],"genre_scores_gemma":[0.08791772,0.050988156,0.62219936,0.012375337,0.0057520596,0.009150265,0.12524521,0.0022450425,0.0841269],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96937066,0.00890338,0.0048407945,0.006090378,0.009977932,0.0008167684],"domain_scores_gemma":[0.94976485,0.0286723,0.00473777,0.0066349236,0.009405894,0.0007842956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013355368,0.0027697326,0.0032403728,0.01445228,0.0025463388,0.010788145,0.006714302,0.0044218153,0.06861979],"category_scores_gemma":[0.06649477,0.0011137092,0.003168371,0.015210476,0.0021631545,0.008297153,0.00498801,0.004030812,0.06607277],"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":[0.00032192952,0.0002359671,0.007595274,0.0067939153,0.00091452553,0.0012103237,0.00076091976,0.0031860117,0.0016154887,0.10602109,0.39906672,0.47227782],"study_design_scores_gemma":[0.000048357204,0.000090978116,0.0018318668,0.0028267044,0.00025698353,0.0019231627,0.00051290815,0.003383056,0.0013386264,0.1244864,0.8631909,0.000110091714],"about_ca_topic_score_codex":0.0013025798,"about_ca_topic_score_gemma":0.0015034605,"teacher_disagreement_score":0.06861979,"about_ca_system_score_codex":0.0023940098,"about_ca_system_score_gemma":0.005136177,"threshold_uncertainty_score":0.22955608},"labels":[],"label_agreement":null},{"id":"W2188524736","doi":"10.1007/978-3-319-10160-6_23","title":"Building Smart Cubes for Reliable and Faster Access to Data","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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":"Online analytical processing; Computer science; Materialized view; Data warehouse; Partition (number theory); Data cube; Set (abstract data type); Cube (algebra); Data mining; Computation; Query optimization; Information retrieval; Theoretical computer science; View; Algorithm; Mathematics; Programming language","score_opus":0.050541103832412414,"score_gpt":0.31498475450503033,"score_spread":0.26444365067261794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2188524736","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015113296,0.0011654106,0.9711354,0.00077041605,0.0002743674,0.00014491082,0.0011349758,0.006231845,0.0040294067],"genre_scores_gemma":[0.13261604,0.0016695885,0.85576296,0.0004349546,0.0001343728,0.00037846423,0.0038326231,0.00061108463,0.004559933],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986759,0.00025905253,0.00010711611,0.00017089702,0.00065132737,0.00013564034],"domain_scores_gemma":[0.9975904,0.0008561546,0.00015980231,0.00081906875,0.00047355716,0.00010097308],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013040731,0.0010767396,0.0010731815,0.0010994336,0.00052420894,0.0018552975,0.0022496434,0.0009819841,0.008879917],"category_scores_gemma":[0.0053997915,0.0007859456,0.00095256104,0.0023935498,0.0009368396,0.004735949,0.0046106377,0.001691238,0.0028145702],"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":[0.0008492309,0.00020814572,0.0028084107,0.0010654962,0.00028516806,0.0005689408,0.0005714918,0.1162644,0.048733883,0.10251914,0.08352416,0.64260167],"study_design_scores_gemma":[0.000084359635,0.00022495871,0.00066310284,0.000126106,0.00007931319,0.0005094869,0.00039656615,0.6653768,0.043318756,0.2223083,0.0668383,0.000074052776],"about_ca_topic_score_codex":0.0014502689,"about_ca_topic_score_gemma":0.002023188,"teacher_disagreement_score":0.008879917,"about_ca_system_score_codex":0.00042372456,"about_ca_system_score_gemma":0.0008469195,"threshold_uncertainty_score":0.0297063},"labels":[],"label_agreement":null},{"id":"W2191117394","doi":"10.3390/a8041175","title":"A Data Analytic Algorithm for Managing, Querying, and Processing Uncertain Big Data in Cloud Environments","year":2015,"lang":"en","type":"article","venue":"Algorithms","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":68,"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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Big data; Computer science; Cloud computing; Database transaction; Transaction data; Uncertain data; Data mining; Data science; Analytics; Database","score_opus":0.15240265186952173,"score_gpt":0.3367926949173147,"score_spread":0.184390043047793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2191117394","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006163544,0.00018474874,0.9911805,0.0004361749,0.000056470682,0.00015742336,0.00014005396,0.0007120046,0.0009692095],"genre_scores_gemma":[0.08815927,0.00022584989,0.9098667,0.00015749656,0.00007236924,0.00026217816,0.00042610132,0.00007573527,0.0007542788],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982645,0.00030349346,0.00015779908,0.0003228952,0.0008057563,0.00014554444],"domain_scores_gemma":[0.9974692,0.0012219714,0.00021573581,0.0003605914,0.00061469426,0.000117789765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018831257,0.0011234847,0.0011771426,0.0020308373,0.0018699265,0.0025122534,0.0025948256,0.0013843187,0.0013921527],"category_scores_gemma":[0.008616394,0.00046051547,0.0010194407,0.00341693,0.0010400119,0.003911374,0.0024071294,0.0018089294,0.00063613575],"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":[0.0005226631,0.0004984964,0.0054802503,0.00039366222,0.0001544587,0.00046393988,0.00056493504,0.3349125,0.010293978,0.08387656,0.021670071,0.5411685],"study_design_scores_gemma":[0.000048253176,0.000041614614,0.00018632598,0.00001502854,0.00001814047,0.0001982715,0.00011427906,0.9649639,0.0029468404,0.026803585,0.0046460894,0.000017630975],"about_ca_topic_score_codex":0.0052822586,"about_ca_topic_score_gemma":0.003855261,"teacher_disagreement_score":0.0052822586,"about_ca_system_score_codex":0.0012686381,"about_ca_system_score_gemma":0.0035921258,"threshold_uncertainty_score":0.010502994},"labels":[],"label_agreement":null},{"id":"W2196676009","doi":"10.1109/cit/iucc/dasc/picom.2015.135","title":"Mining Binary Data with Matrix Algebra","year":2015,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"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 Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Correctness; Computer science; Binary number; Association rule learning; Data mining; Logical matrix; Binary data; Algorithm; Theoretical computer science; Mathematics; Arithmetic","score_opus":0.06869800794617999,"score_gpt":0.3107864526651324,"score_spread":0.2420884447189524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2196676009","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013116409,0.00049715495,0.98182213,0.0005001973,0.000071092734,0.00015814634,0.0008240479,0.0009932485,0.0020174545],"genre_scores_gemma":[0.11378543,0.00077921146,0.88091564,0.00026340593,0.00015559355,0.00034494564,0.002229014,0.000062679894,0.0014641042],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970626,0.00076714915,0.00041033173,0.0005653615,0.001046575,0.0001479395],"domain_scores_gemma":[0.99538946,0.002281368,0.0006596125,0.0007003208,0.0008554164,0.00011375142],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020796808,0.00085309404,0.001319629,0.003476388,0.0009607212,0.0027451303,0.0014492901,0.00057501165,0.0038341878],"category_scores_gemma":[0.012174666,0.0005711793,0.0012394926,0.0056870156,0.00081368943,0.005009809,0.0017558769,0.00149383,0.0020790317],"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":[0.0004510476,0.00043038093,0.008082937,0.0008845932,0.00026945266,0.0006256242,0.0005213861,0.08967776,0.013096606,0.1965948,0.011531853,0.6778335],"study_design_scores_gemma":[0.00007564262,0.00021681827,0.0013084585,0.000093273986,0.00004818618,0.0006106505,0.00033441553,0.6110109,0.008583528,0.35741252,0.020239983,0.00006556889],"about_ca_topic_score_codex":0.0022275543,"about_ca_topic_score_gemma":0.0023337698,"teacher_disagreement_score":0.0038341878,"about_ca_system_score_codex":0.00066436053,"about_ca_system_score_gemma":0.0012505793,"threshold_uncertainty_score":0.0128266215},"labels":[],"label_agreement":null},{"id":"W2206957322","doi":"","title":"Multivariate similarity-based conformity measure (MSCM): an outlier detection measure for data mining applications","year":2008,"lang":"en","type":"article","venue":"International conference on Artificial intelligence and applications","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Outlier; Measure (data warehouse); Conformity; Multivariate statistics; Computer science; Anomaly detection; Similarity (geometry); Data mining; Similarity measure; Statistics; Artificial intelligence; Mathematics; Machine learning; Psychology; Image (mathematics)","score_opus":0.2769317290678133,"score_gpt":0.3783007860891104,"score_spread":0.10136905702129706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2206957322","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053976525,0.0011191951,0.94170636,0.0004152168,0.00012366836,0.00013402442,0.00041532394,0.0008865442,0.0012231212],"genre_scores_gemma":[0.60129064,0.00065446954,0.39497274,0.00024634553,0.00035528792,0.00031046045,0.001168102,0.00016241735,0.00083959056],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9931594,0.0013638728,0.0006656583,0.000784195,0.0038595567,0.00016739123],"domain_scores_gemma":[0.99176383,0.0031221367,0.0018011974,0.0009610308,0.0020736875,0.0002781759],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004524113,0.0007425893,0.001721454,0.0054768715,0.00071156933,0.001519616,0.0014758011,0.0010809185,0.000695841],"category_scores_gemma":[0.019031558,0.00020931434,0.0011279141,0.0055344114,0.0010433283,0.0022549187,0.0016230451,0.0014333895,0.00036357951],"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":[0.0007644027,0.000452926,0.041855827,0.0007374318,0.000885203,0.00040324428,0.00062514516,0.08645818,0.02664548,0.035367046,0.00971659,0.7960886],"study_design_scores_gemma":[0.00006701076,0.0012686531,0.028240705,0.00011852917,0.0002203687,0.0012281219,0.00032629687,0.8821801,0.021698853,0.05307061,0.011365097,0.00021564603],"about_ca_topic_score_codex":0.0010291693,"about_ca_topic_score_gemma":0.0008511576,"teacher_disagreement_score":0.0054768715,"about_ca_system_score_codex":0.0007413755,"about_ca_system_score_gemma":0.0010944558,"threshold_uncertainty_score":0.02392608},"labels":[],"label_agreement":null},{"id":"W2207847180","doi":"10.14778/2824032.2824049","title":"Fuzzy joins in MapReduce","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Joins; Skyline; Computer science; Point (geometry); Hamming distance; Fuzzy logic; Binary number; Algorithm; Data mining; Theoretical computer science; Artificial intelligence; Mathematics; Programming language; Arithmetic","score_opus":0.03116395072858845,"score_gpt":0.24520602154516505,"score_spread":0.2140420708165766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2207847180","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5174333,0.0039302367,0.35098675,0.0028312334,0.0015852825,0.0016076011,0.0057292744,0.03777688,0.07811945],"genre_scores_gemma":[0.6643422,0.0007647894,0.3223282,0.0006564548,0.0002267289,0.000395999,0.005470452,0.0006303902,0.0051846844],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994206,0.0010151591,0.00033481471,0.00097580545,0.0028367958,0.00063154515],"domain_scores_gemma":[0.99545693,0.0016666582,0.00016143073,0.0014803646,0.00083933055,0.0003953603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036824725,0.0011063463,0.0012332445,0.0011782051,0.0026637893,0.0025517656,0.0032082836,0.0012386262,0.0052903723],"category_scores_gemma":[0.0066602402,0.00062511844,0.0010964867,0.0026587457,0.0010340337,0.005090884,0.0027533195,0.001856405,0.0018188988],"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":[0.007912346,0.004774502,0.0115281725,0.0026981984,0.000791632,0.00080273073,0.0020608762,0.23203468,0.044756543,0.06991165,0.09677851,0.5259502],"study_design_scores_gemma":[0.0011894081,0.0019510981,0.0049622925,0.00011237338,0.00025928026,0.00091596955,0.002116526,0.71854943,0.07701304,0.1252849,0.067470714,0.00017497213],"about_ca_topic_score_codex":0.00771948,"about_ca_topic_score_gemma":0.0073085944,"teacher_disagreement_score":0.00771948,"about_ca_system_score_codex":0.0014110061,"about_ca_system_score_gemma":0.00234579,"threshold_uncertainty_score":0.019475043},"labels":[],"label_agreement":null},{"id":"W2214080290","doi":"10.1145/2700409","title":"Classification with Streaming Features: An Emerging-Pattern Mining Approach","year":2015,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Streaming data; Feature selection; Data mining; Benchmark (surveying); Classifier (UML); Curse of dimensionality; Feature (linguistics); Machine learning; Artificial intelligence; Feature vector; Pattern recognition (psychology)","score_opus":0.11101318228584427,"score_gpt":0.32390555529082665,"score_spread":0.21289237300498237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2214080290","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036984995,0.0007916342,0.95903707,0.0003847621,0.00011071055,0.0001713821,0.0006274522,0.0011087628,0.0007832348],"genre_scores_gemma":[0.48803386,0.000791578,0.50621855,0.0001977513,0.00031526896,0.00029129162,0.00220712,0.00012485086,0.0018198299],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99872905,0.0002076957,0.00014900755,0.00043129883,0.0003893489,0.00009358759],"domain_scores_gemma":[0.9963097,0.0012184865,0.00054554717,0.0007189023,0.0010585678,0.00014884931],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017681303,0.00096507336,0.0015211195,0.0029949867,0.00055632344,0.0013139897,0.002436844,0.0009118359,0.0008835172],"category_scores_gemma":[0.0061300136,0.00035565556,0.001008936,0.003925871,0.0005004139,0.0035610385,0.0010938639,0.001398631,0.0006812078],"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":[0.00035923132,0.0004661958,0.025318941,0.00027782097,0.00024824182,0.00060046604,0.00028235756,0.08947644,0.0098674735,0.008495264,0.00989962,0.85470796],"study_design_scores_gemma":[0.000018925653,0.00010517798,0.0022984303,0.00002155433,0.000041313902,0.00025906437,0.00008384064,0.978508,0.0024484775,0.0128702065,0.0033229408,0.000022117385],"about_ca_topic_score_codex":0.0016668997,"about_ca_topic_score_gemma":0.0019823753,"teacher_disagreement_score":0.0029949867,"about_ca_system_score_codex":0.0004834595,"about_ca_system_score_gemma":0.0006526641,"threshold_uncertainty_score":0.009350836},"labels":[],"label_agreement":null},{"id":"W2215860650","doi":"10.1504/ijbdi.2015.070597","title":"Unstructured data mining: use case for CouchDB","year":2015,"lang":"en","type":"article","venue":"International Journal of Big Data Intelligence","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":9,"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 Saskatchewan","funders":"Mitacs","keywords":"NoSQL; Computer science; Semi-structured data; Unstructured data; Database; Append; Storage model; Relational database; Big data; Relational database management system; Data mining; Information retrieval; Data science; World Wide Web","score_opus":0.4767861738691988,"score_gpt":0.4121020276593292,"score_spread":0.06468414620986962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2215860650","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60626024,0.0053812936,0.23498467,0.014343193,0.0008090764,0.0028446862,0.018645149,0.05278997,0.06394175],"genre_scores_gemma":[0.6071859,0.001635837,0.36351797,0.0013433333,0.00015239397,0.00038250364,0.014044924,0.0012812115,0.010455941],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9968411,0.0007205355,0.00026646483,0.0004998244,0.0014476043,0.00022453746],"domain_scores_gemma":[0.99237615,0.00407828,0.0001869399,0.0017323915,0.0012089649,0.00041734573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004074897,0.0005698552,0.0007326583,0.0025536877,0.0017134495,0.0037324436,0.0023220377,0.0016978177,0.0021048277],"category_scores_gemma":[0.011561947,0.00032046626,0.0005837824,0.005244953,0.0010547624,0.0037109356,0.0021978156,0.0014329875,0.0008817535],"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":[0.003350537,0.0023416444,0.071947604,0.002647431,0.00044629216,0.012463824,0.008101081,0.044368103,0.023435263,0.08297857,0.13020615,0.6177136],"study_design_scores_gemma":[0.00060290913,0.00067962543,0.019261427,0.00035612288,0.00016711435,0.0044322726,0.004395621,0.44428277,0.05965037,0.050506502,0.41550183,0.00016331766],"about_ca_topic_score_codex":0.017347405,"about_ca_topic_score_gemma":0.017585441,"teacher_disagreement_score":0.017347405,"about_ca_system_score_codex":0.0013230137,"about_ca_system_score_gemma":0.0018918585,"threshold_uncertainty_score":0.03449285},"labels":[],"label_agreement":null},{"id":"W2218838193","doi":"10.1109/cmpsac.2000.884768","title":"Web Intelligence (WI)","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":71,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Web intelligence; Computer science; World Wide Web; Web development; Web standards; Web engineering; The Internet; Web modeling; Web Accessibility Initiative; Web application security; Social Semantic Web; Data Web; Field (mathematics); Web page; Web service","score_opus":0.039594525865728925,"score_gpt":0.25345153985559354,"score_spread":0.21385701398986462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2218838193","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031555798,0.049432177,0.089471996,0.011494122,0.0048235524,0.0004936901,0.0027757068,0.005056375,0.8332969],"genre_scores_gemma":[0.1114527,0.1398555,0.21853688,0.016564384,0.007874969,0.0011299208,0.012318681,0.002046521,0.4902205],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969405,0.0005531186,0.000327616,0.00043411256,0.0015297107,0.00021488141],"domain_scores_gemma":[0.99784875,0.000533787,0.00024098209,0.0007266661,0.00037707752,0.00027269946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015160029,0.0011487872,0.00074334687,0.0050396817,0.0016480688,0.01162084,0.0017883572,0.0032419746,0.031159515],"category_scores_gemma":[0.0056970166,0.00043882377,0.0006154352,0.007976678,0.0026148616,0.015728869,0.005920741,0.0026024154,0.025252951],"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":[0.00002472371,0.00004575898,0.00053459604,0.000887551,0.000048891503,0.00032977745,0.00046059792,0.00026082605,0.000986241,0.45299178,0.1713248,0.3721045],"study_design_scores_gemma":[0.0000028966956,0.000007893071,0.00019656723,0.00023764864,0.000010308485,0.00035462753,0.00009226901,0.0002455069,0.00029613642,0.048262578,0.9502834,0.000010028929],"about_ca_topic_score_codex":0.0010909775,"about_ca_topic_score_gemma":0.0011847939,"teacher_disagreement_score":0.031159515,"about_ca_system_score_codex":0.001012113,"about_ca_system_score_gemma":0.0017974834,"threshold_uncertainty_score":0.10423899},"labels":[],"label_agreement":null},{"id":"W2219480549","doi":"10.4018/ijssci.2015040102","title":"Analyze Physical Design Process Using Big Data Tool","year":2015,"lang":"en","type":"article","venue":"International Journal of Software Science and Computational Intelligence","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Data mining; Data extraction; Process (computing); Data cleansing; Parsing; Data quality; External Data Representation; Data validation; Regular expression; Database; Programming language; Artificial intelligence","score_opus":0.20034241897556992,"score_gpt":0.3961846232129621,"score_spread":0.19584220423739218,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2219480549","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14207166,0.001431437,0.62979543,0.0014105173,0.00032745424,0.0017238907,0.121200874,0.07772684,0.024311915],"genre_scores_gemma":[0.38879678,0.0015251047,0.43922794,0.00030756046,0.00008818413,0.0028056079,0.15069562,0.0028282548,0.013724896],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99808025,0.00017494013,0.00025202383,0.00030717562,0.0010935067,0.000092070026],"domain_scores_gemma":[0.9963296,0.0013349747,0.00040019114,0.00085737364,0.0009444494,0.00013346634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001543018,0.0013602717,0.0009067294,0.0043122713,0.00055356795,0.0019775662,0.0013028416,0.000663864,0.010260798],"category_scores_gemma":[0.005124186,0.00069443916,0.0014399176,0.0030588664,0.00036345405,0.0017169948,0.0008994529,0.0009809579,0.0032214643],"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":[0.0009013429,0.0010160238,0.083831385,0.004518504,0.00049408694,0.001977162,0.0017023474,0.2059438,0.034353916,0.016828239,0.09920516,0.549228],"study_design_scores_gemma":[0.00017801023,0.00075032323,0.05115611,0.00035463332,0.00023375965,0.0010240545,0.0010538821,0.6456359,0.099292375,0.027246842,0.17281972,0.00025442193],"about_ca_topic_score_codex":0.0025356445,"about_ca_topic_score_gemma":0.0034265528,"teacher_disagreement_score":0.010260798,"about_ca_system_score_codex":0.0006894095,"about_ca_system_score_gemma":0.0015865458,"threshold_uncertainty_score":0.03432578},"labels":[],"label_agreement":null},{"id":"W2223539003","doi":"10.1007/978-3-319-26535-3_58","title":"On the Discovery of Time Distance Constrained Temporal Association Rules","year":2015,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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":"Bishop's University","funders":"","keywords":"Computer science; Association rule learning; Singleton; Multiset; Constraint (computer-aided design); Data mining; Knowledge extraction; Time constraint; Set (abstract data type); Event (particle physics); Artificial intelligence; Mathematics","score_opus":0.018159200885518242,"score_gpt":0.24324942796916096,"score_spread":0.22509022708364274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2223539003","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08527411,0.004362777,0.90186936,0.0016744907,0.0002605559,0.00030376436,0.0022827454,0.0008147729,0.0031573486],"genre_scores_gemma":[0.35289815,0.004272315,0.6263231,0.0010017718,0.0006484941,0.0005256042,0.008961452,0.00022100817,0.0051481887],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.992751,0.0015891929,0.0009272576,0.0016894758,0.002590311,0.00045274416],"domain_scores_gemma":[0.9308943,0.05815254,0.0031994304,0.0038414442,0.0030670157,0.00084525713],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0065322644,0.0012152351,0.0033506209,0.0045147664,0.0012177943,0.0037520917,0.004237249,0.0021066654,0.0025744874],"category_scores_gemma":[0.053137213,0.0011280209,0.0022088396,0.009270431,0.002036426,0.0070690718,0.0042351414,0.0032814012,0.0009850492],"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":[0.0014724827,0.0008496919,0.021590877,0.0011564123,0.00066476484,0.0017707007,0.00096544117,0.15715756,0.005693776,0.10469092,0.012575287,0.69141203],"study_design_scores_gemma":[0.00008740956,0.00019095227,0.00235677,0.00017532292,0.00014858406,0.0006465606,0.0002487852,0.8077768,0.0019720613,0.18147244,0.0048700487,0.000054240663],"about_ca_topic_score_codex":0.0057353047,"about_ca_topic_score_gemma":0.0052088075,"teacher_disagreement_score":0.0065322644,"about_ca_system_score_codex":0.001052353,"about_ca_system_score_gemma":0.0026947972,"threshold_uncertainty_score":0.034546316},"labels":[],"label_agreement":null},{"id":"W2225600736","doi":"10.1007/978-0-387-69937-0_5","title":"Mining Partial Orders from Sequences","year":2007,"lang":"en","type":"book-chapter","venue":"","topic":"Data Mining Algorithms and Applications","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":"Simon Fraser University","funders":"","keywords":"Computer science","score_opus":0.05757596481685249,"score_gpt":0.28194899144935154,"score_spread":0.22437302663249906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2225600736","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0588805,0.0034399552,0.90710276,0.0009616526,0.00022758888,0.00044653282,0.0068174903,0.005138319,0.01698515],"genre_scores_gemma":[0.17844948,0.003262648,0.7793163,0.00023020564,0.00029745785,0.00027126304,0.021837045,0.0005525357,0.01578308],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989084,0.00013666732,0.000098493925,0.00025158143,0.0005410393,0.000063731975],"domain_scores_gemma":[0.9975643,0.0014100292,0.0001640823,0.00046406285,0.00031008915,0.000087378794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006730818,0.0010801135,0.0012454487,0.0032830783,0.00067929237,0.0019043275,0.0013391689,0.0005785482,0.006357227],"category_scores_gemma":[0.005715435,0.0007570436,0.0015898258,0.0043707117,0.0007623371,0.0040673553,0.0010352244,0.0013881947,0.0029562342],"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":[0.00025898826,0.00020798389,0.004395939,0.0010918688,0.00016765419,0.0006088974,0.00039267843,0.031428207,0.007407865,0.062231366,0.019185126,0.8726235],"study_design_scores_gemma":[0.00007460086,0.00027384463,0.00279901,0.00037467247,0.00017395796,0.0021585724,0.00048111836,0.3660562,0.022355596,0.53749657,0.06767961,0.00007624574],"about_ca_topic_score_codex":0.0013403229,"about_ca_topic_score_gemma":0.0032194667,"teacher_disagreement_score":0.006357227,"about_ca_system_score_codex":0.0005776208,"about_ca_system_score_gemma":0.001351552,"threshold_uncertainty_score":0.021267056},"labels":[],"label_agreement":null},{"id":"W2231083320","doi":"10.22215/etd/2008-06473","title":"Novel micro-aggregation techniques for secure statistical databases","year":2008,"lang":"en","type":"dissertation","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; Canadian Heritage; Library and Archives Canada","funders":"Hashemite University","keywords":"Computer science; Information retrieval; Database","score_opus":0.03178988269904404,"score_gpt":0.3221447583006916,"score_spread":0.2903548756016476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2231083320","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013613347,0.000517831,0.9817145,0.00042130612,0.00011596515,0.00007430863,0.0001484162,0.0014390034,0.0019553413],"genre_scores_gemma":[0.3164341,0.0008256118,0.67163527,0.00034464162,0.0004991478,0.00021953897,0.0006024131,0.00034572763,0.009093539],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960328,0.00078967825,0.0004557489,0.00046457935,0.0019734455,0.00028381313],"domain_scores_gemma":[0.9905748,0.002154212,0.0008737123,0.0049432777,0.001243336,0.00021075782],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021805293,0.0005897679,0.0009881698,0.0018165049,0.001032234,0.0026391076,0.0014598144,0.00053889916,0.0038957978],"category_scores_gemma":[0.0076607107,0.0005500016,0.00088951836,0.0033061868,0.00082760944,0.003775356,0.0033091563,0.001487302,0.0019749056],"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":[0.0006555167,0.0002331313,0.0039305342,0.00016235672,0.00018742435,0.00032109834,0.0006648447,0.03698323,0.027470922,0.17061713,0.0137031255,0.7450707],"study_design_scores_gemma":[0.00008579482,0.00026535196,0.0016906663,0.000053836848,0.0001308201,0.0011323788,0.00034621754,0.73934597,0.043695834,0.17610577,0.03708359,0.00006380285],"about_ca_topic_score_codex":0.0009850172,"about_ca_topic_score_gemma":0.0019372911,"teacher_disagreement_score":0.0038957978,"about_ca_system_score_codex":0.000926132,"about_ca_system_score_gemma":0.0015027376,"threshold_uncertainty_score":0.013032734},"labels":[],"label_agreement":null},{"id":"W2235748256","doi":"10.5753/cbie.wcbie.2015.1044","title":"Mineração de dados educacionais e Mundos Virtuais: um estudo exploratório no OpenSim","year":2015,"lang":"pt","type":"article","venue":"Anais ... Workshops do Congresso Brasileiro de Informática na Educação","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Bureau for International Education","keywords":"Computer science; Humanities; Art","score_opus":0.05272818861287019,"score_gpt":0.31485970609692476,"score_spread":0.26213151748405455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2235748256","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4636591,0.0020502014,0.49973866,0.0026550132,0.00027073434,0.0005478496,0.0020196598,0.0071957447,0.021863071],"genre_scores_gemma":[0.80844563,0.0012749267,0.1819163,0.0002530186,0.000052244868,0.00045820558,0.001388474,0.0005597773,0.0056514507],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99696475,0.0012522155,0.00020456639,0.00046127406,0.000932985,0.00018432556],"domain_scores_gemma":[0.99036586,0.005756004,0.0005529197,0.0016413904,0.0012253614,0.00045850678],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038229995,0.0007188541,0.00079694024,0.0016481989,0.0010214443,0.0030084949,0.0014449719,0.000756696,0.0032267035],"category_scores_gemma":[0.02104986,0.0004967994,0.0007595182,0.0016875971,0.0012471398,0.0048145684,0.004339359,0.0013007004,0.0007616216],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015986031,0.0007738779,0.06725296,0.003639039,0.00035538798,0.0018890316,0.029366385,0.054605946,0.05303031,0.08522612,0.013511474,0.6887508],"study_design_scores_gemma":[0.00020743888,0.0015660414,0.036735903,0.0013891988,0.00047372913,0.0027472319,0.019100055,0.46542567,0.09480061,0.12623613,0.2508686,0.00044942505],"about_ca_topic_score_codex":0.0024581894,"about_ca_topic_score_gemma":0.0027065175,"teacher_disagreement_score":0.0038229995,"about_ca_system_score_codex":0.0008228547,"about_ca_system_score_gemma":0.0019358828,"threshold_uncertainty_score":0.020218194},"labels":[],"label_agreement":null},{"id":"W2237607452","doi":"10.5753/cbie.wcbie.2015.1064","title":"Uma Abordagem de Data Warehouse Educacional para Apoio à Tomada de Decisão","year":2015,"lang":"pt","type":"article","venue":"Anais ... Workshops do Congresso Brasileiro de Informática na Educação","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Bureau for International Education","keywords":"Data warehouse; Computer science; Table (database); Transactional leadership; Order (exchange); Database; Materialized view; Knowledge management; Business; Management; Database design","score_opus":0.12594677928781478,"score_gpt":0.3683637212933682,"score_spread":0.24241694200555342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2237607452","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06309375,0.0015252535,0.87674826,0.0066355793,0.0005602485,0.0007379112,0.0017959379,0.031237988,0.017665137],"genre_scores_gemma":[0.15037109,0.0011962972,0.8356382,0.00086122437,0.00014564907,0.00031592266,0.0024743972,0.0016340229,0.00736317],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9898253,0.0033406185,0.0010604847,0.0014305877,0.0039074225,0.00043562235],"domain_scores_gemma":[0.9762565,0.0057671736,0.0009943153,0.00927114,0.006936837,0.00077396963],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018975262,0.0011550225,0.0013282918,0.0040489063,0.0026604293,0.016055679,0.002953305,0.0019595397,0.0026066767],"category_scores_gemma":[0.026134823,0.0013812562,0.0018201431,0.00497417,0.0013408931,0.010391437,0.0038732984,0.0041985502,0.001936573],"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":[0.0008449363,0.0010387439,0.014115818,0.0010313898,0.0003252258,0.0022408194,0.015060233,0.0107382415,0.020130772,0.04826444,0.028631488,0.85757786],"study_design_scores_gemma":[0.00039989856,0.00096727983,0.010400239,0.001721787,0.0010096994,0.0036149656,0.010702177,0.23945057,0.09985683,0.055017468,0.57630205,0.0005570036],"about_ca_topic_score_codex":0.005724661,"about_ca_topic_score_gemma":0.0059559084,"teacher_disagreement_score":0.018975262,"about_ca_system_score_codex":0.0015591416,"about_ca_system_score_gemma":0.004844759,"threshold_uncertainty_score":0.10035193},"labels":[],"label_agreement":null},{"id":"W2247310798","doi":"","title":"A New Search Tool for Collecting Quantitative Data","year":2010,"lang":"en","type":"article","venue":"EdMedia: World Conference on Educational Media and Technology","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","score_opus":0.108624309076709,"score_gpt":0.36479983183584924,"score_spread":0.25617552275914024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2247310798","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01013705,0.0008389267,0.9434085,0.00050225505,0.00013839976,0.0010064144,0.021888731,0.018860187,0.0032195314],"genre_scores_gemma":[0.04335226,0.0003737514,0.9336238,0.00034815856,0.00009184306,0.002372256,0.015087263,0.00060643017,0.0041442025],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9895251,0.002077447,0.0017505074,0.0015617993,0.0048114834,0.00027357484],"domain_scores_gemma":[0.9682892,0.020499012,0.0016373235,0.0037100334,0.0052632615,0.00060110877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006619258,0.0015189426,0.002724651,0.017104674,0.0014314374,0.0037465345,0.0020184624,0.0021866444,0.0097427815],"category_scores_gemma":[0.038642146,0.0008169342,0.0013116684,0.019888548,0.00063169515,0.005933521,0.003090247,0.0012047064,0.006400339],"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":[0.00073984166,0.0005360247,0.012386137,0.003007573,0.00041831963,0.0004141702,0.001131478,0.00354886,0.02480805,0.01678048,0.05766301,0.8785659],"study_design_scores_gemma":[0.0008554279,0.0016432222,0.028070882,0.0010490991,0.0012173543,0.004600795,0.0023759247,0.43533194,0.09276531,0.12914163,0.3023183,0.0006301497],"about_ca_topic_score_codex":0.0027158894,"about_ca_topic_score_gemma":0.005253025,"teacher_disagreement_score":0.017104674,"about_ca_system_score_codex":0.0007094266,"about_ca_system_score_gemma":0.0030350897,"threshold_uncertainty_score":0.035006404},"labels":[],"label_agreement":null},{"id":"W2247396692","doi":"10.1007/978-3-319-22729-0_5","title":"Balancing Tree Size and Accuracy in Fast Mining of Uncertain Frequent Patterns","year":2015,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":11,"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; Upper and lower bounds; Tree (set theory); Data mining; Space (punctuation); False positive paradox; Algorithm; Machine learning; Mathematics","score_opus":0.028343758306821735,"score_gpt":0.2752348080388703,"score_spread":0.24689104973204856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2247396692","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29256946,0.0072656632,0.6896189,0.0024311615,0.00050339656,0.00025861926,0.00082676276,0.002450533,0.0040755393],"genre_scores_gemma":[0.6832435,0.0013290683,0.31180933,0.00029035393,0.00059641275,0.00015654578,0.0007687859,0.00034105004,0.0014648257],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99489504,0.0016336726,0.0005429937,0.0007789959,0.0017422267,0.00040708066],"domain_scores_gemma":[0.9200817,0.06829311,0.0019323238,0.004438658,0.0043214294,0.00093280006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007618347,0.00087633193,0.0018922024,0.002361062,0.0009357121,0.002542297,0.0028852194,0.0021240776,0.0015353272],"category_scores_gemma":[0.05953172,0.000893035,0.00077867456,0.0031281447,0.0008840026,0.0075420174,0.0020927556,0.0014459216,0.0007372922],"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":[0.00316454,0.00040016507,0.01953134,0.0005347232,0.0002608461,0.0003109143,0.0007342036,0.18563657,0.018773068,0.015736237,0.010156656,0.7447608],"study_design_scores_gemma":[0.00014815106,0.00033383237,0.0025033418,0.000061442086,0.00012230793,0.0003949565,0.00020266348,0.95597905,0.004735096,0.03402525,0.0014580997,0.00003577878],"about_ca_topic_score_codex":0.00179423,"about_ca_topic_score_gemma":0.0028228275,"teacher_disagreement_score":0.007618347,"about_ca_system_score_codex":0.0009275618,"about_ca_system_score_gemma":0.0014368896,"threshold_uncertainty_score":0.040290177},"labels":[],"label_agreement":null},{"id":"W2248162944","doi":"10.2495/data030381","title":"A generic Data Mart architecture to support Web mining","year":2003,"lang":"en","type":"article","venue":"International Conference on Data Mining","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hatch (Canada)","funders":"","keywords":"Computer science; Session (web analytics); Web mining; Table (database); World Wide Web; Task (project management); Web page; Architecture; Information retrieval; Dimension (graph theory); Web mapping; Web navigation; Data mining; Engineering","score_opus":0.1893250635618382,"score_gpt":0.36052724099557815,"score_spread":0.17120217743373994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2248162944","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01018681,0.00041263681,0.921486,0.00033755237,0.00017563307,0.00041896108,0.007762587,0.056823965,0.002395795],"genre_scores_gemma":[0.0963467,0.000743652,0.8626626,0.0005636486,0.00012304632,0.00062571507,0.03289585,0.0029796602,0.003059129],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99803597,0.00022593455,0.0004443185,0.00047912935,0.00066775334,0.00014679845],"domain_scores_gemma":[0.99725336,0.0004419348,0.00017857278,0.0013624161,0.00057952513,0.0001842016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029775754,0.0012592041,0.0011527763,0.0021095483,0.0005387076,0.0035937682,0.0037431312,0.0011153389,0.0036706077],"category_scores_gemma":[0.005813645,0.0012831155,0.002414485,0.0027406397,0.0006047186,0.004211317,0.0029954552,0.0023537534,0.0036223189],"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":[0.0015991895,0.0008928915,0.0198253,0.0022335076,0.0008317474,0.0012687715,0.0009181905,0.16785116,0.043020345,0.08171882,0.078282446,0.60155773],"study_design_scores_gemma":[0.00015257318,0.00026139684,0.0035073012,0.00018602707,0.00021564399,0.000777252,0.00017901672,0.7334134,0.03150814,0.05175604,0.17786856,0.00017460616],"about_ca_topic_score_codex":0.0042685326,"about_ca_topic_score_gemma":0.0033921087,"teacher_disagreement_score":0.0042685326,"about_ca_system_score_codex":0.00092849985,"about_ca_system_score_gemma":0.0019425738,"threshold_uncertainty_score":0.01574713},"labels":[],"label_agreement":null},{"id":"W2261853291","doi":"10.1109/newcas.2011.5981220","title":"Association rules learning technique for knowledge mining about scheduling algorithm performance","year":2011,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Scheduling (production processes); Association rule learning; Fair-share scheduling; Two-level scheduling; Dynamic priority scheduling; Machine learning; Algorithm; Artificial intelligence; Engineering; Quality of service","score_opus":0.03253282073797621,"score_gpt":0.26634424457166916,"score_spread":0.23381142383369297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2261853291","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010676989,0.0004441414,0.9846837,0.00035191848,0.00007606012,0.00025428872,0.0008275671,0.0015445537,0.0011408752],"genre_scores_gemma":[0.13624476,0.0006068348,0.85834944,0.00024577265,0.00013480954,0.00069634884,0.0025389846,0.0000764483,0.0011066305],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9940235,0.0014914033,0.001016179,0.0012580901,0.0020141434,0.00019665208],"domain_scores_gemma":[0.97943795,0.015055036,0.0013728704,0.0016742196,0.002227574,0.00023228006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063455235,0.0014952353,0.0020597961,0.0072909757,0.0012098079,0.0021070081,0.003070968,0.0019089817,0.0017367873],"category_scores_gemma":[0.032469533,0.0005540071,0.0019164992,0.00622162,0.0007619301,0.0028892457,0.001211112,0.0039673434,0.0014453861],"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":[0.000349496,0.001314819,0.013687493,0.00061788247,0.0008113489,0.00055017427,0.00041840607,0.084139876,0.0045579877,0.013462417,0.007841861,0.8722483],"study_design_scores_gemma":[0.000081202095,0.00031575045,0.0040555634,0.00019712104,0.00036091072,0.0007395505,0.00023709475,0.92129505,0.012636657,0.04922165,0.010757247,0.00010227197],"about_ca_topic_score_codex":0.0033610573,"about_ca_topic_score_gemma":0.0044932426,"teacher_disagreement_score":0.0072909757,"about_ca_system_score_codex":0.0007493643,"about_ca_system_score_gemma":0.0021814175,"threshold_uncertainty_score":0.033558726},"labels":[],"label_agreement":null},{"id":"W2262769147","doi":"","title":"Model-Based Recommendation System In Support Of Construction Equipment Management - A Case Study","year":2006,"lang":"en","type":"article","venue":"Proceedings of the Joint CIB W78, W102, ICCCBE, ICCC, and DMUCE International Conference on Computing and Decision Making in Civil and Building Engineering, Montreal, Canada, 14-16 June","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Mobile device; Data management; Management system; Work (physics); Data mining; Data science; Risk analysis (engineering); Engineering; Operations management; World Wide Web","score_opus":0.01684351933602662,"score_gpt":0.2520294649280568,"score_spread":0.23518594559203015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2262769147","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88668317,0.000340241,0.09357102,0.0024454158,0.00006474009,0.0004820713,0.00080935727,0.004067442,0.01153652],"genre_scores_gemma":[0.9210078,0.0001554474,0.07327976,0.00012317934,0.000015931584,0.00010913522,0.0007202767,0.000065279026,0.0045231907],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99920875,0.00034515196,0.000080192694,0.00012965912,0.00017013958,0.00006621658],"domain_scores_gemma":[0.9963471,0.002239643,0.00012079598,0.0005329052,0.0005665129,0.0001930329],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015819148,0.0004286818,0.0005159174,0.00064392644,0.0007418324,0.0008272128,0.0013688483,0.0019448586,0.0031842643],"category_scores_gemma":[0.0053573293,0.00021164448,0.00040616517,0.00081268285,0.0002272162,0.0011806379,0.0003812881,0.0005091453,0.0007908089],"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":[0.0021445055,0.0053927675,0.06606542,0.0005935317,0.00028118017,0.013632681,0.0032381127,0.29253533,0.021830998,0.007858456,0.025143445,0.56128347],"study_design_scores_gemma":[0.00019887062,0.0007036513,0.00863963,0.000030177463,0.000085312415,0.001182884,0.00074719684,0.96639395,0.00837952,0.0012005592,0.012386809,0.000051386007],"about_ca_topic_score_codex":0.014415136,"about_ca_topic_score_gemma":0.02034148,"teacher_disagreement_score":0.014415136,"about_ca_system_score_codex":0.00073349144,"about_ca_system_score_gemma":0.00054796087,"threshold_uncertainty_score":0.028662503},"labels":[],"label_agreement":null},{"id":"W2274819190","doi":"10.11575/prism/30582","title":"Using Learning of Behavior Rules to Mine Medical Data for Sequence Rules","year":2004,"lang":"en","type":"article","venue":"PRISM (University of Calgary)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Sequence (biology); Computer science; Set (abstract data type); Data mining; Artificial intelligence; Association rule learning; Operator (biology); Field (mathematics); Genetic algorithm; Machine learning; Mathematics","score_opus":0.0668885352471919,"score_gpt":0.29457990373855475,"score_spread":0.22769136849136284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2274819190","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06582839,0.00028534574,0.93034506,0.0005380971,0.000031591324,0.0002835813,0.00025735854,0.001109381,0.0013210553],"genre_scores_gemma":[0.32389414,0.0002127364,0.6736708,0.00020585973,0.000023027256,0.00023743317,0.00088145846,0.00006848958,0.00080600684],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987734,0.0004078087,0.00012448154,0.00035812138,0.000281199,0.00005490872],"domain_scores_gemma":[0.99397993,0.004289916,0.0005656641,0.00040137532,0.0006536239,0.000109556444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023912962,0.00071013015,0.00070215506,0.0024346705,0.0005400685,0.00088663783,0.0012889581,0.0010248662,0.0007491758],"category_scores_gemma":[0.012447736,0.0003644797,0.00091540534,0.0011675073,0.0009646051,0.0011372848,0.00056179595,0.0011312239,0.00038559685],"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":[0.0001881419,0.0005342039,0.03814254,0.00028427143,0.00033333543,0.00056683185,0.00069772254,0.28794175,0.009587645,0.010488707,0.0022787252,0.648956],"study_design_scores_gemma":[0.00002554674,0.00013747808,0.0024069415,0.00006430938,0.00005411181,0.00025357958,0.00010608965,0.9680619,0.006586245,0.02035004,0.0019312347,0.000022447262],"about_ca_topic_score_codex":0.0057615633,"about_ca_topic_score_gemma":0.006813547,"teacher_disagreement_score":0.0057615633,"about_ca_system_score_codex":0.0007503697,"about_ca_system_score_gemma":0.0013324033,"threshold_uncertainty_score":0.012646496},"labels":[],"label_agreement":null},{"id":"W2276717191","doi":"10.1002/cpe.3773","title":"Parallel social network mining for interesting ‘following’ patterns","year":2016,"lang":"en","type":"article","venue":"Concurrency and Computation Practice and Experience","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":66,"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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; University of Manitoba","keywords":"Interdependence; Computer science; Friendship; Social network (sociolinguistics); Social network analysis; Data science; Data mining; World Wide Web; Social media; Sociology","score_opus":0.0467482113840547,"score_gpt":0.3547713504565648,"score_spread":0.3080231390725101,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2276717191","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39544043,0.0006159044,0.5883375,0.0012697221,0.000118026044,0.00048801614,0.0050558248,0.0029335667,0.005740975],"genre_scores_gemma":[0.7031862,0.00013620038,0.28836244,0.00007962187,0.000058507758,0.00021689359,0.0059389756,0.000090818714,0.0019303726],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979826,0.00030431044,0.00022834024,0.0005948474,0.0007071624,0.00018269572],"domain_scores_gemma":[0.99547845,0.001627872,0.0007527393,0.0011159944,0.00083310757,0.00019192701],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001179324,0.0006236875,0.0010145033,0.004357516,0.0012054892,0.0013887011,0.0017782341,0.0008053427,0.0020384504],"category_scores_gemma":[0.008978977,0.00044973282,0.0011915552,0.004186015,0.0006059856,0.0021943152,0.0015671827,0.0008240564,0.000881683],"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":[0.001028198,0.00091937603,0.11251042,0.00054062513,0.0006061203,0.0014231714,0.0010987243,0.19572821,0.018363886,0.034499496,0.017626703,0.61565506],"study_design_scores_gemma":[0.000030893127,0.000064783715,0.0056235706,0.000018998395,0.000050846604,0.0003863754,0.00021881402,0.9535578,0.005016325,0.029930975,0.0050826976,0.000017903714],"about_ca_topic_score_codex":0.0037743412,"about_ca_topic_score_gemma":0.0062532364,"teacher_disagreement_score":0.004357516,"about_ca_system_score_codex":0.00067822216,"about_ca_system_score_gemma":0.0012984724,"threshold_uncertainty_score":0.007504761},"labels":[],"label_agreement":null},{"id":"W2277267280","doi":"10.20381/ruor-19790","title":"Learning from multirelational data through multiple views","year":2008,"lang":"en","type":"article","venue":"uO Research (University of Ottawa)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Relational database; Computer science; Class (philosophy); Data mining; Construct (python library); Table (database); Skew; Artificial intelligence","score_opus":0.3201139204714333,"score_gpt":0.3537304252528201,"score_spread":0.033616504781386836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2277267280","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024630591,0.00085954694,0.97200173,0.0007143088,0.00003862294,0.00009880845,0.00033992904,0.00042673954,0.00088977657],"genre_scores_gemma":[0.33870083,0.0014203406,0.6556144,0.00044171428,0.00019493687,0.0002858454,0.002320703,0.00010977797,0.00091153453],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99167013,0.0029842337,0.0006037537,0.0022760855,0.0021334006,0.0003324069],"domain_scores_gemma":[0.98098844,0.011127064,0.0015376162,0.0040262653,0.0018963673,0.0004242922],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007720561,0.0014292913,0.001955655,0.0038282042,0.0008521955,0.006049368,0.0029360515,0.0015395031,0.0012422648],"category_scores_gemma":[0.019851977,0.0011909107,0.0035149707,0.0037530186,0.002187908,0.0102383625,0.005621185,0.0035027678,0.00063546497],"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":[0.00057475973,0.0005698797,0.033238526,0.00078618387,0.0011205134,0.0012833806,0.0037380627,0.17246959,0.009118915,0.10835442,0.0071908413,0.66155493],"study_design_scores_gemma":[0.00002913171,0.00015169845,0.00255215,0.00012792514,0.00015791769,0.00030616092,0.0007098202,0.8493436,0.003486869,0.13720445,0.0058728317,0.000057469453],"about_ca_topic_score_codex":0.0032513274,"about_ca_topic_score_gemma":0.003950556,"teacher_disagreement_score":0.007720561,"about_ca_system_score_codex":0.0013066771,"about_ca_system_score_gemma":0.0013773639,"threshold_uncertainty_score":0.04083073},"labels":[],"label_agreement":null},{"id":"W2291907356","doi":"","title":"Webkdd 2002 - Mining Web Data for Discovering Usage Patterns and Profiles: 4th International Workshop Edmonton, Canada, July 23, 2002 (Lecture Notes in Artificial Intelligence)","year":2003,"lang":"en","type":"book","venue":"Springer eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Data science; Computer science; World Wide Web; Library science","score_opus":0.04291274280225486,"score_gpt":0.27214875823973533,"score_spread":0.22923601543748048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2291907356","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07109604,0.026549252,0.41420913,0.01245918,0.0027241285,0.0019642317,0.32109353,0.121993214,0.027911345],"genre_scores_gemma":[0.042112704,0.015527843,0.4002244,0.00092965795,0.00023733004,0.00059468014,0.45998138,0.0054853586,0.074906625],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99801195,0.00013227068,0.00016798356,0.00020894271,0.0013050454,0.00017383388],"domain_scores_gemma":[0.99591535,0.0008315951,0.00014868018,0.00057177374,0.0021027862,0.00042977746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029954023,0.0016455874,0.002581755,0.0063746334,0.0018089603,0.0053836433,0.002682071,0.0011666969,0.0057521197],"category_scores_gemma":[0.0069579943,0.0022278235,0.0017021518,0.007858934,0.00080795726,0.00302017,0.0017428825,0.0023472782,0.008159937],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027958438,0.0003015669,0.008153217,0.0009298496,0.00016651058,0.00029026362,0.00027188522,0.0032652917,0.004099184,0.003073651,0.54462737,0.4345416],"study_design_scores_gemma":[0.0003070988,0.0001577848,0.055155616,0.0010138093,0.0005178723,0.0016809998,0.0008620079,0.12551533,0.047542628,0.01845122,0.7485161,0.00027953292],"about_ca_topic_score_codex":0.28834808,"about_ca_topic_score_gemma":0.47702768,"teacher_disagreement_score":0.7116519,"about_ca_system_score_codex":0.003499993,"about_ca_system_score_gemma":0.015645895,"threshold_uncertainty_score":0.5733394},"labels":[],"label_agreement":null},{"id":"W2293418991","doi":"","title":"Mining Disorder Attributes with Rules and Statistical Learning","year":2014,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Artificial intelligence; Statistical learning","score_opus":0.00998987170509182,"score_gpt":0.23214832927879456,"score_spread":0.22215845757370273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2293418991","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19833967,0.0035944672,0.74714476,0.005008152,0.00091340067,0.001993694,0.025821887,0.008807857,0.008376091],"genre_scores_gemma":[0.4332896,0.00080307294,0.5198621,0.0010790514,0.00048639788,0.00075209443,0.04042453,0.0003498368,0.0029533547],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99166673,0.0025493328,0.00096405577,0.0019130565,0.0024061217,0.0005006132],"domain_scores_gemma":[0.97127825,0.019498698,0.0016938073,0.003560139,0.003174499,0.00079461385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006030314,0.0014081689,0.0023941705,0.009227828,0.0020886918,0.005040689,0.002456392,0.0022524323,0.003389442],"category_scores_gemma":[0.030116506,0.00061033544,0.0021733223,0.007002714,0.0014467252,0.0041611767,0.0021358065,0.0029689851,0.002149073],"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":[0.001175241,0.0018262309,0.08868341,0.0014481071,0.000668176,0.00215376,0.00046874394,0.0692468,0.010332011,0.025535349,0.10662554,0.6918367],"study_design_scores_gemma":[0.00019682442,0.00024053993,0.011752846,0.00023407162,0.00023783234,0.0011346079,0.0005734572,0.84262025,0.01420846,0.10654945,0.0221484,0.000103283295],"about_ca_topic_score_codex":0.0076491814,"about_ca_topic_score_gemma":0.009535586,"teacher_disagreement_score":0.009227828,"about_ca_system_score_codex":0.001569445,"about_ca_system_score_gemma":0.0029418182,"threshold_uncertainty_score":0.031891763},"labels":[],"label_agreement":null},{"id":"W2293843830","doi":"10.1007/978-3-662-47804-2_6","title":"Mining Popular Patterns: A Novel Mining Problem and Its Application to Static Transactional Databases and Dynamic Data Streams","year":2015,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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 Manitoba","funders":"","keywords":"Computer science; Popularity; Data stream mining; Data mining; Transactional leadership; STREAMS; Tree (set theory); Database; Mathematics","score_opus":0.05328995517311378,"score_gpt":0.30167461196281686,"score_spread":0.2483846567897031,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2293843830","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04446996,0.0026264188,0.9454902,0.0029509095,0.00027619713,0.00016548636,0.0011820615,0.000593548,0.0022451296],"genre_scores_gemma":[0.28107524,0.00458185,0.70203507,0.000540936,0.001621535,0.00028275204,0.0023480156,0.00023251784,0.0072820936],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99711335,0.00035647344,0.00035610053,0.0009215824,0.0011092378,0.00014323977],"domain_scores_gemma":[0.9896824,0.005963896,0.0011077748,0.0010318111,0.001756105,0.0004579468],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00287336,0.0012709057,0.0019778975,0.00446539,0.001618538,0.004683827,0.0033409854,0.0030553988,0.0015773718],"category_scores_gemma":[0.016969783,0.0009961121,0.0018557318,0.011634857,0.0016507108,0.010060215,0.00286821,0.0029584316,0.00083891413],"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":[0.0004968775,0.0006178382,0.031954262,0.0011147974,0.00032805098,0.002203093,0.0010183011,0.04461756,0.007925815,0.120024726,0.026053555,0.7636451],"study_design_scores_gemma":[0.000045616947,0.00014893156,0.0034777,0.00009402326,0.00014793825,0.003389261,0.0006118172,0.78756523,0.0044213193,0.18881561,0.011218185,0.00006422012],"about_ca_topic_score_codex":0.0014123772,"about_ca_topic_score_gemma":0.001833751,"teacher_disagreement_score":0.004683827,"about_ca_system_score_codex":0.0007772208,"about_ca_system_score_gemma":0.0010668031,"threshold_uncertainty_score":0.015195966},"labels":[],"label_agreement":null},{"id":"W2294975522","doi":"","title":"Mining of Diverse Social Entities from Linked Data","year":2014,"lang":"en","type":"article","venue":"Mspace (University of Manitoba)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Popularity; Computer science; Scalability; World Wide Web; Social network (sociolinguistics); Tree (set theory); Social web; Space (punctuation); Semantic Web; Linked data; Social Semantic Web; Web mining; Data science; Data mining; Social media; Web service; Database; Mathematics","score_opus":0.04476484864301485,"score_gpt":0.22697804567810614,"score_spread":0.18221319703509128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2294975522","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.258464,0.0017563247,0.711917,0.0016750793,0.000122823,0.0008574038,0.017742835,0.001997985,0.00546664],"genre_scores_gemma":[0.45929044,0.0008108575,0.50645316,0.000217225,0.00010862695,0.0005895408,0.030463737,0.0001161949,0.001950241],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965796,0.0008299072,0.0002946129,0.0007317465,0.001340286,0.00022375699],"domain_scores_gemma":[0.9928671,0.0034772912,0.0010928726,0.0010121593,0.0012072116,0.0003433104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00230665,0.0012224668,0.0010783975,0.0114363525,0.0021898106,0.0020826904,0.0022611034,0.0019515333,0.0008774775],"category_scores_gemma":[0.014148896,0.00059230445,0.0017389238,0.009903424,0.00065313233,0.003443557,0.0030423182,0.0012093973,0.0006512512],"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":[0.00049252505,0.0009914084,0.17754112,0.001234326,0.0012716587,0.005691092,0.004209716,0.13102424,0.013938652,0.049456738,0.030149786,0.5839988],"study_design_scores_gemma":[0.00006166625,0.000096234784,0.017785328,0.00015630908,0.00018400383,0.0015356139,0.0023101019,0.8520599,0.008641067,0.089275196,0.02782663,0.00006795338],"about_ca_topic_score_codex":0.004094176,"about_ca_topic_score_gemma":0.011302265,"teacher_disagreement_score":0.0114363525,"about_ca_system_score_codex":0.0007881134,"about_ca_system_score_gemma":0.001169029,"threshold_uncertainty_score":0.012198925},"labels":[],"label_agreement":null},{"id":"W2298379010","doi":"10.4271/2004-01-2187","title":"Exploring Anthropometric Data through Cluster Analysis","year":2004,"lang":"en","type":"article","venue":"SAE technical papers on CD-ROM/SAE technical paper series","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"","keywords":"Cluster (spacecraft); Computer science; Anthropometry; Geography; Computer network","score_opus":0.08706087982339585,"score_gpt":0.31193591648756397,"score_spread":0.22487503666416814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2298379010","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041435163,0.00032847805,0.94453216,0.0005714304,0.00007670998,0.00031382742,0.0022081563,0.003843076,0.006690974],"genre_scores_gemma":[0.18536457,0.0005342481,0.8039569,0.00009946171,0.00008162614,0.00040028105,0.0049862284,0.0005070876,0.004069529],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984201,0.00037452872,0.0000900287,0.00038556242,0.00062299985,0.0001068946],"domain_scores_gemma":[0.9971762,0.0014816476,0.00021751471,0.00031285043,0.0007210582,0.00009075564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017156891,0.00086509815,0.0006994655,0.007401017,0.00088302564,0.0026140073,0.0011709081,0.0005370785,0.0055015725],"category_scores_gemma":[0.0060353954,0.0003773565,0.001051047,0.0067319586,0.00062496064,0.0016080398,0.0019191235,0.00084375835,0.0021290379],"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":[0.00031497818,0.00029218613,0.027131598,0.00046711433,0.00027550652,0.00044326117,0.0028995061,0.07794747,0.015597995,0.023685882,0.02353269,0.8274117],"study_design_scores_gemma":[0.000046501948,0.00018291455,0.048622094,0.000239696,0.0001561954,0.00046359614,0.005112581,0.80973566,0.014380733,0.06685277,0.05400487,0.00020239188],"about_ca_topic_score_codex":0.008298258,"about_ca_topic_score_gemma":0.0074212286,"teacher_disagreement_score":0.008298258,"about_ca_system_score_codex":0.00078651647,"about_ca_system_score_gemma":0.0011666557,"threshold_uncertainty_score":0.018404603},"labels":[],"label_agreement":null},{"id":"W2318457171","doi":"10.1142/9789812819079_0009","title":"AN ONLINE FREQUENCY RATE BASED ALGORITHM FOR MINING FREQUENT SEQUENCES IN EVOLVING DATA STREAMS","year":2008,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Data stream mining; Computer science; STREAMS; Data mining; Algorithm; Data stream; Telecommunications; Computer network","score_opus":0.10401167032837075,"score_gpt":0.32242209896248375,"score_spread":0.218410428634113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2318457171","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025156986,0.0001864274,0.97345316,0.00008020398,0.000027289254,0.00010821257,0.00008466068,0.0006087563,0.00029428944],"genre_scores_gemma":[0.14000922,0.00010932769,0.8585994,0.0000631797,0.000047392936,0.0002279963,0.0003016867,0.0000415741,0.00060011185],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981824,0.00038886126,0.00020929173,0.00042645153,0.00067841896,0.00011459221],"domain_scores_gemma":[0.9940474,0.003719705,0.00071402057,0.00047402424,0.0008921461,0.00015262893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029071968,0.00069145416,0.0013610766,0.002748725,0.00061532756,0.0010119423,0.002103417,0.0011132064,0.0012270543],"category_scores_gemma":[0.0101044,0.00041034343,0.0006856557,0.0022178139,0.0005553452,0.0018185516,0.0009074217,0.00090508646,0.00051246665],"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":[0.00063834555,0.0004278503,0.00812522,0.00021063996,0.00014914064,0.00025625972,0.00025424053,0.14043562,0.016662765,0.008502346,0.002320898,0.82201654],"study_design_scores_gemma":[0.000041817166,0.00011730466,0.00066232466,0.000010982115,0.00001877209,0.00029229207,0.000022713713,0.99035317,0.003950349,0.0034588892,0.0010564917,0.000015025652],"about_ca_topic_score_codex":0.0016968577,"about_ca_topic_score_gemma":0.0018796078,"teacher_disagreement_score":0.0029071968,"about_ca_system_score_codex":0.0005642239,"about_ca_system_score_gemma":0.001399545,"threshold_uncertainty_score":0.0153749585},"labels":[],"label_agreement":null},{"id":"W2321318280","doi":"10.4310/sii.2011.v4.n1.a2","title":"Detection of rare items with TARGET","year":2011,"lang":"en","type":"article","venue":"Statistics and Its Interface","topic":"Data Mining Algorithms and Applications","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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Decision tree; Rank (graph theory); Artificial intelligence; Machine learning; Data mining; Tree (set theory); Pattern recognition (psychology); Mathematics","score_opus":0.021117910520857396,"score_gpt":0.2449981576040288,"score_spread":0.2238802470831714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2321318280","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23140115,0.0011019412,0.7615747,0.000779201,0.00020260445,0.00021173638,0.00066059025,0.0014747122,0.0025934272],"genre_scores_gemma":[0.6433177,0.00041527997,0.35062656,0.00046450287,0.00019364119,0.00018385581,0.0016947965,0.00016337355,0.0029402585],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9947023,0.00094904326,0.00047684813,0.0014611479,0.0021028114,0.0003079027],"domain_scores_gemma":[0.96651214,0.020333834,0.0037507222,0.0046852874,0.0040209913,0.0006971723],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0067108395,0.000968218,0.002571504,0.0048208167,0.0012441978,0.0036084687,0.003013237,0.0033157854,0.0015063644],"category_scores_gemma":[0.036250588,0.0005438837,0.0014191422,0.0044990974,0.0011137951,0.00504772,0.0021554467,0.002356246,0.0017102837],"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":[0.0017956637,0.00085258926,0.15982237,0.0006379536,0.00067575095,0.0033939139,0.0010334902,0.10721677,0.025069827,0.028014,0.011973358,0.6595143],"study_design_scores_gemma":[0.00006867779,0.00044470205,0.021988839,0.00010146707,0.0002493657,0.0040859515,0.0003587891,0.87788415,0.030803084,0.057179056,0.0067037186,0.000132214],"about_ca_topic_score_codex":0.0014563189,"about_ca_topic_score_gemma":0.0010267128,"teacher_disagreement_score":0.0067108395,"about_ca_system_score_codex":0.0007546487,"about_ca_system_score_gemma":0.00078646746,"threshold_uncertainty_score":0.03549075},"labels":[],"label_agreement":null},{"id":"W2337987574","doi":"10.1007/978-3-319-23528-8_45","title":"Erratum to: Scalable Metric Learning for Co-Embedding","year":2015,"lang":"en","type":"erratum","venue":"Lecture notes in computer science","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":"University of Alberta","funders":"","keywords":"Computer science; Embedding; Scalability; Metric (unit); Theoretical computer science; Artificial intelligence; Database; Engineering","score_opus":0.02565422652218614,"score_gpt":0.3180452750199855,"score_spread":0.29239104849779934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2337987574","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005380015,0.0015018687,0.011781605,0.064278394,0.9095637,0.00005399284,0.0027854564,0.0016696593,0.007827327],"genre_scores_gemma":[0.04261516,0.010999171,0.07845889,0.098732546,0.25361004,0.00051315525,0.029027956,0.0069074556,0.47913563],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948526,0.00061932264,0.0007896661,0.0007311109,0.0027327049,0.00027469906],"domain_scores_gemma":[0.97612894,0.0043020383,0.000925485,0.0026951202,0.01507957,0.00086894643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026968943,0.002182139,0.0020268972,0.0032163083,0.0036566171,0.0035520466,0.0032400077,0.0049281497,0.084054045],"category_scores_gemma":[0.05511467,0.0009301915,0.0011266673,0.0034913318,0.0022289783,0.0041705393,0.0028352018,0.0058183735,0.051615536],"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":[0.00003318435,0.000007876009,0.000050438794,0.000052199346,0.00000629677,0.00006656416,0.000009109185,0.000101118334,0.00008925202,0.0013601361,0.9886199,0.009603998],"study_design_scores_gemma":[0.00006560456,0.000082369705,0.00073899515,0.000310323,0.000045073404,0.000773795,0.0001511191,0.0032756673,0.001714242,0.014702386,0.9780424,0.00009805732],"about_ca_topic_score_codex":0.008051268,"about_ca_topic_score_gemma":0.013033346,"teacher_disagreement_score":0.084054045,"about_ca_system_score_codex":0.0031268825,"about_ca_system_score_gemma":0.0040411013,"threshold_uncertainty_score":0.28118885},"labels":[],"label_agreement":null},{"id":"W2339142581","doi":"10.1007/978-3-031-01749-0","title":"Analyzing Analytics","year":2014,"lang":"en","type":"book","venue":"Synthesis lectures on computer architecture","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada)","funders":"","keywords":"Computer science; Implementation; Data science; Key (lock); Analytics; Data analysis; Focus (optics); Big data; Data mining; Software engineering","score_opus":0.011588165207169607,"score_gpt":0.2278197466445634,"score_spread":0.2162315814373938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2339142581","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012677688,0.025456384,0.74533916,0.018787207,0.0024339221,0.0008974165,0.020664982,0.013136765,0.16060647],"genre_scores_gemma":[0.22652581,0.03835658,0.5868532,0.0056326934,0.003649766,0.0012164396,0.061283264,0.0031631445,0.07331919],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960622,0.00078515237,0.00028489917,0.000731563,0.0018976125,0.0002386031],"domain_scores_gemma":[0.994601,0.0018302514,0.00032168505,0.0014439394,0.0016293495,0.00017386409],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035389352,0.0019258702,0.00091657427,0.0047026756,0.00084380014,0.00713833,0.00201872,0.0011098213,0.022987166],"category_scores_gemma":[0.013377284,0.0005170792,0.0012673537,0.005173026,0.0009887146,0.007241445,0.0032321527,0.0019647465,0.015746374],"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":[0.00012403044,0.000092761176,0.0060282154,0.0013926463,0.00024053329,0.00022833973,0.0004791342,0.014156844,0.0026911877,0.2823016,0.19702664,0.49523807],"study_design_scores_gemma":[0.000020795618,0.0000632367,0.0020241719,0.00063832884,0.00007576696,0.00031323262,0.0006145678,0.053042557,0.0034853767,0.42810088,0.5115676,0.000053488227],"about_ca_topic_score_codex":0.0016683819,"about_ca_topic_score_gemma":0.0013312871,"teacher_disagreement_score":0.022987166,"about_ca_system_score_codex":0.0013395816,"about_ca_system_score_gemma":0.0018688998,"threshold_uncertainty_score":0.07689971},"labels":[],"label_agreement":null},{"id":"W2341381658","doi":"10.1073/pnas.1604553113","title":"Boosting association rule mining in large datasets via Gibbs sampling","year":2016,"lang":"en","type":"article","venue":"Proceedings of the National Academy of Sciences","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Department of Health and Aged Care, Australian Government; National Health and Medical Research Council; Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Association rule learning; Data mining; Computer science; Boosting (machine learning); Markov chain; Apriori algorithm; Database transaction; A priori and a posteriori; Machine learning","score_opus":0.04792729368646059,"score_gpt":0.32246785625118507,"score_spread":0.2745405625647245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2341381658","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03703285,0.0002878845,0.9610627,0.00026601262,0.00002904673,0.00009868087,0.000060305614,0.0006131377,0.00054939504],"genre_scores_gemma":[0.40871474,0.0004092274,0.5883242,0.00042447692,0.00014677465,0.00046509498,0.00060919975,0.00012594955,0.000780367],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99602085,0.0021772454,0.00021253608,0.00055790815,0.00086375495,0.0001676708],"domain_scores_gemma":[0.97735256,0.01859822,0.000576044,0.0017825698,0.0013931416,0.000297579],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011697342,0.00089345797,0.0028175348,0.0020078726,0.0009473162,0.0013899688,0.002332255,0.0011789623,0.001149875],"category_scores_gemma":[0.024768863,0.0010425196,0.0016889313,0.0023359125,0.0015806804,0.0025370317,0.0023784835,0.002287972,0.0005974316],"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":[0.00035872826,0.0003994024,0.010400421,0.0002618502,0.00036896067,0.00027042022,0.00030153035,0.74828285,0.0048720506,0.041681156,0.002492137,0.19031039],"study_design_scores_gemma":[0.000026210093,0.00003795803,0.00028861733,0.0000069998605,0.00001979255,0.000035281104,0.00000962614,0.9835834,0.00057874474,0.015100139,0.00030615434,0.0000070263727],"about_ca_topic_score_codex":0.002034238,"about_ca_topic_score_gemma":0.0035842396,"teacher_disagreement_score":0.011697342,"about_ca_system_score_codex":0.00067718455,"about_ca_system_score_gemma":0.0015925666,"threshold_uncertainty_score":0.06186217},"labels":[],"label_agreement":null},{"id":"W2343814825","doi":"10.1109/tla.2016.7459622","title":"Automatic algorithm to classify and locate research papers using natural language","year":2016,"lang":"en","type":"article","venue":"IEEE Latin America Transactions","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Data mining; Upload; Natural language; Set (abstract data type); Statistical classification; Artificial intelligence; Knowledge base; Algorithm; Information retrieval; Machine learning; World Wide Web","score_opus":0.043277461621018726,"score_gpt":0.3328154659512365,"score_spread":0.2895380043302178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2343814825","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015948923,0.0006373567,0.9656282,0.00060741423,0.00010690362,0.0007950072,0.0029662293,0.009942914,0.0033670752],"genre_scores_gemma":[0.03395757,0.00017261514,0.95978475,0.00014825452,0.000038000475,0.00042849415,0.0037824772,0.0001223517,0.0015654626],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99669206,0.00054551515,0.00057288905,0.0009036962,0.0011380804,0.00014765144],"domain_scores_gemma":[0.9935695,0.0025637492,0.0008485713,0.0005377033,0.0023162758,0.00016426682],"candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.0027903707,0.0010087015,0.0010847155,0.013376944,0.0011969716,0.0037077197,0.0021955904,0.0013663605,0.0038897032],"category_scores_gemma":[0.010725889,0.00040668764,0.0014723928,0.006157146,0.00063936686,0.002946898,0.0016330493,0.0010284274,0.0039001945],"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":[0.00030238982,0.0004425002,0.0071418025,0.0011680507,0.00015008892,0.00046932165,0.0007868193,0.0050107334,0.034756843,0.016333405,0.01902707,0.91441107],"study_design_scores_gemma":[0.00033293976,0.00059131964,0.015260256,0.0007099545,0.00048190172,0.0039991424,0.0024959007,0.5827035,0.11881204,0.0891564,0.18513961,0.0003170807],"about_ca_topic_score_codex":0.0037884344,"about_ca_topic_score_gemma":0.0050875526,"teacher_disagreement_score":0.98662305,"about_ca_system_score_codex":0.0012847467,"about_ca_system_score_gemma":0.004189288,"threshold_uncertainty_score":0.014757097},"labels":[],"label_agreement":null},{"id":"W2351383156","doi":"","title":"Research on Algorithm of Data Preprocessing in Web Usage Mining","year":2007,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Preprocessor; Association rule learning; Data mining; Data pre-processing; Identification (biology); Database transaction; Web mining; Path (computing); Transaction data; Artificial intelligence; Database; Web page; World Wide Web","score_opus":0.11384912889912065,"score_gpt":0.41279690675004665,"score_spread":0.298947777850926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2351383156","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050794873,0.0010453039,0.9912747,0.00026644766,0.000083972875,0.00012562497,0.00014115885,0.0011235704,0.00085965014],"genre_scores_gemma":[0.058921482,0.002126268,0.93491334,0.00019169218,0.00017325328,0.00047929242,0.0011229727,0.00016317448,0.0019085573],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963862,0.0008775471,0.0004376742,0.00097131904,0.0011629596,0.00016434897],"domain_scores_gemma":[0.9945068,0.00300384,0.00028014628,0.0005927875,0.0015191794,0.00009727278],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028616742,0.0010703334,0.0015761468,0.004252176,0.0012226502,0.002843429,0.002620647,0.0012562476,0.002644617],"category_scores_gemma":[0.011653407,0.00069415226,0.0015718117,0.0074633374,0.00085221615,0.004370911,0.0010738304,0.0023206507,0.0016891429],"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":[0.00018419523,0.0001525236,0.005014235,0.00048487826,0.00014046243,0.00012353882,0.00028054052,0.03101788,0.005335803,0.024293179,0.0050780126,0.9278947],"study_design_scores_gemma":[0.00012271288,0.00017895871,0.004114328,0.00019601514,0.00014270567,0.0009040444,0.00028487117,0.8735846,0.029918395,0.06087295,0.029575123,0.000105257284],"about_ca_topic_score_codex":0.0040663434,"about_ca_topic_score_gemma":0.001937875,"teacher_disagreement_score":0.004252176,"about_ca_system_score_codex":0.0012250107,"about_ca_system_score_gemma":0.002344003,"threshold_uncertainty_score":0.015134156},"labels":[],"label_agreement":null},{"id":"W2351532812","doi":"","title":"Application and Research of Decision Tree Algorithm in Protein Structure Prediction","year":2009,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Decision tree; ID3 algorithm; Pruning; Incremental decision tree; Decision tree learning; Algorithm; Alternating decision tree; Machine learning; Data mining; Artificial intelligence; Protein structure prediction; Decision tree model; Tree structure; Protein structure; Binary tree","score_opus":0.014125121448497707,"score_gpt":0.30105783670473735,"score_spread":0.28693271525623965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2351532812","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021349069,0.006717934,0.9672248,0.00058516057,0.0002966738,0.000078510864,0.000111156485,0.0006420746,0.0029947094],"genre_scores_gemma":[0.29083753,0.009769232,0.695457,0.00033738354,0.00039876823,0.00013957058,0.0006678649,0.00017424343,0.0022183685],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968065,0.0010947447,0.00021303218,0.00046314814,0.0012778615,0.00014467555],"domain_scores_gemma":[0.9949818,0.0031827542,0.00016703027,0.00023888361,0.0012925804,0.0001368858],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003533958,0.0008122091,0.0014055436,0.0027508016,0.0007618386,0.0013435199,0.0015477143,0.0011859993,0.0016448692],"category_scores_gemma":[0.009221011,0.0003824559,0.0009926104,0.004057574,0.00076940877,0.0025948319,0.0006063909,0.0015211934,0.0007656647],"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":[0.00033010982,0.00028522647,0.005958237,0.0007338167,0.00024984695,0.00038286,0.00023757677,0.15166256,0.008890393,0.037959374,0.006385943,0.7869241],"study_design_scores_gemma":[0.00006126479,0.00019693366,0.001656605,0.00011014262,0.00010010282,0.00038161263,0.00007429148,0.93918985,0.009333013,0.03693,0.011909053,0.00005716473],"about_ca_topic_score_codex":0.003272987,"about_ca_topic_score_gemma":0.0013108879,"teacher_disagreement_score":0.003533958,"about_ca_system_score_codex":0.000634546,"about_ca_system_score_gemma":0.0011626984,"threshold_uncertainty_score":0.018689573},"labels":[],"label_agreement":null},{"id":"W2351981297","doi":"","title":"Research on Association Analysis Algorithm of Strategic Performance Based on FP-Growth","year":2011,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Association rule learning; Computer science; Process (computing); Data mining; Constraint (computer-aided design); Algorithm; Set (abstract data type); Quality (philosophy); Clipping (morphology); Mathematics","score_opus":0.0871039844103607,"score_gpt":0.31360475934397186,"score_spread":0.22650077493361115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2351981297","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01326204,0.0005441679,0.9829624,0.00036159746,0.00008095966,0.00008404691,0.00011999561,0.0006716924,0.0019131388],"genre_scores_gemma":[0.3020672,0.0014202367,0.6925534,0.0001677838,0.00017730935,0.00043213784,0.00093656266,0.00017371528,0.0020717015],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954419,0.001274406,0.00037680208,0.0007985272,0.0017869632,0.00032137113],"domain_scores_gemma":[0.9840956,0.0099025145,0.00079971255,0.00075843505,0.0042511323,0.00019262324],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006919244,0.0015448137,0.0018926268,0.004901748,0.0011967722,0.0030581786,0.0026940447,0.001255231,0.001511317],"category_scores_gemma":[0.022793097,0.0005317762,0.0015709387,0.006567627,0.0012759824,0.004578617,0.0012665892,0.002639434,0.0008555557],"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":[0.00026707505,0.0001894647,0.013163968,0.0003694289,0.00029686358,0.00037693267,0.0004047479,0.33395213,0.0033087295,0.06429326,0.0063069914,0.5770704],"study_design_scores_gemma":[0.000019023257,0.00004166334,0.0007056279,0.00002319642,0.000038375045,0.00018082671,0.000049223476,0.97634524,0.0019223954,0.018765336,0.0018860536,0.000023175944],"about_ca_topic_score_codex":0.008024153,"about_ca_topic_score_gemma":0.0026501694,"teacher_disagreement_score":0.008024153,"about_ca_system_score_codex":0.0019164754,"about_ca_system_score_gemma":0.0029287557,"threshold_uncertainty_score":0.0365929},"labels":[],"label_agreement":null},{"id":"W2356803596","doi":"","title":"Application of Data Warehouse in Commercial Banks","year":2008,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Data warehouse; Computer science; Dimensional modeling; Data transformation; Process (computing); Data flow diagram; Competition (biology); Credit card; Architecture; Warehouse; Database; Data science; World Wide Web; Business; Marketing","score_opus":0.04650231801150504,"score_gpt":0.2897995692173535,"score_spread":0.24329725120584847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2356803596","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11680689,0.0019510649,0.8427617,0.004229645,0.00031185048,0.00059942796,0.0022709025,0.008720544,0.022348002],"genre_scores_gemma":[0.40026712,0.0030484367,0.5900956,0.00047188214,0.00009276583,0.00025957392,0.0023575192,0.00030178876,0.0031053363],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99761766,0.0010658164,0.000328565,0.00029924687,0.00060341874,0.00008528844],"domain_scores_gemma":[0.99715626,0.0011022359,0.00011242484,0.00070671097,0.00078327226,0.0001390896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003433449,0.000433473,0.00042190836,0.0016363965,0.0008903412,0.003231177,0.001098606,0.0010051928,0.0013837242],"category_scores_gemma":[0.0051018414,0.00063240953,0.0006294382,0.004168142,0.0004871742,0.0027895467,0.001252993,0.00091492094,0.0007317223],"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":[0.00092910964,0.0007939536,0.024640292,0.0015319728,0.00031840647,0.0034449412,0.005212069,0.0672479,0.035666063,0.10895224,0.03749683,0.7137663],"study_design_scores_gemma":[0.00021822451,0.00031817865,0.007924607,0.00049256906,0.00021374076,0.0020963815,0.003348513,0.5820784,0.089157745,0.05721286,0.2567132,0.00022560112],"about_ca_topic_score_codex":0.0033945676,"about_ca_topic_score_gemma":0.0018449515,"teacher_disagreement_score":0.003433449,"about_ca_system_score_codex":0.0009526917,"about_ca_system_score_gemma":0.0012736293,"threshold_uncertainty_score":0.018158019},"labels":[],"label_agreement":null},{"id":"W2357768964","doi":"","title":"Improvement of Association Rules Mining Aigorithm Based on Vector","year":2009,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Association rule learning; Computer science; Data mining; Apriori algorithm; A priori and a posteriori; Association (psychology); Tree (set theory); Support vector machine; Decision tree; Algorithm; Artificial intelligence; Mathematics","score_opus":0.007085379387496552,"score_gpt":0.23463353759885977,"score_spread":0.2275481582113632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2357768964","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012295966,0.00085729803,0.9834626,0.0001701077,0.00009691991,0.000091655485,0.00012474481,0.001963159,0.00093766325],"genre_scores_gemma":[0.09077372,0.0010646263,0.9051758,0.00014708306,0.000114841765,0.00017690969,0.00071547163,0.000109711924,0.0017217388],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99601513,0.0010195876,0.00045023847,0.00069103786,0.0016978377,0.00012623343],"domain_scores_gemma":[0.99547595,0.001795232,0.00031465935,0.00047132518,0.0018677557,0.00007501786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030344042,0.00088547834,0.0012674484,0.0040057935,0.00070502044,0.0018949828,0.0015006391,0.0006257545,0.0017263867],"category_scores_gemma":[0.0075353314,0.0004381738,0.0010152188,0.004722897,0.000549645,0.0028691685,0.0010600772,0.001219274,0.0013877677],"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":[0.00019494345,0.00020603745,0.004207383,0.000290198,0.00021119059,0.00012222318,0.00020400832,0.017682664,0.009675265,0.012575729,0.0037440357,0.9508864],"study_design_scores_gemma":[0.00021446934,0.00085492653,0.0035724635,0.000101015925,0.00032584154,0.001241563,0.00026381464,0.90704817,0.031654984,0.029861197,0.024732813,0.00012873151],"about_ca_topic_score_codex":0.0020679317,"about_ca_topic_score_gemma":0.0014650542,"teacher_disagreement_score":0.0040057935,"about_ca_system_score_codex":0.0004370454,"about_ca_system_score_gemma":0.0014356839,"threshold_uncertainty_score":0.016047597},"labels":[],"label_agreement":null},{"id":"W2359652666","doi":"","title":"Building knowledge around complex objects using InforBright Data Warehousing technology","year":2010,"lang":"en","type":"article","venue":"eSpace (Curtin University)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Laurentian University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data warehouse; Interpretation (philosophy); Data science; Set (abstract data type); Word (group theory); Subject (documents); Data set; Information retrieval; Data mining; Artificial intelligence; World Wide Web","score_opus":0.05150079252232033,"score_gpt":0.29388989632122287,"score_spread":0.24238910379890255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2359652666","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017769424,0.0008143346,0.96050096,0.0013934288,0.000065643784,0.00030333846,0.002662509,0.003374728,0.013115719],"genre_scores_gemma":[0.09236148,0.0017035925,0.89867646,0.00027084103,0.000044775177,0.00017314544,0.004468321,0.00018979871,0.0021116198],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982495,0.00021223199,0.00025710333,0.00040857063,0.00077236,0.00010019996],"domain_scores_gemma":[0.99495333,0.0016776959,0.00042250074,0.0021439474,0.0006698212,0.00013272918],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018980769,0.0008470535,0.00089913886,0.0076744766,0.0017316722,0.0070698382,0.0017328416,0.00092256686,0.0040972005],"category_scores_gemma":[0.0072069042,0.0008180345,0.0023435648,0.0065068766,0.002137185,0.010011813,0.0040177205,0.0020344655,0.0021137986],"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":[0.000117251555,0.00019074506,0.0043966696,0.0017506498,0.00024795183,0.0018757117,0.005313508,0.034098126,0.011698528,0.106102385,0.012779739,0.82142884],"study_design_scores_gemma":[0.00005783387,0.00020318216,0.00834689,0.0016733374,0.0004285092,0.0020879668,0.0045989817,0.1449562,0.042279568,0.50284916,0.2922118,0.0003064931],"about_ca_topic_score_codex":0.009126371,"about_ca_topic_score_gemma":0.010968931,"teacher_disagreement_score":0.009126371,"about_ca_system_score_codex":0.0011453223,"about_ca_system_score_gemma":0.0026259944,"threshold_uncertainty_score":0.018146515},"labels":[],"label_agreement":null},{"id":"W2359728397","doi":"","title":"A Data Mining Algorithm Based on Calculating Multi Segment Support","year":2001,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CAE (Canada)","funders":"","keywords":"Apriori algorithm; Computer science; Data mining; Identifier; Association rule learning; Set (abstract data type); Database transaction; Algorithm; Scale (ratio); A priori and a posteriori; Data set; GSP Algorithm; Database; Artificial intelligence","score_opus":0.08619273370157411,"score_gpt":0.3274819538178026,"score_spread":0.2412892201162285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2359728397","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019985266,0.00097625627,0.9721133,0.0002939867,0.00022102593,0.00040518353,0.00071301864,0.0024709683,0.0028209796],"genre_scores_gemma":[0.12317898,0.0006550033,0.8697477,0.00017931173,0.00017751784,0.00052955205,0.0019450141,0.00012434273,0.003462561],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979893,0.00022259622,0.00025267224,0.0005492509,0.0008730942,0.000113104026],"domain_scores_gemma":[0.9986364,0.0004539474,0.00016417736,0.00012907239,0.0005591266,0.0000572539],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011433357,0.0011603052,0.0015178055,0.0057391915,0.0013160808,0.0019281611,0.0020933563,0.0015788843,0.0028835586],"category_scores_gemma":[0.004213405,0.0005830353,0.0013269162,0.0065871472,0.0005021943,0.0027612112,0.0011309728,0.0011944511,0.0017633615],"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":[0.0005050385,0.00019547807,0.005317115,0.00036217272,0.00021276918,0.00047018498,0.0002605665,0.033039402,0.014866551,0.010196897,0.008963827,0.92561007],"study_design_scores_gemma":[0.00016793775,0.0007066142,0.0039199768,0.00012757658,0.00019509603,0.0024424165,0.00021421509,0.87995416,0.039221574,0.019988002,0.052893236,0.00016923877],"about_ca_topic_score_codex":0.0017459929,"about_ca_topic_score_gemma":0.0010696964,"teacher_disagreement_score":0.0057391915,"about_ca_system_score_codex":0.0006270413,"about_ca_system_score_gemma":0.0009471614,"threshold_uncertainty_score":0.009646475},"labels":[],"label_agreement":null},{"id":"W2361606980","doi":"","title":"Discovery of Quantitative Profit Constraint Association Rules","year":2008,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Association rule learning; Computer science; Database transaction; Profit (economics); Transaction cost; Data mining; Constraint (computer-aided design); Transaction data; Operations research; Microeconomics; Database; Economics; Mathematics","score_opus":0.020936124472986792,"score_gpt":0.25934531406576056,"score_spread":0.23840918959277377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2361606980","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16080521,0.0005261367,0.83253604,0.00060890807,0.00006532492,0.0002477579,0.0006129612,0.0004475349,0.004150227],"genre_scores_gemma":[0.6190679,0.00039044916,0.3765742,0.00012963953,0.00008582094,0.00022723194,0.0016884867,0.000051205338,0.0017851134],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99457103,0.001160629,0.0004989866,0.0009519758,0.0024951354,0.0003222382],"domain_scores_gemma":[0.98780686,0.0075353333,0.001401505,0.00087906665,0.0020613677,0.00031586547],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003464044,0.000679116,0.0015677715,0.0030658906,0.00079493,0.0028138875,0.0014970496,0.0007566019,0.0012410093],"category_scores_gemma":[0.019233277,0.00047881136,0.0010478821,0.0030391135,0.00075298676,0.0028792433,0.0016489767,0.0012765493,0.00034256914],"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":[0.00078316714,0.00063856755,0.055436727,0.000806754,0.00055035466,0.0027467655,0.00067774236,0.16052775,0.017019436,0.16596739,0.0069833654,0.5878619],"study_design_scores_gemma":[0.000061062536,0.00012394496,0.0043237065,0.000055629152,0.0001091158,0.00069773995,0.00024086761,0.8882245,0.008706011,0.09293727,0.0044738264,0.000046316003],"about_ca_topic_score_codex":0.00089891825,"about_ca_topic_score_gemma":0.0007586957,"teacher_disagreement_score":0.003464044,"about_ca_system_score_codex":0.0005904954,"about_ca_system_score_gemma":0.0016139684,"threshold_uncertainty_score":0.018319845},"labels":[],"label_agreement":null},{"id":"W2363371908","doi":"","title":"Application of Association Rules Mining in University Scholarship Evaluation","year":2010,"lang":"en","type":"article","venue":"Journal of Ningxia Teachers University","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Science North","funders":"","keywords":"Association rule learning; Scholarship; Apriori algorithm; Data mining; Association (psychology); Computer science; Data science; A priori and a posteriori; Political science; Psychology; Epistemology; Law","score_opus":0.018894813793372815,"score_gpt":0.2534188156183448,"score_spread":0.23452400182497196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2363371908","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46943733,0.0048902356,0.4954867,0.00228885,0.00042282973,0.0010323726,0.0014380646,0.0018208936,0.02318273],"genre_scores_gemma":[0.8691643,0.00097142195,0.12668435,0.00010177113,0.00012933623,0.00019179075,0.0006808852,0.000037704158,0.002038459],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98678327,0.0059232065,0.0012675036,0.0009803218,0.004664253,0.00038141507],"domain_scores_gemma":[0.9846042,0.008247704,0.00126201,0.0008797349,0.0045088995,0.0004974673],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007798864,0.0005481884,0.0011039323,0.00848619,0.0011900748,0.0028079506,0.0011319525,0.00085068116,0.0015377882],"category_scores_gemma":[0.024891995,0.0002661907,0.00071664306,0.006822381,0.0005245426,0.0021370954,0.0011381333,0.00089019793,0.000755433],"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":[0.00037934622,0.00063428347,0.08912802,0.0003694514,0.00028998184,0.00046565142,0.0007031009,0.016203562,0.0026346918,0.0099858865,0.003904256,0.8753017],"study_design_scores_gemma":[0.0002670487,0.001826593,0.14017789,0.00070419983,0.0010039107,0.002199477,0.0042993315,0.6830221,0.040470425,0.072378926,0.053250182,0.00039998785],"about_ca_topic_score_codex":0.0027204433,"about_ca_topic_score_gemma":0.002888301,"teacher_disagreement_score":0.99220115,"about_ca_system_score_codex":0.0007747743,"about_ca_system_score_gemma":0.0018865796,"threshold_uncertainty_score":0.041244864},"labels":[],"label_agreement":null},{"id":"W2363708264","doi":"","title":"Research and Prospect on Technology of Maximum Frequent Itemsets Mining","year":2005,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Association rule learning; Pruning; Computer science; Data mining","score_opus":0.027688375221625552,"score_gpt":0.3187686448043096,"score_spread":0.29108026958268407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2363708264","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023890896,0.034832556,0.9206126,0.0031386896,0.00061224995,0.00013253329,0.00019417197,0.00055512146,0.016031293],"genre_scores_gemma":[0.25550258,0.06427985,0.66834337,0.0009672113,0.0018721471,0.0003496951,0.00085873215,0.00013812029,0.0076883812],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978661,0.0007162025,0.00015487858,0.00034725395,0.00081930414,0.00009628982],"domain_scores_gemma":[0.9953367,0.0030015227,0.00019891368,0.00040501493,0.000957955,0.00009988215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029098047,0.00065748225,0.00091747474,0.0029858695,0.0005944306,0.002124865,0.0016852667,0.0012090765,0.003402991],"category_scores_gemma":[0.008809377,0.0004376916,0.0008316058,0.005030294,0.00084891426,0.0053180237,0.00066554314,0.0011211685,0.0017258336],"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":[0.00024225349,0.0002104488,0.008979329,0.0013986469,0.00012623478,0.0007579365,0.00042270392,0.014807388,0.011208431,0.09173955,0.005992567,0.86411446],"study_design_scores_gemma":[0.00017525117,0.00082115975,0.008075561,0.0013925051,0.00035966406,0.0062854583,0.0011131756,0.3475801,0.057010047,0.36458302,0.21238673,0.00021731816],"about_ca_topic_score_codex":0.00039043112,"about_ca_topic_score_gemma":0.00030953065,"teacher_disagreement_score":0.003402991,"about_ca_system_score_codex":0.0005141253,"about_ca_system_score_gemma":0.0010066542,"threshold_uncertainty_score":0.015388727},"labels":[],"label_agreement":null},{"id":"W2368161388","doi":"","title":"Mining multivariate association patterns from spatiotemporal data","year":2011,"lang":"en","type":"article","venue":"Journal of Central South University(Science and Technology)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Multivariate statistics; Association rule learning; Data mining; Computer science; Association (psychology); Graph; Multivariate analysis; Artificial intelligence; Machine learning; Theoretical computer science","score_opus":0.03193781534655782,"score_gpt":0.21848597387178706,"score_spread":0.18654815852522924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2368161388","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08189157,0.00043010668,0.91329587,0.00038310117,0.000055712375,0.00016866012,0.0021460159,0.0007457277,0.0008832701],"genre_scores_gemma":[0.39063603,0.00058103434,0.60154444,0.000103527884,0.00008337148,0.00027455387,0.005960667,0.00007499323,0.00074141],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972337,0.0005538583,0.00043011538,0.0007703617,0.00083054346,0.00018154366],"domain_scores_gemma":[0.9921673,0.0044051027,0.0011811551,0.0008412042,0.0012039534,0.00020133321],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026655013,0.0007922624,0.0013343933,0.0062103528,0.0008205613,0.001691002,0.0013263153,0.0008577352,0.0010814588],"category_scores_gemma":[0.014007854,0.00045708928,0.0017459841,0.0073153363,0.0005063144,0.0030714455,0.0017906091,0.0012899418,0.00043949866],"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":[0.00051339064,0.00047947097,0.0874674,0.0008761657,0.0008883784,0.0023555327,0.0009932216,0.12560897,0.00922008,0.03391257,0.007398643,0.7302862],"study_design_scores_gemma":[0.00003964463,0.000115565126,0.010523177,0.000087177905,0.00017677744,0.0010219698,0.00057624676,0.894161,0.0051298933,0.08151786,0.006597387,0.00005328555],"about_ca_topic_score_codex":0.002386226,"about_ca_topic_score_gemma":0.0027520536,"teacher_disagreement_score":0.0062103528,"about_ca_system_score_codex":0.00044015853,"about_ca_system_score_gemma":0.0013442368,"threshold_uncertainty_score":0.014096677},"labels":[],"label_agreement":null},{"id":"W2370488791","doi":"","title":"Personalize Web Site System Based on Web Log Mining","year":2006,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Association rule learning; Web mining; Data mining; Apriori algorithm; Matching (statistics); Data Web; World Wide Web; Information retrieval; Web modeling; A priori and a posteriori; Web site; Web page; The Internet","score_opus":0.007868638903205832,"score_gpt":0.21690213180263032,"score_spread":0.2090334928994245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2370488791","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12873249,0.00026062957,0.8417332,0.00039309406,0.00008092861,0.0007386459,0.00048365135,0.020221148,0.0073561566],"genre_scores_gemma":[0.6445447,0.00023998033,0.34706426,0.00023224228,0.00007402189,0.000357207,0.0012988999,0.00027315365,0.005915596],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987785,0.00024804994,0.000077420074,0.0003061419,0.00051155617,0.00007836062],"domain_scores_gemma":[0.9984061,0.00043410278,0.00015283647,0.0005528076,0.00033984508,0.00011434691],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009688271,0.00046877653,0.00089087925,0.0020187488,0.00069588405,0.0012010438,0.0009817553,0.00060954655,0.00204435],"category_scores_gemma":[0.003280634,0.0003122176,0.0005516846,0.0011864468,0.00039326577,0.0022809608,0.0009797553,0.0007178573,0.0009915914],"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":[0.0005756647,0.0011407884,0.04379921,0.00028301685,0.00017355484,0.00059727085,0.0005898774,0.017908633,0.035434812,0.014150168,0.012940402,0.87240666],"study_design_scores_gemma":[0.00014050392,0.0005420038,0.023341883,0.00006369538,0.00026833054,0.0016873573,0.00030973586,0.8459653,0.07799333,0.024797905,0.024725024,0.00016496905],"about_ca_topic_score_codex":0.0013848144,"about_ca_topic_score_gemma":0.0016648148,"teacher_disagreement_score":0.00204435,"about_ca_system_score_codex":0.0003881821,"about_ca_system_score_gemma":0.0006224301,"threshold_uncertainty_score":0.006839037},"labels":[],"label_agreement":null},{"id":"W2371317906","doi":"","title":"Data Mining Technology Used in Course Selection System","year":2009,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Selection (genetic algorithm); Class (philosophy); Process (computing); Data mining; Course (navigation); Association rule learning; Data science; Machine learning; Artificial intelligence","score_opus":0.02112766052846293,"score_gpt":0.2863705431707589,"score_spread":0.26524288264229595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2371317906","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12568012,0.0028974977,0.734704,0.002416112,0.0012760228,0.004614884,0.039130732,0.0384045,0.05087615],"genre_scores_gemma":[0.4374319,0.0030215906,0.47016016,0.0010715254,0.0003864734,0.00372324,0.038723134,0.00096164434,0.04452028],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974452,0.0002809547,0.00041761805,0.00057337753,0.001114717,0.00016809275],"domain_scores_gemma":[0.99776375,0.00045855888,0.00017630034,0.0003027776,0.0011845893,0.000114117385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014467956,0.0006531196,0.00080211647,0.0043678554,0.001060503,0.0029422757,0.0011138879,0.0007906378,0.008741619],"category_scores_gemma":[0.0058350875,0.00039309319,0.00055575534,0.0053448984,0.00022722376,0.0017970112,0.00068902195,0.0008458924,0.008292108],"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":[0.00089741306,0.0006309816,0.034337133,0.0010638477,0.00018197621,0.0015901861,0.0006349317,0.008254016,0.031677067,0.011169764,0.08790184,0.8216609],"study_design_scores_gemma":[0.0003955224,0.0007042858,0.048283815,0.0005031364,0.00052661105,0.0035367575,0.0007884535,0.16429892,0.23089802,0.011988366,0.5377759,0.0003003039],"about_ca_topic_score_codex":0.0026691013,"about_ca_topic_score_gemma":0.0012502677,"teacher_disagreement_score":0.008741619,"about_ca_system_score_codex":0.00090873736,"about_ca_system_score_gemma":0.0013655104,"threshold_uncertainty_score":0.029243648},"labels":[],"label_agreement":null},{"id":"W2372754274","doi":"","title":"A Self-Adapted Algorithm for Mining Association Rules Based on Hash Pruning","year":2009,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Apriori algorithm; Computer science; Association rule learning; Hash function; Pruning; Data mining; Algorithm; GSP Algorithm; Set (abstract data type); A priori and a posteriori","score_opus":0.01015789984824826,"score_gpt":0.2455539591148124,"score_spread":0.23539605926656415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2372754274","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011471218,0.00038483785,0.9860291,0.000080942315,0.00008227407,0.00016850485,0.000120057564,0.00091918564,0.00074392464],"genre_scores_gemma":[0.06657844,0.00025293644,0.9307525,0.000118745,0.0000949682,0.0002475,0.00056011934,0.000078952464,0.0013158824],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975141,0.0006234323,0.00027480428,0.00041815705,0.0010913392,0.00007813658],"domain_scores_gemma":[0.9955739,0.002046829,0.00031576055,0.00086584635,0.0011044383,0.00009320334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026303814,0.00069365767,0.0012480589,0.003741549,0.000764316,0.0012604112,0.0020808964,0.0009478493,0.0021209386],"category_scores_gemma":[0.0076850066,0.0006039171,0.0011539377,0.0035418875,0.00069950515,0.0023169871,0.0015540133,0.000963256,0.0013089784],"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":[0.00027966232,0.00026111305,0.0076917144,0.00029120684,0.00039148217,0.00040558298,0.00030466687,0.029703107,0.017443325,0.015231848,0.0050832345,0.9229131],"study_design_scores_gemma":[0.00018917302,0.0006795129,0.004941417,0.00010130512,0.00033931268,0.0028753076,0.00016415774,0.9130014,0.022186311,0.03818293,0.017213218,0.00012600054],"about_ca_topic_score_codex":0.0006745539,"about_ca_topic_score_gemma":0.0010203657,"teacher_disagreement_score":0.003741549,"about_ca_system_score_codex":0.00030472223,"about_ca_system_score_gemma":0.00096578023,"threshold_uncertainty_score":0.013910949},"labels":[],"label_agreement":null},{"id":"W2374283405","doi":"","title":"Technology of Data Warehouse Applied in Data Analysis for China National Automatic Payment System","year":2007,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Payment; Computer science; Settlement (finance); Data warehouse; China; Payment system; Capital (architecture); Decision support system; Database; Data mining; Operations research; Data science; World Wide Web","score_opus":0.04020680671217939,"score_gpt":0.31491735912330426,"score_spread":0.27471055241112485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2374283405","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035171974,0.0012610364,0.95047027,0.0015810131,0.00021032953,0.00040444336,0.0013758754,0.0032104456,0.00631469],"genre_scores_gemma":[0.33277398,0.0026313523,0.65441424,0.00042063225,0.00015906351,0.0009415797,0.004062075,0.00019710851,0.0043999734],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971523,0.0006654243,0.00047673428,0.00051158195,0.0010356858,0.00015819899],"domain_scores_gemma":[0.99806947,0.00040482104,0.0001304764,0.00048379766,0.00083867833,0.00007275408],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034039095,0.0006036527,0.0007119166,0.0034140751,0.001194965,0.003717724,0.0013086194,0.0006856727,0.0017657545],"category_scores_gemma":[0.0045465734,0.0006320329,0.0010380667,0.005753077,0.0005993627,0.0040100515,0.0015328198,0.0012373733,0.00077268435],"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":[0.0003998782,0.0002517977,0.02542358,0.0010659605,0.000374248,0.0009902226,0.0018926244,0.038802683,0.022898719,0.1434294,0.033572238,0.7308986],"study_design_scores_gemma":[0.00018778261,0.00022591192,0.0164975,0.00038131714,0.00042963462,0.0013892093,0.0013612324,0.643055,0.05526968,0.09907116,0.18186988,0.00026164265],"about_ca_topic_score_codex":0.00552428,"about_ca_topic_score_gemma":0.0029058782,"teacher_disagreement_score":0.00552428,"about_ca_system_score_codex":0.0017485897,"about_ca_system_score_gemma":0.0035198724,"threshold_uncertainty_score":0.018001854},"labels":[],"label_agreement":null},{"id":"W2376065778","doi":"10.1142/s0218194016500169","title":"Knowledge-Driven User Behavior Pattern Discovery for System Security Enhancement","year":2016,"lang":"en","type":"article","venue":"International Journal of Software Engineering and Knowledge Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mohawk College; Ontario Tech University","funders":"","keywords":"Computer science; Insider threat; Insider; Process (computing); Domain (mathematical analysis); Audit; System administrator; Domain knowledge; Computer security; Software engineering","score_opus":0.009151537299184527,"score_gpt":0.24753457605856746,"score_spread":0.23838303875938294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2376065778","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20532265,0.00049679406,0.7817026,0.0012265554,0.00003007478,0.00055908976,0.001181532,0.0065098307,0.0029709435],"genre_scores_gemma":[0.707163,0.00016928514,0.2905412,0.00012747517,0.000012086655,0.00023252168,0.0009898951,0.00007632622,0.00068823434],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997282,0.00086421,0.0002723092,0.0004695408,0.00091692066,0.00019485518],"domain_scores_gemma":[0.99137515,0.005083986,0.0010238619,0.0012062122,0.0011323962,0.00017840308],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027772698,0.0007392009,0.00093681156,0.0039674863,0.0006609147,0.0013823846,0.0013735926,0.00090917124,0.0007968644],"category_scores_gemma":[0.012286594,0.00047080423,0.000844894,0.002320188,0.00071199297,0.0020669892,0.0010776904,0.0010994682,0.00046158495],"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":[0.0007081452,0.0016003876,0.07915067,0.0005543275,0.00031289263,0.0007629443,0.0015090286,0.11133795,0.024792181,0.008442177,0.0043986384,0.7664307],"study_design_scores_gemma":[0.000023927772,0.00009926444,0.0071994215,0.000046161902,0.00006956558,0.00025424254,0.00025062883,0.9657132,0.0153682,0.008920481,0.0020201039,0.000034738856],"about_ca_topic_score_codex":0.0065184063,"about_ca_topic_score_gemma":0.010853771,"teacher_disagreement_score":0.0065184063,"about_ca_system_score_codex":0.0010354813,"about_ca_system_score_gemma":0.0021013992,"threshold_uncertainty_score":0.014687777},"labels":[],"label_agreement":null},{"id":"W2376654677","doi":"","title":"Knowledge discovery in medical diagnosis data","year":2004,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CAE (Canada)","funders":"","keywords":"ID3 algorithm; Decision tree; ID3; Incremental decision tree; Computer science; Data mining; Decision tree learning; Knowledge extraction; Machine learning; Artificial intelligence; Tree (set theory); Mathematics","score_opus":0.05335688842526208,"score_gpt":0.33686575240882277,"score_spread":0.2835088639835607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2376654677","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07801911,0.0039946036,0.902729,0.0024988034,0.00020418098,0.00038940148,0.005115651,0.0019603646,0.005089015],"genre_scores_gemma":[0.41368,0.0024589333,0.5721676,0.0006343396,0.00020256062,0.00036041593,0.008234726,0.00009147736,0.0021699702],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972938,0.0006763904,0.00023665592,0.00042339446,0.001212259,0.00015740647],"domain_scores_gemma":[0.9941221,0.004343115,0.0002900199,0.00044822154,0.0006709923,0.00012554132],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029532686,0.00043308642,0.0009858697,0.005417079,0.0008920718,0.0018319993,0.0011780283,0.00092924066,0.0015974789],"category_scores_gemma":[0.012423012,0.0002557427,0.001013571,0.004969214,0.00056093716,0.0015478971,0.0012125024,0.0011275101,0.00089641],"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":[0.0005481134,0.0004044639,0.025881752,0.0008013837,0.00024279792,0.0018779646,0.00047381778,0.033233494,0.0057353997,0.039594512,0.013089011,0.8781173],"study_design_scores_gemma":[0.000110749796,0.00023926178,0.014663824,0.00028118127,0.00046450362,0.00329889,0.0004327978,0.7616102,0.03085678,0.15664315,0.03130281,0.00009587467],"about_ca_topic_score_codex":0.003023793,"about_ca_topic_score_gemma":0.0027903002,"teacher_disagreement_score":0.005417079,"about_ca_system_score_codex":0.001135517,"about_ca_system_score_gemma":0.00185447,"threshold_uncertainty_score":0.015618622},"labels":[],"label_agreement":null},{"id":"W2377095519","doi":"","title":"A Design and Implementation of Data Mining Arithmetic Subsystem","year":2006,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Arithmetic; Extension (predicate logic); Factory (object-oriented programming); Variable (mathematics); Plug-in; Algorithm; Programming language; Mathematics","score_opus":0.029849176481748004,"score_gpt":0.2962016924919957,"score_spread":0.2663525160102477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2377095519","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012814282,0.00031151032,0.9522627,0.00020199426,0.000092968905,0.00038607407,0.00043455084,0.026195977,0.0073],"genre_scores_gemma":[0.21671051,0.0005189169,0.75608647,0.0006195247,0.000109744266,0.001118411,0.0029752718,0.0016085292,0.02025254],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988902,0.000116579446,0.00010990642,0.00025771384,0.00047913034,0.00014638453],"domain_scores_gemma":[0.9990251,0.0001673106,0.00007145192,0.00022772086,0.00044654682,0.000061754974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009869062,0.00081065454,0.0005813301,0.0011568002,0.0004859519,0.0017683392,0.0030260577,0.0007428858,0.009278527],"category_scores_gemma":[0.0019948084,0.000664302,0.0005244991,0.0009743678,0.0003649933,0.0016764363,0.00081215263,0.00086781103,0.0043150564],"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":[0.0012820973,0.00034839235,0.00801895,0.0014949108,0.00026476113,0.00084171206,0.001044744,0.018250983,0.16696398,0.06244919,0.04034838,0.69869196],"study_design_scores_gemma":[0.0003349019,0.0007237429,0.0035174876,0.00020532463,0.00039894236,0.0014857663,0.00023231075,0.2970315,0.43217677,0.013212795,0.25053304,0.00014743114],"about_ca_topic_score_codex":0.002975485,"about_ca_topic_score_gemma":0.0019797883,"teacher_disagreement_score":0.009278527,"about_ca_system_score_codex":0.0009552899,"about_ca_system_score_gemma":0.0017230797,"threshold_uncertainty_score":0.031039774},"labels":[],"label_agreement":null},{"id":"W2377726271","doi":"","title":"The Analysis of Error for an Algorithm of Privacy-preserving Rule Mining","year":2007,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Transformation (genetics); Set (abstract data type); Expression (computer science); Algorithm; Data mining; Computation; Approximation error; Database transaction; Data set; Data transformation; Probability of error; Artificial intelligence; Data warehouse; Database","score_opus":0.03248448613419434,"score_gpt":0.3257329496202411,"score_spread":0.2932484634860467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2377726271","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021131983,0.0005245514,0.97642887,0.00039764706,0.000056338948,0.000042643547,0.000052369633,0.00043190824,0.0009335937],"genre_scores_gemma":[0.5892804,0.0006834412,0.40733236,0.00026649865,0.00016214942,0.0002233369,0.0002733177,0.0002967325,0.0014817438],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97902197,0.0064033256,0.0012369357,0.002967286,0.009398833,0.0009715119],"domain_scores_gemma":[0.89751965,0.07985493,0.0036681232,0.010414408,0.008031303,0.00051157677],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013614572,0.0011306545,0.0013017314,0.0024064118,0.0010661026,0.0025767917,0.0020750554,0.0017791679,0.0019508362],"category_scores_gemma":[0.09349873,0.0004143734,0.0012414799,0.002386779,0.0027824237,0.0041090883,0.0022960596,0.0024813134,0.0005350587],"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":[0.0015741205,0.00016989034,0.010442806,0.00047206934,0.00028786407,0.00049938215,0.00045643872,0.6679647,0.01271244,0.10998284,0.0020008364,0.19343667],"study_design_scores_gemma":[0.000015052324,0.00011429009,0.00080288516,0.000025988844,0.000033008244,0.00035876306,0.000027356418,0.96555316,0.008607329,0.023818776,0.00062241784,0.000021106183],"about_ca_topic_score_codex":0.001091895,"about_ca_topic_score_gemma":0.0005124965,"teacher_disagreement_score":0.013614572,"about_ca_system_score_codex":0.0022954894,"about_ca_system_score_gemma":0.0018868435,"threshold_uncertainty_score":0.07200158},"labels":[],"label_agreement":null},{"id":"W2378307117","doi":"","title":"The Course Association Model of the University Based on the Ontology","year":2009,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Ontology; Associative property; Association rule learning; Curriculum; Association (psychology); Selection (genetic algorithm); Test (biology); Object (grammar); Course (navigation); Mathematics education; Data model (GIS); Data mining; Data science; Artificial intelligence; Psychology","score_opus":0.00901101620234099,"score_gpt":0.20936140449422924,"score_spread":0.20035038829188825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2378307117","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059632223,0.0006245547,0.87412184,0.0023702371,0.00035414778,0.0003893065,0.0031090465,0.0011586986,0.058240015],"genre_scores_gemma":[0.6428405,0.0013255846,0.32034308,0.00055478566,0.00021187357,0.0007004031,0.006799396,0.0001464225,0.027077902],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99812514,0.00024151942,0.00019271497,0.00055082986,0.0007316125,0.00015808489],"domain_scores_gemma":[0.99877435,0.0002802406,0.0001377022,0.00019343174,0.00048077415,0.0001334308],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011210921,0.00032064872,0.00030299998,0.0026421314,0.0009969106,0.002764071,0.0012540844,0.0008318202,0.0037230186],"category_scores_gemma":[0.004208484,0.00027792284,0.0011591193,0.0036125786,0.00083141855,0.0066090287,0.000971897,0.0011693949,0.0012517793],"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":[0.00013829359,0.00032164415,0.027195327,0.00022674899,0.00014701983,0.00074785756,0.0016169521,0.034201812,0.0029177845,0.72598696,0.018408641,0.18809095],"study_design_scores_gemma":[0.000072139606,0.00012388737,0.016748112,0.00017109577,0.00029109075,0.0016196968,0.0009792178,0.42915633,0.0029847773,0.37548548,0.17225388,0.0001142869],"about_ca_topic_score_codex":0.022010883,"about_ca_topic_score_gemma":0.017686756,"teacher_disagreement_score":0.022010883,"about_ca_system_score_codex":0.0015559166,"about_ca_system_score_gemma":0.0035289293,"threshold_uncertainty_score":0.043765545},"labels":[],"label_agreement":null},{"id":"W2380498410","doi":"","title":"A Study on the Development of Data Warehouse System and ETL Oriented to Educational Evaluation","year":2007,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Data warehouse; Computer science; Data transformation; Database; Logic model; Transformation (genetics); Dimensional modeling; Warehouse; Process (computing); Online analytical processing; Data mining; Operating system","score_opus":0.08202611328359324,"score_gpt":0.3554092072126796,"score_spread":0.27338309392908633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2380498410","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.680497,0.0032908563,0.24806029,0.004098688,0.00019716797,0.0009574499,0.00038493218,0.00075299,0.06176062],"genre_scores_gemma":[0.8617858,0.002652962,0.1251216,0.00043215707,0.000055782282,0.0002935679,0.00043000592,0.000111808535,0.009116301],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959771,0.002173626,0.00026077495,0.00028414335,0.0011437039,0.00016070735],"domain_scores_gemma":[0.9917561,0.0039542625,0.00031553363,0.0005939672,0.0030135394,0.00036654135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0059737945,0.00020864145,0.00018936988,0.0011238015,0.0004697071,0.0021338083,0.0005673906,0.00049176544,0.0009634096],"category_scores_gemma":[0.010866874,0.00018517737,0.00027966197,0.0016522871,0.00050090585,0.0029725246,0.00038221283,0.00056923635,0.00023793455],"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":[0.00039828176,0.0019835883,0.044951923,0.0013204138,0.000046262845,0.0006852542,0.013749406,0.008041566,0.02240654,0.092126355,0.010674203,0.8036163],"study_design_scores_gemma":[0.00027293697,0.004167666,0.096272305,0.0022434725,0.000307309,0.0030153096,0.025092417,0.17888732,0.17944893,0.027666727,0.48240063,0.0002249471],"about_ca_topic_score_codex":0.0031984323,"about_ca_topic_score_gemma":0.0020850522,"teacher_disagreement_score":0.0059737945,"about_ca_system_score_codex":0.0014967817,"about_ca_system_score_gemma":0.002179094,"threshold_uncertainty_score":0.031592846},"labels":[],"label_agreement":null},{"id":"W2382607006","doi":"","title":"The Application of Data Mining in Fractionizing Clients of Bank","year":2009,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Data warehouse; Data bank; Cluster analysis; Data mining; Service (business); Data science; Commercial bank; Database; Finance; Business; Telecommunications; Marketing; Artificial intelligence","score_opus":0.02699616953765462,"score_gpt":0.3054037567886786,"score_spread":0.278407587251024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2382607006","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16304402,0.0009500887,0.81548434,0.0016838902,0.00013469765,0.0003770135,0.0016873891,0.0025905718,0.014047965],"genre_scores_gemma":[0.6136119,0.0009213965,0.37572744,0.0002728603,0.00009669085,0.00029367537,0.0023055603,0.00015051471,0.006619996],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983827,0.0003275144,0.0001537093,0.000467626,0.00056404393,0.00010446686],"domain_scores_gemma":[0.99703586,0.0010059099,0.00031708187,0.00045590647,0.0010734856,0.00011176199],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001331504,0.00057553744,0.0006576173,0.0022751377,0.0012634395,0.0022370056,0.0014716528,0.0005554169,0.0019056257],"category_scores_gemma":[0.0066709276,0.0003667227,0.0005329738,0.0044805952,0.00055967143,0.0026879867,0.00089384284,0.0011612356,0.0007829093],"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":[0.0004379732,0.00032644268,0.049899813,0.00038442196,0.00010332644,0.00030823462,0.001260845,0.0384298,0.009439039,0.0395648,0.012869809,0.84697556],"study_design_scores_gemma":[0.00008506565,0.00024148329,0.024108574,0.00014424138,0.0001737961,0.0009577657,0.0017016392,0.7128152,0.10047726,0.09310954,0.06605299,0.00013231297],"about_ca_topic_score_codex":0.004344498,"about_ca_topic_score_gemma":0.0030192968,"teacher_disagreement_score":0.004344498,"about_ca_system_score_codex":0.0014303114,"about_ca_system_score_gemma":0.0015112984,"threshold_uncertainty_score":0.010377705},"labels":[],"label_agreement":null},{"id":"W2385188605","doi":"","title":"Application of Data Mining with Attribute Generalization in Sales","year":2009,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Generalization; Online analytical processing; Data mining; Dependency (UML); Relation (database); Process (computing); Order (exchange); Data warehouse; Data science; Artificial intelligence","score_opus":0.02509096868082957,"score_gpt":0.2800964414605618,"score_spread":0.25500547277973223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2385188605","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058766015,0.0007140856,0.9355804,0.00057234877,0.00006982117,0.00022467344,0.0003680909,0.0012773507,0.0024273386],"genre_scores_gemma":[0.38232535,0.0007412679,0.6149569,0.00012889488,0.00008571907,0.00023014534,0.0005724579,0.00007411396,0.00088506454],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970366,0.0009028239,0.00027580195,0.0007282491,0.0009546065,0.00010199574],"domain_scores_gemma":[0.99678755,0.001775359,0.00025625812,0.00068463426,0.0004140795,0.00008204582],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040141633,0.00076850055,0.0013051492,0.002903554,0.0008942624,0.0013167452,0.0012247108,0.0006094464,0.0009082417],"category_scores_gemma":[0.009418998,0.0005641774,0.0016697682,0.0051543,0.0010788902,0.002290795,0.0015865911,0.0015583453,0.00029135283],"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":[0.00029958008,0.00034995173,0.018369565,0.00051954185,0.0004169257,0.0008578841,0.0013474316,0.32540914,0.011212579,0.06414009,0.0028355422,0.57424176],"study_design_scores_gemma":[0.000033562766,0.00007377618,0.004590546,0.00006313674,0.00008191309,0.00039314682,0.00017194997,0.89288193,0.010270383,0.082530126,0.008858548,0.000051018],"about_ca_topic_score_codex":0.004243688,"about_ca_topic_score_gemma":0.0024081487,"teacher_disagreement_score":0.004243688,"about_ca_system_score_codex":0.0010638316,"about_ca_system_score_gemma":0.0015640574,"threshold_uncertainty_score":0.021229208},"labels":[],"label_agreement":null},{"id":"W2387548438","doi":"","title":"Application of Association Rules Mining to Arrangement of Courses in Universities","year":2007,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Association rule learning; Key (lock); Association (psychology); Data mining; Engineering management; Data science; Computer security","score_opus":0.007595427977708517,"score_gpt":0.25470022958072214,"score_spread":0.24710480160301362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2387548438","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4663889,0.00059231056,0.52513486,0.0009627233,0.0001396063,0.0003410947,0.0011742186,0.0012647326,0.0040016286],"genre_scores_gemma":[0.72451067,0.00026609402,0.27340096,0.00008076681,0.00002928996,0.00010469191,0.00083879626,0.000029382507,0.0007393994],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99657744,0.0016601196,0.00029005882,0.0004972467,0.00081093784,0.00016417624],"domain_scores_gemma":[0.9912861,0.006269967,0.0006106446,0.0007899215,0.00077424716,0.00026913124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035953647,0.0004895838,0.00089595484,0.002920567,0.0012482319,0.0011003431,0.0011949543,0.00070065836,0.0011076871],"category_scores_gemma":[0.013070902,0.0004659953,0.00093917805,0.0038590955,0.0005469585,0.0015036272,0.0007163105,0.00076607626,0.0003253521],"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":[0.0009975213,0.001164312,0.11938475,0.00037725453,0.00067544804,0.001317573,0.0008641225,0.3552801,0.004255815,0.012253404,0.004286155,0.49914357],"study_design_scores_gemma":[0.0001178445,0.00026869707,0.01273517,0.000026580698,0.00018150393,0.00058237225,0.00036421863,0.9607509,0.005849215,0.014587354,0.004479724,0.00005639092],"about_ca_topic_score_codex":0.007788256,"about_ca_topic_score_gemma":0.007505539,"teacher_disagreement_score":0.007788256,"about_ca_system_score_codex":0.0007325631,"about_ca_system_score_gemma":0.0018086943,"threshold_uncertainty_score":0.019014359},"labels":[],"label_agreement":null},{"id":"W2390356830","doi":"","title":"Bitstream-oriented Frequent Pattern Sequence Mining Algorithm","year":2011,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Newborn Screening Ontario","funders":"","keywords":"Computer science; Bitstream; Pruning; Data mining; Pattern matching; Data stream; Sequence (biology); Sequential Pattern Mining; Data stream mining; Algorithm; Artificial intelligence; Information retrieval","score_opus":0.05616748204881752,"score_gpt":0.2610055858365664,"score_spread":0.2048381037877489,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2390356830","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040938485,0.0004180101,0.9537196,0.00032440733,0.00013095023,0.00033938186,0.0006972674,0.0013536981,0.002078081],"genre_scores_gemma":[0.21893242,0.00050535804,0.7741711,0.00032735866,0.00013427445,0.0004601326,0.0023431152,0.000073750416,0.003052401],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990094,0.0001518561,0.00013770309,0.00020797324,0.0004105272,0.00008264214],"domain_scores_gemma":[0.9984023,0.0005900516,0.00016711799,0.00018313425,0.00061018765,0.0000472459],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011557274,0.0005799013,0.0009975011,0.0029172613,0.0005737577,0.0008891929,0.0014707359,0.0010477728,0.0023976306],"category_scores_gemma":[0.0048089717,0.0002595064,0.0007394651,0.0030562354,0.00032823393,0.00148858,0.0006579687,0.00075490726,0.0013109634],"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":[0.0005316697,0.00031885962,0.0062672086,0.000317367,0.00021133339,0.0007477529,0.00019769011,0.048792828,0.016902668,0.012885638,0.0061331205,0.90669405],"study_design_scores_gemma":[0.000114030794,0.00032304827,0.001923158,0.000048928498,0.00010209866,0.001815875,0.00007603539,0.9533339,0.013331589,0.019657655,0.009229513,0.000044104556],"about_ca_topic_score_codex":0.0009585945,"about_ca_topic_score_gemma":0.00096004637,"teacher_disagreement_score":0.0029172613,"about_ca_system_score_codex":0.00027278796,"about_ca_system_score_gemma":0.00076812966,"threshold_uncertainty_score":0.008020878},"labels":[],"label_agreement":null},{"id":"W2395660443","doi":"10.4018/978-1-60566-058-5.ch032","title":"A Framework for Efficient Association Rule Mining in XML Data","year":2009,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; XML; Association rule learning; Data mining; Efficient XML Interchange; XML database; Streaming XML; Constraint (computer-aided design); Generalization; XML validation; Selection (genetic algorithm); Information retrieval; Task (project management); XML Schema (W3C); XML Encryption; Artificial intelligence; World Wide Web","score_opus":0.04044477558815176,"score_gpt":0.30061198966354963,"score_spread":0.2601672140753979,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2395660443","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021389058,0.00027857936,0.9977011,0.00012533728,0.00002079882,0.0000981819,0.00020190085,0.0011765469,0.00018361906],"genre_scores_gemma":[0.0038281973,0.0003501754,0.99453026,0.000091180125,0.00003181402,0.00024433387,0.0005668756,0.000055513057,0.0003016522],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9927222,0.0029007108,0.0010135146,0.0010055932,0.002197815,0.0001602098],"domain_scores_gemma":[0.99355376,0.003830938,0.00048582695,0.0013267838,0.0006537198,0.00014906815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010706048,0.0015890631,0.0023020448,0.005449265,0.0011607424,0.0036300833,0.0047512185,0.001959481,0.0036229093],"category_scores_gemma":[0.015783487,0.001465454,0.0041942955,0.006205319,0.0011023396,0.004752664,0.0033225354,0.0037315944,0.0040563927],"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":[0.0002024898,0.000332568,0.0018662252,0.0020539835,0.00077563553,0.0014603283,0.00059325196,0.08597277,0.007862746,0.18655401,0.027082046,0.68524396],"study_design_scores_gemma":[0.00013464362,0.00021404243,0.00086426013,0.00057869474,0.00018378676,0.0025133698,0.00019662798,0.641896,0.0073999986,0.22789119,0.11798454,0.00014299738],"about_ca_topic_score_codex":0.0018086951,"about_ca_topic_score_gemma":0.0025843792,"teacher_disagreement_score":0.010706048,"about_ca_system_score_codex":0.00081619545,"about_ca_system_score_gemma":0.0019127806,"threshold_uncertainty_score":0.056619704},"labels":[],"label_agreement":null},{"id":"W2397124290","doi":"10.1007/978-3-319-22053-6_47","title":"CKNNI: An Improved KNN-Based Missing Value Handling Technique","year":2015,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":31,"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; Missing data; Data mining; Imputation (statistics); Cluster analysis; Centroid; k-nearest neighbors algorithm; Data set; Algorithm; Artificial intelligence; Machine learning","score_opus":0.03167907882061318,"score_gpt":0.28505840536179744,"score_spread":0.2533793265411843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2397124290","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002800121,0.00058281445,0.99010605,0.00013257297,0.00030204802,0.0001178891,0.0008359996,0.004338085,0.0007844395],"genre_scores_gemma":[0.029138168,0.00035333322,0.9631383,0.00022411492,0.00018505525,0.00017087285,0.0029534614,0.00047801813,0.003358627],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950801,0.00068225217,0.00047861415,0.00096553395,0.0024007147,0.00039274924],"domain_scores_gemma":[0.99225736,0.002030432,0.0006067632,0.0018821788,0.0029519787,0.00027126246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0060687517,0.0018989553,0.00280735,0.003946775,0.0015759298,0.0021117537,0.0060762605,0.0019873476,0.0082222745],"category_scores_gemma":[0.016753271,0.0010581702,0.0020056702,0.0050937226,0.0007815589,0.0029847454,0.0036663255,0.004341475,0.006558434],"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":[0.0008139733,0.00025028887,0.002967145,0.00043345676,0.00031220095,0.00020788064,0.00012129872,0.021091696,0.011387352,0.0038512333,0.019997865,0.9385657],"study_design_scores_gemma":[0.00016802271,0.00027536298,0.0033901036,0.00019270129,0.00032443533,0.001019,0.00014072146,0.9149529,0.028215492,0.016530186,0.03459875,0.00019229374],"about_ca_topic_score_codex":0.010281972,"about_ca_topic_score_gemma":0.013983789,"teacher_disagreement_score":0.010281972,"about_ca_system_score_codex":0.0009276687,"about_ca_system_score_gemma":0.0034562638,"threshold_uncertainty_score":0.032095015},"labels":[],"label_agreement":null},{"id":"W2397894633","doi":"","title":"Understanding Users' Interaction Behavior with an Intelligent Educational Game: Prime Climb.","year":2013,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Prime (order theory); Computer science; Association rule learning; Climb; Cluster analysis; Domain (mathematical analysis); Educational data mining; Relation (database); Human–computer interaction; Artificial intelligence; Data mining; Engineering; Mathematics","score_opus":0.1059635585992821,"score_gpt":0.3193814308804808,"score_spread":0.21341787228119874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2397894633","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9809787,0.000082943756,0.016102966,0.00013288013,0.000008836269,0.00012156321,0.0005142715,0.0003553667,0.0017024757],"genre_scores_gemma":[0.97634536,0.000067662615,0.021645555,0.000055225613,0.0000043794994,0.000055746565,0.0006800843,0.000016580014,0.001129463],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9994861,0.00017087019,0.00002973555,0.00015067265,0.0001247336,0.00003784767],"domain_scores_gemma":[0.9954144,0.0030595239,0.0005854632,0.00025019317,0.00037693308,0.00031342937],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007128338,0.0006399329,0.00047362244,0.0013404774,0.0003077017,0.0012182054,0.0005728755,0.0005177413,0.0016498569],"category_scores_gemma":[0.008354917,0.00028127307,0.00034255232,0.0006066612,0.00021780074,0.0010446586,0.00051881454,0.0005358158,0.00060544926],"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":[0.0019369766,0.0016643412,0.77557516,0.00065018906,0.00037536077,0.0007089177,0.008131446,0.004852643,0.027864223,0.00063987414,0.002771124,0.17482975],"study_design_scores_gemma":[0.00004823014,0.001829894,0.8239737,0.0001380508,0.00019233234,0.0011617135,0.005028656,0.15138228,0.00822817,0.001697064,0.006224307,0.000095593816],"about_ca_topic_score_codex":0.0038812454,"about_ca_topic_score_gemma":0.008946385,"teacher_disagreement_score":0.0038812454,"about_ca_system_score_codex":0.0002641449,"about_ca_system_score_gemma":0.0003449071,"threshold_uncertainty_score":0.0077173114},"labels":[],"label_agreement":null},{"id":"W2398022664","doi":"10.1007/978-3-319-25255-1_52","title":"Mining Weighted Frequent Itemsets with the Recency Constraint","year":2015,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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 Moncton","funders":"","keywords":"Pruning; Computer science; Constraint (computer-aided design); Data mining; Property (philosophy); Projection (relational algebra); Algorithm; Mathematics","score_opus":0.02814096298749303,"score_gpt":0.255818271026008,"score_spread":0.227677308038515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2398022664","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28076243,0.007452566,0.6923693,0.00077118684,0.00039438627,0.00061336916,0.012078836,0.0011287245,0.004429261],"genre_scores_gemma":[0.5695617,0.0026031234,0.40162778,0.0002950005,0.0006260799,0.0006862867,0.019928224,0.00022722545,0.0044446257],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995193,0.0007070848,0.0011442513,0.0012333808,0.0014270394,0.00029527588],"domain_scores_gemma":[0.98714906,0.007900736,0.0014377423,0.0014737821,0.0017579556,0.000280719],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029686182,0.0010357748,0.002812371,0.0039666384,0.00079907896,0.0022196167,0.0032464017,0.0014024329,0.0021496005],"category_scores_gemma":[0.020175368,0.0010336442,0.002261297,0.007545598,0.0005258582,0.005120852,0.0011124844,0.0014512961,0.0010133736],"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":[0.0042557325,0.0012720595,0.068554,0.003763358,0.002318752,0.006376754,0.0005688259,0.12662904,0.023429403,0.02739172,0.017697262,0.7177432],"study_design_scores_gemma":[0.00029701894,0.0010249283,0.01599796,0.00053628243,0.0009712576,0.004979107,0.0006610386,0.8845296,0.013770417,0.0617006,0.015325143,0.0002066452],"about_ca_topic_score_codex":0.0023703487,"about_ca_topic_score_gemma":0.0034666262,"teacher_disagreement_score":0.0039666384,"about_ca_system_score_codex":0.00051975646,"about_ca_system_score_gemma":0.0017316715,"threshold_uncertainty_score":0.015699744},"labels":[],"label_agreement":null},{"id":"W2398755758","doi":"","title":"Mining Icebergs in Time-Stamped Databases.","year":2011,"lang":"en","type":"article","venue":"Indian International Conference on Artificial Intelligence","topic":"Data Mining Algorithms and Applications","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 Alberta","funders":"","keywords":"Iceberg; Computer science; Database; Geology","score_opus":0.18212539124276206,"score_gpt":0.3412848615653043,"score_spread":0.15915947032254224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2398755758","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4168661,0.023634696,0.47704244,0.004678037,0.0016471009,0.0008546889,0.05501515,0.004178242,0.0160836],"genre_scores_gemma":[0.8022195,0.0034245623,0.14430912,0.0005078501,0.0005165954,0.00036416174,0.04419601,0.00021302083,0.0042491183],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958903,0.00041858543,0.0006255884,0.0008909585,0.0016178426,0.00055685523],"domain_scores_gemma":[0.9881449,0.005117976,0.0020020737,0.0018856726,0.0022882044,0.0005611763],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032439816,0.00074997905,0.0019397025,0.006409051,0.0014196605,0.004406114,0.0033311318,0.0014962023,0.002917188],"category_scores_gemma":[0.02289528,0.0007594791,0.0013106545,0.010072275,0.0011944256,0.007807824,0.0024666474,0.0017554198,0.0016301855],"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":[0.0040618763,0.0007871306,0.16819608,0.0019499739,0.001063616,0.0040267683,0.0022544663,0.13429134,0.008356781,0.11201439,0.09649342,0.46650413],"study_design_scores_gemma":[0.00016120693,0.00050751877,0.024549935,0.00070961704,0.00041289284,0.002403696,0.0044792113,0.646511,0.011636765,0.23508933,0.07342533,0.000113516515],"about_ca_topic_score_codex":0.006548835,"about_ca_topic_score_gemma":0.008234715,"teacher_disagreement_score":0.006548835,"about_ca_system_score_codex":0.0010290939,"about_ca_system_score_gemma":0.0022765226,"threshold_uncertainty_score":0.017156005},"labels":[],"label_agreement":null},{"id":"W2400262328","doi":"10.2316/journal.201.2015.2.201-2674","title":"EFFECTIVE MINING ALGORITHM OF K-DENSE SUB-GRAPH IN COMPLEX NETWORK BASED ON PROBABILITY ATTRIBUTE GRAPH","year":2015,"lang":"en","type":"article","venue":"Control and Intelligent Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Graph; Power graph analysis; Algorithm; Theoretical computer science","score_opus":0.037326881370174515,"score_gpt":0.25727639854022855,"score_spread":0.21994951717005404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2400262328","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09881231,0.00055118935,0.8970238,0.00032246351,0.00004640614,0.00010162476,0.00061433815,0.0006227671,0.0019050693],"genre_scores_gemma":[0.69280076,0.0007450412,0.3014644,0.00010127839,0.000073833326,0.00016803593,0.0020522228,0.00007751462,0.0025169107],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993994,0.00008208424,0.000041869233,0.00023880556,0.0001796575,0.00005819873],"domain_scores_gemma":[0.99884486,0.00051424286,0.00013845543,0.00012251413,0.00031960194,0.000060316706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040244896,0.00057634333,0.0009836311,0.0028193854,0.00085430365,0.0010329747,0.0016045031,0.00065941096,0.0012299399],"category_scores_gemma":[0.0031591242,0.00037170085,0.0008050953,0.002396285,0.00049316505,0.002151196,0.00083473587,0.00060405413,0.0002794437],"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":[0.0003666632,0.0003066335,0.034058508,0.0006584921,0.00038227264,0.0010518209,0.00090611476,0.4053519,0.012081752,0.06100461,0.013647792,0.47018352],"study_design_scores_gemma":[0.0000110880665,0.000020431726,0.0016799084,0.000012998693,0.000041961735,0.0002494926,0.00006656927,0.9792921,0.001125789,0.016605387,0.0008838407,0.000010486203],"about_ca_topic_score_codex":0.0073579433,"about_ca_topic_score_gemma":0.0065751574,"teacher_disagreement_score":0.0073579433,"about_ca_system_score_codex":0.00065318774,"about_ca_system_score_gemma":0.0010818157,"threshold_uncertainty_score":0.014630258},"labels":[],"label_agreement":null},{"id":"W2400935260","doi":"10.1137/1.9781611973440.88","title":"Efficient Matching of Substrings in Uncertain Sequences","year":2014,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Substring; Subsequence; Computer science; Sequence (biology); Matching (statistics); Scalability; Trajectory; Data mining; Theoretical computer science; Data structure; Mathematics; Programming language; Database","score_opus":0.015405834989054006,"score_gpt":0.2560108658142202,"score_spread":0.2406050308251662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2400935260","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032784,0.00020227463,0.96572167,0.000194531,0.000022971608,0.000053517713,0.00026290314,0.00032761038,0.00043056635],"genre_scores_gemma":[0.36791435,0.00047073167,0.6278046,0.00019628875,0.00010111347,0.00017330998,0.0016566326,0.00022790107,0.0014550686],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99734145,0.00039043243,0.00030939846,0.00092305295,0.00086141773,0.00017428794],"domain_scores_gemma":[0.99076664,0.0062662545,0.0011929341,0.0007930853,0.00073815515,0.000242922],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020458885,0.0005502617,0.0015407614,0.0024913196,0.00085247733,0.0016510928,0.002188769,0.0017986926,0.0018145295],"category_scores_gemma":[0.017234117,0.00072879944,0.0011904757,0.0036250646,0.0010215942,0.0044317553,0.0019410196,0.0016857899,0.00071082346],"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":[0.0005506719,0.00017014808,0.011062785,0.00047955188,0.00015374839,0.00074010354,0.00057989854,0.57592684,0.013532812,0.054576814,0.0025989325,0.33962762],"study_design_scores_gemma":[0.00000942043,0.00006146337,0.00075588375,0.000026138256,0.000017616656,0.00021594005,0.00010180868,0.9300213,0.0048665325,0.062235635,0.0016711532,0.000017087761],"about_ca_topic_score_codex":0.0019124338,"about_ca_topic_score_gemma":0.0016408876,"teacher_disagreement_score":0.0024913196,"about_ca_system_score_codex":0.00085160945,"about_ca_system_score_gemma":0.0011817125,"threshold_uncertainty_score":0.010819793},"labels":[],"label_agreement":null},{"id":"W2404239985","doi":"","title":"Using Strong Lexical Association Extraction in an Understanding of Managers’ Decision Process","year":2014,"lang":"en","type":"article","venue":"The Florida AI Research Society","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Computer science; Task (project management); Association rule learning; Process (computing); Association (psychology); Exploit; Natural language processing; Artificial intelligence; Lexical decision task; Machine learning; Order (exchange); Knowledge management; Data science; Information retrieval; Psychology; Engineering; Cognition","score_opus":0.22749109295032235,"score_gpt":0.4663741661756212,"score_spread":0.23888307322529886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2404239985","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06598567,0.0011767849,0.91759753,0.0031290888,0.000104836894,0.00017382808,0.00082197064,0.0006198613,0.010390401],"genre_scores_gemma":[0.47476214,0.00086197705,0.5208834,0.00039340238,0.0000937597,0.00017431613,0.0011663466,0.00006958804,0.0015950516],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99710375,0.0009914404,0.00058707857,0.00058193854,0.00058752997,0.00014829621],"domain_scores_gemma":[0.9882653,0.008760338,0.0011035587,0.00078249327,0.00090858585,0.00017979299],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042550415,0.0007533887,0.00079879083,0.005269496,0.0015574003,0.005440932,0.0014085391,0.001827014,0.0040269336],"category_scores_gemma":[0.01924124,0.0007171657,0.0009850303,0.0037457997,0.0017670089,0.011852121,0.0020318746,0.0018384228,0.0011816128],"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":[0.00058659713,0.00048346893,0.027077083,0.0015008168,0.00023990807,0.003863379,0.015139265,0.024634153,0.017011723,0.44733343,0.007924052,0.45420614],"study_design_scores_gemma":[0.00004773888,0.00010923787,0.0093183,0.000550003,0.00021941714,0.0016006818,0.006657672,0.19143538,0.008252596,0.7367682,0.04492344,0.00011741182],"about_ca_topic_score_codex":0.002282082,"about_ca_topic_score_gemma":0.0030505802,"teacher_disagreement_score":0.005440932,"about_ca_system_score_codex":0.0010029332,"about_ca_system_score_gemma":0.0020094707,"threshold_uncertainty_score":0.022503078},"labels":[],"label_agreement":null},{"id":"W2404281722","doi":"","title":"Big Data or Right Data","year":2013,"lang":"en","type":"article","venue":"EdShare Southampton (University of Southampton)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Big data; Context (archaeology); Library science; Computer science; World Wide Web; Data science; Sociology; Political science; Geography","score_opus":0.11282186635496198,"score_gpt":0.24949585940100197,"score_spread":0.13667399304604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2404281722","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025070105,0.0364749,0.059020404,0.5660946,0.02830891,0.00018889476,0.0046670674,0.0027037458,0.3000345],"genre_scores_gemma":[0.1681437,0.08603012,0.052154854,0.37443066,0.05595886,0.00060850865,0.008626924,0.005425183,0.24862118],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99053955,0.0038176589,0.0004375978,0.0015096398,0.0031453425,0.0005501611],"domain_scores_gemma":[0.97789955,0.009934852,0.001011242,0.006528565,0.0032666447,0.0013591433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0064410036,0.00085103954,0.0011783622,0.002021124,0.0024594527,0.015673224,0.0019373179,0.004674613,0.06817667],"category_scores_gemma":[0.036525425,0.0005553656,0.00068372226,0.003606508,0.007782175,0.025511334,0.0058586416,0.0071048737,0.028464474],"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":[0.000054930526,0.000019949995,0.00075791153,0.00051041506,0.00003766642,0.00012217254,0.00048395392,0.00034145315,0.00035450447,0.25154775,0.64327085,0.102498524],"study_design_scores_gemma":[0.000007306934,0.000011535813,0.00026077568,0.0005925431,0.000008963202,0.000104360464,0.0005262975,0.0004900755,0.00030428785,0.14580154,0.8518711,0.000021093167],"about_ca_topic_score_codex":0.00243523,"about_ca_topic_score_gemma":0.0015161248,"teacher_disagreement_score":0.06817667,"about_ca_system_score_codex":0.0028219686,"about_ca_system_score_gemma":0.0030565492,"threshold_uncertainty_score":0.22807372},"labels":[],"label_agreement":null},{"id":"W2405618138","doi":"","title":"Frequent pattern mining from dense graph streams","year":2014,"lang":"en","type":"article","venue":"Mspace (University of Manitoba)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"License; STREAMS; Graph; Computer science; Data stream mining; Library science; Data mining; Theoretical computer science; Computer network; Operating system","score_opus":0.01426143990488582,"score_gpt":0.19040219579089504,"score_spread":0.17614075588600922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2405618138","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1269594,0.00085155386,0.86160296,0.0009001001,0.00012208344,0.0003542814,0.005294374,0.0025585494,0.0013567258],"genre_scores_gemma":[0.4695557,0.00085197255,0.51446205,0.00020171353,0.00013723354,0.00042333725,0.01279364,0.00014830731,0.0014260557],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99859256,0.00026681315,0.00017604169,0.00036050862,0.00046352134,0.00014054422],"domain_scores_gemma":[0.9942556,0.0028803954,0.0006811936,0.0008698178,0.0010745273,0.0002384658],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00110866,0.0009078878,0.0010786015,0.005305663,0.0007711297,0.0014420253,0.0014729671,0.000856513,0.0008477839],"category_scores_gemma":[0.009236708,0.00052414375,0.0009750546,0.0045269877,0.0005471514,0.002798821,0.0013970755,0.001060005,0.0003645739],"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":[0.0011580669,0.00060033664,0.041437935,0.0009766712,0.00057409983,0.0032802147,0.0009024601,0.26078695,0.01884027,0.050952226,0.024185041,0.5963058],"study_design_scores_gemma":[0.00006379869,0.000090305395,0.0030911642,0.000038013735,0.000049468126,0.0006045055,0.00029027349,0.91026795,0.0046555996,0.07646764,0.004360132,0.000021237662],"about_ca_topic_score_codex":0.0025323685,"about_ca_topic_score_gemma":0.0038345663,"teacher_disagreement_score":0.005305663,"about_ca_system_score_codex":0.0006053947,"about_ca_system_score_gemma":0.0009107743,"threshold_uncertainty_score":0.0058632493},"labels":[],"label_agreement":null},{"id":"W2405794916","doi":"10.1137/1.9781611974010.17","title":"Data mining for real mining: A robust algorithm for prospectivity mapping with uncertainties","year":2015,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Prospectivity mapping; Data mining; Computer science; Support vector machine; Mineral exploration; Range (aeronautics); Algorithm; Machine learning; Artificial intelligence; Engineering; Geophysics; Geology","score_opus":0.1602540712276387,"score_gpt":0.314013926861992,"score_spread":0.15375985563435327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2405794916","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009955378,0.00015497275,0.99782455,0.00017219431,0.000023664448,0.000037670947,0.00007160719,0.00049322244,0.00022650386],"genre_scores_gemma":[0.035372607,0.00015968541,0.96290016,0.0001348527,0.00006397119,0.0002501429,0.00033024442,0.00012380493,0.00066450104],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99755305,0.00081052806,0.00025129685,0.00061327533,0.00065286894,0.0001189827],"domain_scores_gemma":[0.995018,0.0031514035,0.00036486736,0.0005197364,0.00085348485,0.000092516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004939616,0.0013712288,0.0021204352,0.0023646276,0.0009144254,0.0019301883,0.0027673116,0.002268236,0.002845172],"category_scores_gemma":[0.015557984,0.0010355785,0.0020058565,0.0027344327,0.0011861088,0.0027629093,0.002742946,0.0037963416,0.0016023437],"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":[0.00027816708,0.000127271,0.0013955403,0.000308364,0.0001889444,0.00014892904,0.0001716042,0.40717232,0.003041882,0.029144408,0.0084182955,0.5496043],"study_design_scores_gemma":[0.000023372266,0.000027547429,0.00011052935,0.000023066972,0.00000972744,0.000046155088,0.000016536489,0.97726,0.0010426501,0.018704131,0.0027259775,0.000010391924],"about_ca_topic_score_codex":0.0022293525,"about_ca_topic_score_gemma":0.0018564167,"teacher_disagreement_score":0.004939616,"about_ca_system_score_codex":0.0011223631,"about_ca_system_score_gemma":0.0019691095,"threshold_uncertainty_score":0.026123524},"labels":[],"label_agreement":null},{"id":"W2406609927","doi":"","title":"Mining User's Behaviors in Intelligent Educational Games: Prime Climb a Case Study.","year":2013,"lang":"en","type":"article","venue":"Educational Data Mining","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":"University of British Columbia","funders":"","keywords":"Climb; Computer science; Prime (order theory); Human–computer interaction; Engineering; Mathematics","score_opus":0.06904220657417487,"score_gpt":0.3595855794393796,"score_spread":0.2905433728652047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2406609927","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9895425,0.00023844068,0.00408357,0.0006488361,0.00002215865,0.00031676647,0.0013083022,0.00019741335,0.0036420089],"genre_scores_gemma":[0.981059,0.00021111434,0.013332962,0.00017284551,0.00001013982,0.00016437667,0.0016546497,0.000034156263,0.0033605897],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99922836,0.00033481972,0.00005031493,0.00013346778,0.00016963502,0.00008347096],"domain_scores_gemma":[0.996415,0.002099699,0.00028484355,0.00024744854,0.00044697244,0.0005059623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010644916,0.00040254797,0.00037105966,0.0013992877,0.000995432,0.0010800497,0.00087513204,0.000924608,0.0012570155],"category_scores_gemma":[0.006929438,0.00021109892,0.00031168852,0.001437665,0.0003838895,0.0007805999,0.0008428121,0.0007362387,0.00061452936],"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":[0.0014830764,0.005081356,0.6962558,0.0007303916,0.00034489995,0.008294164,0.016481385,0.0077360636,0.0044418653,0.0025112554,0.028902026,0.22773771],"study_design_scores_gemma":[0.0002915229,0.0025709355,0.77904254,0.00046378217,0.00030732577,0.006274581,0.03740763,0.111431666,0.0074843294,0.0057978244,0.048754755,0.0001731212],"about_ca_topic_score_codex":0.018581457,"about_ca_topic_score_gemma":0.041935302,"teacher_disagreement_score":0.018581457,"about_ca_system_score_codex":0.00056202355,"about_ca_system_score_gemma":0.0007987931,"threshold_uncertainty_score":0.036946595},"labels":[],"label_agreement":null},{"id":"W2406745441","doi":"","title":"Analyzing open data from the city of Montreal","year":2015,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"","keywords":"Open data; Computer science; Context (archaeology); Data science; World Wide Web; Geography","score_opus":0.19996737314698346,"score_gpt":0.38267936776752587,"score_spread":0.1827119946205424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2406745441","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4419178,0.0033335567,0.011525758,0.0061304285,0.0007201797,0.00049492554,0.44829753,0.0026399754,0.084939815],"genre_scores_gemma":[0.6024543,0.0022888237,0.01822104,0.00061472366,0.00034801412,0.00047466476,0.34908575,0.00056804623,0.025944628],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9983438,0.00019452801,0.000058973375,0.00025403217,0.00080913317,0.00033939234],"domain_scores_gemma":[0.9945471,0.0006715475,0.0005427886,0.00049301365,0.0031429925,0.0006025376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008004462,0.0006454115,0.0004131235,0.0061480748,0.0022527387,0.002004116,0.001257764,0.0006120629,0.006377938],"category_scores_gemma":[0.0057643605,0.00019779381,0.00058220624,0.015522056,0.000783839,0.0010184,0.0014754118,0.00085598713,0.00136398],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041856678,0.0002675184,0.3043441,0.0007578756,0.00041890104,0.002401567,0.0039764466,0.011848211,0.0038964648,0.020880729,0.4499254,0.2008642],"study_design_scores_gemma":[0.000038997314,0.000050539722,0.59917396,0.00023636957,0.0000752937,0.00016555985,0.0064848578,0.010659571,0.0025494169,0.0025485586,0.37781858,0.00019827527],"about_ca_topic_score_codex":0.9271395,"about_ca_topic_score_gemma":0.9673296,"teacher_disagreement_score":0.07286048,"about_ca_system_score_codex":0.008160721,"about_ca_system_score_gemma":0.008060722,"threshold_uncertainty_score":0.14657909},"labels":[],"label_agreement":null},{"id":"W2406750717","doi":"","title":"Frequent subgraph mining from streams of linked graph structured data","year":2015,"lang":"en","type":"article","venue":"Mspace (University of Manitoba)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":9,"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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data stream mining; Disjoint sets; Graph; Big data; Theoretical computer science; Data mining; Knowledge graph; Information retrieval; Mathematics","score_opus":0.05193318104658357,"score_gpt":0.23127746484805578,"score_spread":0.17934428380147222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2406750717","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29874098,0.004905407,0.6679152,0.0018142893,0.00027934642,0.0006091765,0.01849618,0.0046222066,0.0026172225],"genre_scores_gemma":[0.5697424,0.0021565543,0.37883765,0.00016710766,0.00022060862,0.00034364342,0.047020506,0.00022671312,0.0012849023],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852604,0.00037849217,0.00015171405,0.00033817955,0.00046665216,0.00013895985],"domain_scores_gemma":[0.9951126,0.00255222,0.00057082105,0.00072588195,0.000782271,0.0002562238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010599631,0.0007900632,0.001012385,0.0054621985,0.00066633645,0.0014272002,0.0012693694,0.0010157644,0.00054667285],"category_scores_gemma":[0.008925575,0.00041398845,0.0011359303,0.0051028165,0.00033860124,0.002449706,0.0013200671,0.0008752579,0.0005754026],"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":[0.0015254167,0.0010200405,0.06498486,0.0017925836,0.0012882093,0.004546123,0.001328653,0.1040648,0.03991049,0.022952145,0.04690614,0.7096805],"study_design_scores_gemma":[0.00011247183,0.0003111361,0.011438829,0.00016042743,0.00029922926,0.0021106107,0.0010749081,0.8692661,0.014219164,0.082755126,0.018188143,0.000063930085],"about_ca_topic_score_codex":0.0022533434,"about_ca_topic_score_gemma":0.0049629016,"teacher_disagreement_score":0.0054621985,"about_ca_system_score_codex":0.00035739355,"about_ca_system_score_gemma":0.0006904675,"threshold_uncertainty_score":0.0056056976},"labels":[],"label_agreement":null},{"id":"W2460072725","doi":"10.1007/978-3-319-34111-8_29","title":"Learning Statistically Significant Contrast Sets","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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 Alberta","funders":"","keywords":"Contrast (vision); Association rule learning; Computer science; Classifier (UML); Artificial intelligence; Machine learning; Data mining; Set (abstract data type); Pattern recognition (psychology)","score_opus":0.01489813950887214,"score_gpt":0.2539503358103343,"score_spread":0.23905219630146218,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2460072725","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054432515,0.0013237689,0.9340052,0.00068513496,0.00016482873,0.00009602189,0.00046814425,0.0024892993,0.006335082],"genre_scores_gemma":[0.4841314,0.00088145235,0.503282,0.00034266393,0.0003376604,0.00023777153,0.003351452,0.0004927861,0.0069428002],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99873096,0.00034560883,0.00006699971,0.00049599085,0.00027609602,0.00008435113],"domain_scores_gemma":[0.9952259,0.0033789736,0.00031322276,0.0006369806,0.0003186551,0.00012621054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023295106,0.001395822,0.0012517589,0.002685536,0.00071018055,0.0023455266,0.0022482204,0.0014110603,0.0059878407],"category_scores_gemma":[0.011258533,0.0008383771,0.0017902802,0.0015126409,0.0012178894,0.003050051,0.00321764,0.0029015692,0.002146129],"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":[0.00057043624,0.00029343233,0.006837931,0.0004108477,0.00044089695,0.0004084254,0.00020837554,0.044372495,0.022498144,0.06620222,0.011047698,0.8467092],"study_design_scores_gemma":[0.000083356266,0.00039882853,0.003557284,0.00012939525,0.00022325618,0.0007018448,0.00016582702,0.73076546,0.022040002,0.23125173,0.010618159,0.00006484294],"about_ca_topic_score_codex":0.00040895105,"about_ca_topic_score_gemma":0.00085689337,"teacher_disagreement_score":0.0059878407,"about_ca_system_score_codex":0.0007086931,"about_ca_system_score_gemma":0.0007698437,"threshold_uncertainty_score":0.020031393},"labels":[],"label_agreement":null},{"id":"W2463715500","doi":"10.1016/j.compmedimag.2016.06.008","title":"WITHDRAWN: Clinical pathways inference from decision rules by hybrid stream mining and fuzzy unordered rule induction strategy","year":2016,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Data Mining Algorithms and Applications","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":"Lakehead University","funders":"Universidade de Macau","keywords":"Rule induction; Rule of inference; Computer science; Inference; Artificial intelligence; Fuzzy inference system; Data mining; Fuzzy inference; Decision rule; Fuzzy rule; Fuzzy logic; Fuzzy set; Fuzzy control system; Adaptive neuro fuzzy inference system","score_opus":0.025612501070720325,"score_gpt":0.29934863912570053,"score_spread":0.2737361380549802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2463715500","genre_codex":"editorial","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017564362,0.014181954,0.0288621,0.4125102,0.4347595,0.0017945548,0.04577794,0.004498072,0.040051363],"genre_scores_gemma":[0.26519853,0.01684507,0.054193463,0.19034299,0.2231499,0.0017456341,0.040215347,0.0012542809,0.20705481],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987166,0.00023923462,0.00023623512,0.0001453979,0.0005354757,0.0001270808],"domain_scores_gemma":[0.9846913,0.006119488,0.0004293127,0.00090396067,0.0067056674,0.0011503174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032153975,0.0007726825,0.0017542094,0.001074792,0.00090315373,0.0018312146,0.0027061931,0.0037658303,0.076341],"category_scores_gemma":[0.041347403,0.00033206912,0.0014488236,0.0012811993,0.0006283722,0.0010253042,0.0007806739,0.002689558,0.019780308],"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":[0.0024430729,0.00011713526,0.001100902,0.000570879,0.00016008447,0.00079004915,0.000034372442,0.00048039423,0.0008737731,0.0029631688,0.8901389,0.100327216],"study_design_scores_gemma":[0.0067453654,0.0012076077,0.014560454,0.0013762362,0.0009866378,0.0035264387,0.0001755255,0.016532613,0.009403316,0.044331625,0.90096736,0.00018686338],"about_ca_topic_score_codex":0.0057456163,"about_ca_topic_score_gemma":0.006786502,"teacher_disagreement_score":0.076341,"about_ca_system_score_codex":0.0012159669,"about_ca_system_score_gemma":0.004269276,"threshold_uncertainty_score":0.2553861},"labels":[],"label_agreement":null},{"id":"W2463958247","doi":"","title":"Analyzing Student Inquiry Data Using Process Discovery and Sequence Classification.","year":2015,"lang":"en","type":"article","venue":"NPARC","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Process (computing); Process mining; Sequential Pattern Mining; Knowledge extraction; Sequence (biology); Set (abstract data type); Data mining; Data science; Business process discovery; Machine learning; Artificial intelligence; Work in process; Engineering","score_opus":0.29182153557591584,"score_gpt":0.4145837869204557,"score_spread":0.12276225134453989,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2463958247","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12157944,0.0011864256,0.85843235,0.0006379049,0.00012963101,0.003098356,0.0073121414,0.0033774567,0.0042462884],"genre_scores_gemma":[0.27101293,0.0006685754,0.71409315,0.00011007811,0.000070620175,0.0023282047,0.010260781,0.00010550068,0.0013501962],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98679173,0.0046116933,0.0017201738,0.0019062153,0.004571881,0.00039827893],"domain_scores_gemma":[0.95124745,0.031571377,0.0048142364,0.0052038943,0.006449042,0.000713935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010752906,0.0013038806,0.0017336261,0.019490344,0.0010220065,0.002962943,0.0017646924,0.001330425,0.0014117272],"category_scores_gemma":[0.033175275,0.00037104875,0.0022995938,0.01461304,0.0007077398,0.0023656085,0.0017693251,0.0017932908,0.0012251415],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00052183296,0.0014001087,0.11825499,0.0017403095,0.00068902754,0.00035922223,0.0023382963,0.024544721,0.0075409925,0.0075673712,0.0034787487,0.8315644],"study_design_scores_gemma":[0.00013496962,0.0011098314,0.08950378,0.00058919995,0.00047102384,0.0013782666,0.002844888,0.79844874,0.036322467,0.036471654,0.032472923,0.00025226615],"about_ca_topic_score_codex":0.008046167,"about_ca_topic_score_gemma":0.008214987,"teacher_disagreement_score":0.019490344,"about_ca_system_score_codex":0.001487836,"about_ca_system_score_gemma":0.0030757221,"threshold_uncertainty_score":0.05686748},"labels":[],"label_agreement":null},{"id":"W2464257012","doi":"10.1007/s10985-016-9372-1","title":"$$L_1$$ L 1 splitting rules in survival forests","year":2016,"lang":"en","type":"article","venue":"Lifetime Data Analysis","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Rank (graph theory); Log-rank test; Statistics; Mathematics; Hazard; Function (biology); Survival analysis; Survival function; Hazard ratio; Data mining; Computer science; Combinatorics; Biology; Confidence interval; Ecology","score_opus":0.03476203151519272,"score_gpt":0.29773644473008115,"score_spread":0.26297441321488846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2464257012","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11135042,0.00086226343,0.8767093,0.0010215213,0.00020112924,0.00018184433,0.0016058017,0.00095491024,0.0071127852],"genre_scores_gemma":[0.603874,0.00044989077,0.3828705,0.00047907385,0.0002101976,0.00029377983,0.004286361,0.00034618567,0.00718993],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983057,0.0005808785,0.00016172079,0.00035607748,0.0003953746,0.00020029148],"domain_scores_gemma":[0.99299014,0.004804823,0.00029066156,0.00078234344,0.0008654222,0.0002667029],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042039203,0.0004012656,0.0008431797,0.0013741362,0.0011147058,0.0013692126,0.0017561058,0.00105615,0.005383952],"category_scores_gemma":[0.014471752,0.00037055224,0.0007889272,0.0012854757,0.00071983546,0.002646849,0.0010632459,0.0018212091,0.0017949911],"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":[0.000461665,0.00035508728,0.022433251,0.00030985,0.00012966801,0.00035017641,0.00040806108,0.0929353,0.003630058,0.086540796,0.022720244,0.76972586],"study_design_scores_gemma":[0.000040875908,0.00011448603,0.0033048699,0.00013932915,0.000098982506,0.00044188736,0.00020673605,0.69585943,0.0034634706,0.28641328,0.009884244,0.000032331835],"about_ca_topic_score_codex":0.0022857678,"about_ca_topic_score_gemma":0.0048028645,"teacher_disagreement_score":0.005383952,"about_ca_system_score_codex":0.0005586301,"about_ca_system_score_gemma":0.0010888568,"threshold_uncertainty_score":0.022232711},"labels":[],"label_agreement":null},{"id":"W2471483531","doi":"10.1007/978-3-540-87563-5_6","title":"On Reduct Construction Algorithms","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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":"University of Regina","funders":"","keywords":"Reduct; Computer science; Heuristics; Selection (genetic algorithm); Algorithm; Data mining; Rough set; Artificial intelligence","score_opus":0.019239655574859082,"score_gpt":0.2498058758665991,"score_spread":0.23056622029174004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2471483531","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007092805,0.002840968,0.9530535,0.0017617368,0.0005419849,0.00020186396,0.00062921736,0.002688318,0.031189661],"genre_scores_gemma":[0.07608454,0.0030409328,0.88281,0.0012327046,0.00087417394,0.0005035587,0.004530499,0.0021683925,0.028755141],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9950119,0.0015646053,0.0003102127,0.0010529915,0.001706834,0.00035343642],"domain_scores_gemma":[0.98914975,0.0060518314,0.00022079088,0.0035768023,0.0008182851,0.00018260322],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039722663,0.002250407,0.0030199443,0.004174605,0.002525147,0.0043351334,0.004440784,0.0024289237,0.020007677],"category_scores_gemma":[0.019313358,0.0019396233,0.004618869,0.0072864145,0.0036100054,0.010904266,0.0074662566,0.009001476,0.0075412435],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022336052,0.00022356106,0.00086715206,0.0004137604,0.00012480031,0.00010596979,0.0003450994,0.027545556,0.001151005,0.49364266,0.05123325,0.42412382],"study_design_scores_gemma":[0.000035653593,0.000033514,0.00023367941,0.00011127408,0.00006540667,0.00015546274,0.000062602354,0.06770188,0.0010849743,0.90596783,0.02452724,0.00002056174],"about_ca_topic_score_codex":0.0022300517,"about_ca_topic_score_gemma":0.002695479,"teacher_disagreement_score":0.020007677,"about_ca_system_score_codex":0.002144459,"about_ca_system_score_gemma":0.002047293,"threshold_uncertainty_score":0.06693232},"labels":[],"label_agreement":null},{"id":"W2477236565","doi":"10.4018/978-1-60566-404-0.ch009","title":"Variations on Associative Classifiers and Classification Results Analyses","year":2009,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Associative property; Computer science; Classifier (UML); Artificial intelligence; Association rule learning; Data mining; Machine learning; Graph; Pattern recognition (psychology); Theoretical computer science; Mathematics","score_opus":0.07568926248331499,"score_gpt":0.32504453137998585,"score_spread":0.24935526889667087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2477236565","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018310857,0.009528346,0.95924246,0.0011762755,0.0006419528,0.00024591683,0.00041602386,0.001542578,0.025375372],"genre_scores_gemma":[0.04957925,0.016453527,0.8968757,0.0018329311,0.00298459,0.0009257341,0.0017719801,0.0010774732,0.0284988],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9852297,0.0037068753,0.0016150122,0.0023379235,0.006703954,0.00040654538],"domain_scores_gemma":[0.9806442,0.013207641,0.0007209525,0.0023231462,0.0029118117,0.0001923103],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008621688,0.0022678669,0.0018742613,0.008630516,0.001131709,0.006506075,0.0041091116,0.0023340685,0.014404774],"category_scores_gemma":[0.02741587,0.0010294719,0.0028852772,0.015811162,0.0027034534,0.012083554,0.0032379508,0.004154174,0.007951487],"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":[0.000096169395,0.00015711378,0.0016148515,0.0008955472,0.00020630426,0.00025291299,0.00064422976,0.009724889,0.001219366,0.33966124,0.03610059,0.6094268],"study_design_scores_gemma":[0.00002744836,0.00007827816,0.001353934,0.0006457585,0.00015837132,0.0011410033,0.00018749556,0.08309529,0.0035533272,0.6681913,0.2414487,0.0001190539],"about_ca_topic_score_codex":0.0016099326,"about_ca_topic_score_gemma":0.00151388,"teacher_disagreement_score":0.014404774,"about_ca_system_score_codex":0.0019411573,"about_ca_system_score_gemma":0.0013020178,"threshold_uncertainty_score":0.048188746},"labels":[],"label_agreement":null},{"id":"W2479777807","doi":"10.4018/978-1-59904-162-9.ch002","title":"Bi-Directional Constraint Pushing in Frequent Pattern Mining","year":2008,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Association rule learning; Constraint (computer-aided design); Data mining; Key (lock); Affinity analysis; Process (computing); Resource (disambiguation); Contrast (vision); Component (thermodynamics); Eclipse; Artificial intelligence; Engineering","score_opus":0.028249108554566554,"score_gpt":0.250031105727978,"score_spread":0.22178199717341143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2479777807","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029548444,0.00855448,0.975971,0.0011426191,0.00033126518,0.00022517171,0.00053294556,0.0007659653,0.0095217675],"genre_scores_gemma":[0.026061472,0.0075960504,0.95628536,0.00042548953,0.00030530815,0.00045015628,0.0011954112,0.00023359369,0.0074472404],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99623543,0.001119377,0.00042011164,0.00065265823,0.001425963,0.0001465536],"domain_scores_gemma":[0.9925289,0.005333033,0.0002990901,0.0009693423,0.00072500226,0.00014452891],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004150079,0.0015862219,0.001601616,0.0028484182,0.0010686406,0.0035455732,0.0033670382,0.0017171631,0.007427308],"category_scores_gemma":[0.013944239,0.0014567073,0.0016750508,0.009968415,0.0012479674,0.00577746,0.0025892227,0.0035406929,0.0063197613],"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":[0.00019883212,0.00014136374,0.0012499308,0.001677682,0.00012888695,0.00056552154,0.00033444952,0.034779422,0.003450761,0.117454246,0.03150405,0.80851483],"study_design_scores_gemma":[0.0000689518,0.0001439344,0.0010167924,0.0006603937,0.000097047705,0.0020072483,0.0002660402,0.38751334,0.00685093,0.41623715,0.1850127,0.00012545881],"about_ca_topic_score_codex":0.0012392133,"about_ca_topic_score_gemma":0.0011007293,"teacher_disagreement_score":0.007427308,"about_ca_system_score_codex":0.0008384278,"about_ca_system_score_gemma":0.0013618538,"threshold_uncertainty_score":0.024846792},"labels":[],"label_agreement":null},{"id":"W2481352207","doi":"10.4018/978-1-4666-0330-1.ch013","title":"Using Association Rules for Query Reformulation","year":2012,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Université du Québec à Trois-Rivières","funders":"","keywords":"Association rule learning; Computer science; Focus (optics); Information retrieval; Association (psychology); Process (computing); Data mining; Volume (thermodynamics); Psychology","score_opus":0.05025205466753676,"score_gpt":0.294768826921094,"score_spread":0.24451677225355725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2481352207","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007143746,0.0031444717,0.9705531,0.0015706645,0.0002920426,0.00039356458,0.0005051985,0.0037265373,0.012670746],"genre_scores_gemma":[0.100611046,0.003083089,0.88159764,0.00087987265,0.00034739487,0.00037566767,0.002269399,0.0007271657,0.010108654],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99203753,0.0027839202,0.00073477696,0.001193798,0.0028789006,0.0003711092],"domain_scores_gemma":[0.99065876,0.0052795284,0.000496434,0.002202295,0.0012372568,0.00012565473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006116656,0.0012002194,0.001536981,0.0037258181,0.0010631755,0.004823453,0.0026969572,0.0012362435,0.012035475],"category_scores_gemma":[0.021432921,0.0007671542,0.0019965142,0.004048808,0.0015725483,0.009157937,0.002601189,0.0022974734,0.007267637],"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":[0.00033989467,0.00026006147,0.0014406816,0.0008362465,0.00023168548,0.00089161267,0.0011869007,0.014583578,0.009968409,0.20356677,0.029916937,0.7367773],"study_design_scores_gemma":[0.00016146444,0.0002474151,0.0009414168,0.00048538082,0.0004012345,0.002473539,0.00088733487,0.29541424,0.033736117,0.38146684,0.2835924,0.00019262367],"about_ca_topic_score_codex":0.0026109868,"about_ca_topic_score_gemma":0.002104946,"teacher_disagreement_score":0.012035475,"about_ca_system_score_codex":0.0011654656,"about_ca_system_score_gemma":0.0013112256,"threshold_uncertainty_score":0.0402627},"labels":[],"label_agreement":null},{"id":"W2481557120","doi":"10.1093/comjnl/bxp010","title":"KRZYSZTOF J. CIOS, WITOLD PEDRYCZ, ROMAN W. SWINIARSKI and LUKASZ A. KURGAN * Data Mining: A Knowledge Discovery Approach. Springer * ((2007)). ISBN: 978-0387333335.  55.99. 606 pp. Hardcover.","year":2009,"lang":"en","type":"article","venue":"The Computer Journal","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Library science; Volume (thermodynamics); Computer science; Physics","score_opus":0.033576470382070456,"score_gpt":0.2682279704166801,"score_spread":0.23465150003460966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2481557120","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0055613625,0.6738257,0.054469194,0.05809603,0.018506512,0.0004387674,0.005348496,0.0019542365,0.1817998],"genre_scores_gemma":[0.013739054,0.61443627,0.025459968,0.005342944,0.008356977,0.00018962461,0.0046265214,0.0009822149,0.32686645],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99888474,0.00008631098,0.000075034644,0.00017983539,0.0007146747,0.000059435344],"domain_scores_gemma":[0.99778336,0.00094582204,0.00026533531,0.000095740426,0.00055726914,0.0003524427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011125003,0.0012928717,0.0015155807,0.004271109,0.00057084544,0.0037612251,0.0009888813,0.0008875858,0.08297981],"category_scores_gemma":[0.004868658,0.00052649766,0.00058045646,0.005753988,0.0011372935,0.005570527,0.0016591216,0.0020660874,0.086494416],"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":[0.00009975458,0.00003951894,0.00034188616,0.0015794692,0.000023240164,0.00021285971,0.00017313079,0.00022823797,0.0012283371,0.0047526574,0.729384,0.26193693],"study_design_scores_gemma":[0.000012411591,0.000028990136,0.0011671466,0.00053963007,0.000025064932,0.0015016117,0.00012846562,0.0002936815,0.0008737961,0.0067423377,0.98865616,0.000030708026],"about_ca_topic_score_codex":0.0011447105,"about_ca_topic_score_gemma":0.0018049722,"teacher_disagreement_score":0.08297981,"about_ca_system_score_codex":0.00080074294,"about_ca_system_score_gemma":0.00094918674,"threshold_uncertainty_score":0.2775951},"labels":[],"label_agreement":null},{"id":"W2482088207","doi":"10.1007/978-3-319-40581-0_31","title":"Computing Theoretically-Sound Upper Bounds to Expected Support for Frequent Pattern Mining Problems over Uncertain Big Data","year":2016,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Data Mining Algorithms and Applications","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 Manitoba","funders":"","keywords":"Computer science; Data mining; Uncertain data; Probabilistic logic; Database transaction; Big data; Upper and lower bounds; Tree (set theory); Transaction data; Artificial intelligence; Mathematics; Database","score_opus":0.09379594328863143,"score_gpt":0.33280221958336237,"score_spread":0.23900627629473092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2482088207","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025027892,0.00453871,0.9590544,0.003296523,0.00047642333,0.0001177108,0.00084422086,0.00093967025,0.0057045785],"genre_scores_gemma":[0.49811995,0.005624486,0.48126623,0.0016651719,0.002958262,0.0008252228,0.0033273802,0.0009097818,0.0053034523],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9881903,0.003855633,0.0007483223,0.0018295681,0.004222769,0.0011534931],"domain_scores_gemma":[0.84028727,0.14305566,0.0030637349,0.0073060887,0.004323679,0.001963598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013514904,0.0030442523,0.0042113326,0.0029598568,0.001423879,0.008987272,0.005966061,0.0034997184,0.007909536],"category_scores_gemma":[0.13460867,0.002152871,0.0030291495,0.004095298,0.004261991,0.013873658,0.0067837574,0.010347174,0.0017966167],"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":[0.0014878402,0.00040993976,0.0034454807,0.001260751,0.00038420016,0.00028197313,0.00051956135,0.5004977,0.0031933906,0.29591706,0.017666375,0.1749358],"study_design_scores_gemma":[0.000044051307,0.00008089374,0.00025303898,0.00011191435,0.000033164135,0.00009211803,0.00006176137,0.6262113,0.0009033859,0.37101343,0.0011701251,0.000024755596],"about_ca_topic_score_codex":0.0011195377,"about_ca_topic_score_gemma":0.0014167238,"teacher_disagreement_score":0.013514904,"about_ca_system_score_codex":0.0037988254,"about_ca_system_score_gemma":0.0035011072,"threshold_uncertainty_score":0.07147449},"labels":[],"label_agreement":null},{"id":"W2482880346","doi":"10.2495/dne-v11-n3-178-185","title":"Extraction of association rules using big data technologies","year":2016,"lang":"en","type":"article","venue":"International Journal of Design & Nature and Ecodynamics","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Junta de Andalucía; European Commission","keywords":"Association rule learning; Association (psychology); Big data; Data association; Computer science; Data mining; Data science; Engineering; Artificial intelligence; Psychology","score_opus":0.04016348812847336,"score_gpt":0.3048546425371829,"score_spread":0.26469115440870955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2482880346","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018355198,0.0011627267,0.9691253,0.0007432765,0.0002825474,0.0007505889,0.0029393374,0.003636745,0.003004342],"genre_scores_gemma":[0.065690614,0.0015196562,0.92430127,0.00021851233,0.00015457784,0.0005833198,0.0062202266,0.000120983255,0.0011908968],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99462163,0.00096367043,0.001141531,0.0009221129,0.0021204674,0.0002305236],"domain_scores_gemma":[0.98751813,0.0062225224,0.0012419925,0.0019915765,0.0027993566,0.000226392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003468079,0.0016411985,0.0026019847,0.012400504,0.0013718943,0.004732585,0.001865458,0.0012667925,0.002861643],"category_scores_gemma":[0.02070777,0.00095278304,0.0027948536,0.009216574,0.0005509749,0.0035186552,0.0019612787,0.0019798554,0.0028743027],"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":[0.00030275126,0.00057917717,0.011862453,0.0012529582,0.00071767165,0.003050423,0.0004954159,0.03541103,0.015472692,0.0160998,0.012986366,0.9017692],"study_design_scores_gemma":[0.00022254833,0.0005120833,0.011010571,0.0006923239,0.00085742195,0.004797589,0.0013680705,0.70171016,0.04804808,0.15056594,0.07996689,0.00024840323],"about_ca_topic_score_codex":0.0018655395,"about_ca_topic_score_gemma":0.0020500587,"teacher_disagreement_score":0.012400504,"about_ca_system_score_codex":0.00055070216,"about_ca_system_score_gemma":0.0028920004,"threshold_uncertainty_score":0.018341184},"labels":[],"label_agreement":null},{"id":"W2483382222","doi":"10.4018/978-1-4666-2455-9.ch042","title":"Heterogeneous Text and Numerical Data Mining with Possible Applications in Business and Financial Sectors","year":2012,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Data science; Data type; Semantics (computer science); Qualitative property; Data processing; Financial sector; Database; Finance; Business; Programming language; Machine learning","score_opus":0.023807763411946896,"score_gpt":0.247941566638982,"score_spread":0.2241338032270351,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2483382222","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009869715,0.110180035,0.70867527,0.003969937,0.0021645115,0.00031600337,0.0027273572,0.0017106016,0.16038658],"genre_scores_gemma":[0.049408894,0.061783288,0.7715675,0.0017990029,0.0019142105,0.00037520446,0.0057532964,0.0006911637,0.10670734],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99936527,0.00011369143,0.00004848938,0.00016210656,0.00028336263,0.000026992444],"domain_scores_gemma":[0.99923754,0.00050996814,0.00003812754,0.00007422897,0.00010469421,0.000035459754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012106835,0.0008556682,0.0008138399,0.0033188548,0.0006708011,0.002856117,0.0015423894,0.0007431223,0.012299958],"category_scores_gemma":[0.0021500334,0.00043117563,0.0009439465,0.0096058585,0.00083994685,0.0041109775,0.0013166787,0.0013631462,0.0049150377],"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":[0.00006381244,0.000112226975,0.00081433996,0.0015102286,0.000052287436,0.0004502432,0.0006365456,0.00345922,0.0044963267,0.24858002,0.06316458,0.6766602],"study_design_scores_gemma":[0.000016766646,0.000035580193,0.0017193253,0.0010711523,0.000062175335,0.0012304467,0.0003577727,0.019156158,0.0042665885,0.32598397,0.6460517,0.00004847053],"about_ca_topic_score_codex":0.0005348363,"about_ca_topic_score_gemma":0.0010438716,"teacher_disagreement_score":0.012299958,"about_ca_system_score_codex":0.00071386644,"about_ca_system_score_gemma":0.00075075135,"threshold_uncertainty_score":0.04114747},"labels":[],"label_agreement":null},{"id":"W2484751293","doi":"10.1007/978-81-322-1952-1","title":"Mathematics and Computing 2013","year":2014,"lang":"en","type":"book","venue":"Springer proceedings in mathematics & statistics","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"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":"Sobolev Institute of Mathematics, Siberian Branch, Russian Academy of Sciences; Russian Academy of Sciences; Institute for Infocomm Research; University of Mysore; Indian Institute of Technology Guwahati; Indian Institute of Science Education and Research Mohali; Indian Institute of Technology Indore; Council of Scientific and Industrial Research, India; Indian Institute of Science; Indian Institute of Technology Kharagpur; Indian Institute of Technology Kanpur; University of Hyderabad; Université de Rouen; Indian Institute of Technology Delhi; South China Normal University; Indian Institute of Technology, Patna; Universidad de Granada; Università Politecnica delle Marche; University of Texas at Arlington; Universidade de Coimbra; Jadavpur University; Nanyang Technological University; University of Delhi; Sungkyunkwan University; National Board for Higher Mathematics; Tsinghua University; Haldia Institute of Technology; International Institute of Information Technology, Hyderabad; Aalborg Universitet; Uppsala Universitet; Defence Research and Development Organisation; Indian Institute of Technology Madras; Australian National University; York University; Massachusetts Institute of Technology; Washington University in St. Louis; Jawaharlal Nehru University; Chalmers Tekniska Högskola; Concordia University; Department of Science and Technology, Ministry of Science and Technology, India; Universidad de Alicante; National University of Singapore; Universität Ulm; University of Canterbury; Athabasca University; University of Oklahoma; Purdue University; Ministry of Communication and Information Technology; Auburn University; University of Central Florida; Tata Institute of Fundamental Research; Ostravská Univerzita v Ostravě; National Institute of Advanced Industrial Science and Technology; Politechnika Warszawska; Harish-Chandra Research Institute","keywords":"Mathematics education; Computer science; Mathematics","score_opus":0.014841339043127993,"score_gpt":0.2506302071875832,"score_spread":0.23578886814445524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2484751293","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017325545,0.06680016,0.053129755,0.010988217,0.010272356,0.000081256294,0.0015255613,0.001530065,0.85394],"genre_scores_gemma":[0.018300498,0.037827544,0.011834941,0.0009969907,0.003708308,0.0001600107,0.0012164274,0.00083222875,0.9251231],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992849,0.000084189305,0.00003768074,0.00017503905,0.0003688681,0.00004929826],"domain_scores_gemma":[0.99918896,0.00019813052,0.000043791086,0.00023483636,0.00023643095,0.000097828466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065704377,0.001346792,0.0015884329,0.0023387603,0.0014473874,0.005637376,0.0010533149,0.0009590983,0.14775409],"category_scores_gemma":[0.0025382217,0.00067766075,0.00063816033,0.005049384,0.0016486705,0.0042861397,0.002393165,0.0028947874,0.09010005],"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":[0.00002023527,0.00002523164,0.00018576995,0.00031749092,0.000018366476,0.000029739127,0.00010475173,0.0010747275,0.0004842456,0.17289607,0.46483663,0.3600069],"study_design_scores_gemma":[0.000004982017,0.000011808014,0.000479501,0.00017310165,0.000015006345,0.00012360804,0.00006043636,0.001517502,0.00023474904,0.12008866,0.8772785,0.000012136456],"about_ca_topic_score_codex":0.0024293626,"about_ca_topic_score_gemma":0.0052464786,"teacher_disagreement_score":0.14775409,"about_ca_system_score_codex":0.0026507138,"about_ca_system_score_gemma":0.0024950504,"threshold_uncertainty_score":0.49428666},"labels":[],"label_agreement":null},{"id":"W2488192133","doi":"10.4018/978-1-59140-557-3.ch224","title":"Visualization Techniques for Data Mining","year":2005,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"","keywords":"Computer science; Knowledge extraction; Data mining; Association rule learning; Data science; Cluster analysis; Visualization; K-optimal pattern discovery; The Internet; Data stream mining; Decision tree; Data warehouse; Machine learning; World Wide Web","score_opus":0.05181101400554882,"score_gpt":0.3255916050696682,"score_spread":0.2737805910641194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2488192133","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009589095,0.039722912,0.9062576,0.0033546146,0.0012308985,0.0003597588,0.0025949043,0.01319646,0.032323956],"genre_scores_gemma":[0.022410925,0.033390827,0.91802907,0.0010185255,0.0010370902,0.0009881188,0.0058057304,0.0016751945,0.015644573],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960478,0.0013627716,0.00040166278,0.00048404036,0.0015834441,0.000120207354],"domain_scores_gemma":[0.9957338,0.0024748144,0.00023612108,0.0006992094,0.0007556847,0.00010043685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038662436,0.0028560357,0.0018967395,0.0060975994,0.0009138811,0.0062161325,0.0032240683,0.0022587455,0.033149518],"category_scores_gemma":[0.0107946545,0.0009824604,0.0017260251,0.010906698,0.0012165948,0.005814199,0.003184487,0.0027981873,0.015120733],"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":[0.00007526359,0.000077691526,0.0006181778,0.0026155044,0.00021840764,0.00028830578,0.0005880734,0.010712386,0.0019060893,0.15079986,0.1733843,0.65871596],"study_design_scores_gemma":[0.000055808905,0.000038827842,0.00055602484,0.00078828685,0.000063739906,0.0006382917,0.00024939145,0.04456213,0.0016608831,0.3481615,0.6031529,0.00007220611],"about_ca_topic_score_codex":0.0016578498,"about_ca_topic_score_gemma":0.001618408,"teacher_disagreement_score":0.033149518,"about_ca_system_score_codex":0.0010659483,"about_ca_system_score_gemma":0.0012502683,"threshold_uncertainty_score":0.11089617},"labels":[],"label_agreement":null},{"id":"W2488195700","doi":"10.4018/978-1-59904-960-1.ch001","title":"OLEMAR","year":2008,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec","funders":"","keywords":"Online analytical processing; Data cube; Computer science; Association rule learning; Aggregate (composite); Data warehouse; Data mining; Granularity; Information retrieval; Representation (politics); Data science","score_opus":0.022078236275676184,"score_gpt":0.24478771356347737,"score_spread":0.2227094772878012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2488195700","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005917819,0.0022421347,0.17612997,0.0034919463,0.001371338,0.0007765196,0.05292916,0.21611914,0.54102206],"genre_scores_gemma":[0.05349325,0.003677748,0.13893083,0.0030926636,0.00064477883,0.0013806063,0.14675497,0.051942624,0.6000826],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975107,0.00029950967,0.00021179779,0.0006061824,0.0010277317,0.00034408385],"domain_scores_gemma":[0.99686843,0.0005253069,0.0001914678,0.0011855498,0.00088423194,0.00034500178],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019644678,0.0016776761,0.0012570418,0.00286491,0.0014428735,0.007122019,0.0036145414,0.002302473,0.36057132],"category_scores_gemma":[0.006262512,0.0011284971,0.0016224125,0.003262203,0.0007360967,0.007371727,0.0067336173,0.0022016997,0.33528537],"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":[0.0007630506,0.00020883445,0.0014349705,0.0011164071,0.00007226595,0.00043527185,0.00047982638,0.0019379575,0.0065890024,0.049864143,0.5194263,0.41767198],"study_design_scores_gemma":[0.000050725128,0.000052619827,0.00045593947,0.00010768055,0.000017816319,0.0002370318,0.000086874905,0.00187776,0.0026411216,0.009662771,0.98477304,0.00003651636],"about_ca_topic_score_codex":0.0020688884,"about_ca_topic_score_gemma":0.0017989923,"teacher_disagreement_score":0.6394287,"about_ca_system_score_codex":0.0010884322,"about_ca_system_score_gemma":0.002044378,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W2488257995","doi":"10.1007/978-3-319-41920-6_30","title":"Building FP-Tree on the Fly: Single-Pass Frequent Itemset Mining","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Tree (set theory); On the fly; Data mining; GSP Algorithm; Database transaction; Fractal tree index; Interval tree; Trie; Tree structure; Apriori algorithm; Algorithm; Association rule learning; Data structure; Database; Binary tree; Mathematics","score_opus":0.030963937685589558,"score_gpt":0.25509422646294105,"score_spread":0.2241302887773515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2488257995","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07954774,0.0035227798,0.8924223,0.0006836261,0.0004923627,0.0005436106,0.007822735,0.012262664,0.0027022096],"genre_scores_gemma":[0.16429262,0.0010907102,0.8156312,0.00022638988,0.00017333003,0.00027976008,0.015009415,0.00039003312,0.002906467],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99805427,0.00021452366,0.00027151714,0.00058302487,0.0006563316,0.00022044021],"domain_scores_gemma":[0.9964939,0.0016354843,0.00020692083,0.0005689539,0.00092750165,0.00016726273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018462288,0.0017472658,0.0033958603,0.0044330033,0.001317683,0.0023789825,0.0038813795,0.0022915658,0.004736466],"category_scores_gemma":[0.007965468,0.0009364697,0.0021152897,0.006252665,0.00032952256,0.0035527288,0.0013632729,0.0015046607,0.0054374104],"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":[0.00059753493,0.00042994582,0.00783749,0.0005985621,0.0003316593,0.0005942548,0.00015660105,0.011962576,0.009768544,0.001511966,0.025336996,0.9408739],"study_design_scores_gemma":[0.00013697518,0.0006800059,0.006369765,0.00016632205,0.0004407106,0.0034890354,0.00042210508,0.93059546,0.02080351,0.019628488,0.017159905,0.00010770517],"about_ca_topic_score_codex":0.004363511,"about_ca_topic_score_gemma":0.0062569506,"teacher_disagreement_score":0.004736466,"about_ca_system_score_codex":0.00044215634,"about_ca_system_score_gemma":0.0022898319,"threshold_uncertainty_score":0.015845},"labels":[],"label_agreement":null},{"id":"W2491486088","doi":"10.4018/978-1-5225-0489-4.ch009","title":"Association Rule Mining in Collaborative Filtering","year":2016,"lang":"en","type":"book-chapter","venue":"Advances in data mining and database management book series","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Association rule learning; Data mining; Computer science; Bitwise operation; Collaborative filtering; Association (psychology); Information retrieval; Operator (biology); Recommender system","score_opus":0.018185279117046076,"score_gpt":0.26813372462202434,"score_spread":0.24994844550497827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2491486088","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011676314,0.01514047,0.95913386,0.0017545004,0.0006530436,0.00020819467,0.0003116877,0.000856559,0.020774],"genre_scores_gemma":[0.038389064,0.021514043,0.9077754,0.0016348036,0.0016559586,0.000781266,0.001442159,0.00022251876,0.026584735],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9913628,0.0034642718,0.00065402675,0.0017220089,0.00257871,0.00021817103],"domain_scores_gemma":[0.9908903,0.0060430914,0.00044456156,0.0013420297,0.0011509549,0.00012899264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006955418,0.0015432672,0.0022954906,0.005135507,0.0013449494,0.0050567156,0.0033000815,0.0034228684,0.013763897],"category_scores_gemma":[0.017610056,0.001023449,0.0019325358,0.008648269,0.0024606006,0.0070563913,0.0026884535,0.0033525643,0.008920599],"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":[0.00009493534,0.00016457948,0.0010531736,0.0013281954,0.00027462488,0.0005406844,0.00052447704,0.026214764,0.0014637249,0.38285136,0.044457793,0.54103166],"study_design_scores_gemma":[0.00005164751,0.00012678385,0.00077150034,0.0007142482,0.00011830883,0.0013291263,0.00022028327,0.14377038,0.0025860786,0.55782807,0.29235366,0.00012987576],"about_ca_topic_score_codex":0.0025514972,"about_ca_topic_score_gemma":0.0017826146,"teacher_disagreement_score":0.013763897,"about_ca_system_score_codex":0.0018106074,"about_ca_system_score_gemma":0.0018529191,"threshold_uncertainty_score":0.046044827},"labels":[],"label_agreement":null},{"id":"W2492107376","doi":"10.1007/978-3-030-67658-2","title":"Machine Learning and Knowledge Discovery in Databases","year":2021,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Computing Technology, Chinese Academy of Sciences; Télécom Paris; University of California, Davis; École Normale Supérieure de Lyon; University of Illinois at Urbana-Champaign; LG Electronics; Technische Universität Dortmund; Sabancı Üniversitesi; ITMO University; University of Chinese Academy of Sciences; Ryukoku University; Universität Konstanz; Eötvös Loránd Tudományegyetem; Stockholms Universitet; Xiamen University; Università della Calabria; Singapore University of Technology and Design; Technische Universität Berlin; Indian Institute of Technology Guwahati; Universidade do Porto; Samsung; Universidade Estadual de Campinas; Nanjing University; Indian Institute of Technology Bombay; Università degli Studi dell'Aquila; Ludwig-Maximilians-Universität München; Shanghai Jiao Tong University; Rheinische Friedrich-Wilhelms-Universität Bonn; Vrije Universiteit Brussel; Westfälische Wilhelms-Universität Münster; Shanghai University of Finance and Economics; Universidade Federal de Uberlândia; Centre National de la Recherche Scientifique; Universidade de Macau; Dartmouth College; University of Tokyo; University of Rochester; Zhengzhou University; Institut \"Jožef Stefan\"; Waseda University; Universiteit Gent; Sorbonne Université; Kungliga Tekniska Högskolan; University of Warwick; Indian Institute of Technology Madras; Johns Hopkins University; Harbin Institute of Technology; Université de Namur; Institut National de Recherche pour l'Agriculture, l'Alimentation et l'Environnement; Universität Wien; Heinrich-Heine-Universität Düsseldorf; Eidgenössische Technische Hochschule Zürich; National Council for Scientific Research; University of Texas at Dallas; Zhejiang University; Aalto-Yliopisto; Università di Pisa; Universidad Autónoma de Madrid; Pohang University of Science and Technology; Beijing Institute of Technology; Fudan University; Sun Yat-sen University; University of Twente; Chongqing University; Insight SFI Research Centre for Data Analytics; Beijing Jiaotong University; Technische Universiteit Delft; University of Toronto; University of Electronic Science and Technology of China; Technische Universität Kaiserslautern; Monash University; Peking University; KU Leuven; University of New South Wales; Gottfried Wilhelm Leibniz Universität Hannover; Rijksuniversiteit Groningen; Itä-Suomen Yliopisto; Eberhard Karls Universität Tübingen; Universiteit Leiden; Umeå Universitet; Helsingin Yliopisto; Universidade Federal do Paraná; Deakin University; University of Bristol; Universidade Federal do Rio Grande do Sul; Technische Universität München; Joint Research Centre; Université d'Orléans; Institut National des Sciences Appliquées de Lyon; Tsinghua University; Chinese Academy of Sciences; Indian National Science Academy; University of Exeter; University of East Anglia; University of Adelaide; Université Grenoble Alpes; Universitat Politècnica de Catalunya; Indian Institute of Technology Kanpur; University of Waikato; Florida State University; Universidade de Coimbra; Oregon State University; University of Queensland; Emory University; Polytechnique Montréal; Universidad de Alicante; Leuphana Universität Lüneburg; Toyota Research Institute; Politecnico di Torino; Universität Kassel; Case Western Reserve University; Institut National Polytechnique de Toulouse; McGill University; Université de Lorraine; Université du Luxembourg; Philipps-Universität Marburg; Leibniz-Gemeinschaft; Pennsylvania State University; University of Oxford; Tianjin University; Universität zu Lübeck; Universiteit Utrecht; Siemens; Aarhus Universitet; Harvard University; Université de Liège; European Commission; University of Alberta; University of Science and Technology of China; Chongqing University of Posts and Telecommunications; Washington State University; University College Dublin; Technische Universiteit Eindhoven; Arizona State University; University of Tsukuba; Purdue University; University of Southern California","keywords":"Computer science; Knowledge extraction; Database; Artificial intelligence; Information retrieval","score_opus":0.01946296800861885,"score_gpt":0.28105900239993303,"score_spread":0.2615960343913142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2492107376","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004705342,0.2698931,0.5750511,0.007582169,0.0046367105,0.00031877024,0.002318876,0.0022902796,0.13320361],"genre_scores_gemma":[0.042643882,0.18408523,0.5266746,0.003033949,0.0041646142,0.00042464017,0.0057661217,0.00080265774,0.23240426],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99905103,0.00019132474,0.00008816012,0.00014750432,0.00048894895,0.000033052198],"domain_scores_gemma":[0.99751663,0.0018395991,0.000081251725,0.00026170906,0.00023927623,0.000061554565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009823649,0.0008682535,0.0016822955,0.002560055,0.0005186294,0.004126997,0.001500075,0.0008805551,0.015909273],"category_scores_gemma":[0.00438257,0.000670764,0.0008360553,0.0074161543,0.0010694417,0.0058799675,0.0014036916,0.0020690055,0.010399904],"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":[0.000059084803,0.00008111139,0.00042025035,0.001884097,0.000095263546,0.00014251983,0.00015354792,0.004351757,0.001184727,0.15087491,0.14449774,0.69625497],"study_design_scores_gemma":[0.00002681259,0.000044618002,0.00080582965,0.000621547,0.000074316726,0.00085684576,0.00010670791,0.025263006,0.001490166,0.3681239,0.60255545,0.00003065603],"about_ca_topic_score_codex":0.00081793516,"about_ca_topic_score_gemma":0.00078846794,"teacher_disagreement_score":0.015909273,"about_ca_system_score_codex":0.00080304645,"about_ca_system_score_gemma":0.0008977683,"threshold_uncertainty_score":0.05322188},"labels":[],"label_agreement":null},{"id":"W2497002025","doi":"10.1142/9789812709677_0017","title":"DISCOVERING MAXIMIZED PROGRESSIVE HIGH-ORDER PATTERNS IN BIOSEQUENCES","year":2007,"lang":"en","type":"book-chapter","venue":"WORLD SCIENTIFIC eBooks","topic":"Data Mining Algorithms and Applications","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 Guelph","funders":"","keywords":"Order (exchange); Computer science; Business","score_opus":0.0373604109659835,"score_gpt":0.27092128412427996,"score_spread":0.23356087315829646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2497002025","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55807877,0.0013656196,0.4283799,0.00065260474,0.00007492228,0.0001495644,0.0032348963,0.0017483457,0.0063154222],"genre_scores_gemma":[0.7646914,0.0006868534,0.22541837,0.00014576688,0.00009022793,0.00009919915,0.004298809,0.0002785489,0.00429074],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994887,0.000060503982,0.000050896626,0.00016531115,0.00016884273,0.00006569393],"domain_scores_gemma":[0.99673945,0.0019025534,0.00038692768,0.00048392953,0.00032654122,0.00016068578],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058101467,0.0004556159,0.0007272218,0.002196026,0.000597289,0.0011664691,0.001046989,0.00072442007,0.002920431],"category_scores_gemma":[0.0057692,0.00048436102,0.00064542744,0.0026808952,0.0006487809,0.0020304644,0.0008625059,0.00086790125,0.000959431],"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":[0.0011608384,0.00043402024,0.06214029,0.0009982147,0.00021615882,0.0032990207,0.0010571309,0.054285645,0.07254274,0.0476452,0.010755611,0.7454651],"study_design_scores_gemma":[0.00010669936,0.00038155963,0.028005863,0.00016555861,0.00019007255,0.004029954,0.00069664104,0.7084972,0.036978915,0.20691094,0.01396795,0.000068679125],"about_ca_topic_score_codex":0.0014119161,"about_ca_topic_score_gemma":0.0027076143,"teacher_disagreement_score":0.002920431,"about_ca_system_score_codex":0.0004741295,"about_ca_system_score_gemma":0.0008088089,"threshold_uncertainty_score":0.009769797},"labels":[],"label_agreement":null},{"id":"W2500152818","doi":"10.1145/2851613.2851884","title":"Efficient closed high-utility itemset mining","year":2016,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Closure (psychology); Database transaction; Tree (set theory); State (computer science); Data mining; Projection (relational algebra); Algorithm; Theoretical computer science; Database; Mathematics","score_opus":0.01745010952650251,"score_gpt":0.24319300988444942,"score_spread":0.22574290035794692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2500152818","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046709392,0.0009845347,0.94829136,0.00013811076,0.0000433061,0.0002804198,0.0008584006,0.0016797805,0.0010147395],"genre_scores_gemma":[0.33408645,0.0005980774,0.6588883,0.00012912725,0.00005276481,0.0003204182,0.004104769,0.00015576625,0.001664289],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974451,0.00046787615,0.0003158497,0.00042718064,0.0011115778,0.00023256757],"domain_scores_gemma":[0.9946143,0.0024787933,0.0004755893,0.0009346351,0.0012855456,0.00021118161],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019911116,0.0008959097,0.0019709761,0.004427207,0.0011918503,0.0019397921,0.0028243314,0.00075404556,0.0012942867],"category_scores_gemma":[0.009682719,0.00068892643,0.0011595306,0.0055778013,0.0006608416,0.003327769,0.0023875227,0.0012374441,0.00093575084],"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":[0.0007178449,0.00043321587,0.01736916,0.0007476499,0.0002593411,0.001096504,0.00046128262,0.066787235,0.014565792,0.02002206,0.0076041515,0.86993587],"study_design_scores_gemma":[0.000060667135,0.00021052767,0.0030381335,0.00010136577,0.00008315194,0.0013346438,0.00027182561,0.9290632,0.016441979,0.04253669,0.0068079364,0.000049965136],"about_ca_topic_score_codex":0.0015121707,"about_ca_topic_score_gemma":0.0022675854,"teacher_disagreement_score":0.004427207,"about_ca_system_score_codex":0.00057099777,"about_ca_system_score_gemma":0.0018165385,"threshold_uncertainty_score":0.010530114},"labels":[],"label_agreement":null},{"id":"W2500377098","doi":"10.1137/1.9781611972740","title":"Proceedings of the 2004 SIAM International Conference on Data Mining","year":2004,"lang":"en","type":"paratext","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":147,"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":"Computer science; Library science; Data science","score_opus":0.07677233096175941,"score_gpt":0.31902827805591116,"score_spread":0.24225594709415177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2500377098","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027319023,0.029117247,0.7381778,0.044544015,0.03678926,0.00090244645,0.01597961,0.019899886,0.08727072],"genre_scores_gemma":[0.06367489,0.037924692,0.3639679,0.0054415534,0.0060543143,0.0009254266,0.059674487,0.0032160676,0.45912063],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980683,0.00046663085,0.00017234054,0.0002732187,0.0009172743,0.00010233329],"domain_scores_gemma":[0.99353313,0.0017061894,0.00021279359,0.0015377371,0.0022889841,0.0007211172],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004984835,0.0014467398,0.0034872121,0.002357706,0.0012951443,0.007638634,0.002146699,0.0015271264,0.046368882],"category_scores_gemma":[0.010123901,0.0009064193,0.0011318291,0.0026602624,0.0009511848,0.003926537,0.0023025188,0.0035613582,0.03835737],"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":[0.0002611124,0.0006052517,0.0016996589,0.00031557097,0.00015527023,0.00011088697,0.00010839795,0.001898218,0.0024948095,0.005989239,0.5692426,0.41711894],"study_design_scores_gemma":[0.000113632115,0.000194416,0.003231253,0.00028783808,0.00028908454,0.0007554923,0.00022040497,0.07783562,0.008252486,0.03483553,0.8739174,0.000066828274],"about_ca_topic_score_codex":0.0040771253,"about_ca_topic_score_gemma":0.007922126,"teacher_disagreement_score":0.046368882,"about_ca_system_score_codex":0.0008182275,"about_ca_system_score_gemma":0.0033639767,"threshold_uncertainty_score":0.1551193},"labels":[],"label_agreement":null},{"id":"W2500522693","doi":"10.1142/9789812772664_0004","title":"INTEGRATED CLUSTERING FOR MICROARRAY DATA","year":2006,"lang":"en","type":"book-chapter","venue":"Science, engineering, and biology informatics","topic":"Data Mining Algorithms and Applications","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 Alberta","funders":"","keywords":"Cluster analysis; Computer science; Data mining; Artificial intelligence","score_opus":0.03330790751607329,"score_gpt":0.25740855197359414,"score_spread":0.22410064445752084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2500522693","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020116256,0.00075931277,0.9912081,0.000080586935,0.00005953634,0.000063827254,0.00065941963,0.0036550954,0.0015024698],"genre_scores_gemma":[0.019808142,0.00055471493,0.9706095,0.000083809035,0.00007522924,0.00025982532,0.004186645,0.00055904913,0.003863071],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99799275,0.0003480441,0.00013175423,0.0004999656,0.0009076407,0.000119929624],"domain_scores_gemma":[0.99858606,0.00029547757,0.000076990225,0.0005983304,0.00039297325,0.000050242612],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017391788,0.0010590728,0.0016967512,0.0027037633,0.0007869727,0.0015617217,0.0024743336,0.000881925,0.0072572683],"category_scores_gemma":[0.0033399344,0.00096364965,0.0019112581,0.0057332604,0.0004168961,0.0018531396,0.0027041403,0.0015458622,0.005524725],"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":[0.00024980842,0.00015826721,0.00101167,0.00048205454,0.00037421478,0.00011354976,0.00016274345,0.037930965,0.032400765,0.024175841,0.028438477,0.87450165],"study_design_scores_gemma":[0.000066144974,0.00016912195,0.004007303,0.00009643772,0.0002525649,0.00059822603,0.000106503285,0.6895322,0.059127346,0.14266415,0.10326776,0.0001121499],"about_ca_topic_score_codex":0.002194669,"about_ca_topic_score_gemma":0.0048429635,"teacher_disagreement_score":0.0072572683,"about_ca_system_score_codex":0.00096770853,"about_ca_system_score_gemma":0.0011755824,"threshold_uncertainty_score":0.024278045},"labels":[],"label_agreement":null},{"id":"W2504862211","doi":"10.4018/978-1-59904-951-9.ch211","title":"Toward Integrating Data Warehousing with Data Mining Techniques","year":2008,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Université du Québec en Outaouais","funders":"","keywords":"Online analytical processing; Data warehouse; Computer science; Data mining; Scope (computer science); Data cube; Multidimensional data; Association rule learning; Exploit; Projection (relational algebra); Relational database; Database; Data science; Algorithm","score_opus":0.09633206626238337,"score_gpt":0.29894542172309096,"score_spread":0.20261335546070758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2504862211","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003224403,0.0033415519,0.98190457,0.0029368731,0.0001585978,0.00013607711,0.00008936147,0.0012062527,0.007002343],"genre_scores_gemma":[0.012522104,0.0030463398,0.98158437,0.0006728201,0.00017295755,0.00010196742,0.00018386984,0.00019031574,0.0015253344],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9913543,0.002833662,0.0007337522,0.0009707005,0.0037789657,0.0003285427],"domain_scores_gemma":[0.9828683,0.00973967,0.00052288297,0.0047466885,0.0017108355,0.00041155255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015354871,0.0021729905,0.0019368837,0.005704222,0.0014209483,0.012399365,0.005485623,0.0025500245,0.0037085812],"category_scores_gemma":[0.015191789,0.002117999,0.0021384503,0.010970199,0.003077274,0.017585581,0.008782375,0.006390143,0.0049077407],"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":[0.000097877906,0.00051750237,0.00201774,0.0020244513,0.00029161398,0.0003680545,0.0015694136,0.015257782,0.006506168,0.3065246,0.009320126,0.65550464],"study_design_scores_gemma":[0.000063991436,0.00020728046,0.0011176654,0.0018827214,0.00019514917,0.00074423215,0.0012619266,0.16011384,0.0136484215,0.56925,0.25133008,0.00018481129],"about_ca_topic_score_codex":0.0017331897,"about_ca_topic_score_gemma":0.0014188964,"teacher_disagreement_score":0.015354871,"about_ca_system_score_codex":0.0013867471,"about_ca_system_score_gemma":0.0031946748,"threshold_uncertainty_score":0.08120531},"labels":[],"label_agreement":null},{"id":"W2506101519","doi":"10.1142/9789814417747_0145","title":"UAPRIORI: AN ALGORITHM FOR FINDING SEQUENTIAL PATTERNS IN PROBABILISTIC DATA","year":2012,"lang":"en","type":"book-chapter","venue":"World Scientific proceedings series on computer engineering and information science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Data mining; Computer science; Probabilistic logic; Cluster analysis; Uncertain data; Ranking (information retrieval); Machine learning; Artificial intelligence","score_opus":0.03793855793307345,"score_gpt":0.25598780613904304,"score_spread":0.2180492482059696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2506101519","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001963998,0.0003729479,0.9905131,0.00016070207,0.00007883264,0.00020174768,0.00078094134,0.0047401013,0.0011876014],"genre_scores_gemma":[0.01713542,0.00025217357,0.9783238,0.0001150964,0.000053574797,0.00037417095,0.0017767857,0.00035353837,0.0016154576],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982407,0.0003278875,0.00017941138,0.00042666376,0.0007079365,0.00011738345],"domain_scores_gemma":[0.9980938,0.0009814193,0.00017076093,0.0003250585,0.00033785362,0.00009109039],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024817265,0.001462426,0.0015106703,0.0055599157,0.0013519125,0.0024774675,0.0034063726,0.0015251639,0.00902357],"category_scores_gemma":[0.010502334,0.0011786221,0.0016611282,0.0060390495,0.0009603181,0.0048116455,0.003140999,0.0023662637,0.0043752003],"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":[0.0003511986,0.00013667395,0.002960744,0.0004539011,0.00012569877,0.00021039927,0.00026506156,0.034708764,0.0035738128,0.024682423,0.032997075,0.8995342],"study_design_scores_gemma":[0.00011019549,0.00013744886,0.0008222641,0.00012564874,0.0000615917,0.000835107,0.00012845581,0.85395575,0.007310092,0.089545585,0.046901125,0.0000667458],"about_ca_topic_score_codex":0.0024388165,"about_ca_topic_score_gemma":0.0034836298,"teacher_disagreement_score":0.00902357,"about_ca_system_score_codex":0.0010317926,"about_ca_system_score_gemma":0.0028316071,"threshold_uncertainty_score":0.030186892},"labels":[],"label_agreement":null},{"id":"W2507635762","doi":"10.1007/978-3-319-46131-1_8","title":"The SPMF Open-Source Data Mining Library Version 2","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":551,"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 Moncton","funders":"","keywords":"Computer science; Implementation; Authorship attribution; Data mining; Plug-in; Open source; Visualization; Information retrieval; Interface (matter); Software; Software engineering; Artificial intelligence; Programming language; Operating system","score_opus":0.032013028241635884,"score_gpt":0.2657663356650473,"score_spread":0.23375330742341144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2507635762","genre_codex":"dataset","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026052233,0.0020889603,0.24442281,0.0008653002,0.00057478354,0.0005880137,0.37257582,0.34792286,0.02835625],"genre_scores_gemma":[0.009871546,0.0019694902,0.30458152,0.0008224488,0.0003022922,0.0013752112,0.58447593,0.058209617,0.03839192],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998166,0.0001286488,0.00023546607,0.00041076154,0.00091763795,0.00014141167],"domain_scores_gemma":[0.99666107,0.001063037,0.00022366307,0.00095383124,0.00094029267,0.00015809936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019402707,0.0022440858,0.001624025,0.008104548,0.000984663,0.0036638982,0.0031427299,0.0010219407,0.09998918],"category_scores_gemma":[0.011069827,0.0016640313,0.0022135412,0.007032293,0.00040691567,0.004346961,0.0031157162,0.001905128,0.16021213],"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":[0.00014918897,0.00006270984,0.001431012,0.00091427943,0.00009253359,0.000094082796,0.000088789806,0.00084491086,0.0024951675,0.0024716675,0.7680002,0.22335552],"study_design_scores_gemma":[0.000107543674,0.000048338938,0.0032908507,0.00033569237,0.00007862146,0.0007284876,0.0000574234,0.007047871,0.010548549,0.017080013,0.96057224,0.00010445293],"about_ca_topic_score_codex":0.0027115482,"about_ca_topic_score_gemma":0.0034625763,"teacher_disagreement_score":0.09998918,"about_ca_system_score_codex":0.00068314746,"about_ca_system_score_gemma":0.0028282944,"threshold_uncertainty_score":0.3344971},"labels":[],"label_agreement":null},{"id":"W2511113538","doi":"10.4018/978-1-5225-0613-3.ch010","title":"A Dynamic and Scalable Decision Tree Based Mining of Educational Data","year":2016,"lang":"en","type":"book-chapter","venue":"Advances in data mining and database management book series","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Laurentian University","funders":"","keywords":"Data science; Computer science; Scalability; Big data; Field (mathematics); Data mining; Data stream mining; Process (computing); The Internet; Decision tree; Globe; World Wide Web; Database","score_opus":0.024275669627684855,"score_gpt":0.2914051498074734,"score_spread":0.26712948017978855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2511113538","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052968472,0.001980428,0.93273324,0.0012077066,0.0002039082,0.00030781145,0.0030170013,0.002915653,0.0046658097],"genre_scores_gemma":[0.19043766,0.0012126765,0.7971091,0.0002492614,0.00013473585,0.0002689199,0.006443167,0.00011873639,0.0040256474],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993075,0.00013063638,0.000073515424,0.00017532085,0.00025455642,0.000058508398],"domain_scores_gemma":[0.9988858,0.00064273854,0.00006210905,0.00010387123,0.0002481,0.000057272184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011165029,0.00051786914,0.00090927124,0.0012403505,0.00061932346,0.0011450207,0.0017422679,0.0006564864,0.0018332002],"category_scores_gemma":[0.0035015778,0.00038221703,0.00092247414,0.0028285524,0.00022330967,0.0016201686,0.0009579969,0.0010349714,0.0007870421],"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":[0.00023770281,0.0003517368,0.004317371,0.00029190248,0.0001374086,0.00045421536,0.0002028141,0.18480186,0.0052209543,0.007673753,0.02241461,0.7738957],"study_design_scores_gemma":[0.000017582604,0.000044966713,0.00070745376,0.000021342174,0.00001833853,0.0000865716,0.00004680358,0.98848945,0.0011356055,0.005940236,0.0034825995,0.000009087863],"about_ca_topic_score_codex":0.0068909787,"about_ca_topic_score_gemma":0.008898317,"teacher_disagreement_score":0.0068909787,"about_ca_system_score_codex":0.0005695525,"about_ca_system_score_gemma":0.0012397498,"threshold_uncertainty_score":0.013701737},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018990753,0.0018868919,0.95252657,0.00041821328,0.00024271524,0.0004443645,0.003413398,0.019902842,0.0021742387],"genre_scores_gemma":[0.04341999,0.0003351131,0.94803405,0.00018689065,0.00007432727,0.00033708205,0.004750748,0.00042981916,0.0024318912],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858737,0.00026443895,0.00022292086,0.00028160575,0.00047898185,0.00016464829],"domain_scores_gemma":[0.99723285,0.0013730223,0.00015451336,0.0005448204,0.00058149354,0.00011332957],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002128504,0.0018484956,0.0020001745,0.0054847547,0.0013023472,0.0019326555,0.0044230707,0.0019505444,0.008165998],"category_scores_gemma":[0.010128777,0.00094134064,0.0014245124,0.0072214874,0.00048040575,0.0039431923,0.002838069,0.0016915842,0.0045075133],"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":[0.0008522374,0.00031287275,0.0029290074,0.00046859443,0.00018869963,0.00023511435,0.00011924483,0.016619638,0.0039351233,0.0045986027,0.030191928,0.93954897],"study_design_scores_gemma":[0.0004705612,0.00041781634,0.0023246922,0.00020411193,0.00019815628,0.0013262179,0.00020574892,0.893647,0.019048937,0.04372665,0.03832556,0.000104590144],"about_ca_topic_score_codex":0.0032487232,"about_ca_topic_score_gemma":0.005698227,"teacher_disagreement_score":0.008165998,"about_ca_system_score_codex":0.0007999422,"about_ca_system_score_gemma":0.0022958629,"threshold_uncertainty_score":0.027317941},"labels":[],"label_agreement":null},{"id":"W2513435641","doi":"","title":"The use of concept hierarchies in privacy preserving data acquisition for data mining","year":2013,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Data mining; Information privacy; Data anonymization; Data collection; Computer security; Mathematics; Statistics","score_opus":0.2109281213054324,"score_gpt":0.3337855382113523,"score_spread":0.12285741690591992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2513435641","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041509154,0.00060880877,0.99223,0.00076076755,0.000037246464,0.00018540368,0.0001104171,0.00015672107,0.0017598147],"genre_scores_gemma":[0.10468187,0.00069570396,0.8927809,0.00033776936,0.00010732471,0.00038100532,0.00023781072,0.000055488075,0.0007221359],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.96593285,0.017559916,0.0020886501,0.0031802754,0.010467511,0.00077070564],"domain_scores_gemma":[0.94853485,0.030745205,0.0039476454,0.012291193,0.0037113265,0.0007698141],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02438896,0.00085021445,0.0011547117,0.00428061,0.0026691724,0.0065435106,0.0034646844,0.0014727925,0.0014881209],"category_scores_gemma":[0.050119776,0.0014634806,0.003177287,0.006060549,0.008154377,0.0148896165,0.0066178255,0.005654959,0.0005798167],"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":[0.00015125964,0.00016447005,0.0026453347,0.00063763635,0.00017863614,0.00026862766,0.0041583613,0.020879172,0.0032095304,0.74712765,0.0031941284,0.21738516],"study_design_scores_gemma":[0.000052177296,0.00019183324,0.0013028274,0.00036888418,0.000099123565,0.0006023061,0.00081457116,0.13599445,0.0056991405,0.81611055,0.03865375,0.0001103472],"about_ca_topic_score_codex":0.0051723,"about_ca_topic_score_gemma":0.003890936,"teacher_disagreement_score":0.02438896,"about_ca_system_score_codex":0.0034400667,"about_ca_system_score_gemma":0.004801447,"threshold_uncertainty_score":0.12898266},"labels":[],"label_agreement":null},{"id":"W2518671462","doi":"10.1007/978-3-319-45814-4_26","title":"B-mine: Frequent Pattern Mining and Its Application to Knowledge Discovery from Social Networks","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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 Manitoba","funders":"","keywords":"Computer science; Data mining; Knowledge extraction; Apriori algorithm; Association rule learning; Bitwise operation; Task (project management); Web mining; Data science; World Wide Web; Web service; Engineering","score_opus":0.015726858711528097,"score_gpt":0.2565420101448054,"score_spread":0.24081515143327728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2518671462","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051789377,0.003023207,0.9740622,0.0006775341,0.00017909317,0.00018525709,0.0040118606,0.010912905,0.0017690072],"genre_scores_gemma":[0.025454199,0.003053934,0.96369165,0.00022767771,0.00018229509,0.0004276834,0.004187468,0.0005669993,0.002208184],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986118,0.00033250853,0.00017527683,0.00026070978,0.0005789017,0.00004078335],"domain_scores_gemma":[0.9945516,0.0041096793,0.00026004977,0.00047285183,0.00046513265,0.00014076248],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023562731,0.0013817996,0.001719567,0.004567,0.0008455596,0.0024512736,0.0018819091,0.0014356333,0.0067877676],"category_scores_gemma":[0.012808528,0.0011196843,0.0012441641,0.0069226325,0.00052301615,0.0040952843,0.0019985274,0.0021409467,0.005992392],"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":[0.00035810343,0.00025896914,0.0026232887,0.0016220937,0.00026046493,0.00044638346,0.0003448866,0.01586495,0.006143231,0.01981006,0.05115064,0.9011169],"study_design_scores_gemma":[0.0001768478,0.00024660054,0.0026280398,0.00033959612,0.00019789925,0.0023087272,0.00022531593,0.7148433,0.011726005,0.18306705,0.08411615,0.00012450949],"about_ca_topic_score_codex":0.001363426,"about_ca_topic_score_gemma":0.0016136026,"teacher_disagreement_score":0.0067877676,"about_ca_system_score_codex":0.00031556172,"about_ca_system_score_gemma":0.00096351566,"threshold_uncertainty_score":0.022707403},"labels":[],"label_agreement":null},{"id":"W2519502568","doi":"10.1145/2938503.2938535","title":"Clickstream Prediction Using Sequential Stream Mining Techniques with Markov Chains","year":2016,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":30,"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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Clickstream; Computer science; Markov chain; Data mining; Data stream; Data stream mining; Web mining; Purchasing; Machine learning; Artificial intelligence; Web page; Web navigation; World Wide Web","score_opus":0.022197842832638134,"score_gpt":0.26136375911638293,"score_spread":0.23916591628374478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2519502568","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.075320825,0.0004620353,0.91954076,0.00033936303,0.00007724589,0.00021735996,0.0009165582,0.0023664227,0.00075941876],"genre_scores_gemma":[0.7521536,0.000751074,0.2426325,0.00011890546,0.00013704467,0.00032011885,0.0023590007,0.000089743764,0.0014380284],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990797,0.0001692769,0.00010202624,0.00021905785,0.00033509984,0.000094734314],"domain_scores_gemma":[0.9953687,0.0029254113,0.00048581476,0.00034091034,0.00067973306,0.00019947556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018341157,0.0009982921,0.0012218405,0.002839392,0.0005771033,0.0011732929,0.0012763329,0.0006530225,0.0010996478],"category_scores_gemma":[0.0070175785,0.00055507664,0.0011965835,0.0024232757,0.00035989238,0.0016894267,0.0007042217,0.0012578106,0.00041047996],"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":[0.0006647644,0.00063727394,0.049617067,0.00021153616,0.00031158485,0.00046921548,0.00022809474,0.60213745,0.0053513567,0.01191994,0.005636369,0.32281533],"study_design_scores_gemma":[0.000007805726,0.000016647913,0.00040841475,0.0000035302685,0.000009148126,0.000021010583,0.000004347841,0.9967777,0.00043344873,0.0021675527,0.00014530217,0.0000050949197],"about_ca_topic_score_codex":0.014665819,"about_ca_topic_score_gemma":0.011896029,"teacher_disagreement_score":0.014665819,"about_ca_system_score_codex":0.00081440195,"about_ca_system_score_gemma":0.0016086501,"threshold_uncertainty_score":0.029160917},"labels":[],"label_agreement":null},{"id":"W2520764256","doi":"10.3968/8722","title":"Analysis of Hot Points on Data Mining Research of Medical in Foreign Countries","year":2016,"lang":"en","type":"article","venue":"Cross-cultural communication","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Data science; Subject (documents); Medical research; Field (mathematics); Computer science; Data mining; Library science; Medicine","score_opus":0.1593352111893424,"score_gpt":0.4612453523043105,"score_spread":0.3019101411149681,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2520764256","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93247896,0.031433135,0.0033301709,0.005032246,0.000282478,0.00011933025,0.0028605727,0.00008896451,0.024374243],"genre_scores_gemma":[0.9829285,0.010023646,0.0028920402,0.00031737363,0.00027317653,0.000080223654,0.0014940951,0.000024748111,0.0019662336],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9954542,0.0012439456,0.00085393025,0.00047544832,0.0014263742,0.00054610224],"domain_scores_gemma":[0.97145283,0.014652266,0.005767051,0.0010755908,0.005579935,0.0014724287],"candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.00605774,0.00033046512,0.0006169951,0.025738358,0.0015537448,0.004465528,0.0004931744,0.0006501687,0.0026054818],"category_scores_gemma":[0.016240135,0.00021174822,0.0006827924,0.044326264,0.0008380441,0.002347832,0.0016387952,0.00047047736,0.00045927396],"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":[0.0007328323,0.00013051259,0.6500869,0.0049069254,0.00051152817,0.0032237135,0.031199493,0.0014779998,0.0047508734,0.023381248,0.009926267,0.26967174],"study_design_scores_gemma":[0.000016723352,0.0001632251,0.8885745,0.0014343947,0.00035314064,0.0018074241,0.050256345,0.0014934525,0.00349329,0.006607302,0.045735724,0.000064487525],"about_ca_topic_score_codex":0.0016402378,"about_ca_topic_score_gemma":0.0022839687,"teacher_disagreement_score":0.97426164,"about_ca_system_score_codex":0.0017736262,"about_ca_system_score_gemma":0.0022353309,"threshold_uncertainty_score":0.03203678},"labels":[],"label_agreement":null},{"id":"W2524418476","doi":"10.21700/ijcis.2016.111","title":"Framework for Visualizing Browsing Patterns Captured in Computer Logs Using Data Mining Techniques","year":2016,"lang":"en","type":"article","venue":"International Journal of Computing and Information Sciences","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Data mining; Visualization; Data science; Information retrieval","score_opus":0.08163730197639742,"score_gpt":0.4007570484119151,"score_spread":0.3191197464355177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2524418476","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006219067,0.00035956147,0.96591973,0.00036908247,0.0000450221,0.00033198876,0.0027760603,0.022499146,0.0014803295],"genre_scores_gemma":[0.04219324,0.00038372888,0.95314777,0.000052445896,0.000018202072,0.00030195675,0.002477981,0.00036431462,0.0010602494],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99952257,0.00007795625,0.00008183187,0.00010781379,0.00015626686,0.000053638665],"domain_scores_gemma":[0.9987056,0.00037434904,0.0001340022,0.0002241625,0.00037194559,0.00018985276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001406272,0.0017642397,0.0009561113,0.008258399,0.0010700282,0.0063943495,0.0017603708,0.0012113296,0.0032071415],"category_scores_gemma":[0.002789157,0.0005821962,0.0015600073,0.004871038,0.0006164026,0.003057446,0.0016370519,0.0016521526,0.0014438536],"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":[0.0005916798,0.0008954426,0.017410485,0.002012212,0.0005039669,0.0013454055,0.0033354312,0.034893107,0.05702542,0.106678925,0.05434537,0.7209626],"study_design_scores_gemma":[0.00012788283,0.00022938638,0.007300832,0.000628477,0.00035698691,0.0014421245,0.0016269507,0.69372,0.03632245,0.12857772,0.12940599,0.0002612228],"about_ca_topic_score_codex":0.01457818,"about_ca_topic_score_gemma":0.020256938,"teacher_disagreement_score":0.01457818,"about_ca_system_score_codex":0.0008938144,"about_ca_system_score_gemma":0.0020470356,"threshold_uncertainty_score":0.028986692},"labels":[],"label_agreement":null},{"id":"W2527711547","doi":"10.5121/ijdkp.2016.6501","title":"Using Ontology Based Semantic Association Rule Mining in Location Based Services","year":2016,"lang":"en","type":"article","venue":"International Journal of Data Mining & Knowledge Management Process","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Association rule learning; Ontology; Information retrieval; Data mining; Data science","score_opus":0.05422144218284687,"score_gpt":0.35759145911862394,"score_spread":0.3033700169357771,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2527711547","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.091776535,0.00069486175,0.90000486,0.0007089337,0.00012038525,0.00045678078,0.00091962004,0.0016510601,0.003666997],"genre_scores_gemma":[0.41305405,0.0006381094,0.5836541,0.00017551909,0.00003744066,0.00027310583,0.0014378721,0.00006652899,0.0006633289],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9939348,0.0019667316,0.00088789477,0.0008031717,0.0020655554,0.0003418285],"domain_scores_gemma":[0.99585754,0.0022438022,0.0004472962,0.0004680454,0.00085023756,0.0001330131],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038600143,0.00063598354,0.0009576405,0.0050231586,0.0013654747,0.0025515568,0.0014037157,0.0010324828,0.00081340375],"category_scores_gemma":[0.010404681,0.00043752458,0.0021958025,0.005722946,0.0008732974,0.0037708804,0.0017593313,0.0010590183,0.00045204343],"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":[0.0006213871,0.0017452522,0.05115607,0.001181704,0.001113278,0.0031147976,0.0025810318,0.14127396,0.015845735,0.06677837,0.0060039293,0.7085844],"study_design_scores_gemma":[0.000051556926,0.00011648322,0.0052417624,0.00015420558,0.0003563793,0.00084346696,0.00097267475,0.9179438,0.012492655,0.0485698,0.0131669175,0.00009034002],"about_ca_topic_score_codex":0.01214003,"about_ca_topic_score_gemma":0.013654685,"teacher_disagreement_score":0.01214003,"about_ca_system_score_codex":0.0010334965,"about_ca_system_score_gemma":0.00285445,"threshold_uncertainty_score":0.024138749},"labels":[],"label_agreement":null},{"id":"W2528099986","doi":"10.1109/dasc-picom-datacom-cyberscitec.2016.148","title":"A Data Science Model for Big Data Analytics of Frequent Patterns","year":2016,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":9,"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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Big data; Computer science; Data science; Data mining; Variety (cybernetics); Tree (set theory); Task (project management); Analytics; Artificial intelligence","score_opus":0.3168023449115383,"score_gpt":0.3607614895957989,"score_spread":0.0439591446842606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2528099986","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040471875,0.0005152753,0.98307806,0.0050599715,0.00018644406,0.00029660063,0.0016783166,0.00065103057,0.004487071],"genre_scores_gemma":[0.17757246,0.0018314935,0.80590576,0.0024084381,0.0009168444,0.0020971661,0.0039973087,0.00017066278,0.0050997795],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99515605,0.0011179084,0.00048342303,0.0009296644,0.002115163,0.00019782734],"domain_scores_gemma":[0.9875053,0.006836443,0.00091705244,0.0020707073,0.0022574714,0.00041298737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005169033,0.0009729433,0.0010288248,0.004283424,0.0012549601,0.0052956897,0.0030292904,0.0020716873,0.0031386423],"category_scores_gemma":[0.019043531,0.0006606294,0.00252067,0.006593884,0.0021955778,0.009633743,0.0022113274,0.0034299106,0.0019988366],"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":[0.00014208267,0.00027085718,0.0045474367,0.0004306685,0.00014615203,0.000499732,0.0005071175,0.0903824,0.0016075982,0.8141355,0.019771509,0.067559004],"study_design_scores_gemma":[0.000039973293,0.00007192469,0.00043515852,0.00005742293,0.000038686067,0.00036884256,0.00011145014,0.43256614,0.0006268996,0.53236747,0.03328259,0.00003345536],"about_ca_topic_score_codex":0.0032939452,"about_ca_topic_score_gemma":0.0034134863,"teacher_disagreement_score":0.0052956897,"about_ca_system_score_codex":0.0022853308,"about_ca_system_score_gemma":0.0031235104,"threshold_uncertainty_score":0.027336776},"labels":[],"label_agreement":null},{"id":"W2529573579","doi":"10.1109/dasc-picom-datacom-cyberscitec.2016.158","title":"PyramidViz: Visual Analytics and Big Data Visualization for Frequent Patterns","year":2016,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":27,"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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Visual analytics; Visualization; Representation (politics); Data visualization; Analytics; Big data; Data science; Prefix; Interactive visual analysis; Extension (predicate logic); Information retrieval; Information visualization; Data mining","score_opus":0.0950244996207088,"score_gpt":0.3378334235962179,"score_spread":0.24280892397550907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2529573579","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009113092,0.00057050626,0.90002894,0.001031134,0.00016015854,0.00037983348,0.0082926005,0.07731589,0.0031078933],"genre_scores_gemma":[0.07790324,0.001345924,0.89741546,0.00038758153,0.0001222409,0.0009770375,0.013532217,0.005364341,0.0029519245],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999114,0.00020364666,0.000097057746,0.00011893068,0.00038269404,0.00008374109],"domain_scores_gemma":[0.9966079,0.0017529292,0.00033146868,0.00042926995,0.00064672105,0.00023169327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020034714,0.0025038442,0.0010824425,0.006255791,0.00065568194,0.0037932643,0.0023650955,0.0014503795,0.016736846],"category_scores_gemma":[0.009685554,0.0009702926,0.001992136,0.0039392053,0.0005994348,0.0050017624,0.0038772118,0.0022328536,0.0031882492],"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":[0.0018152525,0.00043528428,0.0059092306,0.004002006,0.00058496644,0.0019021904,0.005631517,0.02850249,0.045452725,0.06420785,0.24260859,0.598948],"study_design_scores_gemma":[0.00064586353,0.0003359133,0.005751043,0.0007237061,0.00019793311,0.0019451621,0.0010760672,0.6199933,0.04109296,0.12632938,0.20152138,0.0003872486],"about_ca_topic_score_codex":0.0032879347,"about_ca_topic_score_gemma":0.003113368,"teacher_disagreement_score":0.016736846,"about_ca_system_score_codex":0.0006399461,"about_ca_system_score_gemma":0.0010577992,"threshold_uncertainty_score":0.05599028},"labels":[],"label_agreement":null},{"id":"W253312643","doi":"10.1142/s0129626409000055","title":"LOCATING THE MEDIAN OF A TREE IN REAL TIME","year":2009,"lang":"en","type":"article","venue":"Parallel Processing Letters","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Tree (set theory); Computer science; Mathematics; Combinatorics","score_opus":0.014852441517855279,"score_gpt":0.2575654061639926,"score_spread":0.2427129646461373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W253312643","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.181518,0.00015693514,0.8163413,0.00018595907,0.000024894622,0.000021890248,0.00006155446,0.00035834088,0.0013310113],"genre_scores_gemma":[0.8565512,0.000092973474,0.14217666,0.000029893243,0.000014169495,0.0000321472,0.00008841759,0.00006036287,0.00095416885],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99926275,0.00020303953,0.000030888208,0.0002111444,0.00015620656,0.00013605089],"domain_scores_gemma":[0.9968239,0.0019530631,0.00048855826,0.00028164085,0.000289075,0.0001637983],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017246307,0.00041020534,0.0008618836,0.0007037061,0.00065225654,0.0015535576,0.0009272423,0.0010575,0.0015024066],"category_scores_gemma":[0.00826533,0.00041541932,0.00032413844,0.0008254286,0.0009999379,0.0022876726,0.0009473383,0.0006593965,0.00034699086],"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":[0.00042611724,0.00004343019,0.0026349907,0.00003720244,0.000022813732,0.00014278926,0.00015152078,0.9402652,0.007065242,0.016422607,0.00058651005,0.032201637],"study_design_scores_gemma":[0.000007805945,0.000042717227,0.0002812441,0.0000028115155,0.0000035752405,0.00004353911,0.00005392234,0.98553836,0.0020483134,0.011660363,0.00031003926,0.000007296948],"about_ca_topic_score_codex":0.001934296,"about_ca_topic_score_gemma":0.0018153681,"teacher_disagreement_score":0.001934296,"about_ca_system_score_codex":0.0009627219,"about_ca_system_score_gemma":0.001130858,"threshold_uncertainty_score":0.009120822},"labels":[],"label_agreement":null},{"id":"W2533989243","doi":"10.1016/j.eswa.2016.10.028","title":"Mining erasable itemsets with subset and superset itemset constraints","year":2016,"lang":"en","type":"article","venue":"Expert Systems with Applications","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 Alberta","funders":"","keywords":"Pruning; Computer science; Data mining; Algorithm","score_opus":0.013507094472071372,"score_gpt":0.23505872936831732,"score_spread":0.22155163489624594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2533989243","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35044995,0.004317593,0.61490655,0.0011776718,0.00028798173,0.0009834431,0.019150449,0.0012955168,0.0074308095],"genre_scores_gemma":[0.5653013,0.0018037999,0.3999789,0.00047607423,0.00033781843,0.0007570263,0.02574601,0.00019046864,0.005408539],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969151,0.00057620136,0.0006387951,0.0006551934,0.00097265793,0.00024207792],"domain_scores_gemma":[0.9822342,0.0118480325,0.0016439891,0.0017783671,0.001974481,0.00052091485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003094288,0.0013883705,0.0025130252,0.0060107964,0.00093099754,0.0030775797,0.0028600811,0.0014331478,0.004242951],"category_scores_gemma":[0.023389319,0.00092576456,0.0021907443,0.009088566,0.00074125716,0.0050800634,0.001682084,0.0018039672,0.0008793666],"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":[0.0036105406,0.001211918,0.08021401,0.003057699,0.0019466106,0.0071230615,0.00064526056,0.26834202,0.012622789,0.0502381,0.018973393,0.55201465],"study_design_scores_gemma":[0.00026477818,0.0007908865,0.012890513,0.000568866,0.00057220564,0.0033233196,0.0010077569,0.87448925,0.010390883,0.08205666,0.013531061,0.00011383765],"about_ca_topic_score_codex":0.002667887,"about_ca_topic_score_gemma":0.005530012,"teacher_disagreement_score":0.0060107964,"about_ca_system_score_codex":0.0005077021,"about_ca_system_score_gemma":0.00222852,"threshold_uncertainty_score":0.016364336},"labels":[],"label_agreement":null},{"id":"W2537347163","doi":"10.1109/taai.2015.7407089","title":"Mining closed+ high utility itemsets without candidate generation","year":2015,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Lossless compression; Representation (politics); Data mining; Theoretical computer science; Information retrieval; Algorithm; Data compression","score_opus":0.06314924619531743,"score_gpt":0.29134268671359387,"score_spread":0.22819344051827645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2537347163","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.076399274,0.0010847537,0.9119206,0.00039286067,0.000117234136,0.00086806563,0.0030580107,0.0034712132,0.002688002],"genre_scores_gemma":[0.27467,0.0006093756,0.7082914,0.00028072594,0.000107533175,0.00068315264,0.011212751,0.00020811564,0.003936945],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99734086,0.00048569875,0.00037122762,0.00069042837,0.0008555079,0.00025628207],"domain_scores_gemma":[0.9938339,0.0034331926,0.0005530333,0.00091652304,0.0010558793,0.00020745615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002342047,0.001584636,0.0022954163,0.0036098128,0.0011211396,0.0024035617,0.0031389303,0.0017254394,0.0027155795],"category_scores_gemma":[0.012554706,0.0009112157,0.0018928646,0.0053347657,0.00067866244,0.0032575333,0.0022601031,0.0014749946,0.002217242],"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":[0.001316211,0.0006939418,0.014506745,0.0009798306,0.00037205644,0.001891144,0.0004006342,0.111533836,0.011601987,0.014045785,0.015379381,0.8272785],"study_design_scores_gemma":[0.00016562124,0.0005544256,0.0027242627,0.0001344296,0.00014324783,0.0016540027,0.00033986583,0.9362155,0.012658245,0.035560545,0.009793649,0.000056233566],"about_ca_topic_score_codex":0.0016831366,"about_ca_topic_score_gemma":0.0030231704,"teacher_disagreement_score":0.0036098128,"about_ca_system_score_codex":0.0005720169,"about_ca_system_score_gemma":0.002120649,"threshold_uncertainty_score":0.012386084},"labels":[],"label_agreement":null},{"id":"W2540291519","doi":"10.1109/iembs.1991.684456","title":"A Clinical Laboratory Expert System For The Diagnosis Of Thyroid Dysfunction","year":2005,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Expert system; Thyroid dysfunction; Computer science; Scheme (mathematics); Thyroid; Machine learning; Artificial intelligence; Medicine; Internal medicine; Mathematics","score_opus":0.03759616315209907,"score_gpt":0.31990160577132254,"score_spread":0.28230544261922347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2540291519","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010144501,0.0013628992,0.9634396,0.0013546314,0.00027813407,0.00090808363,0.001831331,0.015452614,0.00522827],"genre_scores_gemma":[0.120505534,0.0007441442,0.868709,0.0011533591,0.00018221156,0.00083506474,0.00319735,0.00021333084,0.0044599883],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99777055,0.0006489369,0.00032901735,0.00047541756,0.0006990292,0.00007714496],"domain_scores_gemma":[0.9963521,0.0017439065,0.00024689312,0.00030660073,0.0011520024,0.0001984705],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037671153,0.00074039237,0.0010298477,0.0023159303,0.00067915383,0.0015180302,0.0017562807,0.0014751161,0.006682449],"category_scores_gemma":[0.010957438,0.00029871333,0.0004991733,0.0009759853,0.00030745685,0.0009213563,0.0008376808,0.0012874949,0.0044603394],"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":[0.0008560592,0.0004695523,0.0069922637,0.00094090425,0.00024586305,0.0024139003,0.00031936148,0.02338811,0.025144164,0.0075475737,0.059086632,0.8725956],"study_design_scores_gemma":[0.0012880831,0.0010780458,0.015104878,0.000703354,0.00068547146,0.01050694,0.00031984283,0.7141276,0.040310223,0.029306589,0.18620415,0.00036474952],"about_ca_topic_score_codex":0.003070247,"about_ca_topic_score_gemma":0.0032298139,"teacher_disagreement_score":0.006682449,"about_ca_system_score_codex":0.00067838666,"about_ca_system_score_gemma":0.0024223053,"threshold_uncertainty_score":0.02235502},"labels":[],"label_agreement":null},{"id":"W2540560307","doi":"10.1109/icdmw.2014.128","title":"A Business Intelligence Solution for Frequent Pattern Mining on Social Networks","year":2014,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":13,"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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Apriori algorithm; Data mining; Task (project management); GSP Algorithm; Association rule learning; Machine learning; Artificial intelligence; Engineering","score_opus":0.045148562212151654,"score_gpt":0.2852217715929543,"score_spread":0.24007320938080265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2540560307","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004762671,0.00047795536,0.9834953,0.0016448774,0.0001646994,0.00033428357,0.00068823964,0.0018432464,0.006588824],"genre_scores_gemma":[0.04867089,0.00081187254,0.9431919,0.00035796498,0.00015238544,0.00041948323,0.0012971775,0.00008350989,0.0050147865],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988164,0.00022200847,0.00010179237,0.00026557434,0.00052121794,0.0000731594],"domain_scores_gemma":[0.99911195,0.0003289831,0.00013018351,0.0001351097,0.00023747682,0.000056306202],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011593451,0.0009102638,0.00088963954,0.0026051297,0.0013003504,0.0020690253,0.001495552,0.0017881792,0.006120306],"category_scores_gemma":[0.0049414425,0.0004707412,0.0012981751,0.004392138,0.00039322753,0.0030602422,0.002055475,0.0013942783,0.004140349],"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":[0.0001714561,0.0004455175,0.0022004452,0.00059008703,0.00022643516,0.00085652625,0.00035230702,0.042689953,0.004453701,0.12497079,0.049843214,0.7731996],"study_design_scores_gemma":[0.0000917574,0.00012609702,0.000579788,0.0001126389,0.000083225976,0.0010690561,0.00038619444,0.7316118,0.0033212765,0.18985668,0.072724536,0.000037004636],"about_ca_topic_score_codex":0.0012564103,"about_ca_topic_score_gemma":0.0017624988,"teacher_disagreement_score":0.006120306,"about_ca_system_score_codex":0.0004926733,"about_ca_system_score_gemma":0.0011477639,"threshold_uncertainty_score":0.020474434},"labels":[],"label_agreement":null},{"id":"W2542031809","doi":"10.1109/icdmw.2014.129","title":"DISC: Efficient Uncertain Frequent Pattern Mining with Tightened Upper Bounds","year":2014,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Upper and lower bounds; Computer science; Set (abstract data type); Space (punctuation); Tree (set theory); Data mining; Branch and bound; Algorithm; Mathematical optimization; Mathematics; Combinatorics","score_opus":0.01043820453891834,"score_gpt":0.2287734040819601,"score_spread":0.21833519954304176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2542031809","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038397245,0.0015906122,0.94646925,0.00060468825,0.00015560619,0.00027785843,0.0024076349,0.007020667,0.00307644],"genre_scores_gemma":[0.29488114,0.0007314612,0.6942989,0.00035980987,0.0002267046,0.00045976733,0.006090237,0.00032876502,0.0026231965],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99683064,0.0005056894,0.00031287773,0.00040153347,0.0016791463,0.0002701935],"domain_scores_gemma":[0.9897636,0.0056589944,0.00057782873,0.0021075874,0.0016415134,0.00025059065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027072846,0.0010660391,0.0018146356,0.003440853,0.0010215046,0.0021344025,0.0036184296,0.0011698591,0.0022182686],"category_scores_gemma":[0.025197865,0.0006322824,0.00078047457,0.00465395,0.00084245973,0.003977856,0.0027947207,0.0013991864,0.0011449449],"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":[0.0016212768,0.00032681253,0.007840734,0.0006194323,0.00015294988,0.0006325007,0.0003866159,0.17514579,0.008093808,0.024693592,0.03635873,0.7441278],"study_design_scores_gemma":[0.00012908212,0.000103020386,0.0006380959,0.000029729234,0.000027262458,0.0004579839,0.00008437824,0.9636869,0.005448357,0.021635251,0.0077325664,0.000027349486],"about_ca_topic_score_codex":0.0055548404,"about_ca_topic_score_gemma":0.0047678086,"teacher_disagreement_score":0.0055548404,"about_ca_system_score_codex":0.0012716613,"about_ca_system_score_gemma":0.002349365,"threshold_uncertainty_score":0.014317691},"labels":[],"label_agreement":null},{"id":"W2545356923","doi":"10.1109/wi-iatw.2006.59","title":"Distributed Mining of Constrained Patterns from Wireless Sensor Data","year":2006,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Wireless sensor network; Intension; Distributed computing; Data mining; Distributed Computing Environment; Distributed algorithm; Wireless; Distributed database; Tree (set theory); Wireless network; Computer network","score_opus":0.028961362081009828,"score_gpt":0.25694724654612205,"score_spread":0.22798588446511223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2545356923","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10143134,0.00036563963,0.896342,0.00023762781,0.000027382332,0.00012444284,0.0004596282,0.00055452716,0.00045742147],"genre_scores_gemma":[0.5508784,0.0003948866,0.44575608,0.00010514162,0.000048345755,0.000252708,0.00192463,0.000057194884,0.00058265723],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984701,0.00031881515,0.00019558117,0.0003997088,0.0005116834,0.000104081606],"domain_scores_gemma":[0.9952891,0.0024351187,0.0006704973,0.00083143124,0.00064441323,0.00012950126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013341353,0.0006744096,0.0014245727,0.0018559828,0.0006769145,0.0009389275,0.0015037905,0.0007195985,0.00037393873],"category_scores_gemma":[0.008198458,0.00044640983,0.00068378024,0.003321894,0.00045783978,0.0020951908,0.0012932713,0.0006616363,0.00016939799],"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":[0.00081506383,0.00051075465,0.030281859,0.00058278133,0.0004917269,0.0021523084,0.00074576266,0.3823462,0.04382937,0.011002751,0.004559242,0.5226822],"study_design_scores_gemma":[0.000035910536,0.00008806346,0.0023082553,0.000014393415,0.000044025663,0.00035264812,0.00018139654,0.97173506,0.007950145,0.015815526,0.0014609555,0.000013486872],"about_ca_topic_score_codex":0.0014672392,"about_ca_topic_score_gemma":0.002835447,"teacher_disagreement_score":0.0018559828,"about_ca_system_score_codex":0.00030034134,"about_ca_system_score_gemma":0.000918362,"threshold_uncertainty_score":0.00705564},"labels":[],"label_agreement":null},{"id":"W2545943971","doi":"10.1145/2837060.2837072","title":"FIMaaS","year":2015,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":14,"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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Popularity; Scalability; Variety (cybernetics); Data science; Big data; Service (business); Schedule; Cloud computing; Knowledge extraction; World Wide Web; Data mining; Database; Business; Artificial intelligence","score_opus":0.060479563226180685,"score_gpt":0.2758004244980998,"score_spread":0.21532086127191913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2545943971","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0076275985,0.0026474202,0.19596359,0.0049362397,0.0026554319,0.0011760393,0.040389217,0.32546154,0.4191429],"genre_scores_gemma":[0.09761816,0.0044415183,0.25664967,0.004589247,0.0013109592,0.001846056,0.15830635,0.028517425,0.4467207],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99776375,0.00022494343,0.00016230429,0.0004943216,0.000966724,0.0003877999],"domain_scores_gemma":[0.9966409,0.00051590375,0.00020022712,0.0012923856,0.0008803493,0.00047025227],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016889427,0.0017711408,0.0012878561,0.0031527127,0.001617871,0.0050095827,0.0041967463,0.00236511,0.24444228],"category_scores_gemma":[0.008414421,0.0008654432,0.001467532,0.0030177354,0.0006532494,0.0066681574,0.004116664,0.002358073,0.22793388],"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":[0.00082152657,0.00021205014,0.0015691458,0.00044938474,0.00006978794,0.0004354133,0.00017774045,0.0017526234,0.0054852413,0.031758465,0.63914305,0.31812555],"study_design_scores_gemma":[0.0001009427,0.00006303449,0.000756823,0.00008645301,0.000024874209,0.0005372655,0.000054732995,0.00973932,0.0031862298,0.014717686,0.9706835,0.000049096507],"about_ca_topic_score_codex":0.0034672373,"about_ca_topic_score_gemma":0.0026162036,"teacher_disagreement_score":0.7555577,"about_ca_system_score_codex":0.0012163932,"about_ca_system_score_gemma":0.002289797,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W2546592849","doi":"10.1109/itme.2008.4743972","title":"Medical Knowledge Acquisition Through Data Mining","year":2008,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"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":"Knowledge extraction; Computer science; Knowledge acquisition; Data science; Medical knowledge; Data mining; Knowledge management; Medicine","score_opus":0.09730166805199503,"score_gpt":0.33922758472614883,"score_spread":0.2419259166741538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2546592849","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013877994,0.0075191627,0.94738597,0.011365123,0.00024437933,0.00071906863,0.00083408324,0.000915322,0.017138949],"genre_scores_gemma":[0.18654941,0.014363097,0.7901348,0.0022997311,0.0005311357,0.000630631,0.0016668717,0.00008507342,0.0037392436],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9944772,0.0019349336,0.0004592779,0.0008385849,0.0021148864,0.0001752455],"domain_scores_gemma":[0.9902974,0.0065377764,0.0006534861,0.001244953,0.001075824,0.0001904987],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0068768244,0.00089216745,0.0014795624,0.005627444,0.00090796966,0.005091507,0.0026136828,0.0016406259,0.002257206],"category_scores_gemma":[0.018034896,0.00051850016,0.0013608743,0.0046101166,0.00273818,0.0056063267,0.0044518444,0.002335867,0.0012370687],"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":[0.00022869447,0.00042139535,0.009406634,0.0022121428,0.00037343122,0.00084249815,0.0012821484,0.019424854,0.003665688,0.2269409,0.014160471,0.7210412],"study_design_scores_gemma":[0.000112416004,0.00028510322,0.002704876,0.0015659143,0.00036666603,0.0018118842,0.00084666937,0.15340249,0.012325782,0.6794684,0.14696783,0.00014199823],"about_ca_topic_score_codex":0.0012402897,"about_ca_topic_score_gemma":0.0010386315,"teacher_disagreement_score":0.0068768244,"about_ca_system_score_codex":0.0010751791,"about_ca_system_score_gemma":0.0025423514,"threshold_uncertainty_score":0.03636855},"labels":[],"label_agreement":null},{"id":"W2550345740","doi":"10.5555/3192424.3192599","title":"Mining 'following' patterns from big sparse social networks","year":2016,"lang":"en","type":"article","venue":"Advances in Social Networks Analysis and Mining","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Big data; Social network (sociolinguistics); Computer science; Interdependence; Friendship; Data science; Social group; Social network analysis; Social computing; Data mining; World Wide Web; Social media; Sociology; Social science","score_opus":0.01558531899206473,"score_gpt":0.2750966361612002,"score_spread":0.2595113171691355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2550345740","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53603953,0.0011940479,0.4461579,0.0019706094,0.000099660974,0.00048285734,0.0073946356,0.0013108017,0.0053499197],"genre_scores_gemma":[0.8342417,0.00056783034,0.15491161,0.00020930829,0.00010289528,0.000296714,0.008371945,0.000048422928,0.0012495026],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985494,0.00035777228,0.0001337669,0.00033052193,0.0005085687,0.00012001735],"domain_scores_gemma":[0.99230254,0.0040380047,0.001395589,0.001179603,0.00086432154,0.00021987996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094564166,0.0007720573,0.00091281196,0.0045693787,0.0008999514,0.0009866487,0.001545005,0.0012881136,0.0009512623],"category_scores_gemma":[0.0106881345,0.00042956273,0.0008345728,0.004165202,0.0007198574,0.002711565,0.001336278,0.0008366928,0.0004814365],"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":[0.0010639576,0.00083651434,0.21328238,0.0013406777,0.00075929717,0.0041073044,0.003379448,0.19616047,0.01959354,0.037734892,0.01921832,0.5025232],"study_design_scores_gemma":[0.000033024415,0.00014725447,0.023854908,0.00008575395,0.00010797415,0.0011638803,0.0013518855,0.8962392,0.005691127,0.06275255,0.008538123,0.00003430991],"about_ca_topic_score_codex":0.0041339053,"about_ca_topic_score_gemma":0.0075962082,"teacher_disagreement_score":0.0045693787,"about_ca_system_score_codex":0.0005483193,"about_ca_system_score_gemma":0.00052091334,"threshold_uncertainty_score":0.008219719},"labels":[],"label_agreement":null},{"id":"W2553369270","doi":"10.3934/bdia.2016009","title":"Manifold data mining helps businesses grow more effectively","year":2016,"lang":"en","type":"article","venue":"Big Data and Information Analytics","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Manifold (fluid mechanics); Nonlinear dimensionality reduction; Data mining; Data science; Business; Computer science; Engineering; Artificial intelligence; Mechanical engineering","score_opus":0.08789576314961048,"score_gpt":0.2890048371131446,"score_spread":0.20110907396353414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2553369270","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09710267,0.015671682,0.39616182,0.2523509,0.003940197,0.0006571058,0.007662142,0.0143164685,0.21213703],"genre_scores_gemma":[0.47713196,0.015889365,0.4512689,0.0077293147,0.0028903103,0.00040518166,0.00786041,0.0020572487,0.03476731],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99531186,0.001072336,0.0002322595,0.00069113687,0.0022844514,0.00040788672],"domain_scores_gemma":[0.9837841,0.0043143174,0.0012900278,0.0044850255,0.0044479775,0.0016785566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0070562907,0.0014047741,0.0016123248,0.0052685263,0.0038195492,0.015675012,0.0026010566,0.0021349275,0.010802213],"category_scores_gemma":[0.03297362,0.00079511217,0.0014407666,0.00973438,0.003591967,0.02868064,0.01090026,0.0050454116,0.010592469],"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":[0.00017227986,0.00026537132,0.017097525,0.00044144274,0.00019852885,0.00023499028,0.0020103264,0.007770222,0.0013666274,0.24380837,0.29430535,0.43232897],"study_design_scores_gemma":[0.000038890863,0.000081139435,0.0029426091,0.00029692284,0.00006761239,0.0001524477,0.0043465244,0.031037316,0.0019222508,0.5138356,0.4451996,0.000079022626],"about_ca_topic_score_codex":0.0061003193,"about_ca_topic_score_gemma":0.011297418,"teacher_disagreement_score":0.015675012,"about_ca_system_score_codex":0.0018077305,"about_ca_system_score_gemma":0.0052041914,"threshold_uncertainty_score":0.037317693},"labels":[],"label_agreement":null},{"id":"W2560538820","doi":"10.1109/epec.2016.7771716","title":"Incremental mining of frequent power consumption patterns from smart meters big data","year":2016,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Power consumption; Big data; Computer science; Consumption (sociology); Power (physics); Data mining","score_opus":0.10141207738498183,"score_gpt":0.2858875855523907,"score_spread":0.18447550816740887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560538820","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6283432,0.00079479226,0.3632884,0.00080490485,0.00010861031,0.00031750137,0.0026153028,0.0019228023,0.0018044711],"genre_scores_gemma":[0.8457419,0.00025445322,0.14924209,0.000078690064,0.00006198724,0.00014704648,0.0038609356,0.00003638399,0.00057638757],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987167,0.00021972654,0.00014685909,0.00031300553,0.0004720103,0.00013163635],"domain_scores_gemma":[0.99549854,0.0021517852,0.00051599613,0.00073491,0.0009219274,0.00017683321],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001216538,0.00056925206,0.00088414084,0.0021569273,0.00047966331,0.0010021009,0.0016780443,0.0005171938,0.00031309662],"category_scores_gemma":[0.007564394,0.00037884677,0.0006974214,0.0025533559,0.00028259555,0.0016347226,0.0009666939,0.00074516324,0.00020901299],"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":[0.0009838346,0.0013070124,0.15976194,0.0005550743,0.0005751847,0.002369162,0.0010622267,0.13744472,0.032413825,0.005222396,0.008922303,0.64938235],"study_design_scores_gemma":[0.000029608585,0.00016867963,0.019286582,0.000022846469,0.00009114227,0.00063853414,0.00033101012,0.9621881,0.00853228,0.0060292603,0.0026586656,0.000023267034],"about_ca_topic_score_codex":0.003484441,"about_ca_topic_score_gemma":0.007308276,"teacher_disagreement_score":0.003484441,"about_ca_system_score_codex":0.00032540204,"about_ca_system_score_gemma":0.0009244538,"threshold_uncertainty_score":0.006928265},"labels":[],"label_agreement":null},{"id":"W2561054455","doi":"10.1080/09332480.2000.10542208","title":"On the Edge: Statistics &amp; Computing","year":2000,"lang":"en","type":"article","venue":"CHANCE","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":"Western University","funders":"","keywords":"Computer science; Enhanced Data Rates for GSM Evolution; Statistics; Mathematics; Artificial intelligence","score_opus":0.02965125121622192,"score_gpt":0.27423227500655234,"score_spread":0.24458102379033042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2561054455","genre_codex":"methods","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029960547,0.06985709,0.81384546,0.051693503,0.008495977,0.00007560096,0.00094732974,0.0035729357,0.04851612],"genre_scores_gemma":[0.20769075,0.07988325,0.5797029,0.025351802,0.03671509,0.00075910264,0.0023644792,0.0039332462,0.06359948],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955427,0.0021717364,0.00027305027,0.0006897128,0.0011342026,0.0001885649],"domain_scores_gemma":[0.97257835,0.020323554,0.00088243926,0.0026385114,0.0022968973,0.001280233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047702594,0.0015805042,0.0029791216,0.00426072,0.0018520092,0.009133458,0.0022183657,0.0035273419,0.021351723],"category_scores_gemma":[0.04043169,0.0011452362,0.00094948174,0.010699172,0.0076195872,0.017951248,0.0043580686,0.00853783,0.010835643],"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":[0.000082549974,0.000038563307,0.0011383849,0.00043778398,0.000051928342,0.00011436799,0.0001712687,0.003002633,0.0002494645,0.6159709,0.16207723,0.21666491],"study_design_scores_gemma":[0.000015668435,0.000018533761,0.00024702045,0.00015092298,0.00001954539,0.00012456864,0.000061243976,0.013968981,0.00020533001,0.89917725,0.08598599,0.000024946276],"about_ca_topic_score_codex":0.002816008,"about_ca_topic_score_gemma":0.0024713038,"teacher_disagreement_score":0.021351723,"about_ca_system_score_codex":0.0020330304,"about_ca_system_score_gemma":0.002458544,"threshold_uncertainty_score":0.07142866},"labels":[],"label_agreement":null},{"id":"W256194962","doi":"10.1007/978-3-319-11116-2_56","title":"Efficient Frequent Itemset Mining from Dense Data Streams","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Defense Acquisition Program Administration; Natural Sciences and Engineering Research Council of Canada","keywords":"Data stream mining; Computer science; Data mining; Data stream; STREAMS; Streaming data; Data structure","score_opus":0.031520479952004035,"score_gpt":0.2647085281967489,"score_spread":0.23318804824474487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W256194962","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044042118,0.0015110448,0.9498915,0.00024849834,0.00013384377,0.00020354817,0.0014345661,0.0017532974,0.0007815594],"genre_scores_gemma":[0.23006022,0.0013342053,0.757331,0.00010328618,0.00022958832,0.00028443098,0.008269508,0.0001484709,0.0022392636],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985434,0.00021767797,0.00020564414,0.00025603155,0.0006657497,0.000111410205],"domain_scores_gemma":[0.9954336,0.0028315522,0.00024965932,0.0005985205,0.00076961826,0.00011690902],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012087196,0.0009653985,0.002003915,0.0028932584,0.0006523877,0.0018310831,0.0020097347,0.0009627192,0.0012860763],"category_scores_gemma":[0.007876573,0.0008406066,0.0014136496,0.004585657,0.00030866277,0.0025610123,0.0014327816,0.0013301071,0.0012141817],"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":[0.0007155513,0.00031750917,0.007894637,0.0006516598,0.00033519662,0.0008341655,0.00022490905,0.065256506,0.014308763,0.0055525526,0.009679428,0.8942291],"study_design_scores_gemma":[0.000051124556,0.00012226353,0.0016303018,0.00004596274,0.00008137109,0.00082066207,0.00013503636,0.96992034,0.006424144,0.017611526,0.0031348846,0.000022341119],"about_ca_topic_score_codex":0.0011337516,"about_ca_topic_score_gemma":0.0015471786,"teacher_disagreement_score":0.0028932584,"about_ca_system_score_codex":0.0003197994,"about_ca_system_score_gemma":0.0008210314,"threshold_uncertainty_score":0.0063924193},"labels":[],"label_agreement":null},{"id":"W2563263349","doi":"10.1080/09332480.2000.10542237","title":"On the Edge: Statistics &amp; Computing","year":2000,"lang":"en","type":"article","venue":"CHANCE","topic":"Data Mining Algorithms 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":"Western University","funders":"","keywords":"Computer science; Enhanced Data Rates for GSM Evolution; Statistics; Mathematics; Artificial intelligence","score_opus":0.02965125121622192,"score_gpt":0.27423227500655234,"score_spread":0.24458102379033042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2563263349","genre_codex":"methods","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029960547,0.06985709,0.81384546,0.051693503,0.008495977,0.00007560096,0.00094732974,0.0035729357,0.04851612],"genre_scores_gemma":[0.20769075,0.07988325,0.5797029,0.025351802,0.03671509,0.00075910264,0.0023644792,0.0039332462,0.06359948],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955427,0.0021717364,0.00027305027,0.0006897128,0.0011342026,0.0001885649],"domain_scores_gemma":[0.97257835,0.020323554,0.00088243926,0.0026385114,0.0022968973,0.001280233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047702594,0.0015805042,0.0029791216,0.00426072,0.0018520092,0.009133458,0.0022183657,0.0035273419,0.021351723],"category_scores_gemma":[0.04043169,0.0011452362,0.00094948174,0.010699172,0.0076195872,0.017951248,0.0043580686,0.00853783,0.010835643],"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":[0.000082549974,0.000038563307,0.0011383849,0.00043778398,0.000051928342,0.00011436799,0.0001712687,0.003002633,0.0002494645,0.6159709,0.16207723,0.21666491],"study_design_scores_gemma":[0.000015668435,0.000018533761,0.00024702045,0.00015092298,0.00001954539,0.00012456864,0.000061243976,0.013968981,0.00020533001,0.89917725,0.08598599,0.000024946276],"about_ca_topic_score_codex":0.002816008,"about_ca_topic_score_gemma":0.0024713038,"teacher_disagreement_score":0.021351723,"about_ca_system_score_codex":0.0020330304,"about_ca_system_score_gemma":0.002458544,"threshold_uncertainty_score":0.07142866},"labels":[],"label_agreement":null},{"id":"W2564333292","doi":"10.1080/09332480.2000.10542193","title":"On the Edge: Statistics &amp; Computing","year":2000,"lang":"en","type":"article","venue":"CHANCE","topic":"Data Mining Algorithms and Applications","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":"Western University","funders":"","keywords":"Computer science; Enhanced Data Rates for GSM Evolution; Statistics; Mathematics; Artificial intelligence","score_opus":0.02965125121622192,"score_gpt":0.27423227500655234,"score_spread":0.24458102379033042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2564333292","genre_codex":"methods","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029960547,0.06985709,0.81384546,0.051693503,0.008495977,0.00007560096,0.00094732974,0.0035729357,0.04851612],"genre_scores_gemma":[0.20769075,0.07988325,0.5797029,0.025351802,0.03671509,0.00075910264,0.0023644792,0.0039332462,0.06359948],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955427,0.0021717364,0.00027305027,0.0006897128,0.0011342026,0.0001885649],"domain_scores_gemma":[0.97257835,0.020323554,0.00088243926,0.0026385114,0.0022968973,0.001280233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047702594,0.0015805042,0.0029791216,0.00426072,0.0018520092,0.009133458,0.0022183657,0.0035273419,0.021351723],"category_scores_gemma":[0.04043169,0.0011452362,0.00094948174,0.010699172,0.0076195872,0.017951248,0.0043580686,0.00853783,0.010835643],"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":[0.000082549974,0.000038563307,0.0011383849,0.00043778398,0.000051928342,0.00011436799,0.0001712687,0.003002633,0.0002494645,0.6159709,0.16207723,0.21666491],"study_design_scores_gemma":[0.000015668435,0.000018533761,0.00024702045,0.00015092298,0.00001954539,0.00012456864,0.000061243976,0.013968981,0.00020533001,0.89917725,0.08598599,0.000024946276],"about_ca_topic_score_codex":0.002816008,"about_ca_topic_score_gemma":0.0024713038,"teacher_disagreement_score":0.021351723,"about_ca_system_score_codex":0.0020330304,"about_ca_system_score_gemma":0.002458544,"threshold_uncertainty_score":0.07142866},"labels":[],"label_agreement":null},{"id":"W2565034015","doi":"10.1109/iisa.2016.7785408","title":"Fuzzy joins in MapReduce: Edit and Jaccard distance","year":2016,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Jaccard index; Joins; Computer science; Edit distance; Similarity (geometry); Data mining; Fuzzy logic; Join (topology); Cluster analysis; Information retrieval; Artificial intelligence; Theoretical computer science; Mathematics; Programming language","score_opus":0.01043677729507726,"score_gpt":0.23206183516027176,"score_spread":0.2216250578651945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2565034015","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0629938,0.0015341918,0.92632437,0.0005895619,0.00050583086,0.00045220862,0.00048309358,0.0019960594,0.00512093],"genre_scores_gemma":[0.32850155,0.00074408995,0.6653796,0.00023840816,0.00035140512,0.0002735741,0.0009602774,0.0003162019,0.0032349646],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9940566,0.0013252241,0.00043037307,0.0010104469,0.002886974,0.00029046138],"domain_scores_gemma":[0.9920353,0.0033061863,0.00043837566,0.0019820598,0.0018730348,0.00036500866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00519826,0.0010594764,0.0020586515,0.0030177443,0.0024561044,0.003357116,0.003442199,0.001474777,0.0014078096],"category_scores_gemma":[0.013579882,0.00068582234,0.001397677,0.0050832215,0.0011821492,0.006357299,0.0028302611,0.0021054868,0.00073251454],"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":[0.0016059071,0.0014099615,0.0071940506,0.00076187676,0.0005684814,0.00035975332,0.0017938399,0.15729383,0.014129046,0.15045923,0.019197185,0.64522684],"study_design_scores_gemma":[0.00017030265,0.0006826127,0.0024423653,0.000052595587,0.00014758973,0.0006245324,0.0007423674,0.79905784,0.021073902,0.14810412,0.026725216,0.00017657981],"about_ca_topic_score_codex":0.004352004,"about_ca_topic_score_gemma":0.0056280177,"teacher_disagreement_score":0.00519826,"about_ca_system_score_codex":0.0011825901,"about_ca_system_score_gemma":0.0021674887,"threshold_uncertainty_score":0.027491331},"labels":[],"label_agreement":null},{"id":"W2565866840","doi":"10.1080/09332480.2000.10542224","title":"On the Edge: Statistics &amp; Computing","year":2000,"lang":"en","type":"article","venue":"CHANCE","topic":"Data Mining Algorithms 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":"Western University","funders":"","keywords":"Computer science; Statistics; Enhanced Data Rates for GSM Evolution; Mathematics; Artificial intelligence","score_opus":0.02965125121622192,"score_gpt":0.27423227500655234,"score_spread":0.24458102379033042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2565866840","genre_codex":"methods","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029960547,0.06985709,0.81384546,0.051693503,0.008495977,0.00007560096,0.00094732974,0.0035729357,0.04851612],"genre_scores_gemma":[0.20769075,0.07988325,0.5797029,0.025351802,0.03671509,0.00075910264,0.0023644792,0.0039332462,0.06359948],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955427,0.0021717364,0.00027305027,0.0006897128,0.0011342026,0.0001885649],"domain_scores_gemma":[0.97257835,0.020323554,0.00088243926,0.0026385114,0.0022968973,0.001280233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047702594,0.0015805042,0.0029791216,0.00426072,0.0018520092,0.009133458,0.0022183657,0.0035273419,0.021351723],"category_scores_gemma":[0.04043169,0.0011452362,0.00094948174,0.010699172,0.0076195872,0.017951248,0.0043580686,0.00853783,0.010835643],"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":[0.000082549974,0.000038563307,0.0011383849,0.00043778398,0.000051928342,0.00011436799,0.0001712687,0.003002633,0.0002494645,0.6159709,0.16207723,0.21666491],"study_design_scores_gemma":[0.000015668435,0.000018533761,0.00024702045,0.00015092298,0.00001954539,0.00012456864,0.000061243976,0.013968981,0.00020533001,0.89917725,0.08598599,0.000024946276],"about_ca_topic_score_codex":0.002816008,"about_ca_topic_score_gemma":0.0024713038,"teacher_disagreement_score":0.021351723,"about_ca_system_score_codex":0.0020330304,"about_ca_system_score_gemma":0.002458544,"threshold_uncertainty_score":0.07142866},"labels":[],"label_agreement":null},{"id":"W2566763598","doi":"10.5539/cis.v10n1p23","title":"The Impact of the Pattern-Growth Ordering on the Performances of Pattern Growth-Based Sequential Pattern Mining Algorithms","year":2016,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Data mining; Pruning; Prefix; Field (mathematics); Set (abstract data type); Algorithm; Sequential Pattern Mining; Sequence (biology); Web mining; Pattern search; Tree (set theory); Suffix tree; Pattern recognition (psychology); Data structure; Artificial intelligence; Mathematics; Web page","score_opus":0.017987035979596302,"score_gpt":0.2576322095092082,"score_spread":0.23964517352961187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2566763598","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8223339,0.0054141064,0.16002451,0.001126456,0.00019621389,0.0002863908,0.0013665945,0.0024736496,0.006778162],"genre_scores_gemma":[0.8437768,0.0014603763,0.15004699,0.00015361341,0.00007143755,0.00013055849,0.0030026694,0.00024964014,0.0011078946],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9933955,0.0018024306,0.0009962049,0.001068298,0.0020829092,0.0006546519],"domain_scores_gemma":[0.9400134,0.04734775,0.002275483,0.0051393854,0.004088492,0.0011355557],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007856569,0.0016470985,0.0017294242,0.0023682972,0.0013547176,0.0028355643,0.0016027396,0.0012292097,0.0015704997],"category_scores_gemma":[0.034777947,0.00046675015,0.0006640602,0.0032538425,0.00090634596,0.0043605417,0.0014455807,0.0017224877,0.00075757375],"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":[0.0036336577,0.0015737055,0.0638458,0.00076309923,0.00033555657,0.00041007678,0.00043631846,0.3539589,0.022469547,0.0071818368,0.0046841283,0.54070735],"study_design_scores_gemma":[0.0001199741,0.0010325054,0.0059485724,0.000055087356,0.000108580614,0.0004795999,0.00031250063,0.9629762,0.019314155,0.0075391815,0.0020741164,0.000039470324],"about_ca_topic_score_codex":0.0035652167,"about_ca_topic_score_gemma":0.004011126,"teacher_disagreement_score":0.007856569,"about_ca_system_score_codex":0.0012617428,"about_ca_system_score_gemma":0.0029818818,"threshold_uncertainty_score":0.04154998},"labels":[],"label_agreement":null},{"id":"W2572737325","doi":"10.1109/bibm.2016.7822641","title":"Mining sequential patterns from uncertain big DNA in the spark framework","year":2016,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Big data; Computer science; Scalability; Data mining; SPARK (programming language); DNA sequencing; Biomedicine; Data science; Bioinformatics; DNA; Database; Biology","score_opus":0.0452226995074654,"score_gpt":0.2825070435540311,"score_spread":0.2372843440465657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2572737325","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054580547,0.00067526556,0.93272585,0.00042503962,0.00010093752,0.00027199488,0.0022770877,0.008262258,0.00068101485],"genre_scores_gemma":[0.19723599,0.00039518473,0.7940035,0.00015447786,0.00009119872,0.0003304929,0.0068652118,0.00023116522,0.00069279666],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982881,0.00016352156,0.0001836066,0.0005299845,0.00065328775,0.00018138808],"domain_scores_gemma":[0.9979594,0.00072190166,0.00029641422,0.00033695935,0.00045369545,0.00023160224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014977362,0.0012704161,0.0018299251,0.0024397701,0.0011922801,0.0012851531,0.0026380573,0.00085995696,0.00060498406],"category_scores_gemma":[0.004655768,0.0006635737,0.0017376348,0.003117288,0.0006772449,0.0019152253,0.0013858059,0.00097155443,0.0004934707],"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":[0.0019572491,0.0006583406,0.021648789,0.0012428593,0.00071132625,0.0032637515,0.0008402079,0.47280076,0.043167703,0.021121355,0.022902085,0.40968564],"study_design_scores_gemma":[0.000096683354,0.000084204155,0.001123572,0.000011675464,0.00003854199,0.00047735855,0.0001478696,0.9658762,0.0053407606,0.023124797,0.0036527258,0.000025636087],"about_ca_topic_score_codex":0.0051897424,"about_ca_topic_score_gemma":0.0070741638,"teacher_disagreement_score":0.0051897424,"about_ca_system_score_codex":0.0005359966,"about_ca_system_score_gemma":0.0028794568,"threshold_uncertainty_score":0.010319054},"labels":[],"label_agreement":null},{"id":"W2573482191","doi":"10.1109/ictai.2016.0151","title":"An Efficient Approach for Mining Frequent Patterns over Uncertain Data Streams","year":2016,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Data stream mining; Uncertain data; Sliding window protocol; Data mining; Probabilistic logic; Big data; Data stream; Tree (set theory); Task (project management); Data science; Artificial intelligence; Window (computing); Engineering","score_opus":0.0658649504474581,"score_gpt":0.3203842682322821,"score_spread":0.254519317784824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2573482191","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011553683,0.00031764086,0.9869812,0.00014760012,0.000026680565,0.000075342774,0.0002809798,0.00044169766,0.0001751448],"genre_scores_gemma":[0.17761363,0.00055944535,0.8197496,0.00008496305,0.000088937486,0.00027219258,0.001100678,0.000050541163,0.0004801319],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99839765,0.00023688037,0.00022839384,0.00032242775,0.0007056655,0.000108933324],"domain_scores_gemma":[0.9963987,0.0019354402,0.0004503324,0.00037599096,0.0007420974,0.00009739799],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014895067,0.00083821063,0.0012776471,0.0029324633,0.00073922134,0.0010846597,0.0019991067,0.0009599221,0.00060394994],"category_scores_gemma":[0.008498239,0.00056688354,0.0011222402,0.0046870094,0.00044262043,0.0036040808,0.0010980787,0.0009756865,0.00032257702],"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":[0.0004089796,0.00020201867,0.008557604,0.0004513707,0.0002101269,0.0006552112,0.00038189057,0.2615394,0.012496957,0.020684252,0.005941922,0.6884703],"study_design_scores_gemma":[0.000018172039,0.000051582076,0.0004014859,0.000010346959,0.000020438914,0.0002630371,0.000038166792,0.9851193,0.002023118,0.010672798,0.0013703293,0.0000112208345],"about_ca_topic_score_codex":0.0027625298,"about_ca_topic_score_gemma":0.002970455,"teacher_disagreement_score":0.0029324633,"about_ca_system_score_codex":0.00053453847,"about_ca_system_score_gemma":0.0013257047,"threshold_uncertainty_score":0.00787735},"labels":[],"label_agreement":null},{"id":"W2575204312","doi":"10.1109/bibm.2016.7822529","title":"Top-k utility-based gene regulation sequential pattern discovery","year":2016,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Microarray analysis techniques; Microarray; Computer science; Sequential Pattern Mining; Data mining; Computational biology; Gene; Gene expression; Biology; Genetics","score_opus":0.023415602932811766,"score_gpt":0.2548906680165803,"score_spread":0.23147506508376853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2575204312","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.113297366,0.001111791,0.8785046,0.0002756635,0.000048770948,0.00030032443,0.002311206,0.0032156291,0.00093478366],"genre_scores_gemma":[0.60978365,0.00052245636,0.38181263,0.00014809638,0.000054315446,0.0003655158,0.005489201,0.00015497264,0.0016692479],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988165,0.000220964,0.00012388009,0.00027588094,0.00038515916,0.00017768997],"domain_scores_gemma":[0.9982333,0.0008447945,0.00018329473,0.00024538024,0.00039067297,0.00010252302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012048073,0.0009916953,0.0018426349,0.0031833777,0.0009256221,0.001109038,0.0017550488,0.0007660588,0.0011093746],"category_scores_gemma":[0.005044969,0.00036093002,0.0016532715,0.0037855743,0.000567637,0.0011497445,0.0010132939,0.0009181104,0.0005528801],"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":[0.0011362602,0.0005242477,0.048549887,0.0009265987,0.00042495545,0.00087558175,0.0003655583,0.20917097,0.03136865,0.010793711,0.0091720065,0.68669164],"study_design_scores_gemma":[0.00003297075,0.00009045792,0.0036369257,0.000015829739,0.00006192152,0.00036065278,0.00007228508,0.9760783,0.007860365,0.010021368,0.0017456745,0.00002321176],"about_ca_topic_score_codex":0.0060449345,"about_ca_topic_score_gemma":0.009517405,"teacher_disagreement_score":0.0060449345,"about_ca_system_score_codex":0.0009541379,"about_ca_system_score_gemma":0.0017658209,"threshold_uncertainty_score":0.012019455},"labels":[],"label_agreement":null},{"id":"W2575255383","doi":"10.1109/wi.2016.0111","title":"Web Page Recommendation Based on Bitwise Frequent Pattern Mining","year":2016,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Web mining; Data mining; Web page; Association rule learning; Information retrieval; Apriori algorithm; World Wide Web","score_opus":0.025276828249077968,"score_gpt":0.25681619877679307,"score_spread":0.23153937052771512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2575255383","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.093720004,0.0016442536,0.89716005,0.00061609026,0.00020391561,0.00041069862,0.0014559766,0.0020022162,0.0027866936],"genre_scores_gemma":[0.46456125,0.0012138826,0.5265294,0.0002699784,0.00020284775,0.0003857205,0.0036102254,0.0000887592,0.0031378972],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997872,0.00031900514,0.00030377277,0.0004632304,0.000880348,0.00016154234],"domain_scores_gemma":[0.996292,0.0015890443,0.00046521614,0.00037692377,0.0011512707,0.0001255531],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001219018,0.00082216697,0.0017125225,0.005049339,0.00087592704,0.0010990781,0.001760236,0.0010012038,0.0015785551],"category_scores_gemma":[0.007199505,0.0004316249,0.0010420965,0.005790342,0.00033236938,0.0020700523,0.00069920026,0.0008593824,0.0011256085],"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":[0.0008452868,0.0006003165,0.025944183,0.00047863348,0.00034483042,0.00094517117,0.00019274715,0.058205076,0.013190796,0.0068917894,0.009955849,0.8824054],"study_design_scores_gemma":[0.00006432675,0.00018007089,0.004045466,0.000039773906,0.000111320194,0.0010645984,0.00006548884,0.9757681,0.0046249605,0.011191247,0.0028057473,0.00003886878],"about_ca_topic_score_codex":0.004131105,"about_ca_topic_score_gemma":0.0052372515,"teacher_disagreement_score":0.005049339,"about_ca_system_score_codex":0.00041814783,"about_ca_system_score_gemma":0.0008473328,"threshold_uncertainty_score":0.008214116},"labels":[],"label_agreement":null},{"id":"W2575878511","doi":"10.4108/eai.18-1-2017.152103","title":"A pattern growth-based sequential pattern mining algorithm called prefixSuffixSpan","year":2017,"lang":"en","type":"article","venue":"ICST Transactions on Scalable Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Sequential Pattern Mining; Data mining; Computer science; Field (mathematics); GSP Algorithm; Set (abstract data type); Sequence (biology); Data stream mining; Association rule learning; Mathematics; Apriori algorithm","score_opus":0.024815392391262462,"score_gpt":0.25626347327986765,"score_spread":0.2314480808886052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2575878511","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038187478,0.00089135027,0.94977784,0.0005508946,0.00033404573,0.00053261465,0.0012428426,0.0049936706,0.0034893001],"genre_scores_gemma":[0.14443888,0.0006230995,0.8441104,0.0003418298,0.00014056951,0.00054718717,0.0036030607,0.00031184178,0.0058830664],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99850523,0.0002031396,0.00016133777,0.00037842977,0.0006519565,0.00010001319],"domain_scores_gemma":[0.99816716,0.0006115744,0.0001689717,0.0003466423,0.0006018488,0.000103783044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017227207,0.0011163056,0.0016984515,0.0031425566,0.0009826837,0.001100613,0.0022289187,0.0009962465,0.004117593],"category_scores_gemma":[0.004983523,0.00045866845,0.0009880362,0.0045623723,0.0006405038,0.0020593177,0.0015976864,0.0012357756,0.0017829727],"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":[0.00039654167,0.00033903035,0.0069049327,0.00028207997,0.00016516387,0.00037507524,0.00016451791,0.032308742,0.013731169,0.00824668,0.01650946,0.92057663],"study_design_scores_gemma":[0.00009160989,0.00039759438,0.002288673,0.00004776254,0.00008851843,0.0014488515,0.000101162776,0.9362813,0.017741807,0.014742124,0.026725398,0.000045198634],"about_ca_topic_score_codex":0.0028554,"about_ca_topic_score_gemma":0.0046779024,"teacher_disagreement_score":0.004117593,"about_ca_system_score_codex":0.00051121385,"about_ca_system_score_gemma":0.0022514402,"threshold_uncertainty_score":0.013774693},"labels":[],"label_agreement":null},{"id":"W2578082361","doi":"","title":"Using Semantic Web Technologies for Explaining and Predicting Abnormal Expenses.","year":2016,"lang":"en","type":"article","venue":"International Semantic Web Conference","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":"University of Waterloo","funders":"","keywords":"Computer science; Semantic Web; Information retrieval","score_opus":0.05009066489494174,"score_gpt":0.29932951649541545,"score_spread":0.2492388516004737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2578082361","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7061123,0.0067622513,0.20499386,0.005557497,0.0005612059,0.0005723386,0.024035674,0.0043512313,0.047053646],"genre_scores_gemma":[0.93005264,0.0018281469,0.057106346,0.00017524225,0.00013034305,0.00011141317,0.008630001,0.000096466516,0.0018693078],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99911875,0.0002167115,0.0001202109,0.00012333726,0.0003483391,0.00007263891],"domain_scores_gemma":[0.9970161,0.0015379527,0.00062249374,0.00017867678,0.00055561215,0.000089199064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011448179,0.00072367414,0.00038741148,0.0074471603,0.00040963327,0.002176522,0.000545444,0.0010739481,0.0023780842],"category_scores_gemma":[0.007483835,0.00019524772,0.0007351846,0.005133585,0.00029927632,0.0036173915,0.00058754353,0.00072251,0.0008840734],"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":[0.00093395537,0.0011583238,0.39852014,0.0009482352,0.00078403245,0.0024393685,0.0007201132,0.04300145,0.0056485045,0.043389358,0.03274876,0.46970767],"study_design_scores_gemma":[0.00013647502,0.0002795893,0.14408568,0.0006925204,0.0007483508,0.0015928993,0.0031807302,0.62469006,0.015058282,0.1588091,0.05058084,0.00014544463],"about_ca_topic_score_codex":0.0065585175,"about_ca_topic_score_gemma":0.0091365995,"teacher_disagreement_score":0.0074471603,"about_ca_system_score_codex":0.00084315997,"about_ca_system_score_gemma":0.0010579833,"threshold_uncertainty_score":0.013040662},"labels":[],"label_agreement":null},{"id":"W2578735219","doi":"10.20965/jaciii.2000.p0187","title":"Sampling Research on Advanced Computational Intelligence in Canada","year":2000,"lang":"en","type":"article","venue":"Journal of Advanced Computational Intelligence and Intelligent Informatics","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Computational intelligence; Diversity (politics); Selection (genetic algorithm); Library science; Intelligence analysis; Operations research; Artificial intelligence; Data science; Sociology; Engineering","score_opus":0.0725059410162873,"score_gpt":0.3655839460822779,"score_spread":0.2930780050659906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2578735219","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031146243,0.10014455,0.0098882755,0.14783697,0.0046995603,0.00033193905,0.0041949647,0.00026413886,0.7014935],"genre_scores_gemma":[0.47201458,0.17061111,0.012601244,0.014436389,0.001375085,0.0002807528,0.004182066,0.00032111708,0.3241777],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99208516,0.00094259705,0.0002847158,0.0006640403,0.0047691,0.0012544891],"domain_scores_gemma":[0.982176,0.0026586435,0.00048409993,0.00071112387,0.011603262,0.0023668068],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00554197,0.00075874454,0.0011708423,0.00847014,0.010531084,0.012347382,0.0018013702,0.0017163124,0.040501066],"category_scores_gemma":[0.018855937,0.0006836447,0.00069141533,0.026804125,0.006393014,0.00549783,0.0035392179,0.0032312232,0.0032604963],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0001423434,0.00008380666,0.009667326,0.0005064642,0.000055460274,0.00015960247,0.0028263815,0.0015562898,0.0002510514,0.58554053,0.24536505,0.15384561],"study_design_scores_gemma":[0.000054997883,0.00004038024,0.021883538,0.0010038706,0.000050492396,0.00012682521,0.006378997,0.0037631814,0.00043560864,0.081016295,0.8851642,0.00008166786],"about_ca_topic_score_codex":0.9789504,"about_ca_topic_score_gemma":0.9830179,"teacher_disagreement_score":0.8488877,"about_ca_system_score_codex":0.15111233,"about_ca_system_score_gemma":0.23488206,"threshold_uncertainty_score":0.9845894},"labels":[],"label_agreement":null},{"id":"W2584045454","doi":"10.1109/bigdata.2016.7840678","title":"Distributed and parallel high utility sequential pattern mining","year":2016,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada); York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Correctness; Big data; Pruning; Process (computing); Data mining; Distributed memory; Distributed database; Sequence (biology); Distributed Computing Environment; Distributed computing; Parallel computing; Shared memory; Algorithm","score_opus":0.02436350499762241,"score_gpt":0.25156030257199147,"score_spread":0.22719679757436906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2584045454","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09120961,0.00048225105,0.90319407,0.00044154839,0.00007602087,0.00020822062,0.00043031643,0.0021331187,0.00182479],"genre_scores_gemma":[0.56606966,0.0002428236,0.42995244,0.00011598257,0.00007350579,0.00021524246,0.0011419542,0.000099027064,0.0020894322],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981756,0.00037815154,0.0001529865,0.0005936531,0.0005227447,0.00017685922],"domain_scores_gemma":[0.9968072,0.001207167,0.0002985413,0.00084955146,0.0006594964,0.00017810453],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019925474,0.000689558,0.0011177874,0.001570137,0.0010511761,0.0011772554,0.0020468456,0.00061974506,0.0010614545],"category_scores_gemma":[0.005628981,0.00045093993,0.0008358382,0.0027640066,0.0007385454,0.001955141,0.0014746204,0.00076616317,0.00038243664],"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":[0.0008757708,0.0005257484,0.022675846,0.00047722392,0.00031096066,0.0008772671,0.0004374334,0.3231034,0.016112873,0.021588752,0.009390548,0.6036242],"study_design_scores_gemma":[0.00006555316,0.00008512945,0.001681851,0.000007337557,0.000031633215,0.00032496804,0.000115139395,0.96585745,0.0047018556,0.02505454,0.0020631372,0.000011386479],"about_ca_topic_score_codex":0.003294025,"about_ca_topic_score_gemma":0.005071501,"teacher_disagreement_score":0.003294025,"about_ca_system_score_codex":0.0005653581,"about_ca_system_score_gemma":0.0018985495,"threshold_uncertainty_score":0.010537744},"labels":[],"label_agreement":null},{"id":"W2585472988","doi":"10.1007/s10994-016-5617-1","title":"Memory-adaptive high utility sequential pattern mining over data streams","year":2017,"lang":"en","type":"article","venue":"Machine Learning","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":32,"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; Clickstream; Data stream mining; Data stream; Data mining; Tree (set theory); Web server; The Internet","score_opus":0.05879960194168286,"score_gpt":0.31258075664599344,"score_spread":0.25378115470431056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2585472988","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.078561924,0.00044259257,0.9175768,0.00024121148,0.00007186244,0.00009064818,0.00024272666,0.0020803162,0.0006919059],"genre_scores_gemma":[0.7422067,0.00026048868,0.25414494,0.00012949239,0.000105772895,0.0001268274,0.00055166025,0.000139292,0.0023348876],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989237,0.00021062637,0.00011991312,0.0002313728,0.00038846204,0.00012587491],"domain_scores_gemma":[0.9947914,0.0027746349,0.00034397183,0.0010816264,0.00081482175,0.00019356444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017193968,0.0007386685,0.0011551221,0.0015068945,0.000519698,0.0012266962,0.0020834506,0.00058830256,0.0013333325],"category_scores_gemma":[0.010755144,0.0005230241,0.0004929305,0.002304682,0.000482101,0.0020452703,0.0019211695,0.001001909,0.0005289599],"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":[0.0021648929,0.00047527323,0.011069282,0.00024508146,0.00016335944,0.00036440324,0.00020528551,0.157492,0.015099485,0.0090806335,0.0051233848,0.79851687],"study_design_scores_gemma":[0.000032102515,0.00006636077,0.00053623196,0.0000060571324,0.000017081808,0.00008807048,0.000025762229,0.98773974,0.0033408075,0.00774725,0.000394989,0.0000055197233],"about_ca_topic_score_codex":0.0029129842,"about_ca_topic_score_gemma":0.0043812236,"teacher_disagreement_score":0.0029129842,"about_ca_system_score_codex":0.00043431658,"about_ca_system_score_gemma":0.0012468131,"threshold_uncertainty_score":0.009093165},"labels":[],"label_agreement":null},{"id":"W2586378516","doi":"10.24251/hicss.2017.110","title":"Introduction to Text Mining in Big Data Analytics Minitrack","year":2017,"lang":"en","type":"article","venue":"Proceedings of the ... Annual Hawaii International Conference on System Sciences/Proceedings of the Annual Hawaii International Conference on System Sciences","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Big data; Data science; Analytics; Data mining","score_opus":0.11863692897001825,"score_gpt":0.334029464992193,"score_spread":0.21539253602217473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2586378516","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020088442,0.112269185,0.60355437,0.12216812,0.10717136,0.0010366869,0.0043744873,0.006564309,0.040852584],"genre_scores_gemma":[0.016973931,0.12724543,0.45283425,0.05737323,0.15962136,0.002315212,0.013765095,0.004832336,0.16503917],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99299365,0.0016597317,0.0008582512,0.0016211936,0.0024963235,0.00037086333],"domain_scores_gemma":[0.9652416,0.017251892,0.0010947182,0.0032488029,0.010187197,0.0029756818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010809339,0.0016279303,0.0015556788,0.006893835,0.0025172064,0.010183025,0.0036561778,0.005826013,0.03298813],"category_scores_gemma":[0.022848327,0.001699621,0.0021988573,0.0077736033,0.0027644115,0.015740184,0.005643399,0.013161771,0.025980093],"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":[0.00009437541,0.0001875768,0.0007213577,0.001062239,0.00007674108,0.00015377352,0.00057341816,0.0010958113,0.002658153,0.04117337,0.5742367,0.3779665],"study_design_scores_gemma":[0.000017242104,0.00006546659,0.0007510934,0.00052342116,0.00001540015,0.00031914012,0.0001250499,0.0027293884,0.00067025644,0.032393686,0.9623216,0.00006836804],"about_ca_topic_score_codex":0.0019707622,"about_ca_topic_score_gemma":0.0019481055,"teacher_disagreement_score":0.03298813,"about_ca_system_score_codex":0.0019425027,"about_ca_system_score_gemma":0.00328023,"threshold_uncertainty_score":0.11035627},"labels":[],"label_agreement":null},{"id":"W2587806622","doi":"10.1109/nafips.2016.7851587","title":"The role of conceptualization and operationalization in the use of secondary data","year":2016,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thompson Rivers University","funders":"Directorate for Biological Sciences","keywords":"Operationalization; Conceptualization; Computer science; Data science; Context (archaeology); Process (computing); Interpretation (philosophy); Data collection; Fuzzy logic; Management science; Artificial intelligence; Epistemology; Engineering; Sociology; Programming language; Social science","score_opus":0.06613311752582503,"score_gpt":0.2748919818322194,"score_spread":0.2087588643063944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2587806622","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017361503,0.008126106,0.9353351,0.025399664,0.00051908835,0.00052025844,0.00027953862,0.00013975486,0.0123190535],"genre_scores_gemma":[0.37000278,0.0052642855,0.6174769,0.003036035,0.0008860987,0.0019203039,0.00056674256,0.00014092862,0.0007059446],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8423,0.123876855,0.009669388,0.0077997902,0.014633243,0.0017207259],"domain_scores_gemma":[0.64528227,0.28635386,0.013618122,0.03846604,0.0137716,0.0025081872],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1724874,0.0019778474,0.0032893694,0.012938388,0.0037357628,0.019538488,0.0057453634,0.0042069335,0.0015760778],"category_scores_gemma":[0.20486252,0.0014315159,0.0031741294,0.017556507,0.041404538,0.047239944,0.010826754,0.012033524,0.00037977647],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034992314,0.000053452604,0.0016959759,0.0005214683,0.00008753123,0.00012253395,0.005814817,0.0015535257,0.0003278228,0.9652112,0.000741433,0.023835218],"study_design_scores_gemma":[0.000023740597,0.000061507875,0.000817975,0.00091903395,0.0000497245,0.00021388086,0.0034657344,0.008483895,0.00050560053,0.9736849,0.0117067695,0.000067233115],"about_ca_topic_score_codex":0.0036005413,"about_ca_topic_score_gemma":0.0020137106,"teacher_disagreement_score":0.8275126,"about_ca_system_score_codex":0.007255149,"about_ca_system_score_gemma":0.01114918,"threshold_uncertainty_score":0.9122114},"labels":[],"label_agreement":null},{"id":"W2588159480","doi":"10.29173/cais543","title":"Refining Ranked Retrieval Results for Legal Discovery Search Through Supervised Rank Aggregation","year":2013,"lang":"fr","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Ranking (information retrieval); Information retrieval; Relevance (law); Computer science; Context (archaeology); Metasearch engine; Rank (graph theory); Artificial intelligence; Humanities; Data mining; Mathematics; Geography; Philosophy; Political science; Search engine; Combinatorics; Web search query","score_opus":0.05107547805967532,"score_gpt":0.2819600116558389,"score_spread":0.23088453359616357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2588159480","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1639588,0.0035861675,0.79119146,0.0012365613,0.00018137599,0.0009338204,0.003380495,0.027040994,0.008490317],"genre_scores_gemma":[0.33052087,0.0005017969,0.6618811,0.00012913416,0.00012199585,0.000281288,0.0033294118,0.0004146334,0.002819796],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99253243,0.0018347555,0.00088089815,0.0007591347,0.0036009068,0.00039183485],"domain_scores_gemma":[0.97483575,0.011191381,0.0027630983,0.0033131514,0.00739012,0.00050642114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009585756,0.0011863388,0.0020742943,0.016822005,0.0015714136,0.005936464,0.0022878982,0.0013664588,0.003334523],"category_scores_gemma":[0.034210395,0.00061864796,0.0013507354,0.00680946,0.00058596395,0.0040352824,0.0015366011,0.0010695579,0.0029489878],"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":[0.0008290598,0.0007348292,0.018036306,0.00085053284,0.00040540932,0.00032242405,0.0011467536,0.020457638,0.022704493,0.0076419087,0.014109078,0.9127616],"study_design_scores_gemma":[0.00034551974,0.00094477594,0.012317121,0.00028002533,0.00071996055,0.00088348344,0.000890288,0.8600726,0.08216326,0.019208178,0.021865562,0.00030925026],"about_ca_topic_score_codex":0.010808528,"about_ca_topic_score_gemma":0.0193604,"teacher_disagreement_score":0.016822005,"about_ca_system_score_codex":0.0016776018,"about_ca_system_score_gemma":0.0036086007,"threshold_uncertainty_score":0.050694942},"labels":[],"label_agreement":null},{"id":"W2589334094","doi":"10.3390/ijgi6020048","title":"Geovisualization for Association Rule Mining in Oil and Gas Well Data","year":2017,"lang":"en","type":"article","venue":"ISPRS International Journal of Geo-Information","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Geovisualization; Association rule learning; Visualization; Data mining; Computer science; Association (psychology); Point (geometry); Interpolation (computer graphics); Data visualization; Data science; Information visualization; Artificial intelligence; Mathematics; Image (mathematics)","score_opus":0.02296606625052302,"score_gpt":0.32499137101562886,"score_spread":0.30202530476510586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2589334094","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.081608735,0.0009147976,0.8941939,0.00086594204,0.0001034276,0.00027649588,0.004841853,0.0141230915,0.003071806],"genre_scores_gemma":[0.40570894,0.0007960399,0.5876234,0.0001147634,0.00005170932,0.00036303603,0.0041934894,0.00034946576,0.00079921907],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988489,0.0005015706,0.00009935493,0.00017633461,0.0002836387,0.00009026239],"domain_scores_gemma":[0.99447083,0.0035100959,0.00045321567,0.0007063059,0.00067017745,0.00018934545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028820853,0.0007468765,0.000594708,0.0029814453,0.00031889122,0.0016709341,0.0012207731,0.0005392894,0.0026318668],"category_scores_gemma":[0.013142875,0.00030602008,0.000842178,0.0026109149,0.00043510285,0.0018431023,0.0017899385,0.0009872152,0.00079168123],"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":[0.0013270798,0.0004153806,0.013268299,0.0009413592,0.00020467686,0.000613848,0.002509195,0.083757676,0.028519135,0.015951114,0.019223444,0.83326876],"study_design_scores_gemma":[0.00013598152,0.0002223012,0.007930269,0.00021283759,0.000087431465,0.0004840811,0.0014469804,0.8939022,0.034509204,0.033356737,0.027595924,0.00011597379],"about_ca_topic_score_codex":0.0037835266,"about_ca_topic_score_gemma":0.004756177,"teacher_disagreement_score":0.0037835266,"about_ca_system_score_codex":0.00057032605,"about_ca_system_score_gemma":0.0008406005,"threshold_uncertainty_score":0.01524204},"labels":[],"label_agreement":null},{"id":"W2591701439","doi":"","title":"On efficient and effective association rule mining from XML data","year":2004,"lang":"en","type":"article","venue":"University of Southern Queensland ePrints (University of Southern Queensland)","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":"University of Toronto","funders":"","keywords":"Computer science; Association rule learning; XML; Generalization; Data mining; Tree (set theory); Automatic summarization; XML Schema (W3C); Metric (unit); Document Structure Description; Constraint (computer-aided design); Information retrieval; Theoretical computer science; XML Encryption; World Wide Web","score_opus":0.01045940233434889,"score_gpt":0.18988580219872375,"score_spread":0.17942639986437486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2591701439","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018412873,0.00242473,0.9739352,0.0011018645,0.00016166383,0.00028664686,0.0005524239,0.0018291724,0.0012954049],"genre_scores_gemma":[0.08388783,0.0017473848,0.9078755,0.00056161155,0.00027614753,0.0002794155,0.002146447,0.00018400534,0.003041622],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98952264,0.0037737016,0.0013414343,0.0009154258,0.003965308,0.0004814269],"domain_scores_gemma":[0.9602294,0.03165426,0.00089995225,0.0047798767,0.0021208515,0.0003156967],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0070423563,0.0012172086,0.002560676,0.005171353,0.0012399276,0.0035798484,0.003053408,0.0019884715,0.0021664505],"category_scores_gemma":[0.036798667,0.0013509928,0.0015832086,0.0067523797,0.0019147058,0.008758229,0.0037758886,0.0027185266,0.00143979],"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":[0.0004607832,0.00037350733,0.0026419263,0.00033656415,0.00019387637,0.0003496424,0.00031138692,0.06032109,0.0054579685,0.018943759,0.01100343,0.89960617],"study_design_scores_gemma":[0.00020261055,0.00021533827,0.00198446,0.000119374694,0.0001745608,0.0006901749,0.00029800032,0.88442624,0.009259111,0.08971425,0.0128548555,0.00006092529],"about_ca_topic_score_codex":0.006852586,"about_ca_topic_score_gemma":0.009203415,"teacher_disagreement_score":0.0070423563,"about_ca_system_score_codex":0.0009189126,"about_ca_system_score_gemma":0.0028497793,"threshold_uncertainty_score":0.037244022},"labels":[],"label_agreement":null},{"id":"W2594446691","doi":"10.1613/jair.2890","title":"Predicting the Performance of IDA* using Conditional Distributions","year":2010,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Heuristics; Heuristic; Generalization; Null-move heuristic; Tree (set theory); Distribution (mathematics)","score_opus":0.159017779237055,"score_gpt":0.42872760505917656,"score_spread":0.26970982582212155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2594446691","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4059825,0.0005814948,0.58344334,0.000542986,0.00006371285,0.00012936998,0.000505764,0.004807322,0.0039435807],"genre_scores_gemma":[0.8464265,0.00012096097,0.15195414,0.00007524826,0.000018833336,0.00013167871,0.00046047123,0.00016006794,0.0006520289],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984894,0.0004027772,0.00009502587,0.0003412959,0.00047854037,0.00019304617],"domain_scores_gemma":[0.9785296,0.016204424,0.0011369336,0.0020591556,0.0016673587,0.0004024643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037117063,0.0008334094,0.0009332098,0.002009729,0.0006824193,0.0012333979,0.0020231477,0.0012497933,0.0013761858],"category_scores_gemma":[0.024461584,0.0006220393,0.0006130026,0.0011504409,0.001013431,0.0027005405,0.0011972471,0.0019485265,0.00058110745],"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":[0.00048498006,0.00018165518,0.027866526,0.00010265819,0.000081809565,0.00005942199,0.000147989,0.76881874,0.0037296782,0.011615282,0.0025748734,0.18433638],"study_design_scores_gemma":[0.0000079301935,0.00002577548,0.00056608295,0.00000392724,0.000005448347,0.000011122505,0.000007428083,0.9952781,0.0014562022,0.0025130527,0.000118860095,0.000005995434],"about_ca_topic_score_codex":0.006913771,"about_ca_topic_score_gemma":0.0063533033,"teacher_disagreement_score":0.006913771,"about_ca_system_score_codex":0.0018024319,"about_ca_system_score_gemma":0.002093738,"threshold_uncertainty_score":0.019629598},"labels":[],"label_agreement":null},{"id":"W2602857294","doi":"10.1007/978-3-319-51367-6_9","title":"Frequent and Non-frequent Sequential Itemsets Detection","year":2017,"lang":"en","type":"book-chapter","venue":"Lecture notes in social networks","topic":"Data Mining Algorithms and Applications","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","funders":"","keywords":"Computer science; Data mining; Outlier; Process (computing); Anomaly detection; String (physics); Database transaction; Affinity analysis; Pattern recognition (psychology); Artificial intelligence; Association rule learning; Database; Mathematics","score_opus":0.018436623778116164,"score_gpt":0.2632224241336262,"score_spread":0.24478580035551,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2602857294","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2793435,0.008413195,0.69052184,0.00093892723,0.001356339,0.0006734103,0.007368136,0.002402384,0.008982212],"genre_scores_gemma":[0.56229705,0.0024075967,0.4096279,0.00023884438,0.00075727515,0.0003476942,0.012309157,0.00015925463,0.011855304],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969404,0.00039352884,0.0005427892,0.0007461487,0.0011792082,0.0001980804],"domain_scores_gemma":[0.99244726,0.0041698613,0.000639719,0.0007740571,0.0016197214,0.00034928438],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020945389,0.00092937076,0.0013524476,0.005137502,0.00095288514,0.0021724198,0.0016178156,0.0013430709,0.0030912403],"category_scores_gemma":[0.011053891,0.0004782517,0.0015449807,0.004676042,0.00042431714,0.0021679963,0.0010207887,0.00078644155,0.001873668],"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":[0.0016449927,0.00060302735,0.045960907,0.0013777341,0.00044876552,0.0032424526,0.00033475444,0.012538259,0.020842783,0.012477502,0.013847658,0.8866813],"study_design_scores_gemma":[0.00013856687,0.0011984322,0.036803067,0.0003023005,0.00061997067,0.015990049,0.001071453,0.79206896,0.0422805,0.06266911,0.046679683,0.0001779312],"about_ca_topic_score_codex":0.0006486681,"about_ca_topic_score_gemma":0.0013219744,"teacher_disagreement_score":0.005137502,"about_ca_system_score_codex":0.0003488709,"about_ca_system_score_gemma":0.00091565,"threshold_uncertainty_score":0.011077106},"labels":[],"label_agreement":null},{"id":"W2603902857","doi":"10.22230/src.2017v8n1a268","title":"Automatically Determining Versions of Scholarly Articles","year":2017,"lang":"en","type":"article","venue":"Scholarly and Research Communication","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Arcadia Fund","keywords":"Pairwise comparison; Computer science; Information retrieval; Simple (philosophy); Data science; Data mining; Artificial intelligence","score_opus":0.13746620222851497,"score_gpt":0.4056484116769164,"score_spread":0.26818220944840143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2603902857","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39012235,0.0052008796,0.5405972,0.0025271347,0.00223188,0.0013832443,0.0137991775,0.019976027,0.02416212],"genre_scores_gemma":[0.50554436,0.0015623998,0.4551569,0.00027106598,0.00077169086,0.00041135887,0.024399783,0.0017051474,0.0101773],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98582053,0.0030960927,0.0018205921,0.003505301,0.0052083046,0.0005491793],"domain_scores_gemma":[0.86457205,0.06005375,0.014716445,0.011450004,0.046911154,0.0022965267],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.012266981,0.001175261,0.0013721667,0.014157744,0.0019942892,0.008313458,0.0023510263,0.0020999059,0.004165026],"category_scores_gemma":[0.13654654,0.00070474605,0.0012288444,0.007446903,0.0009798971,0.0073352642,0.0026774474,0.0019561015,0.00678798],"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":[0.0010218867,0.00028284945,0.0862299,0.001957013,0.0003114206,0.0006562532,0.0026828295,0.008612193,0.02128864,0.006809005,0.057756305,0.81239164],"study_design_scores_gemma":[0.00024284655,0.00056718086,0.12736417,0.0013129807,0.0009741763,0.0040803286,0.00485188,0.4701288,0.1335793,0.04525446,0.21108162,0.000562308],"about_ca_topic_score_codex":0.0024678984,"about_ca_topic_score_gemma":0.0032397506,"teacher_disagreement_score":0.9916865,"about_ca_system_score_codex":0.0014972857,"about_ca_system_score_gemma":0.0036734985,"threshold_uncertainty_score":0.06487477},"labels":[],"label_agreement":null},{"id":"W2604199453","doi":"10.3233/ida-170874","title":"Efficiently mining high utility sequential patterns in static and streaming data","year":2017,"lang":"en","type":"article","venue":"Intelligent Data Analysis","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Institute for Information Industry, Ministry of Science and Technology, Taiwan","keywords":"Computer science; Data stream mining; Pruning; Data mining; Data stream; Tree (set theory); Sequential Pattern Mining; Decision tree; Machine learning","score_opus":0.13000967733921617,"score_gpt":0.36734769337269635,"score_spread":0.23733801603348018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2604199453","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15474908,0.0011462943,0.83697426,0.00044507117,0.00006374982,0.00034695963,0.0024310146,0.0028166196,0.0010269417],"genre_scores_gemma":[0.48550835,0.0006947623,0.5073237,0.00014736282,0.00006135631,0.0002911127,0.004626025,0.00015372135,0.0011936428],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99777967,0.00035656098,0.0003320965,0.0006248871,0.0007291996,0.00017757731],"domain_scores_gemma":[0.9940904,0.0030449242,0.0008825358,0.0007432824,0.0010008074,0.00023816073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018727125,0.0011620229,0.0015877866,0.0038609584,0.00081940176,0.0014948517,0.0019411627,0.00089354656,0.00058977463],"category_scores_gemma":[0.009227375,0.0007384574,0.0013540173,0.0059065567,0.0006126369,0.003574622,0.0013248558,0.0010564427,0.000501877],"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":[0.0007445329,0.00044415455,0.07389707,0.0011783057,0.00047916314,0.0031398183,0.000902245,0.16696765,0.025009949,0.010978258,0.008164695,0.70809424],"study_design_scores_gemma":[0.000038822473,0.00019451672,0.004561078,0.000050207254,0.0000910545,0.0012163855,0.00042219396,0.9494213,0.010520015,0.029520757,0.0039301594,0.000033475364],"about_ca_topic_score_codex":0.0025510786,"about_ca_topic_score_gemma":0.004097372,"teacher_disagreement_score":0.0038609584,"about_ca_system_score_codex":0.00046343313,"about_ca_system_score_gemma":0.001698829,"threshold_uncertainty_score":0.009904027},"labels":[],"label_agreement":null},{"id":"W2606579143","doi":"10.1016/j.eswa.2017.04.038","title":"Evaluation of quality measures for contrast patterns by using unseen objects","year":2017,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":18,"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":"Consejo Nacional de Ciencia y Tecnología; Pratt and Whitney Canada","keywords":"Computer science; Quality (philosophy); Contrast (vision); Set (abstract data type); Artificial intelligence; Data mining; Machine learning; Pattern recognition (psychology)","score_opus":0.1123401987785355,"score_gpt":0.3844214697607453,"score_spread":0.2720812709822098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606579143","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6041929,0.0045892578,0.38310292,0.0003752218,0.00024614803,0.00036880857,0.00239217,0.0026772108,0.0020552666],"genre_scores_gemma":[0.79591614,0.00062619254,0.1984651,0.00006813831,0.000119218545,0.000097752854,0.0037008799,0.00034245293,0.0006640276],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945416,0.0008656087,0.0008473885,0.0011894745,0.0021513412,0.00040468056],"domain_scores_gemma":[0.9652925,0.01849933,0.003021658,0.0030891122,0.009080289,0.0010170478],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007324865,0.0012952745,0.0017200698,0.008335731,0.00064160593,0.003675775,0.0018226053,0.0020847647,0.0015563057],"category_scores_gemma":[0.033367492,0.00041030117,0.0015119446,0.003986501,0.00082268735,0.0037351807,0.0017805371,0.001027449,0.0004524864],"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":[0.008758924,0.0012838063,0.11580356,0.0019648643,0.0018655584,0.00052457175,0.00044096977,0.04361811,0.0601353,0.0035904907,0.004670929,0.75734293],"study_design_scores_gemma":[0.00055018783,0.0026321479,0.095931225,0.00021228517,0.001305997,0.0017906082,0.0006551371,0.8010915,0.08649523,0.00588574,0.0032843226,0.00016559898],"about_ca_topic_score_codex":0.0031535942,"about_ca_topic_score_gemma":0.003083075,"teacher_disagreement_score":0.008335731,"about_ca_system_score_codex":0.0010740248,"about_ca_system_score_gemma":0.0009028121,"threshold_uncertainty_score":0.038738012},"labels":[],"label_agreement":null},{"id":"W2610563132","doi":"10.1007/978-3-319-59041-7_14","title":"A New Scalable and Performance-Enhancing Bootstrap Aggregating Scheme for Variables Selection","year":2017,"lang":"en","type":"book-chapter","venue":"Lecture notes in business information processing","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 Rimouski","funders":"","keywords":"Computer science; Scalability; Feature selection; Generalization; Selection (genetic algorithm); Relevance (law); Machine learning; Data mining; Artificial intelligence; Predictive power; Scheme (mathematics); Model selection; Mathematics; Database","score_opus":0.02038024116382591,"score_gpt":0.2553216788253208,"score_spread":0.2349414376614949,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2610563132","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006694684,0.00020885692,0.9905753,0.000109488254,0.00012672984,0.00010017749,0.00020359231,0.0012347503,0.00074635213],"genre_scores_gemma":[0.14711262,0.00025027923,0.8459426,0.00026137073,0.00045261707,0.00035348188,0.0015404318,0.00021743643,0.0038692118],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971245,0.00092200236,0.00020916545,0.00043910055,0.0010737194,0.0002315193],"domain_scores_gemma":[0.9960691,0.0013114578,0.00021724236,0.0013721238,0.0008286681,0.00020135712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029605434,0.0009492338,0.0020414286,0.0013558588,0.0012273969,0.0015644126,0.0029105837,0.0011542905,0.004740588],"category_scores_gemma":[0.010619113,0.0005263145,0.0009778995,0.002687735,0.00060392055,0.0020853847,0.0038048686,0.0020116407,0.00232042],"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":[0.0011973712,0.0003887544,0.0030643234,0.00016162431,0.0002339487,0.0003472113,0.00023038732,0.05558317,0.02728666,0.02379711,0.022391105,0.86531824],"study_design_scores_gemma":[0.00011743122,0.00012118686,0.0011779122,0.000015807576,0.000057929512,0.0002952415,0.000044911252,0.95732236,0.0070502935,0.02664776,0.0071123964,0.000036753157],"about_ca_topic_score_codex":0.0017390571,"about_ca_topic_score_gemma":0.003326822,"teacher_disagreement_score":0.004740588,"about_ca_system_score_codex":0.00040442075,"about_ca_system_score_gemma":0.0015746895,"threshold_uncertainty_score":0.015858889},"labels":[],"label_agreement":null},{"id":"W2612636087","doi":"10.4230/lipics.opodis.2016.34","title":"Deletion without Rebalancing in Non-Blocking Binary Search Trees","year":2017,"lang":"en","type":"article","venue":"DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Dalhousie University","keywords":"Blocking (statistics); Computer science; Binary search tree; Tree (set theory); Binary tree; Lock (firearm); Bounded function; Optimal binary search tree; Algorithm; Theoretical computer science; K-ary tree; Combinatorics; Mathematics; Tree structure","score_opus":0.02315242208962659,"score_gpt":0.3028318129520669,"score_spread":0.2796793908624403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2612636087","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08440622,0.0006685607,0.90186363,0.0005027236,0.00008405554,0.00031154955,0.0003154642,0.005328973,0.0065188813],"genre_scores_gemma":[0.4449048,0.0003658609,0.54469657,0.0005239371,0.00007198796,0.0004238257,0.0008652643,0.00095696445,0.0071908],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975721,0.00057721906,0.0001518805,0.00036533468,0.000761319,0.00057211786],"domain_scores_gemma":[0.9964682,0.0013882227,0.00048921834,0.000859903,0.0005583192,0.00023622988],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018693472,0.00078162673,0.0010597506,0.0007655892,0.0011193074,0.0017267723,0.0028482785,0.0010959426,0.004062423],"category_scores_gemma":[0.0061405418,0.00077843416,0.0009515673,0.0012367048,0.0012230759,0.0035760065,0.002445995,0.0018072702,0.0015207495],"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":[0.0016700807,0.0005993347,0.0032750228,0.0011304676,0.00011210162,0.00046418942,0.0011636809,0.44958302,0.071721576,0.0932657,0.009679994,0.36733478],"study_design_scores_gemma":[0.00038110753,0.00039822963,0.0005936341,0.00008044463,0.00007781918,0.00038541868,0.0002860866,0.9143007,0.023399638,0.04843636,0.011590299,0.00007028835],"about_ca_topic_score_codex":0.0035085713,"about_ca_topic_score_gemma":0.004516314,"teacher_disagreement_score":0.004062423,"about_ca_system_score_codex":0.0012426078,"about_ca_system_score_gemma":0.002573906,"threshold_uncertainty_score":0.013590157},"labels":[],"label_agreement":null},{"id":"W26157273","doi":"10.1589/jpts.27.1609","title":"Expert querying and redirection with rule responder","year":2007,"lang":"en","type":"article","venue":"Journal of Physical Therapy Science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Research and Productivity Council","funders":"","keywords":"Computer science; Data mining","score_opus":0.019266965395153553,"score_gpt":0.30986402215821407,"score_spread":0.2905970567630605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W26157273","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10212103,0.0009161642,0.8307399,0.002564645,0.0004444641,0.002583333,0.0023557984,0.034076113,0.024198638],"genre_scores_gemma":[0.5391534,0.00045299926,0.43992436,0.002074882,0.0002867232,0.0011812539,0.003534768,0.00086943014,0.012522195],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9884093,0.005090131,0.0011807047,0.0022262495,0.0025465174,0.0005471149],"domain_scores_gemma":[0.9683214,0.019762302,0.0011334169,0.0065056714,0.0037388296,0.0005383396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010650329,0.0012677568,0.0019457808,0.0027821988,0.0010352066,0.00220868,0.0032279014,0.002253608,0.013025217],"category_scores_gemma":[0.046521112,0.00046246513,0.0008280196,0.0017732895,0.0007018834,0.00334129,0.0019432858,0.001243783,0.0077188592],"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":[0.0020981184,0.0008742306,0.014291486,0.000619283,0.00014323878,0.0012273316,0.0015487162,0.008555267,0.014586765,0.004477574,0.03195216,0.9196258],"study_design_scores_gemma":[0.0007831299,0.001581043,0.011657712,0.0005615495,0.0005534517,0.0054229945,0.0045474,0.67059225,0.09694345,0.04793066,0.15907976,0.0003465418],"about_ca_topic_score_codex":0.0025139877,"about_ca_topic_score_gemma":0.0025829144,"teacher_disagreement_score":0.013025217,"about_ca_system_score_codex":0.00051068515,"about_ca_system_score_gemma":0.0016192464,"threshold_uncertainty_score":0.05632496},"labels":[],"label_agreement":null},{"id":"W2617643752","doi":"10.1038/nmeth.4299","title":"Clustering","year":2017,"lang":"en","type":"article","venue":"Nature Methods","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":186,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"","keywords":"Cluster analysis; Computational biology; Computer science; Biology; Artificial intelligence","score_opus":0.037101192000325224,"score_gpt":0.44681421703027185,"score_spread":0.4097130250299466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2617643752","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011103174,0.0009787902,0.848076,0.00069966493,0.0009543774,0.0009255686,0.0075910687,0.012607212,0.11706421],"genre_scores_gemma":[0.12497985,0.0013434126,0.6559362,0.0008397775,0.00041348167,0.0010802384,0.03096812,0.0031533733,0.18128552],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99772996,0.00023607266,0.000106423126,0.0007782408,0.0009569162,0.0001924442],"domain_scores_gemma":[0.9984125,0.00015126572,0.0000568298,0.0005726009,0.00074557407,0.000061260784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00090269477,0.0015301309,0.0010902227,0.0048377635,0.0020877398,0.0033260805,0.002533961,0.0015616652,0.049047407],"category_scores_gemma":[0.0034480353,0.00063006807,0.0016862986,0.004865369,0.0005926371,0.0019301028,0.001767952,0.0012538538,0.04320178],"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":[0.00031693486,0.00016162351,0.0018576239,0.0005471633,0.00016193934,0.00015136917,0.00025565448,0.019027313,0.023213996,0.058967482,0.12880312,0.76653576],"study_design_scores_gemma":[0.00009507867,0.00022728217,0.005765708,0.00021855951,0.00018686274,0.0011079918,0.00071121426,0.24227798,0.070426434,0.10625041,0.5725403,0.00019219237],"about_ca_topic_score_codex":0.0037603106,"about_ca_topic_score_gemma":0.0056180833,"teacher_disagreement_score":0.049047407,"about_ca_system_score_codex":0.0011439442,"about_ca_system_score_gemma":0.0019492713,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W2621283693","doi":"10.14419/jacst.v6i2.7011","title":"A heuristic to predict the optimal pattern-growth direction for the pattern growth-based sequential pattern mining approach","year":2017,"lang":"en","type":"article","venue":"Journal of Advanced Computer Science & Technology","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Heuristic; Computer science; Data mining; Set (abstract data type); Field (mathematics); Pattern recognition (psychology); Artificial intelligence; Machine learning; Mathematics","score_opus":0.018105506429943897,"score_gpt":0.27750315165056194,"score_spread":0.25939764522061803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2621283693","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15511629,0.0008153937,0.8347479,0.00071788154,0.000117295145,0.0006375357,0.0008577508,0.0030875008,0.003902457],"genre_scores_gemma":[0.4168757,0.0002661835,0.57880783,0.00022910055,0.000049272065,0.0005161182,0.0017896623,0.00017325548,0.0012929107],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988501,0.00023079777,0.00011776401,0.00029521823,0.00034178668,0.00016432608],"domain_scores_gemma":[0.9942842,0.0034600534,0.00045294096,0.00043413218,0.0011684739,0.00020024939],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017205005,0.0010841659,0.0010168838,0.0026199876,0.0006376001,0.001296205,0.0016039091,0.0013153984,0.002070801],"category_scores_gemma":[0.00931895,0.0005101434,0.00066629326,0.0019770786,0.0008173894,0.0018837255,0.0007650367,0.0010045139,0.0008221967],"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":[0.00076395774,0.00070699234,0.027764285,0.00052383606,0.00015266803,0.0005969249,0.00035277562,0.4537699,0.015019829,0.011797863,0.011919772,0.47663113],"study_design_scores_gemma":[0.000048031503,0.0001248496,0.0008798708,0.000032016545,0.000026803991,0.00014406888,0.000070544054,0.9899899,0.0031752775,0.00437228,0.0011212502,0.000015111807],"about_ca_topic_score_codex":0.0027403594,"about_ca_topic_score_gemma":0.0040726108,"teacher_disagreement_score":0.0027403594,"about_ca_system_score_codex":0.00085239,"about_ca_system_score_gemma":0.0027668339,"threshold_uncertainty_score":0.009099007},"labels":[],"label_agreement":null},{"id":"W2623297651","doi":"10.22237/jmasm/1193891220","title":"A Note on Probability Trees","year":2007,"lang":"en","type":"article","venue":"Journal of Modern Applied Statistical Methods","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Military College of Canada","funders":"","keywords":"Mathematics; Probability and statistics; Statistics; Probability theory; Probability distribution; Econometrics","score_opus":0.053701645915702804,"score_gpt":0.4005363345593097,"score_spread":0.3468346886436069,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2623297651","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017743948,0.06506638,0.261858,0.36989433,0.15034777,0.00010713742,0.0008687332,0.0008802465,0.14920297],"genre_scores_gemma":[0.07667749,0.10797261,0.22181062,0.1461175,0.256593,0.00040499054,0.0012529254,0.001907146,0.18726379],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974331,0.0009012745,0.00021378827,0.0003390562,0.0010114874,0.00010131305],"domain_scores_gemma":[0.9742657,0.020718202,0.00037395637,0.00092301314,0.003049101,0.0006700695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048109395,0.0008814672,0.000748693,0.001785054,0.0033921297,0.0040295008,0.0014198432,0.0031025065,0.013108453],"category_scores_gemma":[0.028944058,0.000586091,0.0012581587,0.0025071667,0.0045606336,0.010987456,0.002209544,0.013576779,0.008737889],"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":[0.000020710891,0.000021141908,0.0002610081,0.0001520108,0.000012459827,0.00023681596,0.00022214004,0.0014562624,0.00021719035,0.41244665,0.5238785,0.061075106],"study_design_scores_gemma":[0.0000058572864,0.000016210055,0.00026227365,0.00019601855,0.0000054474262,0.00019767805,0.00006923057,0.0009365605,0.000110459776,0.5232431,0.4749337,0.000023341721],"about_ca_topic_score_codex":0.0043045473,"about_ca_topic_score_gemma":0.004277071,"teacher_disagreement_score":0.013108453,"about_ca_system_score_codex":0.0019538621,"about_ca_system_score_gemma":0.0023136167,"threshold_uncertainty_score":0.04385215},"labels":[],"label_agreement":null},{"id":"W2625437360","doi":"10.46298/arima.2558","title":"Discovering frequent patterns guided by an ontology","year":2016,"lang":"fr","type":"article","venue":"Revue Africaine de la Recherche en Informatique et Mathématiques Appliquées","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Centre d'Excellence africain en Mathématiques, Informatique et TIC; Agence Universitaire de la Francophonie","keywords":"Ontology; Computer science; Artificial intelligence; Philosophy; Epistemology","score_opus":0.14542738067064484,"score_gpt":0.3995517069751945,"score_spread":0.2541243263045496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2625437360","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049671937,0.00072623184,0.941281,0.0008970546,0.00006808041,0.00054153305,0.002533196,0.001071027,0.003209838],"genre_scores_gemma":[0.10032007,0.0009417422,0.89230126,0.00016440125,0.000042498377,0.0003870717,0.0038449431,0.00011073658,0.0018872081],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99599636,0.0006772205,0.0006305301,0.0008308454,0.0016542175,0.00021087631],"domain_scores_gemma":[0.9948632,0.002530822,0.0006427078,0.00068108353,0.0011246649,0.00015757728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001847899,0.0008038584,0.0007652569,0.007320477,0.0012129656,0.0026947996,0.0012441154,0.00095537637,0.0014511393],"category_scores_gemma":[0.010144881,0.0005035004,0.0025465034,0.005552368,0.0009243662,0.0039294586,0.0015657576,0.0011210254,0.0006268316],"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":[0.0005276103,0.00061258674,0.029040232,0.0022897942,0.0005790724,0.0036272863,0.0046256785,0.018097049,0.062435385,0.08336365,0.008013078,0.7867886],"study_design_scores_gemma":[0.00015514684,0.00049362634,0.027570603,0.0011480955,0.00084394484,0.006944558,0.0065516313,0.44859064,0.060679022,0.29411218,0.152649,0.00026166544],"about_ca_topic_score_codex":0.0068042446,"about_ca_topic_score_gemma":0.009215311,"teacher_disagreement_score":0.007320477,"about_ca_system_score_codex":0.0011475824,"about_ca_system_score_gemma":0.0030979114,"threshold_uncertainty_score":0.013529301},"labels":[],"label_agreement":null},{"id":"W2625583799","doi":"10.6000/1929-7092.2017.06.36","title":"An Academic Search Engine for Personalized Rankings","year":2017,"lang":"en","type":"article","venue":"Journal of Reviews on Global Economics","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Search engine; Ranking (information retrieval); Information retrieval; Computer science; Business; Economics","score_opus":0.07795001581780901,"score_gpt":0.3878039601986616,"score_spread":0.30985394438085256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2625583799","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14512315,0.011995178,0.52425563,0.0048742,0.0022211706,0.004927032,0.03808955,0.12210398,0.14641017],"genre_scores_gemma":[0.42127103,0.0041680997,0.4718286,0.0012543354,0.0008504857,0.0017015173,0.04239819,0.0017345423,0.054793313],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99684745,0.001071466,0.00036592712,0.00024734778,0.0012538916,0.00021389841],"domain_scores_gemma":[0.9935688,0.0018410854,0.00045079846,0.0011805437,0.002374831,0.00058403175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039503644,0.00087049766,0.0012781426,0.0069236914,0.0010912701,0.002770212,0.0014946624,0.0012008357,0.012283725],"category_scores_gemma":[0.012318823,0.0004147437,0.0007477218,0.011057806,0.00026890734,0.0040320316,0.0013796148,0.0008694925,0.009521757],"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":[0.002136457,0.0014062054,0.006850681,0.0020299098,0.00030421186,0.00047839258,0.000410337,0.012181301,0.014282205,0.03618841,0.21476577,0.70896614],"study_design_scores_gemma":[0.0015462541,0.0020381769,0.010979851,0.00029319263,0.00063805864,0.0013593917,0.0007352773,0.3563425,0.03886217,0.05485979,0.53178483,0.0005605406],"about_ca_topic_score_codex":0.002185491,"about_ca_topic_score_gemma":0.0038335996,"teacher_disagreement_score":0.012283725,"about_ca_system_score_codex":0.0008480856,"about_ca_system_score_gemma":0.0026170523,"threshold_uncertainty_score":0.04109311},"labels":[],"label_agreement":null},{"id":"W2626930365","doi":"","title":"Introduction: Special Issue on Open Source Intelligence and Web Mining","year":2011,"lang":"en","type":"article","venue":"International Journal of Networking and Virtual Organisations","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":"University of Calgary","funders":"","keywords":"Open source; Computer science; Web mining; World Wide Web; Data science; Data mining; Information retrieval; Web page; Programming language","score_opus":0.04635805193519723,"score_gpt":0.28294524965035484,"score_spread":0.2365871977151576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2626930365","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00065287534,0.05397755,0.008055099,0.045425475,0.8560078,0.00012430274,0.0011004745,0.0005894514,0.034066882],"genre_scores_gemma":[0.0026817885,0.032662213,0.0030162528,0.014459843,0.7811182,0.00009212971,0.0021704028,0.0006114413,0.16318777],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985348,0.00015121212,0.00016130223,0.00033401602,0.0006975012,0.00012119349],"domain_scores_gemma":[0.9923463,0.0019682052,0.0005742486,0.0006304891,0.0031062257,0.0013745523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021687422,0.0017846258,0.002214406,0.005845057,0.0014080167,0.0055974075,0.0019742176,0.0033416678,0.07496646],"category_scores_gemma":[0.0065806443,0.0006293199,0.001377362,0.0038174284,0.00087872875,0.006549406,0.0021231954,0.004359345,0.045582604],"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":[0.000022060083,0.000043099375,0.00013195278,0.00029450606,0.00001637299,0.000054802207,0.00001162723,0.000065866465,0.0002694744,0.0011168194,0.9463901,0.051583327],"study_design_scores_gemma":[0.000007603024,0.000036507186,0.00075129454,0.00019968979,0.000018190069,0.0002404553,0.000019173774,0.00024368794,0.00018530106,0.0036437137,0.9946396,0.000014919512],"about_ca_topic_score_codex":0.0007733587,"about_ca_topic_score_gemma":0.0025489684,"teacher_disagreement_score":0.07496646,"about_ca_system_score_codex":0.0011126513,"about_ca_system_score_gemma":0.0014204889,"threshold_uncertainty_score":0.2507878},"labels":[],"label_agreement":null},{"id":"W2626975399","doi":"","title":"Narrative generation from extracted associations","year":2015,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Natural language processing; Exploit; Natural language generation; Rhetorical question; Interpretation (philosophy); Artificial intelligence; Causality (physics); Coherence (philosophical gambling strategy); Association rule learning; Pipeline (software); Natural language; Linguistics; Mathematics; Programming language; Statistics","score_opus":0.09738704675361089,"score_gpt":0.30135927751358044,"score_spread":0.20397223075996956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2626975399","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09302056,0.0012017165,0.86783665,0.0010602926,0.0004664507,0.0012083197,0.014050146,0.011245059,0.009910782],"genre_scores_gemma":[0.19051714,0.00041887056,0.78345954,0.00014093811,0.00008155239,0.00054679206,0.020828277,0.0007991662,0.003207734],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961714,0.0013391308,0.00038056192,0.0007803223,0.0011905025,0.00013804297],"domain_scores_gemma":[0.97695756,0.016560107,0.0013116488,0.002299211,0.0026168793,0.00025464135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038873393,0.001700555,0.00067043136,0.0032524806,0.0007940434,0.0022690336,0.0016426663,0.0009121469,0.011334975],"category_scores_gemma":[0.03587837,0.00056622474,0.0012949852,0.003081065,0.00048198798,0.0025878132,0.0019782966,0.0010129256,0.004205789],"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":[0.0011966149,0.000547036,0.019626148,0.0031933216,0.0002770703,0.0028911422,0.004982366,0.036702324,0.02356719,0.03383321,0.03632692,0.8368567],"study_design_scores_gemma":[0.0004721261,0.0007324063,0.009105439,0.00070637366,0.0005037974,0.0032317517,0.003634315,0.57573956,0.100460805,0.07890363,0.22625205,0.00025778537],"about_ca_topic_score_codex":0.0014407069,"about_ca_topic_score_gemma":0.0019812002,"teacher_disagreement_score":0.011334975,"about_ca_system_score_codex":0.0007089694,"about_ca_system_score_gemma":0.0015155663,"threshold_uncertainty_score":0.037919283},"labels":[],"label_agreement":null},{"id":"W2627710665","doi":"10.1145/772862.772887","title":"Multi-relational data mining","year":2002,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Knowledge extraction; Data science; Relational database; Data mining; Information retrieval","score_opus":0.25641928703070915,"score_gpt":0.30813698964909747,"score_spread":0.05171770261838832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2627710665","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037110636,0.027726285,0.9485956,0.003167174,0.00078811566,0.00053655583,0.0033512071,0.0025520802,0.009572045],"genre_scores_gemma":[0.06739901,0.028479781,0.8844896,0.0018138466,0.0011954566,0.0004931945,0.010044333,0.00039272624,0.00569206],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9904523,0.0019556857,0.0011703017,0.0020360653,0.0041171215,0.00026846823],"domain_scores_gemma":[0.98936623,0.0048116497,0.0008931778,0.002504222,0.0021018626,0.0003228285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006857553,0.001218159,0.001647424,0.0056410367,0.0010649444,0.0058543435,0.0039257053,0.0010988682,0.0051433356],"category_scores_gemma":[0.021246817,0.0006189688,0.0018974754,0.009295062,0.00073440105,0.009080381,0.0038846664,0.002009049,0.0058824597],"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":[0.00013034651,0.00018032236,0.007866713,0.0026101544,0.0005474271,0.0010154124,0.00033674552,0.007883908,0.0037988974,0.07670861,0.047306094,0.85161537],"study_design_scores_gemma":[0.000055846063,0.00023715988,0.0042338986,0.0010543884,0.0005908032,0.0075997887,0.0007719019,0.12936562,0.01538532,0.2542057,0.5863222,0.0001773451],"about_ca_topic_score_codex":0.0009818592,"about_ca_topic_score_gemma":0.0012520732,"teacher_disagreement_score":0.006857553,"about_ca_system_score_codex":0.0008066392,"about_ca_system_score_gemma":0.0016402175,"threshold_uncertainty_score":0.036266685},"labels":[],"label_agreement":null},{"id":"W2676841717","doi":"10.4018/978-1-5225-2255-3.ch030","title":"Big Data Analysis and Mining","year":2017,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Big data; Computer science; Data science; Variety (cybernetics); Process (computing); Knowledge extraction; Data mining; Artificial intelligence","score_opus":0.07076471790848139,"score_gpt":0.2934750614001257,"score_spread":0.2227103434916443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2676841717","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020002255,0.25161842,0.3671691,0.029729804,0.011748671,0.0011101676,0.0075992327,0.0049031707,0.32412115],"genre_scores_gemma":[0.02789661,0.30339834,0.4278576,0.015231098,0.012051896,0.0013982713,0.013930777,0.0021862944,0.19604906],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970571,0.00053410843,0.00020604934,0.0004430508,0.0016516373,0.00010806036],"domain_scores_gemma":[0.9971885,0.0015287676,0.0001103168,0.0006273759,0.00040066722,0.00014428365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030266175,0.0019466468,0.0015141482,0.004544569,0.0013128413,0.008209581,0.0032830066,0.0022178888,0.027300108],"category_scores_gemma":[0.006479435,0.000968052,0.0015484653,0.008128837,0.0019866119,0.010106612,0.0046665734,0.003584013,0.021588042],"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":[0.000028951094,0.00004029433,0.0003633621,0.0023564317,0.00011242851,0.0001569779,0.00041802743,0.0020969957,0.000749468,0.23741321,0.3479146,0.4083492],"study_design_scores_gemma":[0.0000060690068,0.000013464012,0.00023310109,0.00063868996,0.000014034955,0.00027188912,0.0001212405,0.0018937625,0.0004313985,0.16683877,0.8295181,0.000019538116],"about_ca_topic_score_codex":0.0008023187,"about_ca_topic_score_gemma":0.0010442496,"teacher_disagreement_score":0.027300108,"about_ca_system_score_codex":0.0013567306,"about_ca_system_score_gemma":0.0024661124,"threshold_uncertainty_score":0.091328025},"labels":[],"label_agreement":null},{"id":"W26972093","doi":"10.1016/j.nephro.2016.01.007","title":"VP: an Efficient Algorithm for Frequent Itemset Mining.","year":2008,"lang":"en","type":"article","venue":"Software Engineering and Knowledge Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Data mining; Algorithm design; Algorithm","score_opus":0.015141328272452466,"score_gpt":0.2297649947016127,"score_spread":0.21462366642916025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W26972093","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0057415194,0.0014423446,0.95412165,0.00041617197,0.00022606022,0.0008550039,0.0064111906,0.029715426,0.0010706943],"genre_scores_gemma":[0.026892453,0.000444347,0.95983595,0.00014123629,0.00007100059,0.0012037787,0.009910403,0.00062439154,0.0008765175],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973068,0.0008265633,0.0005298181,0.00061017496,0.0005605836,0.00016616538],"domain_scores_gemma":[0.9937696,0.0046998225,0.00027704504,0.0005645884,0.0005473984,0.0001414507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004226826,0.0029778217,0.0025062833,0.0071092783,0.0014038661,0.002869031,0.00468674,0.002782491,0.0074505867],"category_scores_gemma":[0.019188209,0.0017872017,0.0030418455,0.0072647305,0.00057774497,0.0038618958,0.0027259316,0.0023100665,0.007117596],"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":[0.00094384985,0.000361421,0.0049184477,0.0015114717,0.0008769218,0.0004828752,0.00029049077,0.060087144,0.0027860946,0.0073500057,0.056798305,0.863593],"study_design_scores_gemma":[0.0004500659,0.00025546976,0.001097434,0.0001658543,0.00017592826,0.0009484054,0.00020403365,0.9350729,0.0027158658,0.035230596,0.023628734,0.000054773172],"about_ca_topic_score_codex":0.0037752036,"about_ca_topic_score_gemma":0.0045652036,"teacher_disagreement_score":0.0074505867,"about_ca_system_score_codex":0.00073515554,"about_ca_system_score_gemma":0.002955586,"threshold_uncertainty_score":0.024924695},"labels":[],"label_agreement":null},{"id":"W27140714","doi":"10.1007/978-3-642-29038-1_21","title":"Fast Tree-Based Mining of Frequent Itemsets from Uncertain Data","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Data mining; Tree (set theory); Key (lock); Compact space; Tree structure; Data structure; Uncertain data; Mathematics","score_opus":0.05112431804604601,"score_gpt":0.2813581045961621,"score_spread":0.23023378655011612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W27140714","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044257157,0.0023560745,0.94658244,0.00029664556,0.0001651053,0.00025310193,0.0025250006,0.002424774,0.0011396668],"genre_scores_gemma":[0.1713416,0.0012739727,0.8165242,0.00014495633,0.00015563532,0.00030518783,0.008504494,0.00014990744,0.001600069],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983968,0.0002902773,0.00021638419,0.00027236826,0.00068625435,0.00013794609],"domain_scores_gemma":[0.99048156,0.006604497,0.00039153436,0.00075309386,0.0015677357,0.00020155971],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018120514,0.000826916,0.002073502,0.0028400968,0.00087043835,0.0016375881,0.0022292677,0.0013258802,0.0025973495],"category_scores_gemma":[0.0111243725,0.00072574057,0.0013897001,0.0054519707,0.00029918304,0.0029299466,0.0012789535,0.0012747851,0.0021093134],"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":[0.00073572865,0.00023156096,0.0047097835,0.0008343098,0.00031774325,0.00061522634,0.000302482,0.052137848,0.0093230605,0.0056336783,0.015909823,0.90924877],"study_design_scores_gemma":[0.00009899574,0.00028491378,0.0019493009,0.000106518426,0.00014231954,0.001292288,0.00019195401,0.9598824,0.00518709,0.024012601,0.006811458,0.00004021549],"about_ca_topic_score_codex":0.0026722574,"about_ca_topic_score_gemma":0.0037255136,"teacher_disagreement_score":0.0028400968,"about_ca_system_score_codex":0.000417385,"about_ca_system_score_gemma":0.0013166124,"threshold_uncertainty_score":0.009583175},"labels":[],"label_agreement":null},{"id":"W2736013904","doi":"10.1145/1809400.1809425","title":"Efficient algorithms for the mining of constrained frequent patterns from uncertain data","year":2010,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Association rule learning; Data mining; K-optimal pattern discovery; Database transaction; Uncertain data; Data stream mining; Knowledge extraction; Geodetic datum; Data science; Database","score_opus":0.10363999971016609,"score_gpt":0.321903110243897,"score_spread":0.21826311053373093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2736013904","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00493444,0.0008094885,0.9929756,0.00018502334,0.000036040194,0.00015310373,0.00019076976,0.00034819322,0.00036726485],"genre_scores_gemma":[0.04114702,0.00073054037,0.95608354,0.000090622074,0.00009723192,0.00045420323,0.00092065585,0.000050332153,0.00042577917],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99670416,0.00079511054,0.0004878687,0.00062959606,0.0011742694,0.0002090059],"domain_scores_gemma":[0.9891756,0.007793809,0.0008052234,0.0010086097,0.0010557722,0.00016096162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037850204,0.0014907981,0.0025709474,0.0036164238,0.0012969843,0.0023644306,0.0036204278,0.0018746885,0.0015454149],"category_scores_gemma":[0.019599667,0.0011423733,0.0016029914,0.006404051,0.00096932007,0.0049301405,0.0028520976,0.0021755397,0.00097190525],"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":[0.0002913763,0.00030832813,0.0026593609,0.00060809695,0.00025658828,0.00040541225,0.00038739902,0.25179565,0.0026393086,0.02984852,0.0071959314,0.703604],"study_design_scores_gemma":[0.00009680348,0.00009077478,0.00047633378,0.000058030233,0.00004814102,0.0004053732,0.00011823342,0.92272294,0.0013424032,0.070610024,0.0040035006,0.000027570368],"about_ca_topic_score_codex":0.0017685117,"about_ca_topic_score_gemma":0.0025570916,"teacher_disagreement_score":0.0037850204,"about_ca_system_score_codex":0.00076373975,"about_ca_system_score_gemma":0.0017613407,"threshold_uncertainty_score":0.020017326},"labels":[],"label_agreement":null},{"id":"W2736132090","doi":"","title":"Proceedings of the 2017 AdKDD & TargetAd Workshop","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.09386743859809221,"score_gpt":0.20813209525359835,"score_spread":0.11426465665550614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2736132090","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020312456,0.06577765,0.32266268,0.19355689,0.211198,0.0014275849,0.06888605,0.026709383,0.08946938],"genre_scores_gemma":[0.057578735,0.07162835,0.20567326,0.02602218,0.038026836,0.0016995465,0.30471006,0.011806839,0.28285423],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9908676,0.0025223424,0.0006100917,0.001279874,0.0042557623,0.00046427737],"domain_scores_gemma":[0.9771713,0.0066901664,0.00035926627,0.0038454556,0.008221088,0.003712763],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01711915,0.0021202979,0.0036473346,0.0039368263,0.0023049563,0.011068344,0.0031381291,0.0026120064,0.032132145],"category_scores_gemma":[0.023741012,0.0012188444,0.0016881797,0.0033610845,0.0019580333,0.010682554,0.005965365,0.00693167,0.034279738],"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":[0.00016499394,0.00011215527,0.0002989732,0.00014675187,0.00004007407,0.00007538119,0.000068629655,0.0005968853,0.00030497028,0.003352001,0.9475602,0.04727902],"study_design_scores_gemma":[0.00008110347,0.000037411366,0.0005940652,0.0001764691,0.000043800213,0.00016135859,0.0001977116,0.0065269694,0.001273976,0.014708283,0.9761578,0.000041158502],"about_ca_topic_score_codex":0.013836152,"about_ca_topic_score_gemma":0.024671005,"teacher_disagreement_score":0.032132145,"about_ca_system_score_codex":0.004428498,"about_ca_system_score_gemma":0.0107673155,"threshold_uncertainty_score":0.107492745},"labels":[],"label_agreement":null},{"id":"W2736526444","doi":"10.1007/978-981-10-5780-9","title":"Advanced Informatics for Computing Research","year":2017,"lang":"en","type":"book","venue":"Communications in computer and information science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint Mary's University","funders":"","keywords":"Computer science; Informatics; Data science; World Wide Web; Library science; Political science; Law","score_opus":0.12218892638361444,"score_gpt":0.42299584633777076,"score_spread":0.3008069199541563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2736526444","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00071842887,0.16185533,0.07257097,0.017249811,0.02782888,0.00022991029,0.00066432345,0.0021316463,0.7167507],"genre_scores_gemma":[0.010257243,0.1255961,0.036689527,0.009146442,0.02495594,0.00061184017,0.001218256,0.0015368662,0.78998774],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982216,0.00033140657,0.00012047866,0.00029546014,0.00092262164,0.00010849115],"domain_scores_gemma":[0.997431,0.0008947902,0.00013669702,0.0007189433,0.00058535393,0.00023316167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014609271,0.002549994,0.002665452,0.006055211,0.0020124181,0.009254197,0.0017068915,0.0016770294,0.062375333],"category_scores_gemma":[0.005291123,0.0008623954,0.00084637536,0.009903261,0.004129177,0.011102846,0.004938552,0.008731453,0.07227747],"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":[0.000012258042,0.000026226937,0.00008741162,0.0007803387,0.000015526814,0.000027843978,0.00022821297,0.00031538817,0.00039358478,0.31767094,0.45380014,0.22664204],"study_design_scores_gemma":[0.0000043379946,0.000008460163,0.00012308192,0.00033396855,0.000007301796,0.000069504225,0.000049744107,0.000342529,0.000092435876,0.12203224,0.8769283,0.000007976298],"about_ca_topic_score_codex":0.00078356906,"about_ca_topic_score_gemma":0.0013124513,"teacher_disagreement_score":0.062375333,"about_ca_system_score_codex":0.003175791,"about_ca_system_score_gemma":0.0041914606,"threshold_uncertainty_score":0.20866627},"labels":[],"label_agreement":null},{"id":"W2738484798","doi":"10.4018/ijhisi.2017100103","title":"Non-Traditional Data Mining Applications in Taiwan National Health Insurance (NHI) Databases","year":2017,"lang":"en","type":"article","venue":"International Journal of Healthcare Information Systems and Informatics","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Decision support system; Data warehouse; Relevance (law); Computer science; Data science; Payment; Domain (mathematical analysis); Process (computing); Clinical decision support system; Knowledge management; Data mining; Database; World Wide Web","score_opus":0.10193699793720475,"score_gpt":0.3702982881468481,"score_spread":0.2683612902096434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2738484798","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.823294,0.004957756,0.15153857,0.0050581,0.00013360917,0.0007548181,0.004057116,0.0018165442,0.008389536],"genre_scores_gemma":[0.8489833,0.00173688,0.1456645,0.00025365347,0.000051469076,0.00026943188,0.0020133352,0.00004319511,0.0009840833],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99672794,0.001393816,0.0005067752,0.0004225846,0.0008189001,0.00012998503],"domain_scores_gemma":[0.9883801,0.008333812,0.00076820626,0.0010841723,0.0011786324,0.00025509123],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005097678,0.00040178906,0.0004317274,0.0029152469,0.00073266774,0.0021053266,0.0012303501,0.0006416304,0.00076330174],"category_scores_gemma":[0.015313543,0.00024658433,0.000544781,0.0049645198,0.00039623777,0.0018060886,0.0014544104,0.0006592473,0.00022687546],"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":[0.0012033776,0.0011235278,0.19025074,0.0020886455,0.00038219945,0.0063289483,0.0059384415,0.056347363,0.014562677,0.033194803,0.016349366,0.67222995],"study_design_scores_gemma":[0.00018992281,0.0004070691,0.065485105,0.0005446901,0.00021182127,0.0025970796,0.009260999,0.8086583,0.027147327,0.035628654,0.04975986,0.00010918984],"about_ca_topic_score_codex":0.008264165,"about_ca_topic_score_gemma":0.007651212,"teacher_disagreement_score":0.008264165,"about_ca_system_score_codex":0.0013187415,"about_ca_system_score_gemma":0.0015540207,"threshold_uncertainty_score":0.02695942},"labels":[],"label_agreement":null},{"id":"W2742189297","doi":"10.82308/8014","title":"The development of an artificially intuitive reasoner","year":2010,"lang":"en","type":"article","venue":"eScholarship@McGill (McGill)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Semantic reasoner; Computer science; Intuition; Certainty; Artificial intelligence; Inference; Rule-based system; Mathematics; Psychology; Cognitive science","score_opus":0.01796914361291553,"score_gpt":0.24874395094372737,"score_spread":0.23077480733081185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2742189297","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006838244,0.00007525677,0.98960644,0.00025969915,0.000044469216,0.00017576983,0.000050771687,0.00082008657,0.0021293103],"genre_scores_gemma":[0.05907609,0.000087992354,0.93901366,0.00013790303,0.000016332304,0.00015652829,0.0001258172,0.0000897305,0.0012959158],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962345,0.0011306219,0.0003108635,0.0008856703,0.0012969136,0.00014150259],"domain_scores_gemma":[0.9930536,0.0037575127,0.00038882633,0.0012469569,0.0013775913,0.00017538275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006026286,0.0005974367,0.0006897608,0.0010449388,0.00068621885,0.0027513027,0.0030459475,0.0014375048,0.0034989847],"category_scores_gemma":[0.016950123,0.0006269765,0.001406633,0.00042304432,0.0024343925,0.0041263113,0.0025640724,0.002273013,0.00090524467],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020685347,0.00024370063,0.002478159,0.00083730003,0.0001664035,0.00045140597,0.0027509,0.08456126,0.037639905,0.60939,0.0042743213,0.25699976],"study_design_scores_gemma":[0.00013555695,0.00053442287,0.0008589339,0.00029908758,0.00013497606,0.0006288693,0.00036726793,0.6738897,0.04554919,0.18623917,0.09121382,0.0001489968],"about_ca_topic_score_codex":0.00078698393,"about_ca_topic_score_gemma":0.0009791618,"teacher_disagreement_score":0.006026286,"about_ca_system_score_codex":0.0009134867,"about_ca_system_score_gemma":0.0022358182,"threshold_uncertainty_score":0.031870425},"labels":[],"label_agreement":null},{"id":"W2743003917","doi":"10.1145/3106426.3106542","title":"Bitwise parallel association rule mining for web page recommendation","year":2017,"lang":"en","type":"article","venue":"Proceedings of the International Conference on Web Intelligence","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":16,"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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Association rule learning; Computer science; Web mining; Data mining; Web page; Big data; Apriori algorithm; Information retrieval; Web analytics; Web intelligence; World Wide Web; Data science; Web modeling","score_opus":0.07745921142831687,"score_gpt":0.32716629996323454,"score_spread":0.2497070885349177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2743003917","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020972919,0.001618347,0.97135293,0.00055649335,0.000200512,0.00022462363,0.00071159034,0.0029503014,0.0014122583],"genre_scores_gemma":[0.21815386,0.0017585749,0.77387714,0.00044208308,0.00024540507,0.00043104857,0.00208435,0.00015064678,0.002856799],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961998,0.0008234781,0.0004672704,0.0008555011,0.0014364022,0.00021750723],"domain_scores_gemma":[0.9932412,0.0025505184,0.00064818666,0.0014850618,0.0019015798,0.00017355286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032577172,0.0009944566,0.0020134347,0.0039950665,0.001205365,0.0016569669,0.0022816989,0.0011204125,0.0021779207],"category_scores_gemma":[0.011542586,0.00070847874,0.0014753268,0.006293891,0.00071606174,0.0029849326,0.0011237282,0.002004698,0.002530737],"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":[0.000945562,0.000569922,0.009818519,0.00033314253,0.0003755225,0.00039881252,0.00016154148,0.13441129,0.008475725,0.011205714,0.0090833055,0.8242209],"study_design_scores_gemma":[0.00006083486,0.00013499624,0.0013863656,0.000023457238,0.00008678877,0.00037212562,0.000031300475,0.97029907,0.0035276294,0.020193309,0.003847985,0.000036100777],"about_ca_topic_score_codex":0.009725683,"about_ca_topic_score_gemma":0.010288045,"teacher_disagreement_score":0.009725683,"about_ca_system_score_codex":0.000750344,"about_ca_system_score_gemma":0.0025264528,"threshold_uncertainty_score":0.019338131},"labels":[],"label_agreement":null},{"id":"W2743348008","doi":"","title":"Utilizing semantics in itemset mining and jointree probability propagation","year":2006,"lang":"en","type":"dissertation","venue":"oURspace (University of Regina)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Bayesian network; Computer science; Soundness; Data mining; Semantics (computer science); Node (physics); Conditional probability; Inference; Probabilistic logic; Artificial intelligence; Theoretical computer science; Machine learning; Mathematics; Programming language","score_opus":0.015059485356473636,"score_gpt":0.21797397043291414,"score_spread":0.2029144850764405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2743348008","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0073139025,0.00008573796,0.9916986,0.000091604525,0.0000071586032,0.000052289142,0.000047465914,0.00016392951,0.00053926866],"genre_scores_gemma":[0.26339823,0.00034461552,0.7343379,0.00011610409,0.00004804895,0.00024490512,0.00030706648,0.00009288018,0.0011101348],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957789,0.001668103,0.00032498388,0.0007619927,0.0012734545,0.00019249826],"domain_scores_gemma":[0.9847569,0.010208303,0.0009941054,0.0021619243,0.001660923,0.00021792098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005847928,0.0010344973,0.0011710346,0.004556944,0.0011042189,0.002849731,0.0022612591,0.0011923749,0.0018022603],"category_scores_gemma":[0.0296022,0.00087228447,0.0020231216,0.005066251,0.0024031799,0.01071495,0.0025383653,0.0013981962,0.000600561],"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":[0.00027510003,0.00023625306,0.009749766,0.00044851468,0.000244271,0.00032125632,0.0008933877,0.22568835,0.005284127,0.35070103,0.0014951702,0.40466273],"study_design_scores_gemma":[0.000028298968,0.00008696253,0.00085602305,0.00005598955,0.000097746735,0.00023220437,0.00011165007,0.6446879,0.0041530854,0.34719098,0.002457253,0.000041988413],"about_ca_topic_score_codex":0.0034850235,"about_ca_topic_score_gemma":0.0046535814,"teacher_disagreement_score":0.005847928,"about_ca_system_score_codex":0.0013024575,"about_ca_system_score_gemma":0.0019742,"threshold_uncertainty_score":0.030927181},"labels":[],"label_agreement":null},{"id":"W2744510879","doi":"10.1016/j.ins.2017.08.031","title":"Information sciences 1968–2016: A retrospective analysis with text mining and bibliometric","year":2017,"lang":"en","type":"article","venue":"Information Sciences","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":227,"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":"Natural Science Foundation of Zhejiang Province; National Natural Science Foundation of China","keywords":"Citation; Data science; Computer science; Construct (python library); Salient; Citation analysis; Bibliometrics; Web of science; Information retrieval; Key (lock); Library science; Political science; MEDLINE","score_opus":0.027400149331771973,"score_gpt":0.30244255983358553,"score_spread":0.27504241050181355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2744510879","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6079813,0.03806808,0.004145121,0.004146655,0.000978367,0.00022674215,0.29191092,0.000447113,0.052095745],"genre_scores_gemma":[0.77948076,0.023489045,0.00430505,0.0007615463,0.001440855,0.00023236685,0.16940725,0.00030233688,0.020580871],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9966582,0.00027470704,0.0007139881,0.00041458724,0.0016229193,0.00031560802],"domain_scores_gemma":[0.96847343,0.0062302756,0.0101263095,0.0031821635,0.010660991,0.0013268609],"candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.0033205037,0.0005663913,0.0006806977,0.029744968,0.0008845802,0.002808987,0.0007704235,0.00069300155,0.0031492766],"category_scores_gemma":[0.02692447,0.00034092966,0.0008009623,0.051159523,0.00080440816,0.0027349123,0.0018930734,0.0009323588,0.0036285836],"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":[0.0011793567,0.00021113124,0.7333357,0.0022343523,0.00064459315,0.00090571394,0.0020348453,0.001316035,0.0017094368,0.005827375,0.064032376,0.18656908],"study_design_scores_gemma":[0.00001441713,0.00010088769,0.77706724,0.0007768211,0.0003539589,0.0007797325,0.0007649763,0.00036756127,0.0025369092,0.0009261089,0.2162664,0.000045051063],"about_ca_topic_score_codex":0.03083964,"about_ca_topic_score_gemma":0.03813508,"teacher_disagreement_score":0.970255,"about_ca_system_score_codex":0.002049643,"about_ca_system_score_gemma":0.0041629793,"threshold_uncertainty_score":0.061320305},"labels":[],"label_agreement":null},{"id":"W2746013538","doi":"10.1515/picbe-2017-0047","title":"Human talent forecasting","year":2017,"lang":"en","type":"article","venue":"Proceedings of the ... International Conference on Business Excellence","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Human resources; Economic shortage; Order (exchange); Face (sociological concept); Computer science; Data science; Visibility; Resource (disambiguation); Sign (mathematics); Human resource management; Operations research; Data mining; Knowledge management; Marketing; Business; Engineering; Government (linguistics); Management; Economics; Geography; Mathematics; Finance","score_opus":0.09963786675806313,"score_gpt":0.3022768333407212,"score_spread":0.20263896658265806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2746013538","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7653709,0.0011773036,0.12311395,0.0018532027,0.00049781566,0.0006701855,0.030598048,0.0042217067,0.0724969],"genre_scores_gemma":[0.96401703,0.0003457183,0.019434594,0.00008867254,0.00006089709,0.00020702572,0.0066116545,0.000044767028,0.009189629],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995604,0.00008351479,0.00001996278,0.00012156998,0.00015495524,0.00005956574],"domain_scores_gemma":[0.9982602,0.0008473727,0.00015123413,0.00015639311,0.00045034965,0.00013443705],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007771624,0.00066371314,0.0003602466,0.002850914,0.00031932688,0.00084301614,0.0006528069,0.00068665034,0.009487846],"category_scores_gemma":[0.0036393777,0.00012986404,0.00042765224,0.0028198923,0.00016983564,0.00068139774,0.00037809793,0.00068776467,0.0034620098],"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":[0.000576318,0.0005311098,0.13298976,0.00028136102,0.00012119821,0.00020744767,0.0002474078,0.4748686,0.002592469,0.0045490856,0.025727404,0.35730785],"study_design_scores_gemma":[0.000015391373,0.00014866087,0.039088693,0.000045442073,0.000021628368,0.000032788023,0.00014321467,0.9502364,0.00220739,0.0027425445,0.005289063,0.000028786812],"about_ca_topic_score_codex":0.013943111,"about_ca_topic_score_gemma":0.0086520715,"teacher_disagreement_score":0.013943111,"about_ca_system_score_codex":0.0009972194,"about_ca_system_score_gemma":0.00041282037,"threshold_uncertainty_score":0.03173995},"labels":[],"label_agreement":null},{"id":"W2752952491","doi":"10.1016/j.procs.2017.08.069","title":"TWINCLE : A Constrained Sequential Rule Mining Algorithm for Event Logs","year":2017,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Event (particle physics); Data mining; Benchmark (surveying); Process mining; Workflow; Consistency (knowledge bases); Artificial intelligence; Database; Business process; Business process management; Work in process","score_opus":0.02904034743449188,"score_gpt":0.307797778905382,"score_spread":0.27875743147089016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2752952491","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01418247,0.00021463478,0.9804766,0.00024963907,0.000046556306,0.0002336886,0.0010205643,0.0030559334,0.00051982584],"genre_scores_gemma":[0.1021106,0.00017903435,0.8925324,0.00016890539,0.000051655214,0.00044307034,0.0034591295,0.00017945145,0.00087574794],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99779534,0.0004884159,0.0003486954,0.00057186285,0.00067483337,0.000120809695],"domain_scores_gemma":[0.9926502,0.004875078,0.0005595669,0.0006511699,0.001069352,0.00019462],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027310278,0.0010371685,0.0016527033,0.0032544597,0.00080415024,0.0014616464,0.0028295075,0.0013267309,0.0021819614],"category_scores_gemma":[0.015617229,0.000693463,0.0012511637,0.003785445,0.00048601002,0.0024528354,0.0013463072,0.0019039913,0.00090968196],"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":[0.0006384537,0.00065118365,0.0128127765,0.0005282322,0.0004285321,0.00062879256,0.00028356662,0.17572254,0.006275579,0.011428776,0.01601363,0.7745878],"study_design_scores_gemma":[0.000049381964,0.000064433625,0.0005193227,0.00001741523,0.00002921792,0.00024976698,0.000034749624,0.9859066,0.0016316461,0.008919222,0.0025597415,0.000018398818],"about_ca_topic_score_codex":0.0054037212,"about_ca_topic_score_gemma":0.00785796,"teacher_disagreement_score":0.0054037212,"about_ca_system_score_codex":0.00057458814,"about_ca_system_score_gemma":0.0024949627,"threshold_uncertainty_score":0.014443219},"labels":[],"label_agreement":null},{"id":"W2767552437","doi":"10.1007/s41060-017-0079-5","title":"Discovering co-location patterns with aggregated spatial transactions and dependency rules","year":2017,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Data Mining Algorithms and Applications","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":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Association rule learning; Computer science; Data mining; Dependency (UML); Database transaction; Contrast (vision); Spatial analysis; Common spatial pattern; Spatial ecology; Artificial intelligence; Statistics; Mathematics","score_opus":0.04159857979522947,"score_gpt":0.3375766672262661,"score_spread":0.29597808743103665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767552437","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71123385,0.0016029741,0.2640372,0.0007131059,0.00014017029,0.00023829196,0.014140169,0.0017257797,0.006168537],"genre_scores_gemma":[0.9200028,0.00036977217,0.06929291,0.000050785715,0.00005866801,0.00008926296,0.008988923,0.000057496633,0.0010892173],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986034,0.00019912128,0.00016968226,0.00043924004,0.00043959185,0.00014899079],"domain_scores_gemma":[0.99543935,0.0021152447,0.0007955235,0.0007354682,0.000692522,0.00022189876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006269143,0.0007912348,0.00081564503,0.0058934037,0.0005988545,0.0017168238,0.0012890139,0.0008155039,0.001865061],"category_scores_gemma":[0.0061803805,0.0004793795,0.0012014643,0.008878174,0.00047100036,0.0026795631,0.0011452929,0.0009519949,0.0011987453],"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":[0.0013161154,0.0008646792,0.552585,0.000828613,0.0014266976,0.0051308023,0.0011008665,0.10737601,0.012812895,0.012534955,0.013020624,0.29100275],"study_design_scores_gemma":[0.000052076124,0.00018885967,0.07307338,0.0001118596,0.0005121493,0.0023523543,0.0014192547,0.87317973,0.0049778903,0.03592463,0.00814584,0.000061932165],"about_ca_topic_score_codex":0.008905873,"about_ca_topic_score_gemma":0.019184107,"teacher_disagreement_score":0.008905873,"about_ca_system_score_codex":0.00044352617,"about_ca_system_score_gemma":0.0010238664,"threshold_uncertainty_score":0.017708123},"labels":[],"label_agreement":null},{"id":"W2770619614","doi":"10.1145/3110025.3110089","title":"Efficient Mining of 'Following' Patterns from Very Big but Sparse Social Networks","year":2017,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":16,"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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Big data; Data science; Data mining","score_opus":0.03622615226874683,"score_gpt":0.2691060725464719,"score_spread":0.23287992027772508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2770619614","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30911478,0.0009228326,0.6816262,0.0016021675,0.00007178646,0.0003128962,0.002271112,0.0013170469,0.0027612033],"genre_scores_gemma":[0.7441408,0.0004382745,0.24722011,0.00026572417,0.00009737344,0.00022029181,0.006025683,0.000060544324,0.0015310821],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99868804,0.00031415504,0.00011152564,0.00037076217,0.00038368194,0.00013177753],"domain_scores_gemma":[0.994177,0.0031962653,0.0010428223,0.000914732,0.00046019285,0.00020904414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009528388,0.00078535976,0.0012114737,0.0025496,0.00094742584,0.0010799982,0.002294807,0.0016056685,0.00065457594],"category_scores_gemma":[0.009231612,0.00054486387,0.001066858,0.00255005,0.0007376447,0.002869559,0.0014553262,0.0010631552,0.00042782674],"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":[0.0006442887,0.00083641085,0.07262276,0.00073890545,0.00059668685,0.0018397942,0.0015905442,0.36540985,0.014649764,0.028822059,0.0151561005,0.49709284],"study_design_scores_gemma":[0.000017620496,0.000049387276,0.0029499326,0.00002538,0.000033160843,0.0003462796,0.00023871937,0.96620584,0.0019708478,0.026116293,0.0020352516,0.000011221245],"about_ca_topic_score_codex":0.0041130963,"about_ca_topic_score_gemma":0.0075757103,"teacher_disagreement_score":0.0041130963,"about_ca_system_score_codex":0.0005984525,"about_ca_system_score_gemma":0.00089592417,"threshold_uncertainty_score":0.008178353},"labels":[],"label_agreement":null},{"id":"W2773435160","doi":"10.1186/s12918-017-0475-4","title":"Mining significant high utility gene regulation sequential patterns","year":2017,"lang":"en","type":"article","venue":"BMC Systems Biology","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Systems biology; Computational biology; Biology; Gene; Gene regulatory network; Regulation of gene expression; Computer science; Genetics; Gene expression","score_opus":0.07164685017363992,"score_gpt":0.30353994342774154,"score_spread":0.23189309325410162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2773435160","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39067152,0.0025788476,0.58812445,0.0006547762,0.00008092751,0.00039102108,0.010096221,0.004766639,0.0026354953],"genre_scores_gemma":[0.7398547,0.0007032664,0.24679667,0.0001329359,0.000071583505,0.00023847655,0.0109524755,0.000118954275,0.0011308424],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99872893,0.00018719754,0.00013498578,0.0004034367,0.00043079111,0.00011467485],"domain_scores_gemma":[0.9970368,0.0015910029,0.00048818102,0.00034407884,0.0004174558,0.00012251077],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011203298,0.0007035891,0.0007585641,0.0030001,0.0005224195,0.0008361955,0.0008456309,0.00057028333,0.0011229449],"category_scores_gemma":[0.0034275283,0.00018838045,0.001101066,0.0027876468,0.00040173944,0.0006161418,0.000634146,0.0005655883,0.00048148606],"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":[0.0011695012,0.0006357871,0.17658162,0.0017462125,0.0004995673,0.0017027352,0.00041726147,0.040905397,0.06535654,0.006558437,0.009818976,0.69460803],"study_design_scores_gemma":[0.00012016779,0.00038631595,0.102104686,0.00015867339,0.00039263087,0.003847209,0.00041626522,0.7562478,0.07575369,0.041798774,0.018692462,0.000081268656],"about_ca_topic_score_codex":0.0016657559,"about_ca_topic_score_gemma":0.0027372465,"teacher_disagreement_score":0.0030001,"about_ca_system_score_codex":0.0005403447,"about_ca_system_score_gemma":0.0010931804,"threshold_uncertainty_score":0.00592494},"labels":[],"label_agreement":null},{"id":"W2777453820","doi":"10.4018/978-1-4666-5202-6.ch030","title":"Big Data Mining and Analytics","year":2014,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Big data; Data science; Analytics; Computer science; Data analysis; Data mining","score_opus":0.06998703304402837,"score_gpt":0.2763552135753789,"score_spread":0.20636818053135053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2777453820","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014157314,0.05563162,0.10433791,0.024457868,0.007450444,0.0013572468,0.069606155,0.026858434,0.7088846],"genre_scores_gemma":[0.006704538,0.075364664,0.10388918,0.010757309,0.004512811,0.001540422,0.066258386,0.011550918,0.7194218],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99893063,0.00010385786,0.00006841606,0.00016931427,0.00067226833,0.000055442968],"domain_scores_gemma":[0.99657816,0.0016178286,0.00013166615,0.00070850394,0.0005242852,0.0004395689],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0020979294,0.0015504992,0.0019261983,0.005969226,0.00082811463,0.0087548345,0.002053601,0.002180468,0.36682793],"category_scores_gemma":[0.008244134,0.0015308012,0.001388516,0.01315132,0.000907015,0.007824024,0.0052847895,0.003955642,0.43760648],"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":[0.000012488841,0.000034255947,0.00017302971,0.00091756455,0.000032445038,0.00004065136,0.00007376147,0.00018976792,0.00058595015,0.006412744,0.8063823,0.18514504],"study_design_scores_gemma":[0.000010317782,0.0000120763025,0.0005903222,0.0006194812,0.000010968347,0.00011648703,0.00008221124,0.0005946761,0.0004254541,0.023437226,0.9740787,0.000022105489],"about_ca_topic_score_codex":0.0007326671,"about_ca_topic_score_gemma":0.0019152253,"teacher_disagreement_score":0.36682793,"about_ca_system_score_codex":0.0008165743,"about_ca_system_score_gemma":0.0020764878,"threshold_uncertainty_score":0.9031431},"labels":[],"label_agreement":null},{"id":"W2784337572","doi":"10.24251/hicss.2018.026","title":"A Communication Model that Bridges Knowledge Delivery between Data Miners and Domain Users","year":2018,"lang":"en","type":"article","venue":"Proceedings of the ... Annual Hawaii International Conference on System Sciences/Proceedings of the Annual Hawaii International Conference on System Sciences","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Mitacs","keywords":"Domain (mathematical analysis); Computer science; Domain knowledge; Bridge (graph theory); Field (mathematics); Subjectivity; Process (computing); Domain analysis; Knowledge management; Data science; Data modeling; Subject-matter expert; Domain model; World Wide Web; Artificial intelligence; Software engineering; Expert system","score_opus":0.10721399486809256,"score_gpt":0.33148079720886575,"score_spread":0.22426680234077317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2784337572","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055040397,0.0002030332,0.8547729,0.024285188,0.0002180816,0.0016928004,0.00023262158,0.0032633115,0.06029161],"genre_scores_gemma":[0.5691301,0.00030282227,0.40444183,0.0026180106,0.00014876187,0.0027005922,0.00057947496,0.00037018865,0.019708164],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9627145,0.025646394,0.00201209,0.0029176374,0.00537991,0.0013295324],"domain_scores_gemma":[0.93230426,0.03715297,0.00559203,0.010105329,0.011418548,0.0034268487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.029581003,0.00092652295,0.0006140492,0.0040087886,0.004929434,0.010797838,0.0030273383,0.0064255693,0.008157688],"category_scores_gemma":[0.05944857,0.00081690424,0.0010810755,0.0021948018,0.0043711886,0.023683935,0.008342494,0.0036043888,0.0047278036],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00080960325,0.0018053505,0.019580072,0.00088545063,0.00013278709,0.0015776233,0.087327704,0.0074556065,0.014071464,0.47195047,0.021524271,0.37287962],"study_design_scores_gemma":[0.0008132901,0.0030424506,0.012954948,0.0019311754,0.00042689117,0.004309018,0.07411602,0.19603874,0.024517609,0.34965506,0.33150703,0.0006877752],"about_ca_topic_score_codex":0.004718638,"about_ca_topic_score_gemma":0.002844546,"teacher_disagreement_score":0.029581003,"about_ca_system_score_codex":0.005810592,"about_ca_system_score_gemma":0.012322692,"threshold_uncertainty_score":0.15644115},"labels":[],"label_agreement":null},{"id":"W2786426445","doi":"","title":"CIGA+ : an Algorithm for Computing a Concise Set of Frequently closed Item Sets","year":2006,"lang":"en","type":"article","venue":"E-ti","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec en Outaouais","funders":"","keywords":"Computer science; Data mining; Set (abstract data type); Association rule learning; Graph; Algorithm; Null (SQL); Dependency (UML); Task (project management); Dependency graph; Data set; Artificial intelligence; Theoretical computer science; Engineering","score_opus":0.02562404693190174,"score_gpt":0.29456045214715726,"score_spread":0.2689364052152555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2786426445","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004721354,0.00038466882,0.98544705,0.000119182005,0.00006887681,0.00034852367,0.001190117,0.0068712174,0.0008489936],"genre_scores_gemma":[0.017066622,0.00017218453,0.9785366,0.000080160506,0.000029218672,0.00038409838,0.0027116828,0.00023689787,0.0007824727],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893516,0.00021989558,0.00014051872,0.00024096026,0.0003875922,0.00007589928],"domain_scores_gemma":[0.99644864,0.0016921338,0.00030433017,0.000710529,0.0007312991,0.00011307597],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019818018,0.001791674,0.0016014345,0.006097807,0.0010279376,0.00252498,0.0028800238,0.0013269483,0.005562184],"category_scores_gemma":[0.010973116,0.00096254173,0.0016059713,0.005613248,0.00067127944,0.00226376,0.0021825742,0.0015080652,0.0046085874],"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":[0.0004059068,0.00018616299,0.00439466,0.0008095294,0.00021607376,0.00040450363,0.00027914066,0.037098594,0.008520034,0.014884598,0.029911691,0.9028892],"study_design_scores_gemma":[0.00021235533,0.0002772101,0.0016527664,0.00018539173,0.00016777957,0.0016158232,0.00025185687,0.86949986,0.012972359,0.058198914,0.054874364,0.000091224865],"about_ca_topic_score_codex":0.0021788504,"about_ca_topic_score_gemma":0.0033292323,"teacher_disagreement_score":0.006097807,"about_ca_system_score_codex":0.0006661675,"about_ca_system_score_gemma":0.002572244,"threshold_uncertainty_score":0.018607378},"labels":[],"label_agreement":null},{"id":"W2787257877","doi":"","title":"Special issue: Data Mining in Cyber, Physical and Social Computing","year":2017,"lang":"en","type":"article","venue":"IEEE Systems Journal","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":"St. Francis Xavier University","funders":"","keywords":"Computer science; Cyber-physical system; Computer security; Data science","score_opus":0.06844753869763014,"score_gpt":0.34001528007642684,"score_spread":0.2715677413787967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2787257877","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014887924,0.03585592,0.006771964,0.025607554,0.90415096,0.00036760795,0.0012298103,0.00080786145,0.023719445],"genre_scores_gemma":[0.0045705717,0.030097755,0.0025164012,0.008670084,0.86419564,0.0003359021,0.0029666491,0.00083816674,0.085808754],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961482,0.0006031181,0.0006859964,0.0007655931,0.0014516341,0.00034549227],"domain_scores_gemma":[0.97581,0.006870841,0.0017999252,0.0018346958,0.0076824343,0.006002212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0059012226,0.0033540973,0.005802868,0.011444312,0.003190561,0.010212891,0.0032581154,0.0058465702,0.105676465],"category_scores_gemma":[0.013585913,0.0011587313,0.0025936349,0.0071233846,0.0015995116,0.008172505,0.0045601553,0.0045385524,0.05298995],"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":[0.000091738046,0.000114770926,0.0004679515,0.00104116,0.000060197723,0.00019606802,0.000019767826,0.00017830195,0.0005734416,0.0012701736,0.9465936,0.049392913],"study_design_scores_gemma":[0.000045291585,0.00029463298,0.0025891813,0.00069404265,0.00009574468,0.0013538636,0.000084987194,0.0019106588,0.0007335782,0.005547278,0.98659873,0.000052009826],"about_ca_topic_score_codex":0.00050710555,"about_ca_topic_score_gemma":0.0015255982,"teacher_disagreement_score":0.105676465,"about_ca_system_score_codex":0.0017413748,"about_ca_system_score_gemma":0.0033701244,"threshold_uncertainty_score":0.35352302},"labels":[],"label_agreement":null},{"id":"W2788623952","doi":"10.1177/1536867x1801700406","title":"Text Mining with n-gram Variables","year":2017,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":40,"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":"Social Sciences and Humanities Research Council of Canada; Universiteit van Tilburg; University of Waterloo","keywords":"n-gram; Computer science; Gram; Categorization; Process (computing); Text categorization; Natural language processing; Sequence (biology); Artificial intelligence; Language model; Programming language","score_opus":0.046007961283892104,"score_gpt":0.321158498507218,"score_spread":0.2751505372233259,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2788623952","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012348824,0.001278711,0.9649223,0.0012032655,0.00027745304,0.0004946763,0.0076813037,0.009060456,0.0027330492],"genre_scores_gemma":[0.115126036,0.0011188671,0.86307,0.00061163964,0.00045236552,0.0011655967,0.014945091,0.0006027891,0.002907686],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99214315,0.0031837623,0.0009517304,0.0018382,0.0016446826,0.00023843574],"domain_scores_gemma":[0.9819826,0.013606342,0.001247119,0.001520518,0.0013770143,0.0002664071],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005160025,0.0014293431,0.0015641616,0.0062179794,0.0014216197,0.003701447,0.0016241821,0.001323207,0.006026517],"category_scores_gemma":[0.041148223,0.00056331925,0.0015331658,0.007900179,0.0010319238,0.005220482,0.0027349086,0.0024879244,0.0059742695],"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":[0.00088500313,0.0003006297,0.0154148,0.0016049547,0.0005513529,0.0009071359,0.0014020775,0.030622242,0.0071836123,0.046417303,0.05641392,0.83829707],"study_design_scores_gemma":[0.00018552513,0.00033602177,0.0067141093,0.0006168091,0.0002508791,0.0009986997,0.0011433116,0.5114467,0.015710538,0.35159448,0.11082228,0.00018069039],"about_ca_topic_score_codex":0.0014818974,"about_ca_topic_score_gemma":0.0020236676,"teacher_disagreement_score":0.0062179794,"about_ca_system_score_codex":0.0007204709,"about_ca_system_score_gemma":0.0017511518,"threshold_uncertainty_score":0.027289093},"labels":[],"label_agreement":null},{"id":"W2788791803","doi":"10.5539/cis.v11n1p98","title":"The Analysis and Implementation of the K - Means Algorithm Based on Hadoop Platform","year":2018,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Big data; Partition (number theory); k-means clustering; Cluster analysis; Algorithm; Cluster (spacecraft); Data mining; Mode (computer interface); Database; Operating system; Machine learning","score_opus":0.010656656140318086,"score_gpt":0.2762192063957575,"score_spread":0.2655625502554394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2788791803","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02132608,0.0013489649,0.960782,0.00052428595,0.00035388782,0.00024252011,0.0005948314,0.0051576407,0.009669806],"genre_scores_gemma":[0.2648721,0.0019630461,0.7222998,0.00021672534,0.00018202857,0.0003976024,0.002279732,0.000580424,0.007208532],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99832994,0.00021701548,0.00012186847,0.00029961308,0.0008965247,0.00013504876],"domain_scores_gemma":[0.99868006,0.0002163921,0.000052028496,0.00012168041,0.0008832798,0.000046641686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085670635,0.00061153463,0.0005241073,0.0011189439,0.0012535744,0.001447559,0.0013792608,0.0005544342,0.002423541],"category_scores_gemma":[0.0031443855,0.00039118482,0.00078798196,0.0015983102,0.0004064177,0.002219753,0.00067800697,0.0010015515,0.0011011583],"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":[0.0004289685,0.00020211046,0.0073023364,0.0009067599,0.00030989884,0.0002661604,0.00056192034,0.14126194,0.018085409,0.034940504,0.032296322,0.7634378],"study_design_scores_gemma":[0.00011030272,0.00018793173,0.006196406,0.0001395308,0.00015108749,0.0006172019,0.00059763726,0.8151532,0.054331746,0.034631345,0.08762725,0.00025634095],"about_ca_topic_score_codex":0.014159554,"about_ca_topic_score_gemma":0.0072717387,"teacher_disagreement_score":0.014159554,"about_ca_system_score_codex":0.00088838127,"about_ca_system_score_gemma":0.0029992214,"threshold_uncertainty_score":0.028154314},"labels":[],"label_agreement":null},{"id":"W2789652994","doi":"10.1109/tie.2018.2795573","title":"Detection of Frequent Alarm Patterns in Industrial Alarm Floods Using Itemset Mining Methods","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Industrial Electronics","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":86,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"ALARM; Computer science; Data mining; Manual fire alarm activation; Visualization; Identification (biology); Real-time computing; Engineering","score_opus":0.08564844060532585,"score_gpt":0.3378349914421768,"score_spread":0.252186550836851,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2789652994","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40549493,0.0011252123,0.586392,0.00033361404,0.00009139901,0.0002752837,0.0032211272,0.0016385376,0.0014278535],"genre_scores_gemma":[0.7571284,0.00041990317,0.23849893,0.00005207151,0.000055077475,0.00020561733,0.0029690245,0.00004515142,0.0006258004],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987662,0.00023076386,0.0003005277,0.00027972565,0.00032238837,0.00010045471],"domain_scores_gemma":[0.9950015,0.003012106,0.0009009467,0.0003664469,0.0005710676,0.00014783628],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014797223,0.0007498233,0.00094556995,0.005417244,0.0005019256,0.0012278734,0.00097509904,0.00077075756,0.0007261837],"category_scores_gemma":[0.0056023938,0.00027280668,0.0008545654,0.0037773582,0.00027785287,0.0010963274,0.00073979323,0.00058606087,0.00036990317],"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":[0.0011033927,0.00095101574,0.18758014,0.0009534067,0.0006440401,0.0039525637,0.0013817166,0.09335713,0.033398513,0.00415639,0.0057568946,0.66676474],"study_design_scores_gemma":[0.0000608213,0.0005143834,0.06605548,0.00015280457,0.00023193676,0.0026339202,0.0009862353,0.8953106,0.019758657,0.008951859,0.0052431338,0.000100246296],"about_ca_topic_score_codex":0.0012715238,"about_ca_topic_score_gemma":0.0016816148,"teacher_disagreement_score":0.005417244,"about_ca_system_score_codex":0.0002602579,"about_ca_system_score_gemma":0.00042776312,"threshold_uncertainty_score":0.007825553},"labels":[],"label_agreement":null},{"id":"W2792504241","doi":"10.1109/ccwc.2018.8301676","title":"An analysis of rock climbing sport regarding performance, sponsorship, and health","year":2018,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University","funders":"","keywords":"Climbing; Preprocessor; Work (physics); Computer science; Data pre-processing; Data science; Engineering; Data mining; Artificial intelligence","score_opus":0.031377460939886546,"score_gpt":0.3139152351214576,"score_spread":0.28253777418157106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792504241","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9955189,0.00010139489,0.0007054214,0.00012777996,0.0000049150026,0.000025833058,0.0025684587,0.000012603446,0.0009347414],"genre_scores_gemma":[0.99411374,0.000099657496,0.0013949245,0.000021997594,0.000013021317,0.000029283605,0.0037489878,0.0000029054374,0.00057545636],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99951935,0.00012127827,0.00004998971,0.000093528986,0.00014690228,0.00006888593],"domain_scores_gemma":[0.99693906,0.001141126,0.0008932937,0.0001978098,0.00048465186,0.00034412928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007671911,0.00024364483,0.00031445836,0.0021553945,0.00041397067,0.00053776003,0.00030292777,0.00033539586,0.0015038062],"category_scores_gemma":[0.003227245,0.00010521847,0.0003786092,0.0026711265,0.00022278522,0.00038110986,0.00037592818,0.0003232891,0.00032301398],"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":[0.00022026915,0.00015936633,0.9744975,0.00008175259,0.00014226313,0.0002465724,0.00039905566,0.0009930733,0.0014554661,0.00011714059,0.0006666734,0.021020798],"study_design_scores_gemma":[0.0000018907772,0.000133263,0.99750596,0.000008448055,0.000020524163,0.00010807293,0.0004905655,0.001132641,0.00014442213,0.000047633446,0.0004007894,0.0000059349986],"about_ca_topic_score_codex":0.014940067,"about_ca_topic_score_gemma":0.039889656,"teacher_disagreement_score":0.014940067,"about_ca_system_score_codex":0.000315246,"about_ca_system_score_gemma":0.0005378879,"threshold_uncertainty_score":0.02970618},"labels":[],"label_agreement":null},{"id":"W2796045805","doi":"10.1007/s10479-018-2830-2","title":"A clustering-based feature selection method for automatically generated relational attributes","year":2018,"lang":"en","type":"article","venue":"Annals of Operations Research","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":"University of Alberta","funders":"","keywords":"Computer science; Data mining; Cluster analysis; Feature selection; Selection (genetic algorithm); Set (abstract data type); Table (database); Relational database; Lasso (programming language); Machine learning; Artificial intelligence","score_opus":0.26245056220044977,"score_gpt":0.4869737738800862,"score_spread":0.22452321167963646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2796045805","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015002637,0.00022339476,0.98139405,0.000077203316,0.000071288036,0.000115326104,0.0003076078,0.002409633,0.00039887027],"genre_scores_gemma":[0.12849583,0.00013890398,0.8671352,0.00007441329,0.00008438526,0.00023454998,0.0017033134,0.00022313035,0.0019102641],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891365,0.00014113291,0.000089210625,0.00028291062,0.00048109074,0.00009199956],"domain_scores_gemma":[0.9986204,0.00048289128,0.00007420096,0.00017619072,0.00059236557,0.00005396469],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011622793,0.00079324364,0.0014258003,0.002747703,0.00077991886,0.000985989,0.0017475146,0.00073052564,0.0020241318],"category_scores_gemma":[0.002892718,0.0003512656,0.0010894072,0.002717949,0.00028677014,0.00087478396,0.00081211625,0.0009381393,0.0011428001],"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":[0.00029151913,0.00024941302,0.0015972193,0.00010949047,0.0001345793,0.00014428311,0.00007960984,0.013024841,0.036885228,0.0021070563,0.008951373,0.9364254],"study_design_scores_gemma":[0.00010260078,0.0001760032,0.0048593516,0.000022683565,0.00012639444,0.0005391124,0.00007962867,0.9507919,0.032350212,0.0044322778,0.0064392253,0.00008057053],"about_ca_topic_score_codex":0.003329954,"about_ca_topic_score_gemma":0.0056332615,"teacher_disagreement_score":0.003329954,"about_ca_system_score_codex":0.00042595546,"about_ca_system_score_gemma":0.0010597021,"threshold_uncertainty_score":0.0067714453},"labels":[],"label_agreement":null},{"id":"W2801771958","doi":"10.3390/info9050119","title":"Fast Identification of High Utility Itemsets from Candidates","year":2018,"lang":"en","type":"article","venue":"Information","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Science Foundation of Hubei Province","keywords":"Computation; Computer science; Identification (biology); Data mining; Tree (set theory); Set (abstract data type); Algorithm; Mathematics","score_opus":0.00928728821890769,"score_gpt":0.2380634091808697,"score_spread":0.228776120961962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801771958","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.104784705,0.0010157152,0.8868128,0.00041067242,0.00009129148,0.0008404357,0.0015143142,0.0023322082,0.0021978568],"genre_scores_gemma":[0.38447788,0.0005789966,0.60598564,0.00015751472,0.000082809995,0.0005337916,0.00542419,0.0001895903,0.0025695064],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99813133,0.00026378082,0.0001892484,0.0003215364,0.0008431774,0.00025090546],"domain_scores_gemma":[0.9947221,0.002510687,0.00056296657,0.0006821664,0.0012424625,0.00027950446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019994273,0.0010980535,0.0019254732,0.004819131,0.0013508096,0.0020459383,0.0019875132,0.00102479,0.0019497938],"category_scores_gemma":[0.012812115,0.0006244598,0.0014729475,0.0054227165,0.0005078541,0.003337738,0.0020336893,0.001168276,0.0013545757],"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":[0.001123935,0.0005266097,0.022613145,0.0007598154,0.00019848123,0.0011388187,0.0008055281,0.04797343,0.016219744,0.023843076,0.017256942,0.8675405],"study_design_scores_gemma":[0.00014512283,0.00048994797,0.007103046,0.00016389304,0.0001389994,0.0018112531,0.000776721,0.892689,0.024613487,0.059346013,0.0126349665,0.00008760372],"about_ca_topic_score_codex":0.0015723086,"about_ca_topic_score_gemma":0.0027248776,"teacher_disagreement_score":0.004819131,"about_ca_system_score_codex":0.00066502125,"about_ca_system_score_gemma":0.0023671326,"threshold_uncertainty_score":0.010574102},"labels":[],"label_agreement":null},{"id":"W2810490377","doi":"10.1007/s10618-020-00677-w","title":"Model-based exception mining for object-relational data","year":2020,"lang":"en","type":"preprint","venue":"Data Mining and Knowledge Discovery","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":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Object (grammar); Outlier; Data mining; Metric (unit); Bayesian network; Probabilistic logic; Relational model; Representation (politics); Relational database; Population; Statistical relational learning; Artificial intelligence; Object model; Graphical model; Data modeling; Statistical model; Database","score_opus":0.20507464499303893,"score_gpt":0.3555595803813095,"score_spread":0.1504849353882706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810490377","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02940197,0.00043785662,0.9637769,0.00037507463,0.00011548149,0.00015448092,0.00076100527,0.0041252016,0.00085201196],"genre_scores_gemma":[0.40286344,0.00039632103,0.5919204,0.00024542102,0.000094709,0.00016690887,0.0026015434,0.0004353208,0.0012759916],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9947812,0.0011412255,0.0006910452,0.00090955716,0.0020674623,0.00040956232],"domain_scores_gemma":[0.9861572,0.005290629,0.0013811648,0.004974446,0.0018241201,0.00037241],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043520927,0.0009239136,0.0020815749,0.0031849092,0.001252931,0.0045027575,0.0034027402,0.0012317377,0.0011720028],"category_scores_gemma":[0.020668542,0.0006942317,0.002827458,0.0034338036,0.0011388735,0.004864201,0.0026993335,0.0022727198,0.0006219551],"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":[0.001143259,0.0007880978,0.043255545,0.00086569315,0.00091341033,0.001157801,0.0007056828,0.26926586,0.011563134,0.07025283,0.017515382,0.5825733],"study_design_scores_gemma":[0.00003735269,0.00009593097,0.0010558754,0.000050687282,0.0001473558,0.0003921858,0.000114504335,0.9068093,0.007525007,0.08075069,0.002988164,0.00003290628],"about_ca_topic_score_codex":0.004516327,"about_ca_topic_score_gemma":0.007145752,"teacher_disagreement_score":0.004516327,"about_ca_system_score_codex":0.0008890066,"about_ca_system_score_gemma":0.0026151366,"threshold_uncertainty_score":0.023016334},"labels":[],"label_agreement":null},{"id":"W2811102277","doi":"10.14569/ijacsa.2018.090620","title":"Generating Relational Database using Ontology Review","year":2018,"lang":"en","type":"article","venue":"International Journal of Advanced Computer Science and Applications","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Relational database; Ontology; Database schema; USable; Database model; Relational model; Inference; Database; Knowledge extraction; Database design; Schema (genetic algorithms); Information retrieval; Data mining; World Wide Web; Artificial intelligence","score_opus":0.03421802743340294,"score_gpt":0.3473999532232925,"score_spread":0.31318192578988957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2811102277","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010368734,0.010481377,0.9456295,0.0018965416,0.0006776504,0.0009865965,0.0032344298,0.0028014183,0.023923779],"genre_scores_gemma":[0.0740156,0.012308308,0.88997823,0.00040552608,0.00020676316,0.00051288994,0.009374537,0.0005074851,0.012690657],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9946025,0.0012108719,0.0007349733,0.00075762795,0.0025229352,0.0001710616],"domain_scores_gemma":[0.99623495,0.0008779517,0.00024091564,0.0007840819,0.0017446347,0.000117491865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034680592,0.00047758108,0.000728955,0.004654938,0.0011220985,0.00429219,0.0019724634,0.0006669276,0.0065692887],"category_scores_gemma":[0.009641517,0.0004517092,0.0020811378,0.0046130475,0.0005942072,0.00570555,0.0021449174,0.0010087336,0.003260047],"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":[0.00010642082,0.00012931573,0.0028684516,0.0016664941,0.00019923082,0.00095177686,0.00096130505,0.0059156185,0.009700452,0.19882675,0.046629176,0.732045],"study_design_scores_gemma":[0.00004526354,0.00007771367,0.0016834527,0.0005790657,0.00021084712,0.0021170576,0.0011297953,0.05336661,0.020183813,0.067497596,0.8530052,0.00010365612],"about_ca_topic_score_codex":0.0044610444,"about_ca_topic_score_gemma":0.003723914,"teacher_disagreement_score":0.0065692887,"about_ca_system_score_codex":0.0011971479,"about_ca_system_score_gemma":0.0029802916,"threshold_uncertainty_score":0.021976471},"labels":[],"label_agreement":null},{"id":"W2819365590","doi":"10.1007/978-3-319-96133-0_1","title":"Fusing Dimension Reduction and Classification for Mining Interesting Frequent Patterns in Patients Data","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms 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":"Ontario Tech University","funders":"","keywords":"Computer science; Dimension (graph theory); Dimensionality reduction; Reduction (mathematics); Data reduction; Data mining; Artificial intelligence; Pattern recognition (psychology); Mathematics; Combinatorics","score_opus":0.06933210639986034,"score_gpt":0.2981770108183694,"score_spread":0.22884490441850905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2819365590","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2037773,0.0074600102,0.77748555,0.0013955614,0.0005020481,0.00035802397,0.0040333685,0.0022185503,0.0027695566],"genre_scores_gemma":[0.6420563,0.0026551634,0.34436667,0.00033109402,0.0007367939,0.0004195691,0.0076223593,0.0001133485,0.001698688],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975569,0.00053437316,0.00036820478,0.00053243194,0.00076687755,0.00024120933],"domain_scores_gemma":[0.99458003,0.003507727,0.00038141198,0.0006666594,0.00070919754,0.00015500598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026306643,0.001314595,0.0024626872,0.004373582,0.0005456952,0.0017280154,0.0011550962,0.0010393141,0.0014173345],"category_scores_gemma":[0.008759603,0.0004347337,0.0025352102,0.0047150073,0.00043091862,0.0018534616,0.0015363101,0.00129767,0.0009190395],"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":[0.00090825907,0.000704322,0.037550323,0.0005838876,0.00081944617,0.00054566714,0.00048368884,0.028072001,0.011714271,0.003958941,0.009356281,0.905303],"study_design_scores_gemma":[0.00008322051,0.00061296346,0.026230425,0.00021678387,0.00073875376,0.0012452782,0.00061802374,0.9202331,0.008873291,0.03372665,0.007314429,0.00010701859],"about_ca_topic_score_codex":0.0017948876,"about_ca_topic_score_gemma":0.0021160387,"teacher_disagreement_score":0.004373582,"about_ca_system_score_codex":0.00036889527,"about_ca_system_score_gemma":0.0009773071,"threshold_uncertainty_score":0.013912439},"labels":[],"label_agreement":null},{"id":"W2885252781","doi":"10.1007/978-981-13-0695-2_9","title":"Constrained Frequent Pattern Mining from Big Data Via Crowdsourcing","year":2018,"lang":"en","type":"book-chapter","venue":"Advances in intelligent systems and computing","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":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Crowdsourcing; Big data; Computer science; Crowds; Data science; Task (project management); Data mining; Knowledge extraction; World Wide Web; Engineering","score_opus":0.0568707664357147,"score_gpt":0.2847238071302123,"score_spread":0.22785304069449758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885252781","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018059308,0.0012323514,0.9756218,0.0004305989,0.00017315825,0.000311522,0.0009740068,0.0007645822,0.002432645],"genre_scores_gemma":[0.30022785,0.0011876931,0.68453944,0.00036748374,0.00044198192,0.00085748476,0.0052175336,0.0003267234,0.006833854],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9937895,0.0017422785,0.00037471592,0.0013476298,0.0024536322,0.00029221518],"domain_scores_gemma":[0.98007625,0.013065295,0.00070378435,0.0040550157,0.0017378245,0.00036187522],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004937835,0.0013931015,0.0027547614,0.0036844886,0.0015743589,0.0029107195,0.0050518885,0.0019742872,0.0031435785],"category_scores_gemma":[0.025343591,0.0010283554,0.002095149,0.006489217,0.0015759878,0.004021166,0.005446637,0.0021794941,0.0015530296],"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":[0.00075878506,0.00041237514,0.0053142584,0.0011934451,0.00065752823,0.0009918385,0.00085230445,0.22484499,0.009518791,0.036145575,0.02362332,0.6956868],"study_design_scores_gemma":[0.000046950157,0.000040798823,0.0007125698,0.00005308736,0.000049143593,0.0001672061,0.00019225015,0.89079106,0.0017840624,0.09956556,0.0065574623,0.00003978358],"about_ca_topic_score_codex":0.0064980416,"about_ca_topic_score_gemma":0.009172812,"teacher_disagreement_score":0.0064980416,"about_ca_system_score_codex":0.001041906,"about_ca_system_score_gemma":0.0022583853,"threshold_uncertainty_score":0.026114106},"labels":[],"label_agreement":null},{"id":"W2886357844","doi":"10.1007/s11053-018-9400-9","title":"Correction to: Calibration of Genetic Algorithm Parameters for Mining-Related Optimization Problems","year":2018,"lang":"en","type":"article","venue":"Natural Resources Research","topic":"Data Mining Algorithms and Applications","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":"McGill University","funders":"","keywords":"Mistake; Calibration; Computer science; Genetic algorithm; Algorithm; Data mining; Information retrieval; Machine learning; Mathematics; Statistics; Political science; Law","score_opus":0.04075672949975935,"score_gpt":0.3377688603082254,"score_spread":0.29701213080846606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2886357844","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00095727283,0.00076988025,0.010338799,0.03844795,0.9386015,0.00008512225,0.0045962203,0.0032261254,0.0029772401],"genre_scores_gemma":[0.14989887,0.00704794,0.11679871,0.06851843,0.3332717,0.0010458145,0.016995056,0.016280686,0.29014283],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99335676,0.0011312461,0.0014272074,0.0012969614,0.0021498727,0.0006379747],"domain_scores_gemma":[0.8950419,0.026111143,0.0033096701,0.010012985,0.06231835,0.0032059876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004030546,0.0023051987,0.0030111447,0.004116776,0.0033477177,0.0042672213,0.0052441573,0.007471113,0.16419359],"category_scores_gemma":[0.14657936,0.0012528087,0.0019163952,0.004929637,0.002526174,0.004010301,0.0033067146,0.010693173,0.06966169],"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":[0.00014206645,0.000024763613,0.00026573593,0.00033526053,0.000040354782,0.00037877413,0.00008973932,0.00051478285,0.00030552465,0.0028867824,0.9771408,0.01787548],"study_design_scores_gemma":[0.00020490726,0.00007706487,0.00291576,0.0004679198,0.000065683635,0.0013995221,0.00031998786,0.0052810106,0.0031321794,0.01179309,0.9741765,0.00016635902],"about_ca_topic_score_codex":0.009786657,"about_ca_topic_score_gemma":0.01058221,"teacher_disagreement_score":0.16419359,"about_ca_system_score_codex":0.0037423456,"about_ca_system_score_gemma":0.0049437713,"threshold_uncertainty_score":0.54928225},"labels":[],"label_agreement":null},{"id":"W2887479280","doi":"10.1007/978-981-13-0695-2_8","title":"Constrained Big Data Mining in an Edge Computing Environment","year":2018,"lang":"en","type":"book-chapter","venue":"Advances in intelligent systems and computing","topic":"Data Mining Algorithms and Applications","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 Manitoba","funders":"","keywords":"Big data; Computer science; Edge computing; Enhanced Data Rates for GSM Evolution; Data mining; Artificial intelligence","score_opus":0.0711218785763092,"score_gpt":0.29936127626499937,"score_spread":0.22823939768869017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2887479280","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025641233,0.0094453385,0.94966656,0.0015334192,0.00037946968,0.00006938789,0.00052867207,0.00062374223,0.012112207],"genre_scores_gemma":[0.3766136,0.014020083,0.58710855,0.0008606101,0.00097224646,0.00018491434,0.0018866028,0.00053238875,0.017821027],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996178,0.00007097949,0.000029673683,0.00008101228,0.0001676134,0.000032833275],"domain_scores_gemma":[0.998579,0.0008877755,0.00006909523,0.00020631941,0.00017663294,0.00008124321],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007180017,0.00057819753,0.0007522506,0.00060120557,0.0004269319,0.0014482554,0.00186624,0.0005797084,0.0023818677],"category_scores_gemma":[0.00294994,0.00043177843,0.00040587952,0.0027845611,0.00046349256,0.0026376457,0.0014200074,0.001321778,0.00065921777],"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":[0.0005099556,0.00017764172,0.003669039,0.0009554038,0.00018782433,0.0006873825,0.00015586978,0.16515319,0.0074791205,0.15080145,0.052905004,0.61731803],"study_design_scores_gemma":[0.000015864562,0.00004304723,0.0012258578,0.00007604917,0.000027410642,0.00046367096,0.000060666847,0.7724207,0.0041194423,0.18893354,0.03258871,0.000025046207],"about_ca_topic_score_codex":0.00085867714,"about_ca_topic_score_gemma":0.0012399288,"teacher_disagreement_score":0.0023818677,"about_ca_system_score_codex":0.00031109832,"about_ca_system_score_gemma":0.0006368564,"threshold_uncertainty_score":0.007968128},"labels":[],"label_agreement":null},{"id":"W2889202450","doi":"10.1016/j.procs.2018.07.294","title":"Spark-based data analytics of sequence motifs in large omics data","year":2018,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":26,"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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; Tertiary Education Trust Fund","keywords":"Computer science; SPARK (programming language); Analytics; DNA sequencing; Genomics; Sequence motif; Data mining; Sequence (biology); Computational biology; Bioinformatics; Data science; Genome; DNA; Biology; Genetics; Gene","score_opus":0.12647893774525143,"score_gpt":0.3419665985896255,"score_spread":0.2154876608443741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889202450","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12650393,0.0008453299,0.8583182,0.0006611087,0.00018460804,0.00038749923,0.0015797706,0.0094330255,0.00208645],"genre_scores_gemma":[0.39146084,0.00041539225,0.6011057,0.00015373135,0.00009474735,0.00027812156,0.004686172,0.00029681408,0.0015084033],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871993,0.0001867531,0.000108025466,0.00033768968,0.00051276915,0.00013492293],"domain_scores_gemma":[0.9982863,0.0005550269,0.0001377267,0.00031542886,0.00046304677,0.00024249322],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017289708,0.0009932583,0.0014251046,0.0017267023,0.0012709856,0.0012523768,0.0020985364,0.00059940846,0.0007026051],"category_scores_gemma":[0.004100866,0.00040739132,0.001242589,0.0030290615,0.0006299456,0.0015188508,0.0015420809,0.00094890024,0.0004942361],"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":[0.0026795373,0.0013535391,0.02194173,0.0010011495,0.0007076684,0.0013114121,0.0011944998,0.28565153,0.07329198,0.020900214,0.02839156,0.5615751],"study_design_scores_gemma":[0.000104160004,0.00017002769,0.0016483933,0.000009707515,0.00003894113,0.00028683819,0.00021175592,0.96007055,0.0140099665,0.018723205,0.0047031185,0.000023299337],"about_ca_topic_score_codex":0.0045175618,"about_ca_topic_score_gemma":0.0056364993,"teacher_disagreement_score":0.0045175618,"about_ca_system_score_codex":0.00057903444,"about_ca_system_score_gemma":0.0021663597,"threshold_uncertainty_score":0.00914377},"labels":[],"label_agreement":null},{"id":"W2890804179","doi":"10.23889/ijpds.v3i4.622","title":"Association rule mining to identify potential under-coding of conditions in the problem list in primary care electronic medical records","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Association rule learning; Coding (social sciences); Medicine; Medical record; Medical diagnosis; Confidence interval; Data mining; Family medicine; Medical emergency; Computer science; Statistics; Mathematics; Internal medicine","score_opus":0.033696190442696554,"score_gpt":0.3872326723535957,"score_spread":0.35353648191089915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890804179","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2811006,0.0040577827,0.6580252,0.007381989,0.00055053795,0.002824937,0.029132875,0.00710206,0.009824004],"genre_scores_gemma":[0.45297214,0.0009810136,0.52145714,0.0009339051,0.00021443304,0.001008041,0.020932771,0.00009368734,0.0014069092],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9835791,0.0059023937,0.0028241752,0.0030135168,0.004143807,0.0005370745],"domain_scores_gemma":[0.91348475,0.065322444,0.009091631,0.0040845843,0.0072625214,0.00075416476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0144136585,0.0009938868,0.0012739016,0.0076014753,0.0009844041,0.0028549032,0.0020325321,0.0011566558,0.00233749],"category_scores_gemma":[0.051463973,0.0004888803,0.001642592,0.00851105,0.0005959126,0.0018545091,0.0015874109,0.0014897287,0.0012739125],"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":[0.0005960412,0.0012060809,0.37236014,0.0016834842,0.001453509,0.0015368148,0.0010860512,0.04044932,0.0028079043,0.006863014,0.028522082,0.54143554],"study_design_scores_gemma":[0.00022201057,0.0008025962,0.111495666,0.0010793047,0.0008476163,0.0029766606,0.0022788951,0.7945658,0.009369981,0.046440113,0.02977158,0.00014973742],"about_ca_topic_score_codex":0.007937667,"about_ca_topic_score_gemma":0.009671865,"teacher_disagreement_score":0.0144136585,"about_ca_system_score_codex":0.0012182293,"about_ca_system_score_gemma":0.0027827676,"threshold_uncertainty_score":0.076227605},"labels":[],"label_agreement":null},{"id":"W2895523194","doi":"10.1007/978-3-319-95810-1_11","title":"Finding Influential Factors for Different Types of Cancer: A Data Mining Approach","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in social networks","topic":"Data Mining Algorithms 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 Calgary","funders":"","keywords":"Cancer; Association rule learning; Scope (computer science); Domain (mathematical analysis); Set (abstract data type); Disease; Data science; Population; Medicine; Data mining; Computer science; Environmental health; Pathology; Mathematics; Internal medicine","score_opus":0.062264058787586764,"score_gpt":0.31629427827926015,"score_spread":0.25403021949167337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2895523194","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7488605,0.013555261,0.1974523,0.002910854,0.00042710162,0.001035823,0.02001681,0.00076808233,0.014973308],"genre_scores_gemma":[0.9109848,0.0024769932,0.07720934,0.00021821937,0.00037461452,0.0002841298,0.00536018,0.000067708184,0.0030239418],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846566,0.00022878523,0.0001603841,0.0005329879,0.0004671413,0.00014510388],"domain_scores_gemma":[0.9900328,0.007200814,0.00088277005,0.0004937537,0.0009891271,0.00040069353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022472527,0.001014198,0.0012346026,0.007564508,0.0011549091,0.0021724075,0.001814531,0.0013011025,0.0038889295],"category_scores_gemma":[0.014506108,0.00043795918,0.0035055815,0.0073695597,0.0006162487,0.0020437846,0.00087721786,0.0015539947,0.0011591209],"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":[0.0006023838,0.0004243537,0.76959383,0.0006996416,0.0014227135,0.00053079636,0.00066283013,0.003338776,0.0028553326,0.003848073,0.0065151015,0.20950618],"study_design_scores_gemma":[0.00019441161,0.0011013664,0.7396521,0.0006418068,0.006116389,0.0069469763,0.0039143725,0.1332405,0.011074003,0.068565436,0.028296823,0.00025585335],"about_ca_topic_score_codex":0.0058810213,"about_ca_topic_score_gemma":0.009996033,"teacher_disagreement_score":0.007564508,"about_ca_system_score_codex":0.0007851394,"about_ca_system_score_gemma":0.0011645273,"threshold_uncertainty_score":0.013009787},"labels":[],"label_agreement":null},{"id":"W2895626021","doi":"10.4018/978-1-59140-557-3.ch185","title":"Rule Qualities and Knowledge Combination for Decision-Making","year":2005,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Process (computing); Data mining; Data science; Quality (philosophy); Knowledge extraction","score_opus":0.026364529738013436,"score_gpt":0.30722411174918685,"score_spread":0.2808595820111734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2895626021","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008607643,0.018774092,0.8378115,0.0044505503,0.0005109644,0.00016321485,0.00058397895,0.00062006264,0.12847798],"genre_scores_gemma":[0.27978307,0.011799066,0.6829584,0.0007860633,0.00070670136,0.0002288022,0.0012539377,0.00016628514,0.022317572],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99787176,0.0007999209,0.0001891873,0.000380519,0.0006707333,0.00008781504],"domain_scores_gemma":[0.9955206,0.0034056052,0.00019025416,0.00048749716,0.00029974314,0.00009625974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030483336,0.0010602514,0.00092930486,0.0021212325,0.0005594824,0.00493732,0.0019341563,0.0012172277,0.018106721],"category_scores_gemma":[0.009262148,0.00042757925,0.001105937,0.003019772,0.0023785615,0.006207096,0.0015463539,0.0019150149,0.00413054],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008178647,0.00007171311,0.0005706276,0.00062449125,0.00011598411,0.0003160179,0.0003570212,0.025085917,0.0006554587,0.63381803,0.011687003,0.3266159],"study_design_scores_gemma":[0.00001421666,0.000029286484,0.0002367896,0.00024831813,0.00003718456,0.00016886799,0.000087501845,0.037053626,0.00048922276,0.93241245,0.029202878,0.000019693993],"about_ca_topic_score_codex":0.0011613152,"about_ca_topic_score_gemma":0.001362193,"teacher_disagreement_score":0.018106721,"about_ca_system_score_codex":0.00132188,"about_ca_system_score_gemma":0.0008243341,"threshold_uncertainty_score":0.06057304},"labels":[],"label_agreement":null},{"id":"W2898055277","doi":"","title":"Ottawa University, Gangwish Library: Data Science: Data Science Resources","year":2016,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Library science; Data science; Information retrieval","score_opus":0.04446073464391085,"score_gpt":0.2709635707124088,"score_spread":0.22650283606849794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898055277","genre_codex":"dataset","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038983931,0.008345703,0.003253192,0.012903627,0.0014966688,0.00027053204,0.52185804,0.013804446,0.43416935],"genre_scores_gemma":[0.009316228,0.01435321,0.012189946,0.0017700504,0.00026697374,0.0002599557,0.13888374,0.0058156676,0.8171443],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99867153,0.000066015135,0.00015443683,0.00025994435,0.0007095651,0.00013858343],"domain_scores_gemma":[0.98933905,0.0021610828,0.0003924234,0.0014653265,0.0039029545,0.0027391615],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0012377247,0.0011216102,0.0017642227,0.008694559,0.006824711,0.011464673,0.0017502233,0.0017725958,0.4913523],"category_scores_gemma":[0.009011154,0.0020429797,0.0007387411,0.02347023,0.0019473917,0.0065422766,0.0031530976,0.0024106326,0.23411953],"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":[0.00011094606,0.00002518425,0.0007222993,0.00062625995,0.00001552313,0.000083232604,0.00026679938,0.00008956301,0.00066003384,0.0027818584,0.94240826,0.052210003],"study_design_scores_gemma":[0.000018518505,0.000008776034,0.0022892223,0.00021252995,0.000017069064,0.000036344438,0.0002670425,0.00008620094,0.00070406025,0.0011676546,0.99515,0.000042535674],"about_ca_topic_score_codex":0.47582862,"about_ca_topic_score_gemma":0.7978241,"teacher_disagreement_score":0.5086477,"about_ca_system_score_codex":0.009587078,"about_ca_system_score_gemma":0.038010936,"threshold_uncertainty_score":0.946118},"labels":[],"label_agreement":null},{"id":"W2898156518","doi":"10.1109/asonam.2018.8508660","title":"Mining ‘Following’ Patterns from Big but Sparsely Distributed Social Network Data","year":2018,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":14,"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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Big data; Computer science; Social network (sociolinguistics); Data science; Interdependence; Variety (cybernetics); Social group; Social computing; World Wide Web; Data mining; Social media; Artificial intelligence","score_opus":0.11031224501941789,"score_gpt":0.2924212039849359,"score_spread":0.182108958965518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898156518","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28903058,0.0009026819,0.6987807,0.001446082,0.00009079766,0.0004053671,0.005208972,0.0015954457,0.0025394154],"genre_scores_gemma":[0.6854466,0.00046146696,0.30165768,0.0002496234,0.00010038887,0.00027474188,0.010335794,0.000061902436,0.001411829],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985039,0.00031724456,0.00013495488,0.00050733355,0.00041038368,0.00012611104],"domain_scores_gemma":[0.9951137,0.0023093917,0.00086552446,0.0010362152,0.0004875917,0.00018771282],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094906613,0.0009284454,0.0010627675,0.0031923554,0.0009088499,0.0010808778,0.0023718611,0.0015107004,0.0006929735],"category_scores_gemma":[0.007584445,0.00043490177,0.0010845802,0.0036197228,0.00068368186,0.0031200808,0.0016015657,0.0010692719,0.0005741655],"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":[0.00075467356,0.00086125126,0.1336253,0.00090991944,0.0007130239,0.0022713465,0.0019077634,0.27776444,0.017049192,0.02304241,0.015809087,0.5252916],"study_design_scores_gemma":[0.000028474175,0.000096152326,0.008434958,0.000048631664,0.00006502066,0.000736198,0.00061045116,0.94192016,0.0043432675,0.03794308,0.005750195,0.00002330135],"about_ca_topic_score_codex":0.0040342766,"about_ca_topic_score_gemma":0.008442253,"teacher_disagreement_score":0.0040342766,"about_ca_system_score_codex":0.0006074697,"about_ca_system_score_gemma":0.00074897695,"threshold_uncertainty_score":0.008021593},"labels":[],"label_agreement":null},{"id":"W2898462192","doi":"10.1109/asonam.2018.8508353","title":"Clickstream Analytics: An Experimental Analysis of the Amazon Users' Simulated Monthly Traffic","year":2018,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Clickstream; Analytics; Computer science; Amazon rainforest; Cloud computing; Data science; Volume (thermodynamics); Data analysis; Big data; Data mining; World Wide Web; The Internet","score_opus":0.021363999186128853,"score_gpt":0.29297013132504557,"score_spread":0.2716061321389167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898462192","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99140644,0.000097637196,0.0038666269,0.00009059992,0.00006187151,0.000084465486,0.002885414,0.0006432825,0.00086370413],"genre_scores_gemma":[0.98861223,0.00007678083,0.006085788,0.00003714777,0.000023647712,0.00005912986,0.004509838,0.000041291656,0.00055414636],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883765,0.00025796876,0.00010921751,0.00019979426,0.0004767123,0.000118712655],"domain_scores_gemma":[0.99533576,0.0024071266,0.00033034984,0.0005843064,0.0009668828,0.00037557658],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012953331,0.0005916816,0.00061272364,0.0011813781,0.00035485358,0.00072213786,0.0008353418,0.000605331,0.0010122948],"category_scores_gemma":[0.004985973,0.00016872208,0.0005002939,0.0016173036,0.0003095805,0.00077279145,0.00046026355,0.00071030844,0.00036334095],"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":[0.011105077,0.012929284,0.35687804,0.0014269294,0.001337011,0.0026732215,0.0017963393,0.19208886,0.10415426,0.007143738,0.04111592,0.26735136],"study_design_scores_gemma":[0.00014772003,0.0028853891,0.10955984,0.00002358976,0.000118658674,0.0006780704,0.00045300566,0.85723466,0.023971923,0.0015115266,0.0033310326,0.000084542815],"about_ca_topic_score_codex":0.008516347,"about_ca_topic_score_gemma":0.007593096,"teacher_disagreement_score":0.008516347,"about_ca_system_score_codex":0.00041721255,"about_ca_system_score_gemma":0.00044338472,"threshold_uncertainty_score":0.01693356},"labels":[],"label_agreement":null},{"id":"W2898670591","doi":"","title":"Privacy Sensitive Construction of Junction Tree Agent Organization for Multiagent Graphical Models.","year":2018,"lang":"en","type":"article","venue":"Probabilistic Graphical Models","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":"University of Guelph","funders":"","keywords":"Computer science; Multi-agent system; Tree (set theory); Graphical model; Computer security; Artificial intelligence","score_opus":0.03175791186320538,"score_gpt":0.2517132354035583,"score_spread":0.2199553235403529,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898670591","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012646043,0.00009071027,0.9845345,0.00021548344,0.000022824957,0.000060786613,0.00026779878,0.000401853,0.0017599595],"genre_scores_gemma":[0.44279456,0.00026538668,0.550397,0.00018712127,0.000048010406,0.00027274556,0.0021911585,0.00027823602,0.0035658507],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99783796,0.0009105736,0.00009624376,0.00042601276,0.00055013393,0.00017911867],"domain_scores_gemma":[0.99437934,0.0026328657,0.000445967,0.0014876728,0.00065594923,0.00039816494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019965027,0.00042807194,0.00081696775,0.0010967155,0.0012061582,0.0019336931,0.002025689,0.0013306171,0.0027094383],"category_scores_gemma":[0.013771046,0.00066197966,0.0014750726,0.0012525892,0.00092381897,0.0032315722,0.0034404376,0.0022871448,0.0009405652],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002233599,0.0003076518,0.0050347294,0.00022790945,0.00015429502,0.0005166122,0.0009942574,0.40818822,0.005799859,0.4242386,0.016568156,0.1377464],"study_design_scores_gemma":[0.000010716007,0.000024723737,0.00022604273,0.000018234017,0.000026863532,0.00008699445,0.00009991051,0.8255509,0.0016155447,0.16870628,0.0036241987,0.000009511945],"about_ca_topic_score_codex":0.0024716705,"about_ca_topic_score_gemma":0.003993754,"teacher_disagreement_score":0.0027094383,"about_ca_system_score_codex":0.0010706716,"about_ca_system_score_gemma":0.0020233816,"threshold_uncertainty_score":0.010558665},"labels":[],"label_agreement":null},{"id":"W2899387524","doi":"10.46430/phes0040","title":"Introducción a Topic Modeling y MALLET","year":2018,"lang":"es","type":"article","venue":"The Programming Historian en español","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Carleton University","funders":"","keywords":"Mallet; Humanities; Computer science; Philosophy; Physics; Acoustics","score_opus":0.017425092061939304,"score_gpt":0.26779934531071853,"score_spread":0.2503742532487792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2899387524","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003492788,0.025557209,0.9290394,0.009634176,0.0024817975,0.00014056638,0.0021651846,0.0014633308,0.026025606],"genre_scores_gemma":[0.14401151,0.05480713,0.7072608,0.0062842076,0.01815438,0.0010310474,0.0069068396,0.0021642062,0.05937994],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99714017,0.001172218,0.0002029209,0.0007748671,0.00056246045,0.00014733204],"domain_scores_gemma":[0.9923894,0.005818425,0.0003481988,0.0006510641,0.0005796164,0.0002134428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004303176,0.001242802,0.0013237806,0.002741994,0.0012694346,0.0047759884,0.002153456,0.0023861432,0.020108169],"category_scores_gemma":[0.012590864,0.0009904385,0.0019213769,0.007166893,0.0016477697,0.0075434735,0.0026929036,0.0051294854,0.008819087],"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":[0.00020644208,0.00010168488,0.0037428741,0.0011569177,0.0002393148,0.00039077128,0.0013888505,0.02093159,0.0012934392,0.5112877,0.07417413,0.3850864],"study_design_scores_gemma":[0.000039029757,0.000069791255,0.0016935549,0.0006415492,0.000120867444,0.0007701792,0.00027595385,0.083697826,0.0012118197,0.4169189,0.49445784,0.00010256889],"about_ca_topic_score_codex":0.005007708,"about_ca_topic_score_gemma":0.0035876536,"teacher_disagreement_score":0.020108169,"about_ca_system_score_codex":0.0017759943,"about_ca_system_score_gemma":0.0019096533,"threshold_uncertainty_score":0.06726849},"labels":[],"label_agreement":null},{"id":"W2901871898","doi":"10.1609/aaai.v33i01.33011495","title":"Constraint-Based Sequential Pattern Mining with Decision Diagrams","year":2019,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"Office of Naval Research","keywords":"Computer science; Constraint (computer-aided design); Data mining; Sequential Pattern Mining; Scalability; Representation (politics); Projection (relational algebra); Artificial intelligence; Algorithm; Database; Mathematics","score_opus":0.0817448956449763,"score_gpt":0.3044731405390466,"score_spread":0.2227282448940703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901871898","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006382488,0.00012554381,0.9914888,0.00011180249,0.000013703286,0.00013825318,0.00041595954,0.00096610107,0.00035728142],"genre_scores_gemma":[0.09483136,0.00019455055,0.9029539,0.000068816895,0.000015975576,0.00026356874,0.001144729,0.000085981585,0.000441087],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965449,0.0012958413,0.00032338215,0.000562462,0.0011441907,0.00012923974],"domain_scores_gemma":[0.9853461,0.011552453,0.00071160385,0.0009794048,0.0012107254,0.00019976303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026960915,0.0009498567,0.0010525566,0.0020422165,0.00053551607,0.0018418527,0.0016436536,0.0007920887,0.0031261141],"category_scores_gemma":[0.019573007,0.0006147727,0.0013570796,0.0030476726,0.00069197203,0.0025334456,0.0015056467,0.0013545906,0.00064010615],"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":[0.00066912884,0.00026989705,0.006351873,0.0010370526,0.00032830262,0.0005270029,0.00028812926,0.40818694,0.010356821,0.06494201,0.0055578267,0.50148505],"study_design_scores_gemma":[0.00006023265,0.000064375454,0.0002586485,0.000029275487,0.000038308997,0.00018575891,0.000039729886,0.9492843,0.0059168264,0.040270224,0.0038351032,0.000017212304],"about_ca_topic_score_codex":0.0034285842,"about_ca_topic_score_gemma":0.00418192,"teacher_disagreement_score":0.0034285842,"about_ca_system_score_codex":0.0008558599,"about_ca_system_score_gemma":0.0028651867,"threshold_uncertainty_score":0.014258504},"labels":[],"label_agreement":null},{"id":"W2902085258","doi":"10.1007/s00180-020-00987-z","title":"BEST: a decision tree algorithm that handles missing values","year":2020,"lang":"en","type":"article","venue":"Computational Statistics","topic":"Data Mining Algorithms and Applications","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":"University of Toronto","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Missing data; Decision tree; Feature (linguistics); Decision tree learning; Tree (set theory); Incremental decision tree","score_opus":0.05119056041956461,"score_gpt":0.2995483670193186,"score_spread":0.24835780659975398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902085258","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003672636,0.0009247303,0.9808868,0.0005008106,0.00030394868,0.00012310961,0.0020909912,0.010577499,0.0009193883],"genre_scores_gemma":[0.044424307,0.00047456948,0.9458104,0.0006905644,0.0002733086,0.00025517936,0.0040751477,0.001892009,0.0021045692],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99582183,0.0015917807,0.000292513,0.0006410359,0.0014210427,0.00023169935],"domain_scores_gemma":[0.99060327,0.006024302,0.00035885564,0.001335624,0.0012968729,0.00038106437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063027455,0.0017643605,0.003235917,0.004558333,0.0015172765,0.0029134662,0.0040941196,0.003144665,0.008195007],"category_scores_gemma":[0.025227686,0.0017526429,0.0022577269,0.0039808066,0.0007887318,0.003923949,0.0033930952,0.003387941,0.005057824],"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":[0.0015094744,0.00047660634,0.004064476,0.0008207394,0.00080079935,0.0003817925,0.00020717294,0.06469321,0.0040779016,0.012984137,0.0986618,0.8113219],"study_design_scores_gemma":[0.00042985755,0.00026086008,0.0009380853,0.00018322041,0.00046683746,0.00083526346,0.00008833459,0.84035766,0.008152427,0.10423941,0.0439382,0.000109939945],"about_ca_topic_score_codex":0.0020506245,"about_ca_topic_score_gemma":0.0044141747,"teacher_disagreement_score":0.008195007,"about_ca_system_score_codex":0.0007221365,"about_ca_system_score_gemma":0.0027552538,"threshold_uncertainty_score":0.033332467},"labels":[],"label_agreement":null},{"id":"W2908387075","doi":"10.1109/icebe.2018.00014","title":"Meta-Feature Based Data Mining Service Selection and Recommendation Using Machine Learning Models","year":2018,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Support vector machine; Machine learning; Artificial intelligence; Feature selection; Data mining; Quality of service; Meta learning (computer science); Multilayer perceptron; Web service; Process (computing); Service (business); Perceptron; Selection (genetic algorithm); Artificial neural network; World Wide Web; Engineering","score_opus":0.23515215374792234,"score_gpt":0.3235037021648072,"score_spread":0.08835154841688489,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2908387075","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14425564,0.0015963075,0.8479936,0.001113496,0.00012417273,0.0002772274,0.0007922065,0.0024017063,0.0014455868],"genre_scores_gemma":[0.7759159,0.00042507536,0.22108054,0.00021449644,0.00009100766,0.00022822358,0.0011169501,0.00006474924,0.00086300384],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974661,0.0008193323,0.00034400445,0.00053640996,0.0006248477,0.00020937363],"domain_scores_gemma":[0.9925039,0.0043460354,0.00069781597,0.0006323902,0.0016090494,0.00021079583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004225891,0.001361577,0.0028373231,0.0036885606,0.00066349056,0.0020702465,0.0021615073,0.0014076466,0.0007134455],"category_scores_gemma":[0.009597234,0.00060377695,0.0027601006,0.00331847,0.00038781555,0.0022899897,0.0006906922,0.0016385901,0.0004501641],"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":[0.00047277976,0.0007828903,0.026316816,0.00031071928,0.0008950486,0.00028146795,0.00015877301,0.7175446,0.004357601,0.0029060375,0.0023035984,0.2436696],"study_design_scores_gemma":[0.0000076220754,0.000049003345,0.00073244714,0.000010298927,0.000031719606,0.000028638051,0.000014721542,0.9968105,0.00093534734,0.0011520943,0.0002187121,0.000008791759],"about_ca_topic_score_codex":0.008971529,"about_ca_topic_score_gemma":0.00977183,"teacher_disagreement_score":0.008971529,"about_ca_system_score_codex":0.0017147795,"about_ca_system_score_gemma":0.0014399545,"threshold_uncertainty_score":0.02234894},"labels":[],"label_agreement":null},{"id":"W2909295950","doi":"10.1007/978-3-030-04921-8_1","title":"A Survey of High Utility Itemset Mining","year":2019,"lang":"en","type":"book-chapter","venue":"Studies in big data","topic":"Data Mining Algorithms and Applications","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":"Université du Québec à Montréal","funders":"","keywords":"Data mining; Profit (economics); Computer science; Field (mathematics); Set (abstract data type); Function (biology); Mathematics","score_opus":0.3901859839747462,"score_gpt":0.37409378307595603,"score_spread":0.016092200898790154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2909295950","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012465836,0.6730349,0.28912187,0.0030713924,0.0011573557,0.0003085652,0.002434585,0.0012829399,0.017122526],"genre_scores_gemma":[0.07312845,0.5665956,0.3334829,0.0018685515,0.0028662106,0.00037637973,0.0067544268,0.0004052944,0.014522201],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972716,0.00059230835,0.00032498996,0.00046835322,0.0012265876,0.00011603753],"domain_scores_gemma":[0.99106103,0.006196414,0.00029742616,0.0007943279,0.0014658269,0.00018506362],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004129873,0.0012555753,0.002368677,0.010243457,0.001039017,0.0036928582,0.0030819043,0.0011344369,0.006384169],"category_scores_gemma":[0.012484642,0.0010555675,0.0013809202,0.032819986,0.0007666076,0.0068466724,0.001982549,0.001835467,0.0038360644],"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":[0.00011770753,0.00016754489,0.0035624483,0.0031895519,0.00009370726,0.00011468603,0.00007675908,0.003913052,0.00073838804,0.016663501,0.02431036,0.94705236],"study_design_scores_gemma":[0.00008929819,0.000708277,0.013580885,0.004963827,0.000487252,0.005809099,0.0006972464,0.15774448,0.008931868,0.20199215,0.6047949,0.00020077535],"about_ca_topic_score_codex":0.0013774708,"about_ca_topic_score_gemma":0.0018502929,"teacher_disagreement_score":0.010243457,"about_ca_system_score_codex":0.0010205207,"about_ca_system_score_gemma":0.001645245,"threshold_uncertainty_score":0.021841109},"labels":[],"label_agreement":null},{"id":"W2911444284","doi":"","title":"Revised Selected Papers of PAKDD 2013 International Workshops on Trends and Applications in Knowledge Discovery and Data Mining - Volume 7867","year":2013,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","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":"Simon Fraser University","funders":"","keywords":"Volume (thermodynamics); Data science; Knowledge extraction; Computer science; Library science; Data mining; Information retrieval","score_opus":0.020815114424589068,"score_gpt":0.28206156846229347,"score_spread":0.2612464540377044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2911444284","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026999805,0.05749892,0.020067401,0.063235044,0.7679495,0.00043723674,0.006983056,0.0012361283,0.079892725],"genre_scores_gemma":[0.010584423,0.042924307,0.010047907,0.007447895,0.16725448,0.00023820743,0.009935098,0.0015812754,0.7499864],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966397,0.00049356365,0.00029175685,0.00049865944,0.0018045908,0.0002716101],"domain_scores_gemma":[0.98144126,0.0019489244,0.0005534375,0.0009186719,0.013106421,0.0020312895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00440575,0.00205521,0.002098738,0.008605111,0.0016934848,0.006940761,0.0020936152,0.0017414487,0.17300706],"category_scores_gemma":[0.0111266235,0.0005711123,0.0017437612,0.006302429,0.0006627142,0.0034735892,0.002383602,0.0024399778,0.07582631],"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":[0.00014370614,0.0000443735,0.00013945875,0.0003126611,0.000022769924,0.00008284892,0.00003596544,0.0003313636,0.00052443665,0.0008085888,0.9415739,0.055980112],"study_design_scores_gemma":[0.000035154684,0.000078761346,0.0008604459,0.00024872803,0.00005720455,0.0001588841,0.00008119363,0.0006250142,0.000864912,0.0022410278,0.99472296,0.000025753097],"about_ca_topic_score_codex":0.0050223414,"about_ca_topic_score_gemma":0.011537184,"teacher_disagreement_score":0.17300706,"about_ca_system_score_codex":0.0034462283,"about_ca_system_score_gemma":0.0034015744,"threshold_uncertainty_score":0.5787662},"labels":[],"label_agreement":null},{"id":"W2911909514","doi":"","title":"Agent-based cooperative heterogeneous data mining","year":2012,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Data mining; Computer science; Cluster analysis; Association rule learning; Set (abstract data type); Knowledge extraction; Selection (genetic algorithm); Machine learning; Artificial intelligence","score_opus":0.08559574516430654,"score_gpt":0.3137981502942159,"score_spread":0.22820240512990939,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2911909514","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04678069,0.0003514385,0.9459644,0.00045974893,0.000059352944,0.00039484326,0.0001107219,0.0013007846,0.004577943],"genre_scores_gemma":[0.59494513,0.00035483835,0.3966697,0.00022199724,0.00005876398,0.0006625986,0.0006458039,0.000114105474,0.00632706],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977617,0.0007349133,0.00015420464,0.0004647123,0.0006768595,0.00020758223],"domain_scores_gemma":[0.9968861,0.0014812794,0.00023766946,0.0006675466,0.0005030532,0.00022435238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032513263,0.00084795384,0.0012982659,0.001103529,0.0014501936,0.0024435993,0.0034950366,0.0010741252,0.001616286],"category_scores_gemma":[0.0052828174,0.00057070615,0.0011319596,0.0013361253,0.0009010401,0.002651246,0.0035665042,0.0011512262,0.00055678684],"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":[0.00071855413,0.0010971078,0.008726051,0.00036868526,0.0003735816,0.00090165617,0.0014596825,0.6937441,0.012177276,0.061585207,0.0066155265,0.21223262],"study_design_scores_gemma":[0.00004963627,0.00006227462,0.00029312348,0.000008810992,0.000026288364,0.000056861278,0.00008251354,0.98317796,0.0017705658,0.009841164,0.004615798,0.0000149593],"about_ca_topic_score_codex":0.0062036994,"about_ca_topic_score_gemma":0.0044080727,"teacher_disagreement_score":0.0062036994,"about_ca_system_score_codex":0.001114099,"about_ca_system_score_gemma":0.0020522783,"threshold_uncertainty_score":0.017194867},"labels":[],"label_agreement":null},{"id":"W2912625373","doi":"","title":"Proceedings of the Canadian Society for computational studies of intelligence, 21st conference on Advances in artificial intelligence","year":2008,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","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":true,"ca_institutions":"Concordia University","funders":"","keywords":"Artificial intelligence; Applications of artificial intelligence; Computer science; Engineering ethics; Political science; Cognitive science; Data science; Engineering; Psychology","score_opus":0.11539963204231889,"score_gpt":0.33642471768254995,"score_spread":0.22102508564023104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912625373","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014014233,0.14279503,0.018844772,0.14099695,0.08964498,0.00040919316,0.014793823,0.0014930428,0.57700795],"genre_scores_gemma":[0.10367398,0.13113336,0.02366345,0.00481057,0.008131074,0.00031689953,0.016751392,0.0012029314,0.7103164],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979673,0.0002456724,0.00010391347,0.00015677827,0.0013068004,0.000219511],"domain_scores_gemma":[0.9890266,0.0012484099,0.00017428966,0.00091420196,0.007049108,0.0015875059],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038490267,0.0008516861,0.0018617655,0.0033636508,0.002971106,0.008694317,0.0016447674,0.0012270521,0.08223679],"category_scores_gemma":[0.010005755,0.00049904437,0.00072734826,0.0043826425,0.0031328143,0.0027866326,0.0024889044,0.0028540264,0.016843043],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009070778,0.0000626471,0.0014734339,0.00022869246,0.000043476804,0.000050914925,0.00015028716,0.000281171,0.00021555848,0.014539226,0.88872033,0.09414344],"study_design_scores_gemma":[0.000024479079,0.000012128105,0.0046242103,0.00024441467,0.00005574833,0.00006330375,0.00048250024,0.00087845407,0.00028078107,0.011407805,0.9818986,0.000027593846],"about_ca_topic_score_codex":0.53384936,"about_ca_topic_score_gemma":0.6901078,"teacher_disagreement_score":0.53384936,"about_ca_system_score_codex":0.010638058,"about_ca_system_score_gemma":0.0402662,"threshold_uncertainty_score":0.9377918},"labels":[],"label_agreement":null},{"id":"W2912803559","doi":"10.1109/bigdata.2018.8622063","title":"Towards a New Approach to Empower Periodic Pattern Mining for Massive Data using Map-Reduce","year":2018,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Timestamp; Data mining; Pruning; Time series; Suffix tree; Big data; Data structure; Machine learning","score_opus":0.1412377093483993,"score_gpt":0.35873013333668763,"score_spread":0.21749242398828833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912803559","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008313541,0.00045166328,0.9855488,0.00054622075,0.00010868323,0.00013189668,0.00031185473,0.0032620458,0.0013253111],"genre_scores_gemma":[0.07601646,0.0005045095,0.9194819,0.000221817,0.00013073806,0.00016973159,0.0012984844,0.00025743566,0.0019189037],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984366,0.00020845927,0.00011662133,0.00035009414,0.00077238545,0.00011579138],"domain_scores_gemma":[0.9986634,0.00022782497,0.00007886241,0.00049436965,0.00044483875,0.00009067646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013518281,0.0009046148,0.0013049745,0.002181238,0.0011520463,0.0019173922,0.0030969295,0.00065952976,0.0014809952],"category_scores_gemma":[0.0028638262,0.00069428165,0.0014954389,0.0031761879,0.0006549016,0.003094322,0.0022474087,0.0012627911,0.0012597032],"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":[0.0005200596,0.00087541604,0.007721472,0.0008569744,0.0005786947,0.0008898975,0.0008492117,0.07915943,0.036405515,0.059289824,0.03885254,0.7740008],"study_design_scores_gemma":[0.00007751728,0.00016765097,0.0018408389,0.00003127621,0.0001061918,0.0007164889,0.00035786798,0.85731775,0.01772491,0.07784791,0.04375326,0.0000584166],"about_ca_topic_score_codex":0.005407326,"about_ca_topic_score_gemma":0.0077241203,"teacher_disagreement_score":0.005407326,"about_ca_system_score_codex":0.00053894636,"about_ca_system_score_gemma":0.001943494,"threshold_uncertainty_score":0.010751724},"labels":[],"label_agreement":null},{"id":"W2913893210","doi":"","title":"Proceedings of the Data Mining and Intelligent Knowledge Management Workshop","year":2012,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Knowledge extraction; Computer science; Data science; Data management; Bridge (graph theory); Personal knowledge management; Software mining; Process (computing); Knowledge management; Data mining; Organizational learning; Software","score_opus":0.06899840394370782,"score_gpt":0.30636953917411125,"score_spread":0.23737113523040343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913893210","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019212283,0.049166415,0.15828602,0.35778862,0.106555924,0.0017593218,0.0071107405,0.0041421936,0.29597852],"genre_scores_gemma":[0.081293456,0.03210743,0.11519742,0.019441964,0.023477688,0.002375002,0.032002393,0.0022019206,0.69190276],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951002,0.0018532446,0.00038810552,0.00064302736,0.0015806679,0.00043469403],"domain_scores_gemma":[0.9901273,0.002735713,0.00024882847,0.0012388948,0.0030965179,0.0025527934],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015203341,0.0014023929,0.001603032,0.001679985,0.0025106322,0.010665902,0.0040912647,0.003942505,0.05280336],"category_scores_gemma":[0.011605346,0.00080360216,0.0017491508,0.0017443597,0.0013585318,0.007427033,0.005560269,0.0059544523,0.028217847],"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":[0.00027374888,0.00034868316,0.00048191182,0.00029083103,0.000051061223,0.00029182425,0.00072981924,0.00085698254,0.0011273474,0.012411677,0.8473726,0.13576351],"study_design_scores_gemma":[0.000043427284,0.000052976422,0.0006288674,0.00030694297,0.00003008915,0.0001426164,0.00062618515,0.0027669494,0.0007339349,0.01105701,0.9835829,0.000028191029],"about_ca_topic_score_codex":0.0039227135,"about_ca_topic_score_gemma":0.006277712,"teacher_disagreement_score":0.94719666,"about_ca_system_score_codex":0.0027760922,"about_ca_system_score_gemma":0.006037178,"threshold_uncertainty_score":0.17664486},"labels":[],"label_agreement":null},{"id":"W2913918884","doi":"10.1109/bigdata.2018.8622138","title":"Candidate List Maintenance in High Utility Sequential Pattern Mining","year":2018,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","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":"Research and Productivity Council; National Research Council Canada","funders":"","keywords":"Concatenation (mathematics); Computer science; Set (abstract data type); Data mining; Tree (set theory); Exploit; Descendant; Sequential Pattern Mining; Artificial intelligence; Mathematics; Arithmetic","score_opus":0.020663896430001747,"score_gpt":0.26834608569359003,"score_spread":0.2476821892635883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913918884","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.084654085,0.001370166,0.90686524,0.00044646763,0.000077297635,0.000507931,0.0012405617,0.0027911176,0.0020470372],"genre_scores_gemma":[0.45290777,0.0005028312,0.53908736,0.00025406425,0.00010815735,0.00051085994,0.0039320346,0.0002711386,0.0024258303],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9935557,0.00226135,0.0006428059,0.0009789605,0.0021228949,0.00043827045],"domain_scores_gemma":[0.97125536,0.019185374,0.0019095769,0.0039146827,0.003113695,0.0006212536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0072429636,0.001066156,0.0019461012,0.0053295204,0.0017466347,0.0027671524,0.0036474124,0.0014806209,0.0029528711],"category_scores_gemma":[0.038413122,0.00088693446,0.0013685973,0.0054993345,0.0011067137,0.0054640067,0.002417188,0.001789017,0.0014061602],"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":[0.0020467124,0.00083634176,0.028091148,0.001049601,0.00031074812,0.0013478969,0.00090635585,0.14604968,0.011069283,0.03594952,0.012691873,0.7596509],"study_design_scores_gemma":[0.00013133611,0.00065705023,0.0025548171,0.0001243189,0.000117448915,0.000851799,0.00031275538,0.9166511,0.011046023,0.060614686,0.0068866913,0.00005194734],"about_ca_topic_score_codex":0.0022735354,"about_ca_topic_score_gemma":0.004543385,"teacher_disagreement_score":0.0072429636,"about_ca_system_score_codex":0.0010211772,"about_ca_system_score_gemma":0.0030801378,"threshold_uncertainty_score":0.038304925},"labels":[],"label_agreement":null},{"id":"W2914604940","doi":"","title":"Proceedings of the 16th Canadian society for computational studies of intelligence conference on Advances in artificial intelligence","year":2003,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","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":true,"ca_institutions":"Université Laval; University of Guelph","funders":"","keywords":"Artificial intelligence; Computer science; Data science; Cognitive science; Psychology","score_opus":0.089113267059031,"score_gpt":0.33901707066820547,"score_spread":0.24990380360917447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914604940","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022760518,0.117224544,0.028549472,0.1580104,0.13700098,0.00044441738,0.011253927,0.0017770524,0.5229787],"genre_scores_gemma":[0.11436299,0.09823911,0.025944898,0.006466069,0.010553026,0.00038295338,0.015782433,0.001450989,0.7268174],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982278,0.0002497863,0.00009537025,0.00012916361,0.0010926983,0.00020530155],"domain_scores_gemma":[0.98918974,0.0013782011,0.00019982578,0.0010614753,0.0061196215,0.0020510885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041142525,0.00079789234,0.0022147263,0.002805276,0.0028598174,0.009416623,0.0016157612,0.0012574549,0.09456912],"category_scores_gemma":[0.010076213,0.00044931544,0.00072527176,0.0034037705,0.0023391808,0.0033352931,0.0030785513,0.0035180934,0.020031447],"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":[0.0001708943,0.00012276335,0.0019002438,0.00023301877,0.00005424619,0.00006294246,0.00023160707,0.0002681449,0.00034295899,0.015911235,0.8679214,0.112780534],"study_design_scores_gemma":[0.000029199287,0.000018283517,0.0048749954,0.00022523635,0.000078638936,0.00008309659,0.00051101745,0.00087493093,0.00044515764,0.014601637,0.978226,0.000031776097],"about_ca_topic_score_codex":0.16311382,"about_ca_topic_score_gemma":0.32903084,"teacher_disagreement_score":0.16311382,"about_ca_system_score_codex":0.006949769,"about_ca_system_score_gemma":0.020346396,"threshold_uncertainty_score":0.32432878},"labels":[],"label_agreement":null},{"id":"W2914818188","doi":"10.5555/2872518.3251212","title":"Session details: BigScholar 2015","year":2015,"lang":"en","type":"article","venue":"The Web Conference","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Session (web analytics); Presentation (obstetrics); Library science; Inclusion (mineral); Pleasure; World Wide Web; Big data; Computer science; State (computer science); Political science; Sociology; Psychology; Medicine; Social science","score_opus":0.07882610516053719,"score_gpt":0.3063348120394692,"score_spread":0.22750870687893204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914818188","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023459299,0.006989064,0.0060418756,0.08326724,0.16030487,0.0030865031,0.07836617,0.0103348885,0.64926344],"genre_scores_gemma":[0.008421472,0.0028010467,0.0026072857,0.016140295,0.02925771,0.0019497197,0.038051855,0.00456547,0.8962052],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974285,0.00043398555,0.00014725339,0.0005102028,0.0010016506,0.00047851587],"domain_scores_gemma":[0.9894331,0.0009291503,0.000414552,0.00091343495,0.0025936347,0.0057160812],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010629769,0.0013573355,0.0014914697,0.0022916629,0.0040322863,0.011047689,0.0026581113,0.0042430656,0.6834679],"category_scores_gemma":[0.009753902,0.0006086778,0.0015935836,0.0019009355,0.0007448672,0.0048257196,0.006961903,0.004147065,0.54891884],"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":[0.00005615574,0.000014780801,0.000055035936,0.00004644862,0.0000025002307,0.000010874561,0.000015542351,0.0000126683,0.00007413619,0.0005859425,0.994054,0.005071981],"study_design_scores_gemma":[0.000024359899,0.00001422781,0.00052839017,0.000060228744,0.0000017859744,0.00000847863,0.000036871417,0.000029423072,0.00006503231,0.00050584396,0.99871504,0.000010330479],"about_ca_topic_score_codex":0.0039079553,"about_ca_topic_score_gemma":0.010771593,"teacher_disagreement_score":0.6834679,"about_ca_system_score_codex":0.0028006686,"about_ca_system_score_gemma":0.0049094246,"threshold_uncertainty_score":0.45149457},"labels":[],"label_agreement":null},{"id":"W2915249159","doi":"10.1051/matecconf/201927004017","title":"Association rules and regression linear model of the groundwater population by the evaluation of uranium","year":2019,"lang":"en","type":"article","venue":"MATEC Web of Conferences","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Alkalinity; Linear regression; Uranium; Regression analysis; Variables; Population; Groundwater; Variable (mathematics); Statistics; Regression; Mathematics; Linear model; Chemistry; Geology; Demography; Materials science; Metallurgy","score_opus":0.036181563277053894,"score_gpt":0.28207646823584975,"score_spread":0.24589490495879585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2915249159","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.301284,0.0017413128,0.67983663,0.0020188421,0.0004287616,0.00048777348,0.007582071,0.0029208525,0.0036997478],"genre_scores_gemma":[0.8582019,0.00091754954,0.118578106,0.00025202983,0.0002425847,0.0010972063,0.008622993,0.00017330184,0.011914344],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9936367,0.002435645,0.0005169498,0.0020913002,0.00082820066,0.0004912541],"domain_scores_gemma":[0.9829161,0.0127925165,0.0013592812,0.0008660498,0.0018216361,0.0002443331],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008396021,0.0016236192,0.0017386904,0.0037715305,0.00067749765,0.0027909493,0.002311841,0.0015137518,0.00468266],"category_scores_gemma":[0.018785238,0.0008025878,0.0031430165,0.0036823696,0.0006791258,0.0019953924,0.0010002523,0.002836198,0.002842937],"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":[0.00075925153,0.00075992406,0.09827758,0.00025080104,0.0011899371,0.0007741736,0.00046500543,0.71382934,0.00089453545,0.009783765,0.0069063893,0.16610926],"study_design_scores_gemma":[0.000017068174,0.0000683776,0.0035900653,0.000023604249,0.0000809977,0.000102656435,0.000049081744,0.9909276,0.00020764401,0.004008729,0.0009051817,0.000019039253],"about_ca_topic_score_codex":0.018872084,"about_ca_topic_score_gemma":0.011639915,"teacher_disagreement_score":0.018872084,"about_ca_system_score_codex":0.0013298899,"about_ca_system_score_gemma":0.0016601857,"threshold_uncertainty_score":0.044402897},"labels":[],"label_agreement":null},{"id":"W2919696585","doi":"","title":"The 3rd international workshop on dew computing.","year":2018,"lang":"en","type":"article","venue":"Conference of the Centre for Advanced Studies on Collaborative Research","topic":"Data Mining Algorithms 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 Prince Edward Island","funders":"","keywords":"Dew; Computer science; Meteorology; Physics","score_opus":0.14482678390761738,"score_gpt":0.4508430175694532,"score_spread":0.30601623366183583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2919696585","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02032814,0.05891904,0.6589293,0.027166035,0.0311819,0.0009873381,0.0076396386,0.011638786,0.18320984],"genre_scores_gemma":[0.094120786,0.034658868,0.29412428,0.005798154,0.004414947,0.0008923184,0.031749655,0.0067037838,0.5275372],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974554,0.000601896,0.00019769909,0.0005384222,0.00085009704,0.00035648912],"domain_scores_gemma":[0.9961383,0.00075701036,0.000072033865,0.001501196,0.0009458561,0.0005856209],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040932857,0.0015360365,0.0015219583,0.0025607662,0.0013675108,0.005219539,0.0032129865,0.0019601842,0.073829874],"category_scores_gemma":[0.008399781,0.0008492444,0.0011558969,0.0035540995,0.00112656,0.009626066,0.0045759073,0.003144302,0.035771605],"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":[0.00040060907,0.00025881687,0.0010193421,0.0003386935,0.00006450063,0.00014299613,0.00029873525,0.0011627877,0.0032417465,0.032366727,0.47215882,0.4885462],"study_design_scores_gemma":[0.000027229804,0.000048965903,0.00094218017,0.00022799845,0.000023544048,0.00025174627,0.00027672137,0.0061000544,0.0027849982,0.026394363,0.9628944,0.000027729631],"about_ca_topic_score_codex":0.004016507,"about_ca_topic_score_gemma":0.00766992,"teacher_disagreement_score":0.073829874,"about_ca_system_score_codex":0.0012622115,"about_ca_system_score_gemma":0.0021081434,"threshold_uncertainty_score":0.24698555},"labels":[],"label_agreement":null},{"id":"W2928318746","doi":"","title":"Big Data Mining to Construct Truck Tours","year":2018,"lang":"en","type":"article","venue":"Scholarship at UWindsor (University of Windsor)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Construct (python library); Truck; Big data; Computer science; Data mining; Engineering","score_opus":0.07045823812558576,"score_gpt":0.26418543765673613,"score_spread":0.19372719953115036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2928318746","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20181116,0.004730137,0.55953133,0.006125352,0.00086583867,0.0016266921,0.2006116,0.011287729,0.013410206],"genre_scores_gemma":[0.40294677,0.0019928266,0.4366038,0.00046287483,0.00018249269,0.00091910805,0.15380958,0.00030040552,0.0027821215],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984212,0.00031161867,0.0002849702,0.00042582618,0.00042865018,0.00012779635],"domain_scores_gemma":[0.99730957,0.0009877346,0.00033075377,0.00066501973,0.00056062,0.0001462887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013281817,0.0013011805,0.00096763845,0.0058093662,0.0009429052,0.0020800924,0.0020834804,0.0010360763,0.0020735147],"category_scores_gemma":[0.0052909167,0.00058808277,0.002267445,0.008411844,0.0005531431,0.0023065382,0.0013139079,0.0013960573,0.0014794476],"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":[0.00064562046,0.0009953887,0.07708841,0.0028149018,0.0010629373,0.001592659,0.0010967528,0.28361154,0.0045209336,0.018246079,0.08558851,0.5227363],"study_design_scores_gemma":[0.000060256054,0.00016768022,0.021555332,0.0003118074,0.00014178464,0.00038187028,0.0020907593,0.8743301,0.0043861363,0.04123189,0.05526208,0.000080327496],"about_ca_topic_score_codex":0.011832886,"about_ca_topic_score_gemma":0.02146303,"teacher_disagreement_score":0.011832886,"about_ca_system_score_codex":0.0012076499,"about_ca_system_score_gemma":0.0015027333,"threshold_uncertainty_score":0.02352804},"labels":[],"label_agreement":null},{"id":"W2937809414","doi":"","title":"Efficient frequent pattern mining from big data and its applications","year":2014,"lang":"en","type":"dissertation","venue":"Mspace (University of Manitoba)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Manitoba","keywords":"Big data; Data mining; Data science; Computer science; Information retrieval","score_opus":0.032602469251538285,"score_gpt":0.2282935583909373,"score_spread":0.195691089139399,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2937809414","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020159692,0.0039816243,0.9680532,0.0018143355,0.00015917965,0.00019143721,0.00083458156,0.0013869782,0.0034189853],"genre_scores_gemma":[0.16047725,0.004262359,0.82966816,0.0002517094,0.00021249062,0.00030177945,0.0025197538,0.00012311075,0.0021833912],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973941,0.0006409991,0.00027491536,0.0004766916,0.0010959563,0.000117304495],"domain_scores_gemma":[0.995214,0.0025532173,0.00031708044,0.00070552615,0.0010812905,0.00012891901],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020108293,0.0008346245,0.0012024341,0.003356486,0.0007619478,0.002077386,0.0015217462,0.0012178968,0.002114854],"category_scores_gemma":[0.011331396,0.0006712951,0.0010173654,0.0057915254,0.00047039735,0.0031211728,0.0014983638,0.0012410566,0.0013468856],"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":[0.00021656553,0.00026897274,0.0056236372,0.00069086713,0.00016636374,0.00061063946,0.00025268013,0.076381825,0.007831978,0.041010592,0.016501034,0.8504448],"study_design_scores_gemma":[0.00005339303,0.00011008134,0.0022485533,0.000137912,0.00005238799,0.00090648385,0.00023423003,0.8528279,0.009064908,0.110728405,0.023598036,0.000037708756],"about_ca_topic_score_codex":0.0009883313,"about_ca_topic_score_gemma":0.0012156623,"teacher_disagreement_score":0.003356486,"about_ca_system_score_codex":0.0006167326,"about_ca_system_score_gemma":0.0011444918,"threshold_uncertainty_score":0.010634363},"labels":[],"label_agreement":null},{"id":"W2943003953","doi":"10.1007/s11280-019-00686-w","title":"Mining top-k sequential patterns in transaction database graphs","year":2019,"lang":"en","type":"article","venue":"World Wide Web","topic":"Data Mining Algorithms and Applications","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":"Simon Fraser University","funders":"National Natural Science Foundation of China; Ministry of Science and Technology","keywords":"Computer science; Database transaction; Graph database; Database; Graph; Sequence (biology); Sequence database; Vertex (graph theory); Transaction data; Theoretical computer science; Algorithm","score_opus":0.016127278338139275,"score_gpt":0.25254544302669313,"score_spread":0.23641816468855387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2943003953","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65377176,0.003526662,0.32003194,0.0016728415,0.00024668907,0.00043897153,0.013399549,0.0028083287,0.0041033155],"genre_scores_gemma":[0.86459863,0.0010136479,0.120198846,0.00017775041,0.00009464249,0.00014416799,0.011309035,0.00015271617,0.0023105452],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987198,0.00013936749,0.00017392036,0.0003697177,0.0004448418,0.0001523775],"domain_scores_gemma":[0.99419206,0.0030671665,0.0007777713,0.0006806861,0.0009269119,0.0003553462],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006232623,0.0006552643,0.00094578345,0.005625619,0.00093376165,0.0019869013,0.0012567336,0.0009747898,0.0014151967],"category_scores_gemma":[0.0073003685,0.00057816337,0.0012273975,0.00519665,0.00046852138,0.0029284342,0.0007086911,0.001077943,0.0006839794],"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":[0.0015082898,0.0011165247,0.24246098,0.0021502948,0.0012914257,0.005184094,0.0011238741,0.082121275,0.02453131,0.022756824,0.027074402,0.58868074],"study_design_scores_gemma":[0.00011520528,0.00042579536,0.040905997,0.00024294292,0.0008907516,0.00471302,0.001516084,0.77948165,0.013038991,0.1440035,0.014595837,0.000070227536],"about_ca_topic_score_codex":0.0043133646,"about_ca_topic_score_gemma":0.010414563,"teacher_disagreement_score":0.005625619,"about_ca_system_score_codex":0.00059080444,"about_ca_system_score_gemma":0.0012348883,"threshold_uncertainty_score":0.008576512},"labels":[],"label_agreement":null},{"id":"W2944906040","doi":"10.1007/978-3-030-19063-7_83","title":"Discovering Correlation in Frequent Subgraphs","year":2019,"lang":"en","type":"book-chapter","venue":"Advances in intelligent systems and computing","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":"University of Manitoba","funders":"","keywords":"Computer science; Correlation; Graph; Knowledge graph; Theoretical computer science; Data science; Data mining; Information retrieval; Mathematics","score_opus":0.014246519405594817,"score_gpt":0.2557647048022925,"score_spread":0.2415181853966977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2944906040","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2988007,0.004480845,0.6722179,0.0011682508,0.00026800312,0.00043132177,0.008790463,0.00393878,0.009903655],"genre_scores_gemma":[0.5966881,0.002272756,0.37140325,0.00029076825,0.0003218588,0.00032128408,0.021454185,0.00040291558,0.0068448535],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99892104,0.00019028164,0.00010163657,0.00032108024,0.00036924542,0.000096634234],"domain_scores_gemma":[0.9970463,0.0017076638,0.00037169323,0.00042228703,0.00033829483,0.000113887305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005992822,0.00065367814,0.0008742911,0.0055712587,0.00071593624,0.0013688945,0.0009427584,0.0006949761,0.0027621344],"category_scores_gemma":[0.005924461,0.00063992897,0.0015571149,0.0050109522,0.0004401443,0.0020212268,0.0011513957,0.000812271,0.0011169108],"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":[0.0007066124,0.0004337813,0.058339935,0.0012881284,0.0009545424,0.0027894143,0.00082264416,0.02742065,0.02884399,0.051853422,0.032636594,0.79391026],"study_design_scores_gemma":[0.000109633824,0.0004212935,0.038537405,0.0003629111,0.00079519383,0.007406151,0.0007340863,0.60243523,0.020861091,0.2803504,0.047893245,0.00009341311],"about_ca_topic_score_codex":0.0014352027,"about_ca_topic_score_gemma":0.003225724,"teacher_disagreement_score":0.0055712587,"about_ca_system_score_codex":0.00046269665,"about_ca_system_score_gemma":0.000613819,"threshold_uncertainty_score":0.00924027},"labels":[],"label_agreement":null},{"id":"W2947038666","doi":"10.5121/csit.2019.90607","title":"NUCLEAR: AN EFFICIENT METHOD FOR MINING FREQUENT ITEMSETS BASED ON KERNELS AND EXTENDABLE SETS","year":2019,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Data mining","score_opus":0.019468588321122044,"score_gpt":0.30405724094800285,"score_spread":0.2845886526268808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947038666","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015739674,0.00031757785,0.9801207,0.000058018406,0.00003485082,0.00017797403,0.00043571068,0.0025307504,0.0005848006],"genre_scores_gemma":[0.14936481,0.00038255652,0.8456118,0.00006776716,0.00005665021,0.0003831323,0.0026731533,0.00015089587,0.0013092331],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983059,0.00029128353,0.000272073,0.00035197847,0.00067597145,0.000102813065],"domain_scores_gemma":[0.997785,0.0009783403,0.0002537012,0.00036949688,0.0005238299,0.000089666915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014376972,0.00092050654,0.0011864541,0.004943304,0.00068857067,0.0011281951,0.0014549909,0.00063044444,0.0018644328],"category_scores_gemma":[0.005871052,0.00041659398,0.0012775115,0.0035947037,0.00053285493,0.0024653794,0.0011658698,0.00079038664,0.0010719422],"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":[0.00039691819,0.00022100727,0.00659313,0.0005252851,0.00026096785,0.0005567303,0.00039369956,0.0420201,0.014206516,0.01520584,0.006435811,0.91318405],"study_design_scores_gemma":[0.00009070216,0.00027415765,0.004065875,0.00007845846,0.00014215843,0.0014472073,0.00024422834,0.93388456,0.011769916,0.03418443,0.013725673,0.00009267812],"about_ca_topic_score_codex":0.0021524122,"about_ca_topic_score_gemma":0.0021505705,"teacher_disagreement_score":0.004943304,"about_ca_system_score_codex":0.00045747485,"about_ca_system_score_gemma":0.0013058162,"threshold_uncertainty_score":0.0076033473},"labels":[],"label_agreement":null},{"id":"W2947193716","doi":"","title":"Flexible Approach for Computer-Assisted Reading and Analysis of Texts.","year":2019,"lang":"en","type":"article","venue":"The Florida AI Research Society","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 Trois-Rivières","funders":"","keywords":"Computer science; Reading (process); Multimedia; Linguistics","score_opus":0.07174660004505412,"score_gpt":0.3686208834862793,"score_spread":0.2968742834412252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947193716","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0055429735,0.0004608248,0.9532078,0.0004326531,0.0001092589,0.00063377107,0.003894205,0.030983318,0.0047351606],"genre_scores_gemma":[0.0467899,0.00021894604,0.93972147,0.00021295543,0.000057099314,0.0006692057,0.0048691253,0.00095330336,0.0065079927],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9955285,0.0014025503,0.00039719883,0.0011833364,0.0013156002,0.0001727019],"domain_scores_gemma":[0.9897412,0.004796079,0.0004024685,0.00270114,0.0018600781,0.0004990173],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032408717,0.0013033492,0.0011679044,0.0064787786,0.0015171277,0.0038814554,0.0033216544,0.001889802,0.018531285],"category_scores_gemma":[0.017148895,0.0007334041,0.0013017495,0.004392751,0.00095881685,0.0037596477,0.005071722,0.0020135583,0.015428926],"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":[0.00045125975,0.00034068263,0.0015921302,0.0005400593,0.00018350164,0.00033333944,0.0011957017,0.0019401879,0.02933958,0.008787154,0.037886366,0.91741],"study_design_scores_gemma":[0.00026736877,0.0004644509,0.011917135,0.0005145432,0.0003470627,0.0024867854,0.0035215972,0.39520296,0.094614126,0.14324017,0.3470477,0.00037612848],"about_ca_topic_score_codex":0.0040678014,"about_ca_topic_score_gemma":0.012751255,"teacher_disagreement_score":0.018531285,"about_ca_system_score_codex":0.00090011256,"about_ca_system_score_gemma":0.002155008,"threshold_uncertainty_score":0.06199336},"labels":[],"label_agreement":null},{"id":"W2947460150","doi":"10.1109/access.2019.2919524","title":"Incremental Mining of High Utility Patterns in One Phase by Absence and Legacy-Based Pruning","year":2019,"lang":"en","type":"article","venue":"IEEE Access","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Science Foundation of Zhejiang Province; National Natural Science Foundation of China; Zhejiang Gongshang University","keywords":"Pruning; Computer science; Scalability; Relevance (law); Data mining; Algorithm; State (computer science); Machine learning; Artificial intelligence; Theoretical computer science; Database","score_opus":0.037593138486086135,"score_gpt":0.31214281591858967,"score_spread":0.2745496774325035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947460150","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12147019,0.0011734494,0.87063485,0.0005194305,0.000113358714,0.00039900895,0.00038630568,0.002201578,0.0031017973],"genre_scores_gemma":[0.38350138,0.0004643923,0.60887724,0.00036423828,0.0001022628,0.00034047232,0.0021580742,0.00018781172,0.0040042014],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969208,0.00042875242,0.00032602524,0.00066255033,0.0013607077,0.00030121484],"domain_scores_gemma":[0.994155,0.0020343976,0.0004893835,0.0014374293,0.001606092,0.00027781085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022062715,0.00076273707,0.0015489189,0.0023295835,0.001223778,0.002035955,0.0043177865,0.0011911943,0.0010989839],"category_scores_gemma":[0.011520698,0.0006466595,0.0012851495,0.0028673646,0.0006738886,0.0034283348,0.0027237907,0.0012810609,0.00060029514],"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":[0.0006285304,0.00073879835,0.022394268,0.00036146358,0.0001965995,0.0010898113,0.0005052641,0.03532092,0.022903262,0.0136215575,0.008062528,0.8941769],"study_design_scores_gemma":[0.00015266132,0.0004033481,0.007768132,0.00008162625,0.00030275958,0.0024152123,0.00029918837,0.931127,0.019954488,0.024081325,0.013350005,0.00006424116],"about_ca_topic_score_codex":0.0033298826,"about_ca_topic_score_gemma":0.007616855,"teacher_disagreement_score":0.0043177865,"about_ca_system_score_codex":0.0005806498,"about_ca_system_score_gemma":0.0021776108,"threshold_uncertainty_score":0.011667967},"labels":[],"label_agreement":null},{"id":"W2954876873","doi":"10.1109/ccgrid.2019.00075","title":"Pattern Mining from big IoT Data with fog Computing: Models, Issues, and Research Perspectives","year":2019,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Big data; SPARK (programming language); Computer science; Data science; Variety (cybernetics); Cloud computing; Internet of Things; Knowledge extraction; Data mining; Class (philosophy); The Internet; Wearable computer; Tree (set theory); World Wide Web; Artificial intelligence","score_opus":0.13136048742919895,"score_gpt":0.3559637073181163,"score_spread":0.22460321988891732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954876873","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03150074,0.22832622,0.65106016,0.049628787,0.002140176,0.00044514672,0.0005038569,0.00054103456,0.035853848],"genre_scores_gemma":[0.4280474,0.26658124,0.2867902,0.0039660046,0.005514434,0.0005589251,0.000788536,0.00017366612,0.007579698],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987858,0.00037392165,0.00007510982,0.00022289755,0.00041292526,0.00012940934],"domain_scores_gemma":[0.9944616,0.0037338033,0.00020986235,0.0004372051,0.00093090656,0.00022653866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004039806,0.00094782846,0.0014330177,0.0019940939,0.00095234875,0.0058865636,0.003191028,0.00225871,0.0012684931],"category_scores_gemma":[0.008543276,0.0008455125,0.0011646553,0.0050408393,0.002880929,0.01053492,0.0016217892,0.0033025981,0.0005509418],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001385448,0.00049296184,0.009676969,0.0013282624,0.00024044614,0.00061670877,0.0006461062,0.13793321,0.0006247691,0.5588063,0.026378918,0.26311678],"study_design_scores_gemma":[0.000015627122,0.000065520144,0.0012833268,0.00035993216,0.00003202877,0.00032266293,0.00036460024,0.6079246,0.0003703461,0.36353454,0.02568411,0.000042781146],"about_ca_topic_score_codex":0.009031897,"about_ca_topic_score_gemma":0.0060213297,"teacher_disagreement_score":0.009031897,"about_ca_system_score_codex":0.001735821,"about_ca_system_score_gemma":0.0019932503,"threshold_uncertainty_score":0.021364808},"labels":[],"label_agreement":null},{"id":"W2959535807","doi":"10.18280/ts.360103","title":"A Novel Frequent Pattern Mining Algorithm for Real-time Radar Data Stream","year":2019,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Radar; Computer science; Data stream; Data mining; Algorithm; Artificial intelligence; Geology; Telecommunications","score_opus":0.034724476853561254,"score_gpt":0.2690146809079006,"score_spread":0.23429020405433934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2959535807","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0075110006,0.00035550783,0.9903853,0.00015313893,0.00009356946,0.000077323646,0.00022630676,0.00081381365,0.0003840272],"genre_scores_gemma":[0.06408026,0.00046706272,0.93288726,0.00012498608,0.00011234794,0.00019214282,0.00093904114,0.000082615246,0.0011142853],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981166,0.00023322963,0.000303113,0.000508191,0.00072563044,0.00011322919],"domain_scores_gemma":[0.997633,0.00077902427,0.00026866686,0.00032450986,0.00091143243,0.0000834087],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015311927,0.00085435377,0.0013707099,0.0035352695,0.0008040166,0.0014421997,0.0020049927,0.0011468383,0.0016108113],"category_scores_gemma":[0.0057525127,0.00043979785,0.0010924018,0.0041356585,0.0003750932,0.0037620133,0.0008482537,0.0014228481,0.0012336269],"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":[0.00040499622,0.00025237104,0.004361827,0.00034873773,0.00020931578,0.00048088364,0.00017520957,0.03728533,0.015093606,0.01078028,0.007613646,0.9229939],"study_design_scores_gemma":[0.000103446735,0.00021410716,0.001517933,0.00005216019,0.000085872554,0.0017692047,0.00008224353,0.95020735,0.012314162,0.016435105,0.017167766,0.00005065935],"about_ca_topic_score_codex":0.0014102955,"about_ca_topic_score_gemma":0.0013263425,"teacher_disagreement_score":0.0035352695,"about_ca_system_score_codex":0.0005237929,"about_ca_system_score_gemma":0.0011576137,"threshold_uncertainty_score":0.008097827},"labels":[],"label_agreement":null},{"id":"W2963677182","doi":"10.1609/aaai.v33i01.33011495","title":"Constraint-Based Sequential Pattern Mining with Decision Diagrams","year":2019,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"Office of Naval Research","keywords":"Constraint (computer-aided design); Computer science; Data mining; Sequential Pattern Mining; Representation (politics); Projection (relational algebra); Scalability; Hybrid algorithm (constraint satisfaction); Artificial intelligence; Constraint logic programming; Constraint satisfaction; Algorithm; Mathematics; Database","score_opus":0.013246463306795884,"score_gpt":0.2416520870841558,"score_spread":0.22840562377735993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963677182","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0073816753,0.0001441453,0.9903072,0.00011368705,0.000014358505,0.00016215057,0.0004935398,0.0010242481,0.00035889624],"genre_scores_gemma":[0.10345646,0.00021156299,0.89413285,0.00007056631,0.000016330456,0.00029080952,0.001297376,0.0000814583,0.00044256318],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968125,0.0011155088,0.0003214158,0.000553584,0.001072926,0.00012404926],"domain_scores_gemma":[0.98652923,0.010565961,0.0007003953,0.0008508602,0.0011657963,0.00018770587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025127383,0.00095684896,0.0010825797,0.0021567303,0.00055980135,0.0017331146,0.0015995931,0.0007434485,0.0029557997],"category_scores_gemma":[0.017999884,0.00057870283,0.0013493121,0.0030979542,0.00065490097,0.0024391226,0.0013996096,0.0013078419,0.0005711605],"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":[0.0006741846,0.00028305786,0.0074346974,0.0010694453,0.0003451545,0.00054511,0.0002787146,0.4037265,0.01079306,0.054977037,0.0055709416,0.5143021],"study_design_scores_gemma":[0.00005776769,0.00007032671,0.00030360874,0.00002889113,0.000039778002,0.00020524143,0.000040204388,0.9573039,0.0059199966,0.032365136,0.0036469712,0.000018270077],"about_ca_topic_score_codex":0.0037512274,"about_ca_topic_score_gemma":0.0046485728,"teacher_disagreement_score":0.0037512274,"about_ca_system_score_codex":0.000847775,"about_ca_system_score_gemma":0.0029979923,"threshold_uncertainty_score":0.013288796},"labels":[],"label_agreement":null},{"id":"W2963702719","doi":"10.1109/icde.2018.00029","title":"Mining Density Contrast Subgraphs","year":2018,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Graph; Computer science; Induced subgraph isomorphism problem; Distance-hereditary graph; Contrast (vision); Theoretical computer science; Data mining; Mathematics; Combinatorics; Line graph; Artificial intelligence; Graph power; Voltage graph","score_opus":0.017133079929009896,"score_gpt":0.25249793934258546,"score_spread":0.23536485941357557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963702719","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28591734,0.00081311027,0.7048625,0.00070283154,0.000044156885,0.00037825006,0.0023030108,0.0013867258,0.003592154],"genre_scores_gemma":[0.71505284,0.0003293087,0.27665246,0.00024392807,0.000067244066,0.00023890892,0.005768307,0.00012504026,0.0015218849],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984332,0.0003013716,0.00010862121,0.00053407694,0.0004941181,0.00012864664],"domain_scores_gemma":[0.9935702,0.0038616944,0.0009503356,0.00073705387,0.00069848174,0.0001822373],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083600945,0.0008675638,0.0010414455,0.0036736047,0.00088834774,0.0009837886,0.001322254,0.0011239017,0.00094783615],"category_scores_gemma":[0.009601359,0.0005889337,0.0010280615,0.0028540755,0.000777496,0.0022050857,0.0015567992,0.00076750043,0.00031116357],"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":[0.0007364593,0.0005851112,0.11190426,0.001300874,0.0007094209,0.0023927798,0.0011251243,0.21070936,0.043089654,0.09392952,0.022028971,0.51148844],"study_design_scores_gemma":[0.00006607967,0.000103398495,0.013171182,0.000060819395,0.00015415235,0.0017589404,0.00042014234,0.8194689,0.017211344,0.13758656,0.009962369,0.000036189238],"about_ca_topic_score_codex":0.0026239257,"about_ca_topic_score_gemma":0.0046424256,"teacher_disagreement_score":0.0036736047,"about_ca_system_score_codex":0.0007579012,"about_ca_system_score_gemma":0.0008656836,"threshold_uncertainty_score":0.0054990053},"labels":[],"label_agreement":null},{"id":"W2965684979","doi":"10.14778/3339490.3339492","title":"Finding theme communities from database networks","year":2019,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Theme (computing); Computer science; Scalability; Database; Tree (set theory); World Wide Web; Mathematics","score_opus":0.0209118966385737,"score_gpt":0.2322965180983817,"score_spread":0.211384621459808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2965684979","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20755139,0.0024862213,0.77524686,0.0011017679,0.00007053184,0.0005424679,0.0054738075,0.001783319,0.0057436908],"genre_scores_gemma":[0.49656573,0.0013169067,0.48753652,0.0002533591,0.000103381986,0.0004305969,0.010268036,0.00022585751,0.0032996219],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846905,0.00027293377,0.00009698834,0.0004942977,0.00047231285,0.000194379],"domain_scores_gemma":[0.99560106,0.0019415978,0.0005544047,0.000510131,0.0010787349,0.0003141409],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010758865,0.0007888487,0.00087080256,0.0064665647,0.0018378726,0.0023392576,0.0016795531,0.0011813118,0.0014100309],"category_scores_gemma":[0.010287098,0.00069517415,0.0010464002,0.005295313,0.0006192045,0.0043598125,0.0027564373,0.0009161823,0.00060143654],"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":[0.0007978403,0.0004441288,0.06862874,0.0018519835,0.00054348685,0.0028856485,0.004873841,0.16679767,0.03682191,0.077835426,0.045150157,0.5933691],"study_design_scores_gemma":[0.000047436588,0.000094239105,0.005899583,0.0001308876,0.000105448824,0.0014739529,0.002282386,0.8278164,0.0066270595,0.1352973,0.020183641,0.000041604817],"about_ca_topic_score_codex":0.0070493855,"about_ca_topic_score_gemma":0.012798343,"teacher_disagreement_score":0.0070493855,"about_ca_system_score_codex":0.0009137038,"about_ca_system_score_gemma":0.0012176259,"threshold_uncertainty_score":0.014016688},"labels":[],"label_agreement":null},{"id":"W2967873511","doi":"10.1007/978-3-030-27520-4_5","title":"Mining Sequential Patterns of Historical Purchases for E-commerce Recommendation","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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 Windsor","funders":"","keywords":"Computer science; Collaborative filtering; Recommender system; Similarity (geometry); Data mining; Sequential Pattern Mining; Cluster analysis; Matrix (chemical analysis); Information retrieval; Artificial intelligence; Machine learning","score_opus":0.041237137699025414,"score_gpt":0.2829753968672345,"score_spread":0.24173825916820907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2967873511","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84639335,0.009014652,0.102632016,0.0010248612,0.0005180687,0.00031428013,0.028645745,0.0019759089,0.009481021],"genre_scores_gemma":[0.8910788,0.0022937146,0.068453446,0.00016169854,0.00037882346,0.00015075484,0.028417168,0.00008509294,0.008980504],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995498,0.0000453128,0.00006501359,0.0001359189,0.00014362924,0.000060275124],"domain_scores_gemma":[0.99906,0.0004246935,0.00014041597,0.0001042032,0.00019024787,0.00008050049],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035450648,0.0007721536,0.0008046673,0.0059014945,0.00045815847,0.0008652564,0.0008612354,0.0007741658,0.004087299],"category_scores_gemma":[0.0018858506,0.0003419358,0.0010135054,0.0067127086,0.00015753838,0.001277245,0.00036141378,0.0006210574,0.0027423147],"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":[0.0011196272,0.001508692,0.28974542,0.0006908485,0.000910844,0.0014328056,0.00019446373,0.012684948,0.012477486,0.0022582174,0.031896587,0.64508003],"study_design_scores_gemma":[0.00013196806,0.00079367415,0.24105954,0.00028995992,0.0009634441,0.0035042402,0.0007523004,0.70654064,0.011908054,0.011528064,0.022418763,0.0001093702],"about_ca_topic_score_codex":0.006637993,"about_ca_topic_score_gemma":0.019657444,"teacher_disagreement_score":0.006637993,"about_ca_system_score_codex":0.00033023648,"about_ca_system_score_gemma":0.0005338518,"threshold_uncertainty_score":0.013673365},"labels":[],"label_agreement":null},{"id":"W2969853078","doi":"10.1007/s11761-019-00272-y","title":"Data mining service recommendation based on dataset features","year":2019,"lang":"en","type":"article","venue":"Service Oriented Computing and Applications","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":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Data mining; Service (business); Data science; Information retrieval; Business","score_opus":0.02455588047636383,"score_gpt":0.29508046017873074,"score_spread":0.27052457970236693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969853078","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8328148,0.0036804727,0.11027769,0.0020753986,0.0006224676,0.00083402154,0.035677765,0.0047840537,0.009233376],"genre_scores_gemma":[0.9045799,0.0010505408,0.060411032,0.00016328898,0.00023197819,0.00019898581,0.03057963,0.0000995273,0.002685028],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99881005,0.000086470456,0.00014034659,0.00023821312,0.0005898418,0.00013508537],"domain_scores_gemma":[0.99781215,0.00061845215,0.00020260194,0.00027872142,0.0008978672,0.00019026593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005981563,0.0008620979,0.0011560428,0.006320878,0.00064927206,0.0014560263,0.0007758777,0.00075905153,0.0017940454],"category_scores_gemma":[0.004608194,0.0001829007,0.0013012622,0.007257196,0.00017639865,0.0014458266,0.00044878636,0.00080739195,0.0013279915],"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":[0.0017129331,0.0013114107,0.4081368,0.00097626,0.0010356171,0.000853413,0.00018925159,0.014314534,0.021497635,0.0023149685,0.043919288,0.50373787],"study_design_scores_gemma":[0.00019462255,0.0007578968,0.16148363,0.0002813037,0.001301366,0.001919224,0.0012028571,0.77057683,0.027873402,0.007908594,0.026379766,0.00012052749],"about_ca_topic_score_codex":0.011060341,"about_ca_topic_score_gemma":0.02397522,"teacher_disagreement_score":0.011060341,"about_ca_system_score_codex":0.00070473267,"about_ca_system_score_gemma":0.0013394004,"threshold_uncertainty_score":0.021991909},"labels":[],"label_agreement":null},{"id":"W2970828623","doi":"10.14778/3342263.3342645","title":"Efficient algorithms for densest subgraph discovery","year":2019,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":115,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Induced subgraph isomorphism problem; Intuition; Computer science; Subgraph isomorphism problem; Graph; Algorithm; Color-coding; Efficient algorithm; Theoretical computer science; Artificial intelligence; Line graph","score_opus":0.013070494118829084,"score_gpt":0.23755038924642918,"score_spread":0.2244798951276001,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970828623","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013130378,0.0009566081,0.97727793,0.0006265506,0.00007726126,0.0003665573,0.001011948,0.0039499993,0.0026027618],"genre_scores_gemma":[0.07665639,0.00054792356,0.914748,0.00024415384,0.00008888763,0.00043749897,0.004659056,0.00044483168,0.0021732524],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99614894,0.0007727728,0.0002957236,0.0011664355,0.0011720717,0.00044414419],"domain_scores_gemma":[0.99054503,0.0048018084,0.0007362175,0.0024066407,0.001161817,0.00034847402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027628767,0.0024508866,0.0026835585,0.005454037,0.0018258239,0.002922295,0.004275587,0.0027045065,0.0063237124],"category_scores_gemma":[0.015302,0.0014699965,0.0027812729,0.007930484,0.0012770729,0.0061166007,0.004554974,0.0024068626,0.0030394227],"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":[0.0003835076,0.0006338007,0.004093499,0.0009383431,0.00028945622,0.00026695954,0.0005675493,0.20482634,0.0063864705,0.044349227,0.037354976,0.6999099],"study_design_scores_gemma":[0.00014947176,0.00008014928,0.00069081143,0.00004501609,0.000077036406,0.00035818852,0.0001911556,0.870224,0.0029184313,0.116618276,0.008617361,0.000030112758],"about_ca_topic_score_codex":0.0065972116,"about_ca_topic_score_gemma":0.013496765,"teacher_disagreement_score":0.0065972116,"about_ca_system_score_codex":0.002329322,"about_ca_system_score_gemma":0.004490763,"threshold_uncertainty_score":0.02115494},"labels":[],"label_agreement":null},{"id":"W2971324562","doi":"10.1007/978-3-030-28374-2_4","title":"Frequent Itemsets as Descriptors of Textual Records","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms 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":"Université du Québec à Trois-Rivières","funders":"","keywords":"Computer science; Medoid; Similarity (geometry); Data mining; Set (abstract data type); Hierarchical clustering; Process (computing); Association rule learning; Cluster analysis; Artificial intelligence; Information retrieval; Data set; Pattern recognition (psychology); Natural language processing","score_opus":0.01979408017618044,"score_gpt":0.2542030724421918,"score_spread":0.23440899226601136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2971324562","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40707842,0.015909629,0.5231001,0.0011785211,0.0010269244,0.0008585145,0.037060734,0.003933761,0.009853343],"genre_scores_gemma":[0.6791566,0.0046236645,0.26392034,0.00016706905,0.00064653676,0.0006479555,0.042138632,0.00017586167,0.008523317],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989145,0.00018705401,0.0001978222,0.00021711791,0.00041100412,0.000072584386],"domain_scores_gemma":[0.99747,0.0015361612,0.00037161045,0.00018879937,0.00034004537,0.00009335709],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000642983,0.00049419556,0.000651528,0.008209794,0.0004447495,0.001947276,0.0009292512,0.00060788466,0.0023085296],"category_scores_gemma":[0.0051164543,0.0003637175,0.0006503933,0.008960442,0.00039634536,0.0027710856,0.0006526358,0.00062391226,0.0012120734],"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":[0.0019648124,0.00059069163,0.027650224,0.002374619,0.00037653712,0.0031279519,0.0014861943,0.02060756,0.040577542,0.11297673,0.028420892,0.7598463],"study_design_scores_gemma":[0.00030899252,0.001435429,0.046591397,0.00089453784,0.0006470948,0.008122156,0.0029995875,0.49543732,0.03239477,0.30741376,0.10349234,0.00026263247],"about_ca_topic_score_codex":0.0008109273,"about_ca_topic_score_gemma":0.0010121708,"teacher_disagreement_score":0.008209794,"about_ca_system_score_codex":0.0005822981,"about_ca_system_score_gemma":0.0004934458,"threshold_uncertainty_score":0.0077227354},"labels":[],"label_agreement":null},{"id":"W2980245743","doi":"10.4135/9781483346397.n110","title":"Educational Data Mining","year":2015,"lang":"en","type":"reference-entry","venue":"The SAGE Encyclopedia of Educational Technology","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Data science; Data mining","score_opus":0.04008068416848926,"score_gpt":0.31983981976846115,"score_spread":0.2797591355999719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2980245743","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04957624,0.012951792,0.4677441,0.0106279515,0.0009384179,0.0067335777,0.3846134,0.014656352,0.052158196],"genre_scores_gemma":[0.19941412,0.009104857,0.3832959,0.0017413835,0.0005784295,0.0038278154,0.38643998,0.000415365,0.01518217],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99406886,0.0011086239,0.0014127857,0.0012640511,0.0018349304,0.0003108277],"domain_scores_gemma":[0.990132,0.004239639,0.00092857576,0.0018833452,0.002422097,0.00039437137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039241244,0.0011886378,0.0015912721,0.00913714,0.0010690978,0.0036988687,0.0026475112,0.0012502838,0.011255721],"category_scores_gemma":[0.020528905,0.00043423442,0.0019026009,0.010787498,0.0003848433,0.0024294932,0.0020412353,0.0017522809,0.009749533],"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":[0.00027067028,0.00063964084,0.042061217,0.002241491,0.00039024407,0.000660202,0.0003120314,0.009509168,0.0012347156,0.011261748,0.111987315,0.81943166],"study_design_scores_gemma":[0.00020759962,0.00044703556,0.046625115,0.0026285343,0.00047720163,0.002757619,0.002312612,0.15508327,0.0134079,0.07701758,0.6988621,0.00017348444],"about_ca_topic_score_codex":0.0042311414,"about_ca_topic_score_gemma":0.0045971856,"teacher_disagreement_score":0.011255721,"about_ca_system_score_codex":0.0013820088,"about_ca_system_score_gemma":0.0035514478,"threshold_uncertainty_score":0.0376541},"labels":[],"label_agreement":null},{"id":"W2981166004","doi":"10.1631/fitee.1800467","title":"A non-group parallel frequent pattern mining algorithm based on conditional patterns","year":2019,"lang":"en","type":"article","venue":"Frontiers of Information Technology & Electronic Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Association rule learning; Data mining; Partition (number theory); Task (project management); Redundancy (engineering); Apriori algorithm; Data redundancy; Big data; Process (computing); Cluster analysis; Algorithm; Machine learning; Database; Mathematics","score_opus":0.0018150353095662338,"score_gpt":0.1744874865691793,"score_spread":0.17267245125961309,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981166004","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019585934,0.0002334358,0.9767715,0.00021016385,0.00008824612,0.00036768618,0.00034131217,0.0013747916,0.0010270363],"genre_scores_gemma":[0.12328078,0.00023209752,0.87150955,0.00014190881,0.000074739764,0.0005216144,0.001469444,0.00013016163,0.0026396534],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985858,0.0001913619,0.00013947298,0.0004147431,0.0005581877,0.000110414934],"domain_scores_gemma":[0.99848384,0.00044899617,0.00016449939,0.00027643947,0.00054169405,0.00008453567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013936802,0.00095364486,0.0015169105,0.002999026,0.0014549632,0.00093770894,0.0025691127,0.00087172195,0.0020982986],"category_scores_gemma":[0.003737087,0.0005875746,0.001389039,0.0036943674,0.00048706442,0.0020978975,0.0011544928,0.001236104,0.0009052805],"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":[0.0004950473,0.0005302335,0.009737495,0.0004045415,0.0003727143,0.000611951,0.00028702608,0.07771409,0.014275131,0.008821639,0.011161086,0.8755891],"study_design_scores_gemma":[0.00019133958,0.00029576215,0.0028546066,0.00003308554,0.00012983332,0.0015146083,0.00011002104,0.9578278,0.009574094,0.01716742,0.010248685,0.000052678985],"about_ca_topic_score_codex":0.003988643,"about_ca_topic_score_gemma":0.0047195246,"teacher_disagreement_score":0.003988643,"about_ca_system_score_codex":0.0005747366,"about_ca_system_score_gemma":0.0023487457,"threshold_uncertainty_score":0.007930875},"labels":[],"label_agreement":null},{"id":"W2983748013","doi":"10.5555/3370272.3370308","title":"Research Challenges in Query Processing and Data Analytics on the Edge","year":2019,"lang":"en","type":"article","venue":"Research Portal (Queen's University Belfast)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Analytics; Query optimization; Data science; Enhanced Data Rates for GSM Evolution; Information retrieval; Data analysis; Data mining; Artificial intelligence","score_opus":0.1540433644246053,"score_gpt":0.36286376477600724,"score_spread":0.20882040035140192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2983748013","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048940472,0.11155662,0.6178402,0.16208841,0.0026414853,0.0003700312,0.00096568867,0.0009877529,0.054609474],"genre_scores_gemma":[0.5208558,0.104130805,0.34452233,0.010870132,0.0073537375,0.00034513226,0.0014734515,0.0006328726,0.009815747],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9872897,0.005145761,0.00081832317,0.0018731578,0.0038100975,0.0010628898],"domain_scores_gemma":[0.9450299,0.044531077,0.0011615946,0.0035196112,0.004597799,0.0011600062],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015659546,0.00092290406,0.0022685672,0.0016130734,0.0020935275,0.0121451095,0.0044530914,0.004887395,0.0046259817],"category_scores_gemma":[0.031065999,0.0010327804,0.0014032185,0.006283399,0.0055332338,0.02484647,0.0037836996,0.0070715384,0.002262585],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004783518,0.00042206244,0.0038003633,0.0023993726,0.00021638117,0.00057580543,0.0014418121,0.060442556,0.0039153164,0.5487392,0.05670374,0.32086515],"study_design_scores_gemma":[0.000059366666,0.00016490818,0.0011725026,0.0004026179,0.000057999736,0.0005495551,0.0024258425,0.27857962,0.0021347739,0.6241816,0.09018496,0.00008618043],"about_ca_topic_score_codex":0.0047797477,"about_ca_topic_score_gemma":0.0022328056,"teacher_disagreement_score":0.015659546,"about_ca_system_score_codex":0.0021006824,"about_ca_system_score_gemma":0.0027706716,"threshold_uncertainty_score":0.08281654},"labels":[],"label_agreement":null},{"id":"W2985552643","doi":"","title":"Advanced Data Mining and Applications: 5th International Conference, ADMA 2009, Beijing, China, August 17-19, 2009: Proceedings","year":2009,"lang":"en","type":"article","venue":"Advanced Data Mining and Applications","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":"Beijing; China; Computer science; Chinese academy of sciences; Data science; Political science","score_opus":0.04427514903601441,"score_gpt":0.33064926940766254,"score_spread":0.2863741203716481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2985552643","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036523856,0.113161854,0.7535725,0.018789994,0.028112605,0.0011714451,0.004560431,0.012216562,0.03189071],"genre_scores_gemma":[0.10671142,0.0864547,0.52581877,0.003706566,0.0064585335,0.00075562473,0.019769171,0.0017556414,0.24856961],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983374,0.00028059576,0.00018892932,0.00028968265,0.0007996266,0.00010383836],"domain_scores_gemma":[0.9958598,0.0006231714,0.00010246768,0.0005743968,0.002349374,0.0004908576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007063755,0.0010090446,0.002262232,0.0019287961,0.0010008371,0.0033150497,0.0019581555,0.0013640053,0.016107801],"category_scores_gemma":[0.0051922216,0.0007903938,0.0010128635,0.002330048,0.001130814,0.0035676213,0.0019325222,0.002898073,0.009901023],"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":[0.00033078415,0.00036429244,0.0022809007,0.00049508695,0.00012588175,0.00016612414,0.00016564749,0.0015268234,0.006618078,0.003893349,0.31893054,0.6651025],"study_design_scores_gemma":[0.0001274006,0.0006618694,0.015349365,0.0005661792,0.00037529776,0.0020197015,0.0005253316,0.09121768,0.022405054,0.014989802,0.851628,0.00013433362],"about_ca_topic_score_codex":0.0036499908,"about_ca_topic_score_gemma":0.0050183134,"teacher_disagreement_score":0.016107801,"about_ca_system_score_codex":0.0009073962,"about_ca_system_score_gemma":0.0029359676,"threshold_uncertainty_score":0.053885937},"labels":[],"label_agreement":null},{"id":"W2989242831","doi":"10.21629/jsee.2019.05.05","title":"MapReduce rationality verification based on object Petri net","year":2019,"lang":"en","type":"article","venue":"Journal of Systems Engineering and Electronics","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Executable; Petri net; Rationality; Object (grammar); Process (computing); Distributed computing; Irrational number; Data mining; Programming language; Artificial intelligence","score_opus":0.006068135918949697,"score_gpt":0.20317303580413457,"score_spread":0.19710489988518487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2989242831","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06281423,0.00012247723,0.92331827,0.0007287199,0.00018323066,0.00036152793,0.0006461016,0.0029792213,0.008846205],"genre_scores_gemma":[0.907671,0.00013818487,0.08690064,0.0001426796,0.000049733786,0.00018328392,0.00057876075,0.00016362945,0.0041720397],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99712175,0.00040708345,0.00014040977,0.0006288362,0.0012146048,0.0004873071],"domain_scores_gemma":[0.99443936,0.003103028,0.00025787638,0.0006907349,0.0013387481,0.00017025517],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020640309,0.000671537,0.0009946489,0.001234204,0.0013115142,0.0023457143,0.0018164235,0.0006496471,0.0067636715],"category_scores_gemma":[0.009203337,0.0004228139,0.0021077262,0.00075186463,0.0014811405,0.0032649375,0.0024185209,0.0016993452,0.0005860989],"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":[0.0012603828,0.0004902189,0.010170837,0.00070521346,0.00033357495,0.0014891522,0.00052922947,0.4684477,0.014672374,0.36285377,0.008839048,0.1302086],"study_design_scores_gemma":[0.00006815808,0.00006185862,0.0007562759,0.00003319172,0.00008606035,0.00012049257,0.00011110473,0.8552495,0.010634573,0.13097122,0.0018714268,0.000036169426],"about_ca_topic_score_codex":0.016320948,"about_ca_topic_score_gemma":0.011797945,"teacher_disagreement_score":0.016320948,"about_ca_system_score_codex":0.0016481024,"about_ca_system_score_gemma":0.006640248,"threshold_uncertainty_score":0.032451868},"labels":[],"label_agreement":null},{"id":"W2989849422","doi":"10.4018/ijdwm.2020010101","title":"Mining Integrated Sequential Patterns From Multiple Databases","year":2019,"lang":"en","type":"article","venue":"International Journal of Data Warehousing and Mining","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Royal Bank of Canada; University of Windsor","funders":"","keywords":"Computer science; Tuple; Sequence (biology); Database transaction; Sequence database; Data mining; GSP Algorithm; Table (database); Database; Position (finance); Association rule learning; Apriori algorithm; Mathematics","score_opus":0.0751542230104232,"score_gpt":0.3248460621996281,"score_spread":0.2496918391892049,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2989849422","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23510258,0.0035154857,0.7413842,0.00095468946,0.00024032414,0.0008826099,0.008559629,0.0044900477,0.004870418],"genre_scores_gemma":[0.44771713,0.001513199,0.53320825,0.00023685262,0.00017308051,0.00046794265,0.014351915,0.0001702589,0.0021613382],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954182,0.00048712493,0.00072930416,0.0011008489,0.0020000236,0.00026444872],"domain_scores_gemma":[0.99385405,0.0022094995,0.00093007344,0.0009779844,0.0017262999,0.0003021171],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019084412,0.0011870504,0.0016290133,0.00831327,0.00083546515,0.0027888785,0.0017822812,0.00095565134,0.0018568806],"category_scores_gemma":[0.010871523,0.0007931681,0.0014933455,0.010527139,0.00042389263,0.0043017115,0.0019501101,0.0010090364,0.0010378684],"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":[0.0011291958,0.0005995979,0.06750132,0.0013709422,0.0009980274,0.005160055,0.00064648857,0.03373677,0.019638104,0.009590455,0.007489883,0.8521392],"study_design_scores_gemma":[0.00017195477,0.000942892,0.026175823,0.0003799822,0.0009257763,0.007393497,0.0018790421,0.81278396,0.03985806,0.07219917,0.037151463,0.00013851217],"about_ca_topic_score_codex":0.0017862304,"about_ca_topic_score_gemma":0.0025984107,"teacher_disagreement_score":0.00831327,"about_ca_system_score_codex":0.0005680938,"about_ca_system_score_gemma":0.0013975452,"threshold_uncertainty_score":0.010092914},"labels":[],"label_agreement":null},{"id":"W2990678853","doi":"10.1007/s10601-020-09312-3","title":"Learning optimal decision trees using constraint programming","year":2020,"lang":"en","type":"article","venue":"Constraints","topic":"Data Mining Algorithms and Applications","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":"Université Laval; Polytechnique Montréal","funders":"","keywords":"Constraint programming; Computer science; Decision tree; Constraint (computer-aided design); Machine learning; Artificial intelligence; Key (lock); Constraint satisfaction; Incremental decision tree; Greedy algorithm; Constraint learning; Decision tree learning; Mathematical optimization; Constraint logic programming; Mathematics; Algorithm; Stochastic programming","score_opus":0.04206220394095465,"score_gpt":0.28838711068591033,"score_spread":0.2463249067449557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990678853","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010124983,0.00093658635,0.98543465,0.00062360597,0.000059464877,0.00014147475,0.00051686744,0.00032253057,0.0018398203],"genre_scores_gemma":[0.19459851,0.0013411718,0.7983378,0.00036760673,0.00017839936,0.0006147668,0.0024051,0.00027035273,0.0018862208],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959186,0.001949827,0.00028500785,0.00080642966,0.00079450425,0.00024562253],"domain_scores_gemma":[0.96801233,0.029088499,0.00089857983,0.000632166,0.0010605373,0.00030794475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00444465,0.0014751422,0.003050035,0.0022672974,0.0009900843,0.003267269,0.002508789,0.0019642976,0.005699894],"category_scores_gemma":[0.026097376,0.0016057625,0.0018924258,0.004825234,0.0012942442,0.0042277016,0.0014648819,0.0039249333,0.000891819],"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":[0.0001730332,0.00026928363,0.001418678,0.00061247917,0.00020315239,0.00017954125,0.00010698153,0.74600875,0.00062071974,0.053353086,0.010361005,0.18669334],"study_design_scores_gemma":[0.00002869451,0.000019559486,0.00007035323,0.000047067635,0.000021244703,0.000026871809,0.000021365373,0.94206995,0.00027744053,0.056389805,0.0010175309,0.000010228464],"about_ca_topic_score_codex":0.0066803284,"about_ca_topic_score_gemma":0.009106113,"teacher_disagreement_score":0.0066803284,"about_ca_system_score_codex":0.001554552,"about_ca_system_score_gemma":0.0030166914,"threshold_uncertainty_score":0.023505807},"labels":[],"label_agreement":null},{"id":"W2996766745","doi":"10.24507/ijicic.14.06.2129","title":"The predictive modeling for learning student results based on sequential rules","year":2018,"lang":"en","type":"article","venue":"International journal of innovative computing, information & control","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Data science","score_opus":0.017386701493296745,"score_gpt":0.3153025746708615,"score_spread":0.29791587317756474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996766745","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.106989756,0.0007407488,0.88893294,0.0004224793,0.00010979775,0.000087869535,0.00026186107,0.00055398676,0.0019005223],"genre_scores_gemma":[0.9573037,0.00043807636,0.038947288,0.00006802406,0.000062888284,0.00012555635,0.00029267877,0.0000376324,0.0027240939],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986002,0.00028572863,0.00010877228,0.00041109428,0.00043280926,0.00016138049],"domain_scores_gemma":[0.99267405,0.0056175953,0.00048212952,0.00034814942,0.0007413483,0.00013667905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029844346,0.0007949148,0.0018547482,0.0013608504,0.0004722139,0.0017230657,0.0023913875,0.001234582,0.0019008204],"category_scores_gemma":[0.010729098,0.0006622081,0.0011261335,0.0012023981,0.0008522645,0.0018794825,0.0007545448,0.0019095333,0.00039131724],"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":[0.00023718816,0.00014300314,0.003868012,0.00012277812,0.00011737892,0.00019477529,0.00013054938,0.9058931,0.0008848358,0.013963534,0.00077667827,0.073668174],"study_design_scores_gemma":[0.0000038972726,0.00001325546,0.00023986552,0.000005132717,0.000012887366,0.000013647453,0.0000023460038,0.9966516,0.00016474762,0.0028373213,0.000051674928,0.000003629153],"about_ca_topic_score_codex":0.01519644,"about_ca_topic_score_gemma":0.009602674,"teacher_disagreement_score":0.01519644,"about_ca_system_score_codex":0.0009207811,"about_ca_system_score_gemma":0.0014177266,"threshold_uncertainty_score":0.030215979},"labels":[],"label_agreement":null},{"id":"W2996798852","doi":"","title":"An efficient approach for mining weighted frequent patterns with dynamic weights.","year":2019,"lang":"en","type":"article","venue":"Mspace (University of Manitoba)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Data mining","score_opus":0.010069182989668683,"score_gpt":0.19792637348500242,"score_spread":0.18785719049533373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996798852","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008498935,0.0004077524,0.988283,0.00013895748,0.000050156388,0.00023480099,0.0008111616,0.00093900645,0.00063633465],"genre_scores_gemma":[0.07974495,0.0004349574,0.9152015,0.000101084865,0.00005356967,0.0004182585,0.0027455399,0.00007413703,0.0012260146],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982621,0.00023810695,0.00020950676,0.0003446073,0.0008450759,0.00010059024],"domain_scores_gemma":[0.9978808,0.00070651504,0.0002906826,0.00032957472,0.0007186625,0.000073729556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010753763,0.0007631756,0.00079157186,0.0053552664,0.000714543,0.0011346434,0.0014730352,0.00083269575,0.0015048934],"category_scores_gemma":[0.007590678,0.00057714916,0.0011230042,0.006433815,0.0003230907,0.0027470943,0.0012171789,0.00087690406,0.001263273],"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":[0.00021780025,0.00023765217,0.006299132,0.00060321443,0.00026027582,0.00071201165,0.00030684017,0.02784766,0.018966127,0.01823904,0.012750987,0.91355926],"study_design_scores_gemma":[0.00010086648,0.0002680802,0.002980226,0.00013295432,0.00020512321,0.0031274753,0.0002925683,0.87299263,0.012589394,0.074618116,0.032622594,0.000069977265],"about_ca_topic_score_codex":0.0015927053,"about_ca_topic_score_gemma":0.0029821072,"teacher_disagreement_score":0.0053552664,"about_ca_system_score_codex":0.00041093535,"about_ca_system_score_gemma":0.0012939372,"threshold_uncertainty_score":0.005687177},"labels":[],"label_agreement":null},{"id":"W2997486962","doi":"10.1007/978-3-030-59065-9_9","title":"High-Utility Interval-Based Sequences","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms 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 Regina","funders":"","keywords":"Pruning; Range (aeronautics); Sequential Pattern Mining; Sequence (biology); Event (particle physics); Efficient algorithm","score_opus":0.027275872602880835,"score_gpt":0.2597194800584349,"score_spread":0.2324436074555541,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997486962","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02692358,0.00068186136,0.96459365,0.00012601083,0.00012391486,0.00007555183,0.0005955411,0.0011855887,0.0056943726],"genre_scores_gemma":[0.40111908,0.00077435427,0.58795977,0.00012455192,0.0001506893,0.00016524353,0.0019777413,0.00022408787,0.007504429],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901485,0.00018379494,0.00006932073,0.000201573,0.00046602116,0.00006449336],"domain_scores_gemma":[0.9964652,0.0018291032,0.0002562674,0.00053314527,0.00076526863,0.00015110149],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010040939,0.0006272759,0.00059551344,0.0015817794,0.00043475852,0.001209285,0.001416429,0.00063807,0.007679409],"category_scores_gemma":[0.009449238,0.0002768185,0.00037181002,0.002449466,0.0004822352,0.0020434745,0.0010483859,0.0010499436,0.0020527744],"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":[0.0010266574,0.00019204876,0.002424495,0.0004983437,0.000049326998,0.0004661196,0.00025098812,0.13465047,0.017893838,0.13305745,0.008708896,0.70078135],"study_design_scores_gemma":[0.00005823956,0.00035794856,0.0012136042,0.00013196327,0.00003591825,0.00077002385,0.00010153517,0.8092074,0.0128328325,0.15904158,0.016201684,0.00004727736],"about_ca_topic_score_codex":0.0007132394,"about_ca_topic_score_gemma":0.0007097725,"teacher_disagreement_score":0.007679409,"about_ca_system_score_codex":0.00050595234,"about_ca_system_score_gemma":0.00052928925,"threshold_uncertainty_score":0.025690138},"labels":[],"label_agreement":null},{"id":"W2997589860","doi":"10.1007/978-3-030-33698-1_4","title":"Simplifying E-Commerce Analytics by Discovering Hidden Knowledge in Big Data Clickstreams","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in social networks","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":"University of Calgary","funders":"","keywords":"Clickstream; Analytics; Big data; Computer science; Data science; Web analytics; Scalability; Data analysis; Order (exchange); Product (mathematics); The Internet; Data mining; World Wide Web; Business; Database","score_opus":0.05935898137818494,"score_gpt":0.3017774614523816,"score_spread":0.24241848007419667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997589860","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1447492,0.002385833,0.8375011,0.0013587282,0.00036615212,0.00015604703,0.003131613,0.0064441087,0.0039072596],"genre_scores_gemma":[0.6671321,0.0026550472,0.3154306,0.0002750092,0.00081276795,0.00012821343,0.007214173,0.00052056997,0.005831517],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986934,0.00020785553,0.00010990299,0.00029317642,0.0005317971,0.00016386512],"domain_scores_gemma":[0.9943111,0.0036819763,0.00031361482,0.0009700757,0.00054456963,0.00017866456],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011005695,0.0017680547,0.0018363328,0.004144736,0.0008137162,0.004173739,0.0014793765,0.001130355,0.0018037098],"category_scores_gemma":[0.010170277,0.001093858,0.0015270116,0.004596675,0.00088667084,0.006956107,0.0022952997,0.0025864618,0.0026806174],"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":[0.00076174404,0.00094962365,0.028086388,0.00043188612,0.0004079901,0.00090479787,0.00048460698,0.1855729,0.024463054,0.022565108,0.020558124,0.7148138],"study_design_scores_gemma":[0.000008926462,0.000030834843,0.0017309197,0.000021035437,0.00004456516,0.00009934623,0.00006675963,0.9648879,0.004776008,0.02686331,0.00145172,0.000018703526],"about_ca_topic_score_codex":0.009684611,"about_ca_topic_score_gemma":0.010472431,"teacher_disagreement_score":0.009684611,"about_ca_system_score_codex":0.00079370977,"about_ca_system_score_gemma":0.0015293092,"threshold_uncertainty_score":0.019256532},"labels":[],"label_agreement":null},{"id":"W2997829892","doi":"","title":"Sliding window based weighted periodic pattern mining over time series data","year":2019,"lang":"en","type":"article","venue":"Mspace (University of Manitoba)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sliding window protocol; Series (stratigraphy); Computer science; Time series; Window (computing); Data mining; Algorithm; Geology; Machine learning","score_opus":0.017667837946924912,"score_gpt":0.20224086585128748,"score_spread":0.18457302790436256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997829892","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21633658,0.0011629098,0.77832913,0.00016706243,0.00010869665,0.00023840817,0.00091505965,0.0018222978,0.00091988774],"genre_scores_gemma":[0.60971236,0.00062566076,0.38633195,0.00005490145,0.00008147756,0.00020633242,0.0018864333,0.00009929449,0.0010015423],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988675,0.00016597228,0.00022310443,0.00036243934,0.00028591554,0.0000950857],"domain_scores_gemma":[0.997781,0.000923299,0.00040709318,0.00034615805,0.00043647908,0.00010591401],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014287838,0.00062908465,0.0010491472,0.003563359,0.0005927464,0.0007467962,0.0010481837,0.0005199914,0.0010482426],"category_scores_gemma":[0.0053302585,0.00030314244,0.00085447094,0.0040099067,0.00028615672,0.0015065825,0.00065704907,0.0004931138,0.00045812794],"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":[0.00080975733,0.0003453882,0.034614664,0.0004907601,0.00047663823,0.0013428368,0.0005581587,0.052597545,0.035078358,0.004291913,0.003681063,0.86571306],"study_design_scores_gemma":[0.000054413595,0.00041872833,0.010289436,0.000044793305,0.00019700918,0.001039723,0.00022248954,0.96035326,0.01593333,0.007300465,0.0041052857,0.000041012318],"about_ca_topic_score_codex":0.0018312155,"about_ca_topic_score_gemma":0.002654131,"teacher_disagreement_score":0.003563359,"about_ca_system_score_codex":0.00019068221,"about_ca_system_score_gemma":0.00062055566,"threshold_uncertainty_score":0.0075562},"labels":[],"label_agreement":null},{"id":"W2998525497","doi":"","title":"WeFreS: weighted frequent subgraph mining in a single large graph","year":2019,"lang":"en","type":"article","venue":"Mspace (University of Manitoba)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":13,"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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Graph; Induced subgraph isomorphism problem; Data mining; Theoretical computer science; Line graph; Voltage graph","score_opus":0.013068104658126568,"score_gpt":0.19270676575750526,"score_spread":0.17963866109937868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998525497","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.096437976,0.00048952503,0.88428307,0.0003454792,0.000075646385,0.00043822607,0.004356557,0.011981875,0.0015916682],"genre_scores_gemma":[0.19541594,0.0001949669,0.7935692,0.0001095586,0.000030118932,0.0002853071,0.008700359,0.00039299898,0.0013016015],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988794,0.00024402801,0.00012677765,0.00032263715,0.0003083647,0.000118724405],"domain_scores_gemma":[0.99736816,0.0013545944,0.0003234321,0.0005038165,0.0003339756,0.00011608729],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013773816,0.0009101475,0.00075660617,0.0041062636,0.0007562822,0.0010018412,0.0016659248,0.0009317106,0.0021963636],"category_scores_gemma":[0.008609583,0.00048856565,0.0012960451,0.0030367277,0.00037877218,0.0019424027,0.0012229128,0.00058869604,0.00089059613],"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":[0.0007568301,0.0003605349,0.034218185,0.0009544715,0.0007211995,0.0012049947,0.00066276395,0.0759168,0.04107065,0.014673907,0.027984165,0.80147547],"study_design_scores_gemma":[0.00010882016,0.00025470916,0.0068571344,0.000091176116,0.0001342044,0.0016298123,0.0003991188,0.91297513,0.020642461,0.03753127,0.019328875,0.000047218302],"about_ca_topic_score_codex":0.0026045537,"about_ca_topic_score_gemma":0.0072130444,"teacher_disagreement_score":0.0041062636,"about_ca_system_score_codex":0.0003835409,"about_ca_system_score_gemma":0.0011116697,"threshold_uncertainty_score":0.007347584},"labels":[],"label_agreement":null},{"id":"W2999658533","doi":"10.3390/info11010044","title":"Dramatically Reducing Search for High Utility Sequential Patterns by Maintaining Candidate Lists","year":2020,"lang":"en","type":"article","venue":"Information","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Concatenation (mathematics); Reduction (mathematics); Data mining; Property (philosophy); Extension (predicate logic); Sequence (biology); Pattern search; Algorithm; Mathematics","score_opus":0.024125519468434935,"score_gpt":0.27403310736290215,"score_spread":0.2499075878944672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2999658533","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07787043,0.0003856419,0.91720027,0.00037777342,0.00004035159,0.00023215909,0.0003061818,0.0017048876,0.0018824112],"genre_scores_gemma":[0.30863202,0.0003566861,0.6859761,0.00016368403,0.00006635487,0.00027265848,0.0012630657,0.00021274523,0.0030566526],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99718297,0.0006268384,0.00019770279,0.00037620778,0.0013809614,0.00023539933],"domain_scores_gemma":[0.987543,0.0074259187,0.0010141206,0.0022277758,0.0015259592,0.00026333999],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028411262,0.00081716664,0.0012754318,0.0018106065,0.0008642536,0.0018357771,0.0024403445,0.00084708864,0.0027499357],"category_scores_gemma":[0.01893881,0.0007178847,0.0011819939,0.0021524162,0.00075830537,0.0044711637,0.0018592887,0.0013911016,0.0012638734],"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":[0.001207389,0.0005340993,0.013296755,0.0005631145,0.00015319708,0.0010191213,0.00081449817,0.119083315,0.048404973,0.04411391,0.0071264463,0.7636832],"study_design_scores_gemma":[0.00007190919,0.000593758,0.001826979,0.00008138562,0.00009520608,0.0007143398,0.00027482453,0.926644,0.02674662,0.034546446,0.008360384,0.00004412681],"about_ca_topic_score_codex":0.0013519698,"about_ca_topic_score_gemma":0.0033003201,"teacher_disagreement_score":0.0028411262,"about_ca_system_score_codex":0.00057071703,"about_ca_system_score_gemma":0.002476485,"threshold_uncertainty_score":0.0150254965},"labels":[],"label_agreement":null},{"id":"W3006371311","doi":"","title":"INDEPENDENT DE-DUPLICATION IN DATA CLEANING","year":2005,"lang":"en","type":"article","venue":"University of Zagreb University Computing Centre (SRCE)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor; University of Calgary","funders":"","keywords":"Gene duplication; Biology; Genetics; Gene","score_opus":0.015655940187028247,"score_gpt":0.21076068833780184,"score_spread":0.1951047481507736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006371311","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029568292,0.0020600567,0.964977,0.00050300185,0.00013831344,0.00028853372,0.00018319221,0.0009436481,0.0013378788],"genre_scores_gemma":[0.16453445,0.0011902166,0.8280863,0.00036613122,0.00012689554,0.00031475854,0.0010431426,0.0002450489,0.0040930114],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98527086,0.00589679,0.0012038,0.002584178,0.0042959694,0.00074839836],"domain_scores_gemma":[0.9642958,0.011267347,0.0022235198,0.017261792,0.004522316,0.00042916826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013218125,0.0011229824,0.0022402348,0.005084507,0.0031950606,0.0025075627,0.0038724483,0.0021409264,0.0013249392],"category_scores_gemma":[0.032336093,0.001332034,0.0016514795,0.0070826528,0.0019855837,0.007025707,0.006989345,0.0019456447,0.0012575483],"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":[0.0006379798,0.00036664464,0.009362202,0.00073231437,0.00025952118,0.00041883314,0.0016280717,0.037818376,0.021763342,0.03179714,0.007017236,0.88819844],"study_design_scores_gemma":[0.00021772423,0.0010209522,0.01010602,0.0004872373,0.00045229393,0.0052784123,0.0031784591,0.48652023,0.26377928,0.13479097,0.09386322,0.00030525823],"about_ca_topic_score_codex":0.00073108176,"about_ca_topic_score_gemma":0.0010637373,"teacher_disagreement_score":0.013218125,"about_ca_system_score_codex":0.00094736216,"about_ca_system_score_gemma":0.0022776157,"threshold_uncertainty_score":0.06990492},"labels":[],"label_agreement":null},{"id":"W3008429170","doi":"10.3233/jifs-179666","title":"An efficient algorithm for fuzzy frequent itemset mining","year":2020,"lang":"en","type":"article","venue":"Journal of Intelligent & Fuzzy Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Apriori algorithm; Data mining; Computer science; Association rule learning; Fuzzy set; Fuzzy logic; A priori and a posteriori; Set (abstract data type); Field (mathematics); Task (project management); Fuzzy set operations; Knowledge extraction; Machine learning; Artificial intelligence; Mathematics","score_opus":0.04078759102705707,"score_gpt":0.29222292468254324,"score_spread":0.25143533365548615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008429170","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030521909,0.00035810767,0.9947907,0.000090870955,0.000060887964,0.0001733541,0.00018126097,0.000746819,0.0005459238],"genre_scores_gemma":[0.030703412,0.0002915223,0.96668667,0.000072953175,0.000050574556,0.00039711175,0.0007231339,0.00004450548,0.0010301184],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983498,0.0003575045,0.00021358288,0.00035088038,0.00060292246,0.00012529084],"domain_scores_gemma":[0.9987311,0.00062460336,0.000086510714,0.00011708282,0.00041098622,0.000029635545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015663465,0.0013833066,0.0016575017,0.0035775339,0.0013219512,0.0012695247,0.0022309208,0.0017641388,0.003885783],"category_scores_gemma":[0.0052113975,0.0006343902,0.0012785577,0.0043584695,0.0003997188,0.002376199,0.0011224609,0.001206369,0.0024356074],"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":[0.00031642403,0.0002069231,0.0015111059,0.00038457956,0.00013092547,0.00029569442,0.00016281917,0.07884039,0.006470462,0.011436892,0.009229456,0.89101416],"study_design_scores_gemma":[0.00017855526,0.00025047452,0.000690709,0.00006565443,0.000063501575,0.0010813763,0.00008069129,0.95441335,0.0067088567,0.019329127,0.017083487,0.000054267934],"about_ca_topic_score_codex":0.002033518,"about_ca_topic_score_gemma":0.0017710144,"teacher_disagreement_score":0.003885783,"about_ca_system_score_codex":0.0006070064,"about_ca_system_score_gemma":0.001542476,"threshold_uncertainty_score":0.012999237},"labels":[],"label_agreement":null},{"id":"W3022175079","doi":"","title":"Research challenges in query processing and data analytics on the edge.","year":2019,"lang":"en","type":"article","venue":"Conference of the Centre for Advanced Studies on Collaborative Research","topic":"Data Mining Algorithms and Applications","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 New Brunswick","funders":"","keywords":"Computer science; Analytics; Data science; Enhanced Data Rates for GSM Evolution; Query optimization; Data analysis; Information retrieval; Data mining; Artificial intelligence","score_opus":0.44616153419620863,"score_gpt":0.48728073808918815,"score_spread":0.04111920389297952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3022175079","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027796255,0.16004716,0.5984855,0.1763468,0.005106479,0.0003358989,0.0020633426,0.001853317,0.027965229],"genre_scores_gemma":[0.2952036,0.10861381,0.54453015,0.018964073,0.012306814,0.00040150268,0.0041144895,0.0010850027,0.014780441],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9854542,0.005525474,0.0011307291,0.0023298815,0.004370137,0.0011896524],"domain_scores_gemma":[0.8740231,0.09751158,0.0018755457,0.010379488,0.012410026,0.0038001558],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.035840575,0.0012187735,0.003581291,0.0034738039,0.0022941192,0.01947695,0.006988951,0.0060653905,0.010550564],"category_scores_gemma":[0.06827036,0.001393769,0.0017171524,0.011604507,0.005971818,0.053827155,0.006608468,0.008851475,0.005160791],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006643774,0.0003173363,0.003686518,0.0014822603,0.0002502079,0.0002990401,0.00080015534,0.011630997,0.0017965583,0.42716306,0.12773168,0.4241777],"study_design_scores_gemma":[0.00005916809,0.00018512891,0.0012083185,0.00048422933,0.00009364373,0.00049342716,0.001929032,0.10271336,0.0022453566,0.7535237,0.13697486,0.00008974688],"about_ca_topic_score_codex":0.005163022,"about_ca_topic_score_gemma":0.00352221,"teacher_disagreement_score":0.035840575,"about_ca_system_score_codex":0.0023557104,"about_ca_system_score_gemma":0.0036772368,"threshold_uncertainty_score":0.18954533},"labels":[],"label_agreement":null},{"id":"W3022567118","doi":"10.48550/arxiv.2005.00081","title":"Scalable Mining of Maximal Quasi-Cliques: An Algorithm-System Codesign Approach","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Clique; Scalability; Pruning; Vertex (graph theory); Algorithm; Task (project management); Graph; Theoretical computer science; Combinatorics; Mathematics; Database","score_opus":0.10870059179833225,"score_gpt":0.20834948778834897,"score_spread":0.09964889599001672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3022567118","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026355134,0.00019871866,0.9623559,0.000558261,0.00007312284,0.0003334721,0.00016373766,0.0073837447,0.0025779407],"genre_scores_gemma":[0.22991467,0.00013008666,0.76517785,0.00025968187,0.00005770722,0.0005095246,0.00081876025,0.0006321509,0.0024996176],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974595,0.00058578054,0.00014364919,0.00071215926,0.00075584446,0.00034309807],"domain_scores_gemma":[0.9946517,0.0019564223,0.00034387465,0.0018222796,0.000984752,0.00024102071],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016640527,0.0011360429,0.0011068163,0.0013080313,0.0012982386,0.0019515054,0.0033710874,0.0011317154,0.003974053],"category_scores_gemma":[0.0080205705,0.0007393862,0.0010145584,0.0023915526,0.001311754,0.0030074054,0.0028219041,0.0015457981,0.0015687608],"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":[0.0005822847,0.0005291541,0.0045785042,0.00039555482,0.00015468831,0.00029112888,0.0005900334,0.41375604,0.027745277,0.041435253,0.022714272,0.4872278],"study_design_scores_gemma":[0.000047991387,0.000042776028,0.00016590102,0.0000066775465,0.000010869574,0.000044492634,0.00005156616,0.9828881,0.0031036779,0.011298119,0.0023295805,0.000010353774],"about_ca_topic_score_codex":0.007854833,"about_ca_topic_score_gemma":0.012412504,"teacher_disagreement_score":0.007854833,"about_ca_system_score_codex":0.0018002557,"about_ca_system_score_gemma":0.0053919326,"threshold_uncertainty_score":0.015618205},"labels":[],"label_agreement":null},{"id":"W3023305178","doi":"","title":"Mining and exploration of attributed graphs: theory and applications.","year":2019,"lang":"en","type":"article","venue":"Conference of the Centre for Advanced Studies on Collaborative Research","topic":"Data Mining Algorithms and Applications","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":"Ontario Tech University; Toronto Metropolitan University","funders":"","keywords":"Graph theory; Computer science; Theoretical computer science; Mathematics; Combinatorics","score_opus":0.10725242008273843,"score_gpt":0.3949353450436607,"score_spread":0.28768292496092224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3023305178","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016122242,0.0048499918,0.9726185,0.0024883775,0.00014417422,0.00013128814,0.0010559278,0.0011056641,0.0014838758],"genre_scores_gemma":[0.2614118,0.0055040466,0.72256464,0.00047210095,0.0004055874,0.00030816055,0.0048323497,0.0003197049,0.0041816197],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99503493,0.0020951198,0.00041496294,0.0010178725,0.0012236201,0.00021347568],"domain_scores_gemma":[0.95211595,0.038076263,0.0019108532,0.00424916,0.0026437915,0.0010039218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006335538,0.00094900234,0.0016538051,0.00773118,0.0015853083,0.0046081827,0.0034433638,0.001517513,0.0024330183],"category_scores_gemma":[0.047280267,0.0012628753,0.002347143,0.010034093,0.0023074534,0.008510555,0.0038215925,0.0027525602,0.0010072216],"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":[0.0002653177,0.0005616727,0.017602405,0.0015941783,0.0007012217,0.00046925884,0.0014425891,0.15612742,0.0019893874,0.1977859,0.030492416,0.59096825],"study_design_scores_gemma":[0.000022412607,0.00004436846,0.0015215673,0.0001487661,0.00007834685,0.00026310078,0.0003787067,0.41135013,0.0015078646,0.5743941,0.010259537,0.000031062686],"about_ca_topic_score_codex":0.0036669248,"about_ca_topic_score_gemma":0.005170627,"teacher_disagreement_score":0.00773118,"about_ca_system_score_codex":0.001351924,"about_ca_system_score_gemma":0.0024171912,"threshold_uncertainty_score":0.033505976},"labels":[],"label_agreement":null},{"id":"W3032125656","doi":"10.36227/techrxiv.12088938.v1","title":"Web service for data aggregation in eSports domain","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Web application; Domain (mathematical analysis); Computer science; Web service; World Wide Web; Service (business); Business; Mathematics; Marketing","score_opus":0.08444892918551193,"score_gpt":0.3204725268345218,"score_spread":0.23602359764900988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3032125656","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042239692,0.00068553974,0.89537835,0.0013616809,0.0006661476,0.00066254515,0.0014092867,0.045743182,0.0118536465],"genre_scores_gemma":[0.46866417,0.0010580465,0.48761854,0.0024724172,0.0006741557,0.0006500665,0.008551166,0.0046776696,0.025633715],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99669576,0.00055682793,0.00047411848,0.00045586398,0.001404957,0.00041251094],"domain_scores_gemma":[0.9960108,0.0007652049,0.00024904148,0.0014111099,0.0011255328,0.0004384489],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032719339,0.00081975514,0.0012215228,0.00205008,0.001420817,0.0035000907,0.0019748097,0.0015443364,0.0060831816],"category_scores_gemma":[0.004747975,0.0005091832,0.0014870727,0.002466556,0.0007562109,0.0038878396,0.0038813984,0.002208023,0.0030936818],"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":[0.0027620855,0.0015865075,0.020698927,0.0014488872,0.0006447822,0.004281857,0.0022500001,0.016115047,0.083695725,0.108171456,0.11965952,0.6386852],"study_design_scores_gemma":[0.00027064793,0.00040991875,0.007906603,0.00025778063,0.00036456078,0.002699966,0.0011605114,0.53580457,0.0969344,0.047939666,0.30601877,0.00023264809],"about_ca_topic_score_codex":0.0053993566,"about_ca_topic_score_gemma":0.0032634295,"teacher_disagreement_score":0.0060831816,"about_ca_system_score_codex":0.0010386459,"about_ca_system_score_gemma":0.0017529416,"threshold_uncertainty_score":0.020350277},"labels":[],"label_agreement":null},{"id":"W3035362865","doi":"10.1142/s2196888820500207","title":"New Descriptors of Textual Records: Getting Help from Frequent Itemsets","year":2020,"lang":"en","type":"article","venue":"Vietnam Journal of Computer Science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Computer science; Cluster analysis; Hierarchical clustering; Data mining; Medoid; Keyword extraction; Information retrieval; Set (abstract data type); Similarity (geometry); Process (computing); Raw data; Document clustering; Association rule learning; Artificial intelligence","score_opus":0.026599824073212396,"score_gpt":0.2530871985306625,"score_spread":0.22648737445745012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035362865","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1554822,0.0043320754,0.7784571,0.0014520464,0.0006771622,0.0015038853,0.04182137,0.009705597,0.00656852],"genre_scores_gemma":[0.29120305,0.002029809,0.6644365,0.0002183237,0.00042234347,0.00088956836,0.037260756,0.00031252005,0.003227112],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983699,0.00024639856,0.00034335835,0.00036392277,0.0005663914,0.00011001879],"domain_scores_gemma":[0.99347645,0.0034540507,0.0007542495,0.00071357604,0.0013883646,0.00021324381],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012962254,0.0008500905,0.0011561061,0.011662905,0.0005408824,0.0018595275,0.001277076,0.0011534947,0.003659215],"category_scores_gemma":[0.012342324,0.00034376635,0.00078151654,0.010098773,0.00036222057,0.0030232796,0.0011473262,0.0008160181,0.0034086735],"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":[0.00084113266,0.00045540291,0.02489039,0.0016764973,0.00015550297,0.0015983569,0.0009211871,0.005413111,0.019819133,0.007841696,0.018962748,0.91742486],"study_design_scores_gemma":[0.0004725104,0.001741975,0.06703277,0.0012321909,0.0007065159,0.00950805,0.007892387,0.608746,0.06376705,0.08594128,0.15247868,0.00048066844],"about_ca_topic_score_codex":0.0014468224,"about_ca_topic_score_gemma":0.0016524894,"teacher_disagreement_score":0.011662905,"about_ca_system_score_codex":0.00046829946,"about_ca_system_score_gemma":0.0007718226,"threshold_uncertainty_score":0.012241304},"labels":[],"label_agreement":null},{"id":"W3039795743","doi":"10.1007/978-3-030-59065-9_18","title":"Building a Competitive Associative Classifier","year":2020,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","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":"University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Classifier (UML); Boosting (machine learning); Support vector machine; Associative property; Ensemble learning; Pruning; Random subspace method; Artificial neural network; Mathematics","score_opus":0.029867308262436644,"score_gpt":0.2990779282720294,"score_spread":0.2692106200095927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3039795743","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06195346,0.0006874821,0.9214003,0.00082982494,0.0005294902,0.00030503256,0.00045834368,0.004294555,0.009541527],"genre_scores_gemma":[0.48279253,0.00054993504,0.49012518,0.0009731516,0.00064797496,0.00046398735,0.0021195172,0.00035279215,0.021974972],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978115,0.0002804624,0.00012043617,0.00050587335,0.0010170845,0.00026453956],"domain_scores_gemma":[0.9973793,0.00067260617,0.000068119014,0.00046663173,0.0012387851,0.000174608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020329673,0.0009013798,0.002060853,0.0019608308,0.00161288,0.002568706,0.0030449487,0.0032320896,0.0075469553],"category_scores_gemma":[0.0054023736,0.00072144176,0.0012827775,0.0015710202,0.0007222046,0.0028101893,0.0024829602,0.0019577192,0.008541278],"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":[0.00047840463,0.0005808392,0.005186077,0.00018330372,0.00024634923,0.00044524754,0.00013631814,0.044085696,0.02594709,0.018604007,0.022488495,0.88161814],"study_design_scores_gemma":[0.00003736208,0.00019116754,0.0006114701,0.00002473881,0.00008716993,0.00031142775,0.00006237132,0.96321106,0.012824111,0.015517435,0.007096869,0.000024755733],"about_ca_topic_score_codex":0.0038364835,"about_ca_topic_score_gemma":0.005212732,"teacher_disagreement_score":0.0075469553,"about_ca_system_score_codex":0.00065495,"about_ca_system_score_gemma":0.0019170356,"threshold_uncertainty_score":0.025247097},"labels":[],"label_agreement":null},{"id":"W3040119961","doi":"10.1145/3394486.3403232","title":"CICLAD: A Fast and Memory-efficient Closed Itemset Miner for Streams","year":2020,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Data stream mining; Task (project management); Association rule learning; Resource (disambiguation); STREAMS; Data stream; Association (psychology)","score_opus":0.023321432597196597,"score_gpt":0.24481070477176015,"score_spread":0.22148927217456355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3040119961","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02940337,0.0017783638,0.93807405,0.00040755686,0.00020263651,0.0007033481,0.004525707,0.02327272,0.001632186],"genre_scores_gemma":[0.1027833,0.00057163945,0.8843419,0.00028937662,0.00007530534,0.0006599866,0.008312504,0.0004656306,0.0025003655],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99841547,0.00022475251,0.00021316981,0.00038168626,0.00065521366,0.00010970635],"domain_scores_gemma":[0.9964568,0.0016117187,0.00027944052,0.00056464254,0.00084382197,0.00024357827],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027029957,0.0011123975,0.0016221444,0.0026887998,0.0008631517,0.0016796389,0.003948168,0.0011286185,0.002350777],"category_scores_gemma":[0.010885706,0.0007926199,0.0010292209,0.0027251628,0.000504794,0.0025529189,0.0023733769,0.001736501,0.0019917672],"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":[0.0018420136,0.0006040303,0.019250806,0.0013354985,0.0006726298,0.0008019948,0.0005319293,0.045351624,0.024035348,0.0068425313,0.03698993,0.86174166],"study_design_scores_gemma":[0.00028559627,0.00032639544,0.0020699496,0.00007741932,0.000109795,0.00083039363,0.0001848852,0.9275908,0.0278121,0.009664402,0.030982472,0.000065772576],"about_ca_topic_score_codex":0.002811701,"about_ca_topic_score_gemma":0.005302694,"teacher_disagreement_score":0.003948168,"about_ca_system_score_codex":0.00060586433,"about_ca_system_score_gemma":0.0033430485,"threshold_uncertainty_score":0.014294982},"labels":[],"label_agreement":null},{"id":"W3040412430","doi":"10.1016/j.eswa.2020.113670","title":"Succinct contrast sets via false positive controlling with an application in clinical process redesign","year":2020,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Data Mining Algorithms 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":"Computer science; Contrast (vision); Process (computing); Machine learning; Artificial intelligence; Set (abstract data type); Decision tree; Outcome (game theory); Inference; Data mining; Big data","score_opus":0.024372856669884976,"score_gpt":0.3109844073328848,"score_spread":0.2866115506629998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3040412430","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00819667,0.00023137676,0.98905563,0.00030720717,0.00006815666,0.00011878426,0.00009427602,0.0014237475,0.00050411647],"genre_scores_gemma":[0.26697224,0.00021826138,0.72980523,0.00030018325,0.00016215663,0.00026486773,0.0002524861,0.00035565216,0.0016688948],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9890454,0.004355091,0.0006270512,0.0016981902,0.0038921966,0.0003821502],"domain_scores_gemma":[0.87915844,0.09836655,0.0047016996,0.009758891,0.007051548,0.00096287037],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01288887,0.0018760514,0.0020609049,0.0026617392,0.0010412744,0.0034690253,0.003832753,0.002423596,0.0035924963],"category_scores_gemma":[0.10047944,0.0011004442,0.0015714653,0.0017944888,0.0029330826,0.004602288,0.004241607,0.0050039934,0.00061670115],"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":[0.0030567134,0.0008210303,0.007032389,0.0004442176,0.0003091872,0.00097482465,0.00061207736,0.29315996,0.018806474,0.10544542,0.0050811106,0.5642566],"study_design_scores_gemma":[0.00012659517,0.00023776195,0.00051915355,0.000046521905,0.00009979065,0.00020091074,0.000031561776,0.93844134,0.012839179,0.04565941,0.00174762,0.000050174065],"about_ca_topic_score_codex":0.00295118,"about_ca_topic_score_gemma":0.0031087217,"teacher_disagreement_score":0.01288887,"about_ca_system_score_codex":0.001658395,"about_ca_system_score_gemma":0.0027577863,"threshold_uncertainty_score":0.06816363},"labels":[],"label_agreement":null},{"id":"W3040858639","doi":"10.24963/ijcai.2020/662","title":"Learning Optimal Decision Trees using Constraint Programming (Extended Abstract)","year":2020,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Polytechnique Montréal","funders":"","keywords":"Computer science; Constraint programming; Constraint (computer-aided design); Key (lock); Decision tree; Artificial intelligence; Machine learning; Greedy algorithm; Constraint satisfaction; Limit (mathematics); Incremental decision tree; Mathematical optimization; Decision tree learning; Mathematics; Algorithm; Stochastic programming","score_opus":0.040657323845968395,"score_gpt":0.29483478468103813,"score_spread":0.25417746083506976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3040858639","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0044004195,0.0003855047,0.9914665,0.0003720863,0.000056937293,0.00007267952,0.00036493075,0.0002049935,0.002675854],"genre_scores_gemma":[0.1390348,0.0010194273,0.85258234,0.00037366795,0.00018808979,0.00055973645,0.0017184842,0.00027349475,0.0042500496],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979139,0.00092019263,0.0001172268,0.00043239447,0.00043205093,0.00018428036],"domain_scores_gemma":[0.99265045,0.0059325686,0.0003361761,0.00033796794,0.00058951706,0.00015334887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023273495,0.0012157421,0.0016067268,0.0010158723,0.0006085163,0.0020885754,0.001292439,0.0011049632,0.010257603],"category_scores_gemma":[0.011855718,0.0006952679,0.0014569063,0.003976366,0.0010302735,0.0021653343,0.001461073,0.00274483,0.001465849],"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":[0.000118820935,0.00018124164,0.00077408494,0.00033314212,0.000095260846,0.00018823249,0.00007163671,0.7467562,0.0007495915,0.0884456,0.012946558,0.14933965],"study_design_scores_gemma":[0.000017500908,0.000017493181,0.000074498224,0.00002521318,0.000008368566,0.000025733672,0.0000104659275,0.9396485,0.0003892829,0.0581423,0.0016326803,0.000007912946],"about_ca_topic_score_codex":0.0076270723,"about_ca_topic_score_gemma":0.0074676485,"teacher_disagreement_score":0.010257603,"about_ca_system_score_codex":0.0012667321,"about_ca_system_score_gemma":0.0020834594,"threshold_uncertainty_score":0.03431511},"labels":[],"label_agreement":null},{"id":"W3047741057","doi":"10.1109/tits.2020.3012387","title":"Uncertain-Driven Analytics of Sequence Data in IoCV Environments","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Transportation Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pruning; Computer science; Data mining; Bridge (graph theory); Knowledge extraction; Analytics; The Internet; Sequence (biology); Machine learning; Artificial intelligence","score_opus":0.13140978047425353,"score_gpt":0.30998556756974727,"score_spread":0.17857578709549374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3047741057","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12585025,0.0004207752,0.8705759,0.00035588437,0.000023657423,0.00012717153,0.00068334944,0.00075019733,0.0012127662],"genre_scores_gemma":[0.80256665,0.00031245177,0.19436342,0.00010450832,0.000029317167,0.000116955955,0.0017974022,0.000042566262,0.00066679454],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983613,0.00033100534,0.00016029945,0.00042928022,0.00057679816,0.00014132042],"domain_scores_gemma":[0.9962859,0.0022513699,0.0004643556,0.0003167325,0.0005270372,0.0001545428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015075074,0.0006572301,0.000892898,0.001797557,0.0007092776,0.0011985137,0.0013503104,0.0006777511,0.0005965812],"category_scores_gemma":[0.007660765,0.00033714302,0.0006749948,0.0023693962,0.0006334595,0.0019262816,0.0014621587,0.0009038734,0.0001760446],"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":[0.0005418379,0.00021014655,0.02034921,0.00034500516,0.0001267164,0.0010123646,0.0006570272,0.70848936,0.007067731,0.022272417,0.0019878857,0.23694038],"study_design_scores_gemma":[0.000005564322,0.000036863974,0.000637766,0.0000083964205,0.000007391739,0.000082883285,0.000087513996,0.984029,0.0015962801,0.013006783,0.0004964771,0.0000051223547],"about_ca_topic_score_codex":0.0044992194,"about_ca_topic_score_gemma":0.0050081406,"teacher_disagreement_score":0.0044992194,"about_ca_system_score_codex":0.00070240966,"about_ca_system_score_gemma":0.001421227,"threshold_uncertainty_score":0.008946061},"labels":[],"label_agreement":null},{"id":"W305941236","doi":"10.1007/978-0-387-36795-8_12","title":"Supervised Learning: Decision Trees, Rule Algorithms, and Their Hybrids","year":2007,"lang":"en","type":"book-chapter","venue":"","topic":"Data Mining Algorithms 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":"Decision tree; Computer science; Artificial intelligence; Machine learning; Hybrid; Decision tree learning; ID3 algorithm; Algorithm; Incremental decision tree; Biology; Botany","score_opus":0.03203105339597353,"score_gpt":0.25828734287988353,"score_spread":0.22625628948391,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W305941236","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028274823,0.11556063,0.84843737,0.00290037,0.0010117466,0.00006745366,0.00043382475,0.0009996361,0.027761547],"genre_scores_gemma":[0.075631544,0.090823285,0.80440044,0.0018090991,0.0032035485,0.00044874358,0.0011134546,0.0003650414,0.0222048],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99768794,0.00086443644,0.00014502765,0.0003370769,0.00090860866,0.000056952784],"domain_scores_gemma":[0.99373746,0.0050596716,0.0002145885,0.0004276223,0.0004531917,0.00010751258],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026312873,0.0012508507,0.002066646,0.0020644276,0.00045918114,0.004950569,0.0022376326,0.001969221,0.004797434],"category_scores_gemma":[0.0098356595,0.0007687635,0.00086009916,0.0061424915,0.002421264,0.006776475,0.0016090078,0.0033283783,0.0038070723],"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":[0.000056247685,0.00011636611,0.00066189346,0.0010451578,0.00010479468,0.000055945107,0.00022656277,0.013381458,0.00056692166,0.26205882,0.042477265,0.67924845],"study_design_scores_gemma":[0.000018423638,0.00004649515,0.0003713475,0.00025841987,0.000025715168,0.00019512509,0.000087570465,0.050310962,0.00047090376,0.8892458,0.05893441,0.00003479819],"about_ca_topic_score_codex":0.0007969266,"about_ca_topic_score_gemma":0.0011396175,"teacher_disagreement_score":0.004950569,"about_ca_system_score_codex":0.0005831837,"about_ca_system_score_gemma":0.0009701054,"threshold_uncertainty_score":0.016049027},"labels":[],"label_agreement":null},{"id":"W30673375","doi":"10.1094/pdis-10-17-1602-re","title":"An Empirical Comparison of Methods for Iceberg-CUBE Construction","year":2001,"lang":"en","type":"article","venue":"The Florida AI Research Society","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"National Natural Science Foundation of China","keywords":"Pruning; Cube (algebra); Top-down and bottom-up design; Iceberg; Aggregate (composite); Computer science; Set (abstract data type); Function (biology); Data mining; Algorithm; Data cube; Mathematics; Geology; Combinatorics","score_opus":0.21824721765232694,"score_gpt":0.5633181396275331,"score_spread":0.34507092197520617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W30673375","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015858814,0.0010485277,0.94718325,0.00027148082,0.00029254082,0.00061860774,0.00063810294,0.003985974,0.030102769],"genre_scores_gemma":[0.06515744,0.0009936149,0.91719395,0.00012588342,0.000063730586,0.00062450534,0.0017980068,0.0015011939,0.0125417905],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950111,0.0013738839,0.0004136144,0.00075257284,0.0021510106,0.00029795023],"domain_scores_gemma":[0.98871803,0.0047283983,0.00047377736,0.003537169,0.0022837876,0.0002588723],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050505823,0.00093464064,0.00065401685,0.0015324164,0.0007824826,0.0019629474,0.00229534,0.00089946185,0.026705112],"category_scores_gemma":[0.017623095,0.00051993487,0.0010873548,0.0022796374,0.00089801254,0.002850235,0.0027264473,0.0013497518,0.009900097],"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":[0.00044705367,0.0002454404,0.0036409376,0.0005504017,0.000061170795,0.00008257572,0.0004917056,0.013038319,0.010928057,0.053241357,0.008996967,0.9082761],"study_design_scores_gemma":[0.000278244,0.0014514483,0.013255502,0.00059954036,0.00018653553,0.0017882914,0.001500206,0.27774253,0.063667975,0.085422836,0.5538789,0.0002279717],"about_ca_topic_score_codex":0.0026269099,"about_ca_topic_score_gemma":0.0036226544,"teacher_disagreement_score":0.026705112,"about_ca_system_score_codex":0.0013182377,"about_ca_system_score_gemma":0.0018739313,"threshold_uncertainty_score":0.08933753},"labels":[],"label_agreement":null},{"id":"W3081119885","doi":"10.1109/access.2020.3019480","title":"A Novel Framework for Recommending Data Mining Algorithm in Dynamic IoT Environment","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Deanship of Scientific Research, King Saud University","keywords":"Computer science; Flexibility (engineering); Domain (mathematical analysis); Data mining; Process (computing); Volume (thermodynamics); Task (project management); Internet of Things; Machine learning; Domain knowledge; Artificial intelligence; Algorithm","score_opus":0.1513563457544865,"score_gpt":0.37178541881466026,"score_spread":0.22042907306017376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3081119885","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034338492,0.0005800514,0.9935557,0.0002550899,0.000064186526,0.00014050586,0.00017189757,0.0007420294,0.0010567884],"genre_scores_gemma":[0.13617332,0.001047283,0.85727173,0.00033094542,0.00024018988,0.000530517,0.0012175579,0.00010373362,0.0030847078],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99784434,0.00036480394,0.00020870131,0.000669711,0.00073420076,0.0001782735],"domain_scores_gemma":[0.9986903,0.00037845914,0.0001266116,0.00013105056,0.00058843795,0.00008520306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021557792,0.001042316,0.0015337433,0.0032559806,0.0011060991,0.0017822805,0.0031195516,0.0014762826,0.0016733283],"category_scores_gemma":[0.004690779,0.00048543568,0.0011972596,0.003419022,0.0005510051,0.0026614543,0.0013261555,0.0014026018,0.0008183799],"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":[0.00018984322,0.00046525773,0.006926937,0.00037193132,0.00023257751,0.00035451326,0.00034725686,0.25988692,0.004578952,0.03699007,0.016736792,0.67291903],"study_design_scores_gemma":[0.000020820342,0.00005015585,0.00040074295,0.000019112253,0.000027069234,0.00012384557,0.000045332305,0.9847425,0.00087962864,0.008267039,0.005406394,0.000017255648],"about_ca_topic_score_codex":0.01817703,"about_ca_topic_score_gemma":0.018544061,"teacher_disagreement_score":0.01817703,"about_ca_system_score_codex":0.0012524609,"about_ca_system_score_gemma":0.0030278594,"threshold_uncertainty_score":0.03614247},"labels":[],"label_agreement":null},{"id":"W3083699309","doi":"10.1007/978-3-030-55789-8_74","title":"Efficient Mining of Pareto-Front High Expected Utility Patterns","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms 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":"Brandon University","funders":"","keywords":"Computer science; Convergence (economics); Set (abstract data type); Data mining; Mathematical optimization; Multi-objective optimization; Pareto optimal; Pareto principle; Machine learning; Mathematics","score_opus":0.02182699020125378,"score_gpt":0.24341930406334686,"score_spread":0.22159231386209308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3083699309","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.170073,0.0012516243,0.82035136,0.0007705307,0.00006169206,0.00019496359,0.00164516,0.0008825012,0.0047690463],"genre_scores_gemma":[0.72591764,0.0006156943,0.2619918,0.00023203566,0.00013931934,0.00020848573,0.004524767,0.0001537276,0.006216522],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984835,0.00037151438,0.00010745272,0.00028916137,0.0005311451,0.00021730298],"domain_scores_gemma":[0.99314284,0.004979036,0.0003940455,0.0005079951,0.0007971777,0.00017900947],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001924493,0.00081940443,0.0015950196,0.0030758858,0.0007688133,0.0021413402,0.0020362225,0.0012538723,0.0025170972],"category_scores_gemma":[0.012038191,0.0006349319,0.0015491629,0.0029483205,0.00060810894,0.00197765,0.0014904715,0.0013383764,0.00080907485],"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":[0.00074306084,0.00091905,0.028658187,0.0006740117,0.0004125219,0.0008666648,0.00038977645,0.30802926,0.0052999207,0.052119818,0.015605593,0.5862821],"study_design_scores_gemma":[0.000032031356,0.00008002209,0.001754362,0.000046860365,0.000036405763,0.00021210469,0.00008579216,0.93696845,0.0012607642,0.058481492,0.0010305772,0.000011118737],"about_ca_topic_score_codex":0.0014909251,"about_ca_topic_score_gemma":0.0026973113,"teacher_disagreement_score":0.0030758858,"about_ca_system_score_codex":0.0008024429,"about_ca_system_score_gemma":0.0013571854,"threshold_uncertainty_score":0.010177851},"labels":[],"label_agreement":null},{"id":"W3085986812","doi":"10.1007/978-981-15-8731-3_8","title":"Vertical Data Mining from Relational Data and Its Application to COVID-19 Data","year":2020,"lang":"en","type":"book-chapter","venue":"Advances in intelligent systems and computing","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":32,"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 British Columbia; University of Manitoba; University of Waterloo","funders":"","keywords":"Big data; Computer science; Data science; Knowledge extraction; Data mining; Coronavirus disease 2019 (COVID-19); Realm; Data stream mining; Relational database; Geography; Infectious disease (medical specialty); Disease","score_opus":0.1255932487070626,"score_gpt":0.35182215214343737,"score_spread":0.22622890343637478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3085986812","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026694406,0.004370145,0.9433967,0.0015056948,0.0004064839,0.00020332813,0.0045732516,0.004269994,0.014580027],"genre_scores_gemma":[0.10599906,0.0031709033,0.8681208,0.00022678515,0.00023269274,0.00018088754,0.009966825,0.0006142315,0.011487829],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99869627,0.00021389413,0.000137487,0.00019772824,0.000680871,0.00007374662],"domain_scores_gemma":[0.99768543,0.001195194,0.00017019708,0.0003610237,0.0005010482,0.00008702778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015908949,0.0004781277,0.0005444846,0.0029804136,0.0009220422,0.0026143293,0.0012289399,0.0005127848,0.0047290623],"category_scores_gemma":[0.006617982,0.00050278817,0.0010769212,0.007673685,0.0005248817,0.0020944243,0.0016845986,0.0012679464,0.002152278],"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":[0.00012080124,0.0001670713,0.009742754,0.00054538465,0.00009504042,0.00042553176,0.0006066791,0.012938805,0.0072661634,0.13282101,0.041007794,0.794263],"study_design_scores_gemma":[0.000026133248,0.000115983115,0.009098902,0.000298197,0.00010422193,0.0016093351,0.0008378545,0.6220398,0.017082904,0.18584366,0.16285968,0.000083322135],"about_ca_topic_score_codex":0.0069305147,"about_ca_topic_score_gemma":0.0074520013,"teacher_disagreement_score":0.0069305147,"about_ca_system_score_codex":0.0007378925,"about_ca_system_score_gemma":0.0012451083,"threshold_uncertainty_score":0.015820265},"labels":[],"label_agreement":null},{"id":"W3093794502","doi":"10.1177/1550147720962999","title":"DARE: A decentralized association rules extraction scheme for embedded data sets in distributed IoT devices","year":2020,"lang":"en","type":"article","venue":"International Journal of Distributed Sensor Networks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"Samsung; Fundação de Amparo à Pesquisa do Estado do Amazonas; Natural Sciences and Engineering Research Council of Canada; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Computer science; Associative property; Internet of Things; Association rule learning; Context (archaeology); Distributed computing; Lift (data mining); Single point of failure; Scheme (mathematics); Artificial intelligence; Data mining; Embedded system","score_opus":0.04436811882283155,"score_gpt":0.33277905809152575,"score_spread":0.2884109392686942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093794502","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016893098,0.0003807223,0.9746051,0.00025546353,0.00006188128,0.00033779183,0.0018287563,0.0046735485,0.0009637705],"genre_scores_gemma":[0.269253,0.0003447954,0.7208266,0.00032613144,0.0000926265,0.0006766997,0.0057244757,0.0001319272,0.0026238533],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974273,0.0003745433,0.0004200859,0.00068783294,0.0009531936,0.00013699812],"domain_scores_gemma":[0.99590623,0.0015329705,0.0005160018,0.0012744862,0.0006336226,0.00013674812],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002820945,0.0007829749,0.0016116312,0.0037630678,0.0009990537,0.0014870487,0.0020400155,0.00092852954,0.0018473988],"category_scores_gemma":[0.009660563,0.00052375696,0.0012303507,0.003282479,0.00047158147,0.0026868633,0.0024791816,0.0013682559,0.0013856653],"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":[0.0006779582,0.0006947838,0.0146845095,0.0004359193,0.00042233666,0.0009497411,0.00040687286,0.06108459,0.014666532,0.013824425,0.01501784,0.8771345],"study_design_scores_gemma":[0.00011120518,0.00017145851,0.0042678015,0.00005685224,0.00010754145,0.0009826999,0.00020709989,0.93422955,0.012869781,0.030085867,0.016849473,0.000060591203],"about_ca_topic_score_codex":0.0015669038,"about_ca_topic_score_gemma":0.004500988,"teacher_disagreement_score":0.0037630678,"about_ca_system_score_codex":0.00056501897,"about_ca_system_score_gemma":0.001642998,"threshold_uncertainty_score":0.014918745},"labels":[],"label_agreement":null},{"id":"W3095661913","doi":"10.1007/978-3-030-62466-8_32","title":"Reasoning Engine for Support Maintenance","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thales (Canada)","funders":"","keywords":"Computer science; Broadcasting (networking); Cluster analysis; Pipeline (software); Representation (politics); Artificial intelligence; Data mining; Machine learning; Information retrieval; Programming language; Computer security","score_opus":0.0175610983378918,"score_gpt":0.2502699543932576,"score_spread":0.23270885605536581,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095661913","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0066073476,0.00076886587,0.929994,0.0007107945,0.0002821737,0.0003339518,0.0034044746,0.043025658,0.014872736],"genre_scores_gemma":[0.081302285,0.00047632083,0.8919352,0.0005453161,0.00013032944,0.00019678651,0.007664143,0.0013874284,0.016362142],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99875116,0.000158858,0.00014582023,0.0003057796,0.0005373267,0.00010101452],"domain_scores_gemma":[0.99807537,0.00076018675,0.000088948094,0.0006232119,0.0003849051,0.00006736178],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016439353,0.001185539,0.0009838641,0.0022049525,0.00075536926,0.0029618458,0.0038189287,0.0015828474,0.02015925],"category_scores_gemma":[0.00536013,0.00078814797,0.0018303083,0.0015895156,0.00060978567,0.0043715355,0.0017611335,0.0020027538,0.008523847],"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":[0.00061649334,0.0004172935,0.001189487,0.0008355302,0.00019985085,0.00047703428,0.0002533266,0.019765178,0.014242462,0.09748907,0.06937056,0.7951437],"study_design_scores_gemma":[0.00022517548,0.00017242934,0.00075878104,0.00028534207,0.0005953595,0.00088429305,0.00014445987,0.572243,0.05694675,0.21272963,0.15491275,0.000102031416],"about_ca_topic_score_codex":0.004225564,"about_ca_topic_score_gemma":0.004872751,"teacher_disagreement_score":0.02015925,"about_ca_system_score_codex":0.0008366553,"about_ca_system_score_gemma":0.0016895216,"threshold_uncertainty_score":0.06743938},"labels":[],"label_agreement":null},{"id":"W3099551741","doi":"10.1002/ett.4168","title":"Mining large‐scale high utility patterns in vehicular ad hoc network environments","year":2020,"lang":"en","type":"article","venue":"Transactions on Emerging Telecommunications Technologies","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Computer science; Vehicular ad hoc network; Wireless ad hoc network; Pruning; Mobile ad hoc network; Set (abstract data type); Big data; Distributed computing; Data mining; Computer network; Wireless","score_opus":0.021063114544044383,"score_gpt":0.2487440567049216,"score_spread":0.22768094216087723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3099551741","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54438627,0.00065214885,0.45115292,0.00045584305,0.00010512448,0.0002035639,0.00084303634,0.0007417535,0.0014593859],"genre_scores_gemma":[0.93010783,0.00019224349,0.06774462,0.000038423183,0.00002252282,0.000051067673,0.0011778622,0.00001997776,0.0006455429],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989465,0.00023906,0.00011266557,0.00022236076,0.00031657738,0.00016296895],"domain_scores_gemma":[0.9983347,0.00062452495,0.0002484834,0.00023844196,0.00038872403,0.0001651625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010454237,0.0007090086,0.0006708666,0.0027166412,0.0009238295,0.0011816708,0.0015149747,0.0005251239,0.00026826252],"category_scores_gemma":[0.0028829146,0.00042602426,0.0005658053,0.0032299322,0.00040168106,0.0011550515,0.0009640841,0.00042299205,0.00014226517],"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":[0.00053560064,0.0005789145,0.10559544,0.0003697742,0.00048313086,0.003682476,0.000532548,0.65194356,0.010937706,0.007879577,0.0060347896,0.21142644],"study_design_scores_gemma":[0.000011864645,0.00006691009,0.0062095253,0.000010769389,0.000025833779,0.00024990924,0.0006147673,0.9818055,0.0027350131,0.006910951,0.001347888,0.000011047343],"about_ca_topic_score_codex":0.004959317,"about_ca_topic_score_gemma":0.007526838,"teacher_disagreement_score":0.004959317,"about_ca_system_score_codex":0.0004204692,"about_ca_system_score_gemma":0.0008247882,"threshold_uncertainty_score":0.009860873},"labels":[],"label_agreement":null},{"id":"W3102733678","doi":"10.1061/9780784482865.054","title":"Using Model Trees to Represent Knowhow of Experienced Estimators in Steel Fabrication Industry","year":2020,"lang":"en","type":"article","venue":"Construction Research Congress 2020","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Estimator; Computer science; Mainstream; Representation (politics); Machine learning; Artificial intelligence; Data modeling; Domain (mathematical analysis); Data mining; Industrial engineering; Engineering; Software engineering; Mathematics; Statistics","score_opus":0.1890323658611402,"score_gpt":0.42232774559156677,"score_spread":0.23329537973042658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3102733678","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1007048,0.00017689324,0.8944908,0.0005455663,0.00002407847,0.00005846508,0.00030373633,0.0002945648,0.0034011311],"genre_scores_gemma":[0.7631953,0.00021919742,0.23415595,0.00011823303,0.00001773948,0.00011470888,0.0006609708,0.000057396875,0.0014604894],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983284,0.00088437827,0.000097147225,0.0003114664,0.0002718856,0.00010670003],"domain_scores_gemma":[0.98636615,0.010246557,0.0010374828,0.0013145376,0.00089015317,0.0001452204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029169593,0.00043991714,0.00043010237,0.0014091678,0.00061726006,0.0022164285,0.0010491058,0.0011146644,0.0019524717],"category_scores_gemma":[0.022879807,0.00034503752,0.0007401747,0.0015588038,0.00092270353,0.0047548707,0.0012543944,0.0014220313,0.00039371502],"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":[0.00037766361,0.00029653576,0.025667109,0.00025470072,0.000118308766,0.00046248533,0.0048589306,0.4996827,0.0031277987,0.18513662,0.002921267,0.27709594],"study_design_scores_gemma":[0.000014412466,0.00007743629,0.0026198397,0.00007170674,0.000028723603,0.00009407569,0.00054363813,0.84577465,0.0020720775,0.14367242,0.0049969587,0.00003399192],"about_ca_topic_score_codex":0.008522642,"about_ca_topic_score_gemma":0.012479135,"teacher_disagreement_score":0.008522642,"about_ca_system_score_codex":0.0014776144,"about_ca_system_score_gemma":0.0013608432,"threshold_uncertainty_score":0.016946018},"labels":[],"label_agreement":null},{"id":"W3107682410","doi":"10.18280/isi.250512","title":"Resource Classification and Knowledge Aggregation of Library and Information Based on Data Mining","year":2020,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Resource (disambiguation); Service (business); Big data; Support vector machine; Data mining; Knowledge extraction; Information retrieval; Data science; Database; Machine learning","score_opus":0.03629407125495823,"score_gpt":0.24194317847195482,"score_spread":0.20564910721699659,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3107682410","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26060972,0.001207665,0.72457904,0.0013786167,0.00012118511,0.00053354516,0.0013144695,0.0009235447,0.009332209],"genre_scores_gemma":[0.9021649,0.00048429577,0.094239,0.00009886377,0.00006482599,0.000186162,0.0011472341,0.000027125743,0.0015874715],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980173,0.00033525022,0.00022466567,0.0005016632,0.0007091442,0.00021194822],"domain_scores_gemma":[0.99752146,0.000915346,0.00043182744,0.0003680918,0.00063622405,0.00012713987],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014483767,0.0006740768,0.0009591239,0.0060051293,0.0011778538,0.0025991362,0.0013897544,0.00069248164,0.000696233],"category_scores_gemma":[0.007159799,0.0002983513,0.0011439115,0.0068798442,0.00071636244,0.004550237,0.0014002483,0.00076299085,0.00022981522],"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":[0.0003936279,0.0006078962,0.09571331,0.0005889707,0.00050142617,0.00096846087,0.0013780458,0.30590484,0.003704391,0.041867077,0.008063098,0.54030895],"study_design_scores_gemma":[0.000006679152,0.000034742166,0.007951514,0.000040313993,0.000081791884,0.00010375814,0.00037725933,0.9694789,0.0019453577,0.017621666,0.0023347286,0.000023402436],"about_ca_topic_score_codex":0.026654493,"about_ca_topic_score_gemma":0.016502602,"teacher_disagreement_score":0.026654493,"about_ca_system_score_codex":0.0030921383,"about_ca_system_score_gemma":0.0019905516,"threshold_uncertainty_score":0.052998662},"labels":[],"label_agreement":null},{"id":"W3108361835","doi":"10.4018/978-1-7998-3473-1.ch125","title":"Big Data Analytics and Mining for Knowledge Discovery","year":2020,"lang":"en","type":"book-chapter","venue":"Advances in logistics, operations, and management science book series","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Big data; Computer science; Data science; Knowledge extraction; Analytics; Variety (cybernetics); Data mining; Data analysis; Artificial intelligence","score_opus":0.08380328567767632,"score_gpt":0.311709269629538,"score_spread":0.22790598395186168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3108361835","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019280273,0.27356046,0.35731652,0.02505437,0.009648438,0.0006824273,0.005347142,0.0060221725,0.32044044],"genre_scores_gemma":[0.028353965,0.2815626,0.4102487,0.012668415,0.009278833,0.0011746957,0.01156754,0.002551622,0.2425936],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977763,0.0003880695,0.00014061884,0.0003828896,0.001217105,0.00009494769],"domain_scores_gemma":[0.99754274,0.0014704874,0.00012134529,0.00041986295,0.0003277986,0.00011781148],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001800147,0.0021503558,0.0015149789,0.0039340034,0.0011539118,0.0077557242,0.002532714,0.0023572226,0.032912705],"category_scores_gemma":[0.00458136,0.00097477034,0.0011797161,0.008286914,0.0025643688,0.0103021,0.0037288317,0.0039550276,0.024216024],"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":[0.000037468923,0.000048253998,0.00028259718,0.0025033776,0.00010438162,0.00017337578,0.00042686326,0.0024218406,0.0008926948,0.34796062,0.36828658,0.27686197],"study_design_scores_gemma":[0.0000075208,0.000014774639,0.00024069806,0.00064981816,0.000013087506,0.00023565502,0.00010964746,0.0024210967,0.0003071824,0.18328005,0.8126983,0.000022220389],"about_ca_topic_score_codex":0.0012800815,"about_ca_topic_score_gemma":0.0016800386,"teacher_disagreement_score":0.032912705,"about_ca_system_score_codex":0.0016637421,"about_ca_system_score_gemma":0.0027547928,"threshold_uncertainty_score":0.110103965},"labels":[],"label_agreement":null},{"id":"W3108900336","doi":"10.1007/978-3-030-63119-2_65","title":"Textual Clustering: Towards a More Efficient Descriptors of Texts","year":2020,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Data Mining Algorithms and Applications","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":"Université du Québec à Trois-Rivières","funders":"","keywords":"Cluster analysis; Hierarchical clustering; Computer science; Medoid; Artificial intelligence; Data mining; Artificial neural network; Document clustering; Pattern recognition (psychology); Brown clustering; Information retrieval; Correlation clustering; Canopy clustering algorithm","score_opus":0.04596565457403039,"score_gpt":0.2916378477862309,"score_spread":0.24567219321220052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3108900336","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010972049,0.0016507368,0.9732107,0.00037291268,0.00029233025,0.00019811165,0.004857679,0.0048999568,0.0035455497],"genre_scores_gemma":[0.04840528,0.0015320365,0.9137632,0.00023688647,0.00042441016,0.00038411326,0.014768678,0.001152681,0.019332662],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871266,0.00019025902,0.0001285128,0.00037760253,0.0005061327,0.000084871404],"domain_scores_gemma":[0.998028,0.00045250612,0.00016883604,0.00054599374,0.0006898848,0.0001147779],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008535432,0.0011483725,0.0013765292,0.0056690183,0.0008802644,0.0023049025,0.002451598,0.0011141638,0.009847592],"category_scores_gemma":[0.003915785,0.0004572754,0.0012289538,0.008366591,0.0006324499,0.0029869098,0.001697994,0.0012017036,0.009248912],"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":[0.00029600688,0.00014223691,0.0011731384,0.000644993,0.00009795332,0.00007229515,0.00024723395,0.008277894,0.041296273,0.023878932,0.041856974,0.88201606],"study_design_scores_gemma":[0.000113946015,0.00037634562,0.007583918,0.00029722878,0.00032240077,0.0012177064,0.0006488106,0.59365606,0.092531584,0.09710136,0.20596965,0.00018106286],"about_ca_topic_score_codex":0.003466799,"about_ca_topic_score_gemma":0.0041249692,"teacher_disagreement_score":0.009847592,"about_ca_system_score_codex":0.0009248882,"about_ca_system_score_gemma":0.0014113367,"threshold_uncertainty_score":0.032943428},"labels":[],"label_agreement":null},{"id":"W3111577069","doi":"10.1016/j.ins.2020.12.004","title":"Fuzzy high-utility pattern mining in parallel and distributed Hadoop framework","year":2020,"lang":"en","type":"article","venue":"Information Sciences","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Computer science; Data mining; Fuzzy logic; Pruning; Set (abstract data type); Big data; Fuzzy set; Machine learning; Artificial intelligence","score_opus":0.03556424353895083,"score_gpt":0.27385815901749677,"score_spread":0.23829391547854595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111577069","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0679172,0.0003825899,0.9264825,0.0002986688,0.000053636177,0.00026552327,0.0006968944,0.0025038475,0.0013990647],"genre_scores_gemma":[0.4464618,0.00023257639,0.54988873,0.00011142729,0.000040349478,0.0002187651,0.0013551967,0.00006799997,0.0016231473],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985905,0.00021746312,0.00014571531,0.0003732351,0.00049785734,0.00017518118],"domain_scores_gemma":[0.9981997,0.0005044434,0.00015689676,0.00040009778,0.0005868904,0.00015191663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016047255,0.00067337725,0.0011593208,0.0021429483,0.0013595963,0.0013881002,0.0026645001,0.0005909252,0.000675163],"category_scores_gemma":[0.0039005508,0.00041033403,0.0012219545,0.002612619,0.0005645187,0.001689643,0.0011155577,0.0006955757,0.00031537976],"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":[0.0010403869,0.0006311845,0.02391262,0.0005642275,0.00053010334,0.0017654842,0.0006751,0.31488875,0.016048461,0.027314376,0.012869724,0.59975946],"study_design_scores_gemma":[0.00003988804,0.00006279701,0.0014790697,0.0000119000315,0.00003959783,0.0003979926,0.00016226781,0.9618399,0.004807401,0.028952878,0.0021866038,0.000019679577],"about_ca_topic_score_codex":0.006534601,"about_ca_topic_score_gemma":0.007154018,"teacher_disagreement_score":0.006534601,"about_ca_system_score_codex":0.00079711236,"about_ca_system_score_gemma":0.002397284,"threshold_uncertainty_score":0.012993157},"labels":[],"label_agreement":null},{"id":"W3118013975","doi":"10.3233/ida-194719","title":"Uni- and multivariate probability density models for numeric subgroup discovery","year":2020,"lang":"en","type":"article","venue":"Intelligent Data Analysis","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Univariate; Kernel density estimation; Multivariate statistics; Curse of dimensionality; Exploratory data analysis; Variance (accounting); Computer science; Statistics; Data mining; Mathematics; Artificial intelligence; Pattern recognition (psychology); Estimator","score_opus":0.12566072815947738,"score_gpt":0.3117743928853609,"score_spread":0.18611366472588353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3118013975","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042810314,0.00044089192,0.99350387,0.0003255424,0.000033391505,0.00006155171,0.0002978208,0.00028654316,0.00076945254],"genre_scores_gemma":[0.4738481,0.002249504,0.5112156,0.00051904947,0.0005052999,0.0010864044,0.0023888375,0.000267856,0.007919258],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99500185,0.0025799028,0.00023597923,0.0009285064,0.0009442438,0.00030950567],"domain_scores_gemma":[0.9778335,0.016050525,0.0016046594,0.0027143974,0.0014098368,0.00038695254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009522427,0.0010907027,0.0019854682,0.003830418,0.0008647166,0.002747174,0.0037944682,0.0019342896,0.0048689186],"category_scores_gemma":[0.035146132,0.00074826076,0.002774577,0.0045653856,0.0018847183,0.0048011485,0.0029252751,0.0037989065,0.00170544],"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":[0.00023987943,0.00021163956,0.01101993,0.00025129225,0.00034516095,0.00022334777,0.00050673384,0.3161451,0.00062795,0.5246367,0.006448483,0.1393438],"study_design_scores_gemma":[0.000010657191,0.000020171363,0.0006407356,0.000025743775,0.000027431402,0.000056718654,0.00003938352,0.7990014,0.00014043089,0.19775067,0.0022657472,0.000020830235],"about_ca_topic_score_codex":0.006127077,"about_ca_topic_score_gemma":0.0046510794,"teacher_disagreement_score":0.009522427,"about_ca_system_score_codex":0.0021040577,"about_ca_system_score_gemma":0.0017405959,"threshold_uncertainty_score":0.050359964},"labels":[],"label_agreement":null},{"id":"W3119260152","doi":"10.1145/3430767","title":"RHUPS","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Intelligent Systems and Technology","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Research Foundation of Korea","keywords":"Computer science; Scalability; Data mining; Database; Sliding window protocol; Data stream; Data stream mining; Window (computing)","score_opus":0.02132961777939066,"score_gpt":0.2588025962539239,"score_spread":0.23747297847453322,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3119260152","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005295831,0.00334356,0.035356738,0.0033745805,0.004494719,0.0008676498,0.036295786,0.027045364,0.88392574],"genre_scores_gemma":[0.040348265,0.0034221068,0.032432683,0.0028209935,0.0011585879,0.00061775674,0.065269046,0.0073998403,0.84653074],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980703,0.00021227018,0.00017703375,0.00049866445,0.00078104995,0.00026059378],"domain_scores_gemma":[0.99755436,0.00025690027,0.000115681,0.0008813016,0.000870501,0.0003213257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012837773,0.0017167708,0.0011890212,0.0034600925,0.0021668803,0.006512354,0.002892432,0.0021465651,0.5993523],"category_scores_gemma":[0.0049475795,0.00076883304,0.0010578859,0.003178411,0.00071975385,0.0053543826,0.004761909,0.0016921463,0.5273242],"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":[0.00041381636,0.00014194447,0.0017146734,0.0007822307,0.000044376517,0.00050749833,0.0003074004,0.0006505026,0.0043675075,0.024976509,0.5994761,0.36661744],"study_design_scores_gemma":[0.000024450625,0.000031683794,0.0005327868,0.00009555267,0.00001354579,0.0003081103,0.000105730054,0.0005329906,0.0015824104,0.0035887589,0.9931645,0.000019489018],"about_ca_topic_score_codex":0.0030555164,"about_ca_topic_score_gemma":0.0030552999,"teacher_disagreement_score":0.5993523,"about_ca_system_score_codex":0.0012500784,"about_ca_system_score_gemma":0.0022046356,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W3120721672","doi":"10.1007/s10489-020-02080-w","title":"Linguistic frequent pattern mining using a compressed structure","year":2021,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Computer science; Data mining; Pruning; Cardinality (data modeling); Fuzzy set; Fuzzy logic; Association rule learning; Membership function; Fuzzy set operations; Type-2 fuzzy sets and systems; Scalability; Fuzzy number; Set (abstract data type); Artificial intelligence; Machine learning; Database","score_opus":0.036761156958239546,"score_gpt":0.2832517477305869,"score_spread":0.24649059077234736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3120721672","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1742048,0.0007343829,0.8053026,0.001543096,0.0002590011,0.0005161001,0.008742009,0.004378377,0.0043196157],"genre_scores_gemma":[0.40695915,0.0004904162,0.5747086,0.00028137388,0.0002736204,0.00054891733,0.013293101,0.0001735865,0.0032712426],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989398,0.00016050324,0.00012322771,0.00016974476,0.00051925593,0.000087469736],"domain_scores_gemma":[0.9953615,0.0018170094,0.00033693388,0.0012407518,0.001100444,0.00014334242],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006075531,0.00039845138,0.0008933388,0.0037515496,0.00089583325,0.0015132206,0.0010588453,0.0007192468,0.0051889447],"category_scores_gemma":[0.008534431,0.00039762567,0.0008649247,0.0046939347,0.0006058447,0.0026286293,0.0015763412,0.0011667485,0.0013816529],"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":[0.0015153695,0.0006510336,0.0068656765,0.00038392487,0.00017321362,0.0017781692,0.00062151393,0.04310531,0.035023473,0.045111354,0.01765638,0.8471147],"study_design_scores_gemma":[0.00019714642,0.00047979306,0.0030143573,0.00010263564,0.00014339863,0.0019720716,0.00037201674,0.8700729,0.014635486,0.09406925,0.014878562,0.00006240847],"about_ca_topic_score_codex":0.003227676,"about_ca_topic_score_gemma":0.0041747023,"teacher_disagreement_score":0.0051889447,"about_ca_system_score_codex":0.00057578465,"about_ca_system_score_gemma":0.0021739905,"threshold_uncertainty_score":0.01735872},"labels":[],"label_agreement":null},{"id":"W3127845768","doi":"10.17762/itii.v7i2.65","title":"NUCLEAR: An Efficient Methods for Mining Frequent Itemsets and Generators from Closed Frequent Itemsets","year":2021,"lang":"en","type":"article","venue":"INFORMATION TECHNOLOGY IN INDUSTRY","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Data mining; Computer science","score_opus":0.019480346737023476,"score_gpt":0.32090403505765924,"score_spread":0.30142368832063576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127845768","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004676538,0.00066032074,0.9907274,0.00015632117,0.000047806112,0.00027253566,0.0007363622,0.002107498,0.0006151562],"genre_scores_gemma":[0.042594362,0.0006254254,0.9517072,0.000120550736,0.00008732837,0.0005729345,0.0030293353,0.00014454505,0.0011184495],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99713033,0.00074317935,0.00039689566,0.0005617031,0.0010355118,0.00013235361],"domain_scores_gemma":[0.9949352,0.0030270175,0.00042659178,0.0005852593,0.0008886799,0.00013719042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00303076,0.001704987,0.0016756201,0.0073754685,0.0010572023,0.0015383895,0.0023343163,0.0011272765,0.00319003],"category_scores_gemma":[0.011709089,0.00069540145,0.0018523284,0.005026625,0.00074405735,0.0038351677,0.0015727362,0.0014995422,0.0021032928],"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":[0.0002948815,0.00022468879,0.0036074119,0.00084387645,0.00022619031,0.00040266063,0.00027978548,0.036736537,0.006317713,0.02339985,0.012911544,0.9147549],"study_design_scores_gemma":[0.00019359776,0.00037689408,0.0019823804,0.00024516502,0.00014786252,0.0015957977,0.00028593032,0.83792084,0.009699202,0.11868978,0.028756483,0.000106104984],"about_ca_topic_score_codex":0.0016030654,"about_ca_topic_score_gemma":0.0021697702,"teacher_disagreement_score":0.0073754685,"about_ca_system_score_codex":0.0006696389,"about_ca_system_score_gemma":0.0023746407,"threshold_uncertainty_score":0.016028404},"labels":[],"label_agreement":null},{"id":"W3133302368","doi":"10.14778/3436905.3436916","title":"Scalable mining of maximal quasi-cliques","year":2020,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Scalability; Clique; Load balancing (electrical power); Speedup; Vertex (graph theory); Graph; Theoretical computer science; Parallel computing; Combinatorics; Mathematics; Database","score_opus":0.02458840115704153,"score_gpt":0.23857404697814444,"score_spread":0.2139856458211029,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3133302368","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22497405,0.000589487,0.7633046,0.00091235474,0.00008724962,0.00035100785,0.0025674126,0.004484023,0.0027299018],"genre_scores_gemma":[0.48519114,0.00022942225,0.50649726,0.0002146251,0.000059577076,0.00023403087,0.0051910067,0.00039476142,0.0019882452],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985026,0.00032633336,0.000078055746,0.0005943389,0.00030178457,0.00019691675],"domain_scores_gemma":[0.9961527,0.0017356564,0.00038903323,0.00081879913,0.0006338066,0.00027005145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013874948,0.0008314549,0.00111341,0.0016421512,0.001132931,0.0015176501,0.0026242076,0.0008921878,0.0014818142],"category_scores_gemma":[0.0072971424,0.00081004336,0.00135172,0.0018038496,0.00068753853,0.0028809907,0.0018838788,0.00075633696,0.0005024457],"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":[0.0012175001,0.00050219556,0.03424282,0.0009978854,0.0005687472,0.0010598837,0.0009304655,0.5326649,0.049361095,0.04031944,0.027024895,0.31111014],"study_design_scores_gemma":[0.00005668528,0.00003601593,0.0012346809,0.0000119741335,0.000025649542,0.00011965601,0.0001331993,0.9720205,0.0034748157,0.020879641,0.0019963773,0.000010904549],"about_ca_topic_score_codex":0.0056494977,"about_ca_topic_score_gemma":0.013920185,"teacher_disagreement_score":0.0056494977,"about_ca_system_score_codex":0.0008097844,"about_ca_system_score_gemma":0.0023132963,"threshold_uncertainty_score":0.01123327},"labels":[],"label_agreement":null},{"id":"W3134176997","doi":"10.21203/rs.3.rs-180857/v1","title":"Knowledgebase Approximation Using Association Rules Aggregation","year":2021,"lang":"en","type":"preprint","venue":"Research Square","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":"University of Waterloo","funders":"","keywords":"Association (psychology); Association rule learning; Computer science; Computational biology; Data mining; Biology; Epistemology; Philosophy","score_opus":0.10091403667160218,"score_gpt":0.40475197032005,"score_spread":0.3038379336484478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134176997","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044626113,0.0028965275,0.9455515,0.000720382,0.00029832378,0.00014338242,0.0007619433,0.002009474,0.0029923317],"genre_scores_gemma":[0.33411154,0.0017892036,0.6549675,0.00029097643,0.00030681488,0.00018349054,0.0031871467,0.00020553844,0.004957811],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99569017,0.0007945911,0.00044518482,0.0007416567,0.002071535,0.0002567464],"domain_scores_gemma":[0.9886423,0.0060743066,0.0005685207,0.0027712402,0.0017237843,0.00021992924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034090134,0.00092407607,0.0029528446,0.005716931,0.0009961007,0.004355894,0.0027568776,0.0014100502,0.0033064396],"category_scores_gemma":[0.022588829,0.0009968873,0.0019163341,0.0076569603,0.00060195726,0.00456857,0.0024951962,0.0023163601,0.0013542327],"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":[0.0007602423,0.0005822899,0.008441447,0.00044738865,0.0005148015,0.0003619265,0.0003722744,0.13018505,0.0031951813,0.02499579,0.014941707,0.81520194],"study_design_scores_gemma":[0.000047269026,0.00006031317,0.0009948727,0.00008080505,0.00019706305,0.00031016802,0.000117390395,0.9460368,0.0025514872,0.045697734,0.0038893754,0.000016663986],"about_ca_topic_score_codex":0.0052437116,"about_ca_topic_score_gemma":0.005922602,"teacher_disagreement_score":0.005716931,"about_ca_system_score_codex":0.0010997206,"about_ca_system_score_gemma":0.0019215014,"threshold_uncertainty_score":0.018028796},"labels":[],"label_agreement":null},{"id":"W3138472208","doi":"10.1145/3259159","title":"Session details: Spatio-temporal data warehouses and data mining","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Session (web analytics); Computer science; Data warehouse; Data mining; Temporal database; Data science; Database; Information retrieval; World Wide Web","score_opus":0.10538454425839229,"score_gpt":0.3471328642654593,"score_spread":0.24174832000706703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138472208","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0062991693,0.011223027,0.041806452,0.033481766,0.059866164,0.0029886856,0.054293767,0.010302989,0.77973795],"genre_scores_gemma":[0.022418441,0.008557295,0.008131974,0.002471152,0.009927513,0.0009272531,0.018561507,0.0013106411,0.9276942],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99935526,0.00014552807,0.000040065053,0.0001494033,0.00019505834,0.00011472226],"domain_scores_gemma":[0.9953603,0.0015313384,0.000107158805,0.00066557835,0.0009220614,0.0014135261],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019931155,0.0015633188,0.0024943075,0.0008805261,0.0018311772,0.004703459,0.0012679416,0.0030620263,0.7554867],"category_scores_gemma":[0.004171565,0.00039859154,0.0014500191,0.002296737,0.00036024937,0.0029607068,0.002329742,0.002181759,0.50703406],"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":[0.0003595471,0.00019413063,0.0002629773,0.00028125016,0.000022401318,0.000076083496,0.000060153896,0.00011337846,0.0016314226,0.0018714736,0.9424467,0.052680485],"study_design_scores_gemma":[0.000128007,0.00019366303,0.0012908542,0.00010873409,0.00003052364,0.00019098757,0.00008973451,0.00080462283,0.00135686,0.002651207,0.99312675,0.000028066168],"about_ca_topic_score_codex":0.0009782503,"about_ca_topic_score_gemma":0.0019534465,"teacher_disagreement_score":0.7554867,"about_ca_system_score_codex":0.00049869914,"about_ca_system_score_gemma":0.0013099605,"threshold_uncertainty_score":0.34876847},"labels":[],"label_agreement":null},{"id":"W3139141769","doi":"10.1109/imcom51814.2021.9377412","title":"Natural Sciences Meet Social Sciences: Census Data Analytics for Detecting Home Language Shifts","year":2021,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; University of Manitoba","keywords":"Census; Microdata (statistics); Analytics; Computer science; Geography; Data science; Population; Sociology; Demography","score_opus":0.1141168266916986,"score_gpt":0.3677779799790345,"score_spread":0.2536611532873359,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139141769","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04074141,0.001679324,0.07172612,0.0048991814,0.00036635355,0.0017004187,0.84069496,0.020542001,0.017650358],"genre_scores_gemma":[0.21714777,0.002134278,0.20453522,0.0010230918,0.0003715416,0.0032636034,0.5655099,0.0012629329,0.0047517405],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99698997,0.0005973507,0.00048908347,0.0004902565,0.0012921154,0.00014116266],"domain_scores_gemma":[0.98464036,0.004300504,0.0027188924,0.003029737,0.004148019,0.0011624551],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003788307,0.0009952598,0.00087019824,0.007912579,0.00063462456,0.0020739182,0.0010444596,0.0008519272,0.008138681],"category_scores_gemma":[0.035308458,0.0005436479,0.0007497258,0.013120741,0.0002517003,0.0022066957,0.0019141757,0.0014198654,0.006370811],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004314434,0.00042716606,0.17405404,0.0017693572,0.0006529295,0.00039752058,0.0008485956,0.00920427,0.0021045208,0.014872097,0.5068915,0.28834662],"study_design_scores_gemma":[0.0002593833,0.00020262957,0.26890233,0.0006865167,0.00018166887,0.0004362505,0.0023312327,0.20099807,0.0067093573,0.05582445,0.46326345,0.00020468365],"about_ca_topic_score_codex":0.028040862,"about_ca_topic_score_gemma":0.029089201,"teacher_disagreement_score":0.028040862,"about_ca_system_score_codex":0.0011337132,"about_ca_system_score_gemma":0.003262169,"threshold_uncertainty_score":0.055755258},"labels":[],"label_agreement":null},{"id":"W3141591971","doi":"10.1109/ideas.2007.4318095","title":"Contrasting the Contrast Sets: An Alternative Approach","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Contrast (vision); Computer science; Association rule learning; Set (abstract data type); Focus (optics); Value (mathematics); Data mining; Artificial intelligence; Machine learning","score_opus":0.03204471525812842,"score_gpt":0.2907036345068925,"score_spread":0.2586589192487641,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3141591971","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022375762,0.00070631824,0.9659159,0.0012358016,0.00019600736,0.0002924506,0.00039008236,0.00052136503,0.00836625],"genre_scores_gemma":[0.20600946,0.00030413282,0.78921777,0.0005998073,0.00021216995,0.00032083824,0.0004907479,0.00015329674,0.0026917453],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9934994,0.0021085849,0.00040455538,0.001824075,0.0018629222,0.00030047176],"domain_scores_gemma":[0.9834161,0.010523591,0.0008229581,0.0031360823,0.0017204114,0.0003809243],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0057184435,0.0013526265,0.0023128684,0.0070427097,0.0017929358,0.0059697186,0.0047990666,0.0029053425,0.008879014],"category_scores_gemma":[0.033154678,0.0007554902,0.002703897,0.0057098526,0.0033130937,0.007962786,0.004379327,0.0034959903,0.0017623075],"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":[0.0010512139,0.00040013806,0.015502214,0.000642392,0.00060174684,0.0007459344,0.002047774,0.014933802,0.010300093,0.43102774,0.0057212603,0.5170257],"study_design_scores_gemma":[0.0002360832,0.000737849,0.0063042967,0.00025996534,0.00049324,0.0036841247,0.0013300942,0.23961696,0.010924188,0.68261796,0.053577434,0.00021786659],"about_ca_topic_score_codex":0.0010791391,"about_ca_topic_score_gemma":0.001328803,"teacher_disagreement_score":0.008879014,"about_ca_system_score_codex":0.00096189545,"about_ca_system_score_gemma":0.001559567,"threshold_uncertainty_score":0.030242383},"labels":[],"label_agreement":null},{"id":"W3144127944","doi":"10.1109/ideas.2007.4318098","title":"Feature Space Enrichment by Incorporation of Implicit Features for Effective Classification","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Classifier (UML); Pattern recognition (psychology); Discriminative model; Feature extraction; Unison; Artificial intelligence; Feature vector; Computer science; Space (punctuation); Data mining","score_opus":0.009552854389385785,"score_gpt":0.27831299669707427,"score_spread":0.26876014230768847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3144127944","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029175231,0.00035364827,0.968274,0.00014902806,0.000038846603,0.00007907751,0.00008313976,0.00073098036,0.0011160788],"genre_scores_gemma":[0.355465,0.00034390477,0.641522,0.00009553234,0.00006893495,0.00022016981,0.00040862884,0.00009272805,0.0017831349],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865,0.00037888877,0.00012078479,0.00024051411,0.0005205088,0.000089307425],"domain_scores_gemma":[0.99657565,0.0016481963,0.00025570032,0.000904954,0.00056007487,0.000055455715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016086493,0.00057070696,0.0007733362,0.0014603699,0.0003130044,0.0015136531,0.0007856959,0.0005694412,0.0015092432],"category_scores_gemma":[0.0069755674,0.0002748857,0.0005669654,0.001817232,0.0007354772,0.0026408415,0.0013697102,0.0011973035,0.0008811073],"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":[0.00019740673,0.0002231478,0.003275075,0.00021232889,0.00007004054,0.00018200846,0.0002831099,0.020133551,0.040993962,0.024646897,0.0023247425,0.9074577],"study_design_scores_gemma":[0.00006969882,0.0005546979,0.0059511764,0.00009611295,0.00012000755,0.0008479434,0.00017419297,0.8267491,0.07376594,0.06297017,0.028604845,0.00009608728],"about_ca_topic_score_codex":0.00032916272,"about_ca_topic_score_gemma":0.00049401453,"teacher_disagreement_score":0.0016086493,"about_ca_system_score_codex":0.0002529219,"about_ca_system_score_gemma":0.0004898018,"threshold_uncertainty_score":0.00850749},"labels":[],"label_agreement":null},{"id":"W3157814887","doi":"","title":"Exploring Data Using Pa erns: A Survey and Open Problems.","year":2021,"lang":"en","type":"article","venue":"Data Warehousing and OLAP","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":"University of Waterloo","funders":"","keywords":"Computer science","score_opus":0.7164711289704015,"score_gpt":0.3942254163047481,"score_spread":0.32224571266565344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3157814887","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0301621,0.19733432,0.7434567,0.012245493,0.00039344965,0.00035494842,0.005129107,0.0025202252,0.008403628],"genre_scores_gemma":[0.18076307,0.1344391,0.6691925,0.001358913,0.0008005755,0.00040618112,0.010143736,0.00043000217,0.0024659368],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.991265,0.0025768415,0.0009611907,0.0017824118,0.0030965004,0.00031805772],"domain_scores_gemma":[0.9517386,0.037955772,0.0018270623,0.004838143,0.0029432185,0.0006972486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007275754,0.0017008674,0.002877505,0.009751159,0.0013053977,0.00858299,0.0058708712,0.002502938,0.0031874382],"category_scores_gemma":[0.042308494,0.0016374415,0.0027800484,0.024352817,0.0021570697,0.02424184,0.0054664873,0.0032407562,0.0019447273],"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":[0.00011362304,0.00033734497,0.016620615,0.004170273,0.00038724515,0.00022441371,0.0008692101,0.010632431,0.0009998176,0.02813469,0.013391254,0.9241191],"study_design_scores_gemma":[0.000040566632,0.00024878437,0.010990208,0.0037529173,0.00039041045,0.0030132052,0.00893762,0.25757623,0.006459481,0.5110933,0.1972958,0.0002014577],"about_ca_topic_score_codex":0.0026403228,"about_ca_topic_score_gemma":0.003231781,"teacher_disagreement_score":0.009751159,"about_ca_system_score_codex":0.0007881536,"about_ca_system_score_gemma":0.0024465234,"threshold_uncertainty_score":0.038478374},"labels":[],"label_agreement":null},{"id":"W3160170194","doi":"10.1002/eng2.12411","title":"Mining web content usage patterns of electronic commerce transactions for enhanced customer services","year":2021,"lang":"en","type":"article","venue":"Engineering Reports","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Web analytics; Web mining; Web page; Visitor pattern; Data warehouse; World Wide Web; Path analysis (statistics); Data mining; Web intelligence; Web development","score_opus":0.013129632430232914,"score_gpt":0.23023882843278795,"score_spread":0.21710919600255504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160170194","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9869108,0.000102374965,0.009428234,0.0000978997,0.0000077938,0.000061221544,0.002138315,0.00037136764,0.0008820137],"genre_scores_gemma":[0.9836331,0.000080309335,0.01177821,0.000014731526,0.000008750226,0.00004673305,0.0038139299,0.000026893591,0.00059734535],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994752,0.00010144556,0.00006464559,0.000099071956,0.00020243393,0.000057226134],"domain_scores_gemma":[0.99793696,0.0009873905,0.0003443412,0.00016037271,0.00045038376,0.000120455225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052607903,0.00033321747,0.00028987328,0.0061478247,0.00028745967,0.000876795,0.00036140086,0.00044343676,0.0008498479],"category_scores_gemma":[0.0030582687,0.00016557856,0.00048466984,0.004245268,0.00015556067,0.00075405167,0.0002618166,0.00031786828,0.00054710475],"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":[0.00055243913,0.0009601097,0.7507042,0.00024458164,0.00033452353,0.0014038186,0.00064632,0.02105069,0.022591036,0.001192392,0.0039914944,0.19632837],"study_design_scores_gemma":[0.00002276095,0.00026726705,0.46890578,0.0000513672,0.00013017403,0.0013346726,0.00089936645,0.5090912,0.0138274,0.0020315163,0.0034024739,0.000036034333],"about_ca_topic_score_codex":0.004055553,"about_ca_topic_score_gemma":0.0057507213,"teacher_disagreement_score":0.0061478247,"about_ca_system_score_codex":0.0004044954,"about_ca_system_score_gemma":0.0004531989,"threshold_uncertainty_score":0.008063912},"labels":[],"label_agreement":null},{"id":"W3162569673","doi":"10.3390/axioms10020093","title":"Transdisciplinary Scientific Strategies for Soft Computing Development: Towards an Era of Data and Business Analytics","year":2021,"lang":"en","type":"article","venue":"Axioms","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Analytics; Data science; Computer science; Soft computing; Data analysis; Work (physics); Plan (archaeology); Management science; Knowledge management; Artificial intelligence; Engineering; Data mining","score_opus":0.07984672160390978,"score_gpt":0.335418122086488,"score_spread":0.25557140048257826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3162569673","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011424799,0.13690546,0.49478093,0.20328103,0.0049992283,0.00025754282,0.00011435045,0.0004147196,0.14782189],"genre_scores_gemma":[0.43306014,0.17727761,0.3181156,0.035829797,0.006276365,0.00093048724,0.00026970185,0.00050905655,0.027731238],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9834683,0.008505129,0.0009809928,0.0012302077,0.0051616384,0.00065381185],"domain_scores_gemma":[0.9781757,0.013733521,0.0011576712,0.0021962079,0.0033171396,0.0014196818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018399818,0.0011870961,0.0012822882,0.007148066,0.0031852152,0.018935958,0.00212874,0.005219172,0.0033703858],"category_scores_gemma":[0.0147120785,0.0006412544,0.0011144796,0.006046891,0.02340291,0.025113475,0.009733921,0.0076930183,0.0016371687],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006034267,0.000019454625,0.00014772442,0.0004107328,0.000017433707,0.000047154226,0.0013283589,0.0004225892,0.0001901702,0.9679463,0.0036461009,0.025817836],"study_design_scores_gemma":[0.0000051889397,0.000024183211,0.00015078415,0.000824561,0.000010399076,0.00014585428,0.0030765908,0.0013809016,0.0004625264,0.8358505,0.15803884,0.000029571005],"about_ca_topic_score_codex":0.0010548542,"about_ca_topic_score_gemma":0.0010905083,"teacher_disagreement_score":0.018935958,"about_ca_system_score_codex":0.0057651754,"about_ca_system_score_gemma":0.01053924,"threshold_uncertainty_score":0.097308695},"labels":[],"label_agreement":null},{"id":"W3163010745","doi":"10.1145/3248790","title":"Session details: Research track 10: graph mining and classification","year":2010,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Session (web analytics); Computer science; Track (disk drive); Graph; Information retrieval; Artificial intelligence; Data mining; World Wide Web; Theoretical computer science; Operating system","score_opus":0.10265910663614891,"score_gpt":0.3691941424807484,"score_spread":0.2665350358445995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3163010745","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008679111,0.02901856,0.053117268,0.045769423,0.080963284,0.0077777603,0.18486403,0.029160623,0.56064993],"genre_scores_gemma":[0.016748508,0.010514276,0.016285837,0.0029992773,0.015708962,0.0018773366,0.099523894,0.0030112101,0.83333063],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970475,0.0005093913,0.00014531266,0.00087148615,0.0010639715,0.0003623015],"domain_scores_gemma":[0.98723894,0.00264992,0.00039241137,0.0024602478,0.0035670681,0.0036913943],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.006647961,0.0032441113,0.0050428226,0.0030256147,0.0028291268,0.0074328817,0.003794351,0.005828953,0.63359255],"category_scores_gemma":[0.00881665,0.00077353383,0.0023984907,0.0054091755,0.0006522764,0.00474239,0.002860353,0.0035099753,0.51347],"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":[0.00021222222,0.0002266085,0.00017793696,0.0003186377,0.000025757094,0.000018038734,0.00001082181,0.00009548789,0.0012590779,0.0006124688,0.951945,0.045098003],"study_design_scores_gemma":[0.00032985143,0.0007594393,0.0027855008,0.0001713234,0.00010454886,0.00013079493,0.00006150461,0.0020443308,0.004209732,0.0039481753,0.98539203,0.000062735744],"about_ca_topic_score_codex":0.0035831546,"about_ca_topic_score_gemma":0.00773414,"teacher_disagreement_score":0.36640745,"about_ca_system_score_codex":0.0017016132,"about_ca_system_score_gemma":0.0047900975,"threshold_uncertainty_score":0.52263576},"labels":[],"label_agreement":null},{"id":"W3166703265","doi":"10.2139/ssrn.3199478","title":"Modeling and Querying Graphical Representations of Statistical Data","year":2010,"lang":"en","type":"article","venue":"SSRN Electronic Journal","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":"Carleton University","funders":"","keywords":"Computer science; Graphical model; Information retrieval; Data mining; Data science; Artificial intelligence","score_opus":0.021136367839464768,"score_gpt":0.3097986633404615,"score_spread":0.28866229550099676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3166703265","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012520825,0.00026139675,0.9807355,0.00038067185,0.00002103211,0.00007181305,0.001460729,0.0041157654,0.00043234613],"genre_scores_gemma":[0.36377618,0.00088518613,0.62585723,0.00027785712,0.00008397992,0.00034656472,0.0068650483,0.0007455455,0.0011623979],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9942272,0.0025403844,0.00057132513,0.00093970203,0.0014990569,0.00022237592],"domain_scores_gemma":[0.97346264,0.019463114,0.0016757825,0.003852666,0.0012248517,0.00032089432],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005373766,0.001243133,0.0015607814,0.0050646695,0.0006922537,0.005769432,0.003477322,0.0018336838,0.002299012],"category_scores_gemma":[0.04096781,0.0010909821,0.0032361292,0.005226005,0.0014220143,0.007121274,0.0029307783,0.0022052787,0.0009871837],"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":[0.00037697607,0.0002908975,0.01362643,0.000998272,0.0004406769,0.00079981796,0.0013185737,0.51623076,0.007219289,0.23238187,0.010569036,0.21574746],"study_design_scores_gemma":[0.000020376596,0.000027926297,0.00039918596,0.000036249596,0.000054300755,0.00014356093,0.00007323074,0.86415213,0.0016545034,0.13140991,0.0020032586,0.000025379988],"about_ca_topic_score_codex":0.006315337,"about_ca_topic_score_gemma":0.009243583,"teacher_disagreement_score":0.006315337,"about_ca_system_score_codex":0.0016384809,"about_ca_system_score_gemma":0.0015610118,"threshold_uncertainty_score":0.028419495},"labels":[],"label_agreement":null},{"id":"W3167384785","doi":"10.15675/gepros.v16i2.2747","title":"Classification of Diseases of The Urinary System using an Expert System","year":2021,"lang":"en","type":"article","venue":"GEPROS. Gestão da Produção, Operações e Sistemas","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Expert system; Urinary system; Computer science; Data mining; Medicine; Artificial intelligence; Internal medicine","score_opus":0.057754935256724434,"score_gpt":0.2889035014369505,"score_spread":0.23114856618022606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3167384785","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26991943,0.00063845713,0.7095512,0.0009749199,0.00015509228,0.0019912943,0.0020094765,0.0025560826,0.012204044],"genre_scores_gemma":[0.46092933,0.0003265959,0.5342114,0.0002070983,0.00004267361,0.00046468867,0.0015140576,0.00003775113,0.0022663795],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99839777,0.0006015667,0.00021369624,0.00031442006,0.0003953355,0.000077200966],"domain_scores_gemma":[0.99648154,0.00213968,0.0002464782,0.00028169772,0.00074410945,0.00010651006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024408242,0.00049185526,0.0005340394,0.0016769008,0.00046488922,0.0015066097,0.0006518041,0.00066899334,0.0030637998],"category_scores_gemma":[0.007481668,0.00017023935,0.0006201551,0.00073515653,0.00029451877,0.000851162,0.0005102005,0.00051433285,0.0007295962],"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":[0.0008527288,0.0011970025,0.06866402,0.0014144101,0.00036486602,0.0012157435,0.0013012137,0.12141684,0.028314134,0.00862887,0.009402492,0.75722766],"study_design_scores_gemma":[0.00020977728,0.0010639085,0.043061532,0.0005156878,0.00035864353,0.0012232654,0.0010292783,0.8866933,0.029613672,0.014050926,0.022055356,0.0001247058],"about_ca_topic_score_codex":0.0027176542,"about_ca_topic_score_gemma":0.0028064675,"teacher_disagreement_score":0.0030637998,"about_ca_system_score_codex":0.00066921045,"about_ca_system_score_gemma":0.0013538329,"threshold_uncertainty_score":0.012908459},"labels":[],"label_agreement":null},{"id":"W3174126363","doi":"10.65109/bnke8963","title":"Constructing Junction Tree Agent Organization with Privacy","year":2021,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Tree (set theory); Computer science; Computer security; Internet privacy; Business; Mathematics; Combinatorics","score_opus":0.01354846186179621,"score_gpt":0.22038449155916479,"score_spread":0.20683602969736858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174126363","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012101764,0.00008581844,0.9853013,0.000215605,0.000016295508,0.000076778444,0.00006964333,0.0005635762,0.0015691762],"genre_scores_gemma":[0.23684558,0.00013454628,0.75957507,0.00013901663,0.000035151053,0.00017366592,0.0005690926,0.00015358797,0.002374309],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996664,0.0010263305,0.00020505089,0.0008105548,0.0009543709,0.00033959732],"domain_scores_gemma":[0.99448377,0.0019002727,0.00049809134,0.0021438135,0.0006348036,0.00033929938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041384343,0.0004926435,0.0009931655,0.0012018386,0.0018166483,0.0028206473,0.0025727921,0.0014964602,0.002745257],"category_scores_gemma":[0.0110396175,0.00063448155,0.0015814487,0.0017453773,0.0016639045,0.006594087,0.0050977743,0.0020465087,0.0007132881],"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":[0.0003124778,0.0002775062,0.005060287,0.00022122299,0.00015753684,0.0004898986,0.0013224015,0.23912098,0.006832303,0.518887,0.009860658,0.21745782],"study_design_scores_gemma":[0.000040312287,0.000049060865,0.000332221,0.000018246785,0.000052034764,0.00016310073,0.0002435103,0.8168025,0.004319082,0.16689904,0.011057793,0.000023045253],"about_ca_topic_score_codex":0.0025806895,"about_ca_topic_score_gemma":0.004035961,"teacher_disagreement_score":0.0041384343,"about_ca_system_score_codex":0.0012626443,"about_ca_system_score_gemma":0.002351938,"threshold_uncertainty_score":0.021886408},"labels":[],"label_agreement":null},{"id":"W3176244545","doi":"10.48550/arxiv.2001.01424","title":"Cross-Dataset Design Discussion Mining","year":2020,"lang":"en","type":"preprint","venue":"Figshare","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Artifact (error); Code refactoring; Relevance (law); Context (archaeology); Documentation; Task (project management); Software; Data mining; Machine learning; Software engineering; Artificial intelligence; Data science; Engineering; Systems engineering; Programming language","score_opus":0.14406923373393768,"score_gpt":0.346395833574453,"score_spread":0.20232659984051535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176244545","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25455412,0.006150856,0.12140949,0.0030069833,0.0010012056,0.0063061123,0.53060275,0.011551508,0.06541696],"genre_scores_gemma":[0.23170096,0.00073510926,0.14746602,0.0010616353,0.0002097154,0.0067062965,0.5935538,0.0009463055,0.017620163],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9864738,0.0039075646,0.0017339366,0.0034732532,0.0037331714,0.0006782398],"domain_scores_gemma":[0.96045697,0.01606946,0.0032605133,0.011706971,0.0074399775,0.0010661599],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009221399,0.0012845087,0.000813826,0.0117555745,0.0022811508,0.003508226,0.0032039906,0.002357059,0.011234826],"category_scores_gemma":[0.039260514,0.000491399,0.0017597894,0.008812296,0.0008070778,0.0029423232,0.0039086035,0.0021943978,0.0069436315],"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":[0.0012931591,0.0022778483,0.10804688,0.0064558787,0.0010485302,0.00097551534,0.003266382,0.007496779,0.011953641,0.017060839,0.31798643,0.5221382],"study_design_scores_gemma":[0.0004088651,0.00052807236,0.094274916,0.00090083526,0.0004966996,0.001216501,0.0037167163,0.032351986,0.026602553,0.017292468,0.8220081,0.00020230623],"about_ca_topic_score_codex":0.0033602878,"about_ca_topic_score_gemma":0.007000553,"teacher_disagreement_score":0.0117555745,"about_ca_system_score_codex":0.0017660805,"about_ca_system_score_gemma":0.0025345893,"threshold_uncertainty_score":0.048768044},"labels":[],"label_agreement":null},{"id":"W3179604620","doi":"10.1007/s10489-021-02536-7","title":"New approaches for mining regular high utility sequential patterns","year":2021,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":47,"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; Data stream mining; Sliding window protocol; Task (project management); Sequential Pattern Mining; Window (computing); Database","score_opus":0.08643271993724345,"score_gpt":0.2779028397942664,"score_spread":0.19147011985702295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3179604620","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009602367,0.0009797772,0.9874586,0.00023585871,0.00007478391,0.000120757104,0.00027156645,0.0005382567,0.00071810116],"genre_scores_gemma":[0.12404426,0.0014010094,0.86797464,0.00021778276,0.00030709876,0.00029773195,0.0012801391,0.00013142006,0.004345818],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972134,0.00040601005,0.00033220794,0.0006948286,0.0012425904,0.00011082847],"domain_scores_gemma":[0.9944829,0.0027380062,0.00054640946,0.0009326237,0.0011104986,0.0001896734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023412504,0.000982109,0.0013318096,0.0058975616,0.0009044007,0.0030124364,0.0024337347,0.00097011507,0.0023691042],"category_scores_gemma":[0.011076297,0.0007141172,0.0014451322,0.007804726,0.0010396264,0.004127005,0.0019854796,0.0019193982,0.0010271912],"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":[0.000422606,0.0003683653,0.010049038,0.00081931974,0.00041891038,0.00061147776,0.00056364207,0.035881884,0.010086929,0.07009419,0.006652268,0.8640313],"study_design_scores_gemma":[0.0000841445,0.00016070159,0.0023753147,0.00010676925,0.00020414333,0.0010720069,0.00022946585,0.8000265,0.0062884563,0.17342915,0.015970258,0.000053035576],"about_ca_topic_score_codex":0.0018429831,"about_ca_topic_score_gemma":0.004046384,"teacher_disagreement_score":0.0058975616,"about_ca_system_score_codex":0.00064092904,"about_ca_system_score_gemma":0.0012153485,"threshold_uncertainty_score":0.012381911},"labels":[],"label_agreement":null},{"id":"W3182789081","doi":"","title":"Discovering spatial associations in images","year":2000,"lang":"en","type":"article","venue":"Proceedings of SPIE - The International Society for Optical Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Focus (optics); Association rule learning; Abstraction; Feature (linguistics); Data mining; Process (computing); Scalability; Association (psychology); Information retrieval; Spatial analysis; Artificial intelligence; Geography; Database","score_opus":0.008726694441781684,"score_gpt":0.23165345380987087,"score_spread":0.2229267593680892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3182789081","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28500587,0.003491681,0.6958254,0.00116139,0.00015140469,0.0003180746,0.0028879235,0.0023268664,0.008831422],"genre_scores_gemma":[0.65439475,0.0017402776,0.337483,0.00021370492,0.00013879745,0.00015201903,0.0032948677,0.00011623124,0.0024663608],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987884,0.00011666476,0.00009584755,0.00037449648,0.0004633833,0.00016114436],"domain_scores_gemma":[0.9984043,0.0004504701,0.00035210434,0.0003264276,0.00038521783,0.00008150174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054257736,0.0005626654,0.00077271456,0.007906604,0.0007765253,0.0019813927,0.00097285485,0.00089582725,0.0022068226],"category_scores_gemma":[0.0036431367,0.00047036525,0.000987638,0.006735078,0.00078824523,0.0025651385,0.001968105,0.000648128,0.0012555633],"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":[0.00059904385,0.00036637523,0.07392829,0.00074933097,0.00032484456,0.0023519322,0.0013571639,0.016269648,0.04704228,0.02070814,0.00909572,0.8272071],"study_design_scores_gemma":[0.000098530145,0.00073679944,0.12313993,0.0005129826,0.0010139283,0.009769152,0.006540884,0.4954502,0.09760049,0.17304158,0.09186097,0.00023457315],"about_ca_topic_score_codex":0.0028813193,"about_ca_topic_score_gemma":0.0042575616,"teacher_disagreement_score":0.007906604,"about_ca_system_score_codex":0.00044640535,"about_ca_system_score_gemma":0.000829042,"threshold_uncertainty_score":0.0073825717},"labels":[],"label_agreement":null},{"id":"W3183918753","doi":"10.3390/genes12081160","title":"Genotype Pattern Mining for Pairs of Interacting Variants Underlying Digenic Traits","year":2021,"lang":"en","type":"article","venue":"Genes","topic":"Data Mining Algorithms and Applications","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 Calgary","funders":"Japan Society for the Promotion of Science; Natural Sciences and Engineering Research Council of Canada","keywords":"Biology; Genetics; Genotype; Epistasis; Retinitis pigmentosa; Phenotype; Gene","score_opus":0.07004570986252151,"score_gpt":0.31067846038151103,"score_spread":0.24063275051898952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3183918753","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66659516,0.0035844173,0.2895717,0.0012615891,0.00019335473,0.00062244607,0.032659322,0.0030052674,0.0025066712],"genre_scores_gemma":[0.801641,0.00047904262,0.16609181,0.00030559622,0.00008838887,0.0004324804,0.029810786,0.00014973337,0.001001146],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99597955,0.0009108877,0.0007372441,0.0015557363,0.00059778366,0.00021883323],"domain_scores_gemma":[0.9855172,0.010127908,0.0016959289,0.0015729064,0.00073445874,0.0003514911],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004073802,0.00080300856,0.0012839553,0.0056496128,0.00057957723,0.0015274057,0.0015976112,0.0012702843,0.0035028744],"category_scores_gemma":[0.017421061,0.00034167367,0.0019491266,0.00427119,0.00040455535,0.0007916216,0.0012771343,0.0008442972,0.00073759974],"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":[0.0023351498,0.0005978973,0.6248662,0.0020815635,0.0028553682,0.0058043194,0.0005074903,0.015099381,0.0184136,0.004284202,0.008893356,0.31426153],"study_design_scores_gemma":[0.0009150725,0.0016368409,0.42713627,0.0007040455,0.0038564773,0.027852217,0.0012024111,0.37651223,0.03603343,0.09542831,0.028480863,0.00024183984],"about_ca_topic_score_codex":0.0014581715,"about_ca_topic_score_gemma":0.0022906547,"teacher_disagreement_score":0.0056496128,"about_ca_system_score_codex":0.00031629243,"about_ca_system_score_gemma":0.0009523474,"threshold_uncertainty_score":0.021544576},"labels":[],"label_agreement":null},{"id":"W3185092620","doi":"10.1145/3423557","title":"The Efficient Mining of Skyline Patterns from a Volunteer Computing Network","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Internet Technology","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Skyline; Computer science; Constraint (computer-aided design); Process (computing); Data mining; Set (abstract data type); Mathematics; Programming language","score_opus":0.011339491007769365,"score_gpt":0.24391195169197652,"score_spread":0.23257246068420714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3185092620","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23152879,0.00084992097,0.7599737,0.000623507,0.00006167332,0.00030170457,0.0019483183,0.001897256,0.0028150645],"genre_scores_gemma":[0.6735351,0.00043243266,0.31915107,0.000107731525,0.000049771075,0.00026645302,0.0043371962,0.0000915914,0.002028638],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990513,0.00020947651,0.000077439145,0.00027790322,0.00026186512,0.00012207113],"domain_scores_gemma":[0.9983632,0.00042592658,0.00030744972,0.00040640877,0.00032672498,0.00017033593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007970424,0.00076304685,0.0009565267,0.0017973721,0.0009565158,0.0011492633,0.0017833471,0.0006252758,0.0007579669],"category_scores_gemma":[0.0035926807,0.00046899644,0.00077479973,0.0035071196,0.00037238857,0.00237619,0.0011132052,0.00050091185,0.00041019826],"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":[0.0017283063,0.00044308248,0.047136404,0.00094517146,0.00030081187,0.002228761,0.0012260436,0.2409554,0.027314963,0.023936616,0.020350495,0.6334339],"study_design_scores_gemma":[0.000020407322,0.00011710476,0.0023397256,0.00002026524,0.000024013756,0.00046658443,0.00030490177,0.97359395,0.0039460175,0.015467445,0.0036869692,0.000012602105],"about_ca_topic_score_codex":0.0023240668,"about_ca_topic_score_gemma":0.0038823518,"teacher_disagreement_score":0.0023240668,"about_ca_system_score_codex":0.00046985399,"about_ca_system_score_gemma":0.001186119,"threshold_uncertainty_score":0.004621029},"labels":[],"label_agreement":null},{"id":"W3197889602","doi":"10.1016/j.datak.2021.101924","title":"Mining high utility patterns in interval-based event sequences","year":2021,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Pruning; Interval (graph theory); Computer science; Event (particle physics); Data mining; Range (aeronautics); Point (geometry); Sequential Pattern Mining; Algorithm; Mathematics; Engineering","score_opus":0.041472155210488644,"score_gpt":0.29062862660563255,"score_spread":0.2491564713951439,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197889602","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55986434,0.0014130869,0.43046483,0.00041700792,0.000104078186,0.00020642643,0.0040340764,0.0011168288,0.0023793085],"genre_scores_gemma":[0.90741086,0.00045303477,0.088227205,0.000049946797,0.00007891272,0.000077922436,0.0027999254,0.000050159455,0.0008520084],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986712,0.000177996,0.00016648191,0.00027628362,0.0005861606,0.00012190303],"domain_scores_gemma":[0.99434376,0.00329743,0.00096351746,0.0004074449,0.00073136133,0.0002565007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009808433,0.0005776577,0.0005798145,0.003808027,0.0004176025,0.0012057895,0.00087601726,0.0005731884,0.0014996456],"category_scores_gemma":[0.008804132,0.00027448582,0.0005805909,0.003324162,0.00036714357,0.0016416368,0.0006820198,0.00078604853,0.00046777082],"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":[0.0027874,0.0010915126,0.21862954,0.0013438554,0.00054781896,0.005843346,0.001157056,0.10110104,0.036640137,0.029247327,0.0056080925,0.5960029],"study_design_scores_gemma":[0.00013726343,0.0008414179,0.055689126,0.00026087646,0.00034550962,0.0040095816,0.00087118195,0.822716,0.022714559,0.08441624,0.007916087,0.000082157574],"about_ca_topic_score_codex":0.0011731973,"about_ca_topic_score_gemma":0.0016930784,"teacher_disagreement_score":0.003808027,"about_ca_system_score_codex":0.00031300948,"about_ca_system_score_gemma":0.00052421645,"threshold_uncertainty_score":0.0051872134},"labels":[],"label_agreement":null},{"id":"W3199597810","doi":"10.1155/2021/6653816","title":"Mining Profitable and Concise Patterns in Large‐Scale Internet of Things Environments","year":2021,"lang":"en","type":"article","venue":"Wireless Communications and Mobile Computing","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"Høgskulen på Vestlandet","keywords":"Computer science; Scalability; SPARK (programming language); Data mining; Scale (ratio); CLs upper limits; Association rule learning; Database","score_opus":0.015174010775863736,"score_gpt":0.25891485379702345,"score_spread":0.24374084302115973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199597810","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35348955,0.0023397305,0.62466764,0.001502525,0.00023819656,0.00080599845,0.0072194724,0.005378612,0.0043582716],"genre_scores_gemma":[0.4871523,0.0010309947,0.49484357,0.00037755637,0.000080933,0.00036632968,0.013100864,0.0002107121,0.00283673],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99814796,0.00023956333,0.0002459358,0.00059400056,0.0005948887,0.00017754702],"domain_scores_gemma":[0.9967769,0.0014025898,0.00053077657,0.00060070114,0.0005051546,0.00018397001],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014062377,0.0014744154,0.0012596216,0.0036038272,0.0011155391,0.0016381168,0.0022573918,0.0011287008,0.00085544004],"category_scores_gemma":[0.005706922,0.0007317889,0.0019503162,0.0040802183,0.00053613324,0.0031349624,0.0014878524,0.000783802,0.0005892911],"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":[0.0007579299,0.0012169473,0.10131955,0.0020807923,0.0010676759,0.0077049625,0.0014162954,0.19838358,0.02222974,0.015245837,0.022033773,0.6265429],"study_design_scores_gemma":[0.000057780006,0.00023847817,0.012251992,0.00010624308,0.00015211,0.0033954855,0.001931732,0.9050628,0.015689062,0.048336122,0.012733011,0.000045075394],"about_ca_topic_score_codex":0.0020300297,"about_ca_topic_score_gemma":0.006087736,"teacher_disagreement_score":0.0036038272,"about_ca_system_score_codex":0.00041724578,"about_ca_system_score_gemma":0.001079989,"threshold_uncertainty_score":0.0074369907},"labels":[],"label_agreement":null},{"id":"W3201056473","doi":"10.1007/s10489-021-02751-2","title":"Analytics of high average-utility patterns in the industrial internet of things","year":2021,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"Natural Science Foundation of Shandong Province; Høgskulen på Vestlandet","keywords":"Computer science; Data mining; Field (mathematics); Analytics; Measure (data warehouse); Internet of Things; Data science; World Wide Web","score_opus":0.051345710271062966,"score_gpt":0.268245381674218,"score_spread":0.21689967140315505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201056473","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75982344,0.00071081973,0.23404357,0.00053634075,0.00006595581,0.00012981892,0.0014900828,0.0006560505,0.002543978],"genre_scores_gemma":[0.9702032,0.00016633244,0.028377019,0.000029697823,0.000012220493,0.000029223102,0.0007653719,0.000012503448,0.00040428576],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989003,0.00014186974,0.00014809644,0.00021094223,0.0004797657,0.000118921685],"domain_scores_gemma":[0.99793494,0.00083526096,0.0004368846,0.00024558755,0.00046056588,0.00008673333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000895992,0.00058239547,0.0006092074,0.003526502,0.0006225111,0.0010888205,0.000745236,0.0005398878,0.0005385669],"category_scores_gemma":[0.0038256191,0.0002465279,0.0005264259,0.0049049426,0.00033553832,0.0014381923,0.00064963195,0.00040536467,0.0001575486],"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":[0.000909423,0.00049270544,0.2591276,0.00063732365,0.00039328492,0.0061191097,0.000701555,0.29613718,0.016906995,0.013031933,0.0051967334,0.4003462],"study_design_scores_gemma":[0.000009430474,0.00010271129,0.030603142,0.000027177215,0.00005081766,0.0009415328,0.0004502979,0.94738936,0.006475453,0.012423789,0.0015027289,0.000023525954],"about_ca_topic_score_codex":0.0018392273,"about_ca_topic_score_gemma":0.002538805,"teacher_disagreement_score":0.003526502,"about_ca_system_score_codex":0.00043537878,"about_ca_system_score_gemma":0.00037174462,"threshold_uncertainty_score":0.0047385097},"labels":[],"label_agreement":null},{"id":"W3207059787","doi":"10.18280/rces.080301","title":"Improving Association Rule Mining Using Clustering-Based Data Mining Model for Traffic Accidents","year":2021,"lang":"en","type":"article","venue":"Review of Computer Engineering Studies","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Association rule learning; Data mining; Cluster analysis; Computer science; Process (computing); Transaction data; Traffic accident; K-optimal pattern discovery; Data stream mining; Association (psychology); Data science; Machine learning; Database transaction; Engineering; Database; Transport engineering","score_opus":0.07553148388924286,"score_gpt":0.33475339020781447,"score_spread":0.2592219063185716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3207059787","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0669197,0.0012926521,0.9261348,0.00080516783,0.0001635315,0.00023472573,0.00035975163,0.0016067384,0.0024828333],"genre_scores_gemma":[0.46615258,0.0020768181,0.5252204,0.0005031842,0.00015413604,0.00040156444,0.0016230536,0.00014985038,0.003718342],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99808526,0.000508978,0.00017861612,0.0005166541,0.00058490783,0.0001256865],"domain_scores_gemma":[0.9971391,0.0011031613,0.0002048253,0.0002346339,0.0012564757,0.00006182001],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024791346,0.0008000745,0.0014597102,0.0021376354,0.0010204765,0.0013981715,0.002114022,0.0011441044,0.0010191887],"category_scores_gemma":[0.005160049,0.0004393093,0.0018518859,0.002598895,0.00042036077,0.0020662781,0.00094688125,0.0013444595,0.0007405264],"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":[0.00040153915,0.0008339436,0.020144645,0.0004961918,0.0004896729,0.0008381406,0.0005455196,0.51703,0.008649255,0.0176518,0.011343866,0.4215755],"study_design_scores_gemma":[0.000021848084,0.00007977853,0.0010794204,0.00002143466,0.00008428029,0.00019038192,0.000052222982,0.98938835,0.002414824,0.004061752,0.002576898,0.000028939345],"about_ca_topic_score_codex":0.007968574,"about_ca_topic_score_gemma":0.006675119,"teacher_disagreement_score":0.007968574,"about_ca_system_score_codex":0.0008733169,"about_ca_system_score_gemma":0.0018305802,"threshold_uncertainty_score":0.015844405},"labels":[],"label_agreement":null},{"id":"W3208091411","doi":"10.5281/zenodo.4683794","title":"Repository Features to Help Researchers: An invitation to a dialogue","year":2021,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Victoria Park","funders":"","keywords":"Data science; Computer science; Epistemology; Engineering ethics; Cognitive science; Psychology; Engineering; Philosophy","score_opus":0.05680646091775602,"score_gpt":0.28816910554158603,"score_spread":0.23136264462383002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208091411","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037250603,0.0018928858,0.011203038,0.9502634,0.02587984,0.0004437706,0.00017089491,0.00039049913,0.0060306545],"genre_scores_gemma":[0.071215756,0.0021658044,0.026061933,0.81611675,0.03293392,0.002511512,0.00028595337,0.0017914169,0.04691693],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9213896,0.047247782,0.0048871525,0.0062892954,0.012970819,0.0072154077],"domain_scores_gemma":[0.8067012,0.1277103,0.0049354145,0.0072725723,0.015239796,0.03814082],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.10742577,0.003166158,0.0025391055,0.0023940576,0.033940125,0.03424429,0.00781519,0.08636369,0.014709023],"category_scores_gemma":[0.14488138,0.0034978762,0.0046060355,0.002194025,0.018283099,0.04284949,0.047439024,0.10053585,0.005787732],"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":[0.00030687038,0.0005324962,0.0009697102,0.0006857546,0.00008679673,0.0074644857,0.17409924,0.0009915996,0.004811627,0.11392475,0.6703194,0.025807276],"study_design_scores_gemma":[0.00006075856,0.00009761647,0.0001951102,0.00030156525,0.000013387486,0.000939554,0.038916476,0.0005837691,0.0003210733,0.017986977,0.94042903,0.00015480879],"about_ca_topic_score_codex":0.003417963,"about_ca_topic_score_gemma":0.0037776916,"teacher_disagreement_score":0.9657557,"about_ca_system_score_codex":0.012465955,"about_ca_system_score_gemma":0.01873275,"threshold_uncertainty_score":0.5681286},"labels":[],"label_agreement":null},{"id":"W3208998979","doi":"10.82308/49931","title":"Copula-based risk aggregation modelling","year":2014,"lang":"en","type":"article","venue":"eScholarship@McGill (McGill)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Copula (linguistics); Econometrics; Computer science; Mathematics","score_opus":0.019630183060600773,"score_gpt":0.2239642959809488,"score_spread":0.20433411292034803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208998979","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033961365,0.00026047154,0.99148166,0.00025750892,0.000042283682,0.000052870735,0.00016387754,0.00015614816,0.0041889306],"genre_scores_gemma":[0.53160566,0.001860134,0.44945666,0.00032469587,0.00024763495,0.0006429082,0.00076493295,0.00028179117,0.014815498],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99736303,0.0011830142,0.00014112097,0.0004200975,0.00063568813,0.00025699977],"domain_scores_gemma":[0.996766,0.001657959,0.0004984092,0.00039708032,0.0005331856,0.00014737733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035849293,0.0013290929,0.001685468,0.0020178938,0.0008512646,0.00444978,0.0028829433,0.0017291452,0.0056034643],"category_scores_gemma":[0.00958333,0.0007058329,0.0020753418,0.003209328,0.0011809225,0.003061006,0.0025699355,0.002822512,0.0012923749],"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":[0.000015118458,0.00004427956,0.0010418061,0.000077487486,0.00011039123,0.00020251145,0.0002162676,0.47465873,0.0004968693,0.4978657,0.0031875768,0.022083322],"study_design_scores_gemma":[0.0000037395043,0.000015524934,0.00025257262,0.000023407214,0.000019755264,0.00006722323,0.000027620767,0.8871412,0.00009857005,0.110230274,0.0021031476,0.000016870876],"about_ca_topic_score_codex":0.0068161385,"about_ca_topic_score_gemma":0.005547802,"teacher_disagreement_score":0.0068161385,"about_ca_system_score_codex":0.0018692005,"about_ca_system_score_gemma":0.0019405817,"threshold_uncertainty_score":0.018959165},"labels":[],"label_agreement":null},{"id":"W3210046716","doi":"10.1145/3473042","title":"A New Approach for Mining Correlated Frequent Subgraphs","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Management Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; University of Manitoba","keywords":"Computer science; Data mining; Graph; Graphical model; Measure (data warehouse); Set (abstract data type); Theoretical computer science; Machine learning","score_opus":0.02602100110023654,"score_gpt":0.24681744209977155,"score_spread":0.22079644099953502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210046716","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015106194,0.000649107,0.9810104,0.00019004903,0.00008175708,0.00021415914,0.0007500402,0.0010719217,0.0009263121],"genre_scores_gemma":[0.1974431,0.000622994,0.79635626,0.00022619533,0.0002137143,0.00043289017,0.0027589682,0.00015790257,0.0017880664],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99632746,0.0006021242,0.0003924241,0.0009975039,0.001477801,0.00020267896],"domain_scores_gemma":[0.9962519,0.0014245472,0.0005704096,0.00055944035,0.0010178605,0.00017582916],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017377415,0.0010807774,0.001370007,0.009756515,0.0010098476,0.0016171918,0.0019353421,0.0010650047,0.0012553601],"category_scores_gemma":[0.007349736,0.0004886015,0.0019544808,0.008010058,0.00068606355,0.0026422157,0.0016767962,0.0011622172,0.00065162644],"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":[0.00052116736,0.00048327696,0.025627159,0.00084654667,0.001116006,0.0013798747,0.0006823329,0.05887666,0.02701619,0.04942416,0.01708446,0.8169421],"study_design_scores_gemma":[0.00007673847,0.00033597546,0.008425761,0.00010537019,0.0004071709,0.0029635185,0.00026142946,0.88170683,0.010784434,0.07099505,0.023837944,0.00009983578],"about_ca_topic_score_codex":0.0021945857,"about_ca_topic_score_gemma":0.0034809804,"teacher_disagreement_score":0.009756515,"about_ca_system_score_codex":0.000660619,"about_ca_system_score_gemma":0.001231583,"threshold_uncertainty_score":0.009190202},"labels":[],"label_agreement":null},{"id":"W3211231734","doi":"10.5281/zenodo.4084763","title":"Data Repository Selection: Criteria That Matter","year":2020,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Mining Algorithms and Applications","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":"Victoria Park","funders":"","keywords":"Selection (genetic algorithm); Computer science; Artificial intelligence","score_opus":0.09740853218669542,"score_gpt":0.2794724886981486,"score_spread":0.18206395651145318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211231734","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"reproducibility","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"reproducibility","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19853196,0.027034845,0.4469619,0.11557115,0.009332297,0.037903618,0.03256859,0.008334162,0.123761415],"genre_scores_gemma":[0.42180505,0.0033936456,0.49807122,0.010030751,0.0025963937,0.012790595,0.02161923,0.0048403144,0.024852715],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.7421916,0.10909888,0.05657029,0.014785736,0.06650315,0.010850283],"domain_scores_gemma":[0.48565948,0.19765316,0.031972952,0.05408777,0.20655166,0.024074994],"candidate_categories":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.18378158,0.0016634087,0.0045651407,0.018393394,0.008462291,0.029299967,0.006209814,0.006999224,0.01380319],"category_scores_gemma":[0.41305664,0.001256615,0.0028487297,0.02149394,0.0043395236,0.017568767,0.008976453,0.0037485159,0.012570186],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0036386421,0.001513272,0.0827554,0.011711931,0.0010055072,0.0015839197,0.0072839363,0.0028056176,0.015972875,0.053799026,0.2265273,0.5914025],"study_design_scores_gemma":[0.002284548,0.0014232189,0.05854807,0.012030888,0.0017516629,0.0050756163,0.017762756,0.033080168,0.04368515,0.113104425,0.71024275,0.0010107871],"about_ca_topic_score_codex":0.0036350007,"about_ca_topic_score_gemma":0.005604222,"teacher_disagreement_score":0.9937902,"about_ca_system_score_codex":0.0044349795,"about_ca_system_score_gemma":0.018610315,"threshold_uncertainty_score":0.97194153},"labels":[],"label_agreement":null},{"id":"W3212326024","doi":"10.1145/3487046","title":"Scalable Mining of High-Utility Sequential Patterns With Three-Tier MapReduce Model","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"Narodowe Centrum Badań i Rozwoju; Høgskulen på Vestlandet","keywords":"Computer science; Scalability; Correctness; Data mining; Completeness (order theory); Computation; Scale (ratio); Database; Algorithm","score_opus":0.05944832735846505,"score_gpt":0.28622481848680353,"score_spread":0.22677649112833848,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212326024","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040699642,0.00026293215,0.954759,0.00036084384,0.00004706087,0.00016915494,0.00046283123,0.001503985,0.0017346542],"genre_scores_gemma":[0.6603029,0.00048574808,0.33424774,0.00015905687,0.00006949661,0.00031837748,0.0011394785,0.0001226553,0.003154552],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989473,0.0001765561,0.000078411555,0.00028560398,0.00034465434,0.00016754138],"domain_scores_gemma":[0.99912006,0.00022245687,0.000065005406,0.0002340859,0.00026712168,0.00009122945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011341069,0.0006174631,0.0009325662,0.00078743784,0.0007444914,0.0012244397,0.002463921,0.0004940712,0.0011360202],"category_scores_gemma":[0.0021451805,0.00044881503,0.0014130144,0.0014526948,0.00048290362,0.0020525418,0.0012652676,0.00064970844,0.00033594563],"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":[0.0005822737,0.00042695412,0.0110723255,0.0004835542,0.00036171288,0.00096212665,0.00051524915,0.7235528,0.01425434,0.05944934,0.011375285,0.17696403],"study_design_scores_gemma":[0.000015714528,0.000033633234,0.00035969142,0.0000032051134,0.0000207153,0.000102937214,0.00004794797,0.98102826,0.0011664644,0.016091475,0.0011210613,0.000008944599],"about_ca_topic_score_codex":0.008288474,"about_ca_topic_score_gemma":0.010885433,"teacher_disagreement_score":0.008288474,"about_ca_system_score_codex":0.00070872216,"about_ca_system_score_gemma":0.0024300606,"threshold_uncertainty_score":0.016480446},"labels":[],"label_agreement":null},{"id":"W3214669299","doi":"10.1007/978-1-4939-7131-2_100665","title":"Mining Complex Networks","year":2018,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Computer science","score_opus":0.05084855379058301,"score_gpt":0.2621994594578493,"score_spread":0.21135090566726628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214669299","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0088694,0.029752778,0.8136216,0.0051199053,0.0016789571,0.00023177719,0.003712228,0.003810197,0.13320313],"genre_scores_gemma":[0.09441764,0.050955776,0.5897591,0.0017562971,0.0029733574,0.0005046389,0.017785655,0.0014055752,0.24044198],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.999632,0.000040772644,0.000018257013,0.0001265006,0.00016718426,0.000015238952],"domain_scores_gemma":[0.9991602,0.00044434326,0.00005086078,0.00017294455,0.00014084823,0.000030813077],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053189637,0.0011678721,0.0006945295,0.002489963,0.00058713433,0.002275847,0.0013556283,0.00081452186,0.022007963],"category_scores_gemma":[0.00349603,0.0006238162,0.0006651306,0.0029601634,0.00053834135,0.004391688,0.0014669766,0.0014752279,0.014071544],"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":[0.000031103704,0.00004491646,0.0008779247,0.00067028654,0.00008432792,0.00013369152,0.00016474257,0.007952058,0.002627065,0.07329112,0.12107119,0.7930516],"study_design_scores_gemma":[0.000011164635,0.000034478064,0.0015434588,0.0004792044,0.00007634192,0.000983757,0.0001553311,0.062399436,0.0068629645,0.41047776,0.5169349,0.00004120184],"about_ca_topic_score_codex":0.00048304565,"about_ca_topic_score_gemma":0.00096086686,"teacher_disagreement_score":0.022007963,"about_ca_system_score_codex":0.00053170096,"about_ca_system_score_gemma":0.0004248579,"threshold_uncertainty_score":0.073624015},"labels":[],"label_agreement":null},{"id":"W3217255868","doi":"10.1111/exsy.12881","title":"A horizontal partitioning‐based method for frequent pattern mining in transport timetable","year":2021,"lang":"en","type":"article","venue":"Expert Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saskatchewan Polytechnic","funders":"Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Computer science; Association rule learning; Data mining; Redundancy (engineering); Task (project management)","score_opus":0.031189390648775666,"score_gpt":0.30665926999409504,"score_spread":0.27546987934531936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3217255868","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03565594,0.00025786718,0.9604968,0.00012846824,0.00003985073,0.0002464797,0.00078913005,0.0015043332,0.00088111],"genre_scores_gemma":[0.15032832,0.00012530145,0.8466025,0.00004000653,0.000027988788,0.00029272755,0.0016047,0.000093031544,0.0008854806],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991322,0.00021341929,0.0001259766,0.00018401965,0.000281,0.000063362044],"domain_scores_gemma":[0.996867,0.0018365778,0.00026014412,0.00022666599,0.000740676,0.00006894927],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092354923,0.000498571,0.0005907425,0.0033710983,0.00055374263,0.00075610814,0.00079548464,0.00048652684,0.002685761],"category_scores_gemma":[0.0058385297,0.00033524528,0.000782694,0.0030101414,0.0002472699,0.0007596561,0.000541622,0.0005385587,0.0007649561],"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":[0.00035346043,0.00024430774,0.00943429,0.00041536003,0.00024081848,0.00049460086,0.0003762563,0.06875113,0.017094856,0.006946329,0.0070392922,0.88860935],"study_design_scores_gemma":[0.00006528914,0.000103291626,0.0041941847,0.000043662916,0.000054955377,0.00050679414,0.00018849852,0.974462,0.0077481065,0.0060743885,0.0065324763,0.000026427944],"about_ca_topic_score_codex":0.004502133,"about_ca_topic_score_gemma":0.0060787783,"teacher_disagreement_score":0.004502133,"about_ca_system_score_codex":0.00031662555,"about_ca_system_score_gemma":0.00087847596,"threshold_uncertainty_score":0.008984745},"labels":[],"label_agreement":null},{"id":"W322462744","doi":"10.1007/11535706_12","title":"Privacy-Preserving Collaborative Association Rule Mining","year":2005,"lang":"en","type":"article","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms 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 Ottawa","funders":"","keywords":"Association rule learning; Computer science; Data mining; Data science","score_opus":0.011467744624427624,"score_gpt":0.2665805409993017,"score_spread":0.25511279637487405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W322462744","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018302921,0.0003419509,0.97853684,0.00047393434,0.00007941362,0.000096217955,0.000269195,0.00054042734,0.001358988],"genre_scores_gemma":[0.6374813,0.00045294134,0.35548767,0.00044201332,0.00033527875,0.00023682845,0.0014104063,0.00010791861,0.0040456634],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.972765,0.01096866,0.0021823691,0.0040517165,0.008593925,0.001438256],"domain_scores_gemma":[0.9077415,0.033161253,0.0036705318,0.049465343,0.0048167706,0.0011446088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014209376,0.00100386,0.0034867497,0.0018928491,0.002460184,0.0042352923,0.0062745595,0.0029674398,0.0020955729],"category_scores_gemma":[0.06414599,0.0014837027,0.002534019,0.003987825,0.0019921314,0.007822159,0.0077734245,0.0033320957,0.0017389338],"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":[0.0034570019,0.0012823396,0.014718301,0.0005757786,0.0010058266,0.0019456182,0.0012117131,0.15404922,0.01802854,0.10132346,0.015365167,0.68703705],"study_design_scores_gemma":[0.0002479607,0.000477826,0.0012019958,0.000050697596,0.0002954784,0.0031296173,0.00031114,0.7794987,0.024134135,0.18370926,0.006865036,0.00007813451],"about_ca_topic_score_codex":0.0007657165,"about_ca_topic_score_gemma":0.000998468,"teacher_disagreement_score":0.014209376,"about_ca_system_score_codex":0.0006148413,"about_ca_system_score_gemma":0.0029719549,"threshold_uncertainty_score":0.07514727},"labels":[],"label_agreement":null},{"id":"W32592253","doi":"10.1007/3-540-45105-6_38","title":"PalmPrints: A Novel Co-evolutionary Algorithm for Clustering Finger Images","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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":"Concordia University","funders":"","keywords":"Cluster analysis; Computer science; Fitness function; Artificial intelligence; Genetic algorithm; Correlation clustering; Pattern recognition (psychology); Evolutionary algorithm; Canopy clustering algorithm; Algorithm; Machine learning","score_opus":0.023760405071552946,"score_gpt":0.2710031404315853,"score_spread":0.24724273536003236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W32592253","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0072898194,0.00021927673,0.99059045,0.00005559342,0.000068241265,0.000039930135,0.00003292259,0.00088303233,0.00082064647],"genre_scores_gemma":[0.06713752,0.00019406404,0.92732614,0.000116177376,0.00005231947,0.000131595,0.00014319923,0.0002917517,0.0046072453],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991278,0.0001333321,0.000041012132,0.00020170539,0.00042156567,0.00007471775],"domain_scores_gemma":[0.9991972,0.00025998492,0.000059562215,0.00013683816,0.00029303014,0.000053429936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001134632,0.001017499,0.0016942855,0.0016065271,0.00079639856,0.0012467175,0.0026497836,0.0020601489,0.0035332127],"category_scores_gemma":[0.0022037013,0.0007328154,0.0009113216,0.0024323252,0.0006943396,0.0015305877,0.0016680689,0.0012708876,0.0014319296],"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":[0.0001848273,0.0001399678,0.0012233752,0.00011310372,0.00018116133,0.00014033631,0.00013991843,0.16081348,0.024835823,0.0048684413,0.004867903,0.80249166],"study_design_scores_gemma":[0.000027671347,0.000055669538,0.0004189173,0.000010275854,0.000028827839,0.00018133222,0.000023368997,0.98695415,0.006628643,0.0023495771,0.0032977343,0.000023712479],"about_ca_topic_score_codex":0.003595095,"about_ca_topic_score_gemma":0.004984521,"teacher_disagreement_score":0.003595095,"about_ca_system_score_codex":0.000570612,"about_ca_system_score_gemma":0.00085320417,"threshold_uncertainty_score":0.01181978},"labels":[],"label_agreement":null},{"id":"W34874223","doi":"10.1007/978-3-642-23544-3_28","title":"Learning Actions in Complex Software Systems","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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":"University of Alberta","funders":"","keywords":"Computer science; Event (particle physics); Set (abstract data type); Data mining; Process (computing); Euclidean distance; Service (business); Software system; Software architecture; Software; Metric (unit); Service-oriented architecture; Process mining; Web service; Server; Artificial intelligence; Software engineering; Machine learning; Business process; Programming language; World Wide Web; Work in process; Business process management","score_opus":0.05122646729565192,"score_gpt":0.2698560062218605,"score_spread":0.2186295389262086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W34874223","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.088996105,0.0010721126,0.90127605,0.0005486411,0.000040716775,0.00003325029,0.00012728901,0.0005475429,0.0073582097],"genre_scores_gemma":[0.79589504,0.0014107763,0.19359583,0.00008464359,0.00006063522,0.000095030846,0.0004286723,0.000080230086,0.008349124],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99975115,0.00008186122,0.000015650476,0.000072791096,0.000058109657,0.000020388994],"domain_scores_gemma":[0.9970457,0.0025914584,0.00010281989,0.00010381424,0.000090211724,0.00006600685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005511096,0.00049106934,0.00035647632,0.00048268982,0.0002452556,0.0007536242,0.000612226,0.00055068824,0.0027755932],"category_scores_gemma":[0.003910884,0.00026260284,0.0003710199,0.00052618637,0.0008199872,0.0016897122,0.0007987619,0.0012874741,0.00033452726],"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":[0.00010061696,0.00013735578,0.008480491,0.00032751096,0.00007081685,0.00016804034,0.00073299144,0.37247285,0.0030670206,0.11609212,0.0034216456,0.4949286],"study_design_scores_gemma":[0.0000072971657,0.000045727833,0.001185958,0.000038623173,0.000011652721,0.00004125748,0.000101495665,0.8290713,0.0011391361,0.16634095,0.0020079294,0.000008586297],"about_ca_topic_score_codex":0.0026601295,"about_ca_topic_score_gemma":0.0043034134,"teacher_disagreement_score":0.0027755932,"about_ca_system_score_codex":0.00047062922,"about_ca_system_score_gemma":0.00046405973,"threshold_uncertainty_score":0.009285212},"labels":[],"label_agreement":null},{"id":"W35054235","doi":"10.3390/diagnostics12010068","title":"Improving Frequent Subgraph Mining in the Presence of Symmetry.","year":2007,"lang":"en","type":"article","venue":"Mining and Learning with Graphs","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Induced subgraph isomorphism problem; Symmetry (geometry); Data mining; Subgraph isomorphism problem; Theoretical computer science; Mathematics; Graph","score_opus":0.010704976805498614,"score_gpt":0.23405675567825945,"score_spread":0.22335177887276084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W35054235","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19360158,0.0031016476,0.7769606,0.0011053318,0.0003067621,0.00078079366,0.010405401,0.010022363,0.0037155063],"genre_scores_gemma":[0.49573398,0.0008537027,0.4750186,0.00041606012,0.00029648564,0.0003967216,0.025019875,0.00045980586,0.0018047913],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954607,0.0012347323,0.00044332122,0.0013492994,0.0011064707,0.0004054588],"domain_scores_gemma":[0.988775,0.006098251,0.0013218353,0.002208455,0.0012823716,0.00031412233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034469177,0.001548424,0.0023896906,0.0058788885,0.0013185587,0.0021105814,0.0026149137,0.001360917,0.0019089617],"category_scores_gemma":[0.023858061,0.00084696145,0.0029502583,0.004237018,0.00064447377,0.0034387952,0.0022069719,0.0011974416,0.0012933421],"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":[0.0012608184,0.0008545194,0.09031134,0.0016775455,0.0014995646,0.0018913504,0.0008040063,0.0904121,0.019263998,0.01561405,0.033346947,0.74306375],"study_design_scores_gemma":[0.00011519685,0.0002735159,0.011123451,0.000101749705,0.00040177637,0.0015699667,0.0004904116,0.9207342,0.0057580327,0.049462672,0.009926069,0.000042869182],"about_ca_topic_score_codex":0.005415043,"about_ca_topic_score_gemma":0.008596459,"teacher_disagreement_score":0.0058788885,"about_ca_system_score_codex":0.00070289115,"about_ca_system_score_gemma":0.0018647868,"threshold_uncertainty_score":0.018229306},"labels":[],"label_agreement":null},{"id":"W36161844","doi":"10.1136/bmjophth-2021-000914","title":"k-tablet Structures and Crossover on Latent Variables for Real-Coded GA.","year":2002,"lang":"en","type":"article","venue":"BMJ Open Ophthalmology","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research","keywords":"Crossover; Latent variable; Computer science; Statistics; Mathematics; Artificial intelligence","score_opus":0.10717352568208172,"score_gpt":0.37740602660187816,"score_spread":0.27023250091979645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W36161844","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031543165,0.001058287,0.9619439,0.00095270126,0.00016928457,0.00026594286,0.0009658128,0.001151134,0.0019498393],"genre_scores_gemma":[0.41006777,0.0011359291,0.5731059,0.00038990073,0.000341621,0.0013033729,0.0026295146,0.00036452347,0.01066152],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9940415,0.0035150861,0.00029076514,0.0010315306,0.00052850385,0.00059259153],"domain_scores_gemma":[0.9422443,0.046301376,0.0020452219,0.007004842,0.0016174379,0.00078679406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015542693,0.0010573026,0.0023578396,0.0029904908,0.0015333082,0.0019806835,0.004227828,0.002742959,0.014637875],"category_scores_gemma":[0.06429997,0.0007249152,0.0026611898,0.002802651,0.0039407043,0.0046962094,0.0034042543,0.005029769,0.0019568438],"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":[0.00088916684,0.00033692882,0.0049553043,0.00024076819,0.0002711917,0.0002675665,0.00060411496,0.2847807,0.00046828328,0.51098734,0.009581655,0.18661697],"study_design_scores_gemma":[0.0000930238,0.00009181273,0.00095054816,0.000068938956,0.00003576741,0.000052610907,0.000055026077,0.73312473,0.00019654863,0.26341957,0.0018799803,0.000031456028],"about_ca_topic_score_codex":0.014105051,"about_ca_topic_score_gemma":0.017878018,"teacher_disagreement_score":0.015542693,"about_ca_system_score_codex":0.0028110044,"about_ca_system_score_gemma":0.003047038,"threshold_uncertainty_score":0.08219862},"labels":[],"label_agreement":null},{"id":"W37574108","doi":"10.1016/j.neuroscience.2023.08.013","title":"Proceedings of the Second international conference on Advanced Data Mining and Applications","year":2005,"lang":"en","type":"article","venue":"Advanced Data Mining and Applications","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Data science","score_opus":0.04679952910546293,"score_gpt":0.31309061575132424,"score_spread":0.2662910866458613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W37574108","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0233624,0.11724678,0.70992005,0.030029545,0.035178613,0.0022532793,0.008770881,0.010618812,0.062619634],"genre_scores_gemma":[0.10555009,0.07220294,0.6032426,0.007098957,0.012439712,0.0032530157,0.04257665,0.001595142,0.15204091],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99509627,0.0013892853,0.0007890351,0.00064958096,0.0018471015,0.00022867082],"domain_scores_gemma":[0.9892664,0.0036447323,0.0003151786,0.0019253778,0.0040583783,0.00078983034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009300333,0.0019102206,0.0033728355,0.0038936962,0.0012553385,0.006390891,0.0030201755,0.0023977628,0.03442465],"category_scores_gemma":[0.017578406,0.00067499414,0.0022648242,0.0036247547,0.0009993226,0.004556079,0.0025066934,0.0037295315,0.018309794],"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":[0.0003184246,0.00025910055,0.0024208683,0.00073144573,0.00036681184,0.00033500453,0.00016686713,0.002746754,0.0020498561,0.006396577,0.23209128,0.7521171],"study_design_scores_gemma":[0.00010641906,0.00031417017,0.004403342,0.0007378241,0.00028090383,0.0012933948,0.00040160658,0.06989038,0.0036855428,0.030978503,0.887809,0.000098859346],"about_ca_topic_score_codex":0.002689439,"about_ca_topic_score_gemma":0.0022825329,"teacher_disagreement_score":0.03442465,"about_ca_system_score_codex":0.0009952186,"about_ca_system_score_gemma":0.003275208,"threshold_uncertainty_score":0.115161955},"labels":[],"label_agreement":null},{"id":"W39051832","doi":"10.1137/1.9781611972740.16","title":"Basic Association Rules","year":2004,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Association rule learning; Computer science; Association (psychology); Probabilistic logic; Data mining; Conditional probability; Inference; Set (abstract data type); Theoretical computer science; Artificial intelligence; Mathematics; Programming language; Statistics","score_opus":0.010856564883678714,"score_gpt":0.2335207612899836,"score_spread":0.2226641964063049,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W39051832","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016255885,0.00907626,0.8918716,0.0033681463,0.0011564508,0.0042064106,0.036001105,0.004592844,0.03347128],"genre_scores_gemma":[0.119321525,0.006474627,0.82136756,0.0019897253,0.00090387004,0.004066351,0.03928386,0.00037894383,0.0062135113],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97531396,0.0043587047,0.004349374,0.006842575,0.008432591,0.0007027441],"domain_scores_gemma":[0.9603363,0.021816384,0.0050798366,0.0049893046,0.007174363,0.00060368574],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011509847,0.0029521275,0.0030167187,0.011923568,0.0023736502,0.0071538417,0.005286504,0.002614107,0.0149627635],"category_scores_gemma":[0.0570563,0.0012065007,0.003977416,0.011559104,0.0023757818,0.009634248,0.0031362562,0.0033915835,0.00982005],"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":[0.0008218651,0.0005825065,0.032430317,0.007838426,0.0020113548,0.0031158878,0.0010784586,0.021661265,0.0053672562,0.23088779,0.10731802,0.5868869],"study_design_scores_gemma":[0.00018691129,0.00028792527,0.006107315,0.002114512,0.0010258057,0.006714595,0.0008244043,0.05935776,0.0058151833,0.6438068,0.27353188,0.00022687989],"about_ca_topic_score_codex":0.001354719,"about_ca_topic_score_gemma":0.0018071445,"teacher_disagreement_score":0.0149627635,"about_ca_system_score_codex":0.0013707848,"about_ca_system_score_gemma":0.003929783,"threshold_uncertainty_score":0.060870647},"labels":[],"label_agreement":null},{"id":"W391464563","doi":"10.1007/978-3-319-06608-0_21","title":"Mining Contrast Subspaces","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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":"Linear subspace; Contrast (vision); Computer science; Pruning; Set (abstract data type); Object (grammar); Time complexity; Data mining; Polynomial; Algorithm; Artificial intelligence; Pattern recognition (psychology); Mathematics; Programming language","score_opus":0.01654142079109158,"score_gpt":0.24524898497943437,"score_spread":0.2287075641883428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W391464563","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.078623034,0.0036981136,0.887856,0.000811516,0.0003638683,0.00024457206,0.0035525397,0.00515848,0.019691829],"genre_scores_gemma":[0.43318844,0.0025189535,0.5212375,0.00043934656,0.00048880413,0.00031769348,0.022652589,0.0011887171,0.01796794],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990972,0.00012294202,0.000052807616,0.00038939618,0.00024165897,0.00009601133],"domain_scores_gemma":[0.99880016,0.00037904514,0.00012114306,0.0003164604,0.00028984703,0.000093421244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007805021,0.0013482075,0.0011563792,0.0034715664,0.0010233597,0.0026466944,0.0013772931,0.0009940279,0.010035281],"category_scores_gemma":[0.0040784343,0.00058197154,0.0014602579,0.0030283607,0.0008040702,0.0033346654,0.0023808233,0.0018069906,0.0063106045],"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":[0.00067115674,0.00022941905,0.008228978,0.00037908225,0.00022864672,0.00043398378,0.00025689843,0.008809305,0.026090631,0.03546297,0.029802516,0.8894064],"study_design_scores_gemma":[0.00014172208,0.00057240145,0.012437935,0.000371611,0.00041724247,0.0034611854,0.0012993984,0.5287139,0.043832522,0.30642217,0.10219557,0.0001343935],"about_ca_topic_score_codex":0.00080410886,"about_ca_topic_score_gemma":0.0013670119,"teacher_disagreement_score":0.010035281,"about_ca_system_score_codex":0.0003753427,"about_ca_system_score_gemma":0.0005869897,"threshold_uncertainty_score":0.033571362},"labels":[],"label_agreement":null},{"id":"W39340227","doi":"","title":"Data mining in mental health","year":2006,"lang":"en","type":"article","venue":"international conference on Modelling and simulation","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Data mining; Association rule learning; Cluster analysis; Naive Bayes classifier; Decision tree; Statistical classification; Machine learning; Process (computing); Artificial intelligence; Support vector machine","score_opus":0.14957696402203455,"score_gpt":0.3665657059767474,"score_spread":0.21698874195471288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W39340227","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008471801,0.10580974,0.8149611,0.028227169,0.0023443,0.0017163275,0.0076870522,0.0024017906,0.028380731],"genre_scores_gemma":[0.10036866,0.07238361,0.8028781,0.005616924,0.0022737645,0.0028355496,0.007746526,0.0002810012,0.0056159603],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98652947,0.0069199307,0.001446435,0.0018341447,0.0030527883,0.00021733357],"domain_scores_gemma":[0.970155,0.023516124,0.0016604993,0.0022955155,0.0019440494,0.00042878021],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012448757,0.0012527406,0.002281293,0.0070120147,0.0011501717,0.0056905053,0.0030489305,0.002659545,0.0050897445],"category_scores_gemma":[0.035182733,0.0007466812,0.0015772494,0.014200173,0.0024640488,0.0051220423,0.0034832258,0.003749709,0.002891985],"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":[0.00020234617,0.00024144103,0.00944681,0.0065599475,0.00072654587,0.0006287344,0.001043349,0.023687044,0.0009846904,0.2712622,0.056514375,0.62870246],"study_design_scores_gemma":[0.00010313722,0.00022344581,0.0073488285,0.0041760243,0.00020238114,0.0013278004,0.0011618031,0.07630078,0.00173637,0.58102465,0.32623512,0.00015968144],"about_ca_topic_score_codex":0.0029974952,"about_ca_topic_score_gemma":0.0019644191,"teacher_disagreement_score":0.012448757,"about_ca_system_score_codex":0.0024736808,"about_ca_system_score_gemma":0.0033946743,"threshold_uncertainty_score":0.06583613},"labels":[],"label_agreement":null},{"id":"W40638181","doi":"10.4018/978-1-60566-010-3.ch011","title":"Association Bundle Identification","year":2009,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Association (psychology); Association rule learning; Statement (logic); Set (abstract data type); Identification (biology); Product (mathematics); Computer science; Mathematics; Artificial intelligence; Psychology; Philosophy; Epistemology","score_opus":0.016529661215263322,"score_gpt":0.25038603042742635,"score_spread":0.23385636921216302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W40638181","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011232805,0.0017114136,0.916039,0.001038054,0.0012550827,0.0019792034,0.012898528,0.012874532,0.0409714],"genre_scores_gemma":[0.10824024,0.0015985076,0.81287885,0.0007702705,0.00052456744,0.0023424975,0.03632563,0.0017950236,0.035524365],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99110645,0.0012987535,0.001075829,0.0023966664,0.003462392,0.0006598672],"domain_scores_gemma":[0.9858095,0.0028161043,0.0011928469,0.003661659,0.005978874,0.00054111396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004989108,0.002025824,0.0021828879,0.010557126,0.0023393445,0.0056803916,0.0037824828,0.0028140054,0.04371049],"category_scores_gemma":[0.026335184,0.0009406306,0.002312448,0.010559457,0.0008419866,0.007522818,0.0062893895,0.0024903954,0.034613516],"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":[0.00044601702,0.00027438806,0.013840437,0.0011125809,0.000256698,0.00074330106,0.00071614876,0.0045863073,0.005230737,0.054860745,0.14417467,0.773758],"study_design_scores_gemma":[0.00012545183,0.00032194017,0.007816249,0.0007166607,0.0003421389,0.004868148,0.001597724,0.15621659,0.02166754,0.18443996,0.62166816,0.00021946603],"about_ca_topic_score_codex":0.0014683813,"about_ca_topic_score_gemma":0.0015189897,"teacher_disagreement_score":0.04371049,"about_ca_system_score_codex":0.0010515783,"about_ca_system_score_gemma":0.0034640967,"threshold_uncertainty_score":0.14622617},"labels":[],"label_agreement":null},{"id":"W406481330","doi":"10.1007/978-3-319-13186-3_37","title":"A Scalable Data Analytics Algorithm for Mining Frequent Patterns from Uncertain Data","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms 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 Manitoba","funders":"","keywords":"Computer science; Scalability; Data mining; Tree (set theory); Analytics; Data analysis; Association rule learning; Data structure; Tree structure; Algorithm; Database; Binary tree; Mathematics","score_opus":0.07842976898321406,"score_gpt":0.3042055701348772,"score_spread":0.22577580115166312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W406481330","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009170138,0.0006139545,0.9848525,0.00033847778,0.00012585214,0.00020231846,0.000900321,0.003082647,0.0007137568],"genre_scores_gemma":[0.052408084,0.0003133306,0.9427687,0.00014415948,0.0001534479,0.00028900403,0.0024729362,0.00013658381,0.00131379],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99835026,0.00015245147,0.00019836261,0.0004060411,0.0007973258,0.00009545794],"domain_scores_gemma":[0.99671835,0.0017088744,0.00021117635,0.0005426869,0.0007024257,0.00011643284],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017303185,0.0013066498,0.002035337,0.002726944,0.0010685353,0.0018984039,0.002689517,0.0011849649,0.0034252682],"category_scores_gemma":[0.007905211,0.0007556151,0.001456203,0.0055049467,0.000594589,0.0037857848,0.0023025505,0.002086702,0.0018349908],"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":[0.00039299403,0.00031547618,0.0023936767,0.00029279018,0.00018543005,0.00031964132,0.00014949197,0.049839187,0.009304418,0.008336646,0.021282457,0.90718794],"study_design_scores_gemma":[0.00009981728,0.00009278695,0.00064814824,0.000032180582,0.000061918574,0.00033481236,0.00007720243,0.9567978,0.0040794876,0.032281183,0.0054708715,0.000023768245],"about_ca_topic_score_codex":0.0031301274,"about_ca_topic_score_gemma":0.004507443,"teacher_disagreement_score":0.0034252682,"about_ca_system_score_codex":0.00071536534,"about_ca_system_score_gemma":0.0019415509,"threshold_uncertainty_score":0.011458695},"labels":[],"label_agreement":null},{"id":"W413120383","doi":"","title":"Frequent Itemset Mining for Query Expansion in Microblog Ad-hoc Search","year":2012,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Microblogging; Computer science; Social media; Data mining; Information retrieval; Process (computing); Volume (thermodynamics); World Wide Web","score_opus":0.07056403817857194,"score_gpt":0.31730981864514873,"score_spread":0.2467457804665768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W413120383","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6925686,0.0021491856,0.2960187,0.0008883944,0.00015468987,0.00064536044,0.0019856845,0.0035742268,0.0020151576],"genre_scores_gemma":[0.79441774,0.00025102656,0.20299293,0.000085780695,0.000068240355,0.00014734015,0.0014555568,0.000040688956,0.0005406972],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982621,0.00058932934,0.0002468042,0.00026010204,0.0005069486,0.0001347468],"domain_scores_gemma":[0.99162066,0.0057381615,0.00062379264,0.0005853488,0.0011601065,0.00027190603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028712007,0.00065485074,0.0015095889,0.0042690127,0.00078669644,0.0010717047,0.0013899541,0.00074116397,0.0011569153],"category_scores_gemma":[0.010088167,0.00037270482,0.000727421,0.004361131,0.00030560757,0.0015050784,0.0006418093,0.0008002723,0.0006831712],"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":[0.002434334,0.0016113681,0.059366167,0.0007651269,0.00052536424,0.001032846,0.0005840472,0.10366636,0.028064843,0.003543699,0.010149271,0.78825665],"study_design_scores_gemma":[0.000058428657,0.00023759078,0.0057917405,0.000018434113,0.00006174045,0.00037293287,0.00020316501,0.9815336,0.008045097,0.0026519885,0.0010056606,0.000019555067],"about_ca_topic_score_codex":0.005292965,"about_ca_topic_score_gemma":0.004566489,"teacher_disagreement_score":0.005292965,"about_ca_system_score_codex":0.00077110843,"about_ca_system_score_gemma":0.0010558038,"threshold_uncertainty_score":0.015184522},"labels":[],"label_agreement":null},{"id":"W4200297779","doi":"10.1109/iscc53001.2021.9631495","title":"Apriori-Roaring-Parallel: Frequent pattern mining based on compressed bitmaps with OpenMP","year":2021,"lang":"en","type":"article","venue":"2021 IEEE Symposium on Computers and Communications (ISCC)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Humber Polytechnic","funders":"","keywords":"Bitmap; Computer science; Apriori algorithm; Association rule learning; Data mining; Process (computing); A priori and a posteriori; Parallel computing; Artificial intelligence","score_opus":0.023817647236226726,"score_gpt":0.25122669662343805,"score_spread":0.22740904938721132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200297779","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03871705,0.00085532,0.93630916,0.00035628973,0.0001831282,0.00046647544,0.0012823904,0.018835194,0.002995036],"genre_scores_gemma":[0.118455246,0.00037656576,0.8753602,0.0001415286,0.00006193183,0.0006119326,0.0025818518,0.000368547,0.0020422414],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986507,0.00028675314,0.0001825553,0.0002800101,0.00046191184,0.00013810137],"domain_scores_gemma":[0.99616015,0.0015323723,0.00032796673,0.0010644103,0.0008045425,0.00011047073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013610214,0.0013873192,0.0011530893,0.0025682575,0.00088336563,0.0018630825,0.0028765642,0.0009207092,0.00447009],"category_scores_gemma":[0.007249176,0.0008651237,0.0010625614,0.004425102,0.00072230655,0.0029320312,0.0016912741,0.0012080697,0.0017214671],"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":[0.0025724324,0.000627897,0.005595266,0.0009052816,0.00039924367,0.000765536,0.00051793497,0.09849696,0.024400875,0.014342847,0.021780616,0.82959515],"study_design_scores_gemma":[0.00024715686,0.00037265196,0.0012269091,0.000047379865,0.00008255106,0.00069803314,0.00017025281,0.93542624,0.02851655,0.021668876,0.0114781875,0.00006522696],"about_ca_topic_score_codex":0.003122225,"about_ca_topic_score_gemma":0.002798769,"teacher_disagreement_score":0.00447009,"about_ca_system_score_codex":0.00053003064,"about_ca_system_score_gemma":0.0016820586,"threshold_uncertainty_score":0.014953911},"labels":[],"label_agreement":null},{"id":"W4205167518","doi":"10.1007/978-3-319-71404-2_3","title":"Association Measures and Matrices","year":2018,"lang":"en","type":"book-chapter","venue":"Use R!","topic":"Data Mining Algorithms 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":"Université de Montréal","funders":"","keywords":"Ordination; Association (psychology); Measure (data warehouse); Multivariate statistics; Cluster analysis; Matrix (chemical analysis); Mathematics; Computer science; Data mining; Statistics; Psychology","score_opus":0.03266237514031254,"score_gpt":0.23798216440699868,"score_spread":0.20531978926668615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205167518","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018479722,0.07378841,0.7067099,0.007726991,0.009692984,0.0001092171,0.0021081984,0.002801273,0.19521508],"genre_scores_gemma":[0.056492127,0.062297758,0.51751506,0.0067657186,0.02134096,0.0009011271,0.0060278815,0.003398137,0.32526127],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.997707,0.00061868876,0.00017137984,0.00058153225,0.00084739673,0.00007396191],"domain_scores_gemma":[0.9968844,0.0017216132,0.00019696978,0.00052344095,0.0005610087,0.00011259373],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018975025,0.0023750744,0.0016215668,0.005377376,0.0009830334,0.0049126474,0.001486011,0.0015318088,0.036869794],"category_scores_gemma":[0.010079557,0.0008140369,0.0010455496,0.008265315,0.0027113806,0.0077857436,0.002469909,0.0036368887,0.03157768],"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":[0.0000136895615,0.0000250873,0.0002004399,0.000443925,0.00004201801,0.00004712355,0.00014885374,0.000804036,0.00042962437,0.5624386,0.16371337,0.2716932],"study_design_scores_gemma":[0.0000033918097,0.000016003642,0.0001904176,0.00013888454,0.00001637085,0.0002038737,0.000050019848,0.0024266301,0.00029353614,0.75445956,0.24218076,0.000020499092],"about_ca_topic_score_codex":0.0006762523,"about_ca_topic_score_gemma":0.00072873867,"teacher_disagreement_score":0.036869794,"about_ca_system_score_codex":0.0008982213,"about_ca_system_score_gemma":0.0010179912,"threshold_uncertainty_score":0.12334174},"labels":[],"label_agreement":null},{"id":"W4205239629","doi":"10.1109/bigdata52589.2021.9671747","title":"A Scalable Multi-factor Fault Analysis Framework for Information Systems","year":2021,"lang":"en","type":"article","venue":"2021 IEEE International Conference on Big Data (Big Data)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Exfo Electro-Optical Engineering (Canada); Concordia University","funders":"","keywords":"Computer science; Data mining; Scalability; Association rule learning; Set (abstract data type); SPARK (programming language); Fault (geology); Database","score_opus":0.3177522349045409,"score_gpt":0.3802030307136332,"score_spread":0.0624507958090923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205239629","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020671678,0.00014230522,0.9933693,0.000102169906,0.00002393257,0.00007369009,0.00030009396,0.003538398,0.0003830358],"genre_scores_gemma":[0.13549139,0.00022808963,0.8615377,0.00007545731,0.00008004592,0.00023593537,0.0011559919,0.0002885906,0.0009067346],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846894,0.0002853246,0.00013263586,0.0002760191,0.0006970665,0.00014013308],"domain_scores_gemma":[0.99804354,0.00074221205,0.00020866974,0.00035799466,0.0005519372,0.0000955829],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002117059,0.0016434385,0.0013822787,0.0022246747,0.0006546564,0.0016501162,0.0018111124,0.00078276935,0.0025270237],"category_scores_gemma":[0.005717058,0.00054199714,0.0023564189,0.001674252,0.00052850106,0.0021141074,0.0013579761,0.0015111559,0.00086482614],"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":[0.00020638338,0.00015151215,0.00526179,0.00037796327,0.00037580315,0.00042742796,0.0001975978,0.6939367,0.0051378845,0.046713024,0.011132228,0.23608172],"study_design_scores_gemma":[0.0000107732685,0.00002001287,0.00022451057,0.0000095077485,0.000018496066,0.00004358712,0.000014458566,0.98042333,0.0006137924,0.01665936,0.0019533853,0.000008831183],"about_ca_topic_score_codex":0.010318472,"about_ca_topic_score_gemma":0.011652681,"teacher_disagreement_score":0.010318472,"about_ca_system_score_codex":0.0009845945,"about_ca_system_score_gemma":0.0021254143,"threshold_uncertainty_score":0.020516813},"labels":[],"label_agreement":null},{"id":"W4205354799","doi":"10.1007/s10489-021-03134-3","title":"Efficient evolutionary computation model of closed high-utility itemset mining","year":2022,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Data Mining Algorithms 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":"Brandon University","funders":"","keywords":"Computer science; Scalability; Data mining; SPARK (programming language); Categorization; Big data; Affinity analysis; Association rule learning; Artificial intelligence; Database","score_opus":0.03281532424979353,"score_gpt":0.26038128930395554,"score_spread":0.22756596505416202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205354799","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052751433,0.00028292797,0.94303715,0.00031478092,0.000048884656,0.00007322308,0.00012703802,0.00016646854,0.0031981121],"genre_scores_gemma":[0.6889425,0.00036658836,0.30194876,0.00013826293,0.00005417538,0.00025004114,0.00045014318,0.00005897058,0.007790419],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992843,0.00018063802,0.000040916548,0.00016602981,0.00022126385,0.00010697795],"domain_scores_gemma":[0.9988469,0.000586479,0.0000626675,0.00011426927,0.00032742487,0.00006223498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009505973,0.00041540765,0.0011067673,0.0011028937,0.00086858624,0.0012992821,0.0021843372,0.0009582868,0.0027125801],"category_scores_gemma":[0.0036529603,0.00034827556,0.0007856584,0.0018252626,0.0006512509,0.0014765053,0.0010320628,0.0008893272,0.00030409274],"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":[0.00013800645,0.00013547251,0.0029070193,0.00007932356,0.000066581975,0.00025594924,0.00014472942,0.8009476,0.0019447578,0.080495514,0.0022169445,0.11066808],"study_design_scores_gemma":[0.000005025293,0.000014503884,0.000111145084,0.0000034632862,0.000007290737,0.000032217853,0.000007995785,0.9887166,0.00017216653,0.010660149,0.00026686818,0.0000025141003],"about_ca_topic_score_codex":0.0061293137,"about_ca_topic_score_gemma":0.00501138,"teacher_disagreement_score":0.0061293137,"about_ca_system_score_codex":0.0010352456,"about_ca_system_score_gemma":0.0014659718,"threshold_uncertainty_score":0.012187302},"labels":[],"label_agreement":null},{"id":"W4205904304","doi":"10.1109/ijcnn.2006.1716831","title":"Multi-view ANNs for Multi-relational Classification","year":2006,"lang":"en","type":"article","venue":"The 2006 IEEE International Joint Conference on Neural Network Proceedings","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Artificial neural network; Relation (database); Artificial intelligence; Bridging (networking); Construct (python library); Exploit; Relational database; Machine learning; Data mining; Statistical relational learning","score_opus":0.15919875916176615,"score_gpt":0.3239139567962549,"score_spread":0.16471519763448875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205904304","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0054090517,0.0010178084,0.99065393,0.00021208407,0.00008169531,0.000044634806,0.00018037713,0.0011286879,0.0012716984],"genre_scores_gemma":[0.18273072,0.0011904703,0.8114708,0.00025589895,0.00017391944,0.00021721839,0.0011480298,0.00012808882,0.0026848034],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986883,0.00038389856,0.00012703272,0.00027653138,0.00046239904,0.00006184388],"domain_scores_gemma":[0.9977481,0.0011177235,0.00019041126,0.00043200137,0.00045948254,0.000052314583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00180512,0.0009123225,0.0010237513,0.0015617745,0.0004975138,0.0014803058,0.0018185775,0.0012046989,0.0036725544],"category_scores_gemma":[0.0057993806,0.00049387914,0.0013176266,0.00219034,0.0003699155,0.0023475753,0.0010190522,0.0018017474,0.001603389],"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":[0.0001249817,0.00010169567,0.0024662302,0.00019419246,0.00025193024,0.00020350105,0.0001125705,0.30992228,0.0049873414,0.021466916,0.0059118276,0.6542565],"study_design_scores_gemma":[0.0000036164195,0.000013202425,0.00026600403,0.000013369624,0.00001250219,0.000042824024,0.0000097039365,0.9881832,0.000821711,0.0086401915,0.001984458,0.000009197392],"about_ca_topic_score_codex":0.003414396,"about_ca_topic_score_gemma":0.0042676954,"teacher_disagreement_score":0.0036725544,"about_ca_system_score_codex":0.00078474823,"about_ca_system_score_gemma":0.00065906293,"threshold_uncertainty_score":0.012285888},"labels":[],"label_agreement":null},{"id":"W4206476877","doi":"10.1145/366413.364795","title":"Polymorphic panelists","year":2001,"lang":"en","type":"article","venue":"ACM SIGCSE Bulletin","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Object (grammar); Class (philosophy); Computer science; Set (abstract data type); Payroll; World Wide Web; Programming language; Artificial intelligence; Management","score_opus":0.02323046340890464,"score_gpt":0.24728474401152947,"score_spread":0.22405428060262483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206476877","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051420555,0.0013234041,0.077664524,0.03128682,0.017872186,0.0010607912,0.002967106,0.010340605,0.85234255],"genre_scores_gemma":[0.036405895,0.0009494654,0.027124986,0.012119759,0.004691408,0.0012167878,0.0029656761,0.0048641236,0.90966195],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9926191,0.0017003407,0.00030450386,0.0017244986,0.0024528422,0.0011987454],"domain_scores_gemma":[0.987973,0.0030169971,0.0005857094,0.0031534217,0.0033198365,0.0019510124],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007328708,0.0010658858,0.0008720443,0.0017972891,0.0054866197,0.0051130843,0.002441291,0.0033989311,0.33828577],"category_scores_gemma":[0.017236346,0.0013510584,0.0015912857,0.0015089982,0.0018093797,0.0061049936,0.009036226,0.0054587126,0.16285498],"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":[0.00013579949,0.000040959643,0.0006592967,0.00010847032,0.000009492279,0.00020640311,0.0010633647,0.00009127761,0.0013287484,0.04911813,0.8706234,0.07661461],"study_design_scores_gemma":[0.0000124219005,0.000010536349,0.0002206377,0.000029911824,0.0000041529224,0.00009844115,0.00017206978,0.00008588621,0.00039113234,0.004058675,0.9949039,0.000012155771],"about_ca_topic_score_codex":0.0020963806,"about_ca_topic_score_gemma":0.0047842227,"teacher_disagreement_score":0.33828577,"about_ca_system_score_codex":0.002330233,"about_ca_system_score_gemma":0.0022295404,"threshold_uncertainty_score":0.94385505},"labels":[],"label_agreement":null},{"id":"W4206545447","doi":"10.24251/hicss.2022.687","title":"Introduction to the Minitrack on Geospatial Big Data Analytics","year":2022,"lang":"en","type":"article","venue":"Proceedings of the ... Annual Hawaii International Conference on System Sciences/Proceedings of the Annual Hawaii International Conference on System Sciences","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":"Toronto Metropolitan University","funders":"","keywords":"Geospatial analysis; Big data; Computer science; Analytics; Data science; Geology; Remote sensing; Data mining","score_opus":0.09063379515364153,"score_gpt":0.3075986118815864,"score_spread":0.21696481672794485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206545447","genre_codex":"methods","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021547172,0.25424042,0.26952985,0.18380927,0.18667151,0.0006481572,0.008386333,0.011722396,0.08283732],"genre_scores_gemma":[0.01656202,0.2531888,0.19114485,0.09627415,0.21047106,0.00086396164,0.018455856,0.0071781203,0.2058611],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99763334,0.00043855188,0.00016415815,0.0004858824,0.0010955336,0.00018251406],"domain_scores_gemma":[0.98426276,0.0064414446,0.00042072605,0.0017514119,0.005082835,0.00204067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004806353,0.0013110284,0.001246299,0.0050204564,0.0016805242,0.00836982,0.0029504392,0.0032308332,0.0436001],"category_scores_gemma":[0.014704353,0.0011063241,0.0011876288,0.0077315713,0.001964927,0.013107664,0.0056174686,0.008896374,0.029450288],"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":[0.000052553576,0.000040241845,0.00038977945,0.0005773773,0.000023278202,0.000045920387,0.00010000041,0.00034860775,0.0011394628,0.017275935,0.83230597,0.14770086],"study_design_scores_gemma":[0.00000777085,0.000021267928,0.0002844855,0.0002702854,0.000007341236,0.000080437196,0.000049411283,0.0006299163,0.00029063007,0.010778746,0.9875536,0.00002608745],"about_ca_topic_score_codex":0.003038248,"about_ca_topic_score_gemma":0.0056021493,"teacher_disagreement_score":0.0436001,"about_ca_system_score_codex":0.001672399,"about_ca_system_score_gemma":0.0026975179,"threshold_uncertainty_score":0.14585692},"labels":[],"label_agreement":null},{"id":"W4210572593","doi":"10.1145/775107.775110","title":"Frequent term-based text clustering","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Cluster analysis; Computer science; Term (time); Document clustering; Data mining; Information retrieval; Clustering high-dimensional data; Hierarchical clustering; Artificial intelligence","score_opus":0.032680051726585564,"score_gpt":0.24196569343515817,"score_spread":0.2092856417085726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210572593","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020270886,0.0010622558,0.96649253,0.00025779963,0.00017673704,0.00064842444,0.0036628402,0.0026088066,0.004819858],"genre_scores_gemma":[0.13164766,0.0007546039,0.8527367,0.00012971419,0.00017170806,0.00056331954,0.009833001,0.00019500169,0.003968327],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965333,0.0005663297,0.00038637462,0.00074512354,0.0015703007,0.00019864939],"domain_scores_gemma":[0.99515116,0.0016275555,0.0004928025,0.00076437177,0.0018520321,0.000111975576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014960947,0.0008696031,0.0010782003,0.007984398,0.0014497082,0.0022460832,0.0018553451,0.0012924568,0.0035985215],"category_scores_gemma":[0.0120167555,0.0002906509,0.0011483589,0.008079923,0.00071311474,0.0020338334,0.0010559055,0.0008664334,0.0034608885],"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":[0.0005075346,0.00023124061,0.00570504,0.0012717373,0.00024149346,0.0008774958,0.00066431,0.05211028,0.024271602,0.055516377,0.02625808,0.8323449],"study_design_scores_gemma":[0.000114470975,0.00027904942,0.0069970074,0.00027346192,0.00022445593,0.003565968,0.0006298505,0.69562864,0.044180177,0.16439122,0.08349011,0.0002255621],"about_ca_topic_score_codex":0.002069553,"about_ca_topic_score_gemma":0.0022360596,"teacher_disagreement_score":0.007984398,"about_ca_system_score_codex":0.00085208094,"about_ca_system_score_gemma":0.0012941911,"threshold_uncertainty_score":0.012038231},"labels":[],"label_agreement":null},{"id":"W4214540750","doi":"10.3390/informatics9010017","title":"Visual Analytics for Predicting Disease Outcomes Using Laboratory Test Results","year":2022,"lang":"en","type":"article","venue":"Informatics","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Western University","funders":"","keywords":"Visual analytics; Computer science; Analytics; Sunrise; Visualization; Interactive visualization; Machine learning; Process (computing); Gradient boosting; Data mining; Artificial intelligence; Data science; Random forest","score_opus":0.02860503085346108,"score_gpt":0.30717405100014455,"score_spread":0.2785690201466835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214540750","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05580205,0.0015838151,0.80041265,0.0023238307,0.00023922308,0.0006681555,0.025286634,0.10179048,0.01189314],"genre_scores_gemma":[0.38024646,0.0014722156,0.5992265,0.00055633206,0.00014222269,0.00056437,0.012592164,0.0017773032,0.0034224421],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995098,0.0001363385,0.00004921652,0.00009278477,0.00016994822,0.000041906373],"domain_scores_gemma":[0.9957824,0.0028128233,0.0002907396,0.00033290318,0.0005979396,0.00018330615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001780971,0.0017035786,0.0005859868,0.00375808,0.00034697462,0.0021773186,0.0012722573,0.00066770986,0.008491279],"category_scores_gemma":[0.0079392865,0.00042710896,0.00079546386,0.0016601108,0.000383444,0.0015456995,0.0018858506,0.000825083,0.0016955747],"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":[0.002498925,0.0004241264,0.03770522,0.0027141382,0.0004294882,0.0014321859,0.0039437828,0.07432898,0.021677023,0.018899724,0.12437031,0.71157616],"study_design_scores_gemma":[0.00034560755,0.00030470383,0.020790245,0.00083638873,0.00023416466,0.00082368363,0.0012026905,0.8008921,0.022085665,0.06006885,0.09217142,0.0002444709],"about_ca_topic_score_codex":0.014362909,"about_ca_topic_score_gemma":0.018170979,"teacher_disagreement_score":0.014362909,"about_ca_system_score_codex":0.0007722821,"about_ca_system_score_gemma":0.0010120836,"threshold_uncertainty_score":0.028558612},"labels":[],"label_agreement":null},{"id":"W4214909787","doi":"10.1109/imcom53663.2022.9721788","title":"Mining Contextual Item Similarity without Concept Hierarchy","year":2022,"lang":"en","type":"article","venue":"2022 16th International Conference on Ubiquitous Information Management and Communication (IMCOM)","topic":"Data Mining Algorithms and Applications","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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; University of Technology Sydney; University of Manitoba","keywords":"Computer science; Data mining; Similarity measure; Similarity (geometry); Measure (data warehouse); Metadata; Heuristic; Information retrieval; Artificial intelligence; Image (mathematics)","score_opus":0.03522629163458004,"score_gpt":0.2831586965514843,"score_spread":0.24793240491690424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214909787","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31423715,0.0025409146,0.673755,0.00022920764,0.00009804263,0.0006398611,0.0023723603,0.0015030903,0.004624394],"genre_scores_gemma":[0.71687317,0.00041509952,0.27725852,0.000102629645,0.00011710317,0.00031188581,0.003819316,0.00006542603,0.001036944],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966016,0.00055021653,0.0003439313,0.00088077557,0.0013559336,0.00026755396],"domain_scores_gemma":[0.9967654,0.0010779282,0.0005226851,0.00068444404,0.0007775934,0.00017197743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012767932,0.0007353409,0.0014991801,0.0073484834,0.0009972402,0.0013275734,0.0015700294,0.0009668639,0.0015356423],"category_scores_gemma":[0.009206359,0.0004326453,0.0011336505,0.008184991,0.0006525416,0.0030581933,0.0019076839,0.00070336286,0.0006421088],"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":[0.0008599345,0.0008552473,0.076340675,0.00085942366,0.00074119284,0.0007438164,0.0008480707,0.050659385,0.012778575,0.029530207,0.008318476,0.81746507],"study_design_scores_gemma":[0.00010251675,0.00085905753,0.0324292,0.00011512185,0.00030693697,0.0012837719,0.0008870965,0.87924725,0.009142518,0.06545479,0.01008862,0.00008307017],"about_ca_topic_score_codex":0.0040314747,"about_ca_topic_score_gemma":0.0058695246,"teacher_disagreement_score":0.0073484834,"about_ca_system_score_codex":0.0008624705,"about_ca_system_score_gemma":0.0015999897,"threshold_uncertainty_score":0.00801605},"labels":[],"label_agreement":null},{"id":"W4223497277","doi":"10.1007/s10489-022-03385-8","title":"UGMINE: utility-based graph mining","year":2022,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":22,"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; Pruning; Data mining; Graph; Decision tree; Machine learning; Artificial intelligence; Theoretical computer science","score_opus":0.027697541902449916,"score_gpt":0.25698810902830427,"score_spread":0.22929056712585436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4223497277","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013202453,0.00069282524,0.9042737,0.0006135089,0.0001171159,0.0005557449,0.010228963,0.066658765,0.0036569296],"genre_scores_gemma":[0.1298172,0.0006631001,0.843156,0.00035806108,0.000063919186,0.000676444,0.018382,0.0025511316,0.0043320935],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99920696,0.00017981125,0.00004651181,0.00016350327,0.0003504662,0.000052896383],"domain_scores_gemma":[0.9983215,0.00090922765,0.0001205728,0.00035212145,0.00022441844,0.00007217625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094951066,0.0012502004,0.0010451886,0.00379711,0.00064005126,0.0016122428,0.0029132296,0.0009959304,0.006367941],"category_scores_gemma":[0.007737119,0.0008107847,0.001396526,0.0027722442,0.00049177156,0.0020041238,0.0016291552,0.0016887987,0.0027870317],"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":[0.0005665734,0.0006345278,0.0064799073,0.0013056608,0.0003697834,0.00046966822,0.00021109525,0.11220083,0.0067361007,0.03587138,0.120277025,0.7148775],"study_design_scores_gemma":[0.00008366854,0.00008491353,0.00071004406,0.000062421415,0.00005310567,0.00027799862,0.000044571203,0.93747866,0.0058204425,0.036207195,0.019150628,0.000026343974],"about_ca_topic_score_codex":0.0044434937,"about_ca_topic_score_gemma":0.009316049,"teacher_disagreement_score":0.006367941,"about_ca_system_score_codex":0.0006397,"about_ca_system_score_gemma":0.0013605917,"threshold_uncertainty_score":0.021302938},"labels":[],"label_agreement":null},{"id":"W4224313182","doi":"10.3390/electronics11091344","title":"ARMatrix: An Interactive Item-to-Rule Matrix for Association Rules Visual Analytics","year":2022,"lang":"en","type":"article","venue":"Electronics","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Association rule learning; Computer science; Visual analytics; Usability; Analytics; Visualization; Exploratory analysis; Human–computer interaction; Metaphor; Association (psychology); Interactive visualization; Interactive visual analysis; Exploratory data analysis; Data mining; Data science; Information retrieval; Psychology","score_opus":0.01102893639648778,"score_gpt":0.3166009620656179,"score_spread":0.3055720256691301,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224313182","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008154527,0.00049343973,0.95091015,0.0005622557,0.00013540183,0.00079366076,0.0053781522,0.029229028,0.0043433565],"genre_scores_gemma":[0.04639632,0.00044185037,0.94356585,0.00025243976,0.000050192266,0.0011747238,0.0037920822,0.00096551894,0.0033609574],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99786574,0.00094857585,0.00019427636,0.00029663555,0.00061317184,0.00008158567],"domain_scores_gemma":[0.9907066,0.00684505,0.00052527856,0.0007858527,0.00074547285,0.0003917793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003961602,0.001956502,0.0010450522,0.0037723945,0.00056520215,0.0032958135,0.0024875507,0.0009703227,0.025832897],"category_scores_gemma":[0.017353332,0.0006493194,0.0014019723,0.0024612232,0.0006379186,0.003214505,0.0039068474,0.0016712189,0.005399067],"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":[0.0027331382,0.0006916218,0.006246376,0.0053767413,0.00050914474,0.0015003644,0.00614497,0.017529236,0.040086146,0.056039724,0.10781049,0.7553321],"study_design_scores_gemma":[0.00066042104,0.0013305182,0.0056633777,0.0013353309,0.00030407266,0.0022544684,0.0024017098,0.43154126,0.03556959,0.18648948,0.33204818,0.00040162713],"about_ca_topic_score_codex":0.0012000912,"about_ca_topic_score_gemma":0.0022394399,"teacher_disagreement_score":0.025832897,"about_ca_system_score_codex":0.0004425004,"about_ca_system_score_gemma":0.000915363,"threshold_uncertainty_score":0.08641964},"labels":[],"label_agreement":null},{"id":"W4226140476","doi":"10.46430/phpt0019","title":"Contagem e mineração de dados de investigação com Unix","year":2021,"lang":"pt","type":"article","venue":"The Programming Historian em português","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Unix; Physics; Operating system; Computer science; Humanities; Art","score_opus":0.03325648029855668,"score_gpt":0.2727971163498416,"score_spread":0.23954063605128492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226140476","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25091806,0.009590658,0.44156694,0.01029558,0.001504007,0.0017464057,0.050181214,0.15633261,0.077864565],"genre_scores_gemma":[0.41489172,0.0056698318,0.47743344,0.001562092,0.0005155174,0.0016269557,0.049662527,0.012702071,0.035935894],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98890615,0.0030589935,0.0014078041,0.0019395632,0.0043280474,0.0003594177],"domain_scores_gemma":[0.9533337,0.018621214,0.0029665595,0.018370872,0.005967715,0.0007401],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014522859,0.0011390315,0.0009466543,0.0062443735,0.0016826799,0.006614731,0.0021100873,0.0009066201,0.008946237],"category_scores_gemma":[0.065070234,0.0010051157,0.0010747412,0.0069381422,0.0012193628,0.0071776635,0.004915455,0.0018832602,0.0035220191],"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":[0.001448474,0.0003534707,0.053955156,0.003646864,0.0005005539,0.0012047363,0.012621707,0.0054007317,0.02678376,0.025423056,0.09200694,0.7766545],"study_design_scores_gemma":[0.00025676168,0.0005951884,0.041843273,0.001956058,0.00056214863,0.0020162386,0.0045076944,0.051324345,0.1046762,0.04593429,0.74603087,0.0002969218],"about_ca_topic_score_codex":0.0034457569,"about_ca_topic_score_gemma":0.003971617,"teacher_disagreement_score":0.014522859,"about_ca_system_score_codex":0.0011765457,"about_ca_system_score_gemma":0.0038756577,"threshold_uncertainty_score":0.076805174},"labels":[],"label_agreement":null},{"id":"W4229076026","doi":"10.1145/3477314.3507301","title":"Generalized graph pattern discovery in linked data with data properties and a domain ontology","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ste. Anne's Hospital; Université du Québec à Montréal","funders":"Genome Canada","keywords":"Computer science; Ontology; Data mining; Graph; Graph database; Linked data; Property (philosophy); Theoretical computer science; Abstraction; Knowledge extraction; Information retrieval; Semantic Web","score_opus":0.04711496985454908,"score_gpt":0.24792155250616518,"score_spread":0.2008065826516161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229076026","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038270425,0.00035683374,0.95584285,0.00075413496,0.000035687437,0.00025629514,0.0020877633,0.0013994527,0.0009966512],"genre_scores_gemma":[0.15819873,0.00035864554,0.8353234,0.00032421696,0.000033925236,0.00033909775,0.004388339,0.00016205569,0.00087170023],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945629,0.0016483244,0.0005794766,0.001427547,0.0015130881,0.0002685993],"domain_scores_gemma":[0.9884063,0.0066821077,0.0012975594,0.0023997286,0.00092159497,0.0002927196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003929178,0.0005574583,0.0008132581,0.0059028817,0.0011589046,0.0032478832,0.0014596274,0.0012249664,0.00083739386],"category_scores_gemma":[0.01922483,0.00074057793,0.00252281,0.007204854,0.0015589694,0.0056505664,0.0033590088,0.0015067705,0.00030617506],"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":[0.00040863972,0.00048755953,0.047885966,0.0022634207,0.000724429,0.006173216,0.0057284646,0.13334204,0.014063844,0.3504925,0.011795218,0.42663473],"study_design_scores_gemma":[0.000047577836,0.00007330708,0.004811141,0.00021652438,0.00014693281,0.0014122529,0.0016795328,0.52201897,0.007384428,0.4340878,0.028073357,0.00004811577],"about_ca_topic_score_codex":0.00709531,"about_ca_topic_score_gemma":0.011956636,"teacher_disagreement_score":0.00709531,"about_ca_system_score_codex":0.0015321661,"about_ca_system_score_gemma":0.0016035883,"threshold_uncertainty_score":0.020779729},"labels":[],"label_agreement":null},{"id":"W4229452682","doi":"10.1016/j.isatra.2022.05.003","title":"Mining high occupancy patterns to analyze incremental data in intelligent systems","year":2022,"lang":"en","type":"article","venue":"ISA Transactions","topic":"Data Mining Algorithms and Applications","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 Alberta","funders":"Ministry of Education, Science and Technology; National Research Foundation of Korea; Sejong University","keywords":"Occupancy; Data mining; Computer science; State (computer science); High dimensional; Database; Artificial intelligence; Engineering; Algorithm","score_opus":0.04650026015073312,"score_gpt":0.29612043670859517,"score_spread":0.24962017655786206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229452682","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4168171,0.0011947711,0.5740731,0.0005080517,0.00018094758,0.00019950035,0.00218762,0.0027809285,0.0020581118],"genre_scores_gemma":[0.8681519,0.00024075112,0.12872949,0.0000628101,0.00005068561,0.00009607217,0.0016585338,0.000113107446,0.00089667516],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992455,0.00008208874,0.00007325836,0.00013863361,0.00034949923,0.00011103091],"domain_scores_gemma":[0.99786973,0.0009767456,0.0002224134,0.00037670787,0.00046161836,0.00009271675],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061338244,0.00058189227,0.00084860134,0.0024686991,0.00061791163,0.0013692746,0.0011407145,0.0005804985,0.0012425333],"category_scores_gemma":[0.0047485903,0.00044657497,0.00069444877,0.002596023,0.0004569416,0.0019732765,0.00096699013,0.00087015267,0.0004900549],"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":[0.0009128653,0.00073993474,0.13532364,0.00064567156,0.00043902377,0.0015751747,0.00092464377,0.18837367,0.0314769,0.014664775,0.008799177,0.6161245],"study_design_scores_gemma":[0.000023646477,0.00015950165,0.009240162,0.000032593634,0.00009603264,0.00045011716,0.00040997262,0.95556056,0.010955167,0.019671686,0.0033786264,0.00002191395],"about_ca_topic_score_codex":0.0034910701,"about_ca_topic_score_gemma":0.0055039525,"teacher_disagreement_score":0.0034910701,"about_ca_system_score_codex":0.00044342954,"about_ca_system_score_gemma":0.00072422536,"threshold_uncertainty_score":0.0069414973},"labels":[],"label_agreement":null},{"id":"W4229517358","doi":"10.1007/978-1-4939-7131-2_100972","title":"Relational Data Mining","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Data Mining Algorithms 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 Calgary","funders":"","keywords":"Computer science; Relational database; Data mining; Data science; Information retrieval","score_opus":0.13984700382022144,"score_gpt":0.28920857073936274,"score_spread":0.1493615669191413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229517358","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024071,0.029433435,0.7137051,0.0043462464,0.0022896884,0.00033504044,0.0048981314,0.0067317877,0.2358534],"genre_scores_gemma":[0.02473022,0.04511657,0.6114031,0.0027143888,0.002313233,0.00034547618,0.018887658,0.0019096608,0.29257974],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989286,0.00009628614,0.00008556657,0.00027459126,0.0005762921,0.000038609902],"domain_scores_gemma":[0.9989316,0.00038305955,0.00004568524,0.0003250832,0.00026833272,0.00004627475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010334733,0.0012427019,0.0009908708,0.0028340681,0.0007632752,0.0035107944,0.0022135011,0.00070116203,0.038404617],"category_scores_gemma":[0.0036194285,0.00075628614,0.0010440964,0.005901679,0.0007164136,0.005478059,0.0021673103,0.0020593726,0.040015202],"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":[0.000017205923,0.000042767482,0.0002431881,0.0005795218,0.000036301135,0.00006510003,0.000125169,0.0012425862,0.0015902068,0.088750295,0.17529564,0.73201203],"study_design_scores_gemma":[0.000005228954,0.00001657752,0.0003521576,0.00027826757,0.000029473618,0.000536248,0.000076157754,0.0065820357,0.00283496,0.12744164,0.8618234,0.000023875886],"about_ca_topic_score_codex":0.0007302886,"about_ca_topic_score_gemma":0.0011081321,"teacher_disagreement_score":0.038404617,"about_ca_system_score_codex":0.0007668779,"about_ca_system_score_gemma":0.0009841082,"threshold_uncertainty_score":0.1284762},"labels":[],"label_agreement":null},{"id":"W4229547968","doi":"10.1007/978-1-4939-7131-2_100938","title":"Query Segmentation","year":2018,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology)","score_opus":0.024757380042117545,"score_gpt":0.2556279933097063,"score_spread":0.23087061326758876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229547968","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0066995956,0.006329936,0.7346876,0.0019101668,0.0010055255,0.000960949,0.0051299827,0.020508984,0.22276728],"genre_scores_gemma":[0.09096808,0.007929334,0.591002,0.0025111088,0.00084704795,0.0007471587,0.024182308,0.006720672,0.27509224],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989318,0.000097286815,0.00005798158,0.0003778511,0.00041919324,0.00011580805],"domain_scores_gemma":[0.9989819,0.0002479526,0.000033466804,0.00036298763,0.00031059497,0.00006305662],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088202715,0.0014464345,0.0013264372,0.0019342022,0.0011043482,0.0034321328,0.002583058,0.001262974,0.07468765],"category_scores_gemma":[0.002534911,0.0007487768,0.0010532808,0.0026566742,0.00087636785,0.0042609754,0.0022281755,0.0018628484,0.050979078],"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":[0.00024053954,0.0001194175,0.00030803538,0.00075586984,0.000040114493,0.00014284514,0.00030731122,0.0027718705,0.0327375,0.08157453,0.2095186,0.6714834],"study_design_scores_gemma":[0.00004269047,0.000105019295,0.00082310045,0.00023743688,0.00008622486,0.0008939888,0.00028741662,0.044287965,0.053995326,0.06411892,0.83504623,0.00007569221],"about_ca_topic_score_codex":0.0036123577,"about_ca_topic_score_gemma":0.0035174298,"teacher_disagreement_score":0.07468765,"about_ca_system_score_codex":0.0015493289,"about_ca_system_score_gemma":0.0016656424,"threshold_uncertainty_score":0.2498551},"labels":[],"label_agreement":null},{"id":"W4229605571","doi":"10.1007/978-1-4939-7131-2_100436","title":"Graph Pattern Mining","year":2018,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Computer science; Graph; Theoretical computer science","score_opus":0.02755938177838925,"score_gpt":0.24263728935243356,"score_spread":0.21507790757404432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229605571","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0055040903,0.015332056,0.7751161,0.0035908073,0.0019595122,0.0004873929,0.006147495,0.01204765,0.17981482],"genre_scores_gemma":[0.039688576,0.022248061,0.68213665,0.0017090836,0.0011958929,0.00038965765,0.022965796,0.0025543093,0.2271119],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9995322,0.000040640898,0.00002410407,0.00016545969,0.00020953138,0.000028106544],"domain_scores_gemma":[0.9993339,0.00019979652,0.0000347622,0.00019568374,0.00019915256,0.00003664498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041938934,0.0014919484,0.0009000371,0.0037228474,0.00068337924,0.0020964553,0.0021495773,0.0008869857,0.036515567],"category_scores_gemma":[0.0018528089,0.00067122217,0.0011277604,0.005179882,0.00049274776,0.0030565015,0.0013445606,0.0016236162,0.033195302],"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":[0.000025213978,0.000062181105,0.00033578134,0.00050225726,0.000041915766,0.000091682545,0.00005992498,0.002448473,0.0027161185,0.027973235,0.16501358,0.8007296],"study_design_scores_gemma":[0.000017307577,0.00005583748,0.0012018464,0.00037964887,0.00008525656,0.0013157373,0.00013416653,0.03964766,0.012248206,0.22250445,0.7223621,0.00004789712],"about_ca_topic_score_codex":0.0010480238,"about_ca_topic_score_gemma":0.0022577173,"teacher_disagreement_score":0.036515567,"about_ca_system_score_codex":0.00058081065,"about_ca_system_score_gemma":0.00081315154,"threshold_uncertainty_score":0.12215674},"labels":[],"label_agreement":null},{"id":"W4230586990","doi":"10.1007/978-1-4939-7131-2_100940","title":"Query Spelling Correction","year":2018,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Spelling; Computer science; Natural language processing; Artificial intelligence; Information retrieval; Linguistics; Philosophy","score_opus":0.023988794610294243,"score_gpt":0.23796528672257117,"score_spread":0.21397649211227693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230586990","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012536583,0.010808957,0.68603516,0.008300157,0.014417983,0.0014415253,0.020496352,0.10312965,0.1428336],"genre_scores_gemma":[0.12291281,0.008718482,0.43618804,0.0059222216,0.004541736,0.0006600024,0.059102893,0.025882063,0.3360717],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9929317,0.00069512916,0.0006732933,0.0009892109,0.004195001,0.00051566877],"domain_scores_gemma":[0.98365074,0.0023668366,0.00050686166,0.0053182216,0.007912022,0.00024522236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031461318,0.0021194306,0.0021470678,0.004535981,0.0018043099,0.0038780204,0.0039562527,0.0015211804,0.07237491],"category_scores_gemma":[0.01940674,0.00062550703,0.001879979,0.0043123616,0.0011118392,0.0031970553,0.0036274423,0.0027332613,0.07262555],"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":[0.00027977835,0.00007321097,0.0005324406,0.00091417547,0.000058524776,0.00042378026,0.00018067709,0.0012610772,0.018484859,0.013080536,0.34349525,0.62121564],"study_design_scores_gemma":[0.000075552016,0.000108921755,0.0011685605,0.00039063225,0.000144486,0.002538638,0.0002673121,0.015320162,0.08733673,0.020638213,0.8718721,0.00013868843],"about_ca_topic_score_codex":0.0057074525,"about_ca_topic_score_gemma":0.004087241,"teacher_disagreement_score":0.07237491,"about_ca_system_score_codex":0.0013910268,"about_ca_system_score_gemma":0.003628659,"threshold_uncertainty_score":0.24211818},"labels":[],"label_agreement":null},{"id":"W4230648111","doi":"10.1007/978-1-4939-7131-2_100858","title":"Pattern Mining","year":2018,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Computer science","score_opus":0.029753161394813463,"score_gpt":0.24630588121381836,"score_spread":0.2165527198190049,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230648111","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033576644,0.009622237,0.6225481,0.0030836852,0.0015543615,0.0006597291,0.005342838,0.010937776,0.34289354],"genre_scores_gemma":[0.021521859,0.01671616,0.4652676,0.002132005,0.0012392284,0.00059131644,0.016773365,0.0016561783,0.47410214],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99932826,0.00004950194,0.00004687854,0.00022378091,0.00031757762,0.000033948192],"domain_scores_gemma":[0.9992613,0.00019337385,0.000034825476,0.00024273166,0.00022843928,0.000039331942],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007157176,0.0015365923,0.00089172553,0.0031039834,0.0006939695,0.0028945766,0.0024759728,0.0009074114,0.08518326],"category_scores_gemma":[0.0023470437,0.0006529092,0.0010541205,0.003690929,0.000484528,0.0039163465,0.0019741594,0.0014827098,0.09647989],"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":[0.000027664306,0.000054217307,0.00023468887,0.00051398267,0.000027915414,0.00009654124,0.000063771055,0.00075979973,0.0039183693,0.030112343,0.1378332,0.82635754],"study_design_scores_gemma":[0.000012637883,0.00004669117,0.0005977116,0.00026689403,0.000034641722,0.001110589,0.00007605297,0.0086644925,0.008935748,0.08338674,0.8968396,0.000028233819],"about_ca_topic_score_codex":0.00048965216,"about_ca_topic_score_gemma":0.00081790553,"teacher_disagreement_score":0.08518326,"about_ca_system_score_codex":0.00052023056,"about_ca_system_score_gemma":0.00091174716,"threshold_uncertainty_score":0.2849664},"labels":[],"label_agreement":null},{"id":"W4231097598","doi":"10.1007/978-1-4614-6170-8_100093","title":"Pattern Mining","year":2014,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Computer science","score_opus":0.02302944454214948,"score_gpt":0.23193206431240004,"score_spread":0.20890261977025057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231097598","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033743426,0.008904162,0.6569314,0.0026291176,0.0012592155,0.0006529977,0.0049115242,0.010344727,0.31099254],"genre_scores_gemma":[0.020464402,0.015471398,0.49671686,0.0018758636,0.000990049,0.000578337,0.015441093,0.0014843004,0.44697767],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993598,0.00004701622,0.00004439396,0.00020913052,0.00030746002,0.000032180487],"domain_scores_gemma":[0.99934214,0.00017777178,0.000031690783,0.00020785074,0.0002070195,0.00003347325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006633448,0.001512726,0.00091588596,0.0030726194,0.0006781611,0.0027206335,0.002445146,0.0008738451,0.078881174],"category_scores_gemma":[0.0021152627,0.0006410088,0.0010273067,0.0036639296,0.00046823657,0.003670191,0.001883868,0.0013886607,0.08605141],"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":[0.000025966057,0.00004958066,0.00023031997,0.00048194767,0.000026755331,0.000097883734,0.00006346025,0.00076818175,0.0038711682,0.027487094,0.125541,0.8413567],"study_design_scores_gemma":[0.000013457203,0.00004969751,0.0006483246,0.0002871077,0.000038015765,0.0012471103,0.00008650249,0.00999035,0.009938693,0.08610477,0.89156514,0.000030818184],"about_ca_topic_score_codex":0.0005383203,"about_ca_topic_score_gemma":0.0009212716,"teacher_disagreement_score":0.078881174,"about_ca_system_score_codex":0.00049675844,"about_ca_system_score_gemma":0.00089550763,"threshold_uncertainty_score":0.26388383},"labels":[],"label_agreement":null},{"id":"W4231647408","doi":"10.1007/978-0-387-39940-9_5047","title":"Convertible Constraints","year":2009,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Database Systems","topic":"Data Mining Algorithms 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":"Convertible; Computer science; Business; Engineering; Structural engineering","score_opus":0.01743872020611639,"score_gpt":0.23801147731627217,"score_spread":0.22057275711015578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231647408","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038763438,0.006504727,0.3455685,0.0014463064,0.00111108,0.0002835937,0.0052445,0.003265691,0.6326993],"genre_scores_gemma":[0.11913518,0.014078373,0.44366986,0.0016828319,0.001009109,0.0005048214,0.020260863,0.003622616,0.39603636],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988354,0.0001522728,0.00010351603,0.0003179048,0.00051012856,0.00008089886],"domain_scores_gemma":[0.99893457,0.00040944607,0.00005122026,0.00036576387,0.0002050963,0.000034009205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075702305,0.0014201393,0.00093456043,0.0020250431,0.000985396,0.004568692,0.0024703,0.0009164049,0.09689434],"category_scores_gemma":[0.004287125,0.00089241576,0.0012881187,0.0035092183,0.0014152741,0.0066404934,0.0021053925,0.0033719684,0.024434065],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000066825836,0.00006391695,0.0001064561,0.00052053516,0.000030176341,0.00019129322,0.00017361956,0.0027318713,0.0013810856,0.6339815,0.08060523,0.2801475],"study_design_scores_gemma":[0.000020406162,0.000018972136,0.00010317288,0.00024211181,0.000024608895,0.00040528216,0.000049482125,0.0039173085,0.0026896964,0.43754393,0.55495954,0.000025481126],"about_ca_topic_score_codex":0.0019622394,"about_ca_topic_score_gemma":0.002637243,"teacher_disagreement_score":0.09689434,"about_ca_system_score_codex":0.0010766514,"about_ca_system_score_gemma":0.0011300558,"threshold_uncertainty_score":0.32414383},"labels":[],"label_agreement":null},{"id":"W4231729257","doi":"10.1007/978-3-662-45942-3_6","title":"Mining Multiple Related Data Sources Using Object-Oriented Model","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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":"University of Windsor","funders":"","keywords":"Computer science; Class hierarchy; Joins; Data mining; Database; Object (grammar); Inheritance (genetic algorithm); Theoretical computer science; Object-oriented programming; Artificial intelligence; Programming language","score_opus":0.0452442112778649,"score_gpt":0.27486780110831577,"score_spread":0.22962358983045086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231729257","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04199513,0.0019700206,0.94687605,0.0006811846,0.0001656117,0.0006125614,0.0019443246,0.0035943605,0.002160712],"genre_scores_gemma":[0.13896821,0.0014433557,0.8502812,0.0003168283,0.000107720385,0.00035961042,0.006191548,0.00025725062,0.0020743043],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99662507,0.00037898045,0.00044115377,0.0006487843,0.0017540188,0.0001519312],"domain_scores_gemma":[0.99638355,0.0016606731,0.00046002772,0.00054174097,0.00081229233,0.00014164759],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028390249,0.0017150008,0.0018281197,0.010280574,0.0013246628,0.0044348324,0.003175794,0.0014343965,0.0011860004],"category_scores_gemma":[0.0066978238,0.00096835184,0.0034315474,0.012763279,0.00058371614,0.0047900407,0.0023739494,0.0012990594,0.00084179046],"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":[0.0006781153,0.0010674419,0.041056108,0.0014890685,0.0014754726,0.00368285,0.0009956363,0.034281302,0.014258649,0.025710708,0.013570413,0.86173415],"study_design_scores_gemma":[0.00018908372,0.00030036716,0.009753327,0.0004706226,0.0017973927,0.0025169984,0.0009827152,0.8249326,0.020404158,0.10583638,0.03266045,0.00015589272],"about_ca_topic_score_codex":0.004063056,"about_ca_topic_score_gemma":0.005796151,"teacher_disagreement_score":0.010280574,"about_ca_system_score_codex":0.0008945069,"about_ca_system_score_gemma":0.0019626066,"threshold_uncertainty_score":0.01501441},"labels":[],"label_agreement":null},{"id":"W4231760126","doi":"10.4018/9871599043647.ch011","title":"Toward Integrating Data Warehousing with Data Mining Techniques","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Université du Québec en Outaouais","funders":"","keywords":"Data warehouse; Computer science; Data science; Database; Data mining","score_opus":0.11530053123595083,"score_gpt":0.2986454262373267,"score_spread":0.18334489500137588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231760126","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003342285,0.0047085094,0.975246,0.0037896174,0.0001949981,0.00017893862,0.00014182464,0.001623371,0.010774346],"genre_scores_gemma":[0.0122484835,0.004262614,0.97966206,0.0007921066,0.00019242628,0.000124267,0.0002794672,0.00025094583,0.0021876919],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9920437,0.0024229945,0.0006262623,0.000880471,0.0037031902,0.00032331957],"domain_scores_gemma":[0.9856757,0.007848047,0.00039930825,0.0041626533,0.0015509211,0.00036340705],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0141850775,0.0021052593,0.0019086575,0.0063656634,0.0015696589,0.01324431,0.005425533,0.0025101916,0.0043206536],"category_scores_gemma":[0.013433764,0.0022271103,0.0021537235,0.01194757,0.0029813715,0.018132703,0.008571498,0.006400642,0.005688962],"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":[0.000085429376,0.0005319464,0.0017447291,0.0020886115,0.00026373696,0.0003279181,0.001636825,0.012928622,0.0063231043,0.2944458,0.010752918,0.66887033],"study_design_scores_gemma":[0.00005883876,0.00018721257,0.0011129408,0.0019562894,0.00017227088,0.0006525434,0.0013661054,0.12040132,0.013111591,0.54061246,0.3201896,0.00017883228],"about_ca_topic_score_codex":0.0018791176,"about_ca_topic_score_gemma":0.0016653746,"teacher_disagreement_score":0.0141850775,"about_ca_system_score_codex":0.0014759528,"about_ca_system_score_gemma":0.0034792225,"threshold_uncertainty_score":0.075018704},"labels":[],"label_agreement":null},{"id":"W4232647314","doi":"10.1007/1-4020-2116-x_14","title":"Artificially supported mining methods","year":2005,"lang":"en","type":"book-chapter","venue":"Kluwer Academic Publishers eBooks","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":"Golder Associates (Canada)","funders":"","keywords":"Mining engineering; Computer science; Geology","score_opus":0.04927751141225481,"score_gpt":0.32399963792062475,"score_spread":0.2747221265083699,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4232647314","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033596943,0.0016552055,0.9698579,0.0008008312,0.0004652343,0.0001274736,0.0005830339,0.0022475955,0.020903036],"genre_scores_gemma":[0.071335115,0.0014690169,0.8965627,0.0004312997,0.00042448146,0.00040128297,0.003172465,0.0007795278,0.025424115],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964734,0.0011660117,0.00029891473,0.0007209477,0.0012486202,0.000092196766],"domain_scores_gemma":[0.9905545,0.0047388826,0.00022411755,0.0032626009,0.001058732,0.00016113097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036604917,0.0012899223,0.0011436893,0.0025850097,0.0010090532,0.0031247074,0.003253207,0.0016673245,0.017891511],"category_scores_gemma":[0.01850056,0.00088123116,0.0013513473,0.0027088583,0.0014051447,0.0037324151,0.0035076526,0.0028580746,0.010456833],"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":[0.00017271917,0.00010783234,0.001401701,0.00051300187,0.000107692475,0.00013924963,0.00018992659,0.015567291,0.0022602845,0.17312223,0.03485356,0.7715646],"study_design_scores_gemma":[0.000056124434,0.000092793714,0.0006891961,0.00025691435,0.00007174154,0.00081221544,0.00011412275,0.367911,0.0060721603,0.4667466,0.15713389,0.000043152257],"about_ca_topic_score_codex":0.00042813906,"about_ca_topic_score_gemma":0.0006895071,"teacher_disagreement_score":0.017891511,"about_ca_system_score_codex":0.00046069967,"about_ca_system_score_gemma":0.0011242373,"threshold_uncertainty_score":0.059853017},"labels":[],"label_agreement":null},{"id":"W4232700090","doi":"10.4018/9781599041629.ch002","title":"Bi-Directional Constraint Pushing in Frequent Pattern Mining","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Association rule learning; Constraint (computer-aided design); Key (lock); Data mining; Process (computing); Affinity analysis; Contrast (vision); Resource (disambiguation); Eclipse; Artificial intelligence; Engineering","score_opus":0.034422391829570693,"score_gpt":0.249673420421399,"score_spread":0.21525102859182832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4232700090","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038905125,0.00514938,0.9822696,0.0009059992,0.00020933767,0.00026094366,0.00065813505,0.0010200873,0.0056360723],"genre_scores_gemma":[0.031156937,0.0045565763,0.9566689,0.00037955955,0.00019678376,0.0005340714,0.0015335176,0.00026089908,0.004712696],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950197,0.0015747963,0.0006043504,0.00077368174,0.0018243705,0.00020301512],"domain_scores_gemma":[0.9901848,0.0070152795,0.00044012084,0.0012119559,0.00096491375,0.00018285569],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049479716,0.0014254989,0.0018272846,0.003195144,0.0012854212,0.0037609462,0.00335584,0.0017734761,0.0068096532],"category_scores_gemma":[0.018693566,0.001578407,0.0018341866,0.0103981625,0.0012328875,0.0060838107,0.0028184808,0.0036597492,0.0056708814],"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":[0.00031391613,0.00022115993,0.0022229948,0.0019020475,0.00019372132,0.00080283935,0.0004863686,0.04943173,0.005298593,0.09645007,0.03031652,0.81236],"study_design_scores_gemma":[0.000082172846,0.00015808384,0.0012212115,0.00061979867,0.00010882427,0.0017557954,0.0003738144,0.55681914,0.009769968,0.31221315,0.1167439,0.0001342129],"about_ca_topic_score_codex":0.0018023734,"about_ca_topic_score_gemma":0.0017928821,"teacher_disagreement_score":0.0068096532,"about_ca_system_score_codex":0.0008338026,"about_ca_system_score_gemma":0.0015952392,"threshold_uncertainty_score":0.02616769},"labels":[],"label_agreement":null},{"id":"W4233121303","doi":"10.2196/32319","title":"Using the Diagnostic Odds Ratio to Select Patterns to Build an Interpretable Pattern-Based Classifier in a Clinical Domain: Multivariate Sequential Pattern Mining Study","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Agencia Estatal de Investigación; European Regional Development Fund; Ministerio de Ciencia e Innovación","keywords":"Multivariate statistics; Discriminative model; Pattern recognition (psychology); Computer science; Classifier (UML); Feature selection; Artificial intelligence; Multivariate analysis; Principal component analysis; Data mining; Machine learning","score_opus":0.06078749236177159,"score_gpt":0.38484665204327717,"score_spread":0.32405915968150556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233121303","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7003226,0.0012941156,0.29519525,0.00062120176,0.00007758535,0.00030164162,0.00069429463,0.00036419602,0.0011290566],"genre_scores_gemma":[0.90190136,0.00024260326,0.09699896,0.00005463993,0.00006322706,0.00009491841,0.00046302952,0.000022878174,0.00015850294],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995786,0.0016718984,0.0007043454,0.00071682525,0.0009094953,0.0002114046],"domain_scores_gemma":[0.96600413,0.028500525,0.002064787,0.0011316236,0.0018496033,0.0004492689],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007623785,0.0008137678,0.0010487644,0.004916432,0.00031038316,0.0013988848,0.0009161299,0.0008434283,0.00101049],"category_scores_gemma":[0.032799747,0.00014626131,0.0013303567,0.0028712978,0.00055427355,0.0013155093,0.00068700506,0.0009176794,0.00017901021],"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":[0.0016587425,0.00072065095,0.54663,0.0004058327,0.000878,0.00044977095,0.00034213052,0.05406227,0.004952638,0.0022565406,0.0011492218,0.38649434],"study_design_scores_gemma":[0.00015509453,0.0010000328,0.06756134,0.00007426996,0.00034568517,0.0010841783,0.00039637779,0.9179922,0.004738536,0.0052765743,0.0013215871,0.000054100972],"about_ca_topic_score_codex":0.0019324594,"about_ca_topic_score_gemma":0.0012923871,"teacher_disagreement_score":0.007623785,"about_ca_system_score_codex":0.0005872155,"about_ca_system_score_gemma":0.00093687937,"threshold_uncertainty_score":0.040318966},"labels":[],"label_agreement":null},{"id":"W4233132785","doi":"10.1109/asonam.2016.7752350","title":"Mining ‘following’ patterns from big sparse social networks","year":2016,"lang":"en","type":"article","venue":"2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":22,"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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Big data; Data science; Data mining","score_opus":0.03686138174885396,"score_gpt":0.31198912031532094,"score_spread":0.275127738566467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233132785","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55947,0.0012944622,0.42213532,0.0019285704,0.00010370152,0.00047308052,0.007557679,0.0013152522,0.005721876],"genre_scores_gemma":[0.8516133,0.00055714045,0.13703622,0.00021914922,0.00010602034,0.0002880143,0.008802792,0.000048304417,0.001329182],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851936,0.000351752,0.00013410658,0.00035041844,0.000518385,0.00012591446],"domain_scores_gemma":[0.99277765,0.0036407518,0.0013805312,0.0011350029,0.0008359518,0.00023019346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009205512,0.00079904514,0.000918783,0.004566441,0.0008598538,0.00097224093,0.0016315721,0.0013702777,0.0009748645],"category_scores_gemma":[0.010281394,0.00044005323,0.00082882866,0.00420847,0.00072220876,0.0026637653,0.0013705773,0.0008371654,0.00052704796],"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":[0.001079574,0.00088924303,0.22945149,0.0012788753,0.00078053045,0.0044790045,0.0034007903,0.19929023,0.019465644,0.037487917,0.021369854,0.48102692],"study_design_scores_gemma":[0.000034002882,0.0001569551,0.025612652,0.00008597576,0.00010913024,0.001214139,0.0012828211,0.8963936,0.0051480653,0.061101764,0.008826043,0.000034909805],"about_ca_topic_score_codex":0.00387494,"about_ca_topic_score_gemma":0.0074091596,"teacher_disagreement_score":0.004566441,"about_ca_system_score_codex":0.00052547065,"about_ca_system_score_gemma":0.00049469847,"threshold_uncertainty_score":0.007704735},"labels":[],"label_agreement":null},{"id":"W4233192642","doi":"10.1109/wi-iat.2011.295","title":"Search beyond Traditional Probabilistic Information Retrieval","year":2011,"lang":"en","type":"article","venue":"","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":"York University","funders":"","keywords":"Computer science; Probabilistic logic; Information retrieval; Divergence-from-randomness model; Artificial intelligence","score_opus":0.06952676659470826,"score_gpt":0.2439552070463557,"score_spread":0.17442844045164746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233192642","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030976105,0.014628185,0.91562855,0.004934988,0.00031403938,0.00024320127,0.0009962908,0.0026916421,0.029587002],"genre_scores_gemma":[0.6237912,0.009514019,0.3412935,0.0017938998,0.00096618576,0.00032255726,0.0022173105,0.00061286014,0.019488525],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99719465,0.0009666113,0.00015499341,0.00041954516,0.0011280759,0.00013606694],"domain_scores_gemma":[0.9894509,0.006746072,0.00036764864,0.0023594734,0.00092388265,0.00015196504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00304178,0.00060440635,0.0020554566,0.00430487,0.0012390729,0.004351822,0.001937186,0.001755241,0.011423335],"category_scores_gemma":[0.024444867,0.00062961155,0.0009791749,0.0058430955,0.0014335376,0.016607368,0.0034621053,0.001672095,0.0033090536],"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":[0.00043870788,0.00025162235,0.0030607253,0.0010409106,0.00028870537,0.00018165301,0.00044988506,0.029831834,0.0035901212,0.4331044,0.030742878,0.49701858],"study_design_scores_gemma":[0.000052987998,0.00010148979,0.00056895794,0.00011651829,0.00014781611,0.0002994029,0.000104175946,0.25045764,0.0018956948,0.7271919,0.019026052,0.000037318136],"about_ca_topic_score_codex":0.0023928483,"about_ca_topic_score_gemma":0.0027551057,"teacher_disagreement_score":0.011423335,"about_ca_system_score_codex":0.0011234076,"about_ca_system_score_gemma":0.0014699629,"threshold_uncertainty_score":0.038214922},"labels":[],"label_agreement":null},{"id":"W4233431886","doi":"10.4018/978-1-59904-951-9.ch122","title":"User-Centered Interactive Data Mining","year":2008,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Focus (optics); Selection (genetic algorithm); Automation; User modeling; Data science; Data mining; Human–computer interaction; User interface; Machine learning; Engineering","score_opus":0.05614117375649545,"score_gpt":0.2921812797810405,"score_spread":0.23604010602454506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233431886","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021992908,0.0012791633,0.9724938,0.0006229366,0.000068096684,0.00020115609,0.0003903051,0.0036314698,0.019113779],"genre_scores_gemma":[0.063682854,0.0022312324,0.9030596,0.00082772126,0.00019187192,0.0005379775,0.002239475,0.0006704223,0.026558788],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9938968,0.0023082863,0.0003459355,0.0009612945,0.002235998,0.0002516961],"domain_scores_gemma":[0.98877674,0.0066412035,0.00027923376,0.0025282726,0.0014272485,0.00034720512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007186813,0.0015287269,0.0012790839,0.002344234,0.00083364133,0.0064527933,0.0056197112,0.0018610717,0.018458935],"category_scores_gemma":[0.013617178,0.0008232206,0.0016276932,0.0041139773,0.0012578946,0.00672627,0.00515047,0.002520104,0.010437814],"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":[0.00025381768,0.00031417236,0.0031220228,0.00138537,0.00019724954,0.00058920466,0.0032852464,0.009619176,0.007918516,0.1869578,0.06144448,0.72491294],"study_design_scores_gemma":[0.00006497649,0.00016878165,0.0021211724,0.0006511964,0.0001482707,0.0025598805,0.0007944807,0.19320957,0.017649043,0.23304495,0.54940075,0.00018687933],"about_ca_topic_score_codex":0.0010131143,"about_ca_topic_score_gemma":0.001422447,"teacher_disagreement_score":0.018458935,"about_ca_system_score_codex":0.00095154875,"about_ca_system_score_gemma":0.0016636099,"threshold_uncertainty_score":0.061751306},"labels":[],"label_agreement":null},{"id":"W4233585779","doi":"10.22215/etd/2014-10523","title":"Empirical Study of Performance of Classification and Clustering Algorithms on Binary Data with Real-World Applications","year":2014,"lang":"en","type":"dissertation","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Cluster analysis; Single-linkage clustering; Hierarchical clustering; Computer science; CURE data clustering algorithm; Correlation clustering; Data mining; Pattern recognition (psychology); Centroid; Medoid; Canopy clustering algorithm; Fuzzy clustering; Artificial intelligence; Entropy (arrow of time); Rand index","score_opus":0.0676863383469383,"score_gpt":0.3537118901673301,"score_spread":0.2860255518203918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233585779","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9817331,0.0018307397,0.011866005,0.0005506253,0.00008530858,0.00009788768,0.0010421431,0.00023739196,0.002556778],"genre_scores_gemma":[0.97748214,0.00044288262,0.017829515,0.000053595828,0.000068180954,0.00009162823,0.0033662447,0.000082478815,0.00058328855],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9869515,0.00650597,0.0013430981,0.0014515236,0.003329895,0.00041807306],"domain_scores_gemma":[0.68727714,0.27580544,0.009822661,0.011097797,0.014338304,0.0016586329],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019987073,0.0007393179,0.00072488276,0.0038881,0.00089704496,0.0029588211,0.0013314271,0.0014090892,0.0011992011],"category_scores_gemma":[0.16640472,0.0002492311,0.00067139685,0.0058158664,0.0015709589,0.003235831,0.0010421382,0.001332678,0.0007543586],"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":[0.00423941,0.0023820351,0.4717976,0.0020823462,0.0013670264,0.00035656116,0.0026124404,0.15903622,0.0045152805,0.008103647,0.016707782,0.3267998],"study_design_scores_gemma":[0.00018129572,0.0027318634,0.38462037,0.00037175068,0.00024702086,0.0011137926,0.0027914653,0.58132744,0.008096286,0.010330663,0.008009528,0.00017853128],"about_ca_topic_score_codex":0.002118107,"about_ca_topic_score_gemma":0.0016369824,"teacher_disagreement_score":0.019987073,"about_ca_system_score_codex":0.0012161921,"about_ca_system_score_gemma":0.0006843592,"threshold_uncertainty_score":0.105703056},"labels":[],"label_agreement":null},{"id":"W4233716913","doi":"10.1007/978-1-4939-7131-2_100429","title":"Graph Mining","year":2018,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Computer science; Graph; Theoretical computer science","score_opus":0.028274776764417912,"score_gpt":0.24494444804329277,"score_spread":0.21666967127887485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233716913","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040882947,0.010528171,0.68291885,0.0039090067,0.0017794674,0.0006122368,0.0076393904,0.014770372,0.27375424],"genre_scores_gemma":[0.039490122,0.01829316,0.6206229,0.0019732993,0.0011655347,0.00045384993,0.0279145,0.0034190337,0.28666767],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9995028,0.000049955568,0.000021558486,0.00017403248,0.00022284813,0.000028877756],"domain_scores_gemma":[0.99919945,0.00022663326,0.00003494258,0.0002693501,0.00022620549,0.000043458633],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004918501,0.0014091268,0.0007846716,0.0036234153,0.0008399088,0.0021742822,0.002248337,0.00091369863,0.05496246],"category_scores_gemma":[0.0021171959,0.00064748374,0.0011825496,0.0039949506,0.00047178107,0.002853424,0.0014589255,0.001680793,0.04579351],"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":[0.000024016295,0.00007516571,0.00027297897,0.0005035621,0.000041406307,0.000072361545,0.00006000339,0.0033464092,0.0027729971,0.04517922,0.23035942,0.7172925],"study_design_scores_gemma":[0.000014102794,0.000034255165,0.0007338788,0.0002671688,0.000055805238,0.0006632256,0.000099377394,0.029842827,0.009511101,0.16678353,0.7919591,0.000035717225],"about_ca_topic_score_codex":0.0014757715,"about_ca_topic_score_gemma":0.0031456307,"teacher_disagreement_score":0.05496246,"about_ca_system_score_codex":0.00067843584,"about_ca_system_score_gemma":0.0010177516,"threshold_uncertainty_score":0.18386775},"labels":[],"label_agreement":null},{"id":"W4233729463","doi":"10.4018/978-1-60566-902-1.ch007","title":"User-Centered Interactive Data Mining","year":2010,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Focus (optics); Knowledge extraction; Selection (genetic algorithm); Data stream mining; Data mining; Data science; Automation; Machine learning; Engineering","score_opus":0.04439279174422866,"score_gpt":0.29475131705348384,"score_spread":0.2503585253092552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233729463","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002148282,0.0017211565,0.965318,0.0006694524,0.00007076837,0.0002258689,0.00044300864,0.004008613,0.025394782],"genre_scores_gemma":[0.049595818,0.0029267282,0.9130537,0.00073852565,0.00016435009,0.00063292007,0.0021547908,0.0007435904,0.029989554],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99428,0.0021824667,0.0003265554,0.0008517638,0.0021290514,0.00023011192],"domain_scores_gemma":[0.9887665,0.0072853956,0.00022583753,0.0022140127,0.0012267636,0.0002814856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0068622218,0.0014456111,0.0012776374,0.0022300824,0.00093459385,0.0069561,0.00488401,0.001648793,0.019161487],"category_scores_gemma":[0.013924814,0.0008583553,0.0016529362,0.004061993,0.0013517238,0.0069205086,0.0054199137,0.0023925493,0.010446821],"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":[0.00018887097,0.0002628809,0.002518574,0.001533572,0.00017752316,0.000499528,0.0043289172,0.0071969116,0.007187971,0.22077473,0.060986504,0.69434404],"study_design_scores_gemma":[0.000054422326,0.00012793938,0.0017291463,0.00075104344,0.0001356783,0.002141065,0.0009252801,0.11630629,0.014948828,0.25491384,0.6078127,0.00015385542],"about_ca_topic_score_codex":0.0010313336,"about_ca_topic_score_gemma":0.0016010145,"teacher_disagreement_score":0.019161487,"about_ca_system_score_codex":0.00093734503,"about_ca_system_score_gemma":0.001770325,"threshold_uncertainty_score":0.06410158},"labels":[],"label_agreement":null},{"id":"W4233989131","doi":"10.1177/1536867x1701700406","title":"Text Mining with n-gram Variables","year":2017,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":19,"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":"n-gram; Gram; Computer science; Statistics; Natural language processing; Mathematics; Geology","score_opus":0.046007961283892104,"score_gpt":0.321158498507218,"score_spread":0.2751505372233259,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233989131","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027121276,0.0016505148,0.9333863,0.0014009066,0.0006516511,0.0005064405,0.013501643,0.01746655,0.004314691],"genre_scores_gemma":[0.2547529,0.00090836274,0.7086029,0.0005266936,0.0007381697,0.0010330853,0.023403779,0.00079875725,0.009235328],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960586,0.001591998,0.0006161751,0.0008442847,0.0006726565,0.00021632442],"domain_scores_gemma":[0.9898823,0.007069179,0.00052498764,0.0013621364,0.00090259465,0.00025879036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035683655,0.0011828747,0.0013566725,0.004330618,0.0016882078,0.0027657973,0.0010128649,0.0012270059,0.008292582],"category_scores_gemma":[0.024992755,0.00054695323,0.0018454802,0.0050684074,0.0006500113,0.0027094807,0.002228484,0.0019920338,0.010477304],"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":[0.0011613292,0.00037478175,0.01587087,0.00091614714,0.00054414314,0.00067837606,0.00053468946,0.010914262,0.011487383,0.018031321,0.057518873,0.88196784],"study_design_scores_gemma":[0.00025602887,0.0007280675,0.013392762,0.0005234457,0.0005192304,0.00151579,0.00092006655,0.6752869,0.031861905,0.18341915,0.09138861,0.0001881214],"about_ca_topic_score_codex":0.0018471024,"about_ca_topic_score_gemma":0.0040990105,"teacher_disagreement_score":0.008292582,"about_ca_system_score_codex":0.00040190454,"about_ca_system_score_gemma":0.0022706762,"threshold_uncertainty_score":0.027741492},"labels":[],"label_agreement":null},{"id":"W4234432664","doi":"10.32920/ryerson.14668077","title":"A mapreduce relational-database index-selection tool","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Selection (genetic algorithm); Index (typography); Index selection; Task (project management); Set (abstract data type); Data mining; Process (computing); Relational database; Big data; Database; Systems engineering; Engineering; Artificial intelligence","score_opus":0.029813393387733922,"score_gpt":0.27023554433060676,"score_spread":0.24042215094287284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234432664","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02185691,0.00047725526,0.7260368,0.00058532,0.00023491372,0.00065205165,0.005188164,0.2347328,0.010235746],"genre_scores_gemma":[0.12913354,0.0003008165,0.8446684,0.0003587995,0.00007124789,0.00038117246,0.011737933,0.00503223,0.008315816],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998911,0.00011898934,0.000090982576,0.00022935598,0.0005624632,0.000087269415],"domain_scores_gemma":[0.9990615,0.00023071193,0.000053347383,0.00028955232,0.000270823,0.00009401455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012039939,0.00091857114,0.00068352517,0.0013819574,0.0009363943,0.0014551412,0.0027435776,0.0005865054,0.005172526],"category_scores_gemma":[0.00312354,0.00069918286,0.0007271944,0.001598671,0.00031748944,0.0016027977,0.0012556261,0.0010453685,0.0037219508],"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":[0.0006419026,0.00074882305,0.004605872,0.00057257817,0.00023896634,0.0006720478,0.00035005974,0.03554428,0.04724123,0.013975169,0.2324423,0.6629668],"study_design_scores_gemma":[0.00024528106,0.0002705732,0.0029083658,0.00005825975,0.000062895,0.0007109515,0.00021903346,0.79406875,0.06502888,0.020930545,0.115349494,0.0001469631],"about_ca_topic_score_codex":0.0038177986,"about_ca_topic_score_gemma":0.0045678066,"teacher_disagreement_score":0.005172526,"about_ca_system_score_codex":0.00057717256,"about_ca_system_score_gemma":0.0015415715,"threshold_uncertainty_score":0.017303824},"labels":[],"label_agreement":null},{"id":"W4234761739","doi":"10.1007/978-3-030-04503-6","title":"Trends and Applications in Knowledge Discovery and Data Mining","year":2018,"lang":"en","type":"book","venue":"Lecture notes in computer science","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":"McGill University","funders":"","keywords":"Computer science; Knowledge extraction; Data science; Data mining; Information retrieval","score_opus":0.028540261169193573,"score_gpt":0.3035353017582714,"score_spread":0.27499504058907787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234761739","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0062402524,0.7667844,0.110407576,0.012407587,0.013822852,0.0002667918,0.0024553353,0.0018124365,0.085802644],"genre_scores_gemma":[0.04125809,0.7440648,0.105897,0.0033454087,0.013175316,0.00039486235,0.004024089,0.00047632377,0.087364145],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99892896,0.0001495849,0.00012587028,0.00013331395,0.0005985621,0.00006372715],"domain_scores_gemma":[0.9968545,0.0016291958,0.00026712872,0.00023973825,0.0008524542,0.00015703926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019121744,0.0010350099,0.0015313552,0.007004515,0.0005407597,0.0043160506,0.0014540448,0.0010956858,0.013604599],"category_scores_gemma":[0.006006766,0.00047072922,0.0008296406,0.017642332,0.0008199844,0.006868971,0.001485267,0.0020693678,0.007613129],"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":[0.000050208648,0.00006873031,0.0008659609,0.0029376857,0.000075028445,0.00012141025,0.00014981475,0.0010832566,0.0012120375,0.0695618,0.10353758,0.8203365],"study_design_scores_gemma":[0.000023085622,0.00009219562,0.0016613598,0.0013486923,0.00012456355,0.00094686204,0.00032876342,0.009452394,0.0015499021,0.23851247,0.74591565,0.00004400935],"about_ca_topic_score_codex":0.0007533101,"about_ca_topic_score_gemma":0.0010369137,"teacher_disagreement_score":0.013604599,"about_ca_system_score_codex":0.000777921,"about_ca_system_score_gemma":0.001297636,"threshold_uncertainty_score":0.04551196},"labels":[],"label_agreement":null},{"id":"W4235689493","doi":"10.1017/cbo9781316588284.001","title":"Foreword","year":2016,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Search engine indexing; Space (punctuation); Raw data; Computer science; Hash function; Data structure; Theoretical computer science; Information retrieval; Programming language; Operating system","score_opus":0.02287764483493232,"score_gpt":0.20072153103464993,"score_spread":0.1778438861997176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235689493","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00041019547,0.028788714,0.0038758807,0.030839326,0.08689544,0.0001393965,0.0021001045,0.0012989038,0.84565204],"genre_scores_gemma":[0.0010459254,0.0065625724,0.00087824493,0.0062819594,0.008554398,0.000039887876,0.0010427915,0.0006333207,0.974961],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993243,0.000051382158,0.00003058738,0.00011732657,0.00042410905,0.000052309104],"domain_scores_gemma":[0.99855596,0.00028312477,0.00006264937,0.00012929668,0.00070423906,0.0002648074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047151247,0.0010363602,0.0009376598,0.0018455083,0.0015360182,0.004750506,0.0015707264,0.0017765852,0.4461473],"category_scores_gemma":[0.0032940737,0.0003633174,0.00074179465,0.001751517,0.0007469388,0.0044496213,0.002073267,0.003899632,0.42350897],"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":[0.0000081661465,0.000010023077,0.000017483007,0.00008552855,0.0000015733267,0.000022879516,0.00002899516,0.000032264365,0.00009131597,0.0050965366,0.9563292,0.038276136],"study_design_scores_gemma":[0.0000010555935,0.000003315795,0.000029666087,0.00006669086,7.1632957e-7,0.0000443467,0.0000150767555,0.00001186404,0.000030903353,0.001422256,0.99837214,0.0000019768934],"about_ca_topic_score_codex":0.0013309491,"about_ca_topic_score_gemma":0.0023596652,"teacher_disagreement_score":0.4461473,"about_ca_system_score_codex":0.0013547622,"about_ca_system_score_gemma":0.001183384,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W4236239227","doi":"10.1007/978-1-4614-6170-8_100496","title":"Relational Data Mining","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Data Mining Algorithms and Applications","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","funders":"","keywords":"Computer science; Data mining","score_opus":0.11478610015591141,"score_gpt":0.27508837533447067,"score_spread":0.16030227517855927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236239227","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024212173,0.025476605,0.745907,0.0035163553,0.0016878207,0.0003293114,0.0044064303,0.0064488836,0.20980635],"genre_scores_gemma":[0.023062048,0.03919944,0.6502752,0.0022536507,0.0016490333,0.00032344475,0.016970647,0.0016813452,0.26458523],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989303,0.00009620001,0.000086149135,0.0002561635,0.00059334893,0.000037810827],"domain_scores_gemma":[0.9990326,0.0003503539,0.000042704232,0.00028269834,0.00025233504,0.000039226157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096067047,0.0012023797,0.000989518,0.0028183977,0.00074235117,0.0032405327,0.0021709008,0.0006623315,0.035397213],"category_scores_gemma":[0.0032746675,0.00073926715,0.0010033179,0.0058126887,0.0006713326,0.005001833,0.002016197,0.0018655066,0.03446624],"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":[0.000015770673,0.000039019837,0.00023943707,0.0005143582,0.00003371425,0.000067687404,0.000121029094,0.0012405902,0.0016065682,0.075646624,0.1543689,0.7661063],"study_design_scores_gemma":[0.000005645064,0.000017755438,0.00038679846,0.00029644,0.00003233362,0.00064134604,0.00008663627,0.0079326965,0.0034113242,0.12229519,0.86486703,0.000026815384],"about_ca_topic_score_codex":0.000853667,"about_ca_topic_score_gemma":0.0013271772,"teacher_disagreement_score":0.035397213,"about_ca_system_score_codex":0.00072698307,"about_ca_system_score_gemma":0.0009776377,"threshold_uncertainty_score":0.118415415},"labels":[],"label_agreement":null},{"id":"W4236396966","doi":"10.1007/978-1-4614-6170-8_100904","title":"Query Spelling Correction","year":2014,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Spelling; Computer science; Natural language processing; Artificial intelligence; Information retrieval; Linguistics; Philosophy","score_opus":0.018250562111067743,"score_gpt":0.2230568779760695,"score_spread":0.20480631586500175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236396966","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012412501,0.009878438,0.71174735,0.0069073252,0.011119588,0.0014282715,0.017220795,0.093092114,0.13619363],"genre_scores_gemma":[0.117300116,0.008314624,0.45782387,0.005224111,0.003528263,0.0006299257,0.050425466,0.02292655,0.33382708],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9932783,0.0006436685,0.0006176819,0.0009010639,0.004067177,0.00049196935],"domain_scores_gemma":[0.9861144,0.0020700821,0.0004422497,0.0045309262,0.006639183,0.00020313078],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029709577,0.0020501257,0.002178644,0.004400282,0.0017879844,0.0036609578,0.0039505484,0.0014179049,0.06679125],"category_scores_gemma":[0.017279807,0.0006222125,0.0018490761,0.0042670714,0.001111368,0.0030968115,0.0035363485,0.002547612,0.06586761],"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":[0.0002780279,0.00007077547,0.0005282913,0.0008328831,0.00005434924,0.00041641455,0.00017927185,0.0012654312,0.018603392,0.013421029,0.3052184,0.65913165],"study_design_scores_gemma":[0.00007395636,0.000110956345,0.0011880057,0.00038149595,0.00014227416,0.0027257244,0.0002875119,0.016677734,0.095244765,0.021232896,0.86179507,0.00013957369],"about_ca_topic_score_codex":0.0060109473,"about_ca_topic_score_gemma":0.0043548974,"teacher_disagreement_score":0.06679125,"about_ca_system_score_codex":0.0013660203,"about_ca_system_score_gemma":0.0034941237,"threshold_uncertainty_score":0.22343898},"labels":[],"label_agreement":null},{"id":"W4236573062","doi":"10.1007/978-1-4614-6170-8_100620","title":"Subgraph Mining","year":2014,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Computer science","score_opus":0.020035940789425003,"score_gpt":0.22603676304007178,"score_spread":0.20600082225064678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236573062","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0068138735,0.00890133,0.73145956,0.0023186516,0.0011219932,0.0005356677,0.008533704,0.013531304,0.2267839],"genre_scores_gemma":[0.05247199,0.013656421,0.6682483,0.0011535006,0.00084151287,0.00038719503,0.039454434,0.0031868494,0.22059971],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9995504,0.00004666008,0.000019812405,0.00015453131,0.00019862095,0.000029966923],"domain_scores_gemma":[0.99943966,0.00014402362,0.00002605379,0.00020916719,0.00014603965,0.00003497559],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003852676,0.0011913112,0.000798924,0.0030738292,0.00076512014,0.001707535,0.0018479316,0.0007077462,0.041513443],"category_scores_gemma":[0.0016650511,0.000548628,0.0011153043,0.0043543577,0.00043545724,0.0027320113,0.0015105739,0.0011976378,0.029370468],"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":[0.000031125826,0.000056593242,0.00043628184,0.00046434812,0.000044513923,0.00008508836,0.0000771075,0.0037242384,0.004041001,0.03694939,0.18946505,0.76462525],"study_design_scores_gemma":[0.00001664837,0.00004363173,0.0012852674,0.00026422687,0.00007812878,0.0011422763,0.00015023985,0.04175883,0.014527573,0.17958072,0.76111144,0.000040917526],"about_ca_topic_score_codex":0.0015997345,"about_ca_topic_score_gemma":0.004108858,"teacher_disagreement_score":0.041513443,"about_ca_system_score_codex":0.00059158204,"about_ca_system_score_gemma":0.00085769343,"threshold_uncertainty_score":0.13887632},"labels":[],"label_agreement":null},{"id":"W4236640576","doi":"10.1007/978-3-642-27739-9_71-2","title":"Certificate Revocation","year":2021,"lang":"en","type":"book-chapter","venue":"","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":"University of Ottawa","funders":"","keywords":"Revocation list; Revocation; Computer science; Root certificate; Certificate; Computer security; Public key certificate; Operating system; Public-key cryptography; Theoretical computer science","score_opus":0.10824683529180434,"score_gpt":0.2709133802974924,"score_spread":0.16266654500568806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236640576","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006687555,0.0016722109,0.11039703,0.0044302647,0.004175863,0.0008670502,0.0021912232,0.010005397,0.8595734],"genre_scores_gemma":[0.12917973,0.0024533179,0.029817566,0.0029179417,0.0008669424,0.0003984109,0.004373954,0.0025409958,0.82745105],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963147,0.0005911066,0.00016603824,0.00067655277,0.0017051768,0.00054640725],"domain_scores_gemma":[0.9932579,0.0010865283,0.00023022575,0.003558606,0.0015200264,0.00034687147],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024872383,0.00085160456,0.00086789625,0.0021433982,0.0019595593,0.0054900916,0.0025279014,0.0021058775,0.119839065],"category_scores_gemma":[0.011994059,0.00052946736,0.0010044704,0.0019337061,0.0015150654,0.007676641,0.004754909,0.0036881666,0.08437796],"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":[0.000287486,0.00016174381,0.0005123751,0.00037783448,0.0000197582,0.00039951637,0.0003941357,0.0021151504,0.0028404796,0.28565598,0.37947997,0.32775563],"study_design_scores_gemma":[0.000030502331,0.0000510495,0.0001920769,0.00015748756,0.000016455542,0.0006016303,0.00017868499,0.0028082733,0.0045893295,0.037073374,0.9542709,0.000030243174],"about_ca_topic_score_codex":0.002392508,"about_ca_topic_score_gemma":0.0025343553,"teacher_disagreement_score":0.119839065,"about_ca_system_score_codex":0.0024531996,"about_ca_system_score_gemma":0.0035564932,"threshold_uncertainty_score":0.40090162},"labels":[],"label_agreement":null},{"id":"W4237492828","doi":"10.4018/978-1-60566-010-3.ch150","title":"Hierarchical Document Clustering","year":2009,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; Concordia University","funders":"","keywords":"Hierarchical clustering; Cluster analysis; Document clustering; Brown clustering; Hierarchy; Computer science; Complete-linkage clustering; Directory; Hierarchical clustering of networks; Single-linkage clustering; Fuzzy clustering; Tree (set theory); Consensus clustering; Data mining; Information retrieval; Artificial intelligence; Canopy clustering algorithm; Mathematics","score_opus":0.017641107023829573,"score_gpt":0.26083931515893066,"score_spread":0.2431982081351011,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237492828","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045133955,0.020000754,0.87279546,0.0013064559,0.00094352954,0.0015115878,0.017415948,0.011560394,0.069952495],"genre_scores_gemma":[0.03840612,0.012396365,0.85958815,0.00060693297,0.00055565394,0.00080785557,0.03370426,0.0012318403,0.052702874],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969702,0.0005828094,0.00024961442,0.0007779267,0.0012570058,0.00016247368],"domain_scores_gemma":[0.9970304,0.0007848987,0.0001705188,0.00060541776,0.0013031403,0.00010560064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017214549,0.0015040933,0.0015760364,0.009631068,0.0017970873,0.005191956,0.0029598805,0.0014002243,0.02500525],"category_scores_gemma":[0.006422894,0.00056765537,0.0016291505,0.015320995,0.0006551445,0.0034466803,0.0021593003,0.001336733,0.031464662],"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":[0.00007159584,0.000066325796,0.0009388465,0.0015099383,0.00017012014,0.00016990888,0.0004286657,0.0069845472,0.0026882517,0.03187753,0.1681255,0.78696877],"study_design_scores_gemma":[0.000041827916,0.000074577554,0.0020624513,0.0005590331,0.00017435265,0.0010560888,0.0004992896,0.06439306,0.0067465613,0.07926447,0.84500533,0.00012282458],"about_ca_topic_score_codex":0.005886948,"about_ca_topic_score_gemma":0.008169254,"teacher_disagreement_score":0.02500525,"about_ca_system_score_codex":0.0017980292,"about_ca_system_score_gemma":0.002909532,"threshold_uncertainty_score":0.08365089},"labels":[],"label_agreement":null},{"id":"W4237733903","doi":"10.4018/9781591405573.ch093","title":"Explanation-Oriented Data Mining","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Knowledge extraction; Computer science; Data science; Data mining; Order (exchange); Information retrieval","score_opus":0.060443389874153174,"score_gpt":0.2752262516850788,"score_spread":0.21478286181092562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237733903","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037830914,0.022079201,0.8234602,0.007934954,0.00072645943,0.0006668548,0.0031107466,0.002331424,0.13590713],"genre_scores_gemma":[0.074373655,0.031478405,0.8200726,0.003622046,0.0009194476,0.00084752694,0.009454047,0.00068274786,0.058549505],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983333,0.0005346269,0.00009349109,0.00033341654,0.0006222619,0.0000828794],"domain_scores_gemma":[0.9969927,0.002036542,0.00013162736,0.0005012369,0.00026206154,0.00007571768],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028601969,0.0014350907,0.001074946,0.0035329722,0.0006989388,0.0044032247,0.0034371205,0.0013488792,0.026793009],"category_scores_gemma":[0.0059979754,0.00053068955,0.0015538054,0.0051017203,0.001656485,0.004763143,0.002792987,0.002111347,0.009583751],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038235117,0.0000823479,0.0012267537,0.0015916128,0.00015940874,0.00020293219,0.0005127036,0.0049601626,0.00061475625,0.465934,0.075399816,0.4492772],"study_design_scores_gemma":[0.000026598638,0.000026263246,0.0005554309,0.00048056114,0.000049105805,0.0003797732,0.00022729053,0.020325277,0.0010190452,0.6624087,0.31447518,0.00002678852],"about_ca_topic_score_codex":0.0007794656,"about_ca_topic_score_gemma":0.0012800321,"teacher_disagreement_score":0.026793009,"about_ca_system_score_codex":0.001106546,"about_ca_system_score_gemma":0.0014751105,"threshold_uncertainty_score":0.0896315},"labels":[],"label_agreement":null},{"id":"W4237989913","doi":"10.4018/9781605669823.ch108","title":"Hyperlink Structure Inspired by Web Usage","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint Mary's University","funders":"","keywords":"Hyperlink; Computer science; World Wide Web; Visualization; Information retrieval; Link analysis; Graph; Web navigation; The Internet; Web mining; Web page; Data science; Data mining; Theoretical computer science","score_opus":0.018442996459801363,"score_gpt":0.22934047986517478,"score_spread":0.21089748340537343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237989913","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06542916,0.004784767,0.82196796,0.0011040088,0.00045035762,0.00019463019,0.0014046147,0.0025328596,0.10213162],"genre_scores_gemma":[0.34405294,0.0059924433,0.58657,0.00033617558,0.00029880746,0.00032724746,0.0033142401,0.00091117626,0.058197025],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997842,0.000042586027,0.000010109013,0.00006988042,0.00007768472,0.00001556646],"domain_scores_gemma":[0.9994055,0.00027876638,0.000051599505,0.00010359674,0.00012308941,0.000037513204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023386073,0.00046805892,0.0003147823,0.0020993534,0.0006263819,0.001547441,0.000642714,0.00060722255,0.009201607],"category_scores_gemma":[0.0020952625,0.00035164805,0.0005858936,0.0038177732,0.00059113366,0.002906894,0.00068225316,0.0010073729,0.0025402808],"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":[0.00009399769,0.00014574121,0.0046258303,0.0006827432,0.00006876447,0.00035237486,0.0011961372,0.033534206,0.020290801,0.46649405,0.021620642,0.45089483],"study_design_scores_gemma":[0.000027190152,0.00009007418,0.0051120585,0.00030262655,0.000076170174,0.00089123927,0.00041210267,0.3276271,0.012621282,0.47942454,0.17335252,0.000063056905],"about_ca_topic_score_codex":0.0010588141,"about_ca_topic_score_gemma":0.0023748723,"teacher_disagreement_score":0.009201607,"about_ca_system_score_codex":0.00054894655,"about_ca_system_score_gemma":0.00045543918,"threshold_uncertainty_score":0.030782461},"labels":[],"label_agreement":null},{"id":"W4238108176","doi":"10.1007/978-1-4614-6170-8_100252","title":"Network Mining","year":2014,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Computer science","score_opus":0.02520841309730137,"score_gpt":0.22884941370659706,"score_spread":0.20364100060929569,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4238108176","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004532295,0.0077937725,0.57216674,0.003964267,0.0017450546,0.00051651476,0.004547424,0.0058729826,0.39886096],"genre_scores_gemma":[0.057151455,0.021611843,0.3766572,0.0015167255,0.0018782292,0.00058075384,0.013880438,0.0014042248,0.52531916],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9996014,0.000038263104,0.000017129447,0.000119295255,0.00019764471,0.000026149844],"domain_scores_gemma":[0.99935895,0.00020151169,0.000035915313,0.00017497859,0.00019724865,0.00003140648],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062129094,0.0011150595,0.0005906358,0.0026296524,0.0008027668,0.00206005,0.0017167855,0.000727577,0.040606625],"category_scores_gemma":[0.0022202749,0.00045996398,0.0006692156,0.0028395972,0.0003322908,0.0031928502,0.0013026498,0.0012225272,0.025333636],"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":[0.000024271636,0.000044066637,0.00050610583,0.00031364735,0.000030601335,0.0000844127,0.00007591504,0.0047280076,0.0015980599,0.057210162,0.16964048,0.76574415],"study_design_scores_gemma":[0.000009993005,0.000025729874,0.00090225483,0.00027614905,0.00004844855,0.0006958853,0.00012514883,0.037042946,0.006175903,0.13266446,0.8220074,0.000025643303],"about_ca_topic_score_codex":0.0012138926,"about_ca_topic_score_gemma":0.0023814214,"teacher_disagreement_score":0.040606625,"about_ca_system_score_codex":0.00063802866,"about_ca_system_score_gemma":0.00073658465,"threshold_uncertainty_score":0.13584268},"labels":[],"label_agreement":null},{"id":"W4238305712","doi":"10.1007/978-1-4939-7131-2_100567","title":"Knowledge Discovery","year":2018,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Computer science","score_opus":0.03148403362289521,"score_gpt":0.26738884686106507,"score_spread":0.23590481323816986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4238305712","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019849457,0.0143599445,0.28237638,0.007828166,0.0018771067,0.0003872838,0.0022215492,0.0024077059,0.68655694],"genre_scores_gemma":[0.035050366,0.029891841,0.26729837,0.0041310834,0.0019925851,0.00046258618,0.009414586,0.00078310166,0.6509755],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99898833,0.00014369524,0.00005984022,0.000264694,0.0004887006,0.0000547803],"domain_scores_gemma":[0.9985361,0.0006258731,0.000046613757,0.0004260446,0.0002988296,0.00006648436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013795932,0.001012738,0.0007792242,0.003447562,0.001014093,0.0052229045,0.0025713132,0.0011086209,0.06658664],"category_scores_gemma":[0.004026693,0.0005323226,0.0009312978,0.0031247756,0.0012670483,0.00608072,0.0032806138,0.0018011172,0.049887054],"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":[0.000020679561,0.000049520717,0.00015329827,0.0005756472,0.000032119275,0.00009048712,0.0001941586,0.0007429939,0.0011258245,0.21806818,0.16081585,0.6181313],"study_design_scores_gemma":[0.0000053084746,0.000012481884,0.00014734693,0.00027811897,0.000017759396,0.0002705861,0.00010323052,0.0023120388,0.001629651,0.18247937,0.81272984,0.00001423791],"about_ca_topic_score_codex":0.0009417914,"about_ca_topic_score_gemma":0.0011778577,"teacher_disagreement_score":0.06658664,"about_ca_system_score_codex":0.0012706963,"about_ca_system_score_gemma":0.0020835863,"threshold_uncertainty_score":0.22275454},"labels":[],"label_agreement":null},{"id":"W4238710876","doi":"10.1007/3-540-36175-8_33","title":"Position Coded Pre-order Linked WAP-Tree for Web Log Sequential Pattern Mining","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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 Windsor","funders":"","keywords":"Computer science; Prefix; Tree (set theory); Trie; Fractal tree index; Suffix tree; Node (physics); Binary tree; Preorder; Suffix; Web log analysis software; Data mining; Tree structure; Theoretical computer science; Algorithm; Web server; Interval tree; Data structure; World Wide Web; Combinatorics; Mathematics; The Internet; Discrete mathematics; Operating system","score_opus":0.02219605984107578,"score_gpt":0.26807849165285247,"score_spread":0.24588243181177669,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4238710876","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051755555,0.0003401082,0.9282742,0.00019266854,0.00015129536,0.00034070766,0.004077212,0.011865873,0.0030023635],"genre_scores_gemma":[0.21623501,0.00017112293,0.770273,0.00009677984,0.000048323305,0.00036408682,0.0077761197,0.00041387885,0.0046216394],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99955934,0.000069351765,0.000060464536,0.00008041026,0.00017923611,0.000051217023],"domain_scores_gemma":[0.9981413,0.00065915956,0.00008131935,0.0005109091,0.00052091235,0.0000864612],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058493443,0.00036077315,0.0006060468,0.0017375544,0.00070414925,0.0010367552,0.001515479,0.00081438484,0.0055499272],"category_scores_gemma":[0.0048478013,0.00032766926,0.00047011985,0.0027476312,0.0002970171,0.001165223,0.0007533894,0.00090531324,0.0020470766],"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":[0.001032757,0.00036027527,0.0036902146,0.00032060145,0.00005260461,0.00038789152,0.000190024,0.048232827,0.0152332615,0.012946425,0.02006378,0.8974893],"study_design_scores_gemma":[0.00011793745,0.00026724164,0.0019953107,0.00007420848,0.0000564234,0.00037430273,0.00013897037,0.9293905,0.017416487,0.03449129,0.015634682,0.000042676573],"about_ca_topic_score_codex":0.0044148955,"about_ca_topic_score_gemma":0.007352376,"teacher_disagreement_score":0.0055499272,"about_ca_system_score_codex":0.0004316385,"about_ca_system_score_gemma":0.0015115495,"threshold_uncertainty_score":0.01856637},"labels":[],"label_agreement":null},{"id":"W4239137943","doi":"10.4018/978-1-60566-026-4.ch499","title":"Process-Based Data Mining","year":2009,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Aga Khan Foundation","funders":"","keywords":"Computer science; Pentium; Database; Operating system","score_opus":0.04481897680771465,"score_gpt":0.29912709183069947,"score_spread":0.25430811502298484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239137943","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007425344,0.0067489096,0.9521411,0.0016466266,0.00060099014,0.0013093756,0.0065153586,0.006354984,0.017257242],"genre_scores_gemma":[0.24293186,0.011913656,0.69572186,0.0015143915,0.0007697116,0.0015368451,0.030301537,0.0005970626,0.014713092],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9949567,0.00055708864,0.00048292603,0.0016323971,0.0021118228,0.00025904085],"domain_scores_gemma":[0.99682224,0.0010487877,0.0003122548,0.00075873686,0.0009867551,0.00007112791],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030229636,0.0025917569,0.0027831146,0.006080766,0.001410685,0.005037554,0.0046061603,0.002062502,0.009739241],"category_scores_gemma":[0.008760754,0.00087408914,0.0040153246,0.008309151,0.0012752059,0.0047475286,0.0026692878,0.0027439166,0.009609012],"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":[0.0004072554,0.0006019944,0.011996222,0.002441909,0.0010361903,0.0007423129,0.00030323127,0.09195012,0.0046679243,0.04626247,0.047772355,0.79181796],"study_design_scores_gemma":[0.000099837824,0.0003385905,0.0040008766,0.0005916728,0.0004474327,0.0013264228,0.00033043133,0.6870359,0.013447938,0.13307819,0.15918954,0.00011316551],"about_ca_topic_score_codex":0.004037414,"about_ca_topic_score_gemma":0.0040572905,"teacher_disagreement_score":0.009739241,"about_ca_system_score_codex":0.0013631034,"about_ca_system_score_gemma":0.0030596342,"threshold_uncertainty_score":0.03258103},"labels":[],"label_agreement":null},{"id":"W4239178708","doi":"10.1007/978-1-4939-7131-2_100951","title":"Reality Mining","year":2018,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Computer science","score_opus":0.053733920987922894,"score_gpt":0.27994074414392484,"score_spread":0.22620682315600193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239178708","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030337693,0.006050683,0.3945812,0.0050893556,0.0018262996,0.00039237374,0.0073946305,0.010309952,0.57132185],"genre_scores_gemma":[0.04063824,0.013380213,0.36974987,0.0022536325,0.0013175507,0.0003989428,0.024061326,0.0023592787,0.545841],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904007,0.000106403844,0.000052831994,0.00028047693,0.00046514752,0.00005497788],"domain_scores_gemma":[0.99875665,0.00031700602,0.000055515527,0.00043603365,0.00037104235,0.00006385667],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010520187,0.0012684949,0.00084972486,0.0025777551,0.0011444794,0.004478575,0.0027332988,0.0012418099,0.11429209],"category_scores_gemma":[0.0042974674,0.0007063073,0.0011240167,0.0028238439,0.0006523059,0.0054226317,0.0025869259,0.0018814604,0.097377695],"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":[0.000048257065,0.000054639095,0.0003375725,0.00052699697,0.000031596486,0.000116277166,0.00015652431,0.0018180296,0.0015754363,0.10540629,0.28439048,0.60553795],"study_design_scores_gemma":[0.0000098165,0.00002190346,0.00034628107,0.00016840723,0.000021950153,0.00050182844,0.00014695368,0.007637207,0.002658409,0.06367541,0.9247859,0.000025948662],"about_ca_topic_score_codex":0.0011279522,"about_ca_topic_score_gemma":0.0017522817,"teacher_disagreement_score":0.11429209,"about_ca_system_score_codex":0.00062529306,"about_ca_system_score_gemma":0.001002331,"threshold_uncertainty_score":0.38234514},"labels":[],"label_agreement":null},{"id":"W4239206664","doi":"10.1007/978-0-387-39940-9_3885","title":"Tree-Structured Classifier","year":2009,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Database 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":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Computer science; Pattern recognition (psychology); Forestry; Geography","score_opus":0.018298514902838094,"score_gpt":0.23816568908139746,"score_spread":0.21986717417855936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239206664","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0076756137,0.0022664212,0.93262327,0.00088153797,0.0011143095,0.00061461097,0.0063398746,0.016467007,0.03201726],"genre_scores_gemma":[0.06768053,0.0016584428,0.83763176,0.00097539317,0.00074878475,0.0005722748,0.024510002,0.0011670138,0.06505578],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99890995,0.00012652065,0.00008318669,0.00032312554,0.00046509935,0.000092019836],"domain_scores_gemma":[0.9984603,0.00039405553,0.000058080088,0.00038753488,0.00062591746,0.00007404431],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010290742,0.0009445502,0.0013113286,0.0021774657,0.00094232504,0.002049022,0.002133699,0.0014546411,0.02718885],"category_scores_gemma":[0.003602085,0.00045430788,0.0011044035,0.0025281818,0.00037379295,0.002492449,0.0013224599,0.0017070937,0.032302678],"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":[0.00012855073,0.00013940748,0.000583375,0.00015438627,0.00005503263,0.00009545275,0.000039393868,0.005932519,0.0046938793,0.013552897,0.10780079,0.8668244],"study_design_scores_gemma":[0.000105202605,0.00032855175,0.0014276833,0.00017915801,0.0001529593,0.0011067751,0.00011606252,0.62162143,0.02446244,0.124054834,0.22636114,0.000083777624],"about_ca_topic_score_codex":0.0022759335,"about_ca_topic_score_gemma":0.00524838,"teacher_disagreement_score":0.02718885,"about_ca_system_score_codex":0.0006322303,"about_ca_system_score_gemma":0.0022341616,"threshold_uncertainty_score":0.090955734},"labels":[],"label_agreement":null},{"id":"W4239752204","doi":"10.1007/978-1-4419-5906-5_71","title":"Certificate Revocation","year":2011,"lang":"en","type":"book-chapter","venue":"","topic":"Data Mining Algorithms and Applications","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":"Revocation; Revocation list; Certificate; Computer science; Computer security; Public key certificate; Programming language; Public-key cryptography; Theoretical computer science","score_opus":0.1565215658751963,"score_gpt":0.26157447271113665,"score_spread":0.10505290683594035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239752204","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012783663,0.0030929607,0.21261898,0.0057038846,0.0052927244,0.0011926917,0.0024626614,0.011449802,0.74540263],"genre_scores_gemma":[0.25285983,0.004424418,0.054608043,0.003079917,0.0011956419,0.0005594317,0.0057090223,0.0026932661,0.67487043],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961443,0.0006306521,0.00021376996,0.00079695974,0.0016140414,0.000600332],"domain_scores_gemma":[0.99335116,0.0010421876,0.00025967593,0.0036354142,0.00141221,0.00029933875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002665035,0.00091545976,0.0010180596,0.002058479,0.0019722644,0.0051914956,0.0026973612,0.0019640818,0.07432026],"category_scores_gemma":[0.012131582,0.00054146274,0.001109946,0.002060299,0.0017908998,0.008762345,0.005050616,0.0038740495,0.048291102],"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":[0.00036647444,0.00019329887,0.0006470556,0.0005154361,0.00002911499,0.00046576918,0.00047480984,0.0032229756,0.003799475,0.33432493,0.2438926,0.41206807],"study_design_scores_gemma":[0.0000491354,0.00008375928,0.0002939968,0.00025220946,0.000032348267,0.0010189367,0.0002751161,0.005207191,0.0088861,0.0650293,0.9188199,0.00005194838],"about_ca_topic_score_codex":0.0019492222,"about_ca_topic_score_gemma":0.0018374983,"teacher_disagreement_score":0.07432026,"about_ca_system_score_codex":0.0024080079,"about_ca_system_score_gemma":0.0033692727,"threshold_uncertainty_score":0.24862605},"labels":[],"label_agreement":null},{"id":"W4239963930","doi":"10.1007/978-1-4757-3283-2_1","title":"Introduction","year":2001,"lang":"en","type":"book-chapter","venue":"","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":"University of Regina","funders":"","keywords":"Generalization; Computer science; Knowledge extraction; Set (abstract data type); Data mining; Data science; Information retrieval; Mathematics","score_opus":0.01746827791194024,"score_gpt":0.22820569743261182,"score_spread":0.21073741952067157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239963930","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00041000312,0.0028427998,0.011896192,0.0028891691,0.0046928884,0.00017245865,0.0022441575,0.0014444138,0.973408],"genre_scores_gemma":[0.0011962777,0.0018518814,0.0025359928,0.00096727593,0.00073160115,0.00008231911,0.001612497,0.00029244224,0.99072963],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994704,0.000042587606,0.00001833096,0.000112436705,0.000302048,0.00005422362],"domain_scores_gemma":[0.9991196,0.0001165374,0.000029828294,0.00014501515,0.00042194294,0.00016714781],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005900026,0.0009531339,0.0005574084,0.0017692567,0.0011458712,0.0036310495,0.0017588825,0.0015425457,0.56634957],"category_scores_gemma":[0.002275313,0.000361644,0.000511865,0.0016539342,0.00054721476,0.0032571738,0.0022994746,0.0016615774,0.5098968],"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":[0.000021793816,0.000037919122,0.00008261322,0.00015773093,0.0000021929197,0.000040270723,0.000086376014,0.00014119383,0.00058795826,0.03244949,0.7424219,0.22397059],"study_design_scores_gemma":[0.0000016080077,0.000006287265,0.00004978389,0.000045892466,9.773814e-7,0.000034674667,0.000020357611,0.00003144523,0.000114075294,0.0040928624,0.9955996,0.0000024104754],"about_ca_topic_score_codex":0.0015005027,"about_ca_topic_score_gemma":0.00238546,"teacher_disagreement_score":0.56634957,"about_ca_system_score_codex":0.0009869152,"about_ca_system_score_gemma":0.0016517894,"threshold_uncertainty_score":0.6185497},"labels":[],"label_agreement":null},{"id":"W4239981520","doi":"10.1007/s10618-009-0144-3","title":"Fast incremental mining of web sequential patterns with PLWAP tree","year":2009,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Data Mining Algorithms and Applications","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 Windsor","funders":"","keywords":"Computer science; Data mining; Tree (set theory); Web mining; Information retrieval; World Wide Web; Mathematics; Web service","score_opus":0.0352025202348579,"score_gpt":0.2851548256075449,"score_spread":0.249952305372687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239981520","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10378817,0.0011707183,0.8797337,0.00032760898,0.00016238498,0.00044847245,0.003385322,0.008791653,0.0021921282],"genre_scores_gemma":[0.27908906,0.00044870545,0.7112548,0.00009837242,0.00007398587,0.00030447874,0.0062989187,0.00024229714,0.0021894085],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991241,0.00011004627,0.00009772813,0.00016554123,0.00041132915,0.00009108273],"domain_scores_gemma":[0.997486,0.0010919488,0.00020693097,0.00040751306,0.0006813127,0.00012624695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008474107,0.0005587126,0.00096313574,0.003480332,0.0007403493,0.0011950828,0.0015350919,0.00059853814,0.0018568397],"category_scores_gemma":[0.0055308226,0.00054113485,0.0009366437,0.003947287,0.00026154966,0.0022466916,0.0010791122,0.00080368377,0.0011561778],"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":[0.00061900495,0.00029772156,0.014442552,0.0005609684,0.0001986943,0.0008946408,0.0002249265,0.020826148,0.017367166,0.004538511,0.014292613,0.9257371],"study_design_scores_gemma":[0.00011608323,0.00028011124,0.0050521344,0.00005567854,0.00018734107,0.0014392851,0.0001957757,0.9434766,0.0155340005,0.021471404,0.012157874,0.00003369222],"about_ca_topic_score_codex":0.0031526694,"about_ca_topic_score_gemma":0.005857447,"teacher_disagreement_score":0.003480332,"about_ca_system_score_codex":0.0002513818,"about_ca_system_score_gemma":0.0011770187,"threshold_uncertainty_score":0.0062686205},"labels":[],"label_agreement":null},{"id":"W4240084214","doi":"10.1007/978-0-387-39940-9_2819","title":"Immersive Data Mining","year":2009,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Database 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":"University of Waterloo","funders":"","keywords":"Computer science; Data science","score_opus":0.037921032441396406,"score_gpt":0.2669606423788349,"score_spread":0.22903960993743847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240084214","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036615324,0.0028413814,0.9437011,0.00059199904,0.0005152007,0.00011679998,0.0020550622,0.010133498,0.036383413],"genre_scores_gemma":[0.047697585,0.006374011,0.8234523,0.0008304152,0.00031159853,0.00039201562,0.0066062864,0.0015890934,0.112746745],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995945,0.00006227337,0.000026489895,0.00010056996,0.00019414154,0.000022139133],"domain_scores_gemma":[0.9989825,0.00059844094,0.000027543238,0.00019625193,0.00013314576,0.00006213467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006631804,0.0013036446,0.00084301655,0.0008799118,0.00031850958,0.0020192494,0.0015949513,0.00073655415,0.055170447],"category_scores_gemma":[0.002119123,0.0007577946,0.0009147548,0.00097306666,0.0004858868,0.0021824671,0.003150539,0.0012244502,0.0137138115],"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":[0.00020116263,0.00018332023,0.0008871236,0.00093430607,0.00013929598,0.0004552398,0.0005309892,0.0141889695,0.02439631,0.033445783,0.15691087,0.7677266],"study_design_scores_gemma":[0.00007987047,0.00020003422,0.0026497121,0.00047595764,0.00008440719,0.0025883154,0.0003744784,0.14394733,0.026796112,0.10836718,0.7143033,0.00013325445],"about_ca_topic_score_codex":0.0007216446,"about_ca_topic_score_gemma":0.0018083295,"teacher_disagreement_score":0.055170447,"about_ca_system_score_codex":0.00020730434,"about_ca_system_score_gemma":0.00040016355,"threshold_uncertainty_score":0.18456352},"labels":[],"label_agreement":null},{"id":"W4241015129","doi":"10.1080/18756891.2011.9727760","title":"Experimental Comparison of Iterative Versus Evolutionary Crisp and Rough Clustering","year":2011,"lang":"en","type":"article","venue":"International Journal of Computational Intelligence Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint Mary's University","funders":"","keywords":"Cluster analysis; Medoid; Rough set; Data mining; Computer science; Self-organizing map; k-medoids; Set (abstract data type); Genetic algorithm; Algorithm; Canopy clustering algorithm; Correlation clustering; Pattern recognition (psychology); Mathematics; Artificial intelligence; Machine learning","score_opus":0.09646447562586563,"score_gpt":0.3715459763866903,"score_spread":0.27508150076082466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241015129","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7691313,0.0018268398,0.20393385,0.00037957274,0.0003039012,0.00052296073,0.0012442173,0.0037189757,0.01893834],"genre_scores_gemma":[0.7651031,0.00042125312,0.22928406,0.000062567844,0.00003107659,0.00027353232,0.0018349516,0.00035662513,0.002632811],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966594,0.0010125894,0.00032383937,0.00047248462,0.0013631139,0.00016853973],"domain_scores_gemma":[0.98396677,0.008650471,0.0004843636,0.0019066633,0.0047816695,0.0002101462],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041633095,0.0007010892,0.0008333919,0.0029319252,0.0010204955,0.0015197897,0.0013777207,0.0009909945,0.0025057753],"category_scores_gemma":[0.017573211,0.0002664004,0.00048432712,0.0032404002,0.000719415,0.0013797074,0.00082772254,0.0004821031,0.0006628645],"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":[0.004956667,0.0014120095,0.0060565625,0.0018553745,0.00047466924,0.00026700465,0.0010217838,0.33927605,0.07649172,0.0073491265,0.005375503,0.5554636],"study_design_scores_gemma":[0.00028237482,0.0019815543,0.017638652,0.0001084086,0.00016157597,0.00036058025,0.00093996036,0.8582055,0.109886885,0.0044749146,0.00579994,0.00015959184],"about_ca_topic_score_codex":0.0033856104,"about_ca_topic_score_gemma":0.0031191646,"teacher_disagreement_score":0.0041633095,"about_ca_system_score_codex":0.0006947757,"about_ca_system_score_gemma":0.000513139,"threshold_uncertainty_score":0.022017956},"labels":[],"label_agreement":null},{"id":"W4241256580","doi":"10.1007/978-1-4614-6170-8_100880","title":"Knowledge Discovery","year":2014,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Computer science","score_opus":0.02476231035065318,"score_gpt":0.2531547928947007,"score_spread":0.22839248254404754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241256580","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019663302,0.013498273,0.29825568,0.006904812,0.0015486568,0.00039510807,0.0020356022,0.0022987612,0.6730968],"genre_scores_gemma":[0.031511504,0.027860874,0.2759037,0.0036562232,0.0015577368,0.0004483305,0.008367275,0.0006907279,0.6500037],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99904674,0.00013496669,0.000055740064,0.00023992248,0.00047212525,0.000050467625],"domain_scores_gemma":[0.99872714,0.0005549259,0.000040785886,0.0003555534,0.0002660794,0.00005547308],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012736535,0.000993501,0.000781518,0.0033858872,0.0009860087,0.0048849694,0.0025157866,0.0010596663,0.063829444],"category_scores_gemma":[0.0035757194,0.0005214608,0.0008969577,0.0030514826,0.001211622,0.0056813043,0.003136389,0.0016846043,0.046375178],"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":[0.000018979237,0.000045777335,0.00014769442,0.0005389706,0.0000301863,0.000092147035,0.00019470246,0.00072855776,0.0010940452,0.20491762,0.15134679,0.6408445],"study_design_scores_gemma":[0.000005308001,0.0000125177585,0.00015031105,0.00028972042,0.000017747228,0.00028823403,0.00011007852,0.0023807106,0.0017128491,0.18326296,0.811755,0.000014539727],"about_ca_topic_score_codex":0.0010203006,"about_ca_topic_score_gemma":0.0013231655,"teacher_disagreement_score":0.063829444,"about_ca_system_score_codex":0.0012262213,"about_ca_system_score_gemma":0.0020275183,"threshold_uncertainty_score":0.21353078},"labels":[],"label_agreement":null},{"id":"W4241351072","doi":"10.1007/978-1-4614-6170-8_100901","title":"Query Log Analysis","year":2014,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Computer science; Information retrieval","score_opus":0.017898343515588742,"score_gpt":0.2359222810300801,"score_spread":0.21802393751449134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241351072","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037560544,0.010482536,0.8310745,0.0041020536,0.00094625575,0.00040125303,0.003384286,0.014746101,0.13110702],"genre_scores_gemma":[0.09168887,0.018687028,0.5046829,0.002998189,0.001976845,0.00056861975,0.01611109,0.004866077,0.35842037],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981724,0.00017624945,0.000098462006,0.00034103106,0.001105821,0.00010606009],"domain_scores_gemma":[0.997982,0.00083667523,0.000069132795,0.00052025134,0.0005343208,0.00005766277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001278733,0.0015605192,0.0011068417,0.0040435237,0.0010181308,0.004174381,0.002228163,0.0008800287,0.039911725],"category_scores_gemma":[0.0056973654,0.0006963186,0.0011035432,0.00427401,0.0009141541,0.005431988,0.0019052767,0.0026726043,0.028163446],"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":[0.00006803392,0.000110760506,0.00058675307,0.0003916874,0.000032816075,0.000088417204,0.00012972699,0.002282764,0.002769668,0.0924758,0.20601977,0.69504386],"study_design_scores_gemma":[0.000020775922,0.00004976836,0.0013609749,0.00030088463,0.000073269184,0.0010855455,0.00018989253,0.07210974,0.012705181,0.27182513,0.6402146,0.000064220185],"about_ca_topic_score_codex":0.0025380189,"about_ca_topic_score_gemma":0.0031049012,"teacher_disagreement_score":0.039911725,"about_ca_system_score_codex":0.001622,"about_ca_system_score_gemma":0.0017880125,"threshold_uncertainty_score":0.13351798},"labels":[],"label_agreement":null},{"id":"W4242040267","doi":"10.1007/978-1-4614-6170-8_100622","title":"Data Transformation","year":2014,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Transformation (genetics); Computer science; Biology","score_opus":0.06256057924494558,"score_gpt":0.2716660858720808,"score_spread":0.20910550662713523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4242040267","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050518382,0.0012794695,0.7860307,0.0020067026,0.0015021592,0.0014496406,0.01463285,0.031906858,0.15613979],"genre_scores_gemma":[0.07707549,0.0037972531,0.62352896,0.0028142412,0.00048571173,0.0015878021,0.05387997,0.00797593,0.22885472],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981761,0.0001775952,0.00014385856,0.0005158801,0.000880361,0.00010624919],"domain_scores_gemma":[0.9983253,0.0002656428,0.000039852974,0.0008717023,0.00045889636,0.000038573155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012762668,0.0011322993,0.00076221616,0.002662428,0.00075224554,0.0030540745,0.0018981338,0.0005176777,0.061898768],"category_scores_gemma":[0.004393974,0.0004812181,0.0017267081,0.0034584845,0.0008038948,0.0029185573,0.0038114926,0.0018248169,0.046933413],"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":[0.00013690026,0.00011769194,0.0005486042,0.0005066361,0.000047588946,0.00016355701,0.0002059358,0.0019707135,0.009070311,0.086082734,0.14647126,0.7546781],"study_design_scores_gemma":[0.000028392866,0.000048333,0.0003943935,0.00011759741,0.000041837582,0.00044301938,0.00018467971,0.011659879,0.034147687,0.0772007,0.8757037,0.000029821174],"about_ca_topic_score_codex":0.0017190613,"about_ca_topic_score_gemma":0.0012067788,"teacher_disagreement_score":0.061898768,"about_ca_system_score_codex":0.0008251152,"about_ca_system_score_gemma":0.00174694,"threshold_uncertainty_score":0.20707202},"labels":[],"label_agreement":null},{"id":"W4242105255","doi":"10.4018/978-1-60566-010-3.ch130","title":"On Explanation-Oriented Data Mining","year":2009,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Data science; Computer science; Task (project management); Knowledge extraction; Scientific discovery; Context (archaeology); Association rule learning; Order (exchange); Data mining; Engineering; Geography; Psychology","score_opus":0.038757316781139084,"score_gpt":0.2799693308494849,"score_spread":0.2412120140683458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4242105255","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030496756,0.03905193,0.9021667,0.0071776477,0.00047271632,0.00026517716,0.00040196968,0.00052375376,0.04689027],"genre_scores_gemma":[0.062420808,0.03932439,0.8710419,0.0040904563,0.0011119792,0.00087041524,0.0014419093,0.00034286454,0.019355316],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961414,0.0018912031,0.00022073249,0.0004339336,0.0011806494,0.00013212141],"domain_scores_gemma":[0.99044096,0.0083243,0.00017901944,0.00052004977,0.00043748206,0.00009831108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0064182305,0.0015567637,0.0010720243,0.004262663,0.00083193,0.0044623283,0.0025323033,0.001789649,0.0059639513],"category_scores_gemma":[0.009362544,0.00069698814,0.0013015957,0.0070683453,0.00526225,0.008471278,0.0032299827,0.004031572,0.0022300135],"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":[0.000036592468,0.0000679939,0.00070413155,0.00086552196,0.000066248074,0.0002001198,0.0011372997,0.0061331633,0.00045597993,0.6409905,0.022608964,0.32673344],"study_design_scores_gemma":[0.000021088192,0.000032663622,0.00047667063,0.00057186844,0.000025886258,0.00034691364,0.00024433088,0.020579914,0.00064966275,0.8402721,0.13674408,0.000034813973],"about_ca_topic_score_codex":0.0014512168,"about_ca_topic_score_gemma":0.0013013281,"teacher_disagreement_score":0.0064182305,"about_ca_system_score_codex":0.0018236797,"about_ca_system_score_gemma":0.0012879181,"threshold_uncertainty_score":0.033943236},"labels":[],"label_agreement":null},{"id":"W4242110560","doi":"10.4018/978-1-60566-010-3.ch244","title":"Profit Mining","year":2009,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Profit (economics); Statistic; Computer science; Data mining; Obstacle; Operations research; Engineering; Economics; Microeconomics; Mathematics; Geography; Statistics","score_opus":0.023413701928680454,"score_gpt":0.2572384990318751,"score_spread":0.23382479710319468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4242110560","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027434317,0.016534735,0.68823963,0.010862424,0.0012624435,0.0013258973,0.010021622,0.002825309,0.24149354],"genre_scores_gemma":[0.503343,0.02148257,0.35699528,0.0020582562,0.001765516,0.0012977943,0.016751206,0.00083498424,0.09547135],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977563,0.000396354,0.00015142126,0.0005741115,0.00094417774,0.00017767836],"domain_scores_gemma":[0.9960277,0.0019460503,0.00035704393,0.0006435401,0.0008739188,0.00015182928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026691584,0.0014152768,0.001278883,0.0038024653,0.0012428854,0.004909301,0.0032140713,0.0013284803,0.02066092],"category_scores_gemma":[0.010924342,0.00046357585,0.0013835746,0.0067015905,0.0009612357,0.006502686,0.0024602085,0.0016532014,0.011835707],"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":[0.00015020392,0.00019509852,0.006001938,0.0009786403,0.00013640012,0.0004166427,0.00022676373,0.014639499,0.0008535039,0.19905533,0.07543515,0.7019109],"study_design_scores_gemma":[0.00005288801,0.00011534784,0.003970944,0.00056101946,0.00010122827,0.001244501,0.0006543506,0.14100404,0.0044644778,0.61709476,0.23065874,0.00007783752],"about_ca_topic_score_codex":0.0009663132,"about_ca_topic_score_gemma":0.0012246771,"teacher_disagreement_score":0.02066092,"about_ca_system_score_codex":0.0017322898,"about_ca_system_score_gemma":0.0017386847,"threshold_uncertainty_score":0.069117606},"labels":[],"label_agreement":null},{"id":"W4242142800","doi":"10.1007/978-1-4614-6170-8_100902","title":"Query Segmentation","year":2014,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Computer science; Artificial intelligence","score_opus":0.018886310080852446,"score_gpt":0.24007069611014448,"score_spread":0.22118438602929202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4242142800","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006577235,0.0057975324,0.7531653,0.0016653088,0.0008235853,0.0009168659,0.0045317267,0.018961536,0.20756106],"genre_scores_gemma":[0.08728182,0.007488469,0.59866154,0.0022113116,0.00069612864,0.00070226257,0.021328209,0.0061827735,0.27544752],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99896073,0.00009426928,0.00005560758,0.0003558449,0.0004214548,0.000112140835],"domain_scores_gemma":[0.99908257,0.00023137033,0.000031059473,0.00032027945,0.00027901112,0.000055631866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008365721,0.0014190746,0.0013501606,0.0018895179,0.0010792398,0.003299302,0.0025620672,0.0012227771,0.070201784],"category_scores_gemma":[0.0023501462,0.00074920006,0.001036185,0.0026107635,0.0008790939,0.004216919,0.0021934605,0.0017626338,0.046785016],"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":[0.00023177444,0.00011242049,0.0003041247,0.0007025366,0.00003798951,0.00014199685,0.0003111682,0.002855391,0.03247662,0.07929003,0.19260626,0.69092965],"study_design_scores_gemma":[0.000042361087,0.00010530986,0.00085829326,0.00024229923,0.00008622431,0.0009646848,0.0003129738,0.048880015,0.057640865,0.06626317,0.82452404,0.0000798251],"about_ca_topic_score_codex":0.0038923225,"about_ca_topic_score_gemma":0.0038172074,"teacher_disagreement_score":0.070201784,"about_ca_system_score_codex":0.0015218243,"about_ca_system_score_gemma":0.0016164936,"threshold_uncertainty_score":0.23484838},"labels":[],"label_agreement":null},{"id":"W4242580366","doi":"10.4018/978-1-59904-951-9.ch193","title":"Data Mining with Incomplete Data","year":2008,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint Mary's University","funders":"","keywords":"Missing data; Ambiguity; Survey data collection; Data mining; Computer science; Data science; Data set; Mathematics; Artificial intelligence; Statistics; Machine learning","score_opus":0.09424581898306579,"score_gpt":0.2878700833209476,"score_spread":0.19362426433788182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4242580366","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029729058,0.0064063556,0.981206,0.00236925,0.00031534015,0.00045281491,0.002714235,0.0007595534,0.0028034726],"genre_scores_gemma":[0.04201966,0.009334821,0.9366029,0.0011191322,0.0007587416,0.0010202299,0.0067993146,0.0001689756,0.0021762182],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96647793,0.01522285,0.0039689294,0.006113424,0.0076467963,0.0005700598],"domain_scores_gemma":[0.93176275,0.0453857,0.0038669282,0.014674097,0.0037746155,0.0005358539],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023760842,0.0021484739,0.0042177443,0.008743752,0.0021115036,0.008488526,0.0062885075,0.003022705,0.0039153593],"category_scores_gemma":[0.0773504,0.0017697219,0.0051041534,0.014238446,0.0029094396,0.013256362,0.008853299,0.0052436846,0.003284831],"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":[0.0002884596,0.00034314083,0.0101745855,0.008397047,0.0017711982,0.0015824969,0.0022345034,0.041507524,0.0019706564,0.17587401,0.043511823,0.7123445],"study_design_scores_gemma":[0.00008802392,0.00020584128,0.002338424,0.0024263759,0.00042863542,0.0022012559,0.0012636067,0.17565538,0.0048493166,0.65652007,0.15387273,0.00015045931],"about_ca_topic_score_codex":0.0011027677,"about_ca_topic_score_gemma":0.0012308124,"teacher_disagreement_score":0.023760842,"about_ca_system_score_codex":0.0014182337,"about_ca_system_score_gemma":0.0032604248,"threshold_uncertainty_score":0.12566084},"labels":[],"label_agreement":null},{"id":"W4243029034","doi":"10.4018/978-1-5225-3926-1.ch035","title":"Non-Traditional Data Mining Applications in Taiwan National Health Insurance (NHI) Databases","year":2017,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Decision support system; Relevance (law); Data science; Data warehouse; Payment; Computer science; Domain (mathematical analysis); Data mining; Knowledge management; Process (computing); Clinical decision support system; Database; World Wide Web","score_opus":0.10853690832734114,"score_gpt":0.3339944801265396,"score_spread":0.22545757179919845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243029034","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34028983,0.0411226,0.55445784,0.010125593,0.00040915894,0.0009854188,0.0063244356,0.0040418254,0.04224326],"genre_scores_gemma":[0.5187632,0.015884236,0.45046398,0.00087236916,0.00018912126,0.0004289218,0.0038033957,0.00021014514,0.0093846],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984925,0.0005633592,0.00019571318,0.0002445708,0.00044324205,0.00006065254],"domain_scores_gemma":[0.9949839,0.003911435,0.00021584758,0.0003915346,0.00040035867,0.00009697601],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030742455,0.0004454935,0.00047257615,0.002436509,0.0006078598,0.0026464728,0.0014596893,0.0007347164,0.0017329934],"category_scores_gemma":[0.007006038,0.00027829246,0.0005770051,0.006195306,0.00040452622,0.0023754134,0.0015791412,0.0009209956,0.00060438155],"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":[0.0002680246,0.0002732189,0.021169739,0.0018958515,0.000117534975,0.0027612376,0.0027756135,0.01552794,0.0072597866,0.045739252,0.027850667,0.8743611],"study_design_scores_gemma":[0.0001074925,0.00026154344,0.031381868,0.0015778535,0.00015266667,0.0041402257,0.0066267555,0.54702115,0.028101312,0.11752324,0.26297635,0.0001295102],"about_ca_topic_score_codex":0.0037773277,"about_ca_topic_score_gemma":0.0038176824,"teacher_disagreement_score":0.0037773277,"about_ca_system_score_codex":0.0012514652,"about_ca_system_score_gemma":0.00100195,"threshold_uncertainty_score":0.016258359},"labels":[],"label_agreement":null},{"id":"W4243491101","doi":"10.1007/978-1-4939-7131-2_100085","title":"Categorical Data Similarity","year":2018,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Categorical variable; Similarity (geometry); Computer science; Natural language processing; Artificial intelligence; Machine learning","score_opus":0.10510844522936101,"score_gpt":0.2989304517172668,"score_spread":0.19382200648790576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243491101","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0070741917,0.011908027,0.88621163,0.0023874715,0.0024141506,0.00033869216,0.0021387027,0.0028002688,0.08472697],"genre_scores_gemma":[0.14096762,0.012559042,0.7392769,0.0015446936,0.0023696064,0.0005473117,0.010410456,0.0008864488,0.09143788],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976235,0.0003006901,0.0002162341,0.00062585593,0.0011525889,0.000081109065],"domain_scores_gemma":[0.9979044,0.00048867223,0.00010592166,0.00066972896,0.00073611975,0.00009517048],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011069224,0.0006981149,0.00111935,0.0041814856,0.00084203196,0.00268975,0.0018030806,0.0008344551,0.015695337],"category_scores_gemma":[0.0071293497,0.00036441372,0.0010744905,0.0074315583,0.0009358837,0.004519269,0.0027054856,0.0016272826,0.008477668],"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":[0.000040011877,0.00005526823,0.00067788066,0.00042910784,0.00004774535,0.0000602975,0.00016237701,0.002026756,0.0023062048,0.14268605,0.05584911,0.7956593],"study_design_scores_gemma":[0.000012668616,0.00012452142,0.0018642772,0.00025236,0.0000644131,0.0014981738,0.00028832705,0.035249624,0.00818977,0.4932841,0.4591009,0.00007084989],"about_ca_topic_score_codex":0.00064786244,"about_ca_topic_score_gemma":0.000669147,"teacher_disagreement_score":0.015695337,"about_ca_system_score_codex":0.0010898858,"about_ca_system_score_gemma":0.0011308931,"threshold_uncertainty_score":0.05250615},"labels":[],"label_agreement":null},{"id":"W4244722394","doi":"10.1007/978-1-4939-7131-2_100667","title":"Mining Time-Evolving Graphs","year":2018,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Computer science","score_opus":0.01988826724898521,"score_gpt":0.2356126645159533,"score_spread":0.2157243972669681,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244722394","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036044203,0.008050996,0.92990077,0.0017931698,0.00063544203,0.00011491339,0.0027237274,0.0029107197,0.017826024],"genre_scores_gemma":[0.2779111,0.014817678,0.6507734,0.0007522171,0.0009116621,0.00017106703,0.01713465,0.0013171358,0.036211025],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99951375,0.000060172722,0.000028701614,0.00018971179,0.00017944568,0.000028230186],"domain_scores_gemma":[0.998585,0.00075425743,0.00011071007,0.00029049237,0.00019689486,0.0000626739],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005429405,0.00074236275,0.0006259084,0.0025062154,0.00041625416,0.0013963432,0.0016257679,0.00082632934,0.0032830923],"category_scores_gemma":[0.0051567066,0.00045105195,0.0009780313,0.0038704847,0.0004069818,0.0030000415,0.0011193377,0.0012946442,0.0019089037],"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":[0.00008234184,0.00007563819,0.0030501895,0.00058433536,0.0001737633,0.000448859,0.00026963855,0.05562298,0.0067902007,0.07266521,0.04228207,0.8179548],"study_design_scores_gemma":[0.000011153824,0.0000478524,0.0025845743,0.00016517118,0.000110635156,0.0013459072,0.00015880432,0.50402004,0.008532095,0.40265715,0.080326155,0.000040416762],"about_ca_topic_score_codex":0.001045228,"about_ca_topic_score_gemma":0.0018079834,"teacher_disagreement_score":0.0032830923,"about_ca_system_score_codex":0.0004988957,"about_ca_system_score_gemma":0.00035243796,"threshold_uncertainty_score":0.01098299},"labels":[],"label_agreement":null},{"id":"W4244736516","doi":"10.1007/978-0-387-39940-9_2182","title":"Classification Tree","year":2009,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Database 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":"University of Waterloo","funders":"","keywords":"Computer science","score_opus":0.02749243220400423,"score_gpt":0.2523173311490298,"score_spread":0.22482489894502558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244736516","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016308332,0.0053807623,0.7165041,0.0027968348,0.0018726764,0.0013547781,0.040888347,0.022668004,0.19222622],"genre_scores_gemma":[0.09743687,0.0038147203,0.6163612,0.001550224,0.0008928204,0.0010051135,0.101600915,0.0020162817,0.17532192],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99905616,0.00010385824,0.000057689504,0.00026288355,0.00043272,0.000086789885],"domain_scores_gemma":[0.9986129,0.00042250124,0.000069540154,0.0003264846,0.00050589733,0.00006267398],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000834374,0.00090269826,0.0009520675,0.002874974,0.00091809384,0.0022387924,0.0019452132,0.0011201735,0.05490608],"category_scores_gemma":[0.0034953838,0.00043524642,0.0011835442,0.003431477,0.00031523276,0.0022481412,0.0010899107,0.0015457813,0.055059418],"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":[0.00012901059,0.00014127781,0.0012358711,0.0003294797,0.00006622126,0.00010792292,0.000060886847,0.0056978604,0.0026036573,0.020571832,0.22808021,0.7409757],"study_design_scores_gemma":[0.0000839052,0.00020566022,0.0027068444,0.00041039006,0.00016820352,0.0011334011,0.00014801542,0.2131593,0.012804709,0.09902819,0.6700815,0.00006988887],"about_ca_topic_score_codex":0.0020666705,"about_ca_topic_score_gemma":0.004124791,"teacher_disagreement_score":0.05490608,"about_ca_system_score_codex":0.0006237024,"about_ca_system_score_gemma":0.0012644713,"threshold_uncertainty_score":0.18367916},"labels":[],"label_agreement":null},{"id":"W4245124041","doi":"10.1007/1-4020-2116-x_12","title":"Mining methods and method selection","year":2005,"lang":"en","type":"book-chapter","venue":"Kluwer Academic Publishers eBooks","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":"Golder Associates (Canada)","funders":"","keywords":"Selection (genetic algorithm); Computer science; Data mining; Artificial intelligence","score_opus":0.03485943803228135,"score_gpt":0.34212779763548185,"score_spread":0.3072683596032005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245124041","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014214533,0.03499598,0.90163845,0.004206068,0.0018356779,0.00030609148,0.001367122,0.0025787647,0.051650405],"genre_scores_gemma":[0.020682663,0.03458431,0.82695836,0.0015886442,0.0028235237,0.001338223,0.0049987505,0.0015934808,0.10543199],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951486,0.0016996041,0.00040188752,0.000671828,0.0019727228,0.000105316525],"domain_scores_gemma":[0.98931307,0.007285649,0.0002774025,0.0016213995,0.0013638586,0.0001386988],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0067795822,0.0016783327,0.0022349758,0.004834133,0.001045117,0.0049206307,0.0025676712,0.001962911,0.035415567],"category_scores_gemma":[0.01902632,0.0013113475,0.0013103874,0.0066601112,0.0015132409,0.0051027755,0.0025690896,0.002670301,0.033216715],"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":[0.000031955577,0.00004771781,0.0007878558,0.00093578844,0.000104477665,0.00011650558,0.00019639882,0.0016379139,0.0005023232,0.06965121,0.09519924,0.8307886],"study_design_scores_gemma":[0.000038544375,0.000070537055,0.0010434132,0.000962604,0.00011358744,0.0011675057,0.00021912914,0.026267903,0.0017504579,0.49142608,0.47688416,0.00005615505],"about_ca_topic_score_codex":0.00054906454,"about_ca_topic_score_gemma":0.0008403919,"teacher_disagreement_score":0.035415567,"about_ca_system_score_codex":0.0005015396,"about_ca_system_score_gemma":0.0015498549,"threshold_uncertainty_score":0.11847687},"labels":[],"label_agreement":null},{"id":"W4245234854","doi":"10.4018/978-1-7998-2460-2.ch044","title":"A Dynamic and Scalable Decision Tree Based Mining of Educational Data","year":2020,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Laurentian University","funders":"","keywords":"Data science; Computer science; Scalability; Big data; Field (mathematics); Data mining; Data stream mining; Process (computing); The Internet; Decision tree; Globe; World Wide Web; Database","score_opus":0.028563006927842284,"score_gpt":0.2801935931703431,"score_spread":0.2516305862425008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245234854","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06273422,0.0019113257,0.9220577,0.0015002002,0.00018292833,0.00033588492,0.0038333663,0.0027041435,0.0047402587],"genre_scores_gemma":[0.24214123,0.00095935253,0.74667275,0.00023907975,0.00011759307,0.00024743538,0.00601262,0.0000988972,0.0035109415],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99920017,0.00017452052,0.0000876452,0.00022150426,0.0002438781,0.00007230857],"domain_scores_gemma":[0.9986889,0.0008158362,0.000073951225,0.00012148541,0.00023360472,0.00006629381],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012790296,0.00052432314,0.0009553659,0.0014266132,0.00064480066,0.0013235436,0.0017748096,0.00079061906,0.0019221203],"category_scores_gemma":[0.003501513,0.0003798753,0.000939896,0.0030829299,0.00027271826,0.0017097244,0.001051096,0.0010849739,0.0008195193],"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":[0.00026992112,0.0004850261,0.005721802,0.0003565313,0.00016146296,0.0005216096,0.00023713449,0.23203027,0.005321186,0.009078763,0.01995385,0.7258625],"study_design_scores_gemma":[0.000016970982,0.00004434572,0.0007189206,0.000020568936,0.000017670269,0.0000762025,0.00005389614,0.98908746,0.0008615401,0.0063125794,0.0027822792,0.000007584676],"about_ca_topic_score_codex":0.0070572803,"about_ca_topic_score_gemma":0.009881993,"teacher_disagreement_score":0.0070572803,"about_ca_system_score_codex":0.00063763774,"about_ca_system_score_gemma":0.001367925,"threshold_uncertainty_score":0.0140324235},"labels":[],"label_agreement":null},{"id":"W4245510866","doi":"10.1017/cbo9781107298019.019","title":"Decision Trees","year":2014,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Forestry; Geography","score_opus":0.020354594496691712,"score_gpt":0.206099291387066,"score_spread":0.1857446968903743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245510866","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060971007,0.023816802,0.8019948,0.004066587,0.0016598431,0.0005161523,0.020281147,0.0068432596,0.13472441],"genre_scores_gemma":[0.102153555,0.022028944,0.69201106,0.0020932714,0.0016090949,0.00085248775,0.054972097,0.0020313996,0.122248076],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979703,0.0006376087,0.00016117215,0.00041982744,0.0006633845,0.00014769705],"domain_scores_gemma":[0.9965534,0.00220726,0.00010709313,0.0004411523,0.0005359454,0.00015522957],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002276635,0.0013060066,0.0013884837,0.0028952388,0.0007974451,0.0028226518,0.0022204607,0.0012351519,0.081384316],"category_scores_gemma":[0.008718511,0.00055668707,0.0016911308,0.004434706,0.00039831083,0.0032191852,0.0013706505,0.0020712584,0.047986716],"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":[0.00014161924,0.00014496589,0.00094574,0.0009147851,0.00018145863,0.0000941598,0.000060912986,0.02253264,0.00049520534,0.048441283,0.23067884,0.69536835],"study_design_scores_gemma":[0.000121323224,0.00017743981,0.001174208,0.0006846034,0.00018887155,0.0005842601,0.00014990666,0.20364124,0.0025192783,0.32307556,0.46760634,0.00007700698],"about_ca_topic_score_codex":0.0016576989,"about_ca_topic_score_gemma":0.0033930822,"teacher_disagreement_score":0.081384316,"about_ca_system_score_codex":0.0009356657,"about_ca_system_score_gemma":0.0013395936,"threshold_uncertainty_score":0.2722577},"labels":[],"label_agreement":null},{"id":"W4245911166","doi":"10.1007/978-1-4939-7131-2_100978","title":"Relationship Extraction","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Data Mining Algorithms and Applications","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","funders":"","keywords":"Extraction (chemistry); Chemistry; Chromatography","score_opus":0.05193771426233489,"score_gpt":0.2875365855305761,"score_spread":0.2355988712682412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245911166","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0057532103,0.0061407816,0.6474205,0.002582952,0.0014529228,0.0018023193,0.02701305,0.023256386,0.2845779],"genre_scores_gemma":[0.04037868,0.00888883,0.6329636,0.0015880401,0.0007205977,0.0008076783,0.06809702,0.0031382742,0.24341734],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99886984,0.000113495895,0.00010777864,0.00038016547,0.00046147726,0.00006718755],"domain_scores_gemma":[0.9985775,0.00038859318,0.00008191449,0.00051126734,0.00038323028,0.000057624482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011585922,0.0015697387,0.0010164154,0.006186965,0.001370099,0.0037223503,0.0022991823,0.0009079778,0.10743131],"category_scores_gemma":[0.0053572278,0.0007043036,0.0016276753,0.007110631,0.0004652113,0.006116279,0.0029322698,0.0015510324,0.10062749],"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":[0.00006530371,0.000083870415,0.0005307739,0.0006024876,0.00004276816,0.00016121857,0.000118627904,0.0004872825,0.005556411,0.034450386,0.15012908,0.80777186],"study_design_scores_gemma":[0.00002059338,0.000046527013,0.0011371324,0.0003615714,0.00010562202,0.0013059287,0.000181515,0.0076804287,0.018512005,0.045101553,0.9255051,0.000042084113],"about_ca_topic_score_codex":0.0011440628,"about_ca_topic_score_gemma":0.002005702,"teacher_disagreement_score":0.10743131,"about_ca_system_score_codex":0.00072718854,"about_ca_system_score_gemma":0.0014696255,"threshold_uncertainty_score":0.35939354},"labels":[],"label_agreement":null},{"id":"W4247495408","doi":"10.4018/978-1-4666-2455-9.ch024","title":"Using Association Rules for Query Reformulation","year":2012,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Université du Québec à Trois-Rivières","funders":"","keywords":"Association rule learning; Computer science; Focus (optics); Association (psychology); Information retrieval; Process (computing); Data mining; Volume (thermodynamics); Natural language processing; Psychology","score_opus":0.05025205466753676,"score_gpt":0.294768826921094,"score_spread":0.24451677225355725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247495408","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007143746,0.0031444717,0.9705531,0.0015706645,0.0002920426,0.00039356458,0.0005051985,0.0037265373,0.012670746],"genre_scores_gemma":[0.100611046,0.003083089,0.88159764,0.00087987265,0.00034739487,0.00037566767,0.002269399,0.0007271657,0.010108654],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99203753,0.0027839202,0.00073477696,0.001193798,0.0028789006,0.0003711092],"domain_scores_gemma":[0.99065876,0.0052795284,0.000496434,0.002202295,0.0012372568,0.00012565473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006116656,0.0012002194,0.001536981,0.0037258181,0.0010631755,0.004823453,0.0026969572,0.0012362435,0.012035475],"category_scores_gemma":[0.021432921,0.0007671542,0.0019965142,0.004048808,0.0015725483,0.009157937,0.002601189,0.0022974734,0.007267637],"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":[0.00033989467,0.00026006147,0.0014406816,0.0008362465,0.00023168548,0.00089161267,0.0011869007,0.014583578,0.009968409,0.20356677,0.029916937,0.7367773],"study_design_scores_gemma":[0.00016146444,0.0002474151,0.0009414168,0.00048538082,0.0004012345,0.002473539,0.00088733487,0.29541424,0.033736117,0.38146684,0.2835924,0.00019262367],"about_ca_topic_score_codex":0.0026109868,"about_ca_topic_score_gemma":0.002104946,"teacher_disagreement_score":0.012035475,"about_ca_system_score_codex":0.0011654656,"about_ca_system_score_gemma":0.0013112256,"threshold_uncertainty_score":0.0402627},"labels":[],"label_agreement":null},{"id":"W4247637609","doi":"10.1007/978-1-4939-7131-2_100936","title":"Query Log Analysis","year":2018,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Computer science","score_opus":0.023348954775176116,"score_gpt":0.25086688356173553,"score_spread":0.2275179287865594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247637609","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003689679,0.010554964,0.8281204,0.004806,0.0011540104,0.0004268858,0.0038234512,0.015840104,0.13158447],"genre_scores_gemma":[0.097993344,0.019217543,0.50706315,0.003555266,0.0025823496,0.00061924814,0.018431883,0.0055717635,0.34496546],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979607,0.00020085972,0.00011165185,0.00040443175,0.0012014689,0.00012089922],"domain_scores_gemma":[0.9975788,0.0009822742,0.00007973835,0.0006583409,0.0006290794,0.00007170318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014750473,0.0016339001,0.0011537179,0.0041801175,0.0010697983,0.0045891954,0.0023822088,0.00095735874,0.042966925],"category_scores_gemma":[0.0068010706,0.0007113791,0.0012047384,0.00443985,0.000969715,0.005964206,0.0020666146,0.0029960934,0.031271156],"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":[0.0000764187,0.00012855044,0.00061565376,0.00043366352,0.000037602316,0.00008921412,0.00013244677,0.0023658457,0.002782361,0.1066886,0.22802491,0.65862477],"study_design_scores_gemma":[0.000021770644,0.000050390445,0.0013110242,0.00029009898,0.000076765944,0.00096905895,0.00017817697,0.070658945,0.012134186,0.28876638,0.6254804,0.00006269793],"about_ca_topic_score_codex":0.0024489393,"about_ca_topic_score_gemma":0.002796118,"teacher_disagreement_score":0.042966925,"about_ca_system_score_codex":0.0017520789,"about_ca_system_score_gemma":0.0018990816,"threshold_uncertainty_score":0.14373869},"labels":[],"label_agreement":null},{"id":"W4247722666","doi":"10.1145/1083142.1083160","title":"A framework for describing and understanding mining tools in software development","year":2005,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Software engineering; Software development; Software; Data science; Programming language","score_opus":0.21010337396463652,"score_gpt":0.31669863392929926,"score_spread":0.10659525996466274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247722666","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00043139304,0.0011315605,0.9946067,0.0011773879,0.00006257793,0.00031579813,0.00017062452,0.00038741226,0.001716616],"genre_scores_gemma":[0.006286789,0.0009976783,0.99066,0.00027335156,0.000070789676,0.0008627946,0.00032951715,0.000076399825,0.0004425824],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97422916,0.0120077375,0.0054723616,0.0025416561,0.0047316,0.0010174786],"domain_scores_gemma":[0.9747038,0.016266555,0.0019829348,0.0032019736,0.0030139415,0.0008307038],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.032020874,0.0034951349,0.0029182283,0.01615641,0.005107893,0.017755982,0.01163788,0.008976724,0.0034127124],"category_scores_gemma":[0.035763253,0.002487973,0.005881442,0.018900521,0.012005077,0.023683047,0.007538845,0.007776712,0.002090576],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002510684,0.00010366576,0.00073125504,0.0009394535,0.00008836326,0.0004974699,0.003142395,0.012009951,0.0007695639,0.9137731,0.005125553,0.06279403],"study_design_scores_gemma":[0.000041236097,0.00009768857,0.00045447756,0.0011850782,0.000085633976,0.00076544547,0.0012419401,0.037693996,0.0010097913,0.8021097,0.15517877,0.00013624605],"about_ca_topic_score_codex":0.013516435,"about_ca_topic_score_gemma":0.0077439095,"teacher_disagreement_score":0.96797913,"about_ca_system_score_codex":0.0055847107,"about_ca_system_score_gemma":0.008740751,"threshold_uncertainty_score":0.1693446},"labels":[],"label_agreement":null},{"id":"W4248144779","doi":"10.22215/etd/2009-09274","title":"Creating better binary classification trees using non-greedy methods","year":2009,"lang":"en","type":"dissertation","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Carleton University; Canadian Heritage; Library and Archives Canada","funders":"","keywords":"Humanities; Auteur theory; Art; Political science; Art history","score_opus":0.055015894614547305,"score_gpt":0.38531179586278436,"score_spread":0.33029590124823704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248144779","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033782847,0.0007986926,0.95260614,0.0007505442,0.0004210617,0.0004957209,0.00062381086,0.004822904,0.005698304],"genre_scores_gemma":[0.10843743,0.0002455607,0.88309765,0.0005918021,0.00015991242,0.00044752285,0.0021110624,0.0006510578,0.004257949],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99702305,0.00084237923,0.00022907973,0.0007239187,0.00084058894,0.00034107204],"domain_scores_gemma":[0.9912709,0.0054673203,0.00040085748,0.0010945805,0.0014736117,0.0002928834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037306887,0.0014160575,0.0020569016,0.003823877,0.0014284451,0.0023960639,0.0028165302,0.0028758694,0.011237745],"category_scores_gemma":[0.014498366,0.0010822177,0.0023778896,0.003580883,0.00065092166,0.0038491678,0.0019664152,0.0025206641,0.0049768025],"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":[0.0004989142,0.00060489937,0.0028271375,0.00037037354,0.00015533004,0.00017600798,0.00027078597,0.101684496,0.005585257,0.017034518,0.030461406,0.8403309],"study_design_scores_gemma":[0.0001510933,0.000112851325,0.0005714733,0.00007275565,0.00006017641,0.00013915956,0.00013025726,0.9580292,0.002057782,0.032121897,0.0065290923,0.000024274566],"about_ca_topic_score_codex":0.0038974911,"about_ca_topic_score_gemma":0.009694508,"teacher_disagreement_score":0.011237745,"about_ca_system_score_codex":0.0013805749,"about_ca_system_score_gemma":0.00226192,"threshold_uncertainty_score":0.03759396},"labels":[],"label_agreement":null},{"id":"W4248335533","doi":"10.1145/502787.502792","title":"Scalable frequent-pattern mining methods","year":2001,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"","keywords":"Computer science; Scalability; Data mining; Database","score_opus":0.04287314662092364,"score_gpt":0.34179891128099127,"score_spread":0.29892576466006765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248335533","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010503729,0.005599785,0.9530264,0.0017295547,0.00074498006,0.000631579,0.005462786,0.011414262,0.010886851],"genre_scores_gemma":[0.11843015,0.0031118258,0.8528494,0.0003374024,0.0008410324,0.0008433872,0.014964067,0.00083429634,0.0077884584],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979532,0.0005704686,0.00016517797,0.00041083148,0.0007637453,0.00013667603],"domain_scores_gemma":[0.99301165,0.0031184515,0.00035566738,0.002083763,0.001166995,0.00026349814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025965627,0.0013460392,0.0020597961,0.0024315466,0.0008472202,0.0017415523,0.0029411428,0.0008340489,0.02723686],"category_scores_gemma":[0.0134576615,0.0006345,0.001003642,0.005021217,0.00037438012,0.0038884603,0.0019752814,0.0011749117,0.013319501],"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":[0.00043246135,0.00021919356,0.0019315182,0.0009889194,0.00028837577,0.00019439559,0.000053498417,0.023432413,0.004744982,0.009860443,0.073738776,0.8841151],"study_design_scores_gemma":[0.0006869712,0.00032308363,0.00258929,0.0003346846,0.00040864272,0.0010140324,0.00018374863,0.7530509,0.01236954,0.15106073,0.077893555,0.000084834595],"about_ca_topic_score_codex":0.0014010533,"about_ca_topic_score_gemma":0.0029741204,"teacher_disagreement_score":0.02723686,"about_ca_system_score_codex":0.00047884675,"about_ca_system_score_gemma":0.001638775,"threshold_uncertainty_score":0.09111631},"labels":[],"label_agreement":null},{"id":"W4248599979","doi":"10.32920/ryerson.14668077.v1","title":"A mapreduce relational-database index-selection tool","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Selection (genetic algorithm); Index (typography); Index selection; Task (project management); Set (abstract data type); Process (computing); Data mining; Relational database; Big data; Database; Systems engineering; Engineering; Artificial intelligence","score_opus":0.029813393387733922,"score_gpt":0.27023554433060676,"score_spread":0.24042215094287284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248599979","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02185691,0.00047725526,0.7260368,0.00058532,0.00023491372,0.00065205165,0.005188164,0.2347328,0.010235746],"genre_scores_gemma":[0.12913354,0.0003008165,0.8446684,0.0003587995,0.00007124789,0.00038117246,0.011737933,0.00503223,0.008315816],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998911,0.00011898934,0.000090982576,0.00022935598,0.0005624632,0.000087269415],"domain_scores_gemma":[0.9990615,0.00023071193,0.000053347383,0.00028955232,0.000270823,0.00009401455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012039939,0.00091857114,0.00068352517,0.0013819574,0.0009363943,0.0014551412,0.0027435776,0.0005865054,0.005172526],"category_scores_gemma":[0.00312354,0.00069918286,0.0007271944,0.001598671,0.00031748944,0.0016027977,0.0012556261,0.0010453685,0.0037219508],"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":[0.0006419026,0.00074882305,0.004605872,0.00057257817,0.00023896634,0.0006720478,0.00035005974,0.03554428,0.04724123,0.013975169,0.2324423,0.6629668],"study_design_scores_gemma":[0.00024528106,0.0002705732,0.0029083658,0.00005825975,0.000062895,0.0007109515,0.00021903346,0.79406875,0.06502888,0.020930545,0.115349494,0.0001469631],"about_ca_topic_score_codex":0.0038177986,"about_ca_topic_score_gemma":0.0045678066,"teacher_disagreement_score":0.005172526,"about_ca_system_score_codex":0.00057717256,"about_ca_system_score_gemma":0.0015415715,"threshold_uncertainty_score":0.017303824},"labels":[],"label_agreement":null},{"id":"W4248822770","doi":"10.1109/ideas.2004.1319823","title":"Incremental mining of Web sequential patterns using PLWAP tree on tolerance MinSupport","year":2004,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Tree (set theory); Data mining; Database; Fractal tree index; Tree structure; Data structure; Incremental decision tree; Decision tree; Decision tree learning; Programming language; Mathematics","score_opus":0.03985169507216933,"score_gpt":0.28707303580120763,"score_spread":0.24722134072903829,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248822770","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1262429,0.0006630653,0.86467046,0.00037259632,0.00006691295,0.0004850992,0.0014506585,0.0045419065,0.0015063911],"genre_scores_gemma":[0.26898834,0.00023227003,0.72610986,0.00013165815,0.000052891188,0.00033538011,0.0029790348,0.0001628952,0.0010076464],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846375,0.00022339614,0.0001765068,0.0002997767,0.0007018713,0.0001347005],"domain_scores_gemma":[0.99625045,0.0017220762,0.00045433317,0.0006286913,0.00077003526,0.00017430545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011085718,0.00056373334,0.0010296421,0.0034425296,0.00072004163,0.001202209,0.002042548,0.0006825299,0.0010559452],"category_scores_gemma":[0.008929199,0.0005983259,0.0008697879,0.00349147,0.00041020045,0.0031714705,0.0013553126,0.00087395206,0.00062279624],"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":[0.0005812193,0.00027142506,0.01991726,0.00037416097,0.00016089533,0.00079843425,0.0005084708,0.062131744,0.016803412,0.006181949,0.006736504,0.88553447],"study_design_scores_gemma":[0.00007007049,0.00024466615,0.0035063557,0.00005554308,0.00008711404,0.0010376067,0.0002461683,0.9528925,0.01448294,0.018619632,0.008717163,0.000040166175],"about_ca_topic_score_codex":0.0031012988,"about_ca_topic_score_gemma":0.0048345756,"teacher_disagreement_score":0.0034425296,"about_ca_system_score_codex":0.00038601077,"about_ca_system_score_gemma":0.001201865,"threshold_uncertainty_score":0.006166458},"labels":[],"label_agreement":null},{"id":"W4249787917","doi":"10.1007/978-1-84996-044-1_6","title":"Efficient Clustering of Databases Induced by Local Patterns","year":2010,"lang":"en","type":"book-chapter","venue":"Advanced information and knowledge processing","topic":"Data Mining Algorithms 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 Alberta","funders":"","keywords":"Cluster analysis; Data mining; Computer science; Coding (social sciences); Similarity measure; Data stream clustering; Similarity (geometry); CURE data clustering algorithm; Database; Correlation clustering; Fuzzy clustering; Artificial intelligence; Mathematics; Statistics","score_opus":0.017433731183945998,"score_gpt":0.26926903242367006,"score_spread":0.2518353012397241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4249787917","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033760656,0.000592137,0.9616225,0.0001615774,0.00004310697,0.00015331665,0.0007012296,0.0013612671,0.0016042484],"genre_scores_gemma":[0.24907307,0.000727523,0.7400106,0.000098803415,0.000072507406,0.00026080557,0.005517838,0.00030314396,0.0039356817],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866736,0.0002510352,0.00011118838,0.00040563082,0.00044757585,0.00011712103],"domain_scores_gemma":[0.9975439,0.00072735467,0.00020278209,0.0009245791,0.00050281896,0.000098607605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073666434,0.00060661376,0.001498919,0.0024560331,0.0008660871,0.0019812577,0.002432972,0.0007208992,0.0017192103],"category_scores_gemma":[0.0048693116,0.0006029673,0.0010599646,0.0054402966,0.00054919807,0.0021127085,0.002291084,0.0008832117,0.0013005078],"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":[0.00052008574,0.00021665709,0.003676605,0.00062761176,0.00024149688,0.0002277971,0.000431832,0.09315597,0.02869832,0.022720436,0.014084709,0.8353985],"study_design_scores_gemma":[0.0000630839,0.00016241809,0.0027171795,0.000059619077,0.00012383852,0.00059932814,0.00037850268,0.8916405,0.019131161,0.07549377,0.009598909,0.000031672334],"about_ca_topic_score_codex":0.001943825,"about_ca_topic_score_gemma":0.0038389335,"teacher_disagreement_score":0.0024560331,"about_ca_system_score_codex":0.0007155201,"about_ca_system_score_gemma":0.001008233,"threshold_uncertainty_score":0.005751312},"labels":[],"label_agreement":null},{"id":"W4249791978","doi":"10.1007/978-1-4939-7131-2_100573","title":"Knowledge Discovery in Networks","year":2018,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Computer science; Computational biology; Biology","score_opus":0.024527327663853554,"score_gpt":0.25831069974483045,"score_spread":0.2337833720809769,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4249791978","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003963475,0.10557023,0.60042244,0.01504189,0.0031730053,0.0001579046,0.0010545823,0.0011785273,0.26943788],"genre_scores_gemma":[0.11394153,0.13658889,0.4444533,0.0043256385,0.0058381283,0.00047382351,0.0036990908,0.00058648444,0.29009306],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991629,0.00021988552,0.000045394765,0.00018749386,0.00034550545,0.000038765862],"domain_scores_gemma":[0.9983088,0.0011537453,0.000059115344,0.00026737558,0.00016667738,0.00004424373],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001174321,0.0008425713,0.00077630224,0.002174065,0.00069632125,0.0038637086,0.0013246547,0.001169004,0.013134726],"category_scores_gemma":[0.0047852444,0.0005233258,0.0006361933,0.003013641,0.0019511628,0.007138158,0.001936972,0.0022718303,0.0062451586],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001710155,0.00003260996,0.00022306871,0.00075746246,0.0000515648,0.00008512395,0.00024106314,0.004833555,0.00058859796,0.59422547,0.07750781,0.3214365],"study_design_scores_gemma":[0.0000041693474,0.000007985067,0.00013530315,0.00028179382,0.000014531303,0.00014584138,0.00006554099,0.009281083,0.0006147528,0.74225485,0.24718408,0.000010068045],"about_ca_topic_score_codex":0.0008568341,"about_ca_topic_score_gemma":0.0008968312,"teacher_disagreement_score":0.013134726,"about_ca_system_score_codex":0.0012963925,"about_ca_system_score_gemma":0.0009900663,"threshold_uncertainty_score":0.043940008},"labels":[],"label_agreement":null},{"id":"W4249961969","doi":"10.1007/978-0-387-39940-9_9003","title":"Extensional Relational Database (ERDB)","year":2009,"lang":"de","type":"book-chapter","venue":"Encyclopedia of Database 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":"University of Waterloo","funders":"","keywords":"Extensional definition; Database; Computer science; Relational database; Geology; Seismology","score_opus":0.03146972623227962,"score_gpt":0.2550147803787909,"score_spread":0.22354505414651127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4249961969","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007445776,0.02381518,0.7646564,0.0021088407,0.0015176039,0.0005026241,0.01699647,0.049410596,0.13354644],"genre_scores_gemma":[0.070629455,0.029806595,0.7171073,0.0026099402,0.0016219247,0.00038704087,0.05631271,0.006222266,0.115302816],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99764144,0.00025948038,0.0003286032,0.0004767473,0.0011629293,0.00013082106],"domain_scores_gemma":[0.9979685,0.00042498132,0.0001628594,0.0008473,0.00045512427,0.00014122023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020611756,0.0008469163,0.0010899906,0.0028477951,0.0006297196,0.004947542,0.002815981,0.0010035072,0.026015254],"category_scores_gemma":[0.0049310243,0.00068356976,0.000814872,0.0059503415,0.00063767086,0.007245203,0.0026741936,0.0019499933,0.021788863],"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":[0.00017761525,0.0001380732,0.0007337874,0.0010742266,0.000049292117,0.00031879562,0.00018947353,0.001551405,0.0072024283,0.123969376,0.19709024,0.6675053],"study_design_scores_gemma":[0.000034747663,0.00005042302,0.00046814108,0.00021330961,0.000056732468,0.0016467867,0.00006363304,0.0037445575,0.005710849,0.04424226,0.9437202,0.000048337588],"about_ca_topic_score_codex":0.0009496169,"about_ca_topic_score_gemma":0.0007708975,"teacher_disagreement_score":0.026015254,"about_ca_system_score_codex":0.00054933334,"about_ca_system_score_gemma":0.001580556,"threshold_uncertainty_score":0.087029696},"labels":[],"label_agreement":null},{"id":"W4250125957","doi":"10.4018/978-1-4666-0023-2.ch004","title":"A Pattern Language for Knowledge Discovery in a Semantic Web Context","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Rimouski","funders":"","keywords":"Computer science; Ontology; Interpretability; Semantic Web; Domain (mathematical analysis); Information retrieval; Knowledge extraction; Data science; Domain knowledge; Context (archaeology); Data mining; Knowledge management; Artificial intelligence","score_opus":0.02728378952972721,"score_gpt":0.26601705670809167,"score_spread":0.23873326717836446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250125957","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00069471647,0.0011096605,0.985508,0.0015928241,0.00029230615,0.00037333203,0.0014963582,0.002062361,0.00687043],"genre_scores_gemma":[0.010330625,0.0014816145,0.9778522,0.00084351405,0.00016128468,0.0010820831,0.0026038752,0.00036430112,0.005280432],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959571,0.0012201283,0.0009844883,0.00059067726,0.0010756237,0.00017197075],"domain_scores_gemma":[0.996747,0.0017453649,0.00032058163,0.00066126464,0.00037731734,0.00014846868],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042526377,0.001648228,0.0018837397,0.0050701154,0.0018625772,0.007000059,0.00406349,0.0031022707,0.010650733],"category_scores_gemma":[0.007569482,0.0013479096,0.0034296808,0.011279408,0.003492628,0.013879538,0.0041501303,0.00486364,0.007979988],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006337821,0.00007093705,0.00030038427,0.0008256618,0.000080553335,0.00070796954,0.0008405006,0.0023128085,0.0013323239,0.8150336,0.03065156,0.14778027],"study_design_scores_gemma":[0.000049630173,0.00004346551,0.00016867959,0.00039167693,0.000038927243,0.0011808093,0.00034351088,0.027142495,0.001434747,0.6815338,0.2876289,0.000043393316],"about_ca_topic_score_codex":0.002964704,"about_ca_topic_score_gemma":0.0035455294,"teacher_disagreement_score":0.010650733,"about_ca_system_score_codex":0.0014496773,"about_ca_system_score_gemma":0.0029400985,"threshold_uncertainty_score":0.035630226},"labels":[],"label_agreement":null},{"id":"W4250301904","doi":"10.4171/owr/2009/03","title":"Random Trees","year":2009,"lang":"en","type":"article","venue":"Oberwolfach Reports","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Mathematics; Combinatorics","score_opus":0.012068730307501226,"score_gpt":0.2467607618148545,"score_spread":0.2346920315073533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250301904","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014660363,0.05010335,0.6744935,0.027570779,0.01085903,0.00024871968,0.0024727192,0.0013192463,0.21827225],"genre_scores_gemma":[0.3536613,0.05848848,0.2692404,0.010633551,0.015462373,0.00088837364,0.007507608,0.0017204738,0.28239745],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99835,0.0005024417,0.00010377295,0.00041504076,0.0004685477,0.00016016056],"domain_scores_gemma":[0.99546826,0.0026990776,0.00018143756,0.00045564896,0.0008417774,0.0003538434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018544171,0.0006928457,0.0013035634,0.0018522957,0.0014386853,0.003292247,0.0011613054,0.0017683189,0.025471052],"category_scores_gemma":[0.01217681,0.0005645076,0.0012491364,0.0020762624,0.0019064277,0.005325884,0.0018848017,0.0035225046,0.009890519],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039920775,0.00001656158,0.00024888956,0.00013531427,0.000029941339,0.00007016137,0.00010681418,0.0044292193,0.00031598145,0.8867927,0.048885614,0.058928683],"study_design_scores_gemma":[0.000020843963,0.000026241705,0.00017952613,0.00009983228,0.000014241757,0.00015191556,0.000039098686,0.009300349,0.0003107838,0.78595024,0.2038832,0.000023788576],"about_ca_topic_score_codex":0.0010261314,"about_ca_topic_score_gemma":0.0012954627,"teacher_disagreement_score":0.025471052,"about_ca_system_score_codex":0.0015937823,"about_ca_system_score_gemma":0.00089478696,"threshold_uncertainty_score":0.08520919},"labels":[],"label_agreement":null},{"id":"W4250540416","doi":"10.1007/978-0-387-39940-9_2255","title":"Conceptual Data Model","year":2009,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Database 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":"University of Waterloo","funders":"","keywords":"Computer science; Conceptual model; Database","score_opus":0.05669677449890225,"score_gpt":0.2737170606541583,"score_spread":0.21702028615525604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250540416","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001709788,0.0012916302,0.9417127,0.0033221846,0.00047785355,0.00048665187,0.0068786633,0.0030733757,0.04104716],"genre_scores_gemma":[0.053765286,0.0034877423,0.84935296,0.0022963437,0.00033002705,0.0011761804,0.027688986,0.0009246931,0.060977824],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99669755,0.0005721562,0.00043378456,0.0008857749,0.0012427738,0.00016790269],"domain_scores_gemma":[0.9971813,0.00068345614,0.00011745116,0.0010751679,0.0007984409,0.00014413876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002853785,0.0011924885,0.00091751583,0.0032485996,0.0011565231,0.008632055,0.0038813336,0.0018502453,0.024317231],"category_scores_gemma":[0.00874712,0.00073890726,0.002063902,0.0045240982,0.0015497118,0.011290048,0.0037201496,0.0030452355,0.014889967],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038830098,0.000058200945,0.00037643156,0.0002753016,0.000033754033,0.00014344021,0.0002840398,0.0030045435,0.00084473286,0.86040056,0.039920747,0.09461955],"study_design_scores_gemma":[0.000025612539,0.00003063029,0.00015608677,0.00020879251,0.00004720603,0.00043854196,0.00018045907,0.023091929,0.0016032733,0.40488866,0.569293,0.00003576699],"about_ca_topic_score_codex":0.004822393,"about_ca_topic_score_gemma":0.004515334,"teacher_disagreement_score":0.024317231,"about_ca_system_score_codex":0.0020710968,"about_ca_system_score_gemma":0.0035958448,"threshold_uncertainty_score":0.08134925},"labels":[],"label_agreement":null},{"id":"W4250676226","doi":"10.1007/978-1-4614-6170-8_110082","title":"Web Mining","year":2014,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Computer science; World Wide Web","score_opus":0.022785065606172706,"score_gpt":0.23554444486367637,"score_spread":0.21275937925750366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250676226","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028589163,0.018527292,0.35106498,0.0048470516,0.0026220332,0.0004440963,0.0036518942,0.010783984,0.60519975],"genre_scores_gemma":[0.014596762,0.019509653,0.18898337,0.0022468595,0.0015367967,0.00025371116,0.00908245,0.0020417348,0.7617487],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992976,0.000055701978,0.00003679282,0.00016348723,0.00041591714,0.00003051099],"domain_scores_gemma":[0.99910337,0.0002747328,0.000036097088,0.00026421805,0.00027040177,0.000051193558],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007038792,0.0012556638,0.000785432,0.0040965606,0.0008327402,0.0034836612,0.0016490434,0.0009646846,0.06801144],"category_scores_gemma":[0.0025120538,0.0006697394,0.00081039657,0.004963999,0.0005032694,0.004777539,0.0017928418,0.0016712332,0.08108222],"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":[0.000011717803,0.000048933955,0.00020497687,0.00030903702,0.000016973976,0.000052404434,0.000065038184,0.0004268552,0.0014000814,0.024740156,0.24213004,0.7305938],"study_design_scores_gemma":[0.0000046553178,0.000011673215,0.00043647064,0.00020347608,0.000015127382,0.0005200088,0.000052088704,0.0033612305,0.002914805,0.047938477,0.9445262,0.000015772544],"about_ca_topic_score_codex":0.0006634415,"about_ca_topic_score_gemma":0.0014314464,"teacher_disagreement_score":0.06801144,"about_ca_system_score_codex":0.0005691615,"about_ca_system_score_gemma":0.0008550236,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W4250701221","doi":"10.1007/978-0-387-39940-9_3532","title":"Scientific Query Languages","year":2009,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Database 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":"University of Waterloo","funders":"","keywords":"Computer science; Programming language; Information retrieval","score_opus":0.01567817065387547,"score_gpt":0.2515235354195402,"score_spread":0.23584536476566473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250701221","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015201307,0.009205211,0.7274083,0.004208918,0.0012446403,0.00039855504,0.009094879,0.027544022,0.21937536],"genre_scores_gemma":[0.032315046,0.020411868,0.5468803,0.004649065,0.00189188,0.0011014531,0.04317027,0.013940825,0.33563927],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99809605,0.00028089364,0.0002442616,0.00032301748,0.0009505028,0.00010524695],"domain_scores_gemma":[0.998408,0.0006347117,0.0000704409,0.00043385322,0.00038025744,0.00007272956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019419361,0.0013743272,0.0013724446,0.0030983326,0.0010137984,0.005856356,0.0025891254,0.001145161,0.07582835],"category_scores_gemma":[0.004364315,0.0013120933,0.0015236377,0.0061084917,0.0014097402,0.009032111,0.0025960773,0.0035784438,0.06760955],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005984294,0.000049541097,0.00013844107,0.00071450503,0.000027896433,0.00007906307,0.0003065674,0.0010384299,0.0033201196,0.39855334,0.31633952,0.27937278],"study_design_scores_gemma":[0.00001969466,0.000014296832,0.00008046007,0.00013168239,0.000013377643,0.00027201956,0.000046160112,0.003229208,0.0022053157,0.16119441,0.83276945,0.000023957602],"about_ca_topic_score_codex":0.0011808983,"about_ca_topic_score_gemma":0.0013434906,"teacher_disagreement_score":0.07582835,"about_ca_system_score_codex":0.0012861786,"about_ca_system_score_gemma":0.0017924042,"threshold_uncertainty_score":0.2536711},"labels":[],"label_agreement":null},{"id":"W4251092169","doi":"10.4018/978-1-5225-7598-6.ch002","title":"Big Data Analysis and Mining","year":2018,"lang":"en","type":"book-chapter","venue":"Advances in computer and electrical engineering book series","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Big data; Computer science; Data science; Variety (cybernetics); Process (computing); Data mining; Knowledge extraction; Artificial intelligence","score_opus":0.015591197712073328,"score_gpt":0.23258967089347082,"score_spread":0.2169984731813975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251092169","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023277877,0.18954511,0.40479913,0.035173796,0.010989878,0.0011613376,0.007883893,0.006179646,0.34193942],"genre_scores_gemma":[0.037830334,0.29728183,0.43692347,0.01715222,0.013196194,0.0015671252,0.0152173,0.00252371,0.17830785],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99648833,0.0005633254,0.00023647516,0.0005129521,0.002076809,0.00012213827],"domain_scores_gemma":[0.9965139,0.0017875864,0.00014632808,0.00071217865,0.00067040307,0.00016964595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003111989,0.0016690913,0.0012540253,0.0042077806,0.0011595334,0.008038516,0.002529163,0.0021219654,0.022291755],"category_scores_gemma":[0.008049185,0.00082114054,0.001193601,0.0065959054,0.0020033056,0.008780097,0.004088497,0.003270499,0.018939164],"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":[0.000028922384,0.000037217877,0.00050657627,0.0019650413,0.00010812635,0.00015245787,0.00040424502,0.0027167138,0.0007676521,0.27116624,0.35258076,0.36956614],"study_design_scores_gemma":[0.000005614242,0.00001426944,0.0002993651,0.00060940045,0.000012574567,0.00023958736,0.00011512522,0.0023106192,0.0004407218,0.17697042,0.81896156,0.000020741174],"about_ca_topic_score_codex":0.0008932438,"about_ca_topic_score_gemma":0.00097346905,"teacher_disagreement_score":0.022291755,"about_ca_system_score_codex":0.0015222026,"about_ca_system_score_gemma":0.002671467,"threshold_uncertainty_score":0.07457334},"labels":[],"label_agreement":null},{"id":"W4251359375","doi":"10.1007/978-1-4939-7131-2_100239","title":"Data Mining","year":2018,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Computer science","score_opus":0.09989567733911701,"score_gpt":0.29690858559122413,"score_spread":0.1970129082521071,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251359375","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018375104,0.021385334,0.43824247,0.008992509,0.0033960796,0.000607626,0.005794975,0.007103809,0.51263976],"genre_scores_gemma":[0.014852878,0.030577973,0.26625437,0.0061112526,0.0029167386,0.00058114005,0.014181005,0.0016048789,0.66291964],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990895,0.00008275351,0.000064624575,0.0002473567,0.00048138425,0.00003436755],"domain_scores_gemma":[0.9988594,0.00038885453,0.00004517238,0.00032843414,0.000320214,0.000057977046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012240304,0.0013400197,0.00088569557,0.0029109407,0.00075361744,0.0033980815,0.0022455438,0.00095736556,0.07667592],"category_scores_gemma":[0.0034790537,0.0006294007,0.00090720906,0.0035954863,0.00065136567,0.0044671795,0.0024359191,0.0020082635,0.09296432],"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":[0.000017259621,0.00004371678,0.0001912162,0.00059449236,0.000024186926,0.000059370563,0.000092237475,0.00055794127,0.0016858019,0.05397144,0.2888589,0.65390337],"study_design_scores_gemma":[0.0000041869957,0.0000123977115,0.00022456217,0.00018856439,0.0000104453775,0.0002981461,0.00003861347,0.0018281832,0.001729893,0.049924083,0.9457286,0.000012205153],"about_ca_topic_score_codex":0.00045658607,"about_ca_topic_score_gemma":0.0006894151,"teacher_disagreement_score":0.07667592,"about_ca_system_score_codex":0.0007682084,"about_ca_system_score_gemma":0.0011186097,"threshold_uncertainty_score":0.2565065},"labels":[],"label_agreement":null},{"id":"W4251416583","doi":"10.1007/978-1-4939-7131-2_101289","title":"Subgraph Mining","year":2018,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Computer science","score_opus":0.026260537644199472,"score_gpt":0.2410276412896204,"score_spread":0.21476710364542093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251416583","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006586122,0.009847098,0.70687795,0.002723077,0.001420902,0.0005459477,0.009354701,0.014417728,0.24822655],"genre_scores_gemma":[0.054150652,0.01536327,0.64433,0.0013607494,0.0010891582,0.00040953973,0.043585386,0.0035737762,0.23613742],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99953103,0.0000492117,0.000020957597,0.00016495012,0.0002030615,0.000030793926],"domain_scores_gemma":[0.9993795,0.00015722052,0.000027602551,0.00023802365,0.00015771233,0.000039839397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041437199,0.0012091697,0.00078425364,0.003041254,0.0007659091,0.0018144767,0.0018685075,0.00073844264,0.045523826],"category_scores_gemma":[0.0018865786,0.0005476019,0.0011306395,0.0043484494,0.00044509326,0.0028908274,0.0015622154,0.0012897275,0.033647064],"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":[0.0000327828,0.00006045254,0.0004292944,0.0004941204,0.000046346857,0.00008418303,0.00007511289,0.0035016087,0.0039272844,0.041038886,0.21051635,0.73979354],"study_design_scores_gemma":[0.000015589403,0.00004095597,0.0011465574,0.0002537027,0.00007165984,0.0010122672,0.00012854341,0.034912266,0.012288426,0.17585583,0.77423686,0.000037273123],"about_ca_topic_score_codex":0.0014365969,"about_ca_topic_score_gemma":0.0036059823,"teacher_disagreement_score":0.045523826,"about_ca_system_score_codex":0.00060388376,"about_ca_system_score_gemma":0.0008747894,"threshold_uncertainty_score":0.15229237},"labels":[],"label_agreement":null},{"id":"W4251445299","doi":"10.1145/775079.775081","title":"Mining frequent item sets by opportunistic projection","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Scalability; Set (abstract data type); Tree (set theory); Data mining; Projection (relational algebra); Database transaction; Algorithm; Database; Mathematics","score_opus":0.05014063780212529,"score_gpt":0.25913997932862065,"score_spread":0.20899934152649535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251445299","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03188948,0.0003071237,0.9649445,0.000112303635,0.000019061825,0.0001890848,0.00035875972,0.0014336936,0.0007458855],"genre_scores_gemma":[0.20995423,0.0003075005,0.78636134,0.00008661348,0.00004133215,0.00049914705,0.0019095151,0.0000866862,0.00075364177],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99781126,0.0006080067,0.00019862017,0.00038653208,0.00086856796,0.00012708163],"domain_scores_gemma":[0.9958759,0.0024205009,0.00032010055,0.0006836969,0.00059717393,0.00010269161],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014470195,0.00078486896,0.0011717489,0.002552874,0.0007563852,0.0015321414,0.0015276805,0.00062140764,0.0012143158],"category_scores_gemma":[0.008033784,0.000706648,0.00088681956,0.0030496581,0.0005443969,0.0027653016,0.0018432313,0.0007406863,0.00083763135],"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":[0.00042082093,0.00029408702,0.012174094,0.00038856082,0.0002651931,0.0006453535,0.0004937842,0.06641503,0.011491529,0.010825148,0.0042726877,0.8923138],"study_design_scores_gemma":[0.00007319939,0.00034809395,0.0032245063,0.00008153407,0.00010443316,0.0019378262,0.00037021574,0.926689,0.014102114,0.042129353,0.010878704,0.00006099368],"about_ca_topic_score_codex":0.00080594386,"about_ca_topic_score_gemma":0.0011134959,"teacher_disagreement_score":0.002552874,"about_ca_system_score_codex":0.00024856144,"about_ca_system_score_gemma":0.0010101147,"threshold_uncertainty_score":0.0076527},"labels":[],"label_agreement":null},{"id":"W4251473408","doi":"10.1007/978-1-4939-7131-2_100736","title":"Network Mining","year":2018,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Computer science","score_opus":0.03215790518756536,"score_gpt":0.24246540115384208,"score_spread":0.2103074959662767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251473408","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004401491,0.008587468,0.5367282,0.004619174,0.0021929939,0.0005139484,0.004834063,0.006192774,0.43192992],"genre_scores_gemma":[0.056785535,0.023596138,0.35185376,0.001756919,0.0023398323,0.00058891467,0.014675748,0.0015144966,0.5468887],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995851,0.00003923969,0.000017794604,0.00012776403,0.00020291121,0.000027239574],"domain_scores_gemma":[0.9993123,0.00021419431,0.00003737078,0.00019141457,0.00020973374,0.000034897766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006640944,0.0011510015,0.0005826237,0.0025763835,0.0008089245,0.0021377911,0.0017777635,0.0007605583,0.043885946],"category_scores_gemma":[0.0024157877,0.00046283207,0.00068470754,0.002792537,0.00034038667,0.0033691432,0.0013488419,0.0013364963,0.028674688],"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":[0.000025864267,0.00004778793,0.00048804272,0.00033920503,0.000031683732,0.000083158004,0.00007388224,0.0043302607,0.0016924996,0.061692633,0.18624805,0.74494684],"study_design_scores_gemma":[0.000009459047,0.00002432271,0.0007994116,0.00025859373,0.000044637185,0.0006248883,0.000105830724,0.030392982,0.0057337475,0.1260547,0.83592796,0.000023469798],"about_ca_topic_score_codex":0.001094715,"about_ca_topic_score_gemma":0.0020771222,"teacher_disagreement_score":0.043885946,"about_ca_system_score_codex":0.0006547759,"about_ca_system_score_gemma":0.0007400397,"threshold_uncertainty_score":0.1468131},"labels":[],"label_agreement":null},{"id":"W4251789155","doi":"10.1007/978-1-4939-7131-2_100598","title":"Link Mining Metric","year":2018,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Link (geometry); Metric (unit); Computer science; Business; Computer network; Marketing","score_opus":0.033824641096776666,"score_gpt":0.2577472329209648,"score_spread":0.22392259182418814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251789155","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019571038,0.014054689,0.7038327,0.004987083,0.002947984,0.0008606353,0.01838859,0.0073681436,0.22798912],"genre_scores_gemma":[0.2616739,0.012626353,0.5331363,0.0017940291,0.0024780985,0.0012192716,0.03869038,0.002230626,0.1461511],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9956632,0.00059057167,0.0002591341,0.0008165997,0.002502976,0.00016748197],"domain_scores_gemma":[0.9959978,0.0010941637,0.00020138882,0.0009435061,0.0014970964,0.0002660884],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023386534,0.0015946523,0.0013155192,0.00837007,0.0010295057,0.0037632838,0.0021404058,0.0013224215,0.01620002],"category_scores_gemma":[0.012025035,0.00029660398,0.00082140893,0.009043154,0.0006417613,0.0059974664,0.0021327273,0.0017609878,0.011476736],"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":[0.00010268059,0.00018772004,0.001598679,0.00055134646,0.00009769206,0.00007188654,0.000039517035,0.008006461,0.002855759,0.106248446,0.13292964,0.74731016],"study_design_scores_gemma":[0.000038637507,0.00043176202,0.0037893828,0.00039911526,0.00020454549,0.0016725775,0.00016638378,0.18254916,0.016346047,0.32732472,0.4669619,0.000115869254],"about_ca_topic_score_codex":0.0012831673,"about_ca_topic_score_gemma":0.0022368918,"teacher_disagreement_score":0.01620002,"about_ca_system_score_codex":0.0017840858,"about_ca_system_score_gemma":0.001905128,"threshold_uncertainty_score":0.05419451},"labels":[],"label_agreement":null},{"id":"W4252225885","doi":"10.4018/978-1-59904-951-9.ch073","title":"Preference-Based Frequent Pattern Mining","year":2008,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Preference; Data mining; Computer science; Sequential Pattern Mining; Constraint (computer-aided design); K-optimal pattern discovery; Machine learning; Artificial intelligence; Association rule learning; Engineering; Mathematics","score_opus":0.05536291666148491,"score_gpt":0.24747623206066535,"score_spread":0.19211331539918045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4252225885","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010088343,0.0013660348,0.9816125,0.000627481,0.00010565355,0.0002753454,0.0010675022,0.000493189,0.004363949],"genre_scores_gemma":[0.1619123,0.0021268604,0.8286776,0.00035941016,0.00018400027,0.00039002555,0.0027279726,0.00011055836,0.003511176],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9939308,0.0019144807,0.0006161188,0.000994059,0.0022876991,0.00025682684],"domain_scores_gemma":[0.98961663,0.0058414694,0.00079910905,0.0015754905,0.0019449387,0.0002222428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004472724,0.0011232359,0.0016284412,0.0037790863,0.00095677376,0.0026106404,0.002501944,0.0011840684,0.004457389],"category_scores_gemma":[0.022272564,0.0005419573,0.0015936177,0.008009422,0.0006856714,0.004801736,0.0014349035,0.001674609,0.0024883305],"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":[0.00029687144,0.0002393447,0.009701507,0.0012649084,0.0003427539,0.0007558568,0.00041548224,0.040556375,0.00445825,0.10202428,0.021027902,0.81891656],"study_design_scores_gemma":[0.00008851175,0.00021473135,0.002946208,0.0003103933,0.00019837255,0.0032666007,0.0005154405,0.5695521,0.0075143813,0.36692387,0.048353944,0.00011544901],"about_ca_topic_score_codex":0.0010873957,"about_ca_topic_score_gemma":0.0013110815,"teacher_disagreement_score":0.004472724,"about_ca_system_score_codex":0.0008416377,"about_ca_system_score_gemma":0.0013708834,"threshold_uncertainty_score":0.023654282},"labels":[],"label_agreement":null},{"id":"W4252403066","doi":"10.1145/342009.335372","title":"Mining frequent patterns without candidate generation","year":2000,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3195,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science","score_opus":0.022867791703394452,"score_gpt":0.2596902950618048,"score_spread":0.23682250335841035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4252403066","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07246657,0.0010268434,0.91779673,0.00044295163,0.00021517978,0.00078999466,0.0016065557,0.0022142155,0.003440989],"genre_scores_gemma":[0.35666856,0.00061507913,0.6301679,0.00030093355,0.00025510104,0.0008406,0.0073484755,0.0001721125,0.0036312134],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954359,0.001249113,0.00050801487,0.0010503294,0.0014429012,0.00031381572],"domain_scores_gemma":[0.98124874,0.012458133,0.000897677,0.0031366642,0.001986318,0.000272529],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043827924,0.001247691,0.0020738482,0.004333536,0.0011300143,0.0024419646,0.0029050452,0.002042173,0.0038177713],"category_scores_gemma":[0.026700675,0.0007844547,0.0018150847,0.004712982,0.0007989789,0.0038099668,0.0019553069,0.0011783858,0.0028029694],"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":[0.0015697406,0.00060511904,0.014241982,0.0009347532,0.0004545501,0.0020223574,0.0003380806,0.038157687,0.014110377,0.023633786,0.010367137,0.89356434],"study_design_scores_gemma":[0.0004492222,0.0013885491,0.0048972396,0.00019267647,0.0004465717,0.0039136764,0.00027595522,0.8844184,0.025498535,0.06096217,0.017455151,0.00010179126],"about_ca_topic_score_codex":0.00066625193,"about_ca_topic_score_gemma":0.00087390916,"teacher_disagreement_score":0.0043827924,"about_ca_system_score_codex":0.00031371452,"about_ca_system_score_gemma":0.0014159752,"threshold_uncertainty_score":0.023178697},"labels":[],"label_agreement":null},{"id":"W4253420130","doi":"10.4018/978-1-61350-474-1.ch010","title":"Exploring Disease Association from the NHANES Data","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Automatic summarization; Disease; Computer science; Association (psychology); Association rule learning; Data mining; Medicine; Artificial intelligence; Psychology; Pathology","score_opus":0.1594916137140618,"score_gpt":0.2690146886425203,"score_spread":0.10952307492845853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253420130","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20636523,0.02383971,0.6186531,0.008417878,0.00036797876,0.0006291407,0.08507086,0.0036008502,0.053055212],"genre_scores_gemma":[0.34631637,0.017183833,0.54852027,0.0011654331,0.0004108606,0.00056960783,0.07519153,0.00023509056,0.010406974],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994043,0.0001731152,0.00005616777,0.00013326081,0.00020987971,0.00002326246],"domain_scores_gemma":[0.99700373,0.0025204676,0.00016990326,0.00012209323,0.00013938699,0.000044373934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012055886,0.0004617031,0.0003804158,0.0035906262,0.00038014245,0.0009865152,0.00056492235,0.0004179697,0.004267618],"category_scores_gemma":[0.00462475,0.00019974474,0.0009490069,0.005333938,0.00021571976,0.001025634,0.0010850442,0.00073803845,0.0013401603],"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":[0.00019163855,0.0001541346,0.0963537,0.0016985368,0.000434836,0.00149061,0.0010877796,0.013005685,0.004943748,0.020905625,0.042554326,0.8171793],"study_design_scores_gemma":[0.000098183664,0.00035549814,0.2248938,0.0010258347,0.000860674,0.0059413896,0.0030369535,0.14279626,0.009054748,0.2196078,0.39216003,0.00016883915],"about_ca_topic_score_codex":0.0039366297,"about_ca_topic_score_gemma":0.008242348,"teacher_disagreement_score":0.004267618,"about_ca_system_score_codex":0.00037084697,"about_ca_system_score_gemma":0.0006734834,"threshold_uncertainty_score":0.014276564},"labels":[],"label_agreement":null},{"id":"W4253473224","doi":"10.4018/987-1-59904-364-7.ch011","title":"Toward Integrating Data Warehousing with Data Mining Techniques","year":2007,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Université du Québec en Outaouais","funders":"","keywords":"Online analytical processing; Data warehouse; Computer science; Data mining; Scope (computer science); Data cube; Multidimensional data; Exploit; Association rule learning; Projection (relational algebra); Relational database; Data science; Database; Information retrieval; Algorithm","score_opus":0.1238891236086742,"score_gpt":0.32630339678784076,"score_spread":0.20241427317916655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253473224","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032601121,0.0030641912,0.98265415,0.0028226567,0.00014875617,0.00013527958,0.000085901804,0.0011918115,0.0066371765],"genre_scores_gemma":[0.012475432,0.002813341,0.9820112,0.00063672644,0.0001609743,0.00010045598,0.00017882462,0.00018293704,0.0014400075],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99139845,0.0028332195,0.0007376871,0.00095789554,0.003745427,0.00032725613],"domain_scores_gemma":[0.98272026,0.009823781,0.00053053064,0.004760443,0.001753057,0.00041194074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01531542,0.002175524,0.0019331706,0.0056227604,0.001434805,0.012166164,0.005438478,0.002545978,0.0036724566],"category_scores_gemma":[0.01539314,0.0021131812,0.0021513044,0.010756326,0.0030075398,0.017296705,0.008611977,0.0062352377,0.0048111794],"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":[0.00010137582,0.0005300752,0.0020983445,0.002026923,0.0002975152,0.0003797675,0.0015987391,0.016089996,0.006702195,0.29343823,0.009053777,0.66768306],"study_design_scores_gemma":[0.00006753571,0.00021660523,0.001152855,0.0018673927,0.00020416864,0.000766478,0.0013068955,0.16949368,0.014497147,0.5629598,0.24727939,0.00018802403],"about_ca_topic_score_codex":0.0017618245,"about_ca_topic_score_gemma":0.0014464553,"teacher_disagreement_score":0.01531542,"about_ca_system_score_codex":0.0013637448,"about_ca_system_score_gemma":0.003195015,"threshold_uncertainty_score":0.08099663},"labels":[],"label_agreement":null},{"id":"W4253572947","doi":"10.1007/978-1-4939-7131-2_101459","title":"Web Mining","year":2018,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Computer science; World Wide Web","score_opus":0.029057023318752775,"score_gpt":0.24920857469952157,"score_spread":0.2201515513807688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253572947","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027145236,0.020178188,0.32535833,0.0056502824,0.0033260242,0.0004360432,0.003908016,0.010678721,0.6277499],"genre_scores_gemma":[0.015230909,0.021705586,0.17963792,0.0026397095,0.0020181243,0.00026330192,0.009850615,0.0021852022,0.76646876],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992581,0.00005946828,0.000039923056,0.00018078301,0.00042916788,0.000032586457],"domain_scores_gemma":[0.9989992,0.00029974786,0.000039401355,0.00030793558,0.00029332936,0.00006036499],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000778314,0.0012866344,0.0007803437,0.0041911663,0.0008467593,0.003723171,0.0016980433,0.0010115809,0.071310475],"category_scores_gemma":[0.0028280213,0.00068621,0.0008484061,0.0050481632,0.00053183397,0.005097201,0.0019031452,0.0018354162,0.08870021],"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":[0.000012455431,0.000052750103,0.0002042223,0.00034005175,0.000018122028,0.000050722603,0.000065626715,0.000425072,0.0014031089,0.028152164,0.26208726,0.7071884],"study_design_scores_gemma":[0.000004409599,0.000011179285,0.00039519253,0.00019074701,0.00001406442,0.00045652088,0.000045375007,0.0028518422,0.0025887236,0.04855756,0.94486994,0.000014349354],"about_ca_topic_score_codex":0.0005840261,"about_ca_topic_score_gemma":0.0012155592,"teacher_disagreement_score":0.071310475,"about_ca_system_score_codex":0.00060634664,"about_ca_system_score_gemma":0.0008757597,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W4254093539","doi":"10.1007/978-1-4939-7131-2_100255","title":"Data Transformation","year":2018,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Transformation (genetics); Computer science; Geography; Geology; Biology","score_opus":0.07877454847275729,"score_gpt":0.28688238651989456,"score_spread":0.20810783804713728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254093539","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050646868,0.0013609993,0.7732797,0.002184837,0.0017104129,0.001457525,0.01594494,0.033814415,0.16518249],"genre_scores_gemma":[0.079651095,0.0039419876,0.61445427,0.0029742704,0.0005494168,0.0016404372,0.05901994,0.008622599,0.22914602],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99812967,0.00018406093,0.00014863747,0.0005366933,0.00089133176,0.00010966804],"domain_scores_gemma":[0.9981981,0.00027586846,0.00004225894,0.00095424236,0.00048738695,0.000042159074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001308331,0.00116496,0.0007634258,0.0027034364,0.00076945795,0.0031356197,0.0019147823,0.0005382741,0.06603466],"category_scores_gemma":[0.004655141,0.0004879687,0.0017392169,0.0035075063,0.0008039446,0.0029720864,0.0038922727,0.0019107659,0.051066145],"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":[0.00013958279,0.00012403213,0.0005641583,0.00052563474,0.00004905441,0.00016591823,0.0002021696,0.0019909553,0.0089329025,0.08883463,0.15681635,0.74165463],"study_design_scores_gemma":[0.000028789293,0.00004674778,0.00037873234,0.000114195755,0.00004030014,0.00042686064,0.00017538486,0.011153255,0.031705454,0.07712793,0.8787734,0.000029031726],"about_ca_topic_score_codex":0.0016088837,"about_ca_topic_score_gemma":0.0011400502,"teacher_disagreement_score":0.06603466,"about_ca_system_score_codex":0.0008250696,"about_ca_system_score_gemma":0.0017645975,"threshold_uncertainty_score":0.22090793},"labels":[],"label_agreement":null},{"id":"W4254656533","doi":"10.1007/978-1-4614-6170-8_100587","title":"Categorical Data Similarity","year":2014,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Categorical variable; Similarity (geometry); Artificial intelligence; Computer science; Natural language processing; Mathematics; Statistics","score_opus":0.08237857441381383,"score_gpt":0.2816371582400747,"score_spread":0.19925858382626085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254656533","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0071842633,0.010791672,0.8941882,0.0020793858,0.0019013387,0.00032687114,0.001956872,0.0025936535,0.0789777],"genre_scores_gemma":[0.13536666,0.01125732,0.75366944,0.0013143424,0.0018277104,0.0005166824,0.009365703,0.0007746091,0.08590742],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977088,0.0002951327,0.00020999576,0.00057732867,0.001131109,0.00007756436],"domain_scores_gemma":[0.9981153,0.0004411345,0.00009898076,0.00058663654,0.0006746044,0.00008328007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001072195,0.0006677051,0.0010943224,0.004087241,0.0008254184,0.0025324046,0.0017759741,0.0007787926,0.014686848],"category_scores_gemma":[0.006389774,0.00034852204,0.0010301155,0.0072556753,0.00091045763,0.004192028,0.002614894,0.0014890452,0.0074107302],"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":[0.00003690836,0.00004999834,0.0006804642,0.00038325277,0.000043738608,0.000059921553,0.00016579525,0.0019876298,0.002263279,0.13014047,0.0499288,0.8142597],"study_design_scores_gemma":[0.000012889967,0.00012553037,0.0020246275,0.00025722125,0.000065282045,0.0016169385,0.0003268613,0.039219663,0.008862564,0.49744317,0.44997087,0.00007432712],"about_ca_topic_score_codex":0.0007163061,"about_ca_topic_score_gemma":0.0007489834,"teacher_disagreement_score":0.014686848,"about_ca_system_score_codex":0.0010527722,"about_ca_system_score_gemma":0.001125118,"threshold_uncertainty_score":0.049132407},"labels":[],"label_agreement":null},{"id":"W4254786677","doi":"10.4018/978-1-59140-557-3.ch056","title":"Data Mining with Incomplete Data","year":2005,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint Mary's University","funders":"","keywords":"Missing data; Ambiguity; Survey data collection; Computer science; Data mining; Data set; Data science; Artificial intelligence; Statistics; Mathematics; Machine learning","score_opus":0.08128089344225493,"score_gpt":0.2934700909831993,"score_spread":0.2121891975409444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254786677","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029337523,0.006117238,0.98179746,0.0023344764,0.0003005632,0.0004504999,0.0025736562,0.00074222236,0.0027501239],"genre_scores_gemma":[0.04013485,0.008694775,0.9398875,0.0010532681,0.00070241676,0.0009806888,0.0062976726,0.00016182747,0.0020869472],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96681845,0.01522398,0.0038886697,0.0059473184,0.0075624185,0.0005591911],"domain_scores_gemma":[0.9292134,0.047230247,0.0039321324,0.015226029,0.0038524312,0.00054573425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024226952,0.0021858083,0.0042609693,0.008810535,0.0021311278,0.008495379,0.006298503,0.0030790635,0.003928753],"category_scores_gemma":[0.079549104,0.0018198825,0.0051664296,0.01413813,0.0029507899,0.013372816,0.008944872,0.0052658203,0.0032644086],"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":[0.00028994767,0.00034782937,0.010158393,0.008242946,0.0018055711,0.0016022536,0.002302741,0.043216016,0.0019277057,0.17831938,0.042901356,0.70888585],"study_design_scores_gemma":[0.000089658344,0.00020804683,0.0022777675,0.0023424495,0.00042543066,0.0021491763,0.0012453891,0.17593136,0.0047498457,0.6628361,0.14759643,0.000148388],"about_ca_topic_score_codex":0.0010942364,"about_ca_topic_score_gemma":0.0012617721,"teacher_disagreement_score":0.024226952,"about_ca_system_score_codex":0.0014270582,"about_ca_system_score_gemma":0.0032147206,"threshold_uncertainty_score":0.1281259},"labels":[],"label_agreement":null},{"id":"W4255161801","doi":"10.4018/978-1-59904-951-9.ch093","title":"Visualization Techniques for Data Mining","year":2008,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"","keywords":"Computer science; Knowledge extraction; Data mining; Data science; Association rule learning; Cluster analysis; K-optimal pattern discovery; The Internet; Decision tree; Visualization; Data warehouse; Data stream mining; Machine learning; World Wide Web","score_opus":0.059889280450946256,"score_gpt":0.31995400322032913,"score_spread":0.26006472276938286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255161801","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009754077,0.041703213,0.90302587,0.0034514687,0.0012780961,0.0003595489,0.0026878847,0.013076538,0.03344195],"genre_scores_gemma":[0.022874078,0.03507978,0.9152936,0.0010645406,0.0010774106,0.0009806689,0.0059269797,0.0016801822,0.016022803],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99607205,0.0013493525,0.00040011594,0.00048666788,0.0015719302,0.000119913966],"domain_scores_gemma":[0.99576354,0.0024817022,0.00023364015,0.00068015244,0.0007422081,0.000098693126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003839174,0.0028419665,0.0018873519,0.006091398,0.0009052581,0.0062186657,0.0032350037,0.0022478697,0.03310618],"category_scores_gemma":[0.010614631,0.0009685198,0.0017232102,0.011026366,0.001224379,0.005776633,0.0031646984,0.0028160869,0.015026466],"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":[0.00007332269,0.00007629393,0.00061524945,0.0026732113,0.00021670271,0.00028488916,0.0005809711,0.010614257,0.0018788697,0.15008076,0.17323369,0.65967184],"study_design_scores_gemma":[0.000053695425,0.000038434453,0.00056536467,0.0008162789,0.000063186184,0.000643664,0.0002529298,0.04435374,0.0016557924,0.34416386,0.60732085,0.00007223166],"about_ca_topic_score_codex":0.0016572956,"about_ca_topic_score_gemma":0.0015932809,"teacher_disagreement_score":0.03310618,"about_ca_system_score_codex":0.0010771331,"about_ca_system_score_gemma":0.0012585423,"threshold_uncertainty_score":0.11075121},"labels":[],"label_agreement":null},{"id":"W4255851574","doi":"10.1007/978-1-4939-7131-2_101032","title":"Search and Querying Social Data","year":2018,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Computer science; Information retrieval","score_opus":0.12795546004126823,"score_gpt":0.32609594501671796,"score_spread":0.19814048497544973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255851574","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009020709,0.037901033,0.81509364,0.009428956,0.0014960521,0.00023579865,0.0028060356,0.0033537922,0.12066397],"genre_scores_gemma":[0.14064682,0.054834712,0.6112804,0.0028278376,0.002515668,0.00057488604,0.010713585,0.0013662289,0.17523985],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998672,0.00026813868,0.00008999011,0.0002468356,0.00065629487,0.000066668086],"domain_scores_gemma":[0.9986707,0.00074945955,0.000040703224,0.00033793322,0.00015722697,0.00004392836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012601785,0.0009766091,0.0011265025,0.0029451542,0.0009073391,0.00460025,0.0015322603,0.0014259267,0.012749431],"category_scores_gemma":[0.0051600444,0.0005403591,0.0010144501,0.006217485,0.0014730028,0.011619476,0.0030504384,0.0016360616,0.008287988],"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":[0.00003575779,0.00004065102,0.000466861,0.0008943362,0.000061115614,0.000094117,0.000540369,0.0028530397,0.0022029504,0.33988744,0.10685257,0.54607075],"study_design_scores_gemma":[0.000010006425,0.000016001602,0.00039420213,0.00022789314,0.000034308483,0.0004500204,0.00031363845,0.031904664,0.0026033437,0.6000124,0.3639998,0.00003361395],"about_ca_topic_score_codex":0.0016817645,"about_ca_topic_score_gemma":0.0019420192,"teacher_disagreement_score":0.012749431,"about_ca_system_score_codex":0.0011682487,"about_ca_system_score_gemma":0.0010022804,"threshold_uncertainty_score":0.042651117},"labels":[],"label_agreement":null},{"id":"W4256184506","doi":"10.4018/978-1-60960-126-3.ch004","title":"Heterogeneous Text and Numerical Data Mining with Possible Applications in Business and Financial Sectors","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Semantics (computer science); Data type; Data science; Data processing; Qualitative property; Data modeling; Data mining; Database; Programming language; Machine learning","score_opus":0.02756939377203025,"score_gpt":0.2426782168533207,"score_spread":0.21510882308129045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4256184506","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0096897995,0.09953389,0.73339397,0.0038142975,0.0018809407,0.00029937836,0.0025028067,0.001614681,0.14727025],"genre_scores_gemma":[0.048615243,0.056929957,0.7867255,0.0017152366,0.001660156,0.0003588319,0.0053795823,0.000625777,0.09798964],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993687,0.00011642636,0.000047772577,0.00015915144,0.0002815556,0.000026369142],"domain_scores_gemma":[0.99920803,0.0005383499,0.000038493003,0.00007687614,0.000103020175,0.000035304674],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012183215,0.0008472795,0.00080530014,0.003164822,0.0006612571,0.0027780887,0.0015420069,0.00073796004,0.011652127],"category_scores_gemma":[0.002176699,0.00043127657,0.0009281067,0.009521321,0.0008518184,0.004081449,0.0012976755,0.0013552493,0.0046481933],"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":[0.000064135944,0.00011305826,0.0008510321,0.0014514053,0.00005118652,0.00047122443,0.0006412313,0.0037129978,0.004472488,0.25614867,0.0606855,0.671337],"study_design_scores_gemma":[0.000017678538,0.000036422505,0.0017504,0.001066755,0.00006300115,0.0012847914,0.0003645547,0.02167744,0.004349729,0.34612256,0.6232171,0.00004954911],"about_ca_topic_score_codex":0.0005674644,"about_ca_topic_score_gemma":0.0011403072,"teacher_disagreement_score":0.011652127,"about_ca_system_score_codex":0.00071015005,"about_ca_system_score_gemma":0.0007544819,"threshold_uncertainty_score":0.038980305},"labels":[],"label_agreement":null},{"id":"W4256196566","doi":"10.1007/978-1-4939-7131-2_100250","title":"Data Mining and Knowledge Discovery in Economic Networks","year":2018,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Knowledge extraction; Data science; Computer science; Data mining","score_opus":0.05028281274821432,"score_gpt":0.27991627337489217,"score_spread":0.22963346062667783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4256196566","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007189685,0.23173834,0.5219939,0.021046294,0.003797249,0.00013101076,0.0014966016,0.00070516084,0.2119018],"genre_scores_gemma":[0.113550134,0.29473102,0.35261962,0.002940304,0.006469278,0.00032757732,0.0031151855,0.00044014645,0.2258068],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996146,0.00008550873,0.000023630651,0.0000743552,0.00018113128,0.000020735903],"domain_scores_gemma":[0.99827147,0.0013939855,0.00004803362,0.0001330412,0.000115296905,0.00003808196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000897191,0.000703508,0.0006698077,0.0018794539,0.00048080247,0.0031564538,0.0011949275,0.000953356,0.009062699],"category_scores_gemma":[0.004576242,0.00040093603,0.00061465206,0.0043696533,0.0014741106,0.004986512,0.0011532024,0.0022768702,0.0037561432],"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":[0.0000166069,0.000043294614,0.00036528634,0.0006544481,0.000038745584,0.00007872653,0.00015836966,0.006514042,0.00029152568,0.6271111,0.0698923,0.29483563],"study_design_scores_gemma":[0.000003606721,0.000006687935,0.0002795326,0.00028928465,0.000013178678,0.00012849862,0.00005078704,0.014593371,0.0003290779,0.76930594,0.21498878,0.000011218847],"about_ca_topic_score_codex":0.0010200576,"about_ca_topic_score_gemma":0.0011986895,"teacher_disagreement_score":0.009062699,"about_ca_system_score_codex":0.0011442144,"about_ca_system_score_gemma":0.0009756683,"threshold_uncertainty_score":0.030317783},"labels":[],"label_agreement":null},{"id":"W4256416331","doi":"10.4018/9781605660103.ch130","title":"On Explanation-Oriented Data Mining","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Data science; Data mining","score_opus":0.05657923940842615,"score_gpt":0.27522013122374,"score_spread":0.21864089181531385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4256416331","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033585806,0.039259683,0.88514936,0.008318951,0.0004517239,0.000326424,0.0005872602,0.0007690794,0.06177903],"genre_scores_gemma":[0.055673916,0.036308542,0.8769004,0.003581535,0.0008455019,0.0008227654,0.0018744833,0.00044209586,0.023550738],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996157,0.0018383992,0.0001984078,0.00041647136,0.0012592085,0.00013050724],"domain_scores_gemma":[0.989908,0.008744629,0.0001800166,0.00058098935,0.0004860277,0.00010037586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063118096,0.0015227455,0.0010056626,0.004381519,0.0008568595,0.004737349,0.0025143104,0.0016794214,0.0081119],"category_scores_gemma":[0.0105909305,0.00074036483,0.0013616456,0.0071272734,0.004405639,0.008766462,0.0032834075,0.0041522887,0.0029283548],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031982094,0.00007004717,0.0007641944,0.0009204705,0.00006506054,0.00017988769,0.0011681056,0.0057362234,0.00045847002,0.59453946,0.027876094,0.36819008],"study_design_scores_gemma":[0.000019645813,0.00003328792,0.0005836958,0.00070307887,0.000028655588,0.00037700037,0.00030769565,0.022941258,0.0007954779,0.80695236,0.1672211,0.000036745656],"about_ca_topic_score_codex":0.0014538476,"about_ca_topic_score_gemma":0.0015991612,"teacher_disagreement_score":0.0081119,"about_ca_system_score_codex":0.0018006635,"about_ca_system_score_gemma":0.001494283,"threshold_uncertainty_score":0.03338039},"labels":[],"label_agreement":null},{"id":"W4256421351","doi":"10.4018/9781591400516.ch003","title":"Cooperative Learning and Virtual Reality-Based Visualization for Data Mining","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"","keywords":"Visualization; Virtual reality; Computer science; Human–computer interaction; Data visualization; Data science; Artificial intelligence","score_opus":0.07010954461761205,"score_gpt":0.3218494956118355,"score_spread":0.25173995099422347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4256421351","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005296535,0.030772949,0.90657556,0.0017537714,0.0004257115,0.00017314187,0.00038749055,0.002771985,0.051842846],"genre_scores_gemma":[0.09335674,0.031976342,0.8340012,0.00060440646,0.00037486354,0.0006301689,0.0012431468,0.00056490104,0.037248313],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99891245,0.0004242311,0.00005557356,0.00017541322,0.00037689242,0.000055455075],"domain_scores_gemma":[0.9982369,0.0012180895,0.00007434264,0.00022452531,0.00017884746,0.000067265355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013688979,0.0011354624,0.0007508869,0.0022385078,0.0005671808,0.004433563,0.0019832652,0.0012432459,0.008238349],"category_scores_gemma":[0.0033869524,0.00048395264,0.0012156507,0.004101674,0.0013426782,0.0033242477,0.0020618446,0.0018684133,0.0031099543],"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":[0.00009960616,0.00012897569,0.00079042686,0.0018763571,0.00012495341,0.0004050348,0.0033085516,0.027422454,0.0063301274,0.28047037,0.051837083,0.6272062],"study_design_scores_gemma":[0.000052755146,0.00011993768,0.0016328068,0.0009725163,0.000079944344,0.0015640592,0.0009657781,0.12947652,0.0063003493,0.3510452,0.5076729,0.00011726586],"about_ca_topic_score_codex":0.00122024,"about_ca_topic_score_gemma":0.0012001621,"teacher_disagreement_score":0.008238349,"about_ca_system_score_codex":0.0009684866,"about_ca_system_score_gemma":0.00084398873,"threshold_uncertainty_score":0.027559996},"labels":[],"label_agreement":null},{"id":"W4283213951","doi":"10.1109/iemtronics55184.2022.9795745","title":"Intelligent Feature Selection on Multivariate Dataset using Advanced Data Profiling","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International IOT, Electronics and Mechatronics Conference (IEMTRONICS)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Feature selection; Profiling (computer programming); Computer science; Data mining; Machine learning; Multivariate statistics; Artificial intelligence","score_opus":0.06475998024089975,"score_gpt":0.3384563381554218,"score_spread":0.27369635791452207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283213951","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27464643,0.00068714167,0.71211684,0.0006548328,0.000114944654,0.00035636342,0.0048380056,0.0056689954,0.0009164725],"genre_scores_gemma":[0.6542778,0.00027422298,0.3359085,0.00009585732,0.00007740327,0.00037847713,0.008264754,0.00008987888,0.0006331204],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988814,0.00032275045,0.000141711,0.00027168336,0.00027306107,0.000109391796],"domain_scores_gemma":[0.997649,0.0013419718,0.0002498337,0.00030873713,0.00037463655,0.00007572836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017137569,0.0008207612,0.0010686142,0.003543458,0.00043257067,0.001151218,0.00057143194,0.00051750056,0.00065576355],"category_scores_gemma":[0.0054444573,0.0001613492,0.0010381349,0.0027343794,0.00022897864,0.0008234677,0.0007678106,0.000689309,0.00041939053],"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":[0.00089544704,0.00053385645,0.044412605,0.00030558545,0.00032631718,0.00074353896,0.00025038203,0.10691775,0.03748658,0.0019239233,0.008749937,0.7974541],"study_design_scores_gemma":[0.000050832314,0.00027040552,0.020288331,0.00004070694,0.00009937394,0.00036689287,0.00017749547,0.9479436,0.020595409,0.0054074195,0.004710342,0.00004920812],"about_ca_topic_score_codex":0.0017203342,"about_ca_topic_score_gemma":0.0015675812,"teacher_disagreement_score":0.003543458,"about_ca_system_score_codex":0.00040814638,"about_ca_system_score_gemma":0.00054499524,"threshold_uncertainty_score":0.0090633035},"labels":[],"label_agreement":null},{"id":"W4283454123","doi":"10.1145/3501247.3531578","title":"Subgraph Representation Learning for Team Mining","year":2022,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University; Toronto Metropolitan University","funders":"","keywords":"Overfitting; Computer science; Machine learning; Artificial intelligence; Heuristic; Graph; Set (abstract data type); Ranking (information retrieval); Representation (politics); Identification (biology); Space (punctuation); Artificial neural network; Theoretical computer science","score_opus":0.029265935214874014,"score_gpt":0.2916004709408035,"score_spread":0.26233453572592946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283454123","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019952668,0.00067558605,0.97520113,0.00046375347,0.000038583537,0.000105254076,0.0009629074,0.0013731929,0.0012269063],"genre_scores_gemma":[0.471837,0.00056043215,0.5177781,0.00036514457,0.00011954825,0.0004007362,0.006339014,0.00023877692,0.002361332],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858874,0.0005965706,0.00006653366,0.00042968156,0.0002211442,0.00009721593],"domain_scores_gemma":[0.99631304,0.002209104,0.00037789418,0.0006264666,0.00033316063,0.00014032079],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013091724,0.0010824694,0.0011721629,0.0032736813,0.00083863246,0.0009899739,0.0019002272,0.0016251751,0.0021668475],"category_scores_gemma":[0.008725964,0.00040792875,0.001489921,0.0035428756,0.0008197977,0.0023125955,0.0013890159,0.0017474366,0.0008229563],"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":[0.00019405462,0.00034190374,0.010208062,0.0006160862,0.00039110993,0.00024473402,0.00039928991,0.49746117,0.003817995,0.04983902,0.019138167,0.41734844],"study_design_scores_gemma":[0.000014162374,0.000028090615,0.0006283707,0.000028958188,0.000026397021,0.00005906141,0.00007112001,0.9121512,0.00093474827,0.08369086,0.0023560987,0.000010900097],"about_ca_topic_score_codex":0.005172646,"about_ca_topic_score_gemma":0.010096928,"teacher_disagreement_score":0.005172646,"about_ca_system_score_codex":0.0012778991,"about_ca_system_score_gemma":0.0013986562,"threshold_uncertainty_score":0.0102850795},"labels":[],"label_agreement":null},{"id":"W4284966291","doi":"10.1007/s10489-022-03699-7","title":"Discovering probabilistically weighted sequential patterns in uncertain databases","year":2022,"lang":"en","type":"article","venue":"Applied Intelligence","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 Manitoba","funders":"","keywords":"Computer science; Pruning; Data mining; Scalability; Probabilistic logic; Sequential Pattern Mining; Sequence (biology); Semantics (computer science); Artificial intelligence; Machine learning; Database","score_opus":0.04439176029157027,"score_gpt":0.29112453916731407,"score_spread":0.2467327788757438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4284966291","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2883688,0.0014299437,0.70620984,0.00095772726,0.00010417531,0.00014143057,0.0012838241,0.00040758133,0.0010967476],"genre_scores_gemma":[0.8672419,0.0007669654,0.12922512,0.00011148174,0.0001785489,0.000111139714,0.0015196824,0.000045509845,0.00079971313],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962476,0.00058823434,0.00055934826,0.0008800892,0.0015072734,0.00021732523],"domain_scores_gemma":[0.980508,0.013931601,0.0025210888,0.0012153832,0.0014602935,0.00036367628],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032542092,0.00071303797,0.0013821864,0.0037600978,0.00064028095,0.0024807304,0.0021131528,0.0013387399,0.0009112544],"category_scores_gemma":[0.025805876,0.0009677588,0.0012070535,0.0042005302,0.0007984666,0.0053513465,0.0012901655,0.0014210058,0.00027126554],"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":[0.0022000899,0.0006797839,0.103440806,0.0011193289,0.0012759764,0.0036139549,0.0009141187,0.46648633,0.007884763,0.05962867,0.004919748,0.34783643],"study_design_scores_gemma":[0.0000323547,0.000088570545,0.0032784485,0.000039967585,0.00014099968,0.0004917965,0.00013847096,0.9143196,0.0017912751,0.07861029,0.0010450657,0.000023191233],"about_ca_topic_score_codex":0.0021621203,"about_ca_topic_score_gemma":0.0034885143,"teacher_disagreement_score":0.0037600978,"about_ca_system_score_codex":0.0006926701,"about_ca_system_score_gemma":0.0009469142,"threshold_uncertainty_score":0.017210066},"labels":[],"label_agreement":null},{"id":"W4287455646","doi":"10.1007/978-3-031-12670-3_19","title":"Q-VIPER: Quantitative Vertical Bitwise Algorithm to Mine Frequent Patterns","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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 Manitoba","funders":"","keywords":"Bitmap; Computer science; Database transaction; Data mining; Algorithm; Big data; Association rule learning; Bitwise operation; Information retrieval; Database; Artificial intelligence","score_opus":0.025681869737629343,"score_gpt":0.2803757633153318,"score_spread":0.25469389357770245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287455646","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012368811,0.0005690112,0.9717401,0.00020449384,0.00017964662,0.00024171399,0.00317025,0.010149967,0.0013760515],"genre_scores_gemma":[0.05258015,0.00021952043,0.93701017,0.00014983033,0.000081673854,0.00033076384,0.0060577095,0.0005697909,0.0030003597],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984755,0.00033002565,0.00018880342,0.00032945586,0.000552376,0.00012379918],"domain_scores_gemma":[0.9974533,0.0011976585,0.00018509442,0.0004526529,0.00061278755,0.00009846954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019971242,0.0011051601,0.0012144025,0.0039977217,0.00086442207,0.0016679927,0.0022822893,0.001311343,0.0146834],"category_scores_gemma":[0.008170812,0.00068390014,0.0011549602,0.0051015387,0.00054815336,0.002468179,0.0019796246,0.0016642483,0.0045773718],"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":[0.0008544027,0.00019390725,0.0033926778,0.00082205207,0.00021018126,0.00018970357,0.00012954189,0.014635201,0.014096147,0.016096197,0.03206126,0.9173187],"study_design_scores_gemma":[0.0004026573,0.0005995503,0.0028605184,0.00018234021,0.000188058,0.0009996475,0.00017114746,0.85608804,0.025842607,0.08454582,0.028038025,0.0000815703],"about_ca_topic_score_codex":0.0010923409,"about_ca_topic_score_gemma":0.001572797,"teacher_disagreement_score":0.0146834,"about_ca_system_score_codex":0.00041104655,"about_ca_system_score_gemma":0.0016236849,"threshold_uncertainty_score":0.049120843},"labels":[],"label_agreement":null},{"id":"W4292906384","doi":"10.1007/978-3-642-37453-1","title":"Advances in Knowledge Discovery and Data Mining","year":2013,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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; Knowledge extraction; Data science; Volume (thermodynamics); Data mining; Information retrieval","score_opus":0.023846120441123983,"score_gpt":0.2973966520615528,"score_spread":0.2735505316204288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292906384","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014084355,0.7895001,0.14860304,0.0063447184,0.004887012,0.00010456203,0.00073951203,0.0009801971,0.04743232],"genre_scores_gemma":[0.015708245,0.7455308,0.16322547,0.0032566157,0.00847931,0.00019104542,0.0020166459,0.00036362253,0.061228223],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99853957,0.00018967081,0.00012673478,0.00019010362,0.0008955327,0.000058410715],"domain_scores_gemma":[0.9949411,0.0035774314,0.00021476382,0.00044570983,0.0006728978,0.00014806546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021167668,0.0014839132,0.0025155905,0.0047861757,0.00045364624,0.003895807,0.0021583235,0.0012465667,0.011350637],"category_scores_gemma":[0.0069108256,0.00069579354,0.0010641153,0.0098451795,0.0014640467,0.006687002,0.0019551867,0.0031594876,0.011038498],"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":[0.000041188312,0.00008400292,0.00033082627,0.0038844945,0.0001365304,0.00009426103,0.00010329866,0.001737464,0.00096796383,0.05777434,0.121855296,0.8129903],"study_design_scores_gemma":[0.000018975175,0.00004911906,0.00062462356,0.00105531,0.00010127387,0.00056442845,0.00007992665,0.006717671,0.0011367323,0.21857935,0.77103627,0.00003623087],"about_ca_topic_score_codex":0.0006731139,"about_ca_topic_score_gemma":0.00088250963,"teacher_disagreement_score":0.011350637,"about_ca_system_score_codex":0.0009095983,"about_ca_system_score_gemma":0.0016283466,"threshold_uncertainty_score":0.037971675},"labels":[],"label_agreement":null},{"id":"W4297665113","doi":"","title":"Proceedings of the Third ACM International Workshop on Multimedia Data Mining","year":2002,"lang":"en","type":"preprint","venue":"","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":"University of Alberta","funders":"","keywords":"Computer science; Multimedia; Data science; World Wide Web","score_opus":0.09552661550641994,"score_gpt":0.3164996444305295,"score_spread":0.22097302892410958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297665113","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047149535,0.05044571,0.7902688,0.024551319,0.038246743,0.000877343,0.004041139,0.007233602,0.03718594],"genre_scores_gemma":[0.16908088,0.046611145,0.5366121,0.0051092026,0.01862111,0.00063560077,0.020874277,0.002763218,0.19969247],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99787545,0.00060365873,0.00018628954,0.00034441194,0.00079459854,0.00019552509],"domain_scores_gemma":[0.9938745,0.0019652764,0.00014709409,0.0013469722,0.0018517149,0.0008143316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006386865,0.0016365718,0.0032919184,0.0025116273,0.0012449992,0.0068712123,0.0026960813,0.0017925858,0.016912337],"category_scores_gemma":[0.008700549,0.00091966236,0.0013204362,0.0018685288,0.0012130158,0.005168692,0.0022294915,0.0034502775,0.00603319],"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":[0.0010355345,0.0007656035,0.0025182818,0.00047551983,0.00030936438,0.00032418713,0.0005108333,0.0022304324,0.010421158,0.009750922,0.4009962,0.57066196],"study_design_scores_gemma":[0.00030872138,0.0006009104,0.008594896,0.0005593032,0.00074464286,0.0017390994,0.0010078928,0.093376875,0.034989584,0.05957802,0.7983259,0.00017416461],"about_ca_topic_score_codex":0.005469103,"about_ca_topic_score_gemma":0.008536429,"teacher_disagreement_score":0.016912337,"about_ca_system_score_codex":0.0010429184,"about_ca_system_score_gemma":0.0024509262,"threshold_uncertainty_score":0.056577444},"labels":[],"label_agreement":null},{"id":"W4297796099","doi":"10.1145/3548785.3548808","title":"Q-Eclat: Vertical Mining of Interesting Quantitative Patterns","year":2022,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; University of Manitoba","keywords":"Computer science; Database transaction; Data mining; Analytics; Prefix; Representation (politics); Database","score_opus":0.05007709117989076,"score_gpt":0.302146536396773,"score_spread":0.25206944521688224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297796099","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028574118,0.0003478909,0.96309084,0.0003098972,0.00005539406,0.0002998212,0.0015827722,0.0041804137,0.0015587992],"genre_scores_gemma":[0.13480808,0.00018562676,0.8571153,0.0002433743,0.000037990172,0.00024307135,0.004886621,0.00026298704,0.0022170283],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99844223,0.00018320707,0.00020357361,0.00039775757,0.0006317032,0.00014160304],"domain_scores_gemma":[0.99644816,0.0014175996,0.00041012853,0.0005459228,0.0010606279,0.00011748508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015139277,0.00100085,0.0007918928,0.0031902716,0.00075362826,0.0016859255,0.0018251888,0.001011273,0.003270751],"category_scores_gemma":[0.0068621887,0.0005569033,0.0015157502,0.0032489935,0.0006507334,0.0024864622,0.0019817604,0.0009934192,0.0014872873],"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":[0.0005504879,0.0003380595,0.017841794,0.00082186033,0.0002284608,0.0008198907,0.0005443294,0.027288606,0.033484567,0.021120373,0.018337682,0.8786239],"study_design_scores_gemma":[0.00015677205,0.0003123735,0.0042567514,0.0001366695,0.0001060178,0.0016161499,0.00034790154,0.8999967,0.02673139,0.04189041,0.02439762,0.00005116692],"about_ca_topic_score_codex":0.0028366256,"about_ca_topic_score_gemma":0.004072837,"teacher_disagreement_score":0.003270751,"about_ca_system_score_codex":0.0005665438,"about_ca_system_score_gemma":0.0015036595,"threshold_uncertainty_score":0.010941744},"labels":[],"label_agreement":null},{"id":"W4297813146","doi":"10.48550/arxiv.1707.03471","title":"Proceedings of the 2017 AdKDD &amp; TargetAd Workshop","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nova scotia; Conjunction (astronomy); Library science; Computer science; History; Physics; Archaeology; Astronomy","score_opus":0.11609474763798724,"score_gpt":0.21874669692682516,"score_spread":0.10265194928883792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297813146","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018288488,0.05420886,0.39724946,0.18758255,0.1372468,0.0014126241,0.090303354,0.03321051,0.08049735],"genre_scores_gemma":[0.0570394,0.06047787,0.26191023,0.020529717,0.021911092,0.0016632002,0.33836144,0.012018558,0.22608858],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9902801,0.0024808971,0.00067816186,0.001326187,0.004804476,0.0004302474],"domain_scores_gemma":[0.97681993,0.0071152803,0.0003642693,0.0040462636,0.008199269,0.003454974],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017141566,0.0020348837,0.004030596,0.004331872,0.0027096842,0.012561772,0.0032406698,0.002641413,0.026791006],"category_scores_gemma":[0.026425065,0.0013390618,0.0016905279,0.0041371905,0.002166698,0.010748733,0.006330521,0.006937275,0.030360067],"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":[0.00013359539,0.00011019439,0.00035593598,0.00015450393,0.00004164406,0.00007195517,0.00007993703,0.00077327044,0.00028963274,0.0037727475,0.94077724,0.05343924],"study_design_scores_gemma":[0.00006842859,0.00003082557,0.0006246183,0.00016811173,0.000043203538,0.00014455034,0.00021316856,0.009494492,0.0016256286,0.016223954,0.97131807,0.00004492543],"about_ca_topic_score_codex":0.019176608,"about_ca_topic_score_gemma":0.03515904,"teacher_disagreement_score":0.973209,"about_ca_system_score_codex":0.0050814976,"about_ca_system_score_gemma":0.013312797,"threshold_uncertainty_score":0.09065437},"labels":[],"label_agreement":null},{"id":"W4298096513","doi":"","title":"Proceedings of the International Workshop on Knowledge Discovery in Multimedia and Complex Data {(KDMCD} 2002), in conjunction with the Sixth Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD-02)","year":2002,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Conjunction (astronomy); Knowledge extraction; Computer science; Data science; Data mining","score_opus":0.06185521006877669,"score_gpt":0.27875357660576466,"score_spread":0.21689836653698796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298096513","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026973428,0.06547591,0.6842614,0.053343583,0.1031554,0.00095242885,0.0058917687,0.0071360064,0.052810192],"genre_scores_gemma":[0.10098209,0.06941319,0.46870345,0.011276568,0.028977178,0.00072232983,0.029144006,0.0033887608,0.28739238],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99740285,0.000803056,0.00024742875,0.00044642994,0.0008851355,0.00021509387],"domain_scores_gemma":[0.9935401,0.0018147555,0.00021183392,0.001074716,0.0021272155,0.0012313393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0060945284,0.0013657926,0.0034732774,0.0016940839,0.0011979121,0.007812417,0.0027130342,0.0020638844,0.022953393],"category_scores_gemma":[0.008312173,0.00073705765,0.0012117674,0.0019270143,0.0012506078,0.0047279787,0.0029015692,0.0041155033,0.010975006],"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":[0.0007337541,0.0006302126,0.0009298251,0.0007734412,0.00018917379,0.00033921763,0.0006261777,0.0018974574,0.005685545,0.010085108,0.5820913,0.39601883],"study_design_scores_gemma":[0.00017956659,0.00024728064,0.0032089027,0.00041525514,0.00029721088,0.0008802209,0.00052085356,0.025067674,0.0090919,0.03372069,0.9262747,0.000095674004],"about_ca_topic_score_codex":0.0049619484,"about_ca_topic_score_gemma":0.011247758,"teacher_disagreement_score":0.022953393,"about_ca_system_score_codex":0.0011548304,"about_ca_system_score_gemma":0.0027431154,"threshold_uncertainty_score":0.07678676},"labels":[],"label_agreement":null},{"id":"W4298133261","doi":"10.1007/978-3-642-53914-5","title":"Advanced Data Mining and Applications","year":2013,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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 Alberta","funders":"","keywords":"Computer science; Volume (thermodynamics); Data mining; Data set; Set (abstract data type); Data science; Artificial intelligence; Programming language","score_opus":0.022654819517960285,"score_gpt":0.27534971972639344,"score_spread":0.25269490020843316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298133261","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037622086,0.13399982,0.6932629,0.0056057815,0.010230099,0.00048919424,0.0032869407,0.0062208544,0.1431422],"genre_scores_gemma":[0.020930283,0.12748948,0.4305625,0.0034402444,0.00803742,0.0006142979,0.008474664,0.001184481,0.39926666],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991135,0.000066618544,0.000085115615,0.00015082392,0.00055036467,0.00003348184],"domain_scores_gemma":[0.9984187,0.0005051819,0.00008763196,0.00035227515,0.00053790235,0.00009836821],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011700641,0.0015228522,0.0018746351,0.0033410517,0.00053529255,0.0024507362,0.0015619284,0.0009381562,0.034500573],"category_scores_gemma":[0.002675262,0.0008028977,0.0011572306,0.0059812376,0.0006507284,0.0033656384,0.002224133,0.002506597,0.037882186],"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":[0.000031455405,0.000060656344,0.00022666626,0.00081775995,0.000054435655,0.000072197276,0.000056005363,0.0014098672,0.0032151975,0.014543715,0.1620678,0.81744426],"study_design_scores_gemma":[0.000014336209,0.000089243644,0.0012366207,0.00045294652,0.00006669967,0.0009159654,0.00005256941,0.014843567,0.0042384667,0.07760353,0.9004437,0.000042359952],"about_ca_topic_score_codex":0.00028338848,"about_ca_topic_score_gemma":0.00042611486,"teacher_disagreement_score":0.034500573,"about_ca_system_score_codex":0.0004364488,"about_ca_system_score_gemma":0.00093186373,"threshold_uncertainty_score":0.11541593},"labels":[],"label_agreement":null},{"id":"W4298150609","doi":"10.1007/978-3-642-37456-2","title":"Advances in Knowledge Discovery and Data Mining","year":2013,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":51,"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":"Knowledge extraction; Computer science; Data science; Volume (thermodynamics); Data mining; Set (abstract data type); Information retrieval","score_opus":0.023846120441123983,"score_gpt":0.2973966520615528,"score_spread":0.2735505316204288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298150609","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014084355,0.7895001,0.14860304,0.0063447184,0.004887012,0.00010456203,0.00073951203,0.0009801971,0.04743232],"genre_scores_gemma":[0.015708245,0.7455308,0.16322547,0.0032566157,0.00847931,0.00019104542,0.0020166459,0.00036362253,0.061228223],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99853957,0.00018967081,0.00012673478,0.00019010362,0.0008955327,0.000058410715],"domain_scores_gemma":[0.9949411,0.0035774314,0.00021476382,0.00044570983,0.0006728978,0.00014806546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021167668,0.0014839132,0.0025155905,0.0047861757,0.00045364624,0.003895807,0.0021583235,0.0012465667,0.011350637],"category_scores_gemma":[0.0069108256,0.00069579354,0.0010641153,0.0098451795,0.0014640467,0.006687002,0.0019551867,0.0031594876,0.011038498],"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":[0.000041188312,0.00008400292,0.00033082627,0.0038844945,0.0001365304,0.00009426103,0.00010329866,0.001737464,0.00096796383,0.05777434,0.121855296,0.8129903],"study_design_scores_gemma":[0.000018975175,0.00004911906,0.00062462356,0.00105531,0.00010127387,0.00056442845,0.00007992665,0.006717671,0.0011367323,0.21857935,0.77103627,0.00003623087],"about_ca_topic_score_codex":0.0006731139,"about_ca_topic_score_gemma":0.00088250963,"teacher_disagreement_score":0.011350637,"about_ca_system_score_codex":0.0009095983,"about_ca_system_score_gemma":0.0016283466,"threshold_uncertainty_score":0.037971675},"labels":[],"label_agreement":null},{"id":"W4299624165","doi":"10.1109/icdm.2012.4","title":"Message from General Co-chairs","year":2012,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Computer security","score_opus":0.02124554834545745,"score_gpt":0.27906833859475644,"score_spread":0.257822790249299,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4299624165","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00038245984,0.0028647583,0.00043937666,0.61448383,0.36778158,0.00007816111,0.000716307,0.00028764026,0.012965784],"genre_scores_gemma":[0.0059355497,0.0034783657,0.00062459434,0.62314117,0.128448,0.0002472351,0.00079249265,0.0003125526,0.23702005],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99801093,0.0002973903,0.00013220485,0.0004059023,0.0008932517,0.00026042724],"domain_scores_gemma":[0.9903218,0.00094447826,0.00031164303,0.00026782783,0.0052833324,0.0028708356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002724607,0.0009427691,0.0011678098,0.00072623347,0.0021755944,0.00426506,0.0016454487,0.011128769,0.08240439],"category_scores_gemma":[0.013800088,0.0004102685,0.0009079571,0.0006433523,0.0008095758,0.0031928031,0.002166065,0.013104531,0.08488797],"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":[0.00001453769,0.000005193568,0.000058568905,0.000016939499,0.0000014370931,0.000022650096,0.0000064676005,0.0000069564867,0.000020445237,0.00015645924,0.99734986,0.0023405463],"study_design_scores_gemma":[0.000018454726,0.000022248294,0.00055500964,0.000077731165,0.0000061311257,0.00015220663,0.00010593893,0.000059637496,0.00011514432,0.00047720489,0.9983918,0.0000184492],"about_ca_topic_score_codex":0.0038651552,"about_ca_topic_score_gemma":0.00565237,"teacher_disagreement_score":0.08240439,"about_ca_system_score_codex":0.0022999241,"about_ca_system_score_gemma":0.004248515,"threshold_uncertainty_score":0.27567017},"labels":[],"label_agreement":null},{"id":"W4299650563","doi":"","title":"Mining Multimedia and Complex Data, {KDD} Workshop {MDM/KDD} 2002, {PAKDD} Workshop {KDMCD} 2002, Revised Papers","year":2003,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Knowledge extraction; Data science; Information retrieval; Data mining; World Wide Web","score_opus":0.04430512630369273,"score_gpt":0.27277502539490894,"score_spread":0.2284698990912162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4299650563","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040291812,0.092379466,0.7600916,0.03544915,0.022590915,0.00058981706,0.017819718,0.009465475,0.021322021],"genre_scores_gemma":[0.15661341,0.07206478,0.6002994,0.0038465974,0.012597706,0.00056362443,0.04313485,0.0022861506,0.108593434],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99874145,0.00020306464,0.0001512228,0.00028641513,0.00055395183,0.00006395614],"domain_scores_gemma":[0.9949045,0.002246709,0.00015518955,0.00076238724,0.0015765516,0.00035465055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002446917,0.0012652937,0.0020027433,0.003856012,0.0012560172,0.0054771057,0.0019536354,0.0015204897,0.011665495],"category_scores_gemma":[0.013977761,0.0011203672,0.00073076796,0.003617233,0.0010131337,0.005139582,0.0014611767,0.0016963222,0.0046135974],"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":[0.00039466284,0.00023183158,0.0020292052,0.0009089337,0.00014491084,0.00021905302,0.00023634995,0.006167845,0.005046659,0.010300577,0.5325323,0.4417877],"study_design_scores_gemma":[0.00020264195,0.00029825012,0.017045412,0.0007783759,0.00047168808,0.0016717755,0.0010158415,0.19621746,0.033569384,0.1297213,0.61881584,0.000192071],"about_ca_topic_score_codex":0.007679653,"about_ca_topic_score_gemma":0.013847504,"teacher_disagreement_score":0.011665495,"about_ca_system_score_codex":0.0012993718,"about_ca_system_score_gemma":0.0020512727,"threshold_uncertainty_score":0.03902495},"labels":[],"label_agreement":null},{"id":"W4299924846","doi":"","title":"Reducing Subject Tree Browsing Complexity","year":2013,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Interdisciplinary Research in Music Media and Technology; McGill University","funders":"","keywords":"Subject (documents); Tree (set theory); Computer science; World Wide Web; Mathematics; Combinatorics","score_opus":0.03447510554845135,"score_gpt":0.2524591331642551,"score_spread":0.21798402761580377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4299924846","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07565986,0.010233887,0.79226524,0.01137548,0.0026876966,0.00057829596,0.008689521,0.024528114,0.07398183],"genre_scores_gemma":[0.27016535,0.006073341,0.60922706,0.0029597944,0.0020166975,0.00043168102,0.02162232,0.008143018,0.079360746],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968316,0.0007723575,0.00021119088,0.0006082016,0.0011196625,0.0004570613],"domain_scores_gemma":[0.9803603,0.008874063,0.00057452876,0.007337704,0.0019815739,0.00087175623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025244518,0.0009898272,0.0024740312,0.0024515418,0.0019483023,0.004655665,0.0021811489,0.0013506962,0.043052513],"category_scores_gemma":[0.019064208,0.0009070102,0.0016454769,0.0060296482,0.0012412729,0.012215909,0.004697422,0.0032274474,0.015578695],"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":[0.0005716052,0.0005030466,0.0028477362,0.0007009229,0.00016569222,0.0002638712,0.0005674263,0.01207407,0.00811378,0.11451348,0.31958202,0.54009634],"study_design_scores_gemma":[0.00016471217,0.00019732706,0.0027510317,0.00019220696,0.00031060074,0.0007755746,0.000538529,0.19461277,0.007100971,0.5845709,0.20870864,0.0000766824],"about_ca_topic_score_codex":0.0052151955,"about_ca_topic_score_gemma":0.012712907,"teacher_disagreement_score":0.043052513,"about_ca_system_score_codex":0.0020449676,"about_ca_system_score_gemma":0.0037751517,"threshold_uncertainty_score":0.14402503},"labels":[],"label_agreement":null},{"id":"W4300599851","doi":"10.21428/594757db.77e18bfa","title":"A Hoeffding Decision Tree Based Approach for Soil Classification","year":2022,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Athabasca University","funders":"","keywords":"Decision tree; Computer science; Machine learning; Statistical classification; Data mining; Java; Terminology; Artificial intelligence","score_opus":0.050764090621630245,"score_gpt":0.2798202835295735,"score_spread":0.22905619290794327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300599851","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029697405,0.0005968701,0.9632758,0.00036109626,0.00014250634,0.0004620787,0.0010681282,0.0014084302,0.0029875897],"genre_scores_gemma":[0.17026137,0.0004008159,0.82348794,0.00022447138,0.000073767,0.0003809736,0.0021325808,0.000106518666,0.0029314908],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99703985,0.0007376849,0.00037584628,0.0006816851,0.0009782247,0.00018675464],"domain_scores_gemma":[0.99437803,0.0035474931,0.00023661459,0.0003014252,0.0014399486,0.00009648269],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039879214,0.0010340879,0.001237014,0.004307735,0.00096963556,0.0018053951,0.0022775938,0.0016469965,0.0034056522],"category_scores_gemma":[0.011803361,0.00048251802,0.0015328754,0.0039926516,0.00051618274,0.0023915966,0.00079226465,0.001489382,0.0013612242],"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":[0.00037663485,0.0003027023,0.010204543,0.00034417055,0.00021378922,0.00033123564,0.00025848942,0.24165508,0.0042194943,0.009504218,0.0079342285,0.72465545],"study_design_scores_gemma":[0.00004533238,0.0002419391,0.0023829397,0.0000780416,0.00007924941,0.000295809,0.00015037922,0.970851,0.003438412,0.015222347,0.0071641374,0.0000504796],"about_ca_topic_score_codex":0.013970035,"about_ca_topic_score_gemma":0.01854506,"teacher_disagreement_score":0.013970035,"about_ca_system_score_codex":0.0012899485,"about_ca_system_score_gemma":0.0018822835,"threshold_uncertainty_score":0.027777493},"labels":[],"label_agreement":null},{"id":"W4301167073","doi":"10.4018/978-1-59904-951-9.ch036","title":"A Framework for Efficient Association Rule Mining in XML Data","year":2008,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; XML; Association rule learning; Efficient XML Interchange; Data mining; XML database; Streaming XML; XML validation; Constraint (computer-aided design); Generalization; Information retrieval; Selection (genetic algorithm); XML Schema (W3C); Tree (set theory); XML Encryption; Database; Artificial intelligence; World Wide Web","score_opus":0.047395535558772524,"score_gpt":0.2965704105238691,"score_spread":0.2491748749650966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4301167073","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021470213,0.00028696668,0.9976897,0.00012719844,0.000021166688,0.00009800921,0.00020048945,0.0011744904,0.0001871362],"genre_scores_gemma":[0.003795637,0.00035881216,0.99455714,0.0000929513,0.000032282438,0.00024246168,0.00056243053,0.00005568848,0.00030263493],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9927578,0.0028889035,0.0009953072,0.0010067683,0.002192065,0.00015914437],"domain_scores_gemma":[0.9936166,0.0037946703,0.00047589178,0.001321667,0.00064390304,0.00014732867],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010684338,0.0016036974,0.0023031083,0.0054637166,0.0011607158,0.0036395814,0.0047808546,0.001967565,0.0036096228],"category_scores_gemma":[0.015689328,0.0014689484,0.004148814,0.006219904,0.0011075177,0.0048019392,0.0033138539,0.00376078,0.004066911],"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":[0.00020053734,0.0003300612,0.0018634058,0.0020279926,0.00076743803,0.0014408686,0.0005884858,0.085353754,0.007847836,0.18739922,0.02752099,0.6846595],"study_design_scores_gemma":[0.00013216566,0.00021213289,0.0008598777,0.00057707075,0.0001811951,0.0025319408,0.00019441993,0.63954496,0.007380503,0.22917692,0.119066276,0.00014245896],"about_ca_topic_score_codex":0.0018116954,"about_ca_topic_score_gemma":0.0025924128,"teacher_disagreement_score":0.010684338,"about_ca_system_score_codex":0.0008120655,"about_ca_system_score_gemma":0.0018947213,"threshold_uncertainty_score":0.056504846},"labels":[],"label_agreement":null},{"id":"W4302149421","doi":"","title":"New design approach to handle spatial vagueness in Spatial OLAP datacubes: Application to agri-environmental data","year":2015,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Online analytical processing; Spatial analysis; Vagueness; Computer science; Data mining; Computer graphics (images); Geography; Artificial intelligence; Data warehouse; Fuzzy logic; Remote sensing","score_opus":0.04033601148786997,"score_gpt":0.25227382507989293,"score_spread":0.21193781359202296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4302149421","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023023123,0.00005290795,0.99646276,0.00013784705,0.000023971135,0.00007558799,0.00006261822,0.0003846198,0.00049736444],"genre_scores_gemma":[0.05920349,0.00015652203,0.9385455,0.0001406936,0.00004292722,0.00031872568,0.0003204408,0.0001601845,0.0011115032],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99611294,0.001346369,0.00043922567,0.0005047917,0.0014290247,0.00016758303],"domain_scores_gemma":[0.994251,0.0018387486,0.00047323076,0.0013386504,0.0017961883,0.00030212683],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052878885,0.0008166467,0.0009847999,0.0012942306,0.0010104111,0.0032622928,0.0022384492,0.0012152137,0.0029008149],"category_scores_gemma":[0.009648113,0.00070080394,0.0014527183,0.0023186356,0.001420932,0.004377124,0.0042361813,0.0018612233,0.0009222404],"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":[0.00059010816,0.0004074314,0.0063408376,0.0010726687,0.00034065256,0.0011968566,0.0036978123,0.34831235,0.04702307,0.2110103,0.01382364,0.36618423],"study_design_scores_gemma":[0.000059501366,0.0001631889,0.00043562136,0.00006965223,0.0000642237,0.0004263906,0.00055962766,0.88632023,0.0142906895,0.056791183,0.040755473,0.00006417399],"about_ca_topic_score_codex":0.0014939813,"about_ca_topic_score_gemma":0.0017774133,"teacher_disagreement_score":0.0052878885,"about_ca_system_score_codex":0.00094361376,"about_ca_system_score_gemma":0.0013804112,"threshold_uncertainty_score":0.027965367},"labels":[],"label_agreement":null},{"id":"W4302614395","doi":"10.1186/s40537-022-00608-0","title":"Adaptive multiple imputations of missing values using the class center","year":2022,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":21,"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 Manitoba","funders":"Thailand Research Fund; Natural Sciences and Engineering Research Council of Canada; Khon Kaen University","keywords":"Imputation (statistics); Missing data; Categorical variable; Computer science; Data mining; Artificial intelligence; Machine learning","score_opus":0.19522271418559686,"score_gpt":0.33417412123125606,"score_spread":0.1389514070456592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4302614395","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017183691,0.0004366473,0.9798456,0.00018976547,0.00012355436,0.00010953589,0.00020389038,0.0014124522,0.0004948528],"genre_scores_gemma":[0.32314548,0.0003264682,0.6731293,0.00024622923,0.00019924444,0.00031362998,0.0012547814,0.00025599406,0.001128894],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9922104,0.0034319737,0.0004648808,0.0019964112,0.001531445,0.00036489885],"domain_scores_gemma":[0.9765385,0.010851828,0.0024089578,0.0049863355,0.004696288,0.0005181684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011393767,0.0010427659,0.0023542058,0.0024612292,0.0014411117,0.0015378892,0.004029055,0.0014574614,0.0021795346],"category_scores_gemma":[0.026362704,0.0005064394,0.0022733829,0.0030634168,0.0009679542,0.0019625756,0.0019139297,0.002583719,0.00078852585],"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":[0.0017836969,0.00069213036,0.028491167,0.00050950074,0.0009569022,0.00048705257,0.00072631554,0.1839453,0.006714864,0.02013231,0.014357018,0.7412037],"study_design_scores_gemma":[0.00008864654,0.00015867273,0.0033539387,0.00006567504,0.0001467606,0.0002173655,0.00014064276,0.9649383,0.009794086,0.01596033,0.0050566783,0.00007893913],"about_ca_topic_score_codex":0.0043479395,"about_ca_topic_score_gemma":0.0032909706,"teacher_disagreement_score":0.011393767,"about_ca_system_score_codex":0.0009786697,"about_ca_system_score_gemma":0.0025983935,"threshold_uncertainty_score":0.06025672},"labels":[],"label_agreement":null},{"id":"W4311079932","doi":"10.1145/3575637.3575645","title":"Finding Multidimensional Simpson's Paradox","year":2022,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; Burnaby Hospital","funders":"","keywords":"Computer science; Curse of dimensionality; Multidimensional data; Data science; Phenomenon; Data mining; Machine learning; Epistemology","score_opus":0.04358511030504669,"score_gpt":0.2740753601844798,"score_spread":0.23049024987943312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311079932","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48575655,0.0029588745,0.48872963,0.0068387124,0.0005146546,0.00016499004,0.0010064741,0.00039842143,0.013631698],"genre_scores_gemma":[0.89724433,0.0008312762,0.098454446,0.0009243557,0.00029593517,0.00015430403,0.0006311869,0.000074774056,0.0013893748],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99411917,0.0018854856,0.0005717825,0.0014461897,0.0015969885,0.00038037525],"domain_scores_gemma":[0.9500843,0.036470424,0.0050537284,0.0041869036,0.0027456132,0.0014590578],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0077705747,0.0006511525,0.002227119,0.004647752,0.00303803,0.0046917857,0.001790905,0.0019412054,0.0029698492],"category_scores_gemma":[0.07232878,0.0006749765,0.0014231299,0.0043415697,0.004138089,0.008352136,0.004317204,0.0036803198,0.0002700079],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003250371,0.00015283062,0.057932362,0.0007496676,0.00042330657,0.0019731652,0.0029789885,0.019592771,0.0027345286,0.79937786,0.0127262445,0.10103331],"study_design_scores_gemma":[0.00004030241,0.00003330301,0.0039059925,0.000076447286,0.00003841929,0.0008158768,0.00064408965,0.068817675,0.00074244046,0.92235386,0.0024592592,0.00007230094],"about_ca_topic_score_codex":0.001140653,"about_ca_topic_score_gemma":0.0009145209,"teacher_disagreement_score":0.0077705747,"about_ca_system_score_codex":0.0017554732,"about_ca_system_score_gemma":0.001618492,"threshold_uncertainty_score":0.041095197},"labels":[],"label_agreement":null},{"id":"W4312121787","doi":"10.48550/arxiv.2212.11364","title":"A Projected Upper Bound for Mining High Utility Patterns from Interval-Based Event Sequences","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Pruning; Interval (graph theory); Upper and lower bounds; Constraint (computer-aided design); Event (particle physics); Computer science; Branch and bound; Data mining; Mathematical optimization; Algorithm; Mathematics; Combinatorics","score_opus":0.09598394824550048,"score_gpt":0.23208740901450042,"score_spread":0.13610346076899993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312121787","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019061387,0.0007663588,0.977693,0.0003249052,0.000032766664,0.00012264278,0.00045941706,0.0007758251,0.00076363975],"genre_scores_gemma":[0.2661028,0.00092644687,0.7278868,0.00042140568,0.00018092709,0.0006417531,0.0024498855,0.00018167263,0.0012083123],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945034,0.0015141134,0.0005062373,0.0011559307,0.001953502,0.00036689098],"domain_scores_gemma":[0.9777165,0.016792078,0.0011661076,0.0017193027,0.002169176,0.00043688394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005364334,0.001216811,0.0024352726,0.0035022185,0.00081121206,0.0031725003,0.0033423842,0.0017372825,0.003051674],"category_scores_gemma":[0.037569936,0.0010251909,0.0014489423,0.004640324,0.001368433,0.004458521,0.0028291966,0.0026986096,0.00091627747],"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":[0.0010890381,0.0005083415,0.009704825,0.0008010146,0.00030620987,0.00061121455,0.00046182857,0.5263621,0.010178327,0.039357822,0.007120707,0.40349856],"study_design_scores_gemma":[0.000026714122,0.000080759804,0.00047007712,0.000047026162,0.000020731222,0.00016022545,0.000029515519,0.9796255,0.00217271,0.01633367,0.0010184044,0.000014635814],"about_ca_topic_score_codex":0.0016543753,"about_ca_topic_score_gemma":0.0021859976,"teacher_disagreement_score":0.005364334,"about_ca_system_score_codex":0.0011931146,"about_ca_system_score_gemma":0.0021023394,"threshold_uncertainty_score":0.028369606},"labels":[],"label_agreement":null},{"id":"W4313729831","doi":"10.1145/1281192.1327955","title":"Second Workshop on Data Mining Case Studies and Practice Prize","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Data science","score_opus":0.14937983619032746,"score_gpt":0.40579232064668497,"score_spread":0.2564124844563575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313729831","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031714115,0.035878494,0.184077,0.20246126,0.10079637,0.001448963,0.009067868,0.0025670186,0.43198892],"genre_scores_gemma":[0.08194231,0.011864004,0.07232195,0.004951625,0.011018323,0.0006022002,0.0083341645,0.0010489315,0.80791646],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99762255,0.0007170896,0.00013808449,0.00037672932,0.0008400935,0.00030540695],"domain_scores_gemma":[0.99015397,0.0027549544,0.00017794235,0.0010571955,0.0030687754,0.0027871218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008616212,0.00083272514,0.0013422143,0.0028360605,0.0014268686,0.005262619,0.002801894,0.0020845286,0.09478795],"category_scores_gemma":[0.009769487,0.000387708,0.0010404895,0.0023316536,0.00088429626,0.0031572296,0.0031869416,0.0024990493,0.023078715],"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":[0.00043264762,0.00018173477,0.0005020289,0.00025593123,0.000037445763,0.00022156817,0.00021038501,0.0008529475,0.0010474657,0.01736548,0.75156593,0.22732642],"study_design_scores_gemma":[0.000080498336,0.00019467124,0.0015548042,0.00022839433,0.000036333964,0.00042405564,0.00041493602,0.0029904298,0.0013766042,0.034040406,0.9586256,0.000033092325],"about_ca_topic_score_codex":0.0020433967,"about_ca_topic_score_gemma":0.004883582,"teacher_disagreement_score":0.09478795,"about_ca_system_score_codex":0.0023320077,"about_ca_system_score_gemma":0.0031987973,"threshold_uncertainty_score":0.3170973},"labels":[],"label_agreement":null},{"id":"W4313906919","doi":"10.1145/3257389","title":"Session details: Data mining track","year":2009,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Session (web analytics); Computer science; Track (disk drive); World Wide Web; Operating system","score_opus":0.06521110196041942,"score_gpt":0.31946098597653416,"score_spread":0.25424988401611476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313906919","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022143133,0.005458461,0.019643124,0.024761759,0.034419205,0.0032030314,0.24648674,0.03048599,0.6333273],"genre_scores_gemma":[0.0048153913,0.0022871993,0.0046797213,0.0023736465,0.0040623494,0.0007274432,0.07485683,0.0024567945,0.9037406],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985676,0.00019751376,0.000105469524,0.0003907363,0.00057811086,0.00016054539],"domain_scores_gemma":[0.99130684,0.0017953034,0.0003249551,0.001905489,0.00251636,0.0021510024],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0036552364,0.0017742376,0.0034223008,0.0029096513,0.0028303512,0.008440513,0.0026638538,0.0039703874,0.8507874],"category_scores_gemma":[0.00999896,0.00075192953,0.0016470781,0.0047681616,0.00036872196,0.0041124127,0.0032811922,0.003053057,0.8142034],"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":[0.000087950066,0.00004706896,0.000108342836,0.000098713615,0.000008299604,0.0000119962615,0.000006139409,0.000026582045,0.00033416497,0.00026101523,0.97652584,0.02248384],"study_design_scores_gemma":[0.000060545033,0.000058162932,0.0006464006,0.00006765169,0.000012762926,0.000040235143,0.000019207282,0.00034067337,0.0007155251,0.00070656644,0.997317,0.000015218893],"about_ca_topic_score_codex":0.0023769033,"about_ca_topic_score_gemma":0.0049293987,"teacher_disagreement_score":0.1492126,"about_ca_system_score_codex":0.0013176021,"about_ca_system_score_gemma":0.002966983,"threshold_uncertainty_score":0.21283358},"labels":[],"label_agreement":null},{"id":"W4316021211","doi":"10.1109/icic56845.2022.10006956","title":"A Time-Window Approach to Recommending Emerging and On-the-rise Items","year":2022,"lang":"en","type":"article","venue":"2022 Seventh International Conference on Informatics and Computing (ICIC)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Window (computing); Database transaction; Computer science; Association rule learning; Recommender system; Quarter (Canadian coin); Transaction data; Data mining; Information retrieval; Database; World Wide Web","score_opus":0.03702280384158295,"score_gpt":0.2732764953356102,"score_spread":0.23625369149402725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4316021211","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14866695,0.0054787844,0.8322914,0.0007183251,0.00042332543,0.00097346527,0.0035036977,0.00401371,0.0039302344],"genre_scores_gemma":[0.42698848,0.0017809536,0.5603307,0.00023333574,0.00022790706,0.00038059242,0.0034551497,0.00012398491,0.0064789285],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99744236,0.00030989223,0.00041143884,0.0009845045,0.00070076995,0.0001509502],"domain_scores_gemma":[0.99648917,0.0014242649,0.00041182572,0.00043306607,0.0010369768,0.00020477809],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002052783,0.0012641413,0.0016671894,0.00499883,0.0008172067,0.0014203705,0.0020221197,0.0011603837,0.0019387347],"category_scores_gemma":[0.005765083,0.0006661078,0.0015115897,0.0054058484,0.00030989587,0.0028629492,0.0006368145,0.0012232093,0.0012876426],"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":[0.0015322372,0.0012242856,0.03825101,0.00062587333,0.0008110445,0.0006067616,0.0006646173,0.04043706,0.020161927,0.0046127755,0.009306255,0.88176614],"study_design_scores_gemma":[0.00013183862,0.0014403912,0.02359872,0.00012721286,0.00052529026,0.0013101622,0.00039895793,0.93250924,0.0154838255,0.0060154544,0.018305311,0.00015360712],"about_ca_topic_score_codex":0.016555551,"about_ca_topic_score_gemma":0.019781724,"teacher_disagreement_score":0.016555551,"about_ca_system_score_codex":0.0006218944,"about_ca_system_score_gemma":0.0011916993,"threshold_uncertainty_score":0.032918394},"labels":[],"label_agreement":null},{"id":"W4317565500","doi":"10.4018/978-1-7998-9220-5.ch075","title":"Big Data Visualization of Association Rules and Frequent Patterns","year":2023,"lang":"en","type":"book-chapter","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Big data; Data science; Visualization; Computer science; Variety (cybernetics); Visual analytics; Encyclopedia; Association rule learning; Data visualization; Analytics; Data mining; Artificial intelligence","score_opus":0.08886069232367587,"score_gpt":0.2944552107717119,"score_spread":0.205594518448036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317565500","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018535776,0.058805343,0.6976735,0.006548793,0.004199683,0.00041330952,0.022712931,0.022606261,0.16850437],"genre_scores_gemma":[0.09548569,0.04087042,0.73592603,0.001588037,0.0013395696,0.0005419181,0.024153512,0.0027065715,0.0973883],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993771,0.0001310319,0.000053310367,0.000106462176,0.00029434843,0.000037795424],"domain_scores_gemma":[0.9977847,0.0013051644,0.0001537273,0.00019713317,0.00047605857,0.00008338901],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082024507,0.0011548795,0.0005843633,0.0043058,0.000453114,0.0035989045,0.0013262471,0.00077032106,0.026848102],"category_scores_gemma":[0.0036623164,0.0005547844,0.00085889694,0.0062772804,0.0004459698,0.0029094908,0.0012130031,0.0011922835,0.0066310386],"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":[0.00022291277,0.000069070506,0.0018467708,0.0018523489,0.00012086777,0.00085049815,0.00083299476,0.009280229,0.005210363,0.08771597,0.3572914,0.53470665],"study_design_scores_gemma":[0.000050932755,0.000066418586,0.0037448634,0.00093332224,0.000067512025,0.002556324,0.00053636095,0.08869409,0.0053867544,0.15382454,0.74403745,0.000101455465],"about_ca_topic_score_codex":0.0018259517,"about_ca_topic_score_gemma":0.0023235725,"teacher_disagreement_score":0.026848102,"about_ca_system_score_codex":0.00044673742,"about_ca_system_score_gemma":0.00062306516,"threshold_uncertainty_score":0.089815855},"labels":[],"label_agreement":null},{"id":"W4317707907","doi":"10.4018/978-1-6684-3662-2.ch033","title":"Big Data Analytics and Mining for Knowledge Discovery","year":2021,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Big data; Computer science; Data science; Knowledge extraction; Analytics; Variety (cybernetics); Data mining; Data analysis; Artificial intelligence","score_opus":0.10090013649827292,"score_gpt":0.3019087860380977,"score_spread":0.20100864953982475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317707907","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016004496,0.3321143,0.28501323,0.024853064,0.007848672,0.00060262904,0.00453243,0.0044038123,0.33903146],"genre_scores_gemma":[0.027195834,0.36663392,0.32964635,0.013497219,0.0086507015,0.0011717272,0.010237316,0.002395867,0.2405711],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99803394,0.0003794865,0.00012040525,0.00036449244,0.001009147,0.00009249072],"domain_scores_gemma":[0.9977482,0.0014321667,0.00010219096,0.00039265363,0.0002105481,0.00011431734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017746954,0.0021072899,0.0016792567,0.004281986,0.0010932382,0.008494415,0.0029318752,0.002779612,0.03404741],"category_scores_gemma":[0.003866312,0.0010470604,0.0013341671,0.010136692,0.0029919269,0.011189901,0.003703127,0.004446302,0.028641641],"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":[0.00003058185,0.000048617054,0.0002724183,0.0029646656,0.00010364697,0.00015435815,0.00045699757,0.0024668726,0.0007975593,0.3478802,0.345624,0.29920015],"study_design_scores_gemma":[0.000007001294,0.00001234177,0.00023871462,0.00076405617,0.000012051263,0.0002121417,0.000115195,0.0017657607,0.00021829712,0.20976348,0.78687096,0.000019982108],"about_ca_topic_score_codex":0.0010867298,"about_ca_topic_score_gemma":0.0013615076,"teacher_disagreement_score":0.03404741,"about_ca_system_score_codex":0.0017973464,"about_ca_system_score_gemma":0.002573803,"threshold_uncertainty_score":0.11389989},"labels":[],"label_agreement":null},{"id":"W4317826942","doi":"10.1109/iv56949.2022.00045","title":"Data. Information and Knowledge Visualization for Frequent Patterns","year":2022,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; University of Manitoba","keywords":"Computer science; Visualization; Big data; Data visualization; Data mining; Data science; Information visualization; Variety (cybernetics); Knowledge extraction; Business intelligence; Data modeling; Information retrieval; Database; Artificial intelligence","score_opus":0.04375335378064978,"score_gpt":0.319662708336515,"score_spread":0.27590935455586524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317826942","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015073961,0.0028973406,0.87589127,0.0061782612,0.0011250827,0.00039425082,0.033094946,0.037332613,0.028012201],"genre_scores_gemma":[0.14747183,0.0018366653,0.81886494,0.00079369405,0.00028476768,0.00043407478,0.018099256,0.0023661705,0.009848636],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99899656,0.0002576685,0.00011670843,0.00019880038,0.00037465026,0.000055593613],"domain_scores_gemma":[0.9970818,0.0012147062,0.00032992917,0.0006249356,0.0006256213,0.00012301703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096463354,0.0010299408,0.00043581353,0.0033795792,0.0006775874,0.003000633,0.0008539342,0.0011094343,0.020424724],"category_scores_gemma":[0.008001583,0.00040553705,0.00073369313,0.0038034297,0.00038135715,0.0026678422,0.0018456102,0.0013133186,0.005578944],"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":[0.0005872821,0.00014433706,0.0039699944,0.0017980637,0.00013061459,0.0007155154,0.0015851061,0.010384045,0.014897641,0.13953033,0.24660577,0.57965136],"study_design_scores_gemma":[0.00014630552,0.00012410384,0.003862518,0.0004923315,0.00008843854,0.0020236399,0.0009928937,0.16736962,0.018635273,0.2567533,0.549392,0.000119626755],"about_ca_topic_score_codex":0.001649546,"about_ca_topic_score_gemma":0.0019408163,"teacher_disagreement_score":0.020424724,"about_ca_system_score_codex":0.00043642777,"about_ca_system_score_gemma":0.0006837594,"threshold_uncertainty_score":0.06832749},"labels":[],"label_agreement":null},{"id":"W4317826954","doi":"10.1109/iv56949.2022.00062","title":"Visualization and Visual Knowledge Discovery from Big Uncertain Data","year":2022,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":11,"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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; University of Manitoba","keywords":"Big data; Computer science; Visualization; Knowledge extraction; Data science; Data visualization; Data mining; Information visualization; Data discovery; Variety (cybernetics); Artificial intelligence; World Wide Web","score_opus":0.058450039386147824,"score_gpt":0.33269899401738584,"score_spread":0.274248954631238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317826954","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01373209,0.00089196,0.97717685,0.002114972,0.000114285365,0.00009547115,0.00094032474,0.0028353217,0.0020986553],"genre_scores_gemma":[0.24801283,0.002130643,0.7449645,0.00041488608,0.0002105026,0.00017239661,0.002302115,0.00038037242,0.0014117268],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99764305,0.00077429216,0.00021655762,0.00038305958,0.0008419535,0.0001409381],"domain_scores_gemma":[0.9905149,0.005393443,0.00088323356,0.0012527913,0.0015469872,0.00040867346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031177104,0.0011482314,0.001065993,0.004738145,0.0007959438,0.0053343656,0.001652989,0.0017270617,0.0028099287],"category_scores_gemma":[0.014503934,0.00078479754,0.0013571661,0.0031629286,0.0011389652,0.0050915265,0.0049175452,0.0019158025,0.00063973723],"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":[0.0014627515,0.00027986625,0.00780552,0.002184973,0.00041685213,0.0023244228,0.0062107793,0.20139077,0.041812673,0.11196347,0.038214583,0.58593327],"study_design_scores_gemma":[0.000061389816,0.00009622256,0.0016846928,0.00020706243,0.00006977479,0.0008350904,0.0013247408,0.79024804,0.015907396,0.16286516,0.026597729,0.000102616985],"about_ca_topic_score_codex":0.0020290192,"about_ca_topic_score_gemma":0.002207814,"teacher_disagreement_score":0.0053343656,"about_ca_system_score_codex":0.00079605717,"about_ca_system_score_gemma":0.00089140824,"threshold_uncertainty_score":0.016488254},"labels":[],"label_agreement":null},{"id":"W4318829313","doi":"10.2139/ssrn.4344431","title":"Informationally Robust Cheap-Talk","year":2023,"lang":"en","type":"article","venue":"SSRN Electronic Journal","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":"University of Toronto","funders":"","keywords":"Cheap talk; Law and economics; Computer science; Mathematical economics; Business; Economics","score_opus":0.013685276979583421,"score_gpt":0.23884124682807434,"score_spread":0.22515596984849093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318829313","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07753992,0.0016925558,0.8616297,0.009674654,0.00091064174,0.00019626941,0.0015956888,0.0041865217,0.042574115],"genre_scores_gemma":[0.88955736,0.00078234053,0.07412343,0.0025169929,0.0016165795,0.00028399721,0.001100973,0.0010343543,0.028984018],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9900253,0.0046059284,0.00043701456,0.0017188034,0.0020176768,0.0011952585],"domain_scores_gemma":[0.9444953,0.03732487,0.0022324102,0.012128448,0.0025379453,0.0012810018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010756589,0.0018717705,0.003579493,0.0024054605,0.0025685497,0.006172033,0.0036474075,0.005866034,0.021836486],"category_scores_gemma":[0.0758411,0.0017523466,0.0019901718,0.0018914128,0.0048433477,0.009153784,0.0071487227,0.005488642,0.008828963],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032890267,0.00038791215,0.0017997473,0.00063897675,0.00042578953,0.00062730006,0.0004743041,0.068619855,0.007446915,0.741742,0.039969992,0.1345782],"study_design_scores_gemma":[0.00010934142,0.00016173892,0.0005479238,0.000048406957,0.00008365839,0.00030638886,0.00011230595,0.14619954,0.0029834257,0.8465343,0.0028395448,0.00007336273],"about_ca_topic_score_codex":0.000623224,"about_ca_topic_score_gemma":0.0005627118,"teacher_disagreement_score":0.021836486,"about_ca_system_score_codex":0.0013620666,"about_ca_system_score_gemma":0.0023426942,"threshold_uncertainty_score":0.07305032},"labels":[],"label_agreement":null},{"id":"W4320008341","doi":"10.1007/978-3-031-20738-9_91","title":"An Analysis of College Students’ Behavior Based on Positive and Negative Association Rules","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes on data engineering and communications technologies","topic":"Data Mining Algorithms and Applications","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":"Association (psychology); Psychology; Association rule learning; Social psychology; Computer science; Artificial intelligence; Psychotherapist","score_opus":0.02784150082564369,"score_gpt":0.28654920288227886,"score_spread":0.2587077020566352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320008341","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9816368,0.0002492475,0.014117562,0.00016287356,0.000036806035,0.000046312263,0.00094924564,0.0002116539,0.0025894728],"genre_scores_gemma":[0.98651683,0.0000738764,0.011209743,0.000028836866,0.000027571468,0.000024181347,0.0011173789,0.0000111223735,0.0009904202],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99922657,0.00024009247,0.00007467348,0.000162311,0.00023550233,0.000060885894],"domain_scores_gemma":[0.9937583,0.004975999,0.00032066545,0.00017463135,0.0005529254,0.00021754662],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012275014,0.00042675366,0.0004536759,0.002696698,0.0003377834,0.0009303892,0.00049652933,0.00039517132,0.001646135],"category_scores_gemma":[0.0045974455,0.00013766527,0.00071540725,0.001546865,0.00022794894,0.0005363538,0.0002975942,0.0004946204,0.00052017753],"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":[0.0016392813,0.00073493697,0.7771775,0.000109128145,0.00039614958,0.0004228421,0.0002938377,0.0064799255,0.0072081373,0.00095638447,0.0018562535,0.20272551],"study_design_scores_gemma":[0.00006411039,0.0011177879,0.6669575,0.000048426904,0.0004567817,0.000997761,0.00092470826,0.31938842,0.005331391,0.0027583044,0.0018873316,0.000067457724],"about_ca_topic_score_codex":0.004092508,"about_ca_topic_score_gemma":0.006177912,"teacher_disagreement_score":0.004092508,"about_ca_system_score_codex":0.00028553483,"about_ca_system_score_gemma":0.00043513998,"threshold_uncertainty_score":0.008137405},"labels":[],"label_agreement":null},{"id":"W4320063332","doi":"10.4018/978-1-7998-9220-5.ch010","title":"Big Data Mining and Analytics With MapReduce","year":2023,"lang":"en","type":"book-chapter","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Big data; Data science; Computer science; Variety (cybernetics); Scalability; Analytics; Encyclopedia; Task (project management); Knowledge extraction; Data mining; Data analysis; Artificial intelligence; Engineering; Database","score_opus":0.1497414589555183,"score_gpt":0.2749641295060857,"score_spread":0.12522267055056738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320063332","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024814105,0.021911746,0.8244625,0.0036776538,0.0020199397,0.0004946215,0.004907674,0.02314057,0.1169039],"genre_scores_gemma":[0.03949566,0.038952693,0.7924198,0.0021527908,0.0016415896,0.0006762177,0.016313987,0.005438474,0.10290882],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987355,0.00011965865,0.00007009431,0.00018037736,0.0008185912,0.000075749056],"domain_scores_gemma":[0.99919194,0.00024339119,0.000025701826,0.00021763954,0.00023569235,0.00008562023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009955098,0.001243693,0.00071785157,0.0020703322,0.00076285447,0.003811011,0.0024065261,0.00080485555,0.016112147],"category_scores_gemma":[0.00217358,0.0009156718,0.0012487211,0.0054787784,0.00062609336,0.0037759282,0.002529862,0.0024931345,0.019390604],"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":[0.00008068401,0.00008604377,0.00030746698,0.0009989323,0.000101762234,0.00018174067,0.00024199099,0.008515951,0.0036916803,0.048600454,0.37928483,0.5579085],"study_design_scores_gemma":[0.000022572118,0.000033324483,0.00034605977,0.00017313783,0.000017454462,0.00043582154,0.00009170768,0.020599095,0.003461885,0.08003135,0.89474094,0.00004665393],"about_ca_topic_score_codex":0.0017781936,"about_ca_topic_score_gemma":0.0021394151,"teacher_disagreement_score":0.016112147,"about_ca_system_score_codex":0.00072397664,"about_ca_system_score_gemma":0.0017647134,"threshold_uncertainty_score":0.05390048},"labels":[],"label_agreement":null},{"id":"W432065228","doi":"10.1007/11539827_3","title":"A Measurement-Theoretic Foundation of Rule Interestingness Evaluation","year":2005,"lang":"en","type":"book-chapter","venue":"Studies in computational intelligence","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Preference; Computer science; Foundation (evidence); Data mining; Measure (data warehouse); Information retrieval; Artificial intelligence; Machine learning; Mathematics; Statistics","score_opus":0.21301924137452416,"score_gpt":0.3984289264026446,"score_spread":0.18540968502812044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W432065228","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010289737,0.0008245806,0.98137164,0.0012401126,0.000108040054,0.000075411306,0.0001814935,0.00023402933,0.0056748968],"genre_scores_gemma":[0.52334064,0.0010519016,0.468737,0.00065257645,0.0011097281,0.0005648796,0.00077886204,0.00031997377,0.0034444178],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97605443,0.009607941,0.0019976182,0.0035217279,0.00792342,0.0008949524],"domain_scores_gemma":[0.8842148,0.091178715,0.0038718306,0.011501136,0.0078003327,0.0014331902],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020070259,0.0015128079,0.0034450903,0.006363061,0.0019063877,0.0077982405,0.006283932,0.0027487918,0.004346924],"category_scores_gemma":[0.10338727,0.0013174352,0.00248093,0.00659949,0.009853526,0.018821431,0.006242374,0.0060795275,0.0007314316],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000077549535,0.00006739812,0.0013062657,0.00012984776,0.0000753908,0.000053591935,0.00017877,0.015864078,0.0008891587,0.9270462,0.0016610094,0.05265082],"study_design_scores_gemma":[0.000011170271,0.000045866076,0.00027680417,0.000033405628,0.000022502334,0.00007062792,0.000029972154,0.11811697,0.00063413515,0.8799014,0.00083507545,0.000022003826],"about_ca_topic_score_codex":0.0012624147,"about_ca_topic_score_gemma":0.00096565514,"teacher_disagreement_score":0.020070259,"about_ca_system_score_codex":0.0032810895,"about_ca_system_score_gemma":0.002112807,"threshold_uncertainty_score":0.10614294},"labels":[],"label_agreement":null},{"id":"W4322617891","doi":"10.1001/jama.2023.0262","title":"Incorrect Data in Table","year":2023,"lang":"en","type":"erratum","venue":"JAMA","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Purdue Pharma (Canada)","funders":"","keywords":"BATES; Medicine; Hacker; Table (database); Art history; Aeronautics; Operating system; Engineering; Database; Art","score_opus":0.04243861210908789,"score_gpt":0.29996563347134514,"score_spread":0.25752702136225725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322617891","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014459504,0.0017981881,0.0029667036,0.10662411,0.39377722,0.0006077292,0.33947846,0.002618831,0.15068276],"genre_scores_gemma":[0.022956807,0.0037405526,0.008790127,0.21285069,0.032293204,0.0014234609,0.18777178,0.0037649535,0.5264085],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99385613,0.00081304007,0.0009785157,0.00060395466,0.0030608235,0.00068747555],"domain_scores_gemma":[0.96166855,0.014922791,0.0018649371,0.0025277901,0.017881157,0.0011347547],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0030463312,0.00097545964,0.0014164763,0.0039908867,0.002704563,0.0031919156,0.001693638,0.0040596225,0.45712715],"category_scores_gemma":[0.06345881,0.00067491597,0.0009652651,0.004836458,0.00087477564,0.0021380282,0.0014780071,0.0049728374,0.23775579],"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":[0.00004275325,0.000011053129,0.0001882516,0.000081112914,0.0000033245417,0.00005828004,0.000008770787,0.000026418656,0.000024051755,0.000676685,0.99478084,0.004098566],"study_design_scores_gemma":[0.00008126833,0.00001681859,0.0010760227,0.00033362207,0.000012145927,0.000177461,0.00006456239,0.00008166254,0.00016873896,0.0018688971,0.99610054,0.000018184868],"about_ca_topic_score_codex":0.0223411,"about_ca_topic_score_gemma":0.029686427,"teacher_disagreement_score":0.45712715,"about_ca_system_score_codex":0.0035242492,"about_ca_system_score_gemma":0.006188135,"threshold_uncertainty_score":0.77434224},"labels":[],"label_agreement":null},{"id":"W43266184","doi":"","title":"Graceful Lobsters Obtained from Diameter Four Trees Using Partitioning Technique.","year":2008,"lang":"en","type":"article","venue":"Ars Combinatoria","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics","score_opus":0.03835592948898357,"score_gpt":0.2536990941832677,"score_spread":0.2153431646942841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W43266184","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4382429,0.0010314378,0.49784154,0.0007448265,0.000267814,0.00018951848,0.0018704126,0.0020192135,0.057792343],"genre_scores_gemma":[0.7854589,0.0005985431,0.17123413,0.00023294069,0.00008205453,0.00013619548,0.0031034744,0.00061278907,0.038540956],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9997552,0.000029838246,0.000017508193,0.000056290894,0.000069378584,0.00007181262],"domain_scores_gemma":[0.99909294,0.00029346158,0.000089602174,0.00032467593,0.00007959759,0.0001198302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029244903,0.00047236454,0.0008132671,0.0013835866,0.0011664056,0.001514043,0.0010001966,0.0006839617,0.007271942],"category_scores_gemma":[0.0020230003,0.00034842567,0.00075592875,0.0011655494,0.0008570281,0.0014800492,0.0017628026,0.0011068144,0.0019733065],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013155359,0.00031748982,0.007657388,0.0007235223,0.00018300314,0.0020972781,0.001417884,0.066447236,0.07716659,0.5065697,0.02638953,0.30971473],"study_design_scores_gemma":[0.00018633775,0.00031712512,0.0066938773,0.0002025878,0.00021778008,0.0020159604,0.0008203993,0.23286921,0.045086697,0.648689,0.062783614,0.000117397416],"about_ca_topic_score_codex":0.0012304714,"about_ca_topic_score_gemma":0.0024872334,"teacher_disagreement_score":0.007271942,"about_ca_system_score_codex":0.0005837679,"about_ca_system_score_gemma":0.00068175525,"threshold_uncertainty_score":0.0243271},"labels":[],"label_agreement":null},{"id":"W4327652278","doi":"10.1007/978-3-031-26390-3","title":"Machine Learning and Knowledge Discovery in Databases","year":2023,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"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":"Microsoft Research Asia; Institut National de Recherche pour l'Agriculture, l'Alimentation et l'Environnement; Insight SFI Research Centre for Data Analytics; Région Normandie; Université de Lyon; Stockholms Universitet; University of Science and Technology of China; Shenzhen University; Julius-Maximilians-Universität Würzburg; Universidad de Córdoba; Rheinische Friedrich-Wilhelms-Universität Bonn; Southeast University; Nanjing University; Univerza v Ljubljani; Universidade Federal de Minas Gerais; Aristotle University of Thessaloniki; Central European Institute of Technology; Universidad de Oviedo; Ludwig-Maximilians-Universität München; Universiteit Utrecht; Temple University; Nankai University; Centre National de la Recherche Scientifique; Universiteit Gent; Sapienza Università di Roma; Université de Liège; Université de Neuchâtel; Technische Universität Wien; Universita degli Studi di Bari Aldo Moro; Université de Caen Normandie; Umeå Universitet; Politechnika Poznańska; University of Southern California; Masdar Institute of Science and Technology; Universitetet i Stavanger; King Abdulaziz University; National and Kapodistrian University of Athens; Johannes Gutenberg-Universität Mainz; Leibniz-Gemeinschaft; Simon Fraser University; Università degli Studi di Padova; Euskal Herriko Unibertsitatea; Albert-Ludwigs-Universität Freiburg; Dalhousie University; Universidad de Zaragoza; University of Waikato; Shanghai Educational Development Foundation; Chalmers Tekniska Högskola; Rijksuniversiteit Groningen; Aalborg Universitet; Abu Dhabi National Oil Company; University of Texas at Dallas; Zhejiang University; Université Paris-Saclay; Aalto-Yliopisto; Humboldt-Universität zu Berlin; Sun Yat-sen University; Technische Universität München; Institut National des Sciences Appliquées de Lyon; Università degli Studi di Milano-Bicocca; Tsinghua University; Chinese Academy of Sciences; Masarykova Univerzita; Universiteit van Amsterdam; Technische Universität Kaiserslautern; Monash University; Technische Universiteit Delft; University of Technology Sydney; KU Leuven; University of New South Wales; Gottfried Wilhelm Leibniz Universität Hannover; Université de La Réunion; Jilin University; National University of Singapore; Indian Institute of Technology Palakkad; Commonwealth Scientific and Industrial Research Organisation; University of Oxford; Sorbonne Université; Kungliga Tekniska Högskolan; Ulster University; Universidade do Porto; Utah State University; Indian Institute of Technology, Patna; Carl von Ossietzky Universität Oldenburg; Blekinge Tekniska Högskola; Beihang University; University of Twente; University of Bristol; Harokopio University; Università di Pisa; Scuola IMT Alti Studi Lucca; Universidad Autónoma de Madrid; Purdue University; University of Macedonia; Eberhard Karls Universität Tübingen; Itä-Suomen Yliopisto; Shandong University; Politechnika Warszawska; Université Bretagne Sud; Institut \"Jožef Stefan\"; Deakin University; Universiti Kuala Lumpur; Helsingin Yliopisto; Aix-Marseille Université; Universiteit Leiden; Universität Bielefeld; Université Grenoble Alpes; Università degli Studi di Trento; Michigan State University; Arizona State University; Università degli Studi di Cagliari; Georgia State University; Deutsches Krebsforschungszentrum; Högskolan i Halmstad; Korea Advanced Institute of Science and Technology; University of Alberta; Indian Council of Agricultural Research; University of Texas at San Antonio; University of Minnesota; TU Graz, Internationale Beziehungen und Mobilitätsprogramme; College of Engineering, Michigan State University; University of Wyoming; Danmarks Tekniske Universitet; Shenzhen Technology University; University College London; Politecnico di Torino; Université Catholique de Louvain; Philipps-Universität Marburg; Università degli Studi di Milano; Indian National Science Academy; Institut National Polytechnique de Toulouse; Microsoft Research; University College Dublin; Syracuse University; University of Ottawa; Technische Universiteit Eindhoven","keywords":"Computer science; Knowledge extraction; Database; Information retrieval; Artificial intelligence; Data science; World Wide Web","score_opus":0.024445144512082982,"score_gpt":0.2906166420676732,"score_spread":0.2661714975555902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327652278","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004635329,0.2597681,0.5984489,0.007553297,0.0043354067,0.0003002367,0.0020280518,0.0021767137,0.12075399],"genre_scores_gemma":[0.045371886,0.18120953,0.545715,0.0030710488,0.00414011,0.0004037424,0.005208564,0.00074222067,0.21413797],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990596,0.00018952906,0.00008884657,0.00014249772,0.00048671025,0.000032737204],"domain_scores_gemma":[0.9975062,0.0018472255,0.00008280166,0.000264167,0.00023900918,0.000060690996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010223477,0.00084265234,0.0016497052,0.0025552816,0.00051248306,0.004103264,0.0014350653,0.00085436105,0.014226699],"category_scores_gemma":[0.0043096617,0.00067518523,0.00084276235,0.0071022473,0.0011092684,0.0057409825,0.0014138771,0.0020989408,0.00938921],"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":[0.00006038981,0.000083153915,0.00043509618,0.0018632549,0.000103939026,0.00014537957,0.00015794489,0.0046024676,0.0012510429,0.15520544,0.13710928,0.69898266],"study_design_scores_gemma":[0.000027743301,0.000046173507,0.0008203212,0.00061908335,0.0000770086,0.00085935474,0.000112455564,0.027553957,0.0016254168,0.3994712,0.5687559,0.000031399497],"about_ca_topic_score_codex":0.00083954394,"about_ca_topic_score_gemma":0.00080515514,"teacher_disagreement_score":0.014226699,"about_ca_system_score_codex":0.0007953959,"about_ca_system_score_gemma":0.0008812106,"threshold_uncertainty_score":0.047593057},"labels":[],"label_agreement":null},{"id":"W4327652279","doi":"10.1007/978-3-031-26409-2","title":"Machine Learning and Knowledge Discovery in Databases","year":2023,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":12,"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":"Microsoft Research Asia; Institut National de Recherche pour l'Agriculture, l'Alimentation et l'Environnement; Insight SFI Research Centre for Data Analytics; Région Normandie; Université de Lyon; Stockholms Universitet; University of Science and Technology of China; Shenzhen University; Julius-Maximilians-Universität Würzburg; Universidad de Córdoba; Rheinische Friedrich-Wilhelms-Universität Bonn; Southeast University; Nanjing University; Univerza v Ljubljani; Universidade Federal de Minas Gerais; Aristotle University of Thessaloniki; Central European Institute of Technology; Universidad de Oviedo; Ludwig-Maximilians-Universität München; Universiteit Utrecht; Temple University; Nankai University; Centre National de la Recherche Scientifique; Universiteit Gent; Sapienza Università di Roma; Université de Liège; Université de Neuchâtel; Technische Universität Wien; Universita degli Studi di Bari Aldo Moro; Université de Caen Normandie; Umeå Universitet; Politechnika Poznańska; University of Southern California; Masdar Institute of Science and Technology; Universitetet i Stavanger; King Abdulaziz University; National and Kapodistrian University of Athens; Johannes Gutenberg-Universität Mainz; Leibniz-Gemeinschaft; Simon Fraser University; Università degli Studi di Padova; Euskal Herriko Unibertsitatea; Albert-Ludwigs-Universität Freiburg; Dalhousie University; Universidad de Zaragoza; University of Waikato; Shanghai Educational Development Foundation; Chalmers Tekniska Högskola; Rijksuniversiteit Groningen; Aalborg Universitet; Abu Dhabi National Oil Company; University of Texas at Dallas; Zhejiang University; Université Paris-Saclay; Aalto-Yliopisto; Humboldt-Universität zu Berlin; Sun Yat-sen University; Technische Universität München; Institut National des Sciences Appliquées de Lyon; Università degli Studi di Milano-Bicocca; Tsinghua University; Chinese Academy of Sciences; Masarykova Univerzita; Universiteit van Amsterdam; Technische Universität Kaiserslautern; Monash University; Technische Universiteit Delft; University of Technology Sydney; KU Leuven; University of New South Wales; Gottfried Wilhelm Leibniz Universität Hannover; Université de La Réunion; Jilin University; National University of Singapore; Indian Institute of Technology Palakkad; Commonwealth Scientific and Industrial Research Organisation; University of Oxford; Sorbonne Université; Kungliga Tekniska Högskolan; Ulster University; Universidade do Porto; Utah State University; Indian Institute of Technology, Patna; Carl von Ossietzky Universität Oldenburg; Blekinge Tekniska Högskola; Beihang University; University of Twente; University of Bristol; Harokopio University; Università di Pisa; Scuola IMT Alti Studi Lucca; Universidad Autónoma de Madrid; Purdue University; University of Macedonia; Eberhard Karls Universität Tübingen; Itä-Suomen Yliopisto; Shandong University; Politechnika Warszawska; Université Bretagne Sud; Institut \"Jožef Stefan\"; Deakin University; Universiti Kuala Lumpur; Helsingin Yliopisto; Aix-Marseille Université; Universiteit Leiden; Universität Bielefeld; Université Grenoble Alpes; Università degli Studi di Trento; Michigan State University; Arizona State University; Università degli Studi di Cagliari; Georgia State University; Deutsches Krebsforschungszentrum; Högskolan i Halmstad; Korea Advanced Institute of Science and Technology; University of Alberta; Indian Council of Agricultural Research; University of Texas at San Antonio; University of Minnesota; TU Graz, Internationale Beziehungen und Mobilitätsprogramme; College of Engineering, Michigan State University; University of Wyoming; Danmarks Tekniske Universitet; Shenzhen Technology University; University College London; Politecnico di Torino; Université Catholique de Louvain; Philipps-Universität Marburg; Università degli Studi di Milano; Indian National Science Academy; Institut National Polytechnique de Toulouse; Microsoft Research; University College Dublin; Syracuse University; University of Ottawa; Technische Universiteit Eindhoven","keywords":"Computer science; Knowledge extraction; Database; Artificial intelligence; Information retrieval; Data science; World Wide Web","score_opus":0.024445144512082982,"score_gpt":0.2906166420676732,"score_spread":0.2661714975555902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327652279","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004635329,0.2597681,0.5984489,0.007553297,0.0043354067,0.0003002367,0.0020280518,0.0021767137,0.12075399],"genre_scores_gemma":[0.045371886,0.18120953,0.545715,0.0030710488,0.00414011,0.0004037424,0.005208564,0.00074222067,0.21413797],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990596,0.00018952906,0.00008884657,0.00014249772,0.00048671025,0.000032737204],"domain_scores_gemma":[0.9975062,0.0018472255,0.00008280166,0.000264167,0.00023900918,0.000060690996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010223477,0.00084265234,0.0016497052,0.0025552816,0.00051248306,0.004103264,0.0014350653,0.00085436105,0.014226699],"category_scores_gemma":[0.0043096617,0.00067518523,0.00084276235,0.0071022473,0.0011092684,0.0057409825,0.0014138771,0.0020989408,0.00938921],"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":[0.00006038981,0.000083153915,0.00043509618,0.0018632549,0.000103939026,0.00014537957,0.00015794489,0.0046024676,0.0012510429,0.15520544,0.13710928,0.69898266],"study_design_scores_gemma":[0.000027743301,0.000046173507,0.0008203212,0.00061908335,0.0000770086,0.00085935474,0.000112455564,0.027553957,0.0016254168,0.3994712,0.5687559,0.000031399497],"about_ca_topic_score_codex":0.00083954394,"about_ca_topic_score_gemma":0.00080515514,"teacher_disagreement_score":0.014226699,"about_ca_system_score_codex":0.0007953959,"about_ca_system_score_gemma":0.0008812106,"threshold_uncertainty_score":0.047593057},"labels":[],"label_agreement":null},{"id":"W4327652731","doi":"10.1007/978-3-031-26412-2","title":"Machine Learning and Knowledge Discovery in Databases","year":2023,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":6,"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":"Microsoft Research Asia; Institut National de Recherche pour l'Agriculture, l'Alimentation et l'Environnement; Insight SFI Research Centre for Data Analytics; Région Normandie; Université de Lyon; Stockholms Universitet; University of Science and Technology of China; Shenzhen University; Julius-Maximilians-Universität Würzburg; Universidad de Córdoba; Rheinische Friedrich-Wilhelms-Universität Bonn; Southeast University; Nanjing University; Univerza v Ljubljani; Universidade Federal de Minas Gerais; Aristotle University of Thessaloniki; Central European Institute of Technology; Universidad de Oviedo; Ludwig-Maximilians-Universität München; Universiteit Utrecht; Temple University; Nankai University; Centre National de la Recherche Scientifique; Universiteit Gent; Sapienza Università di Roma; Université de Liège; Université de Neuchâtel; Technische Universität Wien; Universita degli Studi di Bari Aldo Moro; Université de Caen Normandie; Umeå Universitet; Politechnika Poznańska; University of Southern California; Masdar Institute of Science and Technology; Universitetet i Stavanger; King Abdulaziz University; National and Kapodistrian University of Athens; Johannes Gutenberg-Universität Mainz; Leibniz-Gemeinschaft; Simon Fraser University; Università degli Studi di Padova; Euskal Herriko Unibertsitatea; Albert-Ludwigs-Universität Freiburg; Dalhousie University; Universidad de Zaragoza; University of Waikato; Shanghai Educational Development Foundation; Chalmers Tekniska Högskola; Rijksuniversiteit Groningen; Aalborg Universitet; Abu Dhabi National Oil Company; University of Texas at Dallas; Zhejiang University; Université Paris-Saclay; Aalto-Yliopisto; Humboldt-Universität zu Berlin; Sun Yat-sen University; Technische Universität München; Institut National des Sciences Appliquées de Lyon; Università degli Studi di Milano-Bicocca; Tsinghua University; Chinese Academy of Sciences; Masarykova Univerzita; Universiteit van Amsterdam; Technische Universität Kaiserslautern; Monash University; Technische Universiteit Delft; University of Technology Sydney; KU Leuven; University of New South Wales; Gottfried Wilhelm Leibniz Universität Hannover; Université de La Réunion; Jilin University; National University of Singapore; Indian Institute of Technology Palakkad; Commonwealth Scientific and Industrial Research Organisation; University of Oxford; Sorbonne Université; Kungliga Tekniska Högskolan; Ulster University; Universidade do Porto; Utah State University; Indian Institute of Technology, Patna; Carl von Ossietzky Universität Oldenburg; Blekinge Tekniska Högskola; Beihang University; University of Twente; University of Bristol; Harokopio University; Università di Pisa; Scuola IMT Alti Studi Lucca; Universidad Autónoma de Madrid; Purdue University; University of Macedonia; Eberhard Karls Universität Tübingen; Itä-Suomen Yliopisto; Shandong University; Politechnika Warszawska; Université Bretagne Sud; Institut \"Jožef Stefan\"; Deakin University; Universiti Kuala Lumpur; Helsingin Yliopisto; Aix-Marseille Université; Universiteit Leiden; Universität Bielefeld; Université Grenoble Alpes; Università degli Studi di Trento; Michigan State University; Arizona State University; Università degli Studi di Cagliari; Georgia State University; Deutsches Krebsforschungszentrum; Högskolan i Halmstad; Korea Advanced Institute of Science and Technology; University of Alberta; Indian Council of Agricultural Research; University of Texas at San Antonio; University of Minnesota; TU Graz, Internationale Beziehungen und Mobilitätsprogramme; College of Engineering, Michigan State University; University of Wyoming; Danmarks Tekniske Universitet; Shenzhen Technology University; University College London; Politecnico di Torino; Université Catholique de Louvain; Philipps-Universität Marburg; Università degli Studi di Milano; Indian National Science Academy; Institut National Polytechnique de Toulouse; Microsoft Research; University College Dublin; Syracuse University; University of Ottawa; Technische Universiteit Eindhoven","keywords":"Computer science; Knowledge extraction; Database; Information retrieval; Artificial intelligence","score_opus":0.024445144512082982,"score_gpt":0.2906166420676732,"score_spread":0.2661714975555902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327652731","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004635329,0.2597681,0.5984489,0.007553297,0.0043354067,0.0003002367,0.0020280518,0.0021767137,0.12075399],"genre_scores_gemma":[0.045371886,0.18120953,0.545715,0.0030710488,0.00414011,0.0004037424,0.005208564,0.00074222067,0.21413797],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990596,0.00018952906,0.00008884657,0.00014249772,0.00048671025,0.000032737204],"domain_scores_gemma":[0.9975062,0.0018472255,0.00008280166,0.000264167,0.00023900918,0.000060690996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010223477,0.00084265234,0.0016497052,0.0025552816,0.00051248306,0.004103264,0.0014350653,0.00085436105,0.014226699],"category_scores_gemma":[0.0043096617,0.00067518523,0.00084276235,0.0071022473,0.0011092684,0.0057409825,0.0014138771,0.0020989408,0.00938921],"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":[0.00006038981,0.000083153915,0.00043509618,0.0018632549,0.000103939026,0.00014537957,0.00015794489,0.0046024676,0.0012510429,0.15520544,0.13710928,0.69898266],"study_design_scores_gemma":[0.000027743301,0.000046173507,0.0008203212,0.00061908335,0.0000770086,0.00085935474,0.000112455564,0.027553957,0.0016254168,0.3994712,0.5687559,0.000031399497],"about_ca_topic_score_codex":0.00083954394,"about_ca_topic_score_gemma":0.00080515514,"teacher_disagreement_score":0.014226699,"about_ca_system_score_codex":0.0007953959,"about_ca_system_score_gemma":0.0008812106,"threshold_uncertainty_score":0.047593057},"labels":[],"label_agreement":null},{"id":"W4327656811","doi":"10.1007/978-3-031-26387-3","title":"Machine Learning and Knowledge Discovery in Databases","year":2023,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"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":"Microsoft Research Asia; Institut National de Recherche pour l'Agriculture, l'Alimentation et l'Environnement; Insight SFI Research Centre for Data Analytics; Région Normandie; Université de Lyon; Stockholms Universitet; University of Science and Technology of China; Shenzhen University; Julius-Maximilians-Universität Würzburg; Universidad de Córdoba; Rheinische Friedrich-Wilhelms-Universität Bonn; Southeast University; Nanjing University; Univerza v Ljubljani; Universidade Federal de Minas Gerais; Aristotle University of Thessaloniki; Central European Institute of Technology; Universidad de Oviedo; Ludwig-Maximilians-Universität München; Universiteit Utrecht; Temple University; Nankai University; Centre National de la Recherche Scientifique; Universiteit Gent; Sapienza Università di Roma; Université de Liège; Université de Neuchâtel; Technische Universität Wien; Universita degli Studi di Bari Aldo Moro; Université de Caen Normandie; Umeå Universitet; Politechnika Poznańska; University of Southern California; Masdar Institute of Science and Technology; Universitetet i Stavanger; King Abdulaziz University; National and Kapodistrian University of Athens; Johannes Gutenberg-Universität Mainz; Leibniz-Gemeinschaft; Simon Fraser University; Università degli Studi di Padova; Euskal Herriko Unibertsitatea; Albert-Ludwigs-Universität Freiburg; Dalhousie University; Universidad de Zaragoza; University of Waikato; Shanghai Educational Development Foundation; Chalmers Tekniska Högskola; Rijksuniversiteit Groningen; Aalborg Universitet; Abu Dhabi National Oil Company; University of Texas at Dallas; Zhejiang University; Université Paris-Saclay; Aalto-Yliopisto; Humboldt-Universität zu Berlin; Sun Yat-sen University; Technische Universität München; Institut National des Sciences Appliquées de Lyon; Università degli Studi di Milano-Bicocca; Tsinghua University; Chinese Academy of Sciences; Masarykova Univerzita; Universiteit van Amsterdam; Technische Universität Kaiserslautern; Monash University; Technische Universiteit Delft; University of Technology Sydney; KU Leuven; University of New South Wales; Gottfried Wilhelm Leibniz Universität Hannover; Université de La Réunion; Jilin University; National University of Singapore; Indian Institute of Technology Palakkad; Commonwealth Scientific and Industrial Research Organisation; University of Oxford; Sorbonne Université; Kungliga Tekniska Högskolan; Ulster University; Universidade do Porto; Utah State University; Indian Institute of Technology, Patna; Carl von Ossietzky Universität Oldenburg; Blekinge Tekniska Högskola; Beihang University; University of Twente; University of Bristol; Harokopio University; Università di Pisa; Scuola IMT Alti Studi Lucca; Universidad Autónoma de Madrid; Purdue University; University of Macedonia; Eberhard Karls Universität Tübingen; Itä-Suomen Yliopisto; Shandong University; Politechnika Warszawska; Université Bretagne Sud; Institut \"Jožef Stefan\"; Deakin University; Universiti Kuala Lumpur; Helsingin Yliopisto; Aix-Marseille Université; Universiteit Leiden; Universität Bielefeld; Université Grenoble Alpes; Università degli Studi di Trento; Michigan State University; Arizona State University; Università degli Studi di Cagliari; Georgia State University; Deutsches Krebsforschungszentrum; Högskolan i Halmstad; Korea Advanced Institute of Science and Technology; University of Alberta; Indian Council of Agricultural Research; University of Texas at San Antonio; University of Minnesota; TU Graz, Internationale Beziehungen und Mobilitätsprogramme; College of Engineering, Michigan State University; University of Wyoming; Danmarks Tekniske Universitet; Shenzhen Technology University; University College London; Politecnico di Torino; Université Catholique de Louvain; Philipps-Universität Marburg; Università degli Studi di Milano; Indian National Science Academy; Institut National Polytechnique de Toulouse; Microsoft Research; University College Dublin; Syracuse University; University of Ottawa; Technische Universiteit Eindhoven","keywords":"Computer science; Knowledge extraction; Database; Information retrieval; Data science; Artificial intelligence","score_opus":0.024445144512082982,"score_gpt":0.2906166420676732,"score_spread":0.2661714975555902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327656811","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004635329,0.2597681,0.5984489,0.007553297,0.0043354067,0.0003002367,0.0020280518,0.0021767137,0.12075399],"genre_scores_gemma":[0.045371886,0.18120953,0.545715,0.0030710488,0.00414011,0.0004037424,0.005208564,0.00074222067,0.21413797],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990596,0.00018952906,0.00008884657,0.00014249772,0.00048671025,0.000032737204],"domain_scores_gemma":[0.9975062,0.0018472255,0.00008280166,0.000264167,0.00023900918,0.000060690996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010223477,0.00084265234,0.0016497052,0.0025552816,0.00051248306,0.004103264,0.0014350653,0.00085436105,0.014226699],"category_scores_gemma":[0.0043096617,0.00067518523,0.00084276235,0.0071022473,0.0011092684,0.0057409825,0.0014138771,0.0020989408,0.00938921],"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":[0.00006038981,0.000083153915,0.00043509618,0.0018632549,0.000103939026,0.00014537957,0.00015794489,0.0046024676,0.0012510429,0.15520544,0.13710928,0.69898266],"study_design_scores_gemma":[0.000027743301,0.000046173507,0.0008203212,0.00061908335,0.0000770086,0.00085935474,0.000112455564,0.027553957,0.0016254168,0.3994712,0.5687559,0.000031399497],"about_ca_topic_score_codex":0.00083954394,"about_ca_topic_score_gemma":0.00080515514,"teacher_disagreement_score":0.014226699,"about_ca_system_score_codex":0.0007953959,"about_ca_system_score_gemma":0.0008812106,"threshold_uncertainty_score":0.047593057},"labels":[],"label_agreement":null},{"id":"W4352981311","doi":"10.1109/iscmi56532.2022.10068470","title":"Priority-First Search and Mining Popular Packages","year":2022,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"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 Winnipeg","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Priority queue; Set (abstract data type); Trie; Queue; Tree (set theory); Data mining; String (physics); Data structure; Theoretical computer science; Information retrieval; Programming language; Mathematics","score_opus":0.021224305056971367,"score_gpt":0.2597483910157717,"score_spread":0.2385240859588003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4352981311","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06949991,0.0011313836,0.9227602,0.0007228642,0.000058408586,0.00032821464,0.0018117309,0.0018026594,0.0018846892],"genre_scores_gemma":[0.24147446,0.0005596845,0.7476876,0.00027849164,0.00010927753,0.0004850486,0.005939132,0.00040120006,0.003065081],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99585044,0.0008682859,0.0003142079,0.0011869397,0.0013283436,0.00045174666],"domain_scores_gemma":[0.9912013,0.0052575767,0.0008119822,0.0011328042,0.0012121637,0.0003841098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003514159,0.0013372941,0.002185153,0.0068869535,0.0015655712,0.0029616866,0.0048214,0.0022181978,0.0032475065],"category_scores_gemma":[0.020325739,0.0011054592,0.0025080494,0.01033214,0.0014519201,0.0075419177,0.0024889507,0.0015201053,0.0012445718],"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":[0.0012038335,0.0008046716,0.029060507,0.0016546714,0.0004800313,0.0008852076,0.0019892163,0.15602195,0.011342139,0.18149053,0.03488588,0.5801814],"study_design_scores_gemma":[0.00015638507,0.00018730307,0.0016745339,0.00005770119,0.00009532299,0.000592843,0.00038358473,0.81018174,0.004077096,0.17327127,0.009269045,0.00005318096],"about_ca_topic_score_codex":0.0047786906,"about_ca_topic_score_gemma":0.0068869404,"teacher_disagreement_score":0.0068869535,"about_ca_system_score_codex":0.001479685,"about_ca_system_score_gemma":0.0031042648,"threshold_uncertainty_score":0.018584847},"labels":[],"label_agreement":null},{"id":"W4360765013","doi":"10.1109/asonam55673.2022.10068715","title":"Dynamic Ensemble Associative Learning","year":2022,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Associative property; Artificial intelligence; Random forest; Machine learning; Ensemble learning; Random subspace method; Feature (linguistics); Feature vector; Content-addressable memory; Process (computing); Feature selection; Pattern recognition (psychology); Data mining; Support vector machine; Artificial neural network; Mathematics","score_opus":0.009357205294370665,"score_gpt":0.2471810620330675,"score_spread":0.23782385673869683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360765013","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.074518815,0.0026230395,0.906154,0.00039739592,0.00032691125,0.00026205578,0.0004150378,0.0020510769,0.013251656],"genre_scores_gemma":[0.7501236,0.001914564,0.23503654,0.00054669974,0.00035036833,0.00056516257,0.0012686335,0.00015657564,0.010037819],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980331,0.0005116348,0.0001280443,0.00046806826,0.0007180966,0.00014100531],"domain_scores_gemma":[0.9958972,0.001847181,0.00024191216,0.0007627852,0.0011302391,0.00012066453],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029004524,0.0011059974,0.0017080797,0.002081741,0.0007501277,0.0013361354,0.0020655035,0.0010336624,0.0033057109],"category_scores_gemma":[0.0064809266,0.000379337,0.0009853636,0.0023007023,0.00061156554,0.002896153,0.0019282942,0.001337873,0.0012608459],"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":[0.00013932378,0.00035307242,0.006871495,0.00016882377,0.00035839452,0.00012751533,0.00015576123,0.15784022,0.0022309544,0.013183121,0.006236656,0.81233466],"study_design_scores_gemma":[0.000016141146,0.0001597748,0.0012405299,0.000036590936,0.00009201602,0.00016935816,0.000060134626,0.96889025,0.0029373288,0.02045449,0.005915137,0.000028195098],"about_ca_topic_score_codex":0.002584733,"about_ca_topic_score_gemma":0.0049159634,"teacher_disagreement_score":0.0033057109,"about_ca_system_score_codex":0.00062807667,"about_ca_system_score_gemma":0.00088471547,"threshold_uncertainty_score":0.015339255},"labels":[],"label_agreement":null},{"id":"W4360765119","doi":"10.1109/asonam55673.2022.10068640","title":"Social Network Analysis of Popular YouTube Videos via Vertical Quantitative Mining","year":2022,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data mining; Field (mathematics); Association rule learning; Data science; Information retrieval; Mathematics","score_opus":0.03500594390631368,"score_gpt":0.30918564674223825,"score_spread":0.2741797028359246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360765119","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9249359,0.0011074407,0.04023337,0.0005462762,0.00007332798,0.0003792462,0.022202197,0.0007058198,0.009816441],"genre_scores_gemma":[0.9574071,0.00036636216,0.025353292,0.000037527865,0.00004693046,0.00017031917,0.013800098,0.000024554547,0.002793799],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9994779,0.00009878391,0.000050494706,0.00009441402,0.00019936734,0.000079073485],"domain_scores_gemma":[0.99880695,0.00034817957,0.00026581102,0.000065053304,0.00042860565,0.000085370084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004591545,0.00055261585,0.0003304204,0.0069167246,0.00043638347,0.00062831526,0.00039988136,0.0002895515,0.0019181233],"category_scores_gemma":[0.0023109359,0.000108874694,0.0003727912,0.0042384868,0.00019167532,0.00090079766,0.0006720802,0.00027107837,0.00055204256],"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":[0.0008915119,0.0005537606,0.47126344,0.001150772,0.00053576945,0.001950022,0.0015316426,0.025173027,0.021795804,0.011258536,0.02234898,0.44154674],"study_design_scores_gemma":[0.00002954384,0.00033084414,0.32413593,0.00015618067,0.0001305968,0.0010982031,0.0033026058,0.6417944,0.008085157,0.0062531973,0.014615161,0.00006818365],"about_ca_topic_score_codex":0.026318617,"about_ca_topic_score_gemma":0.036829747,"teacher_disagreement_score":0.026318617,"about_ca_system_score_codex":0.0006866349,"about_ca_system_score_gemma":0.0004380347,"threshold_uncertainty_score":0.05233085},"labels":[],"label_agreement":null},{"id":"W4360982002","doi":"10.1007/978-3-031-26419-1","title":"Machine Learning and Knowledge Discovery in Databases","year":2023,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":24,"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":"Microsoft Research Asia; Institut National de Recherche pour l'Agriculture, l'Alimentation et l'Environnement; Insight SFI Research Centre for Data Analytics; Région Normandie; Stockholms Universitet; University of Science and Technology of China; Univerza v Ljubljani; University of Alberta; Korea Advanced Institute of Science and Technology; Harokopio University; Scuola IMT Alti Studi Lucca; Università di Pisa; Central European Institute of Technology; Universidad de Oviedo; Université Grenoble Alpes; Universität Bielefeld; Ludwig-Maximilians-Universität München; College of Engineering, Michigan State University; University of Wyoming; Danmarks Tekniske Universitet; Temple University; Universiteit Utrecht; Nankai University; Centre National de la Recherche Scientifique; Universiteit Gent; Sapienza Università di Roma; Technische Universität Wien; Universita degli Studi di Bari Aldo Moro; Université de Caen Normandie; Politechnika Poznańska; Masdar Institute of Science and Technology; Microsoft Research; Institut National Polytechnique de Toulouse; King Abdulaziz University; National and Kapodistrian University of Athens; Johannes Gutenberg-Universität Mainz; Leibniz-Gemeinschaft; Simon Fraser University; Università degli Studi di Padova; Euskal Herriko Unibertsitatea; Albert-Ludwigs-Universität Freiburg; Dalhousie University; University of Waikato; Universidad de Zaragoza; Shanghai Educational Development Foundation; Chalmers Tekniska Högskola; Rijksuniversiteit Groningen; Aalborg Universitet; Abu Dhabi National Oil Company; University of Texas at Dallas; Zhejiang University; Université Paris-Saclay; Aalto-Yliopisto; Sun Yat-sen University; Technische Universität München; Institut National des Sciences Appliquées de Lyon; Università degli Studi di Milano-Bicocca; Tsinghua University; Chinese Academy of Sciences; TU Graz, Internationale Beziehungen und Mobilitätsprogramme; University of Minnesota; Monash University; Julius-Maximilians-Universität Würzburg; University of Technology Sydney; KU Leuven; University of New South Wales; Gottfried Wilhelm Leibniz Universität Hannover; Aix-Marseille Université; Universiteit Leiden; University of Texas at San Antonio; Indian Council of Agricultural Research; Jilin University; National University of Singapore; Indian Institute of Technology Palakkad; Commonwealth Scientific and Industrial Research Organisation; Universiti Kuala Lumpur; Helsingin Yliopisto; Deakin University; Blekinge Tekniska Högskola; Beihang University; University of Twente; University of Bristol; University of Oxford; Southeast University; Kungliga Tekniska Högskolan; Ulster University; Universidade do Porto; Indian Institute of Technology, Patna; Carl von Ossietzky Universität Oldenburg; Itä-Suomen Yliopisto; Shandong University; Politechnika Warszawska; Université Bretagne Sud; Universidad de Córdoba; Institut \"Jožef Stefan\"; Université Catholique de Louvain; Politecnico di Torino; Indian National Science Academy; Università degli Studi di Milano; Purdue University; Università degli Studi di Trento; Michigan State University; Università degli Studi di Cagliari; Georgia State University; Deutsches Krebsforschungszentrum; University of Ottawa; Syracuse University; Masarykova Univerzita; Universiteit van Amsterdam; Aristotle University of Thessaloniki; University College Dublin","keywords":"Computer science; Knowledge extraction; Database; Artificial intelligence; Information retrieval","score_opus":0.024445144512082982,"score_gpt":0.2906166420676732,"score_spread":0.2661714975555902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360982002","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004635329,0.2597681,0.5984489,0.007553297,0.0043354067,0.0003002367,0.0020280518,0.0021767137,0.12075399],"genre_scores_gemma":[0.045371886,0.18120953,0.545715,0.0030710488,0.00414011,0.0004037424,0.005208564,0.00074222067,0.21413797],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990596,0.00018952906,0.00008884657,0.00014249772,0.00048671025,0.000032737204],"domain_scores_gemma":[0.9975062,0.0018472255,0.00008280166,0.000264167,0.00023900918,0.000060690996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010223477,0.00084265234,0.0016497052,0.0025552816,0.00051248306,0.004103264,0.0014350653,0.00085436105,0.014226699],"category_scores_gemma":[0.0043096617,0.00067518523,0.00084276235,0.0071022473,0.0011092684,0.0057409825,0.0014138771,0.0020989408,0.00938921],"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":[0.00006038981,0.000083153915,0.00043509618,0.0018632549,0.000103939026,0.00014537957,0.00015794489,0.0046024676,0.0012510429,0.15520544,0.13710928,0.69898266],"study_design_scores_gemma":[0.000027743301,0.000046173507,0.0008203212,0.00061908335,0.0000770086,0.00085935474,0.000112455564,0.027553957,0.0016254168,0.3994712,0.5687559,0.000031399497],"about_ca_topic_score_codex":0.00083954394,"about_ca_topic_score_gemma":0.00080515514,"teacher_disagreement_score":0.014226699,"about_ca_system_score_codex":0.0007953959,"about_ca_system_score_gemma":0.0008812106,"threshold_uncertainty_score":0.047593057},"labels":[],"label_agreement":null},{"id":"W4360985784","doi":"10.1007/978-3-031-26422-1","title":"Machine Learning and Knowledge Discovery in Databases","year":2023,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"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":"Oak Ridge National Laboratory; Instituto Superior Técnico; Leibniz-Gemeinschaft; Microsoft Research Asia; University of California, Riverside; University of Illinois at Urbana-Champaign; Insight SFI Research Centre for Data Analytics; Région Normandie; Technische Universität Dortmund; Basque Center for Applied Mathematics; Universität Kassel; Stockholms Universitet; University of Science and Technology of China; Shenzhen University; Zhejiang University of Technology; Rheinische Friedrich-Wilhelms-Universität Bonn; Southeast University; Nanjing University; Universidade Federal de Minas Gerais; Aristotle University of Thessaloniki; Universidad de Oviedo; Universitat de Barcelona; Ludwig-Maximilians-Universität München; Université de Liège; Turun Yliopisto; National and Kapodistrian University of Athens; Universiteit Utrecht; Temple University; Nankai University; Universidade Federal de Uberlândia; Centre National de la Recherche Scientifique; Universiteit Gent; Sapienza Università di Roma; Renmin University of China; Université de Caen Normandie; Umeå Universitet; Politechnika Poznańska; University of Southern California; Masdar Institute of Science and Technology; Gottfried Wilhelm Leibniz Universität Hannover; Universität Potsdam; Universitetet i Stavanger; King Abdulaziz University; University of Oxford; King Abdullah University of Science and Technology; Università degli Studi di Trento; Harokopio University; Università di Pisa; Scuola IMT Alti Studi Lucca; Universidad Autónoma de Madrid; Linköpings Universitet; Università degli Studi di Padova; Euskal Herriko Unibertsitatea; Universität Wien; Dalhousie University; Abu Dhabi National Oil Company; Humboldt-Universität zu Berlin; Sun Yat-sen University; Institut National des Sciences Appliquées de Lyon; Università degli Studi di Milano-Bicocca; Tsinghua University; Chinese Academy of Sciences; Masarykova Univerzita; Universiteit van Amsterdam; Central European Institute of Technology; University of South Australia; Technische Universität Kaiserslautern; Monash University; Technische Universiteit Delft; University of Technology Sydney; Itä-Suomen Yliopisto; Eberhard Karls Universität Tübingen; Aix-Marseille Université; Universiteit Leiden; University College Cork; Université de La Réunion; Brown University; Jilin University; National University of Singapore; Indian Institute of Technology Palakkad; Commonwealth Scientific and Industrial Research Organisation; Institut National des Sciences Appliquées Rouen; Danmarks Tekniske Universitet; Shenzhen Technology University; Sorbonne Université; Kungliga Tekniska Högskolan; Ulster University; Universidade do Porto; Utah State University; Indian Institute of Technology, Patna; Beihang University; University of Twente; University of Bristol; University of Macedonia; Shandong University; Politechnika Warszawska; Université Bretagne Sud; Institut \"Jožef Stefan\"; University College London; Universität Passau; Deakin University; Universiti Kuala Lumpur; Helsingin Yliopisto; Arizona State University; Università degli Studi di Cagliari; Université Catholique de Louvain; Politecnico di Torino; Universität Bielefeld; Université Grenoble Alpes; Peking University; KU Leuven; Kyungpook National University; University of New South Wales; National University of Ireland; Institut National Polytechnique de Toulouse; Microsoft Research; Högskolan i Halmstad; University of Alberta; Università degli Studi di Napoli Federico II; New Mexico State University; Università degli Studi di Milano; Université du Luxembourg; Universidad de Zaragoza; University of Waikato; Georgia State University; University of Texas at San Antonio; TU Graz, Internationale Beziehungen und Mobilitätsprogramme; Zhejiang University; Université Paris-Saclay; Aalto-Yliopisto; University of Galway; Beijing Normal University; Philipps-Universität Marburg; Georgia Institute of Technology; Technische Universiteit Eindhoven; University of Ottawa; Indian National Science Academy; Universita degli Studi di Bari Aldo Moro; Université de Neuchâtel; University College Dublin; Université de Lyon; Yonsei University","keywords":"Computer science; Knowledge extraction; Database; Artificial intelligence; Information retrieval","score_opus":0.024445144512082982,"score_gpt":0.2906166420676732,"score_spread":0.2661714975555902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360985784","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004635329,0.2597681,0.5984489,0.007553297,0.0043354067,0.0003002367,0.0020280518,0.0021767137,0.12075399],"genre_scores_gemma":[0.045371886,0.18120953,0.545715,0.0030710488,0.00414011,0.0004037424,0.005208564,0.00074222067,0.21413797],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990596,0.00018952906,0.00008884657,0.00014249772,0.00048671025,0.000032737204],"domain_scores_gemma":[0.9975062,0.0018472255,0.00008280166,0.000264167,0.00023900918,0.000060690996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010223477,0.00084265234,0.0016497052,0.0025552816,0.00051248306,0.004103264,0.0014350653,0.00085436105,0.014226699],"category_scores_gemma":[0.0043096617,0.00067518523,0.00084276235,0.0071022473,0.0011092684,0.0057409825,0.0014138771,0.0020989408,0.00938921],"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":[0.00006038981,0.000083153915,0.00043509618,0.0018632549,0.000103939026,0.00014537957,0.00015794489,0.0046024676,0.0012510429,0.15520544,0.13710928,0.69898266],"study_design_scores_gemma":[0.000027743301,0.000046173507,0.0008203212,0.00061908335,0.0000770086,0.00085935474,0.000112455564,0.027553957,0.0016254168,0.3994712,0.5687559,0.000031399497],"about_ca_topic_score_codex":0.00083954394,"about_ca_topic_score_gemma":0.00080515514,"teacher_disagreement_score":0.014226699,"about_ca_system_score_codex":0.0007953959,"about_ca_system_score_gemma":0.0008812106,"threshold_uncertainty_score":0.047593057},"labels":[],"label_agreement":null},{"id":"W4362585011","doi":"10.48084/etasr.5683","title":"Multi-level Association Rule Mining for the Discovery of Strong Underrepresented Patterns","year":2023,"lang":"en","type":"article","venue":"Engineering Technology & Applied Science Research","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"International Development Research Centre; Styrelsen för Internationellt Utvecklingssamarbete","keywords":"Tanzania; Production (economics); Business; Dairy farming; Agriculture; Milk production; Agricultural science; Population; Association rule learning; Cluster (spacecraft); Agricultural economics; Geography; Environmental health; Economics; Environmental science; Environmental planning; Biology; Animal science; Medicine; Computer science; Data mining","score_opus":0.1066213340430877,"score_gpt":0.3716883813356935,"score_spread":0.2650670472926058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362585011","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.091103345,0.0033736832,0.89450645,0.0011689973,0.00016235135,0.0007560166,0.004494464,0.0028222662,0.0016123777],"genre_scores_gemma":[0.38281086,0.00092980225,0.60806185,0.00042699763,0.00009363002,0.00075079297,0.0060904115,0.00008200621,0.0007536514],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9893141,0.0030810775,0.0022251285,0.002801816,0.002080139,0.0004977432],"domain_scores_gemma":[0.9650773,0.025642179,0.0035999827,0.0024168324,0.0027872738,0.00047649766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009303084,0.0014479775,0.003031633,0.009439099,0.0015187741,0.0029996876,0.0027341205,0.0016400807,0.0014761848],"category_scores_gemma":[0.03182368,0.0008788367,0.0034746295,0.007523662,0.00084370724,0.0025860968,0.0022951523,0.0026466765,0.0012343469],"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":[0.00089124613,0.0014114504,0.16989657,0.0027502452,0.003232733,0.003268685,0.0019518905,0.09259983,0.011330074,0.008909321,0.0077191186,0.69603884],"study_design_scores_gemma":[0.00013481978,0.0005179771,0.020182947,0.00063886284,0.00093754363,0.0020288427,0.001172626,0.9133263,0.0077030966,0.043092936,0.010127514,0.00013651389],"about_ca_topic_score_codex":0.004656531,"about_ca_topic_score_gemma":0.0070879566,"teacher_disagreement_score":0.009439099,"about_ca_system_score_codex":0.0007731672,"about_ca_system_score_gemma":0.0031349221,"threshold_uncertainty_score":0.04919994},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2347716,0.0016256642,0.74157935,0.0009055607,0.00030543082,0.00071904395,0.012217961,0.0062748347,0.0016005246],"genre_scores_gemma":[0.5205088,0.00073787203,0.45108843,0.00017541356,0.00033527098,0.0004902874,0.02468143,0.0002568169,0.0017257128],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975858,0.0003067527,0.00029702074,0.0005850206,0.0009914628,0.00023399405],"domain_scores_gemma":[0.9872694,0.0072215796,0.0013049309,0.001361632,0.0022510067,0.0005913974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032122112,0.0011085037,0.0014044873,0.007083253,0.0011945434,0.0027670944,0.0017513352,0.0012146657,0.0016137034],"category_scores_gemma":[0.01731845,0.0005690866,0.0015266554,0.004317969,0.00083029026,0.0029812611,0.0014186287,0.0014971053,0.00064680865],"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":[0.002539031,0.0012642308,0.11654679,0.0014571601,0.0006523001,0.00570815,0.0013071338,0.105635114,0.016584247,0.036382854,0.028044723,0.68387824],"study_design_scores_gemma":[0.00011488122,0.00020211704,0.005832409,0.0001020176,0.000115485935,0.0013380266,0.00036946073,0.94646114,0.0048271185,0.034041304,0.006561076,0.00003494276],"about_ca_topic_score_codex":0.0043692617,"about_ca_topic_score_gemma":0.0050055915,"teacher_disagreement_score":0.007083253,"about_ca_system_score_codex":0.00065968285,"about_ca_system_score_gemma":0.0024181183,"threshold_uncertainty_score":0.016988039},"labels":[],"label_agreement":null},{"id":"W4366384295","doi":"10.3138/cjpe.28.009","title":"Aldrick, J. O., &amp; Rodriguez, H. M. (2013). <i>Building SPSS Graphs to Understand Data.</i>","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Mathematics; Sociology; Statistics; Combinatorics","score_opus":0.1823983063883564,"score_gpt":0.3739319899069526,"score_spread":0.19153368351859618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384295","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018462986,0.05617537,0.6229767,0.1291332,0.0072080432,0.0013926427,0.01644432,0.0077882884,0.14041847],"genre_scores_gemma":[0.14476901,0.08118999,0.6823034,0.016169166,0.002300751,0.0019118642,0.00920749,0.0033005236,0.058847815],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963225,0.0013594114,0.00034525082,0.00018368092,0.0017070142,0.000082158855],"domain_scores_gemma":[0.91535133,0.06348648,0.0041556843,0.002236193,0.0139147565,0.0008555954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011339428,0.0007230038,0.0005161675,0.008247463,0.0014492052,0.004112928,0.0015632838,0.0009644924,0.016657367],"category_scores_gemma":[0.101836085,0.0006107756,0.00071377534,0.008338155,0.002173287,0.004157667,0.0013819081,0.0027081617,0.008382142],"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":[0.00011766795,0.00007963171,0.0074341493,0.0015241908,0.00009239176,0.0001415791,0.002781312,0.0006479096,0.0012975528,0.015722249,0.43047854,0.5396828],"study_design_scores_gemma":[0.00008200234,0.00019284531,0.033451855,0.0031848247,0.0004443934,0.00055793603,0.005036926,0.0033869548,0.006090335,0.06851832,0.8788881,0.00016548033],"about_ca_topic_score_codex":0.018097369,"about_ca_topic_score_gemma":0.045373585,"teacher_disagreement_score":0.018097369,"about_ca_system_score_codex":0.0017902972,"about_ca_system_score_gemma":0.0037884095,"threshold_uncertainty_score":0.059969306},"labels":[],"label_agreement":null},{"id":"W4367191078","doi":"10.48550/arxiv.2304.13717","title":"Association Rules Mining with Auto-Encoders","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Institut National de Santé Publique du Québec","keywords":"Association rule learning; Categorical variable; Computer science; Data mining; Cluster analysis; Set (abstract data type); Artificial neural network; Artificial intelligence; Machine learning","score_opus":0.08079737389236294,"score_gpt":0.19324414438348153,"score_spread":0.11244677049111859,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367191078","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051488344,0.0009424997,0.93909365,0.00045237268,0.00010051642,0.0001862335,0.00091437367,0.0050378446,0.0017841073],"genre_scores_gemma":[0.33872712,0.00052747125,0.6553412,0.0003547636,0.00008977445,0.0002941684,0.0022252908,0.00016927657,0.002270908],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978381,0.00062249,0.00025258533,0.0005057997,0.00063429854,0.0001469045],"domain_scores_gemma":[0.989669,0.006487344,0.0005315364,0.0012381749,0.0019447725,0.00012921348],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030094278,0.0008338621,0.0014631615,0.002621224,0.00059770356,0.0013823636,0.0023656264,0.0010354212,0.002072763],"category_scores_gemma":[0.013485545,0.0008317314,0.0011606578,0.0024151169,0.00058464764,0.0017910029,0.0013052138,0.0016603953,0.001179371],"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":[0.00031891046,0.00033460264,0.008468091,0.00028290166,0.00022950627,0.00041702675,0.00018369715,0.22311254,0.0035718256,0.007115862,0.005287444,0.75067765],"study_design_scores_gemma":[0.000026194235,0.000044451106,0.00069655216,0.000035891506,0.000044580847,0.00018556108,0.00003059322,0.9865975,0.0025402152,0.008528137,0.0012576518,0.000012699942],"about_ca_topic_score_codex":0.005970751,"about_ca_topic_score_gemma":0.007382981,"teacher_disagreement_score":0.005970751,"about_ca_system_score_codex":0.0007075999,"about_ca_system_score_gemma":0.0017899515,"threshold_uncertainty_score":0.015915573},"labels":[],"label_agreement":null},{"id":"W4367310345","doi":"10.24143/2072-9502-2023-2-116-124","title":"Model and algorithm for supporting decision on selection of products for recommendation to user based on analysis of statistical implication","year":2023,"lang":"en","type":"article","venue":"VESTNIK OF ASTRAKHAN STATE TECHNICAL UNIVERSITY SERIES MANAGEMENT COMPUTER SCIENCE AND INFORMATICS","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Edgewood Chemical Biological Center; H2020 European Research Council; Réseau québécois de recherche sur la douleur","keywords":"Computer science; Association rule learning; Recommender system; Data mining; Ranking (information retrieval); Cluster analysis; Measure (data warehouse); Credibility; Inference; Set (abstract data type); Information retrieval; Quality (philosophy); Transparency (behavior); Filter (signal processing); Collaborative filtering; Rank (graph theory); Machine learning; Artificial intelligence; Mathematics","score_opus":0.016984087689850897,"score_gpt":0.2713769939555745,"score_spread":0.25439290626572364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367310345","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011361887,0.00029531174,0.98281974,0.00060768914,0.00006257484,0.00024861575,0.00025419737,0.0007135563,0.0036364049],"genre_scores_gemma":[0.2889371,0.00056681916,0.7010694,0.00035600213,0.00010526063,0.0011724571,0.0009396606,0.00006902411,0.006784316],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990089,0.00019500153,0.000082908125,0.0002613336,0.00032223001,0.00012959115],"domain_scores_gemma":[0.9985061,0.00093792635,0.00010764716,0.00005715751,0.00035388293,0.000037233454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013366331,0.0008058068,0.0016070082,0.0014651283,0.00090613915,0.0019224067,0.0022927905,0.0018518487,0.005854294],"category_scores_gemma":[0.0038313167,0.0004278794,0.001033784,0.0013708097,0.0005225475,0.001690721,0.0010567458,0.0015687264,0.0015192543],"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":[0.00042657214,0.0003332754,0.004599924,0.00030858009,0.00015092369,0.0004919501,0.0002444235,0.61936074,0.0022519573,0.039293032,0.008285871,0.32425272],"study_design_scores_gemma":[0.000034748246,0.000053710384,0.00020821547,0.000016311044,0.000028242903,0.00008234543,0.00002022009,0.9872515,0.00047081162,0.010568253,0.001256916,0.000008626473],"about_ca_topic_score_codex":0.009407985,"about_ca_topic_score_gemma":0.006236464,"teacher_disagreement_score":0.009407985,"about_ca_system_score_codex":0.0013490565,"about_ca_system_score_gemma":0.0026626317,"threshold_uncertainty_score":0.019584596},"labels":[],"label_agreement":null},{"id":"W4377002668","doi":"10.2139/ssrn.4451229","title":"Soilfoodwebs: An R Package for Analyzing and Simulating Nutrient Fluxes Through Food Webs","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Data Mining Algorithms and Applications","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":"Western University; Natural Resources Canada","funders":"","keywords":"Nutrient; Environmental science; R package; Ecology; Biology; Mathematics; Statistics","score_opus":0.048242410808014356,"score_gpt":0.30840003168383046,"score_spread":0.2601576208758161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377002668","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.093981415,0.0008636463,0.53007376,0.0005122477,0.00037580344,0.0003102811,0.1312099,0.23416606,0.00850695],"genre_scores_gemma":[0.27307758,0.0011329843,0.56930315,0.00046191693,0.00012796828,0.0018360169,0.09769995,0.04835117,0.008009258],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9996538,0.00010964127,0.000033338965,0.00009481098,0.00006996279,0.000038391656],"domain_scores_gemma":[0.99868935,0.00080679526,0.000095505566,0.00019426156,0.00015738055,0.00005667099],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010443343,0.0017833395,0.0013022623,0.0013537201,0.00039897836,0.0012381378,0.003032087,0.001062193,0.015476415],"category_scores_gemma":[0.0048867273,0.0010790799,0.0019932028,0.0018524976,0.00041458086,0.0013952452,0.0010829872,0.0015072341,0.0073869275],"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":[0.00066389045,0.0003043103,0.028873634,0.0024181448,0.0024076172,0.0005784473,0.00057323003,0.630736,0.009948443,0.01919346,0.21101393,0.09328887],"study_design_scores_gemma":[0.00031316277,0.0000933026,0.0031690334,0.0000619255,0.0002773118,0.00019404585,0.00007257716,0.9164156,0.006232246,0.016195135,0.056875028,0.00010060958],"about_ca_topic_score_codex":0.012225936,"about_ca_topic_score_gemma":0.013421517,"teacher_disagreement_score":0.015476415,"about_ca_system_score_codex":0.0005229568,"about_ca_system_score_gemma":0.0014414808,"threshold_uncertainty_score":0.051773727},"labels":[],"label_agreement":null},{"id":"W43770393","doi":"","title":"Extended fast feature selection for classification modeling","year":2006,"lang":"en","type":"article","venue":"Annual Conference on Computers","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint Mary's University; Dalhousie University","funders":"","keywords":"Feature selection; Computer science; Data mining; Feature (linguistics); Minimum redundancy feature selection; Filter (signal processing); Selection (genetic algorithm); Set (abstract data type); Artificial intelligence; Quality (philosophy); Data set; Process (computing); Pattern recognition (psychology); Feature extraction; Machine learning","score_opus":0.037718329484804525,"score_gpt":0.2823586606316843,"score_spread":0.24464033114687977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W43770393","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00375798,0.00028153177,0.9950808,0.000066728615,0.000032376196,0.000043836753,0.00007653735,0.00048968097,0.00017059196],"genre_scores_gemma":[0.20453826,0.0010440361,0.78971,0.00012146293,0.00018862022,0.00066497416,0.0009173335,0.00015839032,0.0026570596],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846715,0.00051626656,0.00009378208,0.00025364858,0.00054116244,0.00012795272],"domain_scores_gemma":[0.9980178,0.001022848,0.00012959934,0.00023257222,0.000563437,0.00003375424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002759943,0.0013168555,0.0015401704,0.0018211605,0.0006125757,0.0008522609,0.0012088191,0.00081439264,0.0022648242],"category_scores_gemma":[0.0052572703,0.0004373046,0.0017312709,0.0026062028,0.00040146802,0.0013146639,0.00076095195,0.001192881,0.0009429663],"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":[0.00024625394,0.00008948793,0.0016518106,0.00016951015,0.00019885713,0.00025736453,0.00013279766,0.29279664,0.009464455,0.010140823,0.0058648787,0.67898715],"study_design_scores_gemma":[0.000022824326,0.000065267646,0.0006522721,0.000011126764,0.000024604908,0.00010845762,0.000010636378,0.9882945,0.0019767715,0.005073962,0.0037392806,0.000020303705],"about_ca_topic_score_codex":0.0052017774,"about_ca_topic_score_gemma":0.003191127,"teacher_disagreement_score":0.0052017774,"about_ca_system_score_codex":0.0005389374,"about_ca_system_score_gemma":0.0011492644,"threshold_uncertainty_score":0.014596164},"labels":[],"label_agreement":null},{"id":"W4378673239","doi":"10.54097/hset.v49i.8586","title":"Fundamental results in probability theory","year":2023,"lang":"en","type":"article","venue":"Highlights in Science Engineering and Technology","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Mathematics; Central limit theorem; Random variable; Independent and identically distributed random variables; Chebyshev's inequality; Law of large numbers; Probability theory; Applied mathematics; Discrete mathematics; Statistics; Mathematical analysis","score_opus":0.0118484496285424,"score_gpt":0.23873538061014904,"score_spread":0.22688693098160664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378673239","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0066359327,0.06335283,0.700639,0.016739665,0.0041420585,0.00017548502,0.0022435235,0.00052657677,0.20554493],"genre_scores_gemma":[0.43162394,0.13859767,0.3054893,0.0114129735,0.028261105,0.0015824873,0.0033081272,0.0007422828,0.07898204],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99614954,0.0010101948,0.00028908777,0.0006700365,0.0016162078,0.000265054],"domain_scores_gemma":[0.9924982,0.0052308105,0.0003873466,0.0005311015,0.0011343902,0.00021806624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003981158,0.0016531172,0.002226854,0.0037958657,0.0021428394,0.005720575,0.0017990986,0.0024181297,0.012724049],"category_scores_gemma":[0.010746644,0.00055987685,0.0021384687,0.0047946437,0.0055329395,0.006797274,0.0026009888,0.006296602,0.0061273267],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006293357,0.000012781603,0.00014088198,0.00018689087,0.000020263484,0.00007605444,0.00015873101,0.0017953976,0.00011673258,0.97502214,0.008482302,0.013981518],"study_design_scores_gemma":[0.0000060955826,0.000012968662,0.00013689665,0.00011135937,0.000008559248,0.00013127385,0.000036878737,0.0038663866,0.00007488509,0.95248914,0.043113038,0.000012554372],"about_ca_topic_score_codex":0.0023480821,"about_ca_topic_score_gemma":0.00085144554,"teacher_disagreement_score":0.012724049,"about_ca_system_score_codex":0.003373584,"about_ca_system_score_gemma":0.0023340564,"threshold_uncertainty_score":0.04256618},"labels":[],"label_agreement":null},{"id":"W4379522577","doi":"10.21428/594757db.ae5fdc67","title":"Towards an Automated Framework of Root Cause Analysis in the Canadian Telecom Industry","year":2023,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Bell (Canada)","funders":"","keywords":"Telecommunications; Telecom infrastructure sharing; Process (computing); Enhanced Telecom Operations Map; Telecommunications service; Reliability (semiconductor); Service (business); The Internet; Business; Root cause; Root (linguistics); Population; Computer science; Service provider; Marketing; Engineering; Operations management; World Wide Web","score_opus":0.032624338659444765,"score_gpt":0.33074561899340094,"score_spread":0.2981212803339562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379522577","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01795639,0.0009282682,0.96761775,0.0020149127,0.00006820778,0.0009413925,0.0028471004,0.00338235,0.0042437445],"genre_scores_gemma":[0.14955363,0.0005893486,0.8447922,0.00017425431,0.000034981327,0.00034818973,0.0025088505,0.000132881,0.0018657892],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9940148,0.0018199938,0.0006196716,0.0010616309,0.0019587732,0.00052526384],"domain_scores_gemma":[0.98429614,0.008171197,0.001164998,0.0009155885,0.005076734,0.0003752506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008637063,0.0013771167,0.001396131,0.013773377,0.0037600785,0.0066032577,0.0036551284,0.0016240204,0.002970363],"category_scores_gemma":[0.032390457,0.00086583867,0.0022846186,0.007390292,0.0016479008,0.002430885,0.0034635337,0.0019737056,0.00080985663],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024692292,0.0004602392,0.045088258,0.0010702219,0.0007468632,0.0026474963,0.0037331695,0.35747024,0.0052208514,0.16474622,0.02206976,0.39649972],"study_design_scores_gemma":[0.00004097643,0.00003087717,0.0064315083,0.00019002827,0.0001372051,0.00026282063,0.0011890639,0.93185973,0.0019730467,0.040258627,0.017550198,0.0000759113],"about_ca_topic_score_codex":0.7435155,"about_ca_topic_score_gemma":0.79264104,"teacher_disagreement_score":0.2564845,"about_ca_system_score_codex":0.013631808,"about_ca_system_score_gemma":0.03926414,"threshold_uncertainty_score":0.51598996},"labels":[],"label_agreement":null},{"id":"W4379740345","doi":"10.1145/3555776.3577848","title":"Classification by Frequent Association Rules","year":2023,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Interpretability; Computer science; Artificial intelligence; Associative property; Random subspace method; Machine learning; Association rule learning; Majority rule; Feature (linguistics); Class (philosophy); Rank (graph theory); Data mining; Pattern recognition (psychology); Support vector machine; Mathematics","score_opus":0.025762270761889406,"score_gpt":0.2697516979453656,"score_spread":0.24398942718347616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379740345","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13041984,0.008574435,0.8408567,0.0019880687,0.00068200444,0.0008667762,0.006626934,0.0030021605,0.0069831223],"genre_scores_gemma":[0.5774762,0.004500851,0.39809746,0.00066716067,0.00080693624,0.0010751323,0.013791642,0.00016790366,0.0034167406],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9908449,0.00181034,0.0012381349,0.002362845,0.0032685127,0.00047523345],"domain_scores_gemma":[0.98318994,0.009692226,0.0020553516,0.0019384107,0.0028223647,0.0003017022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00470995,0.0015294803,0.0022149896,0.009906778,0.0011827986,0.00393571,0.0026695926,0.0017733991,0.0020015913],"category_scores_gemma":[0.024190798,0.000728846,0.0024174133,0.0075188177,0.00082870625,0.004655826,0.0015930958,0.0018238879,0.001894355],"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":[0.0006190053,0.00061759923,0.080196045,0.0010399668,0.00080656714,0.0023723198,0.00059913314,0.07405649,0.0042991336,0.016806887,0.02034942,0.7982374],"study_design_scores_gemma":[0.00008658557,0.0003372406,0.014868095,0.00045855384,0.00047862218,0.0046335314,0.00050543534,0.8239252,0.006530822,0.12060845,0.027422722,0.00014481298],"about_ca_topic_score_codex":0.0026565064,"about_ca_topic_score_gemma":0.0025347292,"teacher_disagreement_score":0.009906778,"about_ca_system_score_codex":0.00077016983,"about_ca_system_score_gemma":0.0012089757,"threshold_uncertainty_score":0.02490884},"labels":[],"label_agreement":null},{"id":"W4381161845","doi":"10.20944/preprints202306.1378.v1","title":"Algorithm-based Data Generation (ADG) Engine for Data Analytics","year":2023,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Big data; Computer science; Analytics; Data analysis; Domain (mathematical analysis); Data science; Data mining","score_opus":0.5410040128402656,"score_gpt":0.4267004535432325,"score_spread":0.11430355929703306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381161845","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033562358,0.00037787567,0.9646842,0.00037705997,0.00014612974,0.00035397397,0.0024108593,0.026537163,0.0017565788],"genre_scores_gemma":[0.043435037,0.0002570757,0.94654995,0.00024943214,0.000061651524,0.00046955261,0.0067507275,0.0012027107,0.0010238074],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996624,0.00086828764,0.00046445493,0.00065788336,0.0012565363,0.00012888318],"domain_scores_gemma":[0.9924345,0.0031511432,0.0002936719,0.0025838471,0.0013359102,0.0002009508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050483686,0.0015106271,0.0010492466,0.0037172525,0.00088467385,0.0029851114,0.0028018008,0.0012214239,0.005664958],"category_scores_gemma":[0.016021043,0.00072491314,0.0015430497,0.0043948335,0.0009203636,0.0027297724,0.002584711,0.0025161766,0.0052655735],"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":[0.0008101422,0.00046533888,0.008395842,0.0011192645,0.00037331777,0.0005388117,0.0005160973,0.055183616,0.017093495,0.06058708,0.104742214,0.7501747],"study_design_scores_gemma":[0.00023451283,0.00016744572,0.0018092538,0.0001586191,0.00009212506,0.00074487773,0.00017560314,0.7300806,0.038903143,0.11058981,0.11695307,0.00009091797],"about_ca_topic_score_codex":0.0017854414,"about_ca_topic_score_gemma":0.0019892892,"teacher_disagreement_score":0.005664958,"about_ca_system_score_codex":0.0010715501,"about_ca_system_score_gemma":0.0018496483,"threshold_uncertainty_score":0.026698649},"labels":[],"label_agreement":null},{"id":"W4381803488","doi":"10.5753/sbcars_estendido.2008.24361","title":"Módulo de Integração de Padrões de Análise com Ontologias de Domínio da ferramenta ArgoCASEGEO","year":2008,"lang":"pt","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dominican University College","funders":"","keywords":"Humanities; Physics; Computer science; Philosophy","score_opus":0.07566925162367272,"score_gpt":0.31311332234670347,"score_spread":0.23744407072303075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381803488","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04773381,0.00063092355,0.9326462,0.0011721387,0.00016947185,0.0004293794,0.00041013028,0.0033721295,0.013435791],"genre_scores_gemma":[0.20518838,0.0007364548,0.7790701,0.00022168632,0.00013785469,0.0003869956,0.000749559,0.00058164104,0.012927361],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9931299,0.0013762158,0.0008640149,0.0014545317,0.0028536527,0.00032166849],"domain_scores_gemma":[0.98988813,0.004127754,0.000788609,0.0031132465,0.0017049605,0.00037735223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0060015954,0.0011613031,0.001009596,0.003251723,0.0016975907,0.008287902,0.0016862184,0.0013050243,0.006975234],"category_scores_gemma":[0.020638132,0.0009090114,0.0025412648,0.0025141083,0.0025121004,0.008832223,0.0065149027,0.0022901294,0.0015117755],"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":[0.0004939116,0.00042449078,0.016482193,0.0012710646,0.0002743454,0.0016275033,0.011708914,0.011423786,0.03980055,0.382487,0.005082334,0.52892387],"study_design_scores_gemma":[0.00013946315,0.00057500997,0.012086232,0.0008327976,0.0005637114,0.0026856386,0.0042764805,0.139346,0.06956344,0.470535,0.2991717,0.00022457707],"about_ca_topic_score_codex":0.0029789219,"about_ca_topic_score_gemma":0.002906058,"teacher_disagreement_score":0.008287902,"about_ca_system_score_codex":0.0013709364,"about_ca_system_score_gemma":0.0025864842,"threshold_uncertainty_score":0.03173983},"labels":[],"label_agreement":null},{"id":"W4384519228","doi":"10.1109/tsc.2023.3294945","title":"An Approach for Incremental Mining of Clickstream Patterns as a Service Application","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Services Computing","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Clickstream; Computer science; Data mining; Service (business); Table (database); Machine learning; Data science; World Wide Web; Web service","score_opus":0.023143972159703322,"score_gpt":0.2930586040618406,"score_spread":0.26991463190213727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384519228","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052351862,0.00062619575,0.93286496,0.0004840463,0.00013169285,0.00044351746,0.0010921011,0.010526334,0.001479242],"genre_scores_gemma":[0.38287413,0.0004137329,0.6102323,0.00028883733,0.000147895,0.0003608594,0.00330709,0.00025408767,0.002121192],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981427,0.00019890569,0.0002336799,0.00036789506,0.00087997573,0.00017677226],"domain_scores_gemma":[0.99659914,0.00090773305,0.00020714804,0.0006647134,0.0013661501,0.00025511326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013545164,0.0009890947,0.0011289218,0.0041253786,0.00084312545,0.0016831373,0.0023343673,0.00093569997,0.0009918866],"category_scores_gemma":[0.006754641,0.00050571153,0.0011739463,0.004853648,0.0004970263,0.003125294,0.0017736566,0.0010890296,0.0008942866],"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":[0.0007747022,0.000481415,0.026036365,0.0003319431,0.00016100121,0.0011042707,0.0004871683,0.026899962,0.022385743,0.009589314,0.011698932,0.9000492],"study_design_scores_gemma":[0.00006128398,0.00024401657,0.003810093,0.00002148201,0.00008950454,0.0013572803,0.0002019807,0.9541732,0.017029209,0.013410665,0.009541635,0.000059654845],"about_ca_topic_score_codex":0.005825577,"about_ca_topic_score_gemma":0.0064434703,"teacher_disagreement_score":0.005825577,"about_ca_system_score_codex":0.0005954667,"about_ca_system_score_gemma":0.0017829456,"threshold_uncertainty_score":0.011583328},"labels":[],"label_agreement":null},{"id":"W4385078254","doi":"10.18280/isi.280303","title":"Os-ETL: A High-Efficiency, Open-Scala Solution for Integrating Heterogeneous Data in Large-Scale Data Warehousing","year":2023,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"University of Tlemcen","keywords":"Data warehouse; Scala; Computer science; Database; Scale (ratio); Operating system; Java; Geography","score_opus":0.056956528185854026,"score_gpt":0.30914470654650733,"score_spread":0.2521881783606533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385078254","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011174561,0.00016324184,0.8708575,0.00086666096,0.00020659312,0.00045726149,0.0015122757,0.10803564,0.006726205],"genre_scores_gemma":[0.108194955,0.00053349766,0.83757067,0.0010136899,0.00022769524,0.0007078384,0.014076625,0.023577627,0.014097394],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964012,0.00043062444,0.00035299215,0.0007970771,0.0015902525,0.00042788495],"domain_scores_gemma":[0.9947476,0.00091995846,0.00045701728,0.002222189,0.0010271412,0.00062603306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0051025623,0.001859001,0.0009080271,0.0015130341,0.0017958534,0.0043680645,0.0065538594,0.0011165316,0.0070680007],"category_scores_gemma":[0.007886446,0.001468642,0.0025728694,0.0026392732,0.002699503,0.007972743,0.008636454,0.00383539,0.0051469794],"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":[0.0026125791,0.0011676557,0.021180797,0.0016721415,0.0011187717,0.0023169941,0.0046052155,0.10098465,0.095358774,0.14129755,0.24124463,0.38644022],"study_design_scores_gemma":[0.00051293516,0.00025936248,0.005388426,0.00016963191,0.00014554134,0.0004968197,0.0007544244,0.5492404,0.06856041,0.08311955,0.29096857,0.0003839625],"about_ca_topic_score_codex":0.015454597,"about_ca_topic_score_gemma":0.011660928,"teacher_disagreement_score":0.015454597,"about_ca_system_score_codex":0.0025676787,"about_ca_system_score_gemma":0.0045652664,"threshold_uncertainty_score":0.030729294},"labels":[],"label_agreement":null},{"id":"W4385221855","doi":"10.5465/amproc.2023.19638abstract","title":"Validity of Computationally Derived Patterns: An Algorithmic Inference Quality Framework","year":2023,"lang":"en","type":"article","venue":"Academy of Management Proceedings","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Inference; Computer science; Quality (philosophy); Artificial intelligence; Epistemology","score_opus":0.0871069315162744,"score_gpt":0.3717158387899408,"score_spread":0.2846089072736664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385221855","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01173025,0.00031899352,0.9788092,0.0039907,0.00005940169,0.00037333922,0.00024975653,0.00017340333,0.0042950152],"genre_scores_gemma":[0.36735255,0.00030519435,0.62785465,0.00096931285,0.0002164414,0.0019046036,0.0006189667,0.0001378659,0.00064045645],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.7673542,0.1625575,0.016263695,0.014184721,0.036950804,0.002689082],"domain_scores_gemma":[0.26710162,0.6235928,0.029262232,0.044441998,0.033608735,0.0019925975],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22246352,0.0017434359,0.0026332503,0.011981335,0.003881638,0.012289865,0.006058455,0.005630244,0.0045318054],"category_scores_gemma":[0.5973075,0.001468663,0.0045645055,0.007449067,0.019186027,0.018588599,0.010701666,0.008493294,0.0005645835],"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":[0.00013362837,0.00012634655,0.012145035,0.00055605854,0.00028922723,0.0001236358,0.0022177736,0.033712104,0.00038438867,0.9055955,0.0012476785,0.04346872],"study_design_scores_gemma":[0.00007965206,0.0000862728,0.0015291949,0.00030169956,0.000094496296,0.00007788228,0.00038394768,0.10132027,0.00066539005,0.893292,0.002113591,0.000055578108],"about_ca_topic_score_codex":0.0047524567,"about_ca_topic_score_gemma":0.0029627276,"teacher_disagreement_score":0.7775365,"about_ca_system_score_codex":0.00834831,"about_ca_system_score_gemma":0.010887098,"threshold_uncertainty_score":0.9588409},"labels":[],"label_agreement":null},{"id":"W4385486861","doi":"10.1007/978-3-031-33390-3_9","title":"Trees","year":2023,"lang":"en","type":"book-chapter","venue":"Statisctics and computing/Statistics and computing","topic":"Data Mining Algorithms 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":"Decision tree; Mathematics; Rectangle; Combinatorics; Boosting (machine learning); Artificial intelligence; Computer science; Discrete mathematics; Theoretical computer science","score_opus":0.02492851284539378,"score_gpt":0.26491244602047254,"score_spread":0.23998393317507877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385486861","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0078455,0.002962476,0.4987082,0.0021054815,0.0016458357,0.0004722878,0.021901578,0.014602552,0.44975612],"genre_scores_gemma":[0.083214045,0.0036169267,0.35699558,0.0021461097,0.000784254,0.0006398713,0.044325598,0.006307551,0.50197005],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993299,0.0000726621,0.000029896037,0.00020449296,0.00028349238,0.0000794972],"domain_scores_gemma":[0.9991731,0.00019782492,0.00003595784,0.00029604175,0.00023297204,0.00006404264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039282796,0.0006955042,0.00066901976,0.0015693092,0.0010834953,0.002548423,0.0012730138,0.0009600953,0.117700726],"category_scores_gemma":[0.0024398933,0.00047156794,0.00085768127,0.0021702803,0.0005359662,0.002824315,0.0014302323,0.0017474066,0.086149864],"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":[0.00009506943,0.00007046348,0.00043557477,0.00027825375,0.000034128712,0.00008329147,0.00014250517,0.0042574,0.003088072,0.24547878,0.3077825,0.43825403],"study_design_scores_gemma":[0.00002184387,0.000028268068,0.000248028,0.00008623746,0.000026213644,0.00020939013,0.00006202832,0.012857526,0.0028308267,0.24684508,0.73676765,0.000016953816],"about_ca_topic_score_codex":0.0012105872,"about_ca_topic_score_gemma":0.0024295985,"teacher_disagreement_score":0.117700726,"about_ca_system_score_codex":0.00055255607,"about_ca_system_score_gemma":0.00089529186,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W4385562579","doi":"10.1145/3580305.3599200","title":"The 4th International Workshop on Talent and Management Computing (TMC'2023)","year":2023,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Stony Brook University; University of Science and Technology of China; Carnegie Mellon University; Tianjin University; University of Tennessee, Knoxville; Harbin Institute of Technology; Dalian University of Technology; Baidu; Nanjing University; Beihang University; University of Notre Dame; Nanjing University of Science and Technology; York University","keywords":"Big data; Talent management; Business intelligence; Data management; Knowledge management; Data science; Computer science; Scale (ratio); Competitive intelligence; Technology management; Business","score_opus":0.026231392361159393,"score_gpt":0.29207327575091657,"score_spread":0.26584188338975717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385562579","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016973298,0.09863078,0.3762369,0.10628947,0.14690249,0.001787061,0.009098528,0.008227146,0.23585434],"genre_scores_gemma":[0.09196148,0.051463332,0.23675725,0.015972283,0.028866766,0.0017615473,0.02866383,0.0042734547,0.54028004],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99496317,0.0015680165,0.00025802996,0.0009483592,0.0014765073,0.00078598876],"domain_scores_gemma":[0.9925619,0.0015058547,0.0001798427,0.0011658575,0.0021597657,0.0024267745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008052708,0.0014892622,0.0017598213,0.0027743776,0.0017014156,0.008338802,0.0036285988,0.003298979,0.059232987],"category_scores_gemma":[0.008812333,0.000614022,0.001709736,0.0032989306,0.0013344543,0.006556499,0.005625257,0.0046391236,0.034102343],"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":[0.00027492095,0.00023037834,0.0006519258,0.0004199258,0.000057778772,0.00014102449,0.00033348246,0.001354134,0.0020987103,0.016997978,0.69543207,0.28200763],"study_design_scores_gemma":[0.000026906784,0.00009503235,0.0010252548,0.00040272248,0.000027965878,0.00018247926,0.0003261475,0.0055551855,0.0013348705,0.01725619,0.9737307,0.000036575188],"about_ca_topic_score_codex":0.0044267387,"about_ca_topic_score_gemma":0.006857023,"teacher_disagreement_score":0.059232987,"about_ca_system_score_codex":0.0026260652,"about_ca_system_score_gemma":0.004875307,"threshold_uncertainty_score":0.19815403},"labels":[],"label_agreement":null},{"id":"W4385701495","doi":"10.1007/978-3-031-39831-5_13","title":"Bitwise Vertical Mining of Minimal Rare Patterns","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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 Manitoba","funders":"","keywords":"Computer science; Data mining; Association rule learning; Bitwise operation; Rare events; Efficient algorithm; VIPeR; Interpretation (philosophy); Algorithm; Mathematics; Statistics","score_opus":0.027823421920793158,"score_gpt":0.2630863891843442,"score_spread":0.23526296726355103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385701495","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3004337,0.0025131695,0.67525077,0.000963729,0.0003510135,0.00024220314,0.0068641626,0.0023104057,0.011070862],"genre_scores_gemma":[0.56826705,0.0011733121,0.40024182,0.00029305724,0.0003315571,0.0002563128,0.018195273,0.00032341978,0.0109182615],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99897206,0.0001544054,0.00012013206,0.00020164742,0.00040814315,0.0001435907],"domain_scores_gemma":[0.99696976,0.00132382,0.00036430123,0.00058107957,0.0006046869,0.00015645048],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006807438,0.00051480444,0.00095772865,0.0026783338,0.0006576615,0.0013477774,0.0014164074,0.0006160793,0.004494596],"category_scores_gemma":[0.0053145387,0.0003832903,0.0007138232,0.0032502662,0.000520854,0.0020848182,0.0014989603,0.00086818525,0.0015540244],"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":[0.0014934068,0.00033112036,0.018727366,0.00096726173,0.00019641613,0.0007700971,0.00025661287,0.013977471,0.042060707,0.05259737,0.018918825,0.8497034],"study_design_scores_gemma":[0.00019821277,0.000941781,0.014169111,0.00051015255,0.00031375978,0.004570124,0.0006128332,0.64480144,0.04364335,0.2615797,0.028567307,0.00009231465],"about_ca_topic_score_codex":0.0006603902,"about_ca_topic_score_gemma":0.0016631577,"teacher_disagreement_score":0.004494596,"about_ca_system_score_codex":0.00029116124,"about_ca_system_score_gemma":0.0009940137,"threshold_uncertainty_score":0.015035987},"labels":[],"label_agreement":null},{"id":"W4386211431","doi":"10.1109/icdh60066.2023.00049","title":"Mining Sequential Patterns with Timelines from Digital Health Data","year":2023,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"University of Manitoba","keywords":"Timeline; Interpretability; Relevance (law); Interval (graph theory); Computer science; Data mining; Domain (mathematical analysis); Time point; Point (geometry); Domain knowledge; Artificial intelligence; Mathematics; Statistics","score_opus":0.07765413386716905,"score_gpt":0.3183704162689019,"score_spread":0.24071628240173285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386211431","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21106732,0.0038506077,0.72738945,0.0026474989,0.00034776443,0.0010740929,0.044127766,0.00465755,0.0048379176],"genre_scores_gemma":[0.4563463,0.0015837055,0.5063298,0.00035264762,0.00030468247,0.00073971925,0.03258051,0.000160478,0.00160223],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977865,0.00036782987,0.0004968122,0.00057127076,0.0006680705,0.00010941267],"domain_scores_gemma":[0.99078524,0.004997929,0.0019030331,0.000981681,0.0010919041,0.00024026407],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019837937,0.000844261,0.0006944203,0.006554015,0.00047667444,0.0013875364,0.0008268905,0.0007691852,0.0019064295],"category_scores_gemma":[0.015059248,0.00036087254,0.00095109147,0.006585175,0.00035712245,0.002518811,0.0009803781,0.00078252144,0.0009357125],"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":[0.0013500194,0.0005345488,0.14255713,0.0024525214,0.0005536921,0.0049542296,0.001924772,0.0438275,0.013872276,0.019447474,0.02101353,0.74751234],"study_design_scores_gemma":[0.00029023536,0.00095448684,0.07734231,0.000978564,0.00069884746,0.007825948,0.0032826012,0.5806081,0.029870728,0.17357185,0.12440038,0.00017593779],"about_ca_topic_score_codex":0.0027477867,"about_ca_topic_score_gemma":0.005175893,"teacher_disagreement_score":0.006554015,"about_ca_system_score_codex":0.0005176387,"about_ca_system_score_gemma":0.0011756205,"threshold_uncertainty_score":0.010491431},"labels":[],"label_agreement":null},{"id":"W4386301611","doi":"","title":"Introduction to MySQL with R","year":2018,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; World Wide Web; Programming language","score_opus":0.17465763228382797,"score_gpt":0.528526242195734,"score_spread":0.353868609911906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386301611","genre_codex":"software","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006177932,0.000821861,0.25131112,0.0026942824,0.0010959887,0.0004857061,0.060210668,0.64326257,0.039500058],"genre_scores_gemma":[0.022244299,0.0019688655,0.43342322,0.0061719664,0.001004505,0.0031045268,0.13998827,0.32527974,0.066814676],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9930582,0.0017409051,0.000885678,0.0012215823,0.0024050276,0.0006885147],"domain_scores_gemma":[0.98803234,0.0047966144,0.00058685953,0.0035415015,0.002226891,0.0008157533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007028226,0.0025373732,0.002277661,0.0024898176,0.001407713,0.0076380344,0.007960586,0.0018469723,0.27121127],"category_scores_gemma":[0.036251947,0.0026236922,0.0031033088,0.0036611508,0.001264484,0.009911634,0.007030895,0.0058451984,0.28758016],"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":[0.0002934181,0.000072751485,0.00045349286,0.00069921394,0.00008468125,0.00012583187,0.00016933965,0.0006814373,0.00087315805,0.017589657,0.89971316,0.079243846],"study_design_scores_gemma":[0.00029340916,0.000041876065,0.0006000759,0.00038599333,0.00004311176,0.00030497537,0.00017360607,0.0048924596,0.004304931,0.066507705,0.92229825,0.00015355907],"about_ca_topic_score_codex":0.0035927591,"about_ca_topic_score_gemma":0.0025864572,"teacher_disagreement_score":0.27121127,"about_ca_system_score_codex":0.00097051874,"about_ca_system_score_gemma":0.0030879094,"threshold_uncertainty_score":0.90729207},"labels":[],"label_agreement":null},{"id":"W4386469333","doi":"10.32920/24093720.v1","title":"Mining significant high utility gene regulation sequential patterns","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Gene; Microarray; Microarray analysis techniques; Gene expression; Computational biology; Biology; Genetics","score_opus":0.07948044337412871,"score_gpt":0.29541293721793416,"score_spread":0.21593249384380545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386469333","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28646928,0.0029090692,0.6812478,0.0018550693,0.00013406728,0.0004372003,0.016542751,0.0053986213,0.0050060367],"genre_scores_gemma":[0.78654814,0.0008661753,0.18340693,0.00049536116,0.00013638317,0.00036032143,0.022601113,0.00023926841,0.0053462647],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986725,0.00022764677,0.00011536951,0.0004867472,0.00034816455,0.00014972872],"domain_scores_gemma":[0.9982181,0.0008328541,0.00020136383,0.00036560735,0.00028147828,0.00010062389],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011092759,0.00088145584,0.000941433,0.0029352698,0.00055859203,0.0011253378,0.001282915,0.0008805014,0.002618244],"category_scores_gemma":[0.004393661,0.00036828022,0.0015290123,0.0029560006,0.000540096,0.00089824485,0.0010394502,0.0007659989,0.0009706277],"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":[0.0009507588,0.0006240395,0.11409995,0.0010965419,0.00041394067,0.0016388433,0.00034184303,0.06496291,0.032457348,0.018671596,0.030183768,0.7345586],"study_design_scores_gemma":[0.00010453075,0.00021735443,0.039459597,0.00008418898,0.00015096129,0.0014466566,0.00022580256,0.87067616,0.014472969,0.056003705,0.01711088,0.000047142217],"about_ca_topic_score_codex":0.0034141918,"about_ca_topic_score_gemma":0.0067584235,"teacher_disagreement_score":0.0034141918,"about_ca_system_score_codex":0.00068480015,"about_ca_system_score_gemma":0.0011531936,"threshold_uncertainty_score":0.008758903},"labels":[],"label_agreement":null},{"id":"W4386469584","doi":"10.32920/24093720","title":"Mining significant high utility gene regulation sequential patterns","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Gene; Microarray; Microarray analysis techniques; Gene expression; Computational biology; Biology; Genetics","score_opus":0.07948044337412871,"score_gpt":0.29541293721793416,"score_spread":0.21593249384380545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386469584","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28646928,0.0029090692,0.6812478,0.0018550693,0.00013406728,0.0004372003,0.016542751,0.0053986213,0.0050060367],"genre_scores_gemma":[0.78654814,0.0008661753,0.18340693,0.00049536116,0.00013638317,0.00036032143,0.022601113,0.00023926841,0.0053462647],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986725,0.00022764677,0.00011536951,0.0004867472,0.00034816455,0.00014972872],"domain_scores_gemma":[0.9982181,0.0008328541,0.00020136383,0.00036560735,0.00028147828,0.00010062389],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011092759,0.00088145584,0.000941433,0.0029352698,0.00055859203,0.0011253378,0.001282915,0.0008805014,0.002618244],"category_scores_gemma":[0.004393661,0.00036828022,0.0015290123,0.0029560006,0.000540096,0.00089824485,0.0010394502,0.0007659989,0.0009706277],"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":[0.0009507588,0.0006240395,0.11409995,0.0010965419,0.00041394067,0.0016388433,0.00034184303,0.06496291,0.032457348,0.018671596,0.030183768,0.7345586],"study_design_scores_gemma":[0.00010453075,0.00021735443,0.039459597,0.00008418898,0.00015096129,0.0014466566,0.00022580256,0.87067616,0.014472969,0.056003705,0.01711088,0.000047142217],"about_ca_topic_score_codex":0.0034141918,"about_ca_topic_score_gemma":0.0067584235,"teacher_disagreement_score":0.0034141918,"about_ca_system_score_codex":0.00068480015,"about_ca_system_score_gemma":0.0011531936,"threshold_uncertainty_score":0.008758903},"labels":[],"label_agreement":null},{"id":"W4386497976","doi":"10.1145/3622940","title":"Discovering Interesting Patterns from Hypergraphs","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":14,"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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; University of Manitoba","keywords":"Hypergraph; Data mining; Computer science; Theoretical computer science; Mathematics; Combinatorics","score_opus":0.07976721731493004,"score_gpt":0.31524831086129085,"score_spread":0.23548109354636082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386497976","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06337195,0.0010163671,0.9281379,0.0008289096,0.00004022895,0.00028877356,0.0018645771,0.0013126454,0.0031385696],"genre_scores_gemma":[0.31827945,0.0013394235,0.67260045,0.00031008042,0.00008197915,0.00039442757,0.004742163,0.00015578468,0.0020962572],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981,0.0004964424,0.000148362,0.00057370245,0.0005540704,0.00012744822],"domain_scores_gemma":[0.9946021,0.0031544256,0.0005899136,0.0007431779,0.0007184056,0.00019209775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010250942,0.00070978806,0.00065338885,0.0062330896,0.0009177239,0.002275039,0.0010383886,0.0008503133,0.0014547858],"category_scores_gemma":[0.0077720564,0.00060046,0.0011989224,0.0054555945,0.0008695932,0.003730134,0.0016165783,0.0011097953,0.0004656785],"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":[0.00034786962,0.00034314528,0.037735295,0.0012007288,0.00062530476,0.003206151,0.0017516288,0.092497356,0.022596018,0.16654871,0.015421298,0.6577266],"study_design_scores_gemma":[0.00004659355,0.00008376808,0.005189066,0.00016044367,0.00021022832,0.0017137142,0.0009051104,0.5177238,0.008780741,0.44170013,0.023428211,0.000058203408],"about_ca_topic_score_codex":0.0022533746,"about_ca_topic_score_gemma":0.0046951775,"teacher_disagreement_score":0.0062330896,"about_ca_system_score_codex":0.0007589065,"about_ca_system_score_gemma":0.001293607,"threshold_uncertainty_score":0.0055062175},"labels":[],"label_agreement":null},{"id":"W4386645899","doi":"10.1007/978-3-031-41456-5_19","title":"Efficient Association Rules Minimization Using a Double-Stage Quine-McCluskey-Based Approach","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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 Trois-Rivières","funders":"","keywords":"Computer science; Minification; Algorithm; Association (psychology); Artificial intelligence; Natural language processing; Programming language; Philosophy; Epistemology","score_opus":0.03742393488549111,"score_gpt":0.2713333279970946,"score_spread":0.23390939311160347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386645899","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037238393,0.00027575102,0.9936957,0.00017825165,0.00007532966,0.00013612628,0.00021925662,0.00091542426,0.000780315],"genre_scores_gemma":[0.05706042,0.00021413223,0.93438506,0.00025868596,0.00012723969,0.0003272115,0.0017828491,0.00032374688,0.0055207023],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962196,0.001138243,0.0004172123,0.00064246025,0.001260265,0.00032232289],"domain_scores_gemma":[0.9927872,0.004232753,0.0002164923,0.00087374134,0.0017139416,0.00017591318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003041212,0.001385214,0.003598927,0.0032021834,0.0011358996,0.0023018245,0.0045591895,0.0016056952,0.010364635],"category_scores_gemma":[0.009999678,0.0011227331,0.0028456335,0.0035599929,0.0008180049,0.0022326622,0.002273118,0.0027858496,0.0048428746],"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":[0.0005248437,0.00057376013,0.0012209174,0.0005364554,0.00042696457,0.00030693877,0.0001327352,0.062204737,0.011167021,0.0172208,0.01928573,0.886399],"study_design_scores_gemma":[0.00009525466,0.00022901238,0.0007760059,0.000047063455,0.00016877973,0.0004079664,0.00009910965,0.9650039,0.0046829353,0.02362426,0.004819693,0.000045976085],"about_ca_topic_score_codex":0.004568097,"about_ca_topic_score_gemma":0.009923152,"teacher_disagreement_score":0.010364635,"about_ca_system_score_codex":0.0005830217,"about_ca_system_score_gemma":0.002671452,"threshold_uncertainty_score":0.034673095},"labels":[],"label_agreement":null},{"id":"W4386798086","doi":"10.1007/978-3-031-43412-9","title":"Machine Learning and Knowledge Discovery in Databases: Research Track","year":2023,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"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":"Télécom Paris; University of Illinois at Urbana-Champaign; Malaviya National Institute of Technology, Jaipur; Région Normandie; Instituto Superior Técnico; Shanghai University of Electric Power; Université de Lyon; University of Thessaly; Stockholms Universitet; University of Science and Technology of China; Julius-Maximilians-Universität Würzburg; Instituto Federal Goiás; Universidade Federal de Pernambuco; Rheinische Friedrich-Wilhelms-Universität Bonn; Shandong Academy of Sciences; Southeast University; Nanjing University; Univerza v Ljubljani; Université de Rennes 1; Universidade Federal de Minas Gerais; Università della Calabria; Wuhan University; Università degli Studi di Torino; Aristotle University of Thessaloniki; Anschutz Medical Campus, University of Colorado; Syddansk Universitet; Tsinghua University; Universidad Carlos III de Madrid; Universitat Politècnica de València; Humboldt-Universität zu Berlin; International Institute of Information Technology, Hyderabad; Ludwig-Maximilians-Universität München; Université de Versailles Saint-Quentin-en-Yvelines; Universität Paderborn; National Central University; Shandong University; Politechnika Warszawska; Universiteit Gent; Sapienza Università di Roma; Renmin University of China; Zhejiang University; Keele University; Università degli Studi di Verona; Universität Potsdam; AstraZeneca; Gottfried Wilhelm Leibniz Universität Hannover; Shanghai Jiao Tong University; Leibniz-Gemeinschaft; Simon Fraser University; Università degli Studi di Padova; Université de Namur; Universität Wien; China University of Petroleum, Beijing; Université Paris-Saclay; Aalto-Yliopisto; KU Leuven; Kyungpook National University; Universiteit Maastricht; University of Technology Sydney; Technische Universiteit Delft; Griffith University; University of South Australia; RMIT University; University of Electronic Science and Technology of China; Technische Universität Kaiserslautern; Monash University; Univerzita Karlova v Praze; University College Dublin; Jilin University; National University of Singapore; Politecnico di Torino; Indian Institute of Technology Gandhinagar; Universität Heidelberg; Université de Strasbourg; Conservatoire National des Arts et Métiers; Blekinge Tekniska Högskola; Beihang University; Chongqing University; University of Twente; University of Bristol; University of Bath; University of Oxford; Indian National Science Academy; University of Exeter; Sorbonne Université; Kungliga Tekniska Högskolan; Iowa State University; Universidade do Porto; Indian Institute of Technology, Patna; Boise State University; Institut \"Jožef Stefan\"; Uniwersytet Warszawski; Universität Bielefeld; Amazon Web Services; Itä-Suomen Yliopisto; Universidad Complutense de Madrid; Universidad de Castilla-La Mancha; Alibaba DAMO Academy; Amherst College; Indian Institute of Technology Jodhpur; Department for Enterprise, Trade and Investment, UK Government; University of Waikato; University of Ottawa; West Virginia University; Technische Universität Darmstadt; Università degli Studi di Trento; Michigan State University; Università degli Studi di Firenze; Université du Luxembourg; Università di Pisa; Scuola IMT Alti Studi Lucca; Universidad Autónoma de Madrid; Universiteit Utrecht; Temple University; Zhengzhou University; Indian Council of Agricultural Research; Heilongjiang University; College of Engineering, Michigan State University; University of Wyoming; Eidgenössische Technische Hochschule Zürich; Università Degli Studi di Modena e Reggio Emila; Université de Caen Normandie; Umeå Universitet; Helsingin Yliopisto; Carnegie Mellon University; Högskolan i Halmstad; Universität Osnabrück; Korea Advanced Institute of Science and Technology; Università degli Studi di Napoli Federico II; Malmö Högskola; University of Notre Dame; Xidian University; Università degli Studi di Cagliari; Florida Atlantic University; Aarhus Universitet; Universiteit Leiden; George Mason University; Universitetet i Oslo; Philipps-Universität Marburg; Universidad del Atlántico; Università di Macerata; University of Minnesota","keywords":"Computer science; Knowledge extraction; Track (disk drive); Database; Artificial intelligence; Information retrieval; Data science; Machine learning","score_opus":0.06204229511465486,"score_gpt":0.36040188294869824,"score_spread":0.29835958783404337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386798086","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030632922,0.7174802,0.10543935,0.02007493,0.032861445,0.0008188813,0.0061515667,0.004652287,0.10945813],"genre_scores_gemma":[0.01125019,0.5616077,0.10684257,0.0040239384,0.01848259,0.00043708002,0.01221977,0.0015632358,0.28357294],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982408,0.00019777723,0.00015239841,0.00036164242,0.00093144004,0.000115956296],"domain_scores_gemma":[0.99293077,0.0023004755,0.00032519453,0.000645149,0.0028825854,0.00091584603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040297844,0.0015631581,0.0031662951,0.005964602,0.00089550635,0.006882764,0.0026292447,0.0017132033,0.04284674],"category_scores_gemma":[0.0055873413,0.0014616284,0.0016265234,0.018633913,0.0008850637,0.0104907835,0.002585043,0.0036037862,0.03508946],"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":[0.000078591125,0.00012110657,0.00026487664,0.0014409571,0.000060390914,0.000025975443,0.000034208842,0.0006985192,0.0008769226,0.011335281,0.5715463,0.4135169],"study_design_scores_gemma":[0.00006558955,0.00027014324,0.001736551,0.0013317362,0.000102520826,0.0004292582,0.0000742401,0.0062328973,0.0020015945,0.02025156,0.9674448,0.000059248385],"about_ca_topic_score_codex":0.0036977457,"about_ca_topic_score_gemma":0.0050701727,"teacher_disagreement_score":0.04284674,"about_ca_system_score_codex":0.0023942832,"about_ca_system_score_gemma":0.004813984,"threshold_uncertainty_score":0.1433366},"labels":[],"label_agreement":null},{"id":"W4386798317","doi":"10.1007/978-3-031-43427-3","title":"Machine Learning and Knowledge Discovery in Databases: Applied Data Science and Demo Track","year":2023,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"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":"Télécom Paris; University of Illinois at Urbana-Champaign; Malaviya National Institute of Technology, Jaipur; Région Normandie; Instituto Superior Técnico; Shanghai University of Electric Power; Université de Lyon; University of Thessaly; Stockholms Universitet; University of Science and Technology of China; Julius-Maximilians-Universität Würzburg; Instituto Federal Goiás; Universidade Federal de Pernambuco; Rheinische Friedrich-Wilhelms-Universität Bonn; Shandong Academy of Sciences; Southeast University; Nanjing University; Univerza v Ljubljani; Université de Rennes 1; Universidade Federal de Minas Gerais; Università della Calabria; Wuhan University; Università degli Studi di Torino; Aristotle University of Thessaloniki; Anschutz Medical Campus, University of Colorado; Syddansk Universitet; Tsinghua University; Universidad Carlos III de Madrid; Universitat Politècnica de València; Humboldt-Universität zu Berlin; International Institute of Information Technology, Hyderabad; Ludwig-Maximilians-Universität München; Université de Versailles Saint-Quentin-en-Yvelines; Universität Paderborn; National Central University; Shandong University; Politechnika Warszawska; Universiteit Gent; Sapienza Università di Roma; Renmin University of China; Zhejiang University; Keele University; Università degli Studi di Verona; Universität Potsdam; AstraZeneca; Gottfried Wilhelm Leibniz Universität Hannover; Shanghai Jiao Tong University; Leibniz-Gemeinschaft; Simon Fraser University; Università degli Studi di Padova; Université de Namur; Universität Wien; China University of Petroleum, Beijing; Université Paris-Saclay; Aalto-Yliopisto; KU Leuven; Kyungpook National University; Universiteit Maastricht; University of Technology Sydney; Technische Universiteit Delft; Griffith University; University of South Australia; RMIT University; University of Electronic Science and Technology of China; Technische Universität Kaiserslautern; Monash University; Univerzita Karlova v Praze; University College Dublin; Jilin University; National University of Singapore; Politecnico di Torino; Indian Institute of Technology Gandhinagar; Universität Heidelberg; Université de Strasbourg; Conservatoire National des Arts et Métiers; Blekinge Tekniska Högskola; Beihang University; Chongqing University; University of Twente; University of Bristol; University of Bath; University of Oxford; Indian National Science Academy; University of Exeter; Sorbonne Université; Kungliga Tekniska Högskolan; Iowa State University; Universidade do Porto; Indian Institute of Technology, Patna; Boise State University; Institut \"Jožef Stefan\"; Uniwersytet Warszawski; Universität Bielefeld; Amazon Web Services; Itä-Suomen Yliopisto; Universidad Complutense de Madrid; Universidad de Castilla-La Mancha; Alibaba DAMO Academy; Amherst College; Indian Institute of Technology Jodhpur; Department for Enterprise, Trade and Investment, UK Government; University of Waikato; University of Ottawa; West Virginia University; Technische Universität Darmstadt; Università degli Studi di Trento; Michigan State University; Università degli Studi di Firenze; Université du Luxembourg; Università di Pisa; Scuola IMT Alti Studi Lucca; Universidad Autónoma de Madrid; Universiteit Utrecht; Temple University; Zhengzhou University; Indian Council of Agricultural Research; Heilongjiang University; College of Engineering, Michigan State University; University of Wyoming; Eidgenössische Technische Hochschule Zürich; Università Degli Studi di Modena e Reggio Emila; Université de Caen Normandie; Umeå Universitet; Helsingin Yliopisto; Carnegie Mellon University; Högskolan i Halmstad; Universität Osnabrück; Korea Advanced Institute of Science and Technology; Università degli Studi di Napoli Federico II; Malmö Högskola; University of Notre Dame; Xidian University; Università degli Studi di Cagliari; Florida Atlantic University; Aarhus Universitet; Universiteit Leiden; George Mason University; Universitetet i Oslo; Philipps-Universität Marburg; Universidad del Atlántico; Università di Macerata; University of Minnesota","keywords":"Computer science; Track (disk drive); Database; Knowledge extraction; Information retrieval; Artificial intelligence; Data science; Operating system","score_opus":0.036909266588763645,"score_gpt":0.3015205930331806,"score_spread":0.2646113264444169,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386798317","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004237314,0.5392557,0.22475652,0.0428114,0.02524987,0.0006024951,0.0049669314,0.0053551546,0.15276468],"genre_scores_gemma":[0.02322544,0.42111227,0.18462595,0.005090329,0.017161988,0.00041824748,0.0076499106,0.0025236185,0.33819216],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982584,0.00020637023,0.00011043348,0.00027001236,0.0010668661,0.000087882],"domain_scores_gemma":[0.9920385,0.0031757443,0.00021777241,0.0010238751,0.0025384848,0.001005671],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0059064277,0.0013474347,0.0024530792,0.0052483454,0.00088518055,0.007171706,0.0025038705,0.0014584673,0.036743633],"category_scores_gemma":[0.006069629,0.0015037339,0.0015304994,0.014145229,0.0015187141,0.014427958,0.0028756738,0.005218133,0.020267218],"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":[0.00007570576,0.00012788836,0.00033736875,0.00079184945,0.000046999783,0.00003263749,0.000073720235,0.0013122965,0.0008303071,0.034348972,0.54219663,0.4198256],"study_design_scores_gemma":[0.00003926453,0.00012993944,0.001243289,0.0006347008,0.000045489654,0.00037633372,0.000096372896,0.019045984,0.0019066473,0.056838926,0.9195898,0.00005320603],"about_ca_topic_score_codex":0.0043827114,"about_ca_topic_score_gemma":0.0047141723,"teacher_disagreement_score":0.036743633,"about_ca_system_score_codex":0.002810859,"about_ca_system_score_gemma":0.0032679152,"threshold_uncertainty_score":0.12291974},"labels":[],"label_agreement":null},{"id":"W4386804229","doi":"10.1007/978-3-031-43418-1","title":"Machine Learning and Knowledge Discovery in Databases: Research Track","year":2023,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"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":"Télécom Paris; University of Illinois at Urbana-Champaign; Malaviya National Institute of Technology, Jaipur; Région Normandie; Instituto Superior Técnico; Shanghai University of Electric Power; Université de Lyon; University of Thessaly; Stockholms Universitet; University of Science and Technology of China; Julius-Maximilians-Universität Würzburg; Instituto Federal Goiás; Universidade Federal de Pernambuco; Rheinische Friedrich-Wilhelms-Universität Bonn; Shandong Academy of Sciences; Southeast University; Nanjing University; Univerza v Ljubljani; Université de Rennes 1; Universidade Federal de Minas Gerais; Università della Calabria; Wuhan University; Università degli Studi di Torino; Aristotle University of Thessaloniki; Anschutz Medical Campus, University of Colorado; Syddansk Universitet; Tsinghua University; Universidad Carlos III de Madrid; Universitat Politècnica de València; Humboldt-Universität zu Berlin; International Institute of Information Technology, Hyderabad; Ludwig-Maximilians-Universität München; Université de Versailles Saint-Quentin-en-Yvelines; Universität Paderborn; National Central University; Shandong University; Politechnika Warszawska; Universiteit Gent; Sapienza Università di Roma; Renmin University of China; Zhejiang University; Keele University; Università degli Studi di Verona; Universität Potsdam; AstraZeneca; Gottfried Wilhelm Leibniz Universität Hannover; Shanghai Jiao Tong University; Leibniz-Gemeinschaft; Simon Fraser University; Università degli Studi di Padova; Université de Namur; Universität Wien; China University of Petroleum, Beijing; Université Paris-Saclay; Aalto-Yliopisto; KU Leuven; Kyungpook National University; Universiteit Maastricht; University of Technology Sydney; Technische Universiteit Delft; Griffith University; University of South Australia; RMIT University; University of Electronic Science and Technology of China; Technische Universität Kaiserslautern; Monash University; Univerzita Karlova v Praze; University College Dublin; Jilin University; National University of Singapore; Politecnico di Torino; Indian Institute of Technology Gandhinagar; Universität Heidelberg; Université de Strasbourg; Conservatoire National des Arts et Métiers; Blekinge Tekniska Högskola; Beihang University; Chongqing University; University of Twente; University of Bristol; University of Bath; University of Oxford; Indian National Science Academy; University of Exeter; Sorbonne Université; Kungliga Tekniska Högskolan; Iowa State University; Universidade do Porto; Indian Institute of Technology, Patna; Boise State University; Institut \"Jožef Stefan\"; Uniwersytet Warszawski; Universität Bielefeld; Amazon Web Services; Itä-Suomen Yliopisto; Universidad Complutense de Madrid; Universidad de Castilla-La Mancha; Alibaba DAMO Academy; Amherst College; Indian Institute of Technology Jodhpur; Department for Enterprise, Trade and Investment, UK Government; University of Waikato; University of Ottawa; West Virginia University; Technische Universität Darmstadt; Università degli Studi di Trento; Michigan State University; Università degli Studi di Firenze; Université du Luxembourg; Università di Pisa; Scuola IMT Alti Studi Lucca; Universidad Autónoma de Madrid; Universiteit Utrecht; Temple University; Zhengzhou University; Indian Council of Agricultural Research; Heilongjiang University; College of Engineering, Michigan State University; University of Wyoming; Eidgenössische Technische Hochschule Zürich; Università Degli Studi di Modena e Reggio Emila; Université de Caen Normandie; Umeå Universitet; Helsingin Yliopisto; Carnegie Mellon University; Högskolan i Halmstad; Universität Osnabrück; Korea Advanced Institute of Science and Technology; Università degli Studi di Napoli Federico II; Malmö Högskola; University of Notre Dame; Xidian University; Università degli Studi di Cagliari; Florida Atlantic University; Aarhus Universitet; Universiteit Leiden; George Mason University; Universitetet i Oslo; Philipps-Universität Marburg; Universidad del Atlántico; Università di Macerata; University of Minnesota","keywords":"Computer science; Track (disk drive); Database; Knowledge extraction; Artificial intelligence; Information retrieval; Operating system","score_opus":0.06204229511465486,"score_gpt":0.36040188294869824,"score_spread":0.29835958783404337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386804229","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030632922,0.7174802,0.10543935,0.02007493,0.032861445,0.0008188813,0.0061515667,0.004652287,0.10945813],"genre_scores_gemma":[0.01125019,0.5616077,0.10684257,0.0040239384,0.01848259,0.00043708002,0.01221977,0.0015632358,0.28357294],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982408,0.00019777723,0.00015239841,0.00036164242,0.00093144004,0.000115956296],"domain_scores_gemma":[0.99293077,0.0023004755,0.00032519453,0.000645149,0.0028825854,0.00091584603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040297844,0.0015631581,0.0031662951,0.005964602,0.00089550635,0.006882764,0.0026292447,0.0017132033,0.04284674],"category_scores_gemma":[0.0055873413,0.0014616284,0.0016265234,0.018633913,0.0008850637,0.0104907835,0.002585043,0.0036037862,0.03508946],"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":[0.000078591125,0.00012110657,0.00026487664,0.0014409571,0.000060390914,0.000025975443,0.000034208842,0.0006985192,0.0008769226,0.011335281,0.5715463,0.4135169],"study_design_scores_gemma":[0.00006558955,0.00027014324,0.001736551,0.0013317362,0.000102520826,0.0004292582,0.0000742401,0.0062328973,0.0020015945,0.02025156,0.9674448,0.000059248385],"about_ca_topic_score_codex":0.0036977457,"about_ca_topic_score_gemma":0.0050701727,"teacher_disagreement_score":0.04284674,"about_ca_system_score_codex":0.0023942832,"about_ca_system_score_gemma":0.004813984,"threshold_uncertainty_score":0.1433366},"labels":[],"label_agreement":null},{"id":"W4386804666","doi":"10.1007/978-3-031-43415-0","title":"Machine Learning and Knowledge Discovery in Databases: Research Track","year":2023,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"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":"Télécom Paris; University of Illinois at Urbana-Champaign; Malaviya National Institute of Technology, Jaipur; Région Normandie; Instituto Superior Técnico; Shanghai University of Electric Power; Université de Lyon; University of Thessaly; Stockholms Universitet; University of Science and Technology of China; Julius-Maximilians-Universität Würzburg; Instituto Federal Goiás; Universidade Federal de Pernambuco; Rheinische Friedrich-Wilhelms-Universität Bonn; Shandong Academy of Sciences; Southeast University; Nanjing University; Univerza v Ljubljani; Université de Rennes 1; Universidade Federal de Minas Gerais; Università della Calabria; Wuhan University; Università degli Studi di Torino; Aristotle University of Thessaloniki; Anschutz Medical Campus, University of Colorado; Syddansk Universitet; Tsinghua University; Universidad Carlos III de Madrid; Universitat Politècnica de València; Humboldt-Universität zu Berlin; International Institute of Information Technology, Hyderabad; Ludwig-Maximilians-Universität München; Université de Versailles Saint-Quentin-en-Yvelines; Universität Paderborn; National Central University; Shandong University; Politechnika Warszawska; Universiteit Gent; Sapienza Università di Roma; Renmin University of China; Zhejiang University; Keele University; Università degli Studi di Verona; Universität Potsdam; AstraZeneca; Gottfried Wilhelm Leibniz Universität Hannover; Shanghai Jiao Tong University; Leibniz-Gemeinschaft; Simon Fraser University; Università degli Studi di Padova; Université de Namur; Universität Wien; China University of Petroleum, Beijing; Université Paris-Saclay; Aalto-Yliopisto; KU Leuven; Kyungpook National University; Universiteit Maastricht; University of Technology Sydney; Technische Universiteit Delft; Griffith University; University of South Australia; RMIT University; University of Electronic Science and Technology of China; Technische Universität Kaiserslautern; Monash University; Univerzita Karlova v Praze; University College Dublin; Jilin University; National University of Singapore; Politecnico di Torino; Indian Institute of Technology Gandhinagar; Universität Heidelberg; Université de Strasbourg; Conservatoire National des Arts et Métiers; Blekinge Tekniska Högskola; Beihang University; Chongqing University; University of Twente; University of Bristol; University of Bath; University of Oxford; Indian National Science Academy; University of Exeter; Sorbonne Université; Kungliga Tekniska Högskolan; Iowa State University; Universidade do Porto; Indian Institute of Technology, Patna; Boise State University; Institut \"Jožef Stefan\"; Uniwersytet Warszawski; Universität Bielefeld; Amazon Web Services; Itä-Suomen Yliopisto; Universidad Complutense de Madrid; Universidad de Castilla-La Mancha; Alibaba DAMO Academy; Amherst College; Indian Institute of Technology Jodhpur; Department for Enterprise, Trade and Investment, UK Government; University of Waikato; University of Ottawa; West Virginia University; Technische Universität Darmstadt; Università degli Studi di Trento; Michigan State University; Università degli Studi di Firenze; Université du Luxembourg; Università di Pisa; Scuola IMT Alti Studi Lucca; Universidad Autónoma de Madrid; Universiteit Utrecht; Temple University; Zhengzhou University; Indian Council of Agricultural Research; Heilongjiang University; College of Engineering, Michigan State University; University of Wyoming; Eidgenössische Technische Hochschule Zürich; Università Degli Studi di Modena e Reggio Emila; Université de Caen Normandie; Umeå Universitet; Helsingin Yliopisto; Carnegie Mellon University; Högskolan i Halmstad; Universität Osnabrück; Korea Advanced Institute of Science and Technology; Università degli Studi di Napoli Federico II; Malmö Högskola; University of Notre Dame; Xidian University; Università degli Studi di Cagliari; Florida Atlantic University; Aarhus Universitet; Universiteit Leiden; George Mason University; Universitetet i Oslo; Philipps-Universität Marburg; Universidad del Atlántico; Università di Macerata; University of Minnesota","keywords":"Computer science; Track (disk drive); Database; Knowledge extraction; Information retrieval; Artificial intelligence; Operating system","score_opus":0.06204229511465486,"score_gpt":0.36040188294869824,"score_spread":0.29835958783404337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386804666","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030632922,0.7174802,0.10543935,0.02007493,0.032861445,0.0008188813,0.0061515667,0.004652287,0.10945813],"genre_scores_gemma":[0.01125019,0.5616077,0.10684257,0.0040239384,0.01848259,0.00043708002,0.01221977,0.0015632358,0.28357294],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982408,0.00019777723,0.00015239841,0.00036164242,0.00093144004,0.000115956296],"domain_scores_gemma":[0.99293077,0.0023004755,0.00032519453,0.000645149,0.0028825854,0.00091584603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040297844,0.0015631581,0.0031662951,0.005964602,0.00089550635,0.006882764,0.0026292447,0.0017132033,0.04284674],"category_scores_gemma":[0.0055873413,0.0014616284,0.0016265234,0.018633913,0.0008850637,0.0104907835,0.002585043,0.0036037862,0.03508946],"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":[0.000078591125,0.00012110657,0.00026487664,0.0014409571,0.000060390914,0.000025975443,0.000034208842,0.0006985192,0.0008769226,0.011335281,0.5715463,0.4135169],"study_design_scores_gemma":[0.00006558955,0.00027014324,0.001736551,0.0013317362,0.000102520826,0.0004292582,0.0000742401,0.0062328973,0.0020015945,0.02025156,0.9674448,0.000059248385],"about_ca_topic_score_codex":0.0036977457,"about_ca_topic_score_gemma":0.0050701727,"teacher_disagreement_score":0.04284674,"about_ca_system_score_codex":0.0023942832,"about_ca_system_score_gemma":0.004813984,"threshold_uncertainty_score":0.1433366},"labels":[],"label_agreement":null},{"id":"W4386806337","doi":"10.1007/978-3-031-43430-3","title":"Machine Learning and Knowledge Discovery in Databases: Applied Data Science and Demo Track","year":2023,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"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":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences; Télécom Paris; University of Illinois at Urbana-Champaign; Malaviya National Institute of Technology, Jaipur; Région Normandie; Instituto Superior Técnico; Shanghai University of Electric Power; Université de Lyon; University of Thessaly; Stockholms Universitet; University of Science and Technology of China; Julius-Maximilians-Universität Würzburg; Instituto Federal Goiás; Universidade Federal de Pernambuco; Shandong Academy of Sciences; Southeast University; Nanjing University; Univerza v Ljubljani; Université de Rennes 1; Universidad de Castilla-La Mancha; Universidade Federal de Minas Gerais; Università della Calabria; Wuhan University; Universität zu Köln; Università degli Studi di Torino; Aristotle University of Thessaloniki; Anschutz Medical Campus, University of Colorado; Syddansk Universitet; Universitat Politècnica de València; Humboldt-Universität zu Berlin; Malmö Högskola; International Institute of Information Technology, Hyderabad; Ludwig-Maximilians-Universität München; Uniwersytet Warszawski; Universität Bielefeld; Technische Universität Darmstadt; University of Electronic Science and Technology of China; Université de Versailles Saint-Quentin-en-Yvelines; Universität Paderborn; National Central University; Rheinische Friedrich-Wilhelms-Universität Bonn; Westfälische Wilhelms-Universität Münster; Centre National de la Recherche Scientifique; Shandong University; Politechnika Warszawska; Universiteit Gent; Sapienza Università di Roma; Renmin University of China; Zhejiang University; Keele University; Università degli Studi di Verona; Universität Potsdam; AstraZeneca; Gottfried Wilhelm Leibniz Universität Hannover; University College Cork; Shanghai Jiao Tong University; Leibniz-Gemeinschaft; Simon Fraser University; Università degli Studi di Padova; Université de Namur; Universität Wien; Itä-Suomen Yliopisto; Amazon Web Services; Universidad Complutense de Madrid; China University of Petroleum, Beijing; Université Paris-Saclay; Aalto-Yliopisto; KU Leuven; Kyungpook National University; Universiteit Maastricht; University of Technology Sydney; Technische Universiteit Delft; Queensland University of Technology; University of South Australia; RMIT University; Technische Universität Kaiserslautern; Monash University; Jilin University; National University of Singapore; Université de Strasbourg; Conservatoire National des Arts et Métiers; Blekinge Tekniska Högskola; Beihang University; Chongqing University; University of Twente; University of Bristol; University of Bath; University of Oxford; Universidad Carlos III de Madrid; Tsinghua University; Indian National Science Academy; University of Exeter; Sorbonne Université; Kungliga Tekniska Högskolan; Iowa State University; Universidade do Porto; Indian Institute of Technology, Patna; Boise State University; Institut \"Jožef Stefan\"; Amherst College; Department for Enterprise, Trade and Investment, UK Government; Universiteit van Amsterdam; Universität Heidelberg; Politecnico di Torino; Indian Institute of Technology Gandhinagar; Indian Institute of Technology Jodhpur; University of Waikato; University of Ottawa; West Virginia University; Università degli Studi di Firenze; Université du Luxembourg; Heilongjiang University; College of Engineering, Michigan State University; University of Wyoming; Eidgenössische Technische Hochschule Zürich; Università Degli Studi di Modena e Reggio Emila; Nara Institute of Science and Technology; University of Notre Dame; Université de Caen Normandie; Umeå Universitet; Helsingin Yliopisto; Università di Pisa; Universidad Autónoma de Madrid; Scuola IMT Alti Studi Lucca; Carnegie Mellon University; Högskolan i Halmstad; Universität Osnabrück; Korea Advanced Institute of Science and Technology; Università degli Studi di Napoli Federico II; Università degli Studi di Trento; Michigan State University; Universiteit Utrecht; Temple University; Zhengzhou University; Indian Council of Agricultural Research; Griffith University; Università degli Studi di Cagliari; Arizona State University; Xidian University; Florida Atlantic University; University College Dublin; Univerzita Karlova v Praze; Tongji University; Aarhus Universitet; Universiteit Leiden; George Mason University; Carl von Ossietzky Universität Oldenburg; Universitetet i Oslo; Philipps-Universität Marburg; Universidad del Atlántico; Università di Macerata; University of Minnesota","keywords":"Computer science; Track (disk drive); Knowledge extraction; Database; Information retrieval; Data science; World Wide Web; Artificial intelligence; Operating system","score_opus":0.036909266588763645,"score_gpt":0.3015205930331806,"score_spread":0.2646113264444169,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386806337","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004237314,0.5392557,0.22475652,0.0428114,0.02524987,0.0006024951,0.0049669314,0.0053551546,0.15276468],"genre_scores_gemma":[0.02322544,0.42111227,0.18462595,0.005090329,0.017161988,0.00041824748,0.0076499106,0.0025236185,0.33819216],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982584,0.00020637023,0.00011043348,0.00027001236,0.0010668661,0.000087882],"domain_scores_gemma":[0.9920385,0.0031757443,0.00021777241,0.0010238751,0.0025384848,0.001005671],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0059064277,0.0013474347,0.0024530792,0.0052483454,0.00088518055,0.007171706,0.0025038705,0.0014584673,0.036743633],"category_scores_gemma":[0.006069629,0.0015037339,0.0015304994,0.014145229,0.0015187141,0.014427958,0.0028756738,0.005218133,0.020267218],"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":[0.00007570576,0.00012788836,0.00033736875,0.00079184945,0.000046999783,0.00003263749,0.000073720235,0.0013122965,0.0008303071,0.034348972,0.54219663,0.4198256],"study_design_scores_gemma":[0.00003926453,0.00012993944,0.001243289,0.0006347008,0.000045489654,0.00037633372,0.000096372896,0.019045984,0.0019066473,0.056838926,0.9195898,0.00005320603],"about_ca_topic_score_codex":0.0043827114,"about_ca_topic_score_gemma":0.0047141723,"teacher_disagreement_score":0.036743633,"about_ca_system_score_codex":0.002810859,"about_ca_system_score_gemma":0.0032679152,"threshold_uncertainty_score":0.12291974},"labels":[],"label_agreement":null},{"id":"W4386811929","doi":"10.1007/978-3-031-43424-2","title":"Machine Learning and Knowledge Discovery in Databases: Research Track","year":2023,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"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":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences; Télécom Paris; University of Illinois at Urbana-Champaign; Malaviya National Institute of Technology, Jaipur; Région Normandie; Instituto Superior Técnico; Shanghai University of Electric Power; Université de Lyon; University of Thessaly; Stockholms Universitet; University of Science and Technology of China; Julius-Maximilians-Universität Würzburg; Instituto Federal Goiás; Universidade Federal de Pernambuco; Shandong Academy of Sciences; Southeast University; Nanjing University; Univerza v Ljubljani; Université de Rennes 1; Universidade Federal de Minas Gerais; Università della Calabria; Wuhan University; Universität zu Köln; Università degli Studi di Torino; Aristotle University of Thessaloniki; Anschutz Medical Campus, University of Colorado; Syddansk Universitet; Universitat Politècnica de València; Humboldt-Universität zu Berlin; Malmö Högskola; International Institute of Information Technology, Hyderabad; Ludwig-Maximilians-Universität München; Uniwersytet Warszawski; Universität Bielefeld; Technische Universität Darmstadt; University of Electronic Science and Technology of China; Xidian University; Université de Versailles Saint-Quentin-en-Yvelines; Universität Paderborn; National Central University; Université de Caen Normandie; Umeå Universitet; Rheinische Friedrich-Wilhelms-Universität Bonn; Westfälische Wilhelms-Universität Münster; Centre National de la Recherche Scientifique; Shandong University; Politechnika Warszawska; Universiteit Gent; Sapienza Università di Roma; Renmin University of China; Università degli Studi di Verona; Universität Potsdam; AstraZeneca; Gottfried Wilhelm Leibniz Universität Hannover; Leibniz-Gemeinschaft; Pennsylvania State University; Simon Fraser University; Università degli Studi di Padova; Université de Namur; Universität Wien; China University of Petroleum, Beijing; Keele University; Zhejiang University; Université Paris-Saclay; Aalto-Yliopisto; KU Leuven; Kyungpook National University; Universiteit Maastricht; University of Technology Sydney; Technische Universiteit Delft; Queensland University of Technology; University of South Australia; RMIT University; Technische Universität Kaiserslautern; Monash University; Shanghai Jiao Tong University; University College Cork; Université de La Réunion; Jilin University; National University of Singapore; Université de Strasbourg; Conservatoire National des Arts et Métiers; Blekinge Tekniska Högskola; Beihang University; Chongqing University; University of Twente; University of Bristol; Kunming University of Science and Technology; University of Bath; University of Oxford; Universidad Carlos III de Madrid; Tsinghua University; Indian National Science Academy; University of Exeter; Sorbonne Université; University of Texas Rio Grande Valley; Kungliga Tekniska Högskolan; Iowa State University; Universidade do Porto; Indian Institute of Technology, Patna; Boise State University; Institut \"Jožef Stefan\"; Eberhard Karls Universität Tübingen; Itä-Suomen Yliopisto; Amazon Web Services; Universidad Complutense de Madrid; Universidad de Castilla-La Mancha; Alibaba DAMO Academy; Heilongjiang University; College of Engineering, Michigan State University; University of Wyoming; Universität Passau; Università degli Studi di Firenze; Université du Luxembourg; Amherst College; Department for Enterprise, Trade and Investment, UK Government; Universiteit van Amsterdam; Huazhong University of Science and Technology; Universität Heidelberg; Politecnico di Torino; Indian Institute of Technology Gandhinagar; Indian Institute of Technology Jodhpur; University of Waikato; University of Ottawa; West Virginia University; Eidgenössische Technische Hochschule Zürich; Nara Institute of Science and Technology; Università Degli Studi di Modena e Reggio Emila; Università di Pisa; Scuola IMT Alti Studi Lucca; Universidad Autónoma de Madrid; Universiteit Utrecht; Temple University; Zhengzhou University; Indian Council of Agricultural Research; Philipps-Universität Marburg; Florida Atlantic University; University of Pennsylvania; University of Notre Dame; Helsingin Yliopisto; Carnegie Mellon University; Università degli Studi di Trento; Michigan State University; Högskolan i Halmstad; Universität Osnabrück; Korea Advanced Institute of Science and Technology; Università degli Studi di Napoli Federico II; Griffith University; Arizona State University; Università degli Studi di Cagliari; University College Dublin; Univerzita Karlova v Praze; Universiteit Leiden; George Mason University; Universidad del Atlántico; Università di Macerata; University of Minnesota; Tongji University; Aarhus Universitet; Universitetet i Oslo; Carl von Ossietzky Universität Oldenburg","keywords":"Computer science; Knowledge extraction; Track (disk drive); Artificial intelligence; Database; Information retrieval; Machine learning; Data science","score_opus":0.06204229511465486,"score_gpt":0.36040188294869824,"score_spread":0.29835958783404337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386811929","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030632922,0.7174802,0.10543935,0.02007493,0.032861445,0.0008188813,0.0061515667,0.004652287,0.10945813],"genre_scores_gemma":[0.01125019,0.5616077,0.10684257,0.0040239384,0.01848259,0.00043708002,0.01221977,0.0015632358,0.28357294],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982408,0.00019777723,0.00015239841,0.00036164242,0.00093144004,0.000115956296],"domain_scores_gemma":[0.99293077,0.0023004755,0.00032519453,0.000645149,0.0028825854,0.00091584603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040297844,0.0015631581,0.0031662951,0.005964602,0.00089550635,0.006882764,0.0026292447,0.0017132033,0.04284674],"category_scores_gemma":[0.0055873413,0.0014616284,0.0016265234,0.018633913,0.0008850637,0.0104907835,0.002585043,0.0036037862,0.03508946],"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":[0.000078591125,0.00012110657,0.00026487664,0.0014409571,0.000060390914,0.000025975443,0.000034208842,0.0006985192,0.0008769226,0.011335281,0.5715463,0.4135169],"study_design_scores_gemma":[0.00006558955,0.00027014324,0.001736551,0.0013317362,0.000102520826,0.0004292582,0.0000742401,0.0062328973,0.0020015945,0.02025156,0.9674448,0.000059248385],"about_ca_topic_score_codex":0.0036977457,"about_ca_topic_score_gemma":0.0050701727,"teacher_disagreement_score":0.04284674,"about_ca_system_score_codex":0.0023942832,"about_ca_system_score_gemma":0.004813984,"threshold_uncertainty_score":0.1433366},"labels":[],"label_agreement":null},{"id":"W4386811934","doi":"10.1007/978-3-031-43421-1","title":"Machine Learning and Knowledge Discovery in Databases: Research Track","year":2023,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Télécom Paris; University of Illinois at Urbana-Champaign; Malaviya National Institute of Technology, Jaipur; Région Normandie; Instituto Superior Técnico; Shanghai University of Electric Power; Université de Lyon; University of Thessaly; Stockholms Universitet; University of Science and Technology of China; Julius-Maximilians-Universität Würzburg; Instituto Federal Goiás; Universidade Federal de Pernambuco; Rheinische Friedrich-Wilhelms-Universität Bonn; Shandong Academy of Sciences; Southeast University; Nanjing University; Univerza v Ljubljani; Université de Rennes 1; Universidade Federal de Minas Gerais; Università della Calabria; Wuhan University; Università degli Studi di Torino; Aristotle University of Thessaloniki; Anschutz Medical Campus, University of Colorado; Syddansk Universitet; Tsinghua University; Universidad Carlos III de Madrid; Universitat Politècnica de València; Humboldt-Universität zu Berlin; International Institute of Information Technology, Hyderabad; Ludwig-Maximilians-Universität München; Université de Versailles Saint-Quentin-en-Yvelines; Universität Paderborn; National Central University; Shandong University; Politechnika Warszawska; Universiteit Gent; Sapienza Università di Roma; Renmin University of China; Zhejiang University; Keele University; Università degli Studi di Verona; Universität Potsdam; AstraZeneca; Gottfried Wilhelm Leibniz Universität Hannover; Shanghai Jiao Tong University; Leibniz-Gemeinschaft; Simon Fraser University; Università degli Studi di Padova; Université de Namur; Universität Wien; China University of Petroleum, Beijing; Université Paris-Saclay; Aalto-Yliopisto; KU Leuven; Kyungpook National University; Universiteit Maastricht; University of Technology Sydney; Technische Universiteit Delft; Griffith University; University of South Australia; RMIT University; University of Electronic Science and Technology of China; Technische Universität Kaiserslautern; Monash University; Univerzita Karlova v Praze; University College Dublin; Jilin University; National University of Singapore; Politecnico di Torino; Indian Institute of Technology Gandhinagar; Universität Heidelberg; Université de Strasbourg; Conservatoire National des Arts et Métiers; Blekinge Tekniska Högskola; Beihang University; Chongqing University; University of Twente; University of Bristol; University of Bath; University of Oxford; Indian National Science Academy; University of Exeter; Sorbonne Université; Kungliga Tekniska Högskolan; Iowa State University; Universidade do Porto; Indian Institute of Technology, Patna; Boise State University; Institut \"Jožef Stefan\"; Uniwersytet Warszawski; Universität Bielefeld; Amazon Web Services; Itä-Suomen Yliopisto; Universidad Complutense de Madrid; Universidad de Castilla-La Mancha; Alibaba DAMO Academy; Amherst College; Indian Institute of Technology Jodhpur; Department for Enterprise, Trade and Investment, UK Government; University of Waikato; University of Ottawa; West Virginia University; Technische Universität Darmstadt; Università degli Studi di Trento; Michigan State University; Università degli Studi di Firenze; Université du Luxembourg; Università di Pisa; Scuola IMT Alti Studi Lucca; Universidad Autónoma de Madrid; Universiteit Utrecht; Temple University; Zhengzhou University; Indian Council of Agricultural Research; Heilongjiang University; College of Engineering, Michigan State University; University of Wyoming; Eidgenössische Technische Hochschule Zürich; Università Degli Studi di Modena e Reggio Emila; Université de Caen Normandie; Umeå Universitet; Helsingin Yliopisto; Carnegie Mellon University; Högskolan i Halmstad; Universität Osnabrück; Korea Advanced Institute of Science and Technology; Università degli Studi di Napoli Federico II; Malmö Högskola; University of Notre Dame; Xidian University; Università degli Studi di Cagliari; Florida Atlantic University; Aarhus Universitet; Universiteit Leiden; George Mason University; Universitetet i Oslo; Philipps-Universität Marburg; Universidad del Atlántico; Università di Macerata; University of Minnesota","keywords":"Computer science; Knowledge extraction; Track (disk drive); Artificial intelligence; Database; Information retrieval; Data science; Machine learning; Operating system","score_opus":0.06204229511465486,"score_gpt":0.36040188294869824,"score_spread":0.29835958783404337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386811934","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030632922,0.7174802,0.10543935,0.02007493,0.032861445,0.0008188813,0.0061515667,0.004652287,0.10945813],"genre_scores_gemma":[0.01125019,0.5616077,0.10684257,0.0040239384,0.01848259,0.00043708002,0.01221977,0.0015632358,0.28357294],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982408,0.00019777723,0.00015239841,0.00036164242,0.00093144004,0.000115956296],"domain_scores_gemma":[0.99293077,0.0023004755,0.00032519453,0.000645149,0.0028825854,0.00091584603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040297844,0.0015631581,0.0031662951,0.005964602,0.00089550635,0.006882764,0.0026292447,0.0017132033,0.04284674],"category_scores_gemma":[0.0055873413,0.0014616284,0.0016265234,0.018633913,0.0008850637,0.0104907835,0.002585043,0.0036037862,0.03508946],"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":[0.000078591125,0.00012110657,0.00026487664,0.0014409571,0.000060390914,0.000025975443,0.000034208842,0.0006985192,0.0008769226,0.011335281,0.5715463,0.4135169],"study_design_scores_gemma":[0.00006558955,0.00027014324,0.001736551,0.0013317362,0.000102520826,0.0004292582,0.0000742401,0.0062328973,0.0020015945,0.02025156,0.9674448,0.000059248385],"about_ca_topic_score_codex":0.0036977457,"about_ca_topic_score_gemma":0.0050701727,"teacher_disagreement_score":0.04284674,"about_ca_system_score_codex":0.0023942832,"about_ca_system_score_gemma":0.004813984,"threshold_uncertainty_score":0.1433366},"labels":[],"label_agreement":null},{"id":"W4386869806","doi":"10.2139/ssrn.4567954","title":"Multi-View Representation Learning to Schema Match Databases","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","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":"Centre for Addiction and Mental Health","funders":"","keywords":"Schema (genetic algorithms); Computer science; Database; Information retrieval; Representation (politics); Schema evolution; Database schema; Database design; Political science","score_opus":0.07372381270653196,"score_gpt":0.35845269146096875,"score_spread":0.2847288787544368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386869806","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028737092,0.0015220476,0.96147037,0.00091887644,0.00014269563,0.00019416341,0.001383316,0.0042376365,0.0013937581],"genre_scores_gemma":[0.37625912,0.00093254255,0.6106996,0.0007484809,0.00016388507,0.00026524148,0.0076524443,0.00037661492,0.0029020885],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99617445,0.0010938637,0.00029840445,0.0011994271,0.00096712547,0.0002666633],"domain_scores_gemma":[0.99224067,0.0033802323,0.00038593984,0.002919191,0.0008089469,0.00026501363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034064713,0.0009727033,0.0020455983,0.0035562126,0.00086985633,0.003644028,0.0035902185,0.002408206,0.004884177],"category_scores_gemma":[0.016612766,0.00076035684,0.002334233,0.0057864864,0.0008301684,0.0071046716,0.0036805067,0.0029501785,0.0020959487],"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":[0.00064805924,0.00075981213,0.008198251,0.00043194767,0.000493235,0.00019274888,0.00037924998,0.050707143,0.005380304,0.02572522,0.029157322,0.8779267],"study_design_scores_gemma":[0.000047472422,0.0001594974,0.00085086585,0.00006207274,0.00012694263,0.00023318308,0.00023533175,0.917802,0.0046727005,0.07086649,0.0049202703,0.00002314718],"about_ca_topic_score_codex":0.0059515797,"about_ca_topic_score_gemma":0.0071311085,"teacher_disagreement_score":0.0059515797,"about_ca_system_score_codex":0.0015230848,"about_ca_system_score_gemma":0.0019056131,"threshold_uncertainty_score":0.018015325},"labels":[],"label_agreement":null},{"id":"W4387052136","doi":"10.21105/joss.05259","title":"geocmeans: An R package for spatial fuzzyc-means","year":2023,"lang":"en","type":"article","venue":"The Journal of Open Source Software","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Fuzzy logic; Computer science; Computer graphics (images); Artificial intelligence","score_opus":0.044322402773073075,"score_gpt":0.3208009551682992,"score_spread":0.2764785523952261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387052136","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026071293,0.0011094839,0.6026226,0.0008369023,0.00060815696,0.00032667656,0.12255476,0.26313075,0.006203487],"genre_scores_gemma":[0.023712,0.0010037192,0.75339353,0.000952087,0.00022641507,0.0029300232,0.094026424,0.11556727,0.008188536],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99775416,0.0006601578,0.00021324835,0.000603902,0.0005979568,0.00017057084],"domain_scores_gemma":[0.99431866,0.003188944,0.0004713601,0.0008528333,0.000987798,0.00018034545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032518343,0.0031053382,0.0027144887,0.003305211,0.0010578245,0.0030389442,0.004849667,0.0016997367,0.095503464],"category_scores_gemma":[0.023471056,0.0017061594,0.0031244368,0.003475285,0.0008932921,0.0026776486,0.0033580365,0.0033690212,0.06942832],"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":[0.00047268113,0.00008318894,0.003452689,0.0031784314,0.0011495011,0.00036229,0.00056763564,0.024206756,0.0034117093,0.028444365,0.8134206,0.121250145],"study_design_scores_gemma":[0.00045072628,0.00010217666,0.004261167,0.0005637344,0.00046287134,0.0005877018,0.00017535505,0.09773063,0.008389187,0.09636859,0.7905773,0.0003305673],"about_ca_topic_score_codex":0.009769334,"about_ca_topic_score_gemma":0.012280543,"teacher_disagreement_score":0.095503464,"about_ca_system_score_codex":0.0010481427,"about_ca_system_score_gemma":0.0035611992,"threshold_uncertainty_score":0.3194909},"labels":[],"label_agreement":null},{"id":"W4387145819","doi":"10.1007/978-3-031-42430-4_30","title":"A Projected Upper Bound for Mining High Utility Patterns from Interval-Based Event Sequences","year":2023,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","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":"University of Regina","funders":"","keywords":"Pruning; Interval (graph theory); Upper and lower bounds; Event (particle physics); Constraint (computer-aided design); Computer science; Branch and bound; Data mining; Mathematical optimization; Algorithm; Mathematics; Combinatorics; Physics","score_opus":0.07527730592061883,"score_gpt":0.32622547633851956,"score_spread":0.25094817041790074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387145819","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00824033,0.0016807346,0.98535943,0.00032197338,0.00012936008,0.00010502657,0.001029883,0.0009976306,0.0021355716],"genre_scores_gemma":[0.20683445,0.0033437482,0.77431935,0.000549746,0.0009876963,0.000850255,0.005739575,0.00045748294,0.0069176517],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99256116,0.0014078824,0.00053394755,0.0014447579,0.0034388052,0.0006134181],"domain_scores_gemma":[0.97271764,0.020764105,0.00084604096,0.002443725,0.002509796,0.00071875734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0059221387,0.0021207954,0.0035134912,0.0036267808,0.0010066604,0.005718896,0.004800183,0.0016752724,0.00912134],"category_scores_gemma":[0.038492434,0.0011871594,0.0021242728,0.0061585554,0.0015705028,0.006047909,0.004286319,0.0046431413,0.0026452597],"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":[0.0017266033,0.00063345564,0.004844473,0.0010881737,0.00040964005,0.00040889223,0.00027530376,0.40569592,0.007133748,0.09038481,0.020766143,0.46663287],"study_design_scores_gemma":[0.000024173647,0.00010010835,0.00044522076,0.000061545055,0.000038415197,0.00014511812,0.000027318292,0.954494,0.0012064171,0.041435134,0.00200023,0.000022345159],"about_ca_topic_score_codex":0.0033652848,"about_ca_topic_score_gemma":0.0027706402,"teacher_disagreement_score":0.00912134,"about_ca_system_score_codex":0.0019209088,"about_ca_system_score_gemma":0.0026952915,"threshold_uncertainty_score":0.03131962},"labels":[],"label_agreement":null},{"id":"W4387757194","doi":"10.23977/acss.2023.070810","title":"An Approach of Improved Traversal Merging of Transaction Data for Faster Apriori Algorithm","year":2023,"lang":"en","type":"article","venue":"Advances in Computer Signals and Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Tree traversal; Apriori algorithm; Association rule learning; Computer science; Data mining; Benchmark (surveying); A priori and a posteriori; Algorithm; Preprocessor; Data pre-processing; Merge (version control); Artificial intelligence; Parallel computing","score_opus":0.03984186272003694,"score_gpt":0.30966765083015907,"score_spread":0.26982578811012214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387757194","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012637389,0.00037545254,0.98373556,0.00017093119,0.00007209692,0.00014676552,0.00020331594,0.0018231913,0.0008352975],"genre_scores_gemma":[0.08282483,0.00034890155,0.9130785,0.00013695743,0.00008568444,0.00027300927,0.0014702212,0.00024340325,0.0015385166],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99496907,0.0008749691,0.0006195464,0.0011564692,0.0019617656,0.00041819122],"domain_scores_gemma":[0.99601656,0.000931827,0.00039328967,0.0009744466,0.0015224335,0.00016145017],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033541864,0.0015216824,0.0019271474,0.0041062795,0.0014692429,0.0025786,0.003356205,0.0011238379,0.0031229565],"category_scores_gemma":[0.009566328,0.001168945,0.0020391906,0.008817929,0.0008754819,0.0056509175,0.0027838661,0.0020978146,0.0017231158],"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":[0.0010372235,0.00039990895,0.0075349016,0.00045721914,0.0003726733,0.0006461387,0.0010104481,0.05708292,0.052302938,0.038621556,0.012898802,0.8276352],"study_design_scores_gemma":[0.00020208479,0.00067891413,0.0029034803,0.00004403739,0.00022015843,0.0017503974,0.00047604766,0.89175534,0.042681094,0.028013604,0.031092916,0.00018188958],"about_ca_topic_score_codex":0.0045882477,"about_ca_topic_score_gemma":0.0042333943,"teacher_disagreement_score":0.0045882477,"about_ca_system_score_codex":0.0008763975,"about_ca_system_score_gemma":0.003958717,"threshold_uncertainty_score":0.017738879},"labels":[],"label_agreement":null},{"id":"W4388425994","doi":"10.1109/dsaa60987.2023.10302550","title":"Enhanced Mining of High Utility Patterns from Streams of Dynamic Profit","year":2023,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"University of Manitoba","keywords":"Data stream mining; Computer science; Data mining; Scalability; Big data; Data stream; Knowledge extraction; Dynamic data; Profit (economics); Stream processing; Data science; Distributed computing; Database","score_opus":0.01769419806256547,"score_gpt":0.26780775898580794,"score_spread":0.2501135609232425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388425994","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20645018,0.00088444276,0.7852132,0.00078447955,0.00013610654,0.0003269285,0.0014640787,0.0024191374,0.002321557],"genre_scores_gemma":[0.6932924,0.0005615451,0.30129436,0.00016816302,0.00010930082,0.00015746389,0.0028418503,0.0000962731,0.0014786517],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988417,0.00017397043,0.00012380241,0.00026363094,0.00047167513,0.00012530452],"domain_scores_gemma":[0.99689215,0.0011389485,0.00047327307,0.00043859897,0.0008979715,0.00015921844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00150034,0.0007720256,0.0010814278,0.0027822251,0.00052857306,0.0015411135,0.0013870233,0.0005986422,0.00052303955],"category_scores_gemma":[0.006427036,0.0002967686,0.00082561345,0.0044190683,0.000402123,0.0022498511,0.0009602458,0.0009560935,0.00035908923],"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":[0.0006987619,0.00068421743,0.06966057,0.0004004899,0.0003457681,0.0014737296,0.00045126906,0.12408276,0.015472354,0.013546434,0.008310104,0.7648735],"study_design_scores_gemma":[0.00003193847,0.00009044673,0.0054165125,0.000019516503,0.000038656497,0.00043300848,0.00014730546,0.96884847,0.00655761,0.015400922,0.0029959814,0.000019603469],"about_ca_topic_score_codex":0.0018639936,"about_ca_topic_score_gemma":0.002459957,"teacher_disagreement_score":0.0027822251,"about_ca_system_score_codex":0.00043676945,"about_ca_system_score_gemma":0.000994938,"threshold_uncertainty_score":0.00793463},"labels":[],"label_agreement":null},{"id":"W4389071095","doi":"10.1016/j.eswa.2023.122754","title":"A new tree-based approach to mine sequential patterns","year":2023,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Data Mining Algorithms and Applications","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 Manitoba","funders":"","keywords":"Computer science; Pruning; Data mining; Tree (set theory); Sequence database; Depth-first search; Set (abstract data type); Heuristic; Search tree; Sequence (biology); Database; Artificial intelligence; Search algorithm; Algorithm; Mathematics","score_opus":0.03183737925473632,"score_gpt":0.27552079480129293,"score_spread":0.24368341554655662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389071095","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005603025,0.0006924522,0.9887656,0.00020898435,0.00013069976,0.00022291354,0.0014979966,0.001834117,0.00104423],"genre_scores_gemma":[0.037067108,0.0005280755,0.9558922,0.00019587648,0.000115758834,0.00024376619,0.0031786265,0.00017439967,0.0026040834],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99806315,0.00022083396,0.00022135372,0.0005074439,0.00088853197,0.00009869997],"domain_scores_gemma":[0.9964855,0.0015101156,0.0002653528,0.00037270808,0.0011773261,0.0001890106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011462719,0.00095078745,0.0014454954,0.005181421,0.00091498275,0.002179546,0.0017390788,0.0014531147,0.0034626487],"category_scores_gemma":[0.006276879,0.00053296465,0.0014876674,0.006890525,0.00047414683,0.0032197132,0.0012171987,0.0014413998,0.0025420033],"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":[0.00035993714,0.0003879938,0.0059992247,0.0007802835,0.00042321024,0.0005842296,0.0003792069,0.020975605,0.026327137,0.017863039,0.024713349,0.90120685],"study_design_scores_gemma":[0.00013103218,0.00037678378,0.0034991251,0.00020269709,0.00040791126,0.0020647277,0.00023104248,0.86252236,0.010699335,0.06888806,0.050857387,0.00011958478],"about_ca_topic_score_codex":0.004251118,"about_ca_topic_score_gemma":0.007826901,"teacher_disagreement_score":0.005181421,"about_ca_system_score_codex":0.00044373464,"about_ca_system_score_gemma":0.0018289578,"threshold_uncertainty_score":0.011583686},"labels":[],"label_agreement":null},{"id":"W4389084193","doi":"10.1007/978-3-031-47627-3_3","title":"A Primer on Database Indexing","year":2023,"lang":"en","type":"book-chapter","venue":"SpringerBriefs in computer science","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":"Online transaction processing; Search engine indexing; Computer science; Information retrieval; Database index; Hash function; Database; Database transaction; Transaction processing; Programming language","score_opus":0.04176890255042397,"score_gpt":0.2773764541281852,"score_spread":0.2356075515777612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389084193","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012105779,0.20124613,0.561521,0.021375258,0.0167337,0.0004800932,0.005449238,0.010846534,0.18113746],"genre_scores_gemma":[0.0142739415,0.1988837,0.45744905,0.017629433,0.0161641,0.00079063425,0.012476851,0.0052506886,0.27708167],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.996807,0.0004329341,0.0004361503,0.0004483907,0.0017134064,0.0001622526],"domain_scores_gemma":[0.99524915,0.0019686301,0.00017340375,0.0013085101,0.0010518628,0.00024834252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003406206,0.0015127906,0.002704985,0.012604227,0.0019449486,0.012799415,0.0042501087,0.002446527,0.051670287],"category_scores_gemma":[0.009362893,0.0017614672,0.001367249,0.028782707,0.0032474496,0.026063459,0.005062325,0.0050627813,0.048576545],"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":[0.000031502088,0.000055412143,0.00012875468,0.0006867535,0.000014498665,0.000057681085,0.00020419828,0.0006028964,0.0011926846,0.13797174,0.342212,0.516842],"study_design_scores_gemma":[0.000006952394,0.000013994513,0.00009261023,0.00021952775,0.00000700711,0.00027799408,0.00006066858,0.0011032046,0.0004916935,0.07045819,0.9272478,0.000020284757],"about_ca_topic_score_codex":0.0021093043,"about_ca_topic_score_gemma":0.0021178739,"teacher_disagreement_score":0.051670287,"about_ca_system_score_codex":0.0021775495,"about_ca_system_score_gemma":0.0021382223,"threshold_uncertainty_score":0.1728543},"labels":[],"label_agreement":null},{"id":"W4389998977","doi":"10.18280/mmep.100609","title":"Employing Data Mining Techniques for Engineering Soil Classification: A Unified Soil Classification System Approach","year":2023,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Unified Soil Classification System; Computer science; Data mining; Soil classification; Environmental science; Soil science; Soil water","score_opus":0.12821256687043395,"score_gpt":0.26823654184913887,"score_spread":0.14002397497870492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389998977","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016745225,0.000699968,0.97871864,0.0004685441,0.00007004264,0.00019095863,0.00043631298,0.000433705,0.0022366862],"genre_scores_gemma":[0.18329558,0.0011378012,0.81225556,0.00019483545,0.00010037442,0.00030504155,0.00095961697,0.0000537409,0.0016974971],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99820566,0.0003974719,0.0002702534,0.0002948497,0.00074254867,0.0000891928],"domain_scores_gemma":[0.99818784,0.0004956254,0.00019099581,0.00028124326,0.0007799822,0.00006427904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021594707,0.00063701184,0.0014067428,0.0043798345,0.0007598494,0.003643308,0.0013188821,0.000819027,0.0011876735],"category_scores_gemma":[0.0043694647,0.00035033337,0.0014551356,0.0045590536,0.000802706,0.002223609,0.001743924,0.00095681194,0.000636583],"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":[0.00020191177,0.0004382654,0.020968439,0.0008350139,0.00054077874,0.00028014122,0.0005601855,0.060960837,0.01792564,0.07794148,0.00682803,0.81251925],"study_design_scores_gemma":[0.000046593595,0.00025944458,0.010027825,0.0002700554,0.00041696522,0.00051443867,0.00045306343,0.8668935,0.014158308,0.07950348,0.027360292,0.000096110205],"about_ca_topic_score_codex":0.004384008,"about_ca_topic_score_gemma":0.005289268,"teacher_disagreement_score":0.004384008,"about_ca_system_score_codex":0.00096179463,"about_ca_system_score_gemma":0.0023128572,"threshold_uncertainty_score":0.011420548},"labels":[],"label_agreement":null},{"id":"W4390078536","doi":"10.1016/j.asoc.2023.111191","title":"Granular fuzzy rule-based model construction under the collaboration of multiple organizations","year":2023,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Data Mining Algorithms and Applications","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":"Ministry of Education Key Projects of Philosophy and Social Sciences Research; Natural Science Foundation of Chongqing; Ministry of Education of the People's Republic of China; National Natural Science Foundation of China","keywords":"Computer science; Data mining; Granularity; Cluster analysis; Construct (python library); Fuzzy logic; Set (abstract data type); Fuzzy rule; Data modeling; Data set; Fuzzy set; Artificial intelligence; Machine learning; Database","score_opus":0.014101702687057963,"score_gpt":0.24176381757667154,"score_spread":0.22766211488961358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390078536","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06576116,0.00013208628,0.9295862,0.00033241295,0.000036780337,0.00009721541,0.00023078034,0.00025813413,0.0035652334],"genre_scores_gemma":[0.8094348,0.000176293,0.18775111,0.000060766477,0.000027806225,0.00016313833,0.00049192924,0.000030806583,0.0018633303],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998052,0.00047945383,0.00017617342,0.0004298985,0.000658652,0.00020384988],"domain_scores_gemma":[0.99707615,0.0012854656,0.0004122094,0.00050359074,0.0005747733,0.00014783263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020609824,0.00042405067,0.0010186242,0.0016157343,0.000845666,0.0029964822,0.0016597599,0.0011671182,0.0018353725],"category_scores_gemma":[0.007326856,0.0003792117,0.0015523724,0.0019671847,0.0009679708,0.002886044,0.0017163255,0.0011096178,0.00030019935],"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":[0.00019745462,0.000109496315,0.0037801603,0.00014986312,0.00016769729,0.0008963371,0.00045669574,0.81657475,0.002470917,0.11791997,0.0010852566,0.056191422],"study_design_scores_gemma":[0.000008913035,0.000012624536,0.00023766974,0.000012147152,0.000027937049,0.00004218558,0.000045290813,0.96431434,0.00041017504,0.034549594,0.0003309724,0.000008174849],"about_ca_topic_score_codex":0.0075642145,"about_ca_topic_score_gemma":0.0046223276,"teacher_disagreement_score":0.0075642145,"about_ca_system_score_codex":0.0011402088,"about_ca_system_score_gemma":0.0018766882,"threshold_uncertainty_score":0.015040398},"labels":[],"label_agreement":null},{"id":"W4390188127","doi":"10.1109/dasc/picom/cbdcom/cy59711.2023.10361366","title":"Efficient Vertical Mining of Frequent Quantitative Patterns","year":2023,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":8,"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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; University of Manitoba","keywords":"Computer science; Association rule learning; Bitmap; Data mining; Scalability; Database transaction; Data science; Artificial intelligence; Database","score_opus":0.0453042526928973,"score_gpt":0.3105550925922213,"score_spread":0.265250839899324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390188127","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14613536,0.0007558347,0.844463,0.00033732026,0.00006181811,0.00033556647,0.0016894782,0.0028604995,0.0033611066],"genre_scores_gemma":[0.49199364,0.00041203087,0.49771068,0.00013800622,0.000050688177,0.0002542674,0.006899626,0.00015220187,0.002388759],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99811673,0.00026404046,0.00022104937,0.00038023348,0.0008057861,0.0002121991],"domain_scores_gemma":[0.996166,0.0012731504,0.0004840814,0.0006415352,0.0013059265,0.00012936628],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012698536,0.00094927906,0.0011976161,0.002253798,0.0006484356,0.0013131297,0.0014030013,0.00057093624,0.0018831338],"category_scores_gemma":[0.0065823714,0.000604129,0.0010346969,0.0030329821,0.00038865235,0.0022388273,0.0017683333,0.00069187215,0.0007909358],"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":[0.0005771331,0.0003256453,0.017050564,0.00058833533,0.00016698896,0.0007371005,0.00034950467,0.0916584,0.036407243,0.01516696,0.007273575,0.8296986],"study_design_scores_gemma":[0.00006408994,0.00017894917,0.0025397143,0.000034917277,0.00004370024,0.00044493386,0.00019108264,0.9648312,0.008469991,0.019417575,0.003766809,0.000017019594],"about_ca_topic_score_codex":0.0020333333,"about_ca_topic_score_gemma":0.0025333082,"teacher_disagreement_score":0.002253798,"about_ca_system_score_codex":0.0004367412,"about_ca_system_score_gemma":0.0014311404,"threshold_uncertainty_score":0.0067156553},"labels":[],"label_agreement":null},{"id":"W4391020777","doi":"10.1109/smarttechcon57526.2023.10391642","title":"Statistical Analysis of Ecological Mathematical Model Based on Data Warehouse","year":2023,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Computer science; Data warehouse; Field (mathematics); The Internet; Competition (biology); Data science; Stability (learning theory); Biological data; Ecosystem model; Mathematical model; Marine ecosystem; Database; Ecology; World Wide Web; Ecosystem","score_opus":0.1071361683302552,"score_gpt":0.35051622392110676,"score_spread":0.24338005559085157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391020777","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22876805,0.0005999204,0.7605528,0.000826073,0.00006151219,0.00017046127,0.0037981968,0.0020322024,0.0031906248],"genre_scores_gemma":[0.88820183,0.0006998824,0.101980746,0.00011460843,0.00006583857,0.00038539284,0.0072682826,0.000119320604,0.0011640259],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99748504,0.00074038684,0.00032744466,0.000495575,0.0007802719,0.00017119992],"domain_scores_gemma":[0.9927308,0.0037587332,0.0009235595,0.0010971483,0.0013063978,0.00018334088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038565302,0.0006135813,0.00096570805,0.0041543082,0.00058782444,0.0033117284,0.001513537,0.0005408615,0.0011680685],"category_scores_gemma":[0.012029352,0.00043120483,0.001592982,0.0037357039,0.0005664517,0.0038960252,0.0011637743,0.000862353,0.00024486467],"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":[0.00042837125,0.00047475236,0.101522945,0.00054731907,0.0007441868,0.0010886604,0.0009850203,0.52209204,0.0040226863,0.26084787,0.013495861,0.093750395],"study_design_scores_gemma":[0.000008994625,0.000022522652,0.0034316883,0.000010693225,0.00002826512,0.000099068384,0.000086043794,0.9732901,0.0006480795,0.021086503,0.0012650683,0.000022970813],"about_ca_topic_score_codex":0.007138732,"about_ca_topic_score_gemma":0.0031441748,"teacher_disagreement_score":0.007138732,"about_ca_system_score_codex":0.001600181,"about_ca_system_score_gemma":0.0012781852,"threshold_uncertainty_score":0.020395517},"labels":[],"label_agreement":null},{"id":"W4391021321","doi":"10.1109/smarttechcon57526.2023.10391364","title":"Research on Majorization Algorithm and Application of Geotechnical Engineering Structure Based on Granule Swarm Majorization","year":2023,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Majorization; Swarm behaviour; Mathematical optimization; Particle swarm optimization; Algorithm; Mathematics; Computer science; Combinatorics","score_opus":0.019053616029532105,"score_gpt":0.30250863451125154,"score_spread":0.28345501848171945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391021321","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007023301,0.00040526438,0.9903598,0.000109032895,0.00004118743,0.000028071534,0.000015400647,0.00017946782,0.0018384848],"genre_scores_gemma":[0.5044336,0.0024024302,0.4856697,0.00018370293,0.00020524836,0.00030392376,0.0003183952,0.00023027381,0.0062527647],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99952614,0.0000921394,0.00003672719,0.00012718924,0.0001736933,0.000044165736],"domain_scores_gemma":[0.999509,0.00016152459,0.000046933408,0.000045385856,0.0002145006,0.000022660415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007621577,0.00089400937,0.0009798907,0.0009862122,0.00043026824,0.0010454367,0.0008185916,0.000710452,0.0017069156],"category_scores_gemma":[0.0014194417,0.00039504663,0.001155778,0.0012510528,0.00074106053,0.0015085636,0.00069325516,0.00087488355,0.00039047244],"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":[0.000091619666,0.00006233474,0.0021672957,0.000330864,0.00011558594,0.00009724415,0.00024879642,0.60080785,0.01952822,0.05863842,0.0035686858,0.31434312],"study_design_scores_gemma":[0.000016605152,0.00004977313,0.00036960273,0.000013015922,0.000018456763,0.000059594102,0.000025729067,0.98378885,0.003447467,0.008623902,0.0035733522,0.000013755356],"about_ca_topic_score_codex":0.002823872,"about_ca_topic_score_gemma":0.0011993827,"teacher_disagreement_score":0.002823872,"about_ca_system_score_codex":0.00081398454,"about_ca_system_score_gemma":0.0010104126,"threshold_uncertainty_score":0.005905926},"labels":[],"label_agreement":null},{"id":"W4391096379","doi":"10.1109/bigdata59044.2023.10386531","title":"Refactoring ETL Flows in The Wild","year":2023,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Code refactoring; Computer science; IBM; Context (archaeology); Pipeline (software); Data integration; Data flow diagram; Data mining; Database; Software engineering; Operating system; Software","score_opus":0.04099050327581285,"score_gpt":0.2888281117088855,"score_spread":0.24783760843307265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391096379","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31392995,0.0007990208,0.62047935,0.0014481499,0.0003750586,0.0006847024,0.0019927837,0.057260424,0.0030305597],"genre_scores_gemma":[0.4487873,0.00042630913,0.5350908,0.0006689703,0.00008399905,0.00030657003,0.0057563097,0.005106059,0.003773685],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9949352,0.0013262132,0.0005016456,0.001182639,0.001711141,0.00034313017],"domain_scores_gemma":[0.96333915,0.014511498,0.0023374492,0.0142114535,0.004998452,0.0006019686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007409404,0.0015587868,0.0006143223,0.0019547895,0.0009702048,0.0019735263,0.0026838533,0.0011508481,0.0014823222],"category_scores_gemma":[0.035669643,0.0010378847,0.001355696,0.0015855053,0.0013141318,0.00447615,0.002428153,0.0023224575,0.00092324533],"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":[0.001115081,0.00095276476,0.04741264,0.000817016,0.00031579682,0.0018794424,0.0031769383,0.08045189,0.07379559,0.011155299,0.020364938,0.75856256],"study_design_scores_gemma":[0.00023153078,0.00065081345,0.011231062,0.000269136,0.00020998971,0.0014487135,0.0011637276,0.751318,0.14240357,0.033361673,0.0575043,0.0002074997],"about_ca_topic_score_codex":0.0047490927,"about_ca_topic_score_gemma":0.004194457,"teacher_disagreement_score":0.007409404,"about_ca_system_score_codex":0.0011446615,"about_ca_system_score_gemma":0.001842021,"threshold_uncertainty_score":0.039185166},"labels":[],"label_agreement":null},{"id":"W4391392503","doi":"10.5539/cis.v17n1p1","title":"Expanding the Breadth of Ability in Artificial Intelligence Systems with Decision Trees","year":2024,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Decision tree; Machine learning","score_opus":0.02518388695967329,"score_gpt":0.2926664620425641,"score_spread":0.2674825750828908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391392503","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06843244,0.0060174214,0.8785605,0.004050543,0.00008072893,0.00017186535,0.000079864316,0.0012264929,0.041380093],"genre_scores_gemma":[0.60803556,0.0037757882,0.38293236,0.00090020755,0.0002399766,0.0002447272,0.000102866165,0.00024291004,0.0035255898],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966695,0.001461684,0.00025195192,0.00041704503,0.0009936967,0.00020608636],"domain_scores_gemma":[0.98936135,0.008459703,0.0003307991,0.0010894422,0.00047646838,0.00028213722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0059678904,0.0008651019,0.00082079327,0.001815331,0.0011639529,0.0040183673,0.0015402504,0.001320689,0.0031235446],"category_scores_gemma":[0.01303058,0.0006208624,0.000883982,0.0016331241,0.0039120633,0.013356267,0.0064711007,0.0022237888,0.001080762],"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":[0.0003098926,0.00028306362,0.0052244486,0.0010504443,0.00014338362,0.00046924935,0.005654212,0.03725932,0.015524526,0.48985127,0.001852818,0.44237748],"study_design_scores_gemma":[0.00010255517,0.00050848175,0.0013476439,0.0005960055,0.0001887779,0.0008319451,0.00094478927,0.13124803,0.010331335,0.7777457,0.07605235,0.00010246738],"about_ca_topic_score_codex":0.00069935655,"about_ca_topic_score_gemma":0.00069692306,"teacher_disagreement_score":0.0059678904,"about_ca_system_score_codex":0.0005469548,"about_ca_system_score_gemma":0.0009805528,"threshold_uncertainty_score":0.031561553},"labels":[],"label_agreement":null},{"id":"W4391417631","doi":"10.48550/arxiv.2401.15330","title":"Optimal Sparse Survival Trees","year":2024,"lang":"en","type":"preprint","venue":"PubMed","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute on Drug Abuse; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Tree (set theory); Mathematics; Combinatorics","score_opus":0.048124231935973295,"score_gpt":0.25762628296361495,"score_spread":0.20950205102764166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391417631","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04247099,0.0009920121,0.93945175,0.0017391836,0.00007837922,0.00013000374,0.0030490118,0.0012455358,0.010843211],"genre_scores_gemma":[0.6112591,0.0022377442,0.36033997,0.0010371146,0.00038508393,0.0006818772,0.011175178,0.0007605874,0.012123307],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988096,0.0003986822,0.000055252363,0.0002919376,0.00028697032,0.00015756665],"domain_scores_gemma":[0.9911238,0.0071882294,0.00042576971,0.00047271146,0.0005478609,0.00024163019],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017015769,0.0009517006,0.0012581084,0.0013507927,0.00087566377,0.0015671746,0.0011708222,0.001880218,0.009668672],"category_scores_gemma":[0.017555447,0.0007408949,0.001327796,0.0018481611,0.0011817383,0.0030456262,0.0017401809,0.002367358,0.0023878135],"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":[0.00027779563,0.00015156325,0.00371477,0.00045624588,0.00007159662,0.0003270415,0.0004334852,0.52170235,0.002657869,0.2962976,0.042867336,0.13104236],"study_design_scores_gemma":[0.000032310883,0.000034419103,0.00033575756,0.000064633874,0.000018591103,0.00011912674,0.000057708527,0.6047163,0.0005401179,0.3894641,0.0046043973,0.000012556691],"about_ca_topic_score_codex":0.0020032045,"about_ca_topic_score_gemma":0.0041901213,"teacher_disagreement_score":0.009668672,"about_ca_system_score_codex":0.0011548558,"about_ca_system_score_gemma":0.0013653043,"threshold_uncertainty_score":0.032344937},"labels":[],"label_agreement":null},{"id":"W4391938566","doi":"10.7146/hn.v5i2.142739","title":"Tyndale STEPBible Data development for machine analysis and computational linguistics","year":2019,"lang":"en","type":"article","venue":"HIPHIL Novum","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Tyndale University","funders":"","keywords":"Computer science; Linguistics; Natural language processing; Philosophy","score_opus":0.040369798406899436,"score_gpt":0.2970036244541125,"score_spread":0.2566338260472131,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391938566","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005062789,0.00032249987,0.021677691,0.0012583033,0.00055164204,0.0008389557,0.8784337,0.014098741,0.07775569],"genre_scores_gemma":[0.009748328,0.00023701473,0.039521545,0.0003350633,0.00010784905,0.0036024142,0.8816726,0.0074792,0.05729599],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99747545,0.00038184275,0.00026553794,0.00050125003,0.001131729,0.00024417214],"domain_scores_gemma":[0.98599535,0.003458453,0.00073177513,0.004159473,0.0042650434,0.0013898946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002586547,0.00082850334,0.0009847423,0.0067923763,0.001884208,0.0038726858,0.0020799935,0.0010226882,0.19458094],"category_scores_gemma":[0.021659788,0.0010380469,0.00085793174,0.008854646,0.00086302386,0.0038669563,0.0050885733,0.0028159637,0.16908957],"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":[0.00033323315,0.00008663468,0.002195795,0.0003864293,0.000019451421,0.00019700284,0.0002591807,0.00023837254,0.0011415898,0.008682526,0.94591373,0.040546056],"study_design_scores_gemma":[0.00007651961,0.0000322441,0.0035924388,0.0001608266,0.000008391753,0.00016073338,0.00014763557,0.00066439237,0.0023700409,0.004110195,0.9886419,0.000034600554],"about_ca_topic_score_codex":0.009341516,"about_ca_topic_score_gemma":0.02019553,"teacher_disagreement_score":0.19458094,"about_ca_system_score_codex":0.0012753656,"about_ca_system_score_gemma":0.004601329,"threshold_uncertainty_score":0.6509381},"labels":[],"label_agreement":null},{"id":"W4392412456","doi":"10.1109/swc57546.2023.10448861","title":"A Scalable Algorithm for Vertical Mining of Quantitative Frequent Patterns","year":2023,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Scalability; Algorithm design; Data mining; Algorithm; Database","score_opus":0.051436200931180044,"score_gpt":0.32084182702988795,"score_spread":0.2694056260987079,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392412456","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009890416,0.00026166643,0.98365825,0.00021121897,0.00007663382,0.00025440598,0.00039872815,0.0036763875,0.0015723377],"genre_scores_gemma":[0.09399496,0.00016682073,0.9015025,0.00016120197,0.000067803965,0.00041370766,0.0018691028,0.00019588953,0.0016280442],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983821,0.00022015498,0.00017160916,0.00042782663,0.0006297139,0.00016854516],"domain_scores_gemma":[0.9981292,0.00069587363,0.00017232099,0.00039955575,0.0005190108,0.00008404512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016167521,0.0012667105,0.0011792632,0.0020483218,0.00073016825,0.0012505971,0.0021157397,0.0009953101,0.005342245],"category_scores_gemma":[0.006219665,0.0006307518,0.0011609232,0.002870906,0.000584439,0.002755664,0.002184277,0.0013192691,0.001926875],"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":[0.00043739507,0.00020151043,0.0025556523,0.00037286791,0.00010844785,0.00027847636,0.00016728073,0.098181844,0.017248753,0.017898165,0.01586481,0.8466849],"study_design_scores_gemma":[0.00014292302,0.00012102715,0.0003460268,0.000025555792,0.000024885612,0.00028628812,0.00006391255,0.97079515,0.003514498,0.019150145,0.0055113714,0.000018147728],"about_ca_topic_score_codex":0.0022540027,"about_ca_topic_score_gemma":0.0025558006,"teacher_disagreement_score":0.005342245,"about_ca_system_score_codex":0.00061881775,"about_ca_system_score_gemma":0.0019857113,"threshold_uncertainty_score":0.017871618},"labels":[],"label_agreement":null},{"id":"W4392457954","doi":"10.22214/ijraset.2024.58693","title":"Research Paper on Role of Data Features and Data Collection Tools in Artificial Intelligence","year":2024,"lang":"en","type":"article","venue":"International Journal for Research in Applied Science and Engineering Technology","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Data collection; Artificial intelligence; Data science; Sociology; Social science","score_opus":0.22383088308012367,"score_gpt":0.47826155377397955,"score_spread":0.2544306706938559,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392457954","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08177964,0.087040514,0.6071974,0.09096011,0.007211963,0.0015612687,0.0029449693,0.003268039,0.11803612],"genre_scores_gemma":[0.6341274,0.041398056,0.29246783,0.0056244307,0.0037669821,0.0010351334,0.0033934508,0.00091171963,0.017275037],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98770547,0.005834201,0.000998177,0.0020875956,0.0030273108,0.00034716865],"domain_scores_gemma":[0.8771674,0.0945269,0.003844887,0.00785489,0.014317471,0.0022884896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021852124,0.0010647988,0.0010524357,0.0052457917,0.0013942649,0.011829731,0.0030372662,0.002181705,0.007169078],"category_scores_gemma":[0.07444918,0.0006571593,0.001262051,0.013125107,0.003116888,0.024716388,0.0030437259,0.0032946623,0.0018216417],"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":[0.0006298768,0.00044789637,0.025744276,0.0025875955,0.00027365627,0.00051820406,0.002050708,0.007735724,0.0017454056,0.23862642,0.041623905,0.6780164],"study_design_scores_gemma":[0.00026868717,0.0007487088,0.021684201,0.004381486,0.0006098417,0.0017124162,0.0053203213,0.15091905,0.012935701,0.36720556,0.43387955,0.00033451035],"about_ca_topic_score_codex":0.0038215995,"about_ca_topic_score_gemma":0.0012711708,"teacher_disagreement_score":0.021852124,"about_ca_system_score_codex":0.0031882992,"about_ca_system_score_gemma":0.0038482922,"threshold_uncertainty_score":0.11556643},"labels":[],"label_agreement":null},{"id":"W4392588267","doi":"10.1007/s10489-024-05356-7","title":"Graph-based substructure pattern mining with edge-weight","year":2024,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Data Mining Algorithms and Applications","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 Manitoba","funders":"","keywords":"Computer science; Substructure; Enhanced Data Rates for GSM Evolution; Graph; Pattern recognition (psychology); Artificial intelligence; Theoretical computer science","score_opus":0.013236943861075396,"score_gpt":0.2370589433546355,"score_spread":0.2238219994935601,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392588267","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.103022814,0.0010240916,0.88488954,0.00024200401,0.00012858682,0.00046000828,0.0030733796,0.0051644538,0.0019951533],"genre_scores_gemma":[0.33384222,0.00050971867,0.65594375,0.00014286194,0.000064390646,0.00025681278,0.0061054956,0.00022282235,0.0029119402],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99926645,0.00007526202,0.00008224821,0.0002449397,0.00027439848,0.000056670706],"domain_scores_gemma":[0.9989612,0.00038575556,0.000105443505,0.00018893149,0.00029645412,0.00006224176],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004886462,0.0008045362,0.001237378,0.0051756552,0.0005894298,0.0010678794,0.0016367113,0.000791441,0.0025195433],"category_scores_gemma":[0.0026394427,0.00031120362,0.0013230288,0.0053905877,0.00039223165,0.001394668,0.0010812335,0.0007719605,0.0011272357],"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":[0.0008362111,0.00055828405,0.0159897,0.00070987194,0.00060256565,0.00053427677,0.00016418131,0.038995944,0.033744365,0.005601907,0.007949756,0.89431286],"study_design_scores_gemma":[0.00010117673,0.000277729,0.0059460755,0.00005802953,0.0003904337,0.00084155734,0.00015385513,0.9478652,0.01745585,0.02019995,0.006664883,0.000045276447],"about_ca_topic_score_codex":0.0038422388,"about_ca_topic_score_gemma":0.006636176,"teacher_disagreement_score":0.0051756552,"about_ca_system_score_codex":0.00033618434,"about_ca_system_score_gemma":0.000914199,"threshold_uncertainty_score":0.008428752},"labels":[],"label_agreement":null},{"id":"W4392845515","doi":"10.1145/3625007.3627497","title":"CFAR++: Enhancing Rule Based Classifier","year":2023,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Classifier (UML); Pattern recognition (psychology); Rule-based system; Data mining","score_opus":0.027117908906257735,"score_gpt":0.2707455851698921,"score_spread":0.24362767626363438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392845515","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034125563,0.001976046,0.9352177,0.00067002047,0.0005144065,0.00031792768,0.001606491,0.018586945,0.006984927],"genre_scores_gemma":[0.18597093,0.0012152569,0.7985619,0.00096109987,0.000398031,0.00035027112,0.004244176,0.00057350745,0.0077248313],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99713206,0.0004623707,0.00021059175,0.0005460339,0.0014885565,0.00016034089],"domain_scores_gemma":[0.9939978,0.0021561524,0.0003478618,0.001248165,0.0020856436,0.00016439437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030414232,0.0012133833,0.0016291605,0.002743225,0.0006335308,0.001718743,0.0033817755,0.0016399317,0.0032616975],"category_scores_gemma":[0.010474877,0.00051186694,0.0011989727,0.002903362,0.00041208154,0.002845958,0.0014252071,0.002188189,0.004618408],"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":[0.00021501184,0.00040219276,0.0050278367,0.00020139404,0.00014807511,0.00024668375,0.000093226605,0.057404716,0.005520358,0.004068045,0.026177347,0.9004951],"study_design_scores_gemma":[0.00004300524,0.00020912189,0.0011348815,0.000051646213,0.00009257807,0.00046017417,0.00003238688,0.96186686,0.0073670396,0.007772241,0.020928213,0.000041911342],"about_ca_topic_score_codex":0.0055159195,"about_ca_topic_score_gemma":0.007846183,"teacher_disagreement_score":0.0055159195,"about_ca_system_score_codex":0.0004961996,"about_ca_system_score_gemma":0.001504137,"threshold_uncertainty_score":0.01608473},"labels":[],"label_agreement":null},{"id":"W4392846249","doi":"10.1145/3625007.3627334","title":"Social network mining and analytics for quantitative patterns","year":2023,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Analytics; Data science; Social network analysis; Social network (sociolinguistics); World Wide Web; Social media","score_opus":0.08457761569685772,"score_gpt":0.35241089041079504,"score_spread":0.2678332747139373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392846249","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028394822,0.0017412741,0.94947994,0.0023956546,0.00013630807,0.0006180478,0.0053538075,0.0032569808,0.0086231725],"genre_scores_gemma":[0.36513454,0.001993298,0.61968815,0.0004701257,0.00020491553,0.0008238222,0.008210778,0.00016479217,0.0033095905],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99591184,0.0011977381,0.0003249389,0.00070326205,0.0017269286,0.00013537644],"domain_scores_gemma":[0.9922901,0.004388882,0.001061644,0.0009689089,0.0011361171,0.00015438782],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023843742,0.0013657329,0.0008998905,0.005925174,0.0006940568,0.0021743537,0.0013238746,0.00093558064,0.0035058197],"category_scores_gemma":[0.016211357,0.0003823251,0.0009980419,0.0059262696,0.0007570642,0.0048866714,0.0020526326,0.0012321057,0.0014374829],"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":[0.00029420014,0.00038898803,0.026668694,0.0017219633,0.0004900507,0.00070910173,0.0009915539,0.12584095,0.007341821,0.13486388,0.028995613,0.671693],"study_design_scores_gemma":[0.000032515352,0.00008693389,0.0039639305,0.00017280874,0.00005522151,0.00048012592,0.0005816687,0.758079,0.004378262,0.20234258,0.029788239,0.000038633196],"about_ca_topic_score_codex":0.0020672714,"about_ca_topic_score_gemma":0.0025061427,"teacher_disagreement_score":0.005925174,"about_ca_system_score_codex":0.0009311984,"about_ca_system_score_gemma":0.00092798466,"threshold_uncertainty_score":0.012609959},"labels":[],"label_agreement":null},{"id":"W4393412842","doi":"10.5281/zenodo.7488425","title":"Sheep pseudoDB: simulated database of sheep genetic variants","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Database; Computer science","score_opus":0.03169396252765817,"score_gpt":0.25819633184415436,"score_spread":0.2265023693164962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393412842","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019137235,0.00049411476,0.001819922,0.00035558626,0.00012214156,0.000080842576,0.9752362,0.0011690261,0.0015849891],"genre_scores_gemma":[0.013467249,0.00011820792,0.0021853333,0.00012988977,0.000010477821,0.0001324678,0.983297,0.00004951202,0.00060994143],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994035,0.00015184244,0.00006724679,0.00017163243,0.00014992592,0.000055945013],"domain_scores_gemma":[0.9984682,0.00062427646,0.000090253976,0.0004007596,0.00024943842,0.00016705987],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010808454,0.0010364965,0.0008662558,0.0014989603,0.00039178735,0.0008822759,0.0021868078,0.001508491,0.008166288],"category_scores_gemma":[0.0049234754,0.00036625806,0.000883409,0.0020058565,0.00032148007,0.0004413423,0.0008214911,0.0010986013,0.0055266176],"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":[0.001928094,0.00047940528,0.026896358,0.0015442444,0.00049501023,0.0007724665,0.0000935632,0.014356411,0.002724359,0.0023345163,0.9265962,0.021779247],"study_design_scores_gemma":[0.0040276777,0.0007216584,0.06612567,0.0006274849,0.0005264974,0.0042449506,0.0004812185,0.061191816,0.008943531,0.011108352,0.8418393,0.00016186025],"about_ca_topic_score_codex":0.008301289,"about_ca_topic_score_gemma":0.013482298,"teacher_disagreement_score":0.008301289,"about_ca_system_score_codex":0.00063551794,"about_ca_system_score_gemma":0.0012143892,"threshold_uncertainty_score":0.027318954},"labels":[],"label_agreement":null},{"id":"W4393453032","doi":"10.5281/zenodo.7488424","title":"Sheep pseudoDB: simulated database of sheep genetic variants","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Database; Computer science","score_opus":0.03169396252765817,"score_gpt":0.25819633184415436,"score_spread":0.2265023693164962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393453032","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019137235,0.00049411476,0.001819922,0.00035558626,0.00012214156,0.000080842576,0.9752362,0.0011690261,0.0015849891],"genre_scores_gemma":[0.013467249,0.00011820792,0.0021853333,0.00012988977,0.000010477821,0.0001324678,0.983297,0.00004951202,0.00060994143],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994035,0.00015184244,0.00006724679,0.00017163243,0.00014992592,0.000055945013],"domain_scores_gemma":[0.9984682,0.00062427646,0.000090253976,0.0004007596,0.00024943842,0.00016705987],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010808454,0.0010364965,0.0008662558,0.0014989603,0.00039178735,0.0008822759,0.0021868078,0.001508491,0.008166288],"category_scores_gemma":[0.0049234754,0.00036625806,0.000883409,0.0020058565,0.00032148007,0.0004413423,0.0008214911,0.0010986013,0.0055266176],"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":[0.001928094,0.00047940528,0.026896358,0.0015442444,0.00049501023,0.0007724665,0.0000935632,0.014356411,0.002724359,0.0023345163,0.9265962,0.021779247],"study_design_scores_gemma":[0.0040276777,0.0007216584,0.06612567,0.0006274849,0.0005264974,0.0042449506,0.0004812185,0.061191816,0.008943531,0.011108352,0.8418393,0.00016186025],"about_ca_topic_score_codex":0.008301289,"about_ca_topic_score_gemma":0.013482298,"teacher_disagreement_score":0.008301289,"about_ca_system_score_codex":0.00063551794,"about_ca_system_score_gemma":0.0012143892,"threshold_uncertainty_score":0.027318954},"labels":[],"label_agreement":null},{"id":"W4393821888","doi":"10.5281/zenodo.7439295","title":"Log Dataset","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science","score_opus":0.04229074189782631,"score_gpt":0.26993921849922553,"score_spread":0.22764847660139922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393821888","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00093966647,0.0000714973,0.00024197377,0.000091931295,0.000053652362,0.000050801398,0.9956474,0.0020964483,0.00080658187],"genre_scores_gemma":[0.0014658691,0.00006488484,0.00079258723,0.00006075392,0.000010269466,0.00012527568,0.9966794,0.000118259515,0.000682723],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998784,0.00013784358,0.00019016828,0.0003200189,0.00037794045,0.00019013946],"domain_scores_gemma":[0.9968362,0.00076769566,0.00023875982,0.0010709467,0.00080112234,0.0002852092],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009057468,0.0027010222,0.0012166469,0.004584079,0.00085999264,0.0015298073,0.0021074675,0.0018177874,0.03665855],"category_scores_gemma":[0.005340833,0.0005689925,0.0012259493,0.005285431,0.00051140925,0.0013147327,0.0013094597,0.001661829,0.044639908],"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":[0.0001871212,0.00014775652,0.0013093728,0.00063978264,0.000035673693,0.000057514142,0.000023337132,0.0011730787,0.00052866555,0.00046131987,0.98835117,0.007085231],"study_design_scores_gemma":[0.00075032533,0.0001562215,0.00970958,0.00029998776,0.00008688836,0.00030550946,0.00023871512,0.0072588045,0.0027482796,0.0037027334,0.97464913,0.00009379134],"about_ca_topic_score_codex":0.012072839,"about_ca_topic_score_gemma":0.017050143,"teacher_disagreement_score":0.03665855,"about_ca_system_score_codex":0.0010373045,"about_ca_system_score_gemma":0.0029688878,"threshold_uncertainty_score":0.12263507},"labels":[],"label_agreement":null},{"id":"W4394400498","doi":"10.6084/m9.figshare.1194732","title":"Distance-based Data Accumulation","year":2014,"lang":"en","type":"dataset","venue":"Figshare","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.17342543670323726,"score_gpt":0.35644237057538053,"score_spread":0.18301693387214327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394400498","genre_codex":"methods","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02649245,0.0016595777,0.45701355,0.0009514651,0.002038701,0.004036662,0.3780435,0.10514061,0.024623478],"genre_scores_gemma":[0.091080785,0.0008231045,0.5948981,0.000478964,0.0003210656,0.0040160366,0.29196468,0.005460336,0.010956792],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9938113,0.0006593029,0.0008015849,0.0024619626,0.0018791734,0.00038670452],"domain_scores_gemma":[0.9866535,0.0018659859,0.0007747803,0.0047110277,0.005458981,0.00053571275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00514035,0.0024155222,0.0018105133,0.007030106,0.0011341237,0.003368482,0.0035225882,0.0013829942,0.027944235],"category_scores_gemma":[0.029717078,0.00090315245,0.0014795914,0.0061545055,0.0005949989,0.0043210434,0.005822562,0.0022621911,0.035545584],"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":[0.0017510029,0.00068749476,0.020750307,0.0023631405,0.00049822597,0.00044277182,0.0013229477,0.010379846,0.02154997,0.009681144,0.30204436,0.6285288],"study_design_scores_gemma":[0.00035516015,0.0009850448,0.035926387,0.0010880406,0.00037407,0.0008750147,0.00256548,0.18553977,0.04530511,0.030792097,0.69563425,0.0005595991],"about_ca_topic_score_codex":0.0050894353,"about_ca_topic_score_gemma":0.008809968,"teacher_disagreement_score":0.027944235,"about_ca_system_score_codex":0.00085177744,"about_ca_system_score_gemma":0.0026439065,"threshold_uncertainty_score":0.09348279},"labels":[],"label_agreement":null},{"id":"W4395075562","doi":"10.1007/978-981-97-2262-4","title":"Advances in Knowledge Discovery and Data Mining","year":2024,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"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":"China University of Geosciences; National Cheng Kung University; National Taiwan University of Science and Technology; Università di Pisa; Uppsala Universitet; Universidad de Zaragoza; University of Dhaka; University of Illinois at Urbana-Champaign; National Taiwan University; Syddansk Universitet; Hokkaido University; National Tsing Hua University; Shanghai Jiao Tong University; Pontificia Universidade Católica do Paraná; Università degli Studi di Pavia; Shanxi University; Nanjing University of Aeronautics and Astronautics; University of Massachusetts Boston; East China Normal University; Chang Gung University; Chinese Academy of Sciences; University of Science and Technology of China; South Asian University; Nanyang Technological University; Macquarie University; University of Pittsburgh; Massey University; Indian Institute of Technology Delhi; Chang Gung Medical Foundation; National Kaohsiung University of Science and Technology; Université Paris-Est Créteil Val-de-Marne; University of Minnesota; Politecnico di Torino; Swinburne University of Technology; McMaster University; Santa Clara University; Nanjing University; New Mexico State University; University of Texas at Arlington; Deakin University; University of Maryland, Baltimore County; Georgia State University; Arizona State University; Budapesti Műszaki és Gazdaságtudományi Egyetem; Ohio State University","keywords":"Computer science; Knowledge extraction; Data science; Data mining; Information retrieval","score_opus":0.02452480294645317,"score_gpt":0.3100417151756988,"score_spread":0.28551691222924563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395075562","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013746329,0.75534815,0.16363874,0.0074196286,0.0057490324,0.00011334662,0.0009717233,0.0013111399,0.06407352],"genre_scores_gemma":[0.016895127,0.660654,0.20566444,0.0040626726,0.009392346,0.00021166583,0.0024782156,0.0005764241,0.100065015],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986527,0.00018751396,0.00010196503,0.0001838624,0.0008220495,0.000051911593],"domain_scores_gemma":[0.99456316,0.0040767845,0.00019191006,0.00044190258,0.00057613367,0.00015010165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020198412,0.0014110995,0.0023757832,0.004549782,0.00044280125,0.0040989756,0.0019823536,0.001144747,0.01582803],"category_scores_gemma":[0.006946946,0.0006919393,0.0009797189,0.009675236,0.0014767747,0.0067283823,0.0018805249,0.003052839,0.015311595],"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":[0.000052151554,0.00008581511,0.00031620642,0.003266896,0.00012972891,0.00008435489,0.00009736895,0.0019086027,0.0010540782,0.07533087,0.1814598,0.7362142],"study_design_scores_gemma":[0.00001885285,0.000044175624,0.00053625274,0.0007956305,0.00007882926,0.00041764477,0.0000658564,0.007056772,0.0008804963,0.21195361,0.77812284,0.000029056308],"about_ca_topic_score_codex":0.000798642,"about_ca_topic_score_gemma":0.0010219121,"teacher_disagreement_score":0.01582803,"about_ca_system_score_codex":0.0008985213,"about_ca_system_score_gemma":0.0015317344,"threshold_uncertainty_score":0.052950084},"labels":[],"label_agreement":null},{"id":"W4395098119","doi":"10.1007/978-981-97-2242-6","title":"Advances in Knowledge Discovery and Data Mining","year":2024,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"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":"China University of Geosciences; National Cheng Kung University; National Taiwan University of Science and Technology; Università di Pisa; Uppsala Universitet; Universidad de Zaragoza; University of Dhaka; University of Illinois at Urbana-Champaign; National Taiwan University; Syddansk Universitet; Hokkaido University; National Tsing Hua University; Shanghai Jiao Tong University; Pontificia Universidade Católica do Paraná; Università degli Studi di Pavia; Shanxi University; Nanjing University of Aeronautics and Astronautics; University of Massachusetts Boston; East China Normal University; Chang Gung University; Chinese Academy of Sciences; University of Science and Technology of China; South Asian University; Nanyang Technological University; Macquarie University; University of Pittsburgh; Massey University; Indian Institute of Technology Delhi; Chang Gung Medical Foundation; National Kaohsiung University of Science and Technology; Université Paris-Est Créteil Val-de-Marne; University of Minnesota; Politecnico di Torino; Swinburne University of Technology; McMaster University; Santa Clara University; Nanjing University; New Mexico State University; University of Texas at Arlington; Deakin University; University of Maryland, Baltimore County; Georgia State University; Arizona State University; Budapesti Műszaki és Gazdaságtudományi Egyetem; Ohio State University","keywords":"Computer science; Knowledge extraction; Data science; Data mining; Information retrieval","score_opus":0.02452480294645317,"score_gpt":0.3100417151756988,"score_spread":0.28551691222924563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395098119","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013746329,0.75534815,0.16363874,0.0074196286,0.0057490324,0.00011334662,0.0009717233,0.0013111399,0.06407352],"genre_scores_gemma":[0.016895127,0.660654,0.20566444,0.0040626726,0.009392346,0.00021166583,0.0024782156,0.0005764241,0.100065015],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986527,0.00018751396,0.00010196503,0.0001838624,0.0008220495,0.000051911593],"domain_scores_gemma":[0.99456316,0.0040767845,0.00019191006,0.00044190258,0.00057613367,0.00015010165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020198412,0.0014110995,0.0023757832,0.004549782,0.00044280125,0.0040989756,0.0019823536,0.001144747,0.01582803],"category_scores_gemma":[0.006946946,0.0006919393,0.0009797189,0.009675236,0.0014767747,0.0067283823,0.0018805249,0.003052839,0.015311595],"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":[0.000052151554,0.00008581511,0.00031620642,0.003266896,0.00012972891,0.00008435489,0.00009736895,0.0019086027,0.0010540782,0.07533087,0.1814598,0.7362142],"study_design_scores_gemma":[0.00001885285,0.000044175624,0.00053625274,0.0007956305,0.00007882926,0.00041764477,0.0000658564,0.007056772,0.0008804963,0.21195361,0.77812284,0.000029056308],"about_ca_topic_score_codex":0.000798642,"about_ca_topic_score_gemma":0.0010219121,"teacher_disagreement_score":0.01582803,"about_ca_system_score_codex":0.0008985213,"about_ca_system_score_gemma":0.0015317344,"threshold_uncertainty_score":0.052950084},"labels":[],"label_agreement":null},{"id":"W4395098215","doi":"10.1007/978-981-97-2253-2","title":"Advances in Knowledge Discovery and Data Mining","year":2024,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"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":"China University of Geosciences; National Cheng Kung University; National Taiwan University of Science and Technology; Università di Pisa; Uppsala Universitet; Universidad de Zaragoza; University of Dhaka; University of Illinois at Urbana-Champaign; National Taiwan University; Syddansk Universitet; Hokkaido University; National Tsing Hua University; Shanghai Jiao Tong University; Pontificia Universidade Católica do Paraná; Università degli Studi di Pavia; Shanxi University; Nanjing University of Aeronautics and Astronautics; University of Massachusetts Boston; East China Normal University; Chang Gung University; Chinese Academy of Sciences; University of Science and Technology of China; South Asian University; Nanyang Technological University; Macquarie University; University of Pittsburgh; Massey University; Indian Institute of Technology Delhi; Chang Gung Medical Foundation; National Kaohsiung University of Science and Technology; Université Paris-Est Créteil Val-de-Marne; University of Minnesota; Politecnico di Torino; Swinburne University of Technology; McMaster University; Santa Clara University; Nanjing University; New Mexico State University; University of Texas at Arlington; Deakin University; University of Maryland, Baltimore County; Georgia State University; Arizona State University; Budapesti Műszaki és Gazdaságtudományi Egyetem; Ohio State University","keywords":"Computer science; Knowledge extraction; Data science; Data mining; Information retrieval","score_opus":0.02452480294645317,"score_gpt":0.3100417151756988,"score_spread":0.28551691222924563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395098215","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013746329,0.75534815,0.16363874,0.0074196286,0.0057490324,0.00011334662,0.0009717233,0.0013111399,0.06407352],"genre_scores_gemma":[0.016895127,0.660654,0.20566444,0.0040626726,0.009392346,0.00021166583,0.0024782156,0.0005764241,0.100065015],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986527,0.00018751396,0.00010196503,0.0001838624,0.0008220495,0.000051911593],"domain_scores_gemma":[0.99456316,0.0040767845,0.00019191006,0.00044190258,0.00057613367,0.00015010165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020198412,0.0014110995,0.0023757832,0.004549782,0.00044280125,0.0040989756,0.0019823536,0.001144747,0.01582803],"category_scores_gemma":[0.006946946,0.0006919393,0.0009797189,0.009675236,0.0014767747,0.0067283823,0.0018805249,0.003052839,0.015311595],"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":[0.000052151554,0.00008581511,0.00031620642,0.003266896,0.00012972891,0.00008435489,0.00009736895,0.0019086027,0.0010540782,0.07533087,0.1814598,0.7362142],"study_design_scores_gemma":[0.00001885285,0.000044175624,0.00053625274,0.0007956305,0.00007882926,0.00041764477,0.0000658564,0.007056772,0.0008804963,0.21195361,0.77812284,0.000029056308],"about_ca_topic_score_codex":0.000798642,"about_ca_topic_score_gemma":0.0010219121,"teacher_disagreement_score":0.01582803,"about_ca_system_score_codex":0.0008985213,"about_ca_system_score_gemma":0.0015317344,"threshold_uncertainty_score":0.052950084},"labels":[],"label_agreement":null},{"id":"W4396910355","doi":"10.1007/978-3-031-54908-3","title":"Linear Algebra in Data Science","year":2024,"lang":"en","type":"book","venue":"Compact textbooks in mathematics","topic":"Data Mining Algorithms and Applications","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":"Mount Royal University","funders":"","keywords":"Linear algebra; Algebra over a field; Computer science; Mathematics; Pure mathematics; Geometry","score_opus":0.08072283189659074,"score_gpt":0.34454866601158446,"score_spread":0.2638258341149937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396910355","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013458316,0.047994677,0.16388644,0.008493273,0.0073477253,0.00010031461,0.0017680855,0.002331318,0.7667324],"genre_scores_gemma":[0.009983942,0.017775744,0.032501906,0.0022509643,0.004142944,0.00013805393,0.0014699649,0.0010488622,0.93068755],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992021,0.0001337391,0.000044233137,0.00011906601,0.0004602184,0.00004064511],"domain_scores_gemma":[0.9989471,0.000503647,0.000046917496,0.00019192761,0.00024387005,0.00006650919],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063004345,0.0012678421,0.0012289201,0.002409383,0.0009220325,0.004716518,0.0010064451,0.0007058807,0.09637865],"category_scores_gemma":[0.0022774478,0.0007934127,0.00070251845,0.006542038,0.0017786345,0.0054573724,0.0017723967,0.003400091,0.067400545],"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":[0.000013053968,0.0000353583,0.00006881783,0.00034640147,0.000014909295,0.000028739732,0.00018054515,0.0007322072,0.0007516544,0.30809486,0.503148,0.18658544],"study_design_scores_gemma":[0.000005547806,0.00001361116,0.00016546751,0.0001284836,0.00000832837,0.00008648386,0.00006226633,0.0014737652,0.00041309022,0.21110322,0.7865275,0.000012138363],"about_ca_topic_score_codex":0.0009539502,"about_ca_topic_score_gemma":0.0018720147,"teacher_disagreement_score":0.09637865,"about_ca_system_score_codex":0.001565706,"about_ca_system_score_gemma":0.0016769703,"threshold_uncertainty_score":0.3224187},"labels":[],"label_agreement":null},{"id":"W4396913608","doi":"10.48550/arxiv.2405.07364","title":"BoQ: A Place is Worth a Bag of Learnable Queries","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fonds de recherche du Québec – Nature et technologies; Nvidia","keywords":"Computer science; Business","score_opus":0.058508315250116676,"score_gpt":0.18940138979297205,"score_spread":0.13089307454285537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396913608","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05270063,0.004480396,0.85221434,0.0023823734,0.0007804937,0.00059519365,0.015097057,0.061444957,0.0103045525],"genre_scores_gemma":[0.40308815,0.0013582053,0.5392965,0.002160145,0.00039134087,0.00045250048,0.03261594,0.0034800605,0.01715716],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998803,0.00014779295,0.000070899856,0.0004923729,0.00034379834,0.00014225977],"domain_scores_gemma":[0.998835,0.00032004347,0.00008311519,0.00045464496,0.00023007787,0.00007718044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012125954,0.0020434873,0.0016560866,0.0014993136,0.00075043266,0.00250872,0.004646285,0.0027690635,0.013978138],"category_scores_gemma":[0.0050725713,0.0006615893,0.0012519319,0.0022311555,0.0010105247,0.008347912,0.004439062,0.0019111178,0.006212357],"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":[0.0011140474,0.00041495133,0.004793222,0.0010180314,0.00024502637,0.00032065075,0.0004009442,0.047886938,0.019740421,0.01913004,0.1528852,0.7520506],"study_design_scores_gemma":[0.00024410675,0.0005608921,0.0026355346,0.000115776056,0.00015535172,0.0007361712,0.0007081201,0.84556454,0.023842882,0.0598455,0.065475,0.000116135],"about_ca_topic_score_codex":0.011435134,"about_ca_topic_score_gemma":0.016692827,"teacher_disagreement_score":0.013978138,"about_ca_system_score_codex":0.0011601874,"about_ca_system_score_gemma":0.0012744034,"threshold_uncertainty_score":0.046761453},"labels":[],"label_agreement":null},{"id":"W4399212572","doi":"10.28924/2291-8639-22-2024-95","title":"A New Mood’s Median Test for Imprecise Data","year":2024,"lang":"en","type":"article","venue":"International Journal of Analysis and Applications","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Test (biology); Mood; Statistics; Psychology; Social psychology","score_opus":0.024253573533671552,"score_gpt":0.33911849310494246,"score_spread":0.31486491957127094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399212572","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04719689,0.000506451,0.94500256,0.00044293609,0.00024149829,0.00022442616,0.00077694753,0.0005830189,0.0050252904],"genre_scores_gemma":[0.6917623,0.00044483755,0.30253464,0.0005555829,0.00051896344,0.00073568523,0.0016102224,0.00013856523,0.0016991905],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9856403,0.0053830603,0.0012502371,0.0027347591,0.00446822,0.00052338664],"domain_scores_gemma":[0.95005924,0.03691188,0.0037607453,0.0027524477,0.005634881,0.0008807076],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01157469,0.0008899982,0.0019462717,0.00504055,0.0010640809,0.003489075,0.0028578993,0.002347027,0.004973092],"category_scores_gemma":[0.082268655,0.00037839488,0.0018982884,0.0033200998,0.0024634593,0.005584237,0.0027876506,0.002037245,0.00094137114],"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":[0.002486831,0.0005511467,0.06584279,0.0012730715,0.0013828941,0.0014774199,0.00090397574,0.084916495,0.015745997,0.20390438,0.011014979,0.6105001],"study_design_scores_gemma":[0.00030765048,0.0022958284,0.028102214,0.00029859427,0.00032590807,0.0019818782,0.00082829973,0.7167152,0.012055656,0.22102413,0.015664985,0.00039970162],"about_ca_topic_score_codex":0.00064758677,"about_ca_topic_score_gemma":0.00041471364,"teacher_disagreement_score":0.01157469,"about_ca_system_score_codex":0.0009841007,"about_ca_system_score_gemma":0.0016961423,"threshold_uncertainty_score":0.061213493},"labels":[],"label_agreement":null},{"id":"W4400657330","doi":"10.3329/dujase.v8i1.72984","title":"Mining Weighted Patterns from Time Series Databases Based on Sliding Window","year":2024,"lang":"en","type":"article","venue":"Dhaka University Journal of Applied Science and Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Sliding window protocol; Trie; Computer science; Data mining; Suffix; Novelty; Suffix tree; Variety (cybernetics); Series (stratigraphy); Tree (set theory); Time series; Window (computing); String (physics); Data structure; Pattern recognition (psychology); Artificial intelligence; Machine learning; Mathematics","score_opus":0.008557701322931623,"score_gpt":0.18575942851591148,"score_spread":0.17720172719297986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400657330","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16597012,0.0014303152,0.8265772,0.00024246237,0.000097440374,0.0002729168,0.001910726,0.0025737523,0.00092507596],"genre_scores_gemma":[0.5433122,0.0010517725,0.44973364,0.00008700611,0.000118246855,0.00038219287,0.004463173,0.0001274881,0.00072420953],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99770147,0.00022728667,0.0004967954,0.00071082485,0.000719364,0.00014433393],"domain_scores_gemma":[0.99580526,0.0016710627,0.00087356206,0.000649422,0.0008087323,0.00019186006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015005213,0.0011231713,0.0014666385,0.0068412535,0.00063851435,0.0017433398,0.0016316009,0.0007160075,0.0011174994],"category_scores_gemma":[0.009065059,0.00056046096,0.0014460876,0.008070301,0.00039003268,0.0033410743,0.0013593187,0.0009561053,0.00074101915],"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":[0.00086533854,0.00041341753,0.06009408,0.0006809616,0.000754107,0.0021147972,0.0008465362,0.07114012,0.02884004,0.0080552995,0.0053295367,0.8208657],"study_design_scores_gemma":[0.000043525364,0.00029493414,0.009199025,0.0000672827,0.00016859164,0.001089417,0.00044916154,0.9594967,0.0101353275,0.015361339,0.0036479386,0.00004673747],"about_ca_topic_score_codex":0.0020962588,"about_ca_topic_score_gemma":0.002491924,"teacher_disagreement_score":0.0068412535,"about_ca_system_score_codex":0.0003116478,"about_ca_system_score_gemma":0.0007938032,"threshold_uncertainty_score":0.007935584},"labels":[],"label_agreement":null},{"id":"W4400967584","doi":"","title":"Analyse non supervisée de corpus de documents pour la recherche de sujets : une nouvelle approche basée sur le clustering et la maximisation des traits","year":2024,"lang":"fr","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Centre National de la Recherche Scientifique; Université du Québec à Montréal","keywords":"Computer science; Cluster analysis; Humanities; Artificial intelligence; Philosophy","score_opus":0.13717682190591748,"score_gpt":0.3074384311851966,"score_spread":0.1702616092792791,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400967584","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.073207654,0.0026745196,0.9168451,0.0005900705,0.00018203215,0.00025346738,0.0007973287,0.003434839,0.0020150095],"genre_scores_gemma":[0.37568414,0.0014832371,0.59710425,0.00033858576,0.000454796,0.000521856,0.0038017575,0.0010705416,0.019540826],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963425,0.0010331122,0.00020972059,0.0010366557,0.0011717897,0.00020619447],"domain_scores_gemma":[0.99255836,0.0038646164,0.0003607337,0.00089714595,0.0021289545,0.00019014336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036779619,0.0016722224,0.0019672802,0.0033642661,0.00092411827,0.0024007782,0.0019003049,0.0023600715,0.002253144],"category_scores_gemma":[0.009396832,0.00072839984,0.0017339529,0.0016817789,0.0009214674,0.0017116007,0.0010782137,0.0015650176,0.002024337],"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":[0.0015649218,0.00037640164,0.0062455307,0.00070528145,0.0006208395,0.0004492528,0.0007465372,0.043752164,0.17590451,0.004460684,0.006572551,0.75860137],"study_design_scores_gemma":[0.00011942385,0.00055844634,0.014496929,0.0001134625,0.00040607186,0.0008737956,0.00044775533,0.8709767,0.08870826,0.008878082,0.014319066,0.0001020536],"about_ca_topic_score_codex":0.009859408,"about_ca_topic_score_gemma":0.012193191,"teacher_disagreement_score":0.009859408,"about_ca_system_score_codex":0.0009601022,"about_ca_system_score_gemma":0.0018366509,"threshold_uncertainty_score":0.019604027},"labels":[],"label_agreement":null},{"id":"W4401114488","doi":"10.1109/ecti-con60892.2024.10595036","title":"A Graph-based Data Mining Approach for Template Recognition using Large Log Datasets in Software Systems","year":2024,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Data mining; Software; Graph; Pattern recognition (psychology); Artificial intelligence; Theoretical computer science; Operating system","score_opus":0.14915702477570925,"score_gpt":0.33783504821614785,"score_spread":0.1886780234404386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401114488","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08307741,0.0009415277,0.863812,0.00078531087,0.00008006939,0.0007184986,0.011204338,0.037817255,0.00156364],"genre_scores_gemma":[0.2436624,0.0004427263,0.73688996,0.00017983459,0.00003326488,0.00050347246,0.016909227,0.0004947223,0.00088440656],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986524,0.00022248045,0.00018206061,0.00047457265,0.00039615386,0.00007232602],"domain_scores_gemma":[0.99648285,0.0017332894,0.00040918175,0.00067906664,0.00059521006,0.0001002983],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012263731,0.001225068,0.00082893495,0.008480354,0.0008632755,0.0015817982,0.0017890986,0.001041135,0.00062431494],"category_scores_gemma":[0.006602761,0.0004971642,0.0013565937,0.006155007,0.00044788758,0.0023283872,0.00096183404,0.0012295224,0.00085259957],"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":[0.0003196128,0.0008466477,0.03392262,0.0008791021,0.0003588062,0.0008451328,0.00051697815,0.0770491,0.025700638,0.006130266,0.023765555,0.8296656],"study_design_scores_gemma":[0.000030738316,0.000121080644,0.008018994,0.0000515468,0.00007050801,0.00047960994,0.00029839185,0.94791734,0.017434638,0.015993701,0.009527491,0.00005593218],"about_ca_topic_score_codex":0.01052407,"about_ca_topic_score_gemma":0.021354867,"teacher_disagreement_score":0.01052407,"about_ca_system_score_codex":0.00081074267,"about_ca_system_score_gemma":0.0015933355,"threshold_uncertainty_score":0.020925641},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018884774,0.00046340656,0.9748174,0.00021228321,0.00006124932,0.0001912493,0.0005337298,0.0038577442,0.0009781953],"genre_scores_gemma":[0.15064165,0.00026301248,0.84436506,0.00011858634,0.00006392386,0.00019286755,0.0012725133,0.00016590235,0.00291656],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985738,0.00019915639,0.00014805862,0.00023485947,0.00071441306,0.00012971014],"domain_scores_gemma":[0.9971834,0.0013367911,0.00015931402,0.00062719325,0.00060416525,0.000089240246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010775052,0.00064324436,0.0010946759,0.0027223572,0.00058916333,0.001618055,0.0023859015,0.0006824392,0.002380143],"category_scores_gemma":[0.0065494273,0.0004804291,0.0009732841,0.0030212426,0.00049608655,0.0022856873,0.0020098477,0.0012516559,0.0012084696],"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":[0.0003474447,0.00022287242,0.0029917364,0.00023261867,0.000089614936,0.00041055444,0.00018825497,0.021596223,0.012542823,0.012645695,0.0064409296,0.9422913],"study_design_scores_gemma":[0.000064218235,0.00012950363,0.0012369042,0.000032525724,0.00006688264,0.00068183674,0.000114333314,0.94638443,0.011723514,0.032176327,0.0073551866,0.000034208133],"about_ca_topic_score_codex":0.0028157134,"about_ca_topic_score_gemma":0.006929664,"teacher_disagreement_score":0.0028157134,"about_ca_system_score_codex":0.00042903423,"about_ca_system_score_gemma":0.0016692748,"threshold_uncertainty_score":0.007962346},"labels":[],"label_agreement":null},{"id":"W4401879325","doi":"10.1109/compsac61105.2024.00277","title":"Application of a Novel Fuzzy Pattern Mining Algorithm for Sequence Data","year":2024,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thompson Rivers University; University of Manitoba","funders":"","keywords":"Computer science; Sequence (biology); Sequential Pattern Mining; Data mining; Fuzzy logic; Algorithm; Artificial intelligence; Pattern recognition (psychology)","score_opus":0.08891548007989457,"score_gpt":0.3423208725250949,"score_spread":0.25340539244520033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401879325","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007016825,0.000045941557,0.9922044,0.000079542435,0.000017276852,0.00004436625,0.00006251598,0.00023072123,0.0002983216],"genre_scores_gemma":[0.09869485,0.00008335165,0.8998844,0.00007294549,0.000025508585,0.00013341004,0.0002400048,0.000028104116,0.0008374647],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99922514,0.000088585206,0.00008276719,0.0003041081,0.00025464687,0.00004465343],"domain_scores_gemma":[0.99846375,0.00081889465,0.000143838,0.00013048825,0.00040335438,0.000039686605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010858125,0.0004771315,0.00067227276,0.0014466207,0.00055748515,0.0007949463,0.001251306,0.000838203,0.0013685146],"category_scores_gemma":[0.004849911,0.0003085239,0.0008891649,0.0015207516,0.00040074898,0.0010826064,0.00069481024,0.00097549544,0.00041105208],"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":[0.00017881113,0.00012491686,0.004408421,0.00016159278,0.00013181324,0.00030491556,0.00020154436,0.22980432,0.012510099,0.031156085,0.0026450048,0.71837246],"study_design_scores_gemma":[0.000010713713,0.000025296857,0.0002814316,0.000007093999,0.000009776936,0.0001332379,0.0000122881365,0.98656696,0.0025645613,0.009078284,0.0013027203,0.00000759661],"about_ca_topic_score_codex":0.0041318564,"about_ca_topic_score_gemma":0.0035674823,"teacher_disagreement_score":0.0041318564,"about_ca_system_score_codex":0.00062639447,"about_ca_system_score_gemma":0.0012728579,"threshold_uncertainty_score":0.008215606},"labels":[],"label_agreement":null},{"id":"W4401927852","doi":"10.30998/faktorexacta.v17i2.20625","title":"Application of Data Mining to Prediction of New Students' Interested Departements With an Approach Naive Bayes Algorithm","year":2024,"lang":"en","type":"article","venue":"Faktor Exacta","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"ASTER","funders":"","keywords":"Naive Bayes classifier; Computer science; Bayes' theorem; Machine learning; Data mining; Artificial intelligence; Algorithm; Bayesian probability; Support vector machine","score_opus":0.055636619993318204,"score_gpt":0.33660520469854177,"score_spread":0.28096858470522357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401927852","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055434003,0.0010812462,0.9362732,0.0010892298,0.00023821583,0.00067599193,0.00077357277,0.0010022988,0.0034322958],"genre_scores_gemma":[0.36598024,0.0007883766,0.629719,0.0003477643,0.00013711576,0.00055134535,0.0010310914,0.000044661465,0.0014004628],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9935502,0.0024748899,0.0007945372,0.0009767953,0.0020035887,0.00020005346],"domain_scores_gemma":[0.9880998,0.0082805855,0.00071335473,0.0004989129,0.002253344,0.00015398649],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005862673,0.0011144583,0.0013718819,0.0045858747,0.0010930529,0.0023808368,0.0013388718,0.0012862184,0.0011544934],"category_scores_gemma":[0.0191739,0.00065832306,0.0017872569,0.0035977985,0.0005567828,0.0017772594,0.0006351695,0.0016016092,0.0005479638],"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":[0.00039327503,0.0007326717,0.06338473,0.00085272157,0.00077388325,0.00038299532,0.0008471287,0.23342189,0.003897948,0.013819481,0.0064596115,0.6750336],"study_design_scores_gemma":[0.000059868355,0.00022357274,0.0067159934,0.00022543823,0.00017406483,0.00021963018,0.00027191098,0.959164,0.003069276,0.023424024,0.0063606515,0.000091459486],"about_ca_topic_score_codex":0.012918855,"about_ca_topic_score_gemma":0.009750822,"teacher_disagreement_score":0.012918855,"about_ca_system_score_codex":0.0012959334,"about_ca_system_score_gemma":0.002442549,"threshold_uncertainty_score":0.031005144},"labels":[],"label_agreement":null},{"id":"W4402035557","doi":"10.32920/26882485","title":"Graph and Semantic Analysis Approach for Template Recognition in Large Scale Log Data","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Graph; Scale (ratio); Natural language processing; Artificial intelligence; Data mining; Pattern recognition (psychology); Information retrieval; Theoretical computer science; Cartography","score_opus":0.07290353216277942,"score_gpt":0.31520915932004273,"score_spread":0.2423056271572633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402035557","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008264501,0.00009126514,0.9860299,0.00018414996,0.000022871534,0.00009018991,0.00075444474,0.003901696,0.00066105125],"genre_scores_gemma":[0.123820335,0.00021374032,0.86947554,0.00014513919,0.000040325995,0.00020523377,0.0037201156,0.000534753,0.0018448004],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988858,0.00019758423,0.00009979677,0.0003096046,0.0004316933,0.000075560936],"domain_scores_gemma":[0.9968046,0.0014503411,0.00034412503,0.00072831404,0.0005762746,0.00009625979],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094614667,0.0007658266,0.0006535648,0.0064995904,0.000891633,0.001677982,0.0014892876,0.0010461275,0.0020219455],"category_scores_gemma":[0.004807884,0.0004015354,0.001525657,0.004997884,0.0009556527,0.0027739014,0.0011759397,0.0013633864,0.001103394],"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":[0.00022562109,0.0005818836,0.010580069,0.00039840883,0.00018871205,0.00083013676,0.0005628188,0.124927066,0.030349854,0.073132545,0.014720462,0.74350244],"study_design_scores_gemma":[0.000011759748,0.00003552779,0.0013845228,0.000021371645,0.000027041577,0.00017938256,0.00015993569,0.92066896,0.008374068,0.0625547,0.0065550185,0.000027644492],"about_ca_topic_score_codex":0.0081429435,"about_ca_topic_score_gemma":0.014315733,"teacher_disagreement_score":0.0081429435,"about_ca_system_score_codex":0.0010367256,"about_ca_system_score_gemma":0.0018938405,"threshold_uncertainty_score":0.016191125},"labels":[],"label_agreement":null},{"id":"W4402035625","doi":"10.32920/26882485.v1","title":"Graph and Semantic Analysis Approach for Template Recognition in Large Scale Log Data","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Graph; Scale (ratio); Natural language processing; Information retrieval; Artificial intelligence; Data mining; Theoretical computer science; Geography; Cartography","score_opus":0.07290353216277942,"score_gpt":0.31520915932004273,"score_spread":0.2423056271572633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402035625","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008264501,0.00009126514,0.9860299,0.00018414996,0.000022871534,0.00009018991,0.00075444474,0.003901696,0.00066105125],"genre_scores_gemma":[0.123820335,0.00021374032,0.86947554,0.00014513919,0.000040325995,0.00020523377,0.0037201156,0.000534753,0.0018448004],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988858,0.00019758423,0.00009979677,0.0003096046,0.0004316933,0.000075560936],"domain_scores_gemma":[0.9968046,0.0014503411,0.00034412503,0.00072831404,0.0005762746,0.00009625979],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094614667,0.0007658266,0.0006535648,0.0064995904,0.000891633,0.001677982,0.0014892876,0.0010461275,0.0020219455],"category_scores_gemma":[0.004807884,0.0004015354,0.001525657,0.004997884,0.0009556527,0.0027739014,0.0011759397,0.0013633864,0.001103394],"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":[0.00022562109,0.0005818836,0.010580069,0.00039840883,0.00018871205,0.00083013676,0.0005628188,0.124927066,0.030349854,0.073132545,0.014720462,0.74350244],"study_design_scores_gemma":[0.000011759748,0.00003552779,0.0013845228,0.000021371645,0.000027041577,0.00017938256,0.00015993569,0.92066896,0.008374068,0.0625547,0.0065550185,0.000027644492],"about_ca_topic_score_codex":0.0081429435,"about_ca_topic_score_gemma":0.014315733,"teacher_disagreement_score":0.0081429435,"about_ca_system_score_codex":0.0010367256,"about_ca_system_score_gemma":0.0018938405,"threshold_uncertainty_score":0.016191125},"labels":[],"label_agreement":null},{"id":"W4402480488","doi":"10.1007/978-3-031-63402-4_36","title":"Candidate Performance Prediction—A Detailed Analysis Using Predictive Analytics Workbench","year":2024,"lang":"en","type":"book-chapter","venue":"Studies in systems, decision and control","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":"Horizon College and Seminary","funders":"","keywords":"Workbench; Analytics; Computer science; Predictive analytics; Data mining; Data science; Visualization","score_opus":0.041095889834807275,"score_gpt":0.3064838129333459,"score_spread":0.26538792309853865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402480488","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0948181,0.001304209,0.87048835,0.00064518926,0.00013654027,0.00032488658,0.003415011,0.0044876724,0.024380047],"genre_scores_gemma":[0.6407526,0.0013686741,0.32670423,0.00014559702,0.00017222979,0.00041606996,0.006087941,0.00074957154,0.0236031],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991303,0.00012329505,0.000034798235,0.00013709598,0.0005032645,0.00007131634],"domain_scores_gemma":[0.997897,0.0012702015,0.00009470413,0.000266187,0.00042454214,0.000047286794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011829394,0.0014584569,0.0009838978,0.0025010162,0.0006319724,0.0030448546,0.0014639901,0.0006345251,0.010746127],"category_scores_gemma":[0.0044897012,0.000394826,0.0009923952,0.0025483258,0.00037897282,0.0031476484,0.00078659446,0.0011222177,0.0032748093],"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":[0.00046425514,0.0003920352,0.017085204,0.00032600274,0.00012834085,0.0005265652,0.00024256659,0.24606267,0.012116757,0.061980512,0.018843623,0.6418314],"study_design_scores_gemma":[0.000010903367,0.00017911165,0.003452932,0.00005609637,0.000048025395,0.000108775734,0.00012574552,0.9587661,0.008071798,0.023104243,0.0060357903,0.00004043053],"about_ca_topic_score_codex":0.003266482,"about_ca_topic_score_gemma":0.0024876487,"teacher_disagreement_score":0.010746127,"about_ca_system_score_codex":0.00067061436,"about_ca_system_score_gemma":0.0008322356,"threshold_uncertainty_score":0.03594935},"labels":[],"label_agreement":null},{"id":"W4402569628","doi":"10.1109/access.2024.3462635","title":"Knowledge Graph Generation and Application for Unstructured Data Using Data Processing Pipeline","year":2024,"lang":"en","type":"article","venue":"IEEE Access","topic":"Data Mining Algorithms and Applications","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":"Cistel Technology (Canada); Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Unstructured data; Pipeline (software); Graph; Data modeling; Graph database; Data mining; Big data; Database; Theoretical computer science; Programming language","score_opus":0.20825656200637097,"score_gpt":0.42761065684653343,"score_spread":0.21935409484016247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402569628","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03833137,0.00028210753,0.90275246,0.0008410457,0.00014966153,0.0011626049,0.009782233,0.04260692,0.0040916065],"genre_scores_gemma":[0.091437265,0.00021512675,0.88872266,0.00013709204,0.000022990924,0.00049875944,0.01682623,0.0006538668,0.0014860275],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998544,0.00033813465,0.00015546831,0.00045308605,0.00043799923,0.000071363385],"domain_scores_gemma":[0.99247414,0.0041944273,0.0003642182,0.001453651,0.001335088,0.00017851996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023190482,0.0010490282,0.00057174003,0.00610941,0.00088844093,0.0018212342,0.001538785,0.0008973693,0.0038011977],"category_scores_gemma":[0.013161963,0.00052847737,0.0013385944,0.0049875933,0.0005922452,0.002947785,0.0025418568,0.0015377707,0.0015434803],"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":[0.00050132116,0.0005469506,0.005291405,0.0012227114,0.00018929147,0.0011633368,0.002283902,0.052552506,0.027223092,0.017547283,0.034242917,0.8572352],"study_design_scores_gemma":[0.00016512742,0.0002832309,0.0035600492,0.00014824458,0.0001364057,0.00054797874,0.0015547498,0.8031346,0.061438996,0.059412707,0.0694935,0.00012435406],"about_ca_topic_score_codex":0.0074694194,"about_ca_topic_score_gemma":0.009282236,"teacher_disagreement_score":0.0074694194,"about_ca_system_score_codex":0.0010149707,"about_ca_system_score_gemma":0.0018997623,"threshold_uncertainty_score":0.014851868},"labels":[],"label_agreement":null},{"id":"W4402670184","doi":"10.18653/v1/2024.findings-acl.627","title":"LLM Performance Predictors are good initializers for Architecture Search","year":2024,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":8,"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":"Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Architecture; Computer science; Computer architecture","score_opus":0.02301374538322617,"score_gpt":0.2768504187826188,"score_spread":0.25383667339939264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402670184","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15462962,0.0025766375,0.76699424,0.0022346114,0.0006217266,0.00038791882,0.002998742,0.04810709,0.02144951],"genre_scores_gemma":[0.6475566,0.00043539965,0.3327845,0.0006538084,0.00028705975,0.00059643295,0.0047133253,0.0029335814,0.010039279],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99819547,0.00071383704,0.000118365555,0.00029356504,0.00046786547,0.00021080286],"domain_scores_gemma":[0.9927912,0.003490579,0.0004346609,0.0013720043,0.0016407279,0.00027081114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024843405,0.0015998482,0.0010039556,0.0028104912,0.0008934678,0.001772509,0.0015033567,0.0013376647,0.0094592],"category_scores_gemma":[0.023877745,0.00084193604,0.00064582715,0.0014786068,0.00047989108,0.0035594804,0.0013931526,0.0029195843,0.00744599],"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":[0.0011999432,0.00046709395,0.02794594,0.00036839602,0.00013900726,0.00013929816,0.0001871268,0.12122993,0.008819235,0.00995682,0.05106863,0.77847856],"study_design_scores_gemma":[0.00010187819,0.00038742076,0.0033964177,0.0001601675,0.000084969615,0.00009551003,0.00011095907,0.9468549,0.01839817,0.020406365,0.009951791,0.00005138444],"about_ca_topic_score_codex":0.0020815083,"about_ca_topic_score_gemma":0.004736814,"teacher_disagreement_score":0.0094592,"about_ca_system_score_codex":0.0011357529,"about_ca_system_score_gemma":0.0015787114,"threshold_uncertainty_score":0.031644166},"labels":[],"label_agreement":null},{"id":"W4403661739","doi":"10.48550/arxiv.2409.08440","title":"A Simple 4-Approximation Algorithm for Maximum Agreement Forests on Multiple Unrooted Binary Trees","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Simple (philosophy); Binary number; Mathematics; Binary tree; Statistical physics; Applied mathematics; Combinatorics; Algorithm; Physics; Forestry; Geography; Arithmetic","score_opus":0.06506725166700413,"score_gpt":0.2217817075597279,"score_spread":0.15671445589272376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403661739","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014440953,0.00027634786,0.97669107,0.0004710715,0.00009260308,0.00022782713,0.00034790876,0.0025133553,0.0049388846],"genre_scores_gemma":[0.09000721,0.0001159395,0.9060182,0.00021432493,0.00006256775,0.00030631112,0.0008946751,0.0002965536,0.0020841176],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99809545,0.00034060908,0.000119048986,0.00044532793,0.00061944046,0.00038008761],"domain_scores_gemma":[0.9976351,0.0011184799,0.00020053145,0.0005910938,0.00031528142,0.00013955949],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013363702,0.0012692714,0.0014097871,0.0011594683,0.0011524755,0.0020147688,0.0025387977,0.0015804463,0.011342384],"category_scores_gemma":[0.0057209954,0.00084268453,0.0016533029,0.002388351,0.00079891225,0.0039105713,0.0029817754,0.0039449832,0.0036036065],"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":[0.00085264014,0.0006223564,0.0015377894,0.0006466643,0.00013477242,0.00027582576,0.0005406585,0.27510008,0.017707357,0.08971651,0.025654936,0.5872105],"study_design_scores_gemma":[0.00026985092,0.0001365402,0.00028163404,0.00006485557,0.0000462384,0.00022131931,0.00017872904,0.8455343,0.006650569,0.13574138,0.010839592,0.00003496948],"about_ca_topic_score_codex":0.002241345,"about_ca_topic_score_gemma":0.00379654,"teacher_disagreement_score":0.011342384,"about_ca_system_score_codex":0.001670721,"about_ca_system_score_gemma":0.0026218875,"threshold_uncertainty_score":0.03794402},"labels":[],"label_agreement":null},{"id":"W4404524972","doi":"10.1007/978-3-031-77731-8_5","title":"Association Rules Mining with Auto-encoders","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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":"Université Laval","funders":"","keywords":"Computer science; Association rule learning; Association (psychology); Data mining; Encoder; Artificial intelligence; Operating system","score_opus":0.013171627316337012,"score_gpt":0.23903915366069597,"score_spread":0.22586752634435897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404524972","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01961875,0.0021118324,0.96452177,0.00030219488,0.00024504203,0.00018194648,0.001872938,0.008878965,0.0022666561],"genre_scores_gemma":[0.23525055,0.0013005725,0.74906313,0.0003633263,0.00024316023,0.00032002857,0.0069083534,0.00039715134,0.006153782],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976222,0.0005932606,0.0002809614,0.0007424331,0.0006317775,0.00012952612],"domain_scores_gemma":[0.9930692,0.004452509,0.00024718934,0.0011581307,0.00097114936,0.00010190758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028969285,0.0009417928,0.0015516719,0.002885904,0.00056101574,0.0018661363,0.0020410537,0.0010478502,0.005040945],"category_scores_gemma":[0.009455421,0.0010061465,0.0017329166,0.0029135258,0.00046468232,0.0025465628,0.0016467449,0.0017584515,0.004306287],"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":[0.00040548263,0.00024512512,0.0023079822,0.00027785188,0.0002844393,0.00034594862,0.000077141165,0.026544377,0.00493286,0.0055494676,0.008985111,0.9500443],"study_design_scores_gemma":[0.00007587331,0.00016439117,0.0014585559,0.00013452861,0.00025289317,0.00088302745,0.000060913782,0.94637465,0.012805943,0.029824294,0.007913826,0.00005114654],"about_ca_topic_score_codex":0.0027525038,"about_ca_topic_score_gemma":0.0040674075,"teacher_disagreement_score":0.005040945,"about_ca_system_score_codex":0.00046910884,"about_ca_system_score_gemma":0.0013224517,"threshold_uncertainty_score":0.016863644},"labels":[],"label_agreement":null},{"id":"W4404968319","doi":"10.1007/978-3-031-78093-6_5","title":"Mining Historical Multi-behavior Sequential Patterns for e-Commerce Recommendation","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms 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 Windsor","funders":"","keywords":"Computer science; E-commerce; Recommender system; World Wide Web; Data mining; Information retrieval","score_opus":0.05755073016334569,"score_gpt":0.3100129681990633,"score_spread":0.25246223803571766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404968319","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6475495,0.008405517,0.30867973,0.0011738953,0.0005386494,0.0004473405,0.020409724,0.0033642226,0.009431371],"genre_scores_gemma":[0.85490525,0.0020169567,0.11507838,0.00016522189,0.00027628615,0.000193229,0.018280255,0.00012535314,0.008959093],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99950314,0.0000484236,0.00006407919,0.0001514688,0.00017687635,0.00005608281],"domain_scores_gemma":[0.99901474,0.0003663813,0.00016331398,0.00012823247,0.0002377968,0.0000895633],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035490398,0.0007426918,0.0007215896,0.00541977,0.00052119617,0.00084000686,0.0008662521,0.0007043479,0.002886972],"category_scores_gemma":[0.0021156147,0.00030989913,0.00093079614,0.0059148027,0.00018699585,0.0012991948,0.00038986653,0.0006645287,0.0020552913],"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":[0.0007724976,0.0009878031,0.20048708,0.00062192103,0.00070075126,0.00139314,0.00021762779,0.021202663,0.014375384,0.0037526602,0.023216242,0.73227227],"study_design_scores_gemma":[0.000070002,0.0005524333,0.11848032,0.0001940634,0.00061662984,0.0030677237,0.00049070653,0.8276992,0.009749735,0.018890956,0.020107526,0.000080706704],"about_ca_topic_score_codex":0.006553068,"about_ca_topic_score_gemma":0.015793905,"teacher_disagreement_score":0.006553068,"about_ca_system_score_codex":0.0003744478,"about_ca_system_score_gemma":0.0005370503,"threshold_uncertainty_score":0.013029814},"labels":[],"label_agreement":null},{"id":"W4405130376","doi":"10.2139/ssrn.5037738","title":"Unleashing the benefits of SparkContext for Big Data","year":2024,"lang":"en","type":"article","venue":"SSRN Electronic Journal","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":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Big data; Data science; Computer science; Business; Data mining","score_opus":0.06117778190044694,"score_gpt":0.29192676309271753,"score_spread":0.2307489811922706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405130376","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.108703725,0.033051163,0.43200916,0.15520625,0.025117401,0.000903162,0.0074900114,0.15198441,0.08553466],"genre_scores_gemma":[0.50557476,0.011260098,0.3677785,0.045009542,0.0106505025,0.0006950296,0.01304518,0.024537409,0.021448966],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9690048,0.007665107,0.0018740474,0.0033266188,0.015156519,0.0029729223],"domain_scores_gemma":[0.8856347,0.03883471,0.0019188027,0.054887574,0.010972838,0.007751378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022450544,0.0018764891,0.002636325,0.0020777558,0.0036480972,0.009939365,0.008543951,0.003661389,0.009323978],"category_scores_gemma":[0.09778231,0.002137134,0.0025744324,0.004956934,0.006242197,0.031346872,0.017936291,0.011167748,0.008960784],"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":[0.0048739268,0.0004867189,0.01033758,0.0017351412,0.0004355011,0.0006478414,0.0017793643,0.0037939432,0.011281108,0.19211207,0.496415,0.27610183],"study_design_scores_gemma":[0.00070794154,0.00053405546,0.003082895,0.0007176123,0.0003422438,0.0011323786,0.0012569218,0.050777443,0.014445292,0.48378336,0.44287345,0.00034637548],"about_ca_topic_score_codex":0.0048816004,"about_ca_topic_score_gemma":0.00814121,"teacher_disagreement_score":0.022450544,"about_ca_system_score_codex":0.0016105168,"about_ca_system_score_gemma":0.009657296,"threshold_uncertainty_score":0.11873126},"labels":[],"label_agreement":null},{"id":"W4405387288","doi":"10.1145/3698322.3698338","title":"An exploration of pattern mining with ChatGPT","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Geology; Mining engineering","score_opus":0.051500898618042426,"score_gpt":0.3027845480752028,"score_spread":0.25128364945716036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405387288","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021868045,0.00053301564,0.96907413,0.0025948929,0.000045839417,0.00017254008,0.00058620283,0.001985145,0.003140162],"genre_scores_gemma":[0.16633528,0.00046108203,0.82907414,0.00054354634,0.000064885135,0.00034982368,0.0011231655,0.00037122835,0.0016768274],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99082583,0.005691087,0.0004323617,0.0010942486,0.0017575916,0.00019893816],"domain_scores_gemma":[0.964351,0.028863985,0.0011609135,0.0038023528,0.0013492613,0.0004724501],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0091018975,0.0009830887,0.00093151035,0.004244224,0.0013992884,0.0041211043,0.0029179552,0.0012930798,0.0028619326],"category_scores_gemma":[0.04104067,0.00078595005,0.0017907514,0.0049296324,0.003322406,0.010492685,0.005293736,0.0023374532,0.00084881973],"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":[0.0006446138,0.0004370015,0.020565825,0.0024497123,0.00037158022,0.0041443324,0.022949925,0.037668735,0.010782901,0.3480735,0.017220352,0.5346915],"study_design_scores_gemma":[0.00008518039,0.0003243639,0.0030831664,0.00044557717,0.000075564734,0.002956351,0.004984874,0.42571065,0.009872836,0.47920516,0.07315936,0.000096913296],"about_ca_topic_score_codex":0.0017098173,"about_ca_topic_score_gemma":0.0028027827,"teacher_disagreement_score":0.0091018975,"about_ca_system_score_codex":0.001200408,"about_ca_system_score_gemma":0.0015310228,"threshold_uncertainty_score":0.048135996},"labels":[],"label_agreement":null},{"id":"W4405657255","doi":"10.18280/ria.380601","title":"Analysis of the MapReduce Performance in Hadoop","year":2024,"lang":"fr","type":"article","venue":"Revue d intelligence artificielle","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Database; Operating system; Parallel computing","score_opus":0.054954098046545725,"score_gpt":0.2952621955024741,"score_spread":0.2403080974559284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405657255","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9850294,0.0003820495,0.0058866423,0.00020779477,0.000048297443,0.000046237357,0.000833007,0.00091031916,0.006656374],"genre_scores_gemma":[0.9972771,0.00009081028,0.001397143,0.000015444763,0.000012815397,0.000014648406,0.0006466398,0.000055571225,0.0004898824],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99847144,0.00018979158,0.00006658017,0.00030042237,0.0006191622,0.00035267582],"domain_scores_gemma":[0.99586356,0.001999644,0.00018763835,0.00033186172,0.0013255164,0.00029182364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012564606,0.00054567127,0.00048453073,0.00116899,0.0007542439,0.0008422935,0.00083375094,0.00043443625,0.0009915106],"category_scores_gemma":[0.004857178,0.00029863103,0.00044589626,0.0018334368,0.0005578814,0.00092038634,0.00033037126,0.000798464,0.00046253082],"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":[0.003965407,0.0014887042,0.111929655,0.0007770063,0.00044958421,0.0010706156,0.0012822037,0.6777524,0.092142336,0.008950162,0.017034816,0.08315716],"study_design_scores_gemma":[0.000056815672,0.000950663,0.12220771,0.0000315986,0.00006611823,0.00038318173,0.0006772127,0.83204323,0.037538715,0.0024970078,0.0034569863,0.000090943526],"about_ca_topic_score_codex":0.0114079015,"about_ca_topic_score_gemma":0.00494501,"teacher_disagreement_score":0.0114079015,"about_ca_system_score_codex":0.0012354896,"about_ca_system_score_gemma":0.0011374191,"threshold_uncertainty_score":0.022683024},"labels":[],"label_agreement":null},{"id":"W4405727093","doi":"10.3233/faia241407","title":"An Efficient Approach for Mining Temporal Fuzzy High-Utility Itemsets","year":2024,"lang":"en","type":"book-chapter","venue":"Frontiers in artificial intelligence and applications","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; University of Dhaka","keywords":"Data mining; Computer science; Pruning; Fuzzy logic; Overhead (engineering); Field (mathematics); Property (philosophy); Database transaction; Artificial intelligence; Machine learning; Database; Mathematics","score_opus":0.04623024611822934,"score_gpt":0.29043752616522095,"score_spread":0.2442072800469916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405727093","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016746748,0.0010509116,0.97851413,0.0001461551,0.000093864706,0.00029835833,0.0007796157,0.0010146563,0.0013556019],"genre_scores_gemma":[0.10083077,0.000649612,0.8922304,0.00012740958,0.00008153218,0.00031851986,0.0026700122,0.00006716812,0.0030245855],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992287,0.00009300227,0.00008451148,0.0001694648,0.00036235814,0.00006197084],"domain_scores_gemma":[0.99905735,0.00037515897,0.000080056765,0.00014311285,0.00030359344,0.000040763705],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007486417,0.00085431465,0.0010246421,0.0028486156,0.00087918184,0.0011042703,0.0018016401,0.0009006607,0.0025293904],"category_scores_gemma":[0.0027670192,0.00043884342,0.001206523,0.0048277923,0.00029660735,0.0015701506,0.0009738894,0.00079090113,0.0011160562],"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":[0.0002549221,0.00028001456,0.0031615603,0.0004771385,0.00018076754,0.0008526392,0.00025692835,0.067358956,0.014734414,0.01370914,0.011489803,0.8872437],"study_design_scores_gemma":[0.000069934686,0.0002638804,0.0019206161,0.000084001935,0.00014256501,0.0016885875,0.00019369287,0.940214,0.008668341,0.030401561,0.016301991,0.000050806808],"about_ca_topic_score_codex":0.0023652054,"about_ca_topic_score_gemma":0.004737518,"teacher_disagreement_score":0.0028486156,"about_ca_system_score_codex":0.00042995624,"about_ca_system_score_gemma":0.0012988707,"threshold_uncertainty_score":0.008461654},"labels":[],"label_agreement":null},{"id":"W4405793555","doi":"10.1007/s10489-024-06137-y","title":"A tree-based framework to mine top-K closed sequential patterns","year":2024,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Data Mining Algorithms and Applications","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":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; University of Manitoba","keywords":"Computer science; Tree (set theory); Data mining; Algorithm; Combinatorics; Mathematics","score_opus":0.02684388380175468,"score_gpt":0.3006824329469483,"score_spread":0.2738385491451936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405793555","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006869664,0.0005701224,0.9873411,0.00021116188,0.00005673857,0.0001845521,0.0015508,0.0024157222,0.0008001425],"genre_scores_gemma":[0.07056762,0.0004481019,0.92199504,0.00014571594,0.00006371956,0.00021542444,0.0043837666,0.00017745343,0.0020031033],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985209,0.00020941002,0.00017894339,0.00040109275,0.000558127,0.0001315162],"domain_scores_gemma":[0.9973943,0.0009893692,0.00021464696,0.00030088288,0.0009200223,0.0001808188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014030254,0.0009399788,0.0014818049,0.004328661,0.0013265768,0.0021403236,0.0019935113,0.0015920694,0.0035551027],"category_scores_gemma":[0.006093373,0.0005135914,0.0016075086,0.006172808,0.0005322075,0.0026214349,0.0013460648,0.0015464047,0.0027982646],"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":[0.00058804854,0.00046337376,0.0074451487,0.0008204786,0.00036122152,0.0007515132,0.0004538054,0.044623107,0.021774208,0.031103436,0.030912437,0.8607031],"study_design_scores_gemma":[0.000069753216,0.00021162511,0.0017208348,0.00011594562,0.00017584908,0.0009755862,0.00018740937,0.89502084,0.006575806,0.07247041,0.022414945,0.000060959486],"about_ca_topic_score_codex":0.0068256743,"about_ca_topic_score_gemma":0.014220346,"teacher_disagreement_score":0.0068256743,"about_ca_system_score_codex":0.0006389127,"about_ca_system_score_gemma":0.0028610427,"threshold_uncertainty_score":0.013571918},"labels":[],"label_agreement":null},{"id":"W4406238774","doi":"10.1007/978-3-030-71522-9_71","title":"Certificate Revocation","year":2025,"lang":"en","type":"book-chapter","venue":"","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":"University of Ottawa","funders":"","keywords":"Computer science; Revocation list; Revocation; Certificate; Computer security; Operating system; Public key certificate; Theoretical computer science; Public-key cryptography; Overhead (engineering)","score_opus":0.07527060373977518,"score_gpt":0.2725859521477529,"score_spread":0.1973153484079777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406238774","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0075567854,0.0016002576,0.11618101,0.0046444805,0.0043313354,0.0009435938,0.0022581564,0.010449344,0.852035],"genre_scores_gemma":[0.14743353,0.002303918,0.030931726,0.0030515376,0.00088703836,0.0004146639,0.00440497,0.0025624232,0.80801016],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99612385,0.00062073086,0.00017957794,0.00071953767,0.001769297,0.00058698567],"domain_scores_gemma":[0.992841,0.0011248563,0.00024755267,0.0038071985,0.0016109135,0.00036841698],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026105412,0.0008533367,0.0008714902,0.0021597904,0.0019705945,0.005545834,0.002547143,0.0021206662,0.11824739],"category_scores_gemma":[0.012623855,0.00052691984,0.0010361638,0.0018904041,0.0015701918,0.007740155,0.004857457,0.0037416648,0.08177175],"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":[0.00031859972,0.00017479132,0.0005631522,0.00038925023,0.000021750362,0.00043262177,0.0004152612,0.0021979955,0.0031147161,0.30284688,0.365231,0.324294],"study_design_scores_gemma":[0.000034533437,0.000057413494,0.00021357246,0.00016437944,0.000018557861,0.00063390844,0.00019815392,0.0030720374,0.0052245953,0.039810747,0.9505392,0.000032918113],"about_ca_topic_score_codex":0.002423639,"about_ca_topic_score_gemma":0.0024948271,"teacher_disagreement_score":0.11824739,"about_ca_system_score_codex":0.0024673596,"about_ca_system_score_gemma":0.0036467423,"threshold_uncertainty_score":0.39557695},"labels":[],"label_agreement":null},{"id":"W4406659350","doi":"10.1016/b978-0-434-98607-1.50039-x","title":"10.1016/b978-0-434-98607-1.50039-x","year":2000,"lang":"en","type":"book-chapter","venue":"Time to knit","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Database","score_opus":0.011273482176118349,"score_gpt":0.18741760882189906,"score_spread":0.17614412664578072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406659350","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00029865597,0.00062730396,0.0020809919,0.0004570563,0.0002298813,0.000065951666,0.0013039621,0.0018154784,0.9931206],"genre_scores_gemma":[0.0007152815,0.00038617794,0.0008447267,0.00016259894,0.000051084597,0.000052280677,0.00080712576,0.00039453368,0.9965862],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.999438,0.00003705959,0.00004120578,0.00019573976,0.00017936568,0.00010865164],"domain_scores_gemma":[0.9979679,0.0006677976,0.00016547683,0.00031545726,0.0003254235,0.00055795826],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0010951097,0.0025564034,0.0016056165,0.0022648994,0.0012880198,0.004546416,0.003148714,0.004119613,0.97980267],"category_scores_gemma":[0.0021168494,0.00086559413,0.0009452367,0.002734945,0.0011828588,0.005597803,0.0031593207,0.0022859732,0.9896617],"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":[0.00013690162,0.00013560806,0.0004487094,0.00042818196,0.00002031991,0.000113680675,0.00007460368,0.00045166494,0.0021114128,0.00592131,0.37826553,0.61189204],"study_design_scores_gemma":[0.00002173188,0.00005296697,0.00059517415,0.00028249712,0.000010587849,0.00020587235,0.00007456963,0.00022390942,0.00042001923,0.0014500984,0.9966462,0.000016380274],"about_ca_topic_score_codex":0.0029262642,"about_ca_topic_score_gemma":0.002441471,"teacher_disagreement_score":0.020197332,"about_ca_system_score_codex":0.00096768414,"about_ca_system_score_gemma":0.0008077548,"threshold_uncertainty_score":0.02880907},"labels":[],"label_agreement":null},{"id":"W4406670964","doi":"10.1016/b978-0-08-057206-2.50010-3","title":"10.1016/b978-0-08-057206-2.50010-3","year":2000,"lang":"en","type":"book-chapter","venue":"Time to knit","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Division (mathematics); Computer science; Mathematics; Arithmetic","score_opus":0.011120548297825399,"score_gpt":0.1883262568290845,"score_spread":0.17720570853125908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406670964","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00030813937,0.00057284354,0.002600107,0.0005617182,0.000272007,0.0000676291,0.0014176243,0.0019793913,0.9922206],"genre_scores_gemma":[0.00089414575,0.00033463156,0.00082935375,0.00016170817,0.000054488755,0.000048423524,0.0007895155,0.000475401,0.9964122],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993351,0.000044492845,0.000047977064,0.00022490504,0.00022572093,0.0001216604],"domain_scores_gemma":[0.99754745,0.0008158766,0.0001891121,0.0004092903,0.00047154265,0.00056684256],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0013016652,0.0022704934,0.001727957,0.0020831414,0.001344512,0.005869346,0.0032474324,0.004370917,0.9821315],"category_scores_gemma":[0.0023154765,0.0009741454,0.0011160765,0.0026960187,0.0014132956,0.005373185,0.003122283,0.0026074355,0.9913685],"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":[0.00017892166,0.0001245019,0.0005271421,0.0004461402,0.00002698586,0.00013634207,0.00008362401,0.0006110736,0.0027502747,0.0072258697,0.36878815,0.6191009],"study_design_scores_gemma":[0.000023630506,0.00005192377,0.00049291487,0.00025001133,0.000010302926,0.00022305305,0.0000719432,0.00026789453,0.00044764482,0.0014613745,0.9966822,0.000016988113],"about_ca_topic_score_codex":0.0028862003,"about_ca_topic_score_gemma":0.0023501462,"teacher_disagreement_score":0.017868519,"about_ca_system_score_codex":0.0011189022,"about_ca_system_score_gemma":0.0008582731,"threshold_uncertainty_score":0.025487185},"labels":[],"label_agreement":null},{"id":"W4408238568","doi":"10.7763/ijcte.2025.v17.1366","title":"Enhancing Tag Recommendation Precision on Stack Overflow Data Warehouse: An Integrated Approach Combining Numeric Attributes, Feature Extraction Techniques, and Multiple Machine Learning Algorithms","year":2025,"lang":"en","type":"article","venue":"International Journal of Computer Theory and Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Stack (abstract data type); Data mining; Data warehouse; Algorithm; Machine learning; Feature (linguistics); Artificial intelligence; Operating system","score_opus":0.01649627597894825,"score_gpt":0.2781303409130938,"score_spread":0.26163406493414554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408238568","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34606594,0.0017025536,0.62769824,0.0006378582,0.00015706653,0.00032167655,0.0031110998,0.01679528,0.0035103818],"genre_scores_gemma":[0.4830093,0.0003610058,0.5119959,0.00014830583,0.00006830619,0.00011085297,0.0029538036,0.0001635667,0.0011889108],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973429,0.00056538184,0.00034813667,0.0005572942,0.0009949548,0.00019136007],"domain_scores_gemma":[0.9889025,0.0047611417,0.00091984664,0.0019536815,0.003173675,0.00028912132],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005410874,0.0012102472,0.0018443658,0.008777403,0.000992809,0.0031620911,0.0013458233,0.0009629513,0.00065134617],"category_scores_gemma":[0.014261179,0.0004344116,0.0012459642,0.0077762264,0.0003195772,0.003840688,0.0012904886,0.0010419878,0.000936683],"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":[0.00088330405,0.00059949956,0.058361165,0.000338458,0.00041577537,0.00023367311,0.000598903,0.03240456,0.021514295,0.0015995196,0.006912666,0.8761382],"study_design_scores_gemma":[0.000068328074,0.00038460045,0.023803994,0.000098919874,0.00029446834,0.00027675854,0.0006993276,0.92346305,0.038211953,0.005131761,0.007411209,0.00015558259],"about_ca_topic_score_codex":0.01421641,"about_ca_topic_score_gemma":0.022106,"teacher_disagreement_score":0.01421641,"about_ca_system_score_codex":0.0010925084,"about_ca_system_score_gemma":0.0017285435,"threshold_uncertainty_score":0.028615832},"labels":[],"label_agreement":null},{"id":"W4408397895","doi":"10.2139/ssrn.5177518","title":"Informationally Robust Cheap-Talk","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","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":"University of Toronto","funders":"","keywords":"Business; Computer science","score_opus":0.012733320078885694,"score_gpt":0.2506201254677737,"score_spread":0.23788680538888798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408397895","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07533092,0.0019157589,0.862049,0.011162509,0.0009368511,0.00020690168,0.0018290362,0.0040724576,0.042496663],"genre_scores_gemma":[0.88223183,0.00095591246,0.077871785,0.0030753864,0.0019526507,0.0003347327,0.0012065597,0.0011854941,0.03118557],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9888946,0.0052967733,0.00048146927,0.001875496,0.0021990682,0.0012526867],"domain_scores_gemma":[0.93174535,0.046840325,0.0027106528,0.014534263,0.0027081568,0.0014612154],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012215542,0.0020609128,0.0041330378,0.0025908537,0.0027390306,0.006892979,0.003995469,0.0065910146,0.022805814],"category_scores_gemma":[0.08421252,0.0020451897,0.0021807784,0.002210894,0.005246695,0.010290195,0.007890264,0.0064368276,0.008633018],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003031074,0.00034499762,0.001526311,0.0006591708,0.0004100955,0.0005797448,0.00042226535,0.06193806,0.0062491465,0.78164274,0.036983382,0.10621297],"study_design_scores_gemma":[0.00009993331,0.00012189071,0.0003994006,0.00004314921,0.000071908325,0.00025832112,0.00008355325,0.117548086,0.0024170042,0.87663674,0.002261848,0.000058246635],"about_ca_topic_score_codex":0.00056988205,"about_ca_topic_score_gemma":0.00049984484,"teacher_disagreement_score":0.022805814,"about_ca_system_score_codex":0.0015158918,"about_ca_system_score_gemma":0.0024241344,"threshold_uncertainty_score":0.07629305},"labels":[],"label_agreement":null},{"id":"W4409374113","doi":"10.1016/b978-0-443-15888-9.00003-0","title":"Input: concepts, instances, attributes","year":2025,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","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":"Polytechnique Montréal","funders":"","keywords":"Computer science","score_opus":0.019189061992539745,"score_gpt":0.26520712929004403,"score_spread":0.24601806729750428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409374113","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06607724,0.0027778996,0.25509948,0.0094974125,0.0010294233,0.003156129,0.5666791,0.045927513,0.04975574],"genre_scores_gemma":[0.10317325,0.0017759508,0.54070574,0.0012348868,0.00041469303,0.0034081591,0.32259023,0.0022271206,0.024469959],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995029,0.00007611361,0.0000341172,0.00018653573,0.0001594431,0.000040955598],"domain_scores_gemma":[0.9985114,0.0010203577,0.00005529674,0.00011567699,0.0002269732,0.000070219605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000781011,0.0029167235,0.0013854556,0.0017455103,0.000532893,0.0025409346,0.0016660589,0.0026055411,0.10064804],"category_scores_gemma":[0.0072935917,0.00074079324,0.0013978513,0.0021564008,0.000413363,0.0030235038,0.0020271556,0.0012855546,0.029142275],"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":[0.0015886076,0.00056589255,0.0054476764,0.00450495,0.0001931755,0.0007339254,0.0004226745,0.013519185,0.007259251,0.010501933,0.5112468,0.44401595],"study_design_scores_gemma":[0.0028863288,0.0008410048,0.0082499515,0.0023535155,0.0005479395,0.0019053061,0.0017195959,0.2934905,0.03669408,0.091585524,0.559517,0.00020930474],"about_ca_topic_score_codex":0.0031229018,"about_ca_topic_score_gemma":0.0034856712,"teacher_disagreement_score":0.10064804,"about_ca_system_score_codex":0.001054384,"about_ca_system_score_gemma":0.0016946411,"threshold_uncertainty_score":0.33670127},"labels":[],"label_agreement":null},{"id":"W4409374139","doi":"10.1016/b978-0-443-15888-9.00004-2","title":"Output: knowledge representation","year":2025,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","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":"Polytechnique Montréal","funders":"","keywords":"Representation (politics); Computer science; Political science","score_opus":0.028200147002603152,"score_gpt":0.2874745713453071,"score_spread":0.2592744243427039,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409374139","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022406077,0.0021958924,0.41089362,0.0061078654,0.0027849725,0.002007863,0.16234425,0.14013717,0.25112233],"genre_scores_gemma":[0.11845743,0.0021550767,0.45537654,0.0016756239,0.0007036139,0.0018618089,0.23622128,0.0071737133,0.17637491],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99909925,0.00013892855,0.00007085342,0.00032713177,0.00027421783,0.0000896524],"domain_scores_gemma":[0.99913543,0.00030844874,0.000032318047,0.0002016029,0.0002762144,0.000046060988],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007074256,0.0022778702,0.0014267538,0.0030561965,0.0006414338,0.0042820554,0.0015296807,0.0017516796,0.18071426],"category_scores_gemma":[0.004581167,0.0005110484,0.0019264423,0.0023773885,0.00039273282,0.002886313,0.0027963372,0.0010379514,0.1243786],"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":[0.0005731041,0.00018797247,0.0011416889,0.0009167509,0.00012889721,0.00033472345,0.00017194875,0.003759469,0.006727545,0.010203307,0.3627241,0.6131304],"study_design_scores_gemma":[0.00043901283,0.00035546,0.004371737,0.0007130293,0.00057968486,0.0010030495,0.0008510493,0.11391224,0.04746588,0.116977364,0.7131597,0.00017181663],"about_ca_topic_score_codex":0.0027864394,"about_ca_topic_score_gemma":0.0020049307,"teacher_disagreement_score":0.18071426,"about_ca_system_score_codex":0.0009433882,"about_ca_system_score_gemma":0.0015681089,"threshold_uncertainty_score":0.6045494},"labels":[],"label_agreement":null},{"id":"W4409552965","doi":"10.63485/bcw2c-56q53","title":"More on the case for open data","year":2006,"lang":"en","type":"preprint","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Business","score_opus":0.17338894622438852,"score_gpt":0.3827702475333527,"score_spread":0.20938130130896418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409552965","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00039857323,0.032010626,0.011400344,0.9072927,0.010699448,0.00002117911,0.00083786494,0.000146452,0.037192874],"genre_scores_gemma":[0.03980465,0.071258806,0.03037255,0.71093327,0.0620076,0.00024063083,0.0020320383,0.0016758265,0.08167461],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9781214,0.011024957,0.0010634349,0.0028073492,0.0059683993,0.0010145068],"domain_scores_gemma":[0.81696147,0.1447945,0.002490185,0.01713545,0.015338068,0.0032804024],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.032286007,0.0009634844,0.0017676272,0.005461955,0.0054995692,0.017317193,0.003601645,0.015398062,0.08541679],"category_scores_gemma":[0.16143557,0.0008185238,0.0020873514,0.007598699,0.017123107,0.08894359,0.007873603,0.02653874,0.012229801],"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":[0.000030495783,0.000021813566,0.00038954904,0.00024995275,0.000033735607,0.000121502926,0.0006116246,0.00019081234,0.00006710445,0.50359195,0.47419247,0.020498987],"study_design_scores_gemma":[0.000019168221,0.0000060901293,0.0002995496,0.00077912473,0.00000757176,0.000116831936,0.0006410024,0.0002184153,0.000054178432,0.28962716,0.70819336,0.000037554153],"about_ca_topic_score_codex":0.013287241,"about_ca_topic_score_gemma":0.018549234,"teacher_disagreement_score":0.9963983,"about_ca_system_score_codex":0.004988311,"about_ca_system_score_gemma":0.0037288193,"threshold_uncertainty_score":0.28574765},"labels":[],"label_agreement":null},{"id":"W4409576359","doi":"10.61091/jcmcc127a-130","title":"Frequent itemset mining optimization and computational complexity analysis based on improved Apriori algorithm","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Apriori algorithm; Computer science; Data mining; Association rule learning; A priori and a posteriori; Algorithm","score_opus":0.015688132115711365,"score_gpt":0.2707916611535055,"score_spread":0.25510352903779415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409576359","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044249427,0.0013910427,0.95022464,0.0005537842,0.000104916675,0.00013752884,0.00028471017,0.0005934467,0.0024605426],"genre_scores_gemma":[0.38378423,0.0014010934,0.6105117,0.00023679658,0.00022371937,0.00048830005,0.0010805721,0.00012937529,0.0021441788],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996358,0.0009980273,0.00042420384,0.0007359964,0.0012050752,0.00027870302],"domain_scores_gemma":[0.9935364,0.0036304027,0.00039595494,0.00046644575,0.001864145,0.00010670458],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033033658,0.0013800892,0.0019299155,0.0028473185,0.0006712065,0.0018424348,0.0017662587,0.0010018125,0.0019505278],"category_scores_gemma":[0.010884289,0.00049433764,0.0018619115,0.0036145377,0.0006275157,0.002540363,0.00086497125,0.0016302848,0.00042747046],"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":[0.0004443135,0.000272028,0.009463902,0.00044309653,0.00036283667,0.0003767317,0.00019480888,0.6794828,0.0054018986,0.020277241,0.0048377533,0.27844247],"study_design_scores_gemma":[0.000025648333,0.00009220618,0.0008918957,0.000013338044,0.00004595654,0.00012980148,0.000029995063,0.9901966,0.0013644123,0.0061280387,0.0010673916,0.000014757168],"about_ca_topic_score_codex":0.0035983762,"about_ca_topic_score_gemma":0.0023050187,"teacher_disagreement_score":0.0035983762,"about_ca_system_score_codex":0.0011697225,"about_ca_system_score_gemma":0.0020090223,"threshold_uncertainty_score":0.017470062},"labels":[],"label_agreement":null},{"id":"W4409603194","doi":"10.61091/jcmcc127b-140","title":"Research on Optimization Methods of Knowledge Discovery Algorithms for Library Data Mining","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Office for Philosophy and Social Sciences","keywords":"Computer science; Knowledge extraction; Data mining; Data science; Algorithm; Information retrieval","score_opus":0.09402424131578067,"score_gpt":0.4174308182576229,"score_spread":0.3234065769418422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409603194","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029726853,0.0024561344,0.9921349,0.0005558905,0.000063919,0.00006370308,0.000069759604,0.00016943546,0.001513581],"genre_scores_gemma":[0.12434214,0.006033626,0.86541736,0.0005161719,0.0003681806,0.0005192716,0.0005671351,0.00020254531,0.0020335813],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.99435544,0.002340953,0.0004797722,0.0012145792,0.0014054889,0.00020385186],"domain_scores_gemma":[0.983304,0.013182772,0.0007160333,0.0007886678,0.0018802888,0.0001281663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0077381153,0.0017706504,0.0024673138,0.0030593243,0.00085829606,0.0035274087,0.002562813,0.0014856389,0.0018471085],"category_scores_gemma":[0.026630236,0.0010698859,0.0022717188,0.0061920183,0.0014857231,0.0050606346,0.0014144738,0.0032412815,0.00073122914],"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":[0.000102697566,0.00022169117,0.0025513738,0.0007692609,0.00046642395,0.0000634116,0.00017910311,0.49786022,0.0009939158,0.08261835,0.004106943,0.4100667],"study_design_scores_gemma":[0.000012894972,0.00002946941,0.00031141116,0.000053726802,0.000032944987,0.000035636127,0.000038391758,0.96025705,0.0006566907,0.036119424,0.002436614,0.000015669366],"about_ca_topic_score_codex":0.0058679637,"about_ca_topic_score_gemma":0.0033384727,"teacher_disagreement_score":0.0077381153,"about_ca_system_score_codex":0.002538992,"about_ca_system_score_gemma":0.0030156204,"threshold_uncertainty_score":0.040923536},"labels":[],"label_agreement":null},{"id":"W4409793570","doi":"10.61091/jcmcc127a-162","title":"Research on Decision Tree-Based Risk Control Strategies in E-Commerce Platforms","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Decision tree; Control (management); Computer science; Tree (set theory); Risk analysis (engineering); Business; Data science; Data mining; Artificial intelligence; Mathematics","score_opus":0.02700829846696938,"score_gpt":0.3349308092400209,"score_spread":0.3079225107730515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409793570","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054273527,0.002411057,0.9352868,0.00054602,0.00008273546,0.00021684021,0.00005749256,0.0002359417,0.0068895314],"genre_scores_gemma":[0.85113984,0.002646003,0.14380679,0.00013661075,0.000069061556,0.00020091687,0.00014615717,0.000034567365,0.0018199894],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.997617,0.0009237849,0.00016751082,0.0003504582,0.00074033474,0.00020089072],"domain_scores_gemma":[0.9970245,0.0015964236,0.00037671896,0.000100478646,0.0007367448,0.00016507147],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002860507,0.0010966449,0.00095655903,0.0022121188,0.00068731775,0.0024161944,0.0014575308,0.0008434613,0.001909038],"category_scores_gemma":[0.006049864,0.00043618347,0.0011813624,0.0019110425,0.000597525,0.0034242917,0.00089224364,0.0010736611,0.0002451955],"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":[0.00016754195,0.0003373645,0.0057656546,0.0005693735,0.0003635569,0.000253934,0.00072357454,0.6345891,0.003472497,0.08069941,0.0015842061,0.27147382],"study_design_scores_gemma":[0.000022839098,0.00015131506,0.0008524238,0.000064898566,0.000078348115,0.000063400636,0.00019052296,0.9705356,0.0009313621,0.025156783,0.001927301,0.000025283713],"about_ca_topic_score_codex":0.0054586558,"about_ca_topic_score_gemma":0.0025641848,"teacher_disagreement_score":0.0054586558,"about_ca_system_score_codex":0.0015529165,"about_ca_system_score_gemma":0.001884598,"threshold_uncertainty_score":0.015127957},"labels":[],"label_agreement":null},{"id":"W4410187497","doi":"10.63278/1487","title":"Synthetic Cognition Meets Data Deluge: Architecting Agentic AI Models for Self-Regulating Knowledge Graphs in Heterogeneous Data Warehousing","year":2025,"lang":"en","type":"article","venue":"Metallurgical and Materials Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Optech (Canada)","funders":"","keywords":"Data warehouse; Knowledge graph; Cognition; Data science; Materials science; Computer science; Data mining; Artificial intelligence; Neuroscience; Psychology","score_opus":0.04568384548912052,"score_gpt":0.2909916036330006,"score_spread":0.24530775814388006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410187497","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03335166,0.00026963913,0.95123,0.0024746961,0.00009123858,0.00015167796,0.000077720826,0.0009163749,0.011437053],"genre_scores_gemma":[0.39608717,0.00044138049,0.5974576,0.0003801724,0.000050641185,0.00029695517,0.00024742572,0.00034180994,0.0046968465],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990349,0.0004858486,0.000068388494,0.00015282133,0.00017700267,0.00008113942],"domain_scores_gemma":[0.9971902,0.0014948361,0.0001950996,0.0005665136,0.00028340056,0.00026995913],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025276935,0.00064122694,0.00045665292,0.0010293096,0.0012459519,0.006230411,0.0024305428,0.0015758324,0.0031689224],"category_scores_gemma":[0.005995477,0.00061006297,0.0012784384,0.0005651265,0.0041566226,0.0055761375,0.0038038872,0.00206724,0.0006659301],"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":[0.00009863853,0.00018716136,0.0022451913,0.00021224965,0.000119463555,0.00033571484,0.0045035547,0.42785335,0.0035705063,0.50404346,0.002357122,0.054473612],"study_design_scores_gemma":[0.000021892787,0.00004536265,0.00014931272,0.000045531335,0.000029491757,0.000053646872,0.00067234284,0.71070987,0.0013221407,0.2693491,0.01756885,0.000032432737],"about_ca_topic_score_codex":0.006131353,"about_ca_topic_score_gemma":0.008871917,"teacher_disagreement_score":0.006230411,"about_ca_system_score_codex":0.0017568325,"about_ca_system_score_gemma":0.0023435939,"threshold_uncertainty_score":0.013367891},"labels":[],"label_agreement":null},{"id":"W4410350959","doi":"10.1101/2025.05.07.652750","title":"Improving plant functional annotation from knowledge graphs using Graph Neural Networks","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Knowledge graph; Computer science; Annotation; Artificial neural network; Graph; Artificial intelligence; Theoretical computer science","score_opus":0.02143391006112888,"score_gpt":0.22797371228028462,"score_spread":0.20653980221915574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410350959","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19251361,0.001629993,0.785399,0.0012564788,0.00011320631,0.00020013502,0.00575106,0.006435135,0.0067014215],"genre_scores_gemma":[0.6374958,0.0009997487,0.34365875,0.0004622736,0.00006184833,0.0001745272,0.013850286,0.00031339502,0.0029832553],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995821,0.00009670123,0.000022930233,0.00018397473,0.00007981783,0.000034510016],"domain_scores_gemma":[0.9984648,0.0009532883,0.00014507305,0.00017865967,0.00021457222,0.00004360696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054414454,0.00096476125,0.00046716767,0.0031949969,0.00052554277,0.0008789221,0.0008352037,0.0008916814,0.0018156361],"category_scores_gemma":[0.0031014036,0.0003919248,0.0010437235,0.002064513,0.00049079047,0.0016370807,0.0009746542,0.0010671335,0.00054276665],"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":[0.00024646378,0.00028933163,0.010383546,0.00056072196,0.00023442524,0.00031935723,0.00026335078,0.62922615,0.011897079,0.013430365,0.010370746,0.32277858],"study_design_scores_gemma":[0.000008171994,0.000018290133,0.0011349203,0.000034546396,0.00004020759,0.00002412965,0.0000509968,0.9779494,0.0021397786,0.016228141,0.002362568,0.000008857504],"about_ca_topic_score_codex":0.018228432,"about_ca_topic_score_gemma":0.026405113,"teacher_disagreement_score":0.018228432,"about_ca_system_score_codex":0.0011156385,"about_ca_system_score_gemma":0.0006819743,"threshold_uncertainty_score":0.03624469},"labels":[],"label_agreement":null},{"id":"W4410610020","doi":"10.1145/3735635","title":"Do Current Language Models Support Code Intelligence for R Programming Language?","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Programming language; Current (fluid); First-generation programming language; Programming paradigm","score_opus":0.09567141734564485,"score_gpt":0.37935461176167246,"score_spread":0.28368319441602763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410610020","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.072939575,0.007815368,0.7034459,0.012629806,0.0014513546,0.00049972406,0.018248448,0.16730689,0.015662942],"genre_scores_gemma":[0.3224582,0.0040821033,0.5804629,0.006999962,0.0005595901,0.0011729944,0.057299268,0.018724952,0.008240093],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98989457,0.004841242,0.00067374855,0.0028169404,0.0013651992,0.00040827927],"domain_scores_gemma":[0.9589766,0.024269307,0.0023166852,0.0092684645,0.004369041,0.00079986535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011167321,0.0024287596,0.0013539528,0.0019259262,0.00061059615,0.0045305477,0.004706239,0.0019954266,0.0051963343],"category_scores_gemma":[0.07583054,0.0012017819,0.0027300592,0.0022039446,0.0013098832,0.008976677,0.0026763144,0.004779557,0.012608322],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015228937,0.00051566045,0.026586741,0.003757023,0.0010388779,0.00037206325,0.001272316,0.103347786,0.010578712,0.02433263,0.21613291,0.61054236],"study_design_scores_gemma":[0.00029948165,0.00036213046,0.0044401004,0.000599706,0.0003168162,0.00048696855,0.00032761015,0.8213017,0.009557451,0.043565497,0.11855236,0.00019006334],"about_ca_topic_score_codex":0.0067509026,"about_ca_topic_score_gemma":0.01255785,"teacher_disagreement_score":0.011167321,"about_ca_system_score_codex":0.001311418,"about_ca_system_score_gemma":0.003919497,"threshold_uncertainty_score":0.059059143},"labels":[],"label_agreement":null},{"id":"W4410863964","doi":"10.1007/978-3-031-84756-1_8","title":"Sequence-Based DNN PCGML","year":2025,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on games and computational intelligence","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":"University of Sudbury; University of Alberta","funders":"","keywords":"Sequence (biology); Computer science; Biology; Genetics","score_opus":0.03336864294852234,"score_gpt":0.2779717979551326,"score_spread":0.24460315500661026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410863964","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006616824,0.00081003475,0.96091104,0.00037606256,0.00041516236,0.00016204402,0.0015170375,0.00768237,0.021509342],"genre_scores_gemma":[0.21858479,0.0013482734,0.7087686,0.0011728881,0.0002950304,0.0004959382,0.0069568437,0.0010927812,0.061284844],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9996252,0.000054465414,0.000030885065,0.00014127576,0.00010693333,0.000041258096],"domain_scores_gemma":[0.9995216,0.0001375164,0.000019902049,0.00009915549,0.00019210615,0.000029750476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061084086,0.00070488977,0.0006275552,0.0007992598,0.000406764,0.0010753957,0.002029877,0.00097105413,0.021157194],"category_scores_gemma":[0.0015628419,0.0003733252,0.00065278227,0.00081153406,0.00043108175,0.0017387443,0.0010694166,0.0013716369,0.007617655],"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":[0.00017463825,0.000081584454,0.0002730097,0.00025337265,0.000043150336,0.00011703152,0.000046094865,0.11091217,0.0098937275,0.04792283,0.024436746,0.80584556],"study_design_scores_gemma":[0.000021532906,0.00006434776,0.0001537219,0.000052208747,0.000024302071,0.000090630034,0.000019771147,0.9199206,0.0092044035,0.047737114,0.02269632,0.000014962008],"about_ca_topic_score_codex":0.011155201,"about_ca_topic_score_gemma":0.019730957,"teacher_disagreement_score":0.021157194,"about_ca_system_score_codex":0.0012882064,"about_ca_system_score_gemma":0.0012253468,"threshold_uncertainty_score":0.07077789},"labels":[],"label_agreement":null},{"id":"W4410956460","doi":"10.1007/s42729-024-01724-x","title":"Improving Phosphorus Recommendation Models with Random Forest Regressor. Case of Corn (Zea mays L.)","year":2025,"lang":"en","type":"article","venue":"Journal of soil science and plant nutrition","topic":"Data Mining Algorithms and Applications","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":"Université Laval","funders":"OCP Group","keywords":"Zea mays; Phosphorus; Agronomy; Environmental science; Agroforestry; Biology; Chemistry","score_opus":0.014929573897088301,"score_gpt":0.24176556564804183,"score_spread":0.22683599175095354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410956460","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6540353,0.0044457954,0.33037505,0.002565365,0.00026011502,0.00011525138,0.00206645,0.0018934765,0.0042432114],"genre_scores_gemma":[0.9235649,0.00047451965,0.07170181,0.00021749824,0.00010332323,0.000035925852,0.0011813738,0.00004345677,0.0026772737],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99954283,0.00020581878,0.000023292105,0.00011373061,0.000060665232,0.000053705116],"domain_scores_gemma":[0.9967366,0.002405306,0.00012185443,0.00014576694,0.00051198376,0.00007843622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002080534,0.00077589694,0.0009234625,0.00085786026,0.00043746055,0.0006882036,0.0011122095,0.0011380641,0.001058323],"category_scores_gemma":[0.0045452765,0.0003399171,0.0007327348,0.00070578384,0.00019250078,0.0010280757,0.00033792804,0.0008892959,0.00045766632],"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":[0.0006264307,0.0005786224,0.01987727,0.00015839298,0.00035423358,0.00017020237,0.00005339346,0.7818219,0.0019060334,0.0013778763,0.007305601,0.18577003],"study_design_scores_gemma":[0.000014159542,0.00003400749,0.0006736088,0.000003493007,0.000025389578,0.000007026133,0.000009527014,0.9984251,0.00018972687,0.00045549867,0.00015867261,0.0000038035964],"about_ca_topic_score_codex":0.07308677,"about_ca_topic_score_gemma":0.087939195,"teacher_disagreement_score":0.07308677,"about_ca_system_score_codex":0.00058172835,"about_ca_system_score_gemma":0.0010976844,"threshold_uncertainty_score":0.14532274},"labels":[],"label_agreement":null},{"id":"W4412603234","doi":"10.2139/ssrn.5353923","title":"Generative AI for Data Scraping","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Data Mining Algorithms 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":"McGill University","funders":"","keywords":"Generative grammar; Artificial intelligence; Computer science; Generative model; Natural language processing; Data science","score_opus":0.043554538676280834,"score_gpt":0.3401694084707009,"score_spread":0.29661486979442003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412603234","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031298585,0.00042984795,0.99266666,0.00046521745,0.000058499667,0.000043576656,0.00008492427,0.001265094,0.0018563048],"genre_scores_gemma":[0.33848876,0.00084609876,0.6467939,0.0010567287,0.00020215304,0.00032531115,0.00092056853,0.0010888306,0.010277625],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962669,0.0016241459,0.00024625595,0.00066288724,0.0009623163,0.00023754314],"domain_scores_gemma":[0.9789659,0.015253928,0.00037370127,0.004146113,0.0009146754,0.00034570618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040419973,0.0007928805,0.0018134259,0.0017959148,0.0013902793,0.0028192473,0.0032506802,0.002227369,0.006834511],"category_scores_gemma":[0.023114791,0.0010603954,0.002602658,0.0022533445,0.0032939874,0.0036963653,0.006485669,0.0048263147,0.0015603014],"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":[0.00021211196,0.00013678773,0.0022332072,0.00062136643,0.00024635086,0.0005608633,0.0010563752,0.29838833,0.0041946294,0.4172316,0.013539134,0.26157928],"study_design_scores_gemma":[0.000015152279,0.000020079118,0.00008235014,0.000037975085,0.000024300436,0.00011844213,0.000050724677,0.72675,0.0010724434,0.2679644,0.0038502216,0.00001380643],"about_ca_topic_score_codex":0.0030562428,"about_ca_topic_score_gemma":0.004464125,"teacher_disagreement_score":0.006834511,"about_ca_system_score_codex":0.0012730622,"about_ca_system_score_gemma":0.0015393317,"threshold_uncertainty_score":0.022863686},"labels":[],"label_agreement":null},{"id":"W4412877219","doi":"10.1145/3711896.3737849","title":"The 4th Workshop on AI Agent for Information Retrieval: Generating and Ranking","year":2025,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Lawrence Berkeley National Laboratory; University of California, San Diego; University of Illinois at Urbana-Champaign; University of Technology Sydney; Arizona State University; Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; University of Illinois at Chicago; Tencent; Georgia Institute of Technology; Institute for Catastrophic Loss Reduction; National Science Foundation","keywords":"Ranking (information retrieval); Computer science; Information retrieval; Artificial intelligence","score_opus":0.017806743319193404,"score_gpt":0.2906828532696844,"score_spread":0.272876109950491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412877219","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014260606,0.039030813,0.75086516,0.0709382,0.03731166,0.002008347,0.0026179599,0.0037620557,0.079205155],"genre_scores_gemma":[0.1435598,0.023145076,0.5245367,0.0141103305,0.019232564,0.0026586012,0.009757033,0.002508167,0.26049167],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9925559,0.0037348813,0.0005240459,0.001263315,0.0012158693,0.000705956],"domain_scores_gemma":[0.9886149,0.005350452,0.00024112729,0.001528501,0.0026819608,0.0015831146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01555464,0.0018904983,0.0025265804,0.0021830155,0.0019477181,0.011340192,0.0046912488,0.0050440812,0.024186315],"category_scores_gemma":[0.01793153,0.0010290595,0.0032832983,0.0020056874,0.0022181873,0.008035092,0.0053063277,0.0071113147,0.010939391],"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":[0.00072764925,0.00077356177,0.00082924287,0.0008208514,0.00031005312,0.00042871063,0.0015573696,0.014512139,0.003646872,0.07920577,0.59650576,0.30068198],"study_design_scores_gemma":[0.00016420457,0.0003805789,0.0008674136,0.00058112177,0.00013422054,0.00032494587,0.0008107224,0.06886635,0.003938268,0.086766794,0.83701545,0.00015005835],"about_ca_topic_score_codex":0.0057014236,"about_ca_topic_score_gemma":0.0061954763,"teacher_disagreement_score":0.024186315,"about_ca_system_score_codex":0.0040414697,"about_ca_system_score_gemma":0.0048808157,"threshold_uncertainty_score":0.08226174},"labels":[],"label_agreement":null},{"id":"W4412888345","doi":"10.18653/v1/2025.findings-acl.576","title":"User Behavior Prediction as a Generic, Robust, Scalable, and Low-Cost Evaluation Strategy for Estimating Generalization in LLMs","year":2025,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Generalization; Scalability; Computer science; Artificial intelligence; Machine learning; Mathematics; Database","score_opus":0.04778180600852341,"score_gpt":0.3289911020724153,"score_spread":0.2812092960638919,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412888345","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20732361,0.002024948,0.75872874,0.0019624624,0.00020569027,0.0004572452,0.0039703012,0.02182429,0.0035027273],"genre_scores_gemma":[0.7966494,0.00025881364,0.19396144,0.0006540424,0.00012959757,0.000373175,0.005855518,0.00045556435,0.0016624122],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966614,0.0013628051,0.00023840718,0.0009352922,0.0005660191,0.0002360723],"domain_scores_gemma":[0.9872285,0.0070562107,0.00064747565,0.0033323742,0.0012734878,0.00046187863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006361771,0.0017578286,0.0016049745,0.0018662562,0.0005833494,0.0017780504,0.0019220895,0.0018983858,0.0016634688],"category_scores_gemma":[0.027329031,0.0006742599,0.001308053,0.0012264374,0.00094551593,0.004080641,0.0021603352,0.0029633697,0.0010526673],"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":[0.0012870337,0.00064996653,0.040134385,0.00036609566,0.0006304755,0.00020164961,0.00030504772,0.5693594,0.009043495,0.00574921,0.017352482,0.35492072],"study_design_scores_gemma":[0.000021526037,0.000115507224,0.0019307559,0.000016255975,0.000026999442,0.00004433441,0.000033051616,0.9901091,0.0015566108,0.0054491423,0.00067873544,0.00001795596],"about_ca_topic_score_codex":0.010322091,"about_ca_topic_score_gemma":0.014316863,"teacher_disagreement_score":0.010322091,"about_ca_system_score_codex":0.0015519792,"about_ca_system_score_gemma":0.0017625593,"threshold_uncertainty_score":0.033644617},"labels":[],"label_agreement":null},{"id":"W4413098261","doi":"10.22541/au.175382408.89466370/v1","title":"How to go with the flow: flow matching in bioinformatics and computational biology","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute; Vector Institute","funders":"","keywords":"Flow (mathematics); Matching (statistics); Computer science; Computational biology; Biology; Bioinformatics; Mathematics; Mechanics; Physics","score_opus":0.015549306668332367,"score_gpt":0.26205823287515195,"score_spread":0.24650892620681958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413098261","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018069935,0.0068066893,0.9784282,0.00963722,0.00046544475,0.000045760444,0.00019640886,0.0005702754,0.0020430011],"genre_scores_gemma":[0.13015488,0.021658735,0.8311853,0.0060727666,0.0024238515,0.00046824067,0.0010567228,0.0010724986,0.0059070433],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971654,0.0010800333,0.0001885494,0.00078465283,0.00062849914,0.00015288065],"domain_scores_gemma":[0.992262,0.0053216373,0.000430111,0.00092604366,0.00068316766,0.00037701306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006646396,0.0010512116,0.0018491248,0.002803532,0.0017048969,0.0054151425,0.0030000098,0.0041958275,0.0056025083],"category_scores_gemma":[0.023482386,0.0010115837,0.0018607918,0.0034999745,0.007265611,0.017103849,0.0051724133,0.006487074,0.0019232194],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010276522,0.000059709124,0.0012610231,0.00043222637,0.00011060315,0.0001170477,0.00039073784,0.050180893,0.0011509461,0.70579755,0.02067707,0.21971937],"study_design_scores_gemma":[0.00001790285,0.000017169337,0.00017126565,0.00013096089,0.000016835134,0.000078055695,0.00005445976,0.11164608,0.00055512413,0.8666073,0.020667192,0.00003760564],"about_ca_topic_score_codex":0.0042801406,"about_ca_topic_score_gemma":0.002117088,"teacher_disagreement_score":0.006646396,"about_ca_system_score_codex":0.0017794416,"about_ca_system_score_gemma":0.0027545923,"threshold_uncertainty_score":0.035149932},"labels":[],"label_agreement":null},{"id":"W4413290154","doi":"10.1145/3745676.3745751","title":"A Deep Learning Framework for Sequence Mining with Bidirectional LSTM and Multi-Scale Attention","year":2025,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Artificial intelligence; Deep learning; Scale (ratio); Sequence (biology); Sequence learning; Machine learning; Sequential Pattern Mining; Chemistry","score_opus":0.02572878843357282,"score_gpt":0.3021858141239449,"score_spread":0.2764570256903721,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413290154","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009956986,0.00050662115,0.98651624,0.0002036223,0.000052447365,0.000037118112,0.00022810575,0.0017015147,0.0007973945],"genre_scores_gemma":[0.43395168,0.0008090107,0.55900323,0.00038196816,0.00010763174,0.0002888896,0.0010510762,0.00018554102,0.0042209234],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997002,0.00005741911,0.000021395472,0.00011641855,0.0000591856,0.000045328525],"domain_scores_gemma":[0.9996377,0.0001490149,0.000042335876,0.000053797263,0.000091581365,0.000025569556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083985,0.00091987965,0.00063873804,0.0008916423,0.00033032493,0.0008108489,0.0017546229,0.00092461717,0.002084961],"category_scores_gemma":[0.0018690082,0.0004709016,0.0008992057,0.0012079438,0.00034846005,0.0017260531,0.0011949872,0.0015793286,0.00084117625],"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":[0.00014560124,0.0001905313,0.0021140224,0.00023820114,0.00023108217,0.00021246445,0.00014334964,0.4033098,0.014286455,0.015494096,0.004272997,0.5593614],"study_design_scores_gemma":[0.0000035213238,0.000022834538,0.00014555136,0.000008020464,0.000011796437,0.000024378302,0.000007810796,0.9918703,0.0010464533,0.006213355,0.0006413489,0.00000463684],"about_ca_topic_score_codex":0.008719203,"about_ca_topic_score_gemma":0.016715117,"teacher_disagreement_score":0.008719203,"about_ca_system_score_codex":0.0009846672,"about_ca_system_score_gemma":0.0014066423,"threshold_uncertainty_score":0.017336905},"labels":[],"label_agreement":null},{"id":"W4413344713","doi":"10.1007/978-3-032-02215-8_7","title":"An Enhanced FP-Growth Algorithm with Hybrid Adaptive Support Threshold for Association Rule Mining","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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 Manitoba","funders":"","keywords":"Association rule learning; Computer science; Algorithm; Association (psychology); Data mining","score_opus":0.012265090170242443,"score_gpt":0.2501160330562981,"score_spread":0.23785094288605566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413344713","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016364364,0.00091487134,0.977836,0.00023749075,0.0002455561,0.00010881387,0.00038662538,0.002525778,0.0013804676],"genre_scores_gemma":[0.10868954,0.00039492024,0.8862979,0.00018399698,0.00018514322,0.0001816232,0.0010666954,0.00018581042,0.002814417],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817455,0.00034660482,0.00016574613,0.00034813484,0.0008167294,0.00014821075],"domain_scores_gemma":[0.99612063,0.0017274827,0.00011985464,0.0004949805,0.0014043618,0.00013266307],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021704424,0.0009015765,0.0020733303,0.00224709,0.0007932535,0.0017192888,0.0034936005,0.0013868568,0.0030468714],"category_scores_gemma":[0.0063530686,0.00052445836,0.0010948406,0.0035736694,0.00044842524,0.0018873152,0.0015436397,0.0015148773,0.0025383085],"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":[0.00046997517,0.00032315232,0.0024995399,0.00019383305,0.0001563855,0.00039836188,0.000078309364,0.058757532,0.012434726,0.0042304075,0.00914118,0.9113167],"study_design_scores_gemma":[0.000042697255,0.000096036594,0.00056529813,0.000017482223,0.00005149334,0.00039302403,0.00002367579,0.9867851,0.0045386893,0.003785828,0.0036786248,0.000022018841],"about_ca_topic_score_codex":0.0050408873,"about_ca_topic_score_gemma":0.004438746,"teacher_disagreement_score":0.0050408873,"about_ca_system_score_codex":0.00044150982,"about_ca_system_score_gemma":0.0016900066,"threshold_uncertainty_score":0.011478543},"labels":[],"label_agreement":null},{"id":"W4413817476","doi":"10.22541/au.175382408.89466370/v2","title":"How to go with the flow: flow matching in bioinformatics and computational biology","year":2025,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute; Vector Institute","funders":"National Energy Research Scientific Computing Center; U.S. Department of Energy","keywords":"Flow (mathematics); Matching (statistics); Computer science; Computational biology; Data science; Biology; Bioinformatics; Medicine; Physics; Mechanics","score_opus":0.009479196476580895,"score_gpt":0.2472564379104022,"score_spread":0.23777724143382128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413817476","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018069935,0.0068066893,0.9784282,0.00963722,0.00046544475,0.000045760444,0.00019640886,0.0005702754,0.0020430011],"genre_scores_gemma":[0.13015488,0.021658735,0.8311853,0.0060727666,0.0024238515,0.00046824067,0.0010567228,0.0010724986,0.0059070433],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971654,0.0010800333,0.0001885494,0.00078465283,0.00062849914,0.00015288065],"domain_scores_gemma":[0.992262,0.0053216373,0.000430111,0.00092604366,0.00068316766,0.00037701306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006646396,0.0010512116,0.0018491248,0.002803532,0.0017048969,0.0054151425,0.0030000098,0.0041958275,0.0056025083],"category_scores_gemma":[0.023482386,0.0010115837,0.0018607918,0.0034999745,0.007265611,0.017103849,0.0051724133,0.006487074,0.0019232194],"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":[0.00010276522,0.000059709124,0.0012610231,0.00043222637,0.00011060315,0.0001170477,0.00039073784,0.050180893,0.0011509461,0.70579755,0.02067707,0.21971937],"study_design_scores_gemma":[0.00001790285,0.000017169337,0.00017126565,0.00013096089,0.000016835134,0.000078055695,0.00005445976,0.11164608,0.00055512413,0.8666073,0.020667192,0.00003760564],"about_ca_topic_score_codex":0.0042801406,"about_ca_topic_score_gemma":0.002117088,"teacher_disagreement_score":0.006646396,"about_ca_system_score_codex":0.0017794416,"about_ca_system_score_gemma":0.0027545923,"threshold_uncertainty_score":0.035149932},"labels":[],"label_agreement":null},{"id":"W4413863055","doi":"10.35490/ec3.2025.438","title":"GPT-powered Multi-agent System for Facility Management: Knowledge Graph-based Data Integration","year":2025,"lang":"en","type":"article","venue":"Computing in construction","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hudbay Minerals (Canada)","funders":"","keywords":"Computer science; Data integration; Data management; Graph; Knowledge management; Systems engineering; Database; Engineering; Theoretical computer science","score_opus":0.0534441709826027,"score_gpt":0.3254745874622914,"score_spread":0.27203041647968873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413863055","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036199618,0.000104748855,0.90163904,0.0005733041,0.000073135765,0.0004239061,0.0013047531,0.051812284,0.00786919],"genre_scores_gemma":[0.49772042,0.00017949495,0.49181646,0.0003588035,0.000036072986,0.0004298491,0.0031915205,0.0011296474,0.0051376903],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99958795,0.00009125581,0.00003567078,0.00011479647,0.00013823612,0.00003215004],"domain_scores_gemma":[0.999173,0.00027733977,0.000065765125,0.0002489467,0.00015007603,0.0000848177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074622774,0.00048556412,0.00040768445,0.0008594614,0.00045372298,0.0014742286,0.0016179633,0.0006048757,0.0034743818],"category_scores_gemma":[0.0024893545,0.00027416594,0.00044490382,0.0007908345,0.00040442613,0.001594858,0.0017918105,0.0008468937,0.0012779953],"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":[0.00096550403,0.0008769223,0.008829627,0.0006376786,0.00028206856,0.0017562313,0.001507592,0.23337944,0.04409595,0.027879998,0.046169773,0.6336193],"study_design_scores_gemma":[0.00008908901,0.000107717344,0.0015173756,0.000029140638,0.00005591266,0.00020653574,0.0001343254,0.94070923,0.013129112,0.014259035,0.029717565,0.000044935656],"about_ca_topic_score_codex":0.005994227,"about_ca_topic_score_gemma":0.005871923,"teacher_disagreement_score":0.005994227,"about_ca_system_score_codex":0.0006150209,"about_ca_system_score_gemma":0.0012999455,"threshold_uncertainty_score":0.011918664},"labels":[],"label_agreement":null},{"id":"W4413956551","doi":"10.29284/iisae.1.2.2025.23-30","title":"Optimized Information Integration in Data Mining Using Ensemble Classification","year":2025,"lang":"en","type":"article","venue":"Innovations in Intelligent Systems and Advanced Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Data mining; Information retrieval; Artificial intelligence","score_opus":0.04827922096538739,"score_gpt":0.3067864241097575,"score_spread":0.2585072031443701,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413956551","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013026932,0.0001243849,0.98593175,0.000059333674,0.0000117977315,0.00003200985,0.000024968083,0.00033111311,0.00045775017],"genre_scores_gemma":[0.45188212,0.0002410665,0.54602575,0.00011034945,0.00006551845,0.000190203,0.00032911476,0.00015949273,0.0009964689],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970208,0.0009295456,0.00023221782,0.00045717746,0.0011588568,0.0002013912],"domain_scores_gemma":[0.9955094,0.00246864,0.00030037874,0.00069865095,0.000920451,0.000102519094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004611872,0.0007673659,0.0013252225,0.0019752702,0.0007084423,0.0017940857,0.0015991147,0.001022909,0.0009440122],"category_scores_gemma":[0.012630335,0.0005002431,0.0011738815,0.0019287686,0.0007591177,0.0033481077,0.0026145072,0.0013515082,0.00051483733],"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":[0.00016875943,0.00015625644,0.003575001,0.00012097682,0.00020573023,0.00014515738,0.0003476159,0.49194685,0.011283986,0.02128444,0.00118437,0.4695808],"study_design_scores_gemma":[0.0000055897062,0.000041262218,0.0003914113,0.000013077157,0.000026532118,0.000029039655,0.000026358175,0.9739604,0.0048845154,0.019884309,0.00072521943,0.000012251473],"about_ca_topic_score_codex":0.0014037932,"about_ca_topic_score_gemma":0.0013980956,"teacher_disagreement_score":0.004611872,"about_ca_system_score_codex":0.0006764557,"about_ca_system_score_gemma":0.0011280768,"threshold_uncertainty_score":0.024390161},"labels":[],"label_agreement":null},{"id":"W4414031611","doi":"10.1613/jair.1.18144","title":"Optimal Decision Trees for Interpretable and Constrained Clustering","year":2025,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"University of Toronto; Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institute for Advanced Research","keywords":"Cluster analysis; Computer science; Artificial intelligence; Decision tree; Machine learning; Data mining","score_opus":0.11335411472548461,"score_gpt":0.44265946752776775,"score_spread":0.3293053528022831,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414031611","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007387942,0.00021795885,0.99013513,0.00031681356,0.000030761355,0.00007468793,0.00021943485,0.00020702099,0.0014102783],"genre_scores_gemma":[0.19404201,0.00039695812,0.8015698,0.0003095106,0.00008040686,0.000402727,0.0013561266,0.00021407138,0.0016283805],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965425,0.0016806775,0.00020905971,0.000582343,0.0007716624,0.00021361021],"domain_scores_gemma":[0.99294734,0.005130474,0.0004094226,0.00056191016,0.0007754375,0.00017543757],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034899602,0.0012067845,0.0014222147,0.0015971609,0.0010065017,0.0019297143,0.0017910218,0.0019643726,0.004510456],"category_scores_gemma":[0.017435728,0.000644221,0.0015129591,0.0025637385,0.0016074813,0.0027375186,0.0019482096,0.003010674,0.0008240878],"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":[0.00015798013,0.00011639341,0.0010321887,0.00031271073,0.000071543756,0.00016733515,0.00037738896,0.718653,0.0020995827,0.15269397,0.006573679,0.11774423],"study_design_scores_gemma":[0.000021837333,0.0000281003,0.000111847075,0.000035538913,0.000011303601,0.00003728117,0.00004762426,0.8680327,0.0005904954,0.12946802,0.0016042776,0.000010877225],"about_ca_topic_score_codex":0.0024362528,"about_ca_topic_score_gemma":0.004326637,"teacher_disagreement_score":0.004510456,"about_ca_system_score_codex":0.0017877257,"about_ca_system_score_gemma":0.0022916857,"threshold_uncertainty_score":0.018456876},"labels":[],"label_agreement":null},{"id":"W4414231634","doi":"10.1109/sera65747.2025.11154502","title":"Mining Patterns for Maximal Coverage in Time Series","year":2025,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Identification (biology); Time series; Series (stratigraphy); Set (abstract data type); Variety (cybernetics); Constraint (computer-aided design); Focus (optics); Key (lock); Solver; State (computer science)","score_opus":0.011289818123375631,"score_gpt":0.25601865039703287,"score_spread":0.24472883227365724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414231634","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12639357,0.00075807347,0.86625725,0.0007350367,0.00003948277,0.00027458536,0.0024403222,0.0015223504,0.0015794546],"genre_scores_gemma":[0.539639,0.00059050194,0.45011556,0.00022442601,0.000101543636,0.00071595714,0.0072354567,0.0003819556,0.0009956408],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974922,0.00048085742,0.0002851488,0.0006395176,0.000872497,0.00022984942],"domain_scores_gemma":[0.9893566,0.007749068,0.0009937953,0.0006959754,0.0009881164,0.00021654257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019730201,0.0013422295,0.0015927107,0.0032771572,0.0006954667,0.0015240569,0.00131421,0.0014364526,0.0025117456],"category_scores_gemma":[0.02407427,0.00083933154,0.0021607783,0.003299559,0.000773696,0.0027644706,0.0017371402,0.0015394042,0.0006590491],"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":[0.0005298223,0.000642444,0.04567415,0.0016879737,0.00064702757,0.0024103548,0.0018016208,0.48092943,0.02461979,0.03327265,0.0119271595,0.39585763],"study_design_scores_gemma":[0.000033410324,0.00010857938,0.002072677,0.00007798641,0.000048881648,0.00034244586,0.00020786977,0.95540035,0.0037100252,0.036086917,0.0018895495,0.000021304973],"about_ca_topic_score_codex":0.0029093218,"about_ca_topic_score_gemma":0.003234836,"teacher_disagreement_score":0.0032771572,"about_ca_system_score_codex":0.00053936883,"about_ca_system_score_gemma":0.0014979744,"threshold_uncertainty_score":0.010434449},"labels":[],"label_agreement":null},{"id":"W4414404425","doi":"10.22541/au.175382408.89466370/v3","title":"How to go with the flow: flow matching in bioinformatics and computational biology","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute; Vector Institute","funders":"National Energy Research Scientific Computing Center; U.S. Department of Energy; Lawrence Berkeley National Laboratory; National Institutes of Health; National Science Foundation","keywords":"Task (project management); State (computer science); Matching (statistics); Systems biology; Computational model; Modelling biological systems; Computational genomics","score_opus":0.015549306668332367,"score_gpt":0.26205823287515195,"score_spread":0.24650892620681958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414404425","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018069935,0.0068066893,0.9784282,0.00963722,0.00046544475,0.000045760444,0.00019640886,0.0005702754,0.0020430011],"genre_scores_gemma":[0.13015488,0.021658735,0.8311853,0.0060727666,0.0024238515,0.00046824067,0.0010567228,0.0010724986,0.0059070433],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971654,0.0010800333,0.0001885494,0.00078465283,0.00062849914,0.00015288065],"domain_scores_gemma":[0.992262,0.0053216373,0.000430111,0.00092604366,0.00068316766,0.00037701306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006646396,0.0010512116,0.0018491248,0.002803532,0.0017048969,0.0054151425,0.0030000098,0.0041958275,0.0056025083],"category_scores_gemma":[0.023482386,0.0010115837,0.0018607918,0.0034999745,0.007265611,0.017103849,0.0051724133,0.006487074,0.0019232194],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010276522,0.000059709124,0.0012610231,0.00043222637,0.00011060315,0.0001170477,0.00039073784,0.050180893,0.0011509461,0.70579755,0.02067707,0.21971937],"study_design_scores_gemma":[0.00001790285,0.000017169337,0.00017126565,0.00013096089,0.000016835134,0.000078055695,0.00005445976,0.11164608,0.00055512413,0.8666073,0.020667192,0.00003760564],"about_ca_topic_score_codex":0.0042801406,"about_ca_topic_score_gemma":0.002117088,"teacher_disagreement_score":0.006646396,"about_ca_system_score_codex":0.0017794416,"about_ca_system_score_gemma":0.0027545923,"threshold_uncertainty_score":0.035149932},"labels":[],"label_agreement":null},{"id":"W4416210151","doi":"10.23977/acss.2025.090319","title":"A Review of Research on Pruning Strategies in Maximum Frequent Itemset Mining Algorithms","year":2025,"lang":"","type":"review","venue":"Advances in Computer Signals and Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Pruning; Enumeration; Process (computing); Efficient algorithm; Space (punctuation); Order (exchange)","score_opus":0.11356534971579027,"score_gpt":0.43745782679711154,"score_spread":0.3238924770813213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416210151","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00080318097,0.9734302,0.020651001,0.0006100863,0.0005001863,0.000046155423,0.00010507957,0.0000836814,0.0037703165],"genre_scores_gemma":[0.005350799,0.9665005,0.025683613,0.00036620302,0.00068169314,0.00007595515,0.0003009447,0.00002459048,0.0010156641],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99804026,0.0003973287,0.00031993736,0.00035521467,0.0007870575,0.000100267745],"domain_scores_gemma":[0.99393576,0.0039537293,0.0002994892,0.00019470375,0.0015266499,0.00008960426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029844518,0.0013986769,0.0017655293,0.0060950425,0.0007003052,0.001930416,0.002070408,0.0015575702,0.0027864021],"category_scores_gemma":[0.007440121,0.00091677526,0.0012968143,0.012559797,0.0007278752,0.004253872,0.00075630925,0.0019919616,0.002834219],"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":[0.000077064564,0.00010020467,0.0006960739,0.0136116715,0.00013385601,0.00017304042,0.00013505685,0.0026783934,0.0011896859,0.017428955,0.018604282,0.9451717],"study_design_scores_gemma":[0.00005031595,0.00035216368,0.0027504738,0.011562912,0.00059337675,0.003040271,0.00028610427,0.008105225,0.0030644771,0.032186087,0.937858,0.00015066602],"about_ca_topic_score_codex":0.0016066962,"about_ca_topic_score_gemma":0.0014783252,"teacher_disagreement_score":0.0060950425,"about_ca_system_score_codex":0.0010941045,"about_ca_system_score_gemma":0.002201691,"threshold_uncertainty_score":0.015783489},"labels":[],"label_agreement":null},{"id":"W48920344","doi":"","title":"Knowledge Discovery and Interestingness Measures: A Survey","year":2012,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Knowledge extraction; Computer science; Ranking (information retrieval); Data mining; Data science; Representation (politics); Information retrieval","score_opus":0.08284764621487632,"score_gpt":0.3122887665810429,"score_spread":0.22944112036616654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W48920344","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021332566,0.65052515,0.2980987,0.0052332003,0.0007402408,0.00031423048,0.0017666003,0.0005486892,0.02144063],"genre_scores_gemma":[0.22191207,0.461575,0.30059975,0.001587585,0.0056841164,0.0009515314,0.0034430758,0.00029848947,0.003948383],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9888453,0.0023583106,0.001314074,0.0017450267,0.005433477,0.00030378797],"domain_scores_gemma":[0.94298685,0.047769263,0.003004191,0.0020313517,0.0035924353,0.0006158946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010583732,0.0021053797,0.0040186727,0.015213799,0.0012732962,0.0060157785,0.002840017,0.0025096938,0.0025316568],"category_scores_gemma":[0.03301667,0.00072167144,0.0016987191,0.01959477,0.0035954658,0.012918064,0.00197119,0.0029563732,0.0010889169],"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":[0.00017034516,0.0003365746,0.014212912,0.0054130545,0.0003500857,0.00023199197,0.0003863748,0.012777497,0.0011413917,0.19522718,0.010998228,0.7587544],"study_design_scores_gemma":[0.00008190672,0.00068820635,0.012748777,0.0030308494,0.0005514907,0.003135612,0.00090448523,0.09221947,0.004680452,0.6876865,0.19397832,0.00029394316],"about_ca_topic_score_codex":0.0009893384,"about_ca_topic_score_gemma":0.0006202172,"teacher_disagreement_score":0.015213799,"about_ca_system_score_codex":0.0022834723,"about_ca_system_score_gemma":0.0018801328,"threshold_uncertainty_score":0.055972755},"labels":[],"label_agreement":null},{"id":"W51487941","doi":"10.1007/978-3-642-21043-3_43","title":"COSINE: A Vertical Group Difference Approach to Contrast Set Mining","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Contrast (vision); Computer science; Group (periodic table); Set (abstract data type); Trigonometric functions; Algorithm; Artificial intelligence; Mathematics; Geometry; Programming language","score_opus":0.03398937478566339,"score_gpt":0.24866948160778735,"score_spread":0.21468010682212396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W51487941","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011036637,0.00058379857,0.9811763,0.0001407404,0.00022074758,0.00024351873,0.0012379659,0.0038263411,0.0015338995],"genre_scores_gemma":[0.06982351,0.0002725262,0.9231027,0.00010884483,0.00017085331,0.00032394906,0.0032956419,0.0006420811,0.0022598938],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99635446,0.00088253664,0.00033853741,0.0006460056,0.0015700106,0.00020850282],"domain_scores_gemma":[0.99630415,0.0016715699,0.000190919,0.00079179666,0.00088820053,0.00015344708],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032781542,0.0010030675,0.0022122767,0.004957317,0.0011450273,0.0025595569,0.003635232,0.0012699323,0.005531494],"category_scores_gemma":[0.011805647,0.00061879714,0.0016847638,0.0069739367,0.00077492004,0.002658412,0.00270441,0.0017865296,0.0022085265],"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":[0.000876994,0.0003931492,0.003357347,0.00042646646,0.0004378754,0.00013226658,0.00024776626,0.016087826,0.012484864,0.02078519,0.020045256,0.92472506],"study_design_scores_gemma":[0.00023377349,0.000542145,0.004814716,0.000092159506,0.0002627822,0.00064604887,0.0003881394,0.84380686,0.022942077,0.085675135,0.04045195,0.00014422077],"about_ca_topic_score_codex":0.002897726,"about_ca_topic_score_gemma":0.003472654,"teacher_disagreement_score":0.005531494,"about_ca_system_score_codex":0.0006916295,"about_ca_system_score_gemma":0.0014878602,"threshold_uncertainty_score":0.01850468},"labels":[],"label_agreement":null},{"id":"W53285091","doi":"10.5220/0002292601520159","title":"EXPLORATIVE DATA MINING FOR THE SIZING OF POPULATION GROUPS","year":2009,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Sizing; Computer science; Population; Data science; Data mining; Chemistry; Environmental health; Medicine","score_opus":0.11384232517895784,"score_gpt":0.33662998904150687,"score_spread":0.22278766386254903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W53285091","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26477793,0.0018937724,0.67418057,0.007716753,0.0022423079,0.0018437767,0.017352829,0.005869348,0.024122722],"genre_scores_gemma":[0.7339459,0.0006637876,0.23966826,0.00027448012,0.0006754603,0.0010548357,0.008624883,0.00044694895,0.014645496],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99570316,0.00113898,0.00036163,0.0008146035,0.0017851009,0.00019652017],"domain_scores_gemma":[0.96538,0.018168123,0.0030271122,0.00536557,0.0070303846,0.0010288334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007047169,0.0007419481,0.001552657,0.0049578957,0.0014542491,0.0023180235,0.0025654007,0.0011644019,0.016089637],"category_scores_gemma":[0.056654073,0.00056901504,0.0010329196,0.0041220966,0.0007459053,0.002953479,0.001888111,0.0012039595,0.0062385886],"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":[0.0007740657,0.00024185124,0.07603086,0.0011087969,0.00032057447,0.00059255515,0.0009948361,0.04172547,0.0067826114,0.029510899,0.06978449,0.77213305],"study_design_scores_gemma":[0.0003784815,0.00067166856,0.0521541,0.00059836655,0.00035101455,0.0012490491,0.0021286195,0.6308236,0.031736065,0.17147958,0.108160555,0.00026882748],"about_ca_topic_score_codex":0.00097521895,"about_ca_topic_score_gemma":0.001909686,"teacher_disagreement_score":0.016089637,"about_ca_system_score_codex":0.00062775647,"about_ca_system_score_gemma":0.0019630857,"threshold_uncertainty_score":0.05382526},"labels":[],"label_agreement":null},{"id":"W54192826","doi":"10.1007/978-3-642-32584-7_17","title":"A Fast Algorithm for Frequent Itemset Mining Using Patricia* Structures","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms 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":"Carleton University","funders":"","keywords":"Trie; Tree traversal; Prefix; Computer science; Tree (set theory); Interval tree; Data structure; Data mining; Algorithm; Tree structure; Theoretical computer science; Segment tree; Fractal tree index; Node (physics); Search tree; Binary tree; Mathematics; Search algorithm; Combinatorics; Programming language","score_opus":0.033145127694572694,"score_gpt":0.28004621794085094,"score_spread":0.24690109024627824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W54192826","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01610289,0.00068303576,0.9669142,0.00031435816,0.00014280826,0.00037787753,0.0017036775,0.011994376,0.001766756],"genre_scores_gemma":[0.024905639,0.00015081654,0.9696473,0.000083020605,0.000040140403,0.0003068008,0.0032187917,0.00018955569,0.0014579814],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988619,0.00018677466,0.00015485995,0.00028150322,0.00040879147,0.000106149644],"domain_scores_gemma":[0.9974717,0.0010074258,0.00014457067,0.0005932113,0.00070504163,0.000078072175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012674979,0.0011732063,0.0017233964,0.003736973,0.0017304578,0.0019073935,0.0029762096,0.0013344302,0.00616701],"category_scores_gemma":[0.00635723,0.0013584818,0.0017577668,0.005448355,0.00041769847,0.0031929824,0.0021533843,0.0015713905,0.0058330633],"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":[0.00040597658,0.0002310667,0.0022628047,0.00028594656,0.0001361115,0.00022436798,0.00016577593,0.009404694,0.007690521,0.00778107,0.025388215,0.9460234],"study_design_scores_gemma":[0.00040675834,0.00065161876,0.002810563,0.00013799699,0.00021039699,0.0024141534,0.00026752404,0.8771155,0.023118418,0.049011927,0.04373371,0.00012138836],"about_ca_topic_score_codex":0.002171345,"about_ca_topic_score_gemma":0.0033750918,"teacher_disagreement_score":0.00616701,"about_ca_system_score_codex":0.0005994141,"about_ca_system_score_gemma":0.0020897007,"threshold_uncertainty_score":0.020630777},"labels":[],"label_agreement":null},{"id":"W566444363","doi":"","title":"Feature Model Mining","year":2008,"lang":"en","type":"dissertation","venue":"UWSpace (University of Waterloo)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Waterloo","keywords":"Feature (linguistics); Computer science; Data mining; Artificial intelligence","score_opus":0.01375342100873586,"score_gpt":0.20830159223573078,"score_spread":0.19454817122699491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W566444363","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035737034,0.00089974824,0.9212808,0.0012225168,0.00014768906,0.0011750754,0.01909836,0.008826085,0.011612729],"genre_scores_gemma":[0.29550424,0.00093098957,0.6182085,0.00067531434,0.00009964716,0.0014033237,0.074059136,0.0009418577,0.008176972],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99659306,0.00042107125,0.0003078488,0.0010854279,0.0013186327,0.00027395107],"domain_scores_gemma":[0.99575007,0.0018538776,0.0003267486,0.00077909604,0.0011958431,0.000094380055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016263168,0.002019253,0.001241179,0.0057962914,0.0012426362,0.0025838015,0.004593081,0.001747919,0.008559217],"category_scores_gemma":[0.010702675,0.0008306867,0.0046301754,0.0038759026,0.00069562776,0.0033913334,0.0023242922,0.0017425797,0.004712879],"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":[0.00034357584,0.00057637173,0.023899628,0.0011491339,0.0005544261,0.0025428652,0.00040482642,0.09501775,0.010459816,0.032154094,0.06912165,0.7637758],"study_design_scores_gemma":[0.0001169973,0.0002356564,0.0047816043,0.0002596872,0.0003150494,0.0024750985,0.0005381577,0.84577245,0.014098847,0.07010542,0.06120501,0.00009605212],"about_ca_topic_score_codex":0.007091921,"about_ca_topic_score_gemma":0.010389368,"teacher_disagreement_score":0.008559217,"about_ca_system_score_codex":0.0015430305,"about_ca_system_score_gemma":0.0027799439,"threshold_uncertainty_score":0.028633475},"labels":[],"label_agreement":null},{"id":"W568873395","doi":"","title":"Measures and adjustments of pattern frequency distributions","year":2010,"lang":"en","type":"dissertation","venue":"Spectrum Research Repository (Concordia University)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Overfitting; Set (abstract data type); Data mining; Computer science; Anomaly (physics); Measure (data warehouse); Raw data; Mode (computer interface); Anomaly detection; Artificial intelligence; Algorithm","score_opus":0.026047128931165047,"score_gpt":0.2819933123888944,"score_spread":0.25594618345772935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W568873395","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041962232,0.00024659783,0.9521196,0.0004486696,0.000038055892,0.00016212414,0.00017647418,0.00036358702,0.0044826693],"genre_scores_gemma":[0.56532353,0.00039379857,0.4307517,0.00017984831,0.00008608355,0.0004663447,0.00033403918,0.0001461939,0.0023185755],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9931629,0.002490403,0.0005204401,0.0015367998,0.0020404132,0.00024903877],"domain_scores_gemma":[0.9747877,0.015081953,0.0030730807,0.0041485084,0.0026050394,0.00030362295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008716228,0.0006349355,0.000566809,0.0023705077,0.0005904498,0.002745526,0.001788221,0.0009947063,0.002552779],"category_scores_gemma":[0.07037065,0.0005493679,0.0007839212,0.0021190997,0.0021085388,0.0048782453,0.0020189572,0.0017688551,0.0006270506],"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":[0.00020398079,0.00013540167,0.022365546,0.0003414114,0.00011741194,0.00023034237,0.0017340367,0.0773329,0.0133620165,0.45610672,0.0021665592,0.4259037],"study_design_scores_gemma":[0.000049321865,0.0003037156,0.021727903,0.0001939212,0.000067775996,0.0008480265,0.0010287871,0.46942624,0.014123229,0.47671965,0.0153685035,0.00014285387],"about_ca_topic_score_codex":0.000936496,"about_ca_topic_score_gemma":0.0007508901,"teacher_disagreement_score":0.008716228,"about_ca_system_score_codex":0.0014404175,"about_ca_system_score_gemma":0.0009530717,"threshold_uncertainty_score":0.046096385},"labels":[],"label_agreement":null},{"id":"W581782849","doi":"","title":"KDD-2002 : proceedings of the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, July 23-26, 2002, Edmonton, Alberta, Canada","year":2002,"lang":"en","type":"book","venue":"Association for Computing Machinery eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":100,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Knowledge extraction; Library science; Data science; Computer science; Data mining","score_opus":0.029901217336675535,"score_gpt":0.2639706669744599,"score_spread":0.2340694496377844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W581782849","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007424499,0.10811759,0.4838264,0.022062173,0.04675171,0.0011940525,0.08200086,0.050375033,0.1982477],"genre_scores_gemma":[0.010602748,0.0699491,0.20760936,0.0023814726,0.0021975643,0.00026426095,0.126025,0.005600837,0.5753698],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99869907,0.00008661584,0.00007589416,0.00013878949,0.00092572265,0.0000738688],"domain_scores_gemma":[0.9952773,0.0008329603,0.00009364255,0.00046802658,0.0026403738,0.00068778073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023472235,0.0017716222,0.0037950343,0.0033603387,0.0012535935,0.0071300417,0.003231635,0.001143912,0.057648238],"category_scores_gemma":[0.004729233,0.0015386766,0.0009960035,0.0060052145,0.00082512276,0.003450743,0.0018340886,0.0029798397,0.05350459],"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":[0.000047799185,0.000058483634,0.00020821534,0.00025486466,0.000027455413,0.00003970719,0.000035661556,0.000705264,0.00039197144,0.0017894369,0.8704868,0.12595421],"study_design_scores_gemma":[0.000048300524,0.000042523196,0.0015298198,0.00018097753,0.0000679174,0.00030861478,0.0000699142,0.008900159,0.0018643937,0.008235243,0.9787049,0.000047324178],"about_ca_topic_score_codex":0.05551121,"about_ca_topic_score_gemma":0.14474364,"teacher_disagreement_score":0.057648238,"about_ca_system_score_codex":0.0020890725,"about_ca_system_score_gemma":0.00789278,"threshold_uncertainty_score":0.19285256},"labels":[],"label_agreement":null},{"id":"W59565414","doi":"","title":"Graceful Lobsters Obtained by Component Moving of Diameter Four Trees.","year":2006,"lang":"en","type":"article","venue":"Ars Combinatoria","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Component (thermodynamics); Mathematics; Fishery; Biology; Physics","score_opus":0.01015828359208773,"score_gpt":0.2166958584855118,"score_spread":0.20653757489342406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W59565414","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57505125,0.0011565398,0.33666053,0.0011812878,0.00044479987,0.00013626597,0.0012441846,0.0024478897,0.081677176],"genre_scores_gemma":[0.8564597,0.0005498849,0.085660696,0.00033121152,0.00010027236,0.00010609158,0.001616002,0.00073179323,0.054444306],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99971646,0.00003039976,0.000015772783,0.000073044255,0.000058417074,0.00010600618],"domain_scores_gemma":[0.99890363,0.0003330593,0.00012205624,0.00035103102,0.00007602373,0.00021423193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035971915,0.00053486694,0.0008321342,0.0012440515,0.0014575364,0.0020002571,0.0014883421,0.0009310109,0.010753297],"category_scores_gemma":[0.0032986104,0.00038948614,0.00076069526,0.0010178142,0.0012496897,0.0019233045,0.0026428367,0.0013555379,0.002637918],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007664023,0.00013547363,0.004108812,0.00025632925,0.00010410221,0.0009930296,0.00088180235,0.031085212,0.017131638,0.8093121,0.022958744,0.11226641],"study_design_scores_gemma":[0.00012445587,0.00012893748,0.0026702764,0.00011102192,0.00014512724,0.0008197903,0.00051218993,0.12629493,0.01396813,0.80781734,0.047332507,0.000075213226],"about_ca_topic_score_codex":0.0018334987,"about_ca_topic_score_gemma":0.002889911,"teacher_disagreement_score":0.010753297,"about_ca_system_score_codex":0.00076832547,"about_ca_system_score_gemma":0.00059355085,"threshold_uncertainty_score":0.03597337},"labels":[],"label_agreement":null},{"id":"W62188274","doi":"10.5555/1760894.1760939","title":"Position coded pre-order linked WAP-tree for web log sequential pattern mining","year":2003,"lang":"en","type":"article","venue":"Knowledge Discovery and Data Mining","topic":"Data Mining Algorithms and Applications","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":"University of Windsor","funders":"","keywords":"Prefix; Computer science; Tree (set theory); Trie; Fractal tree index; Web log analysis software; Suffix tree; Preorder; Suffix; Node (physics); Segment tree; Binary tree; Tree structure; Data mining; Interval tree; Data structure; Algorithm; Web server; Mathematics; World Wide Web; The Internet; Combinatorics; Discrete mathematics; Operating system","score_opus":0.0458814739950354,"score_gpt":0.3150776749332564,"score_spread":0.269196200938221,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W62188274","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07068932,0.00028229764,0.91159624,0.0002493764,0.00015846733,0.0003560605,0.004157714,0.009114987,0.003395488],"genre_scores_gemma":[0.30465794,0.00015300456,0.6833202,0.00010162737,0.000044712353,0.00036152318,0.0067467424,0.00033955774,0.0042746365],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994723,0.00008494771,0.0000660927,0.000089997586,0.00021933482,0.000067329194],"domain_scores_gemma":[0.997686,0.0007625698,0.000111289286,0.0006402308,0.0006874198,0.000112405425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068259786,0.0003256922,0.000583097,0.0020634297,0.00089054496,0.0011508848,0.0014009298,0.0008913896,0.0044374163],"category_scores_gemma":[0.0060026087,0.00031098444,0.00050084665,0.0028287114,0.00037452826,0.0013433556,0.0007991502,0.00096869835,0.0015443166],"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":[0.0015050324,0.00051534513,0.0077465116,0.00038683828,0.000073421295,0.0006871356,0.00031700506,0.0726266,0.018625591,0.02821346,0.018453307,0.8508497],"study_design_scores_gemma":[0.0000984909,0.00024716018,0.0021356973,0.00006914465,0.000059712915,0.00034145828,0.0001510062,0.9245768,0.015539753,0.0432299,0.013506464,0.00004440171],"about_ca_topic_score_codex":0.0050740107,"about_ca_topic_score_gemma":0.008183492,"teacher_disagreement_score":0.0050740107,"about_ca_system_score_codex":0.00049100525,"about_ca_system_score_gemma":0.0018199207,"threshold_uncertainty_score":0.014844656},"labels":[],"label_agreement":null},{"id":"W6925235043","doi":"10.17605/osf.io/s84k7","title":"Materials","year":2023,"lang":"en","type":"article","venue":"OSF Preprints (OSF Preprints)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"","score_opus":0.021913892893062656,"score_gpt":0.27278774369968023,"score_spread":0.25087385080661756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6925235043","genre_codex":"dataset","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05077769,0.00346381,0.033796262,0.0058392542,0.0056741,0.11743597,0.7071209,0.0018218268,0.07407005],"genre_scores_gemma":[0.059808344,0.0033702953,0.04395679,0.0124251675,0.0012698006,0.45812377,0.32646218,0.0013587453,0.09322487],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984675,0.0004908712,0.00033937735,0.00029963662,0.00027354705,0.00012909377],"domain_scores_gemma":[0.99101526,0.0031992951,0.0005193035,0.0015200303,0.003111646,0.0006344217],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0036327455,0.0017172563,0.002389185,0.0023983947,0.0026312247,0.0025895517,0.0021502667,0.002141546,0.31513318],"category_scores_gemma":[0.024563352,0.00097324286,0.00083201367,0.0024149294,0.0009865382,0.0018325669,0.0013797107,0.0032334446,0.12831318],"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":[0.00628047,0.00447963,0.015530151,0.003894771,0.00010184686,0.0011899254,0.0014476966,0.0011682598,0.0011523252,0.011016531,0.8236249,0.13011353],"study_design_scores_gemma":[0.004752684,0.0026544987,0.036771763,0.002740462,0.00019010172,0.0022494257,0.002727137,0.0013487721,0.0016186532,0.028685007,0.915917,0.0003444409],"about_ca_topic_score_codex":0.00468152,"about_ca_topic_score_gemma":0.005358669,"teacher_disagreement_score":0.6848668,"about_ca_system_score_codex":0.0013254276,"about_ca_system_score_gemma":0.004091348,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W6925265789","doi":"10.17611/dp/12743730","title":"Magnetotelluric Transfer Functions","year":2016,"lang":"en","type":"other","venue":"NSF Seismological Facility for the Advancement of Geoscience (SAGE)","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":"Geological Survey of Canada","funders":"","keywords":"Magnetotellurics; Transfer function; Field (mathematics); Transfer (computing); Interpretation (philosophy)","score_opus":0.02441277411199986,"score_gpt":0.27099905239161864,"score_spread":0.2465862782796188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6925265789","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00545163,0.0011274955,0.90326756,0.00063310313,0.000791148,0.00010095644,0.0049971133,0.008048608,0.07558242],"genre_scores_gemma":[0.24515495,0.0041459636,0.34113,0.0010511569,0.0012205326,0.00042476328,0.022357501,0.0038768402,0.38063833],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9995604,0.000049684106,0.000016237487,0.00011218857,0.0002070116,0.0000545618],"domain_scores_gemma":[0.99962986,0.00004540771,0.000033823726,0.0001291706,0.0001392418,0.000022471182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046395246,0.0013945517,0.0006073837,0.0013795432,0.00050415425,0.00200688,0.0012331282,0.0011814856,0.04769711],"category_scores_gemma":[0.0018981093,0.00029213497,0.000625237,0.002115357,0.0003631626,0.0014686413,0.0011465177,0.0010826957,0.06998242],"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":[0.00021371,0.00007581994,0.0011316936,0.00027063902,0.000054896467,0.0001690382,0.0000911093,0.01840202,0.03517404,0.075721525,0.1125114,0.7561841],"study_design_scores_gemma":[0.00007989078,0.00015579595,0.00485515,0.00018388717,0.000087227745,0.0010443418,0.00012460123,0.1712866,0.09802282,0.075076245,0.64888966,0.00019373298],"about_ca_topic_score_codex":0.0010066566,"about_ca_topic_score_gemma":0.0010698278,"teacher_disagreement_score":0.04769711,"about_ca_system_score_codex":0.00042007916,"about_ca_system_score_gemma":0.00076844374,"threshold_uncertainty_score":0.1595627},"labels":[],"label_agreement":null},{"id":"W6929585171","doi":"10.5061/dryad.1c14t","title":"Data from: Patterns of selection and allele diversity of class I and class II major histocompatibility loci across the species range of sockeye salmon (Oncorhynchus nerka)","year":2013,"lang":"en","type":"dataset","venue":"Data Archiving and Networked Services (DANS)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Fisheries and Oceans Canada","funders":"","keywords":"Major histocompatibility complex; Balancing selection; Allele; Population; Microsatellite; Loss of heterozygosity; Selection (genetic algorithm); MHC class I; Genetic diversity","score_opus":0.03850458521007763,"score_gpt":0.26913354096441944,"score_spread":0.2306289557543418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6929585171","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.057580758,0.00027985955,0.000797713,0.00034961983,0.00009634587,0.000104095176,0.939236,0.000548405,0.0010071265],"genre_scores_gemma":[0.027381994,0.00009964863,0.0020835085,0.0000751178,0.000010621263,0.00020948063,0.9693066,0.000039487473,0.000793572],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993079,0.000085993684,0.00013793536,0.00018145135,0.00018840804,0.000098243756],"domain_scores_gemma":[0.9984877,0.0003492117,0.00020749269,0.00027777773,0.0005272929,0.00015047795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013035261,0.0008109679,0.00061296957,0.0020258587,0.0005336206,0.00068248046,0.0010746568,0.00087796757,0.0028448934],"category_scores_gemma":[0.00379947,0.00025913972,0.00069402665,0.0024742126,0.0003573309,0.0003769107,0.0010261328,0.00080172904,0.002603516],"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":[0.0011040353,0.00053876935,0.18126833,0.0027052104,0.0006587732,0.0006678439,0.00060592074,0.0060709463,0.005101851,0.001511325,0.74408275,0.055684287],"study_design_scores_gemma":[0.00079241063,0.00019425174,0.47524294,0.00042851636,0.00031488974,0.0008978899,0.0009649419,0.011513369,0.008366505,0.0016953906,0.4994373,0.00015159421],"about_ca_topic_score_codex":0.025993219,"about_ca_topic_score_gemma":0.05709868,"teacher_disagreement_score":0.025993219,"about_ca_system_score_codex":0.0009899711,"about_ca_system_score_gemma":0.0017054309,"threshold_uncertainty_score":0.051683843},"labels":[],"label_agreement":null},{"id":"W6930196570","doi":"10.5281/zenodo.1202349","title":"Accounting For The Simpson-Yule Effect In Standardized Mortality Ratios","year":2018,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Standardized mortality ratio; Mortality rate; Logistic regression; Multivariate statistics; Multivariate analysis; Medical care; MEDLINE","score_opus":0.03587352609681505,"score_gpt":0.2930629283659117,"score_spread":0.25718940226909665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930196570","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08815321,0.0017344943,0.9025344,0.0013538499,0.0007552043,0.00024749292,0.00093184604,0.000965165,0.003324281],"genre_scores_gemma":[0.8103222,0.0013260624,0.18029694,0.00070737593,0.0010208532,0.00041434218,0.0013561583,0.00041252183,0.0041435896],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97216356,0.017516674,0.0018798946,0.0031759338,0.004213635,0.0010502739],"domain_scores_gemma":[0.84221095,0.11722308,0.010406304,0.022410527,0.006488728,0.0012604839],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.055571742,0.0014911885,0.0017099273,0.003484676,0.0008078584,0.0028954481,0.0030641071,0.0012350989,0.0024727972],"category_scores_gemma":[0.19796546,0.00064372,0.0024257484,0.004674906,0.0026547117,0.003804733,0.0034697508,0.0032039417,0.00090080156],"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":[0.00045160452,0.00018104527,0.40741935,0.00036887333,0.0025003685,0.0008121047,0.001308294,0.16843367,0.0008807497,0.19111073,0.013403835,0.21312943],"study_design_scores_gemma":[0.0001343183,0.00048846763,0.07369078,0.00025442298,0.00048362126,0.000814282,0.0004873288,0.63254875,0.002130101,0.27210867,0.016653895,0.00020535426],"about_ca_topic_score_codex":0.012244135,"about_ca_topic_score_gemma":0.009961434,"teacher_disagreement_score":0.055571742,"about_ca_system_score_codex":0.0013915588,"about_ca_system_score_gemma":0.0028582881,"threshold_uncertainty_score":0.293895},"labels":[],"label_agreement":null},{"id":"W6930333033","doi":"10.5281/zenodo.12257009","title":"Karl kopinski sketchbook pdf","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Paraphernalia; Ceylon; Limiting; TSG101","score_opus":0.026325241347465958,"score_gpt":0.24863942655428478,"score_spread":0.22231418520681884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930333033","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00039723451,0.0017904943,0.0055652508,0.0010596699,0.0025824814,0.00030365033,0.0056441827,0.009145351,0.9735117],"genre_scores_gemma":[0.0012213076,0.0014450727,0.0017115506,0.00043575102,0.00035047758,0.00010443553,0.0025364333,0.00176757,0.9904275],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995509,0.000024045008,0.000024678686,0.00006821565,0.00028222258,0.000049858118],"domain_scores_gemma":[0.99883527,0.00018171871,0.00004108047,0.0001483145,0.0005501893,0.00024346307],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00039416656,0.0017405122,0.0010210824,0.0020096286,0.0010481516,0.004834599,0.0020268345,0.0014594683,0.88384914],"category_scores_gemma":[0.0030395973,0.0006476794,0.00088740536,0.0017452976,0.0005083546,0.0048850714,0.0027282399,0.0021677199,0.84866077],"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":[0.000032994423,0.000027403497,0.000025981579,0.00019766546,0.0000018439473,0.00007767127,0.0000272664,0.00011830337,0.00061472657,0.0021043234,0.91605324,0.08071861],"study_design_scores_gemma":[0.0000068515383,0.00001053438,0.00010273442,0.00006443847,0.0000017956988,0.00010365132,0.000028369006,0.00005882844,0.00023451462,0.0007194094,0.99866164,0.0000072276866],"about_ca_topic_score_codex":0.0016817525,"about_ca_topic_score_gemma":0.002781794,"teacher_disagreement_score":0.116150856,"about_ca_system_score_codex":0.00087829307,"about_ca_system_score_gemma":0.0012818414,"threshold_uncertainty_score":0.16567504},"labels":[],"label_agreement":null},{"id":"W6931553911","doi":"10.5683/sp3/frwmzu","title":"Kananaskis Lakes Alberta / British Columbia. 1:50,000. Map Sheet 082J11, ed. 1, 1967","year":2022,"lang":"en","type":"dataset","venue":"Borealis","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Georeference; General partnership; Raster graphics; Geographic information system; Natural (archaeology); Aerial photography; Government (linguistics); Orthophoto","score_opus":0.009547603913462393,"score_gpt":0.23038512295739028,"score_spread":0.22083751904392787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931553911","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015082116,0.00012633792,0.00003161706,0.00003604396,0.000022262677,0.0000063501648,0.9965821,0.00014173257,0.0029027935],"genre_scores_gemma":[0.00070549635,0.00026528625,0.00018680141,0.000021540474,0.0000058193764,0.000024967761,0.9916221,0.00006807834,0.0070999055],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994759,0.000019754367,0.00003472973,0.00012305398,0.00022368721,0.00012302675],"domain_scores_gemma":[0.99843305,0.00008818327,0.00008557496,0.00015474609,0.0010599743,0.00017846377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036986067,0.0022652186,0.0013177376,0.005550038,0.0014951882,0.0034787797,0.0018030968,0.0006165037,0.087592],"category_scores_gemma":[0.0020799716,0.00077714754,0.0004881758,0.024676638,0.00048023384,0.00085674925,0.0007995352,0.0013229846,0.0922558],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018306768,0.0000043802947,0.000597222,0.00016475683,0.0000059135414,0.000015525287,0.000018608398,0.00009227172,0.000029133687,0.00017393459,0.99512875,0.003751148],"study_design_scores_gemma":[0.000036495174,0.0000030888052,0.0095947245,0.00018804504,0.00001015376,0.000031059426,0.00018314918,0.00015335207,0.00012533992,0.00026899757,0.98938787,0.000017708184],"about_ca_topic_score_codex":0.9221479,"about_ca_topic_score_gemma":0.96009517,"teacher_disagreement_score":0.087592,"about_ca_system_score_codex":0.008016436,"about_ca_system_score_gemma":0.016429802,"threshold_uncertainty_score":0.29302448},"labels":[],"label_agreement":null},{"id":"W6931564120","doi":"10.5281/zenodo.7007914","title":"QuadraticModels.jl","year":2019,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Quadratic equation; Mathematical model; Process (computing); Component (thermodynamics); Quadratic programming","score_opus":0.03428813210180064,"score_gpt":0.24825642583406288,"score_spread":0.21396829373226223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931564120","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00058170554,0.0011716986,0.8361883,0.00061998784,0.00043153434,0.00017864029,0.04632184,0.08726535,0.027240884],"genre_scores_gemma":[0.03250947,0.0026213266,0.7054368,0.0012377511,0.0004140506,0.0024521993,0.10753931,0.05849149,0.08929768],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992372,0.00021976056,0.000068184556,0.00014502392,0.00025078925,0.00007918996],"domain_scores_gemma":[0.99844944,0.00093503535,0.000077187586,0.00021150924,0.00027627655,0.000050536346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015358676,0.0024752107,0.0014535001,0.0012275985,0.00059580896,0.0019808013,0.0028959573,0.0018006593,0.21557398],"category_scores_gemma":[0.0053219474,0.0018447355,0.002836654,0.0013353836,0.00042553034,0.0021547023,0.0021240443,0.0030487669,0.10142083],"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":[0.00009805823,0.00011726602,0.0005600017,0.0016762489,0.00023810682,0.00012703227,0.00009673354,0.06323533,0.001495795,0.102134794,0.6889174,0.14130324],"study_design_scores_gemma":[0.00022288896,0.000058659083,0.0003303101,0.000256515,0.000086941385,0.00017235371,0.000029373361,0.3383418,0.0025632158,0.10850046,0.5493616,0.0000758197],"about_ca_topic_score_codex":0.0075964313,"about_ca_topic_score_gemma":0.01614813,"teacher_disagreement_score":0.21557398,"about_ca_system_score_codex":0.00079013885,"about_ca_system_score_gemma":0.0017213868,"threshold_uncertainty_score":0.72116685},"labels":[],"label_agreement":null},{"id":"W6931611271","doi":"10.5281/zenodo.7963043","title":"Oxneriaria supertegens S. Y. Kondr. & Lőkös Acta Bot. Hung.","year":2023,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Hymenium; Ascocarp; Thallus; Ascospore; Conidium","score_opus":0.043697193110206,"score_gpt":0.2550730601575655,"score_spread":0.21137586704735947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931611271","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09231395,0.18220334,0.0045498814,0.0036941343,0.0024081555,0.00048424088,0.004743398,0.0008156212,0.7087873],"genre_scores_gemma":[0.48433933,0.08842468,0.006558349,0.001792928,0.00092219486,0.00031550133,0.00636593,0.00021909145,0.4110619],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9998596,0.000014093951,0.000016132079,0.000047227222,0.000040454448,0.000022597113],"domain_scores_gemma":[0.99989486,0.000015688653,0.000031259377,0.000011861134,0.000031625925,0.000014744958],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014863511,0.0008185484,0.0003968303,0.0012211093,0.0007491444,0.00064037985,0.0003468536,0.00044054058,0.037190218],"category_scores_gemma":[0.00023119853,0.00025340245,0.00021920053,0.00078621454,0.00036629263,0.0010374162,0.0012428749,0.0006776765,0.013356361],"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":[0.00017219175,0.000096526535,0.005084142,0.0012574202,0.000026176385,0.0019679228,0.0008286603,0.0003313311,0.014958702,0.0071779797,0.058761105,0.90933776],"study_design_scores_gemma":[0.00003231016,0.00007593891,0.051896818,0.00045444787,0.00003456978,0.0025683248,0.00078200095,0.00014812086,0.0014024149,0.0011786919,0.9414122,0.0000142134395],"about_ca_topic_score_codex":0.01529213,"about_ca_topic_score_gemma":0.017963644,"teacher_disagreement_score":0.037190218,"about_ca_system_score_codex":0.000864813,"about_ca_system_score_gemma":0.0005830464,"threshold_uncertainty_score":0.12441373},"labels":[],"label_agreement":null},{"id":"W6958293152","doi":"10.6084/m9.figshare.26628508","title":"Additional file 3 of Artificial Intelligence based wrapper for high dimensional feature selection","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Feature selection; Selection (genetic algorithm); Feature (linguistics); High dimensional; Pattern recognition (psychology)","score_opus":0.03317930514029781,"score_gpt":0.265185943691474,"score_spread":0.2320066385511762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958293152","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003001207,0.000026214306,0.0012268455,0.00007600705,0.00004663704,0.0000957822,0.9940502,0.00301606,0.0011621012],"genre_scores_gemma":[0.0065586716,0.00009114818,0.010187218,0.0003604372,0.00009720567,0.0013390366,0.96696055,0.0061132195,0.0082925465],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989262,0.00017353575,0.00014962698,0.00030914624,0.0002829614,0.000158444],"domain_scores_gemma":[0.9825487,0.012932175,0.0005539851,0.001285894,0.0022758988,0.0004032923],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0020931321,0.0017571076,0.0015842618,0.0024318935,0.0009812677,0.002404527,0.0028234127,0.0013075056,0.85050005],"category_scores_gemma":[0.026555648,0.000786756,0.001741127,0.00401108,0.00037306652,0.0020703825,0.0013932687,0.0013021103,0.28726816],"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":[0.00053863454,0.00009493322,0.0014768091,0.0021222248,0.00008175658,0.000088553505,0.000047459256,0.0006289426,0.00033334628,0.0006423451,0.9834135,0.010531567],"study_design_scores_gemma":[0.005387104,0.0004503649,0.015158183,0.0016721378,0.00037145417,0.00050732173,0.00033345123,0.007485359,0.0053409706,0.020041604,0.94299054,0.00026159402],"about_ca_topic_score_codex":0.004572592,"about_ca_topic_score_gemma":0.009342858,"teacher_disagreement_score":0.85050005,"about_ca_system_score_codex":0.0008831788,"about_ca_system_score_gemma":0.0017740568,"threshold_uncertainty_score":0.21324354},"labels":[],"label_agreement":null},{"id":"W6963518645","doi":"10.22044/jadm.2023.13034.2448","title":"Parallel Incremental Mining of Regular-Frequent Patterns from WSNs Big Data","year":2023,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Canada West","funders":"","keywords":"Big data; Data stream mining; Volume (thermodynamics); Wireless sensor network; Tree (set theory); Decision tree; Map reduce; Data structure","score_opus":0.4590513499596829,"score_gpt":0.5405339547208408,"score_spread":0.08148260476115787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6963518645","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41087887,0.00064340123,0.57866436,0.00048788192,0.0001740086,0.0003637423,0.0019155766,0.0040957006,0.0027764048],"genre_scores_gemma":[0.6541014,0.0003379916,0.33968106,0.00006464807,0.000057500663,0.00022311063,0.0043274025,0.00011966432,0.001087247],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903214,0.00014048934,0.000087338456,0.00023893644,0.00039594562,0.00010516306],"domain_scores_gemma":[0.9978205,0.00069706695,0.00019963915,0.0005342218,0.0006306181,0.00011797991],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010799982,0.00054413854,0.00071609963,0.0014093904,0.0005699198,0.00092358404,0.001311092,0.00025169525,0.0004928605],"category_scores_gemma":[0.0043288334,0.00036199912,0.00085576944,0.002021958,0.00030700225,0.0012726961,0.0008582703,0.0005004179,0.00027964998],"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":[0.0011972556,0.00058510556,0.04302199,0.0006195909,0.00044645785,0.0011374176,0.0006886937,0.22231366,0.03991555,0.0049086604,0.009107823,0.6760577],"study_design_scores_gemma":[0.0000477006,0.0001753142,0.008178025,0.000014003491,0.00007690574,0.00046595332,0.0002469282,0.96687615,0.01271117,0.007622062,0.003567109,0.00001861156],"about_ca_topic_score_codex":0.0036731584,"about_ca_topic_score_gemma":0.0075351894,"teacher_disagreement_score":0.0036731584,"about_ca_system_score_codex":0.00032308517,"about_ca_system_score_gemma":0.0012072375,"threshold_uncertainty_score":0.0073035955},"labels":[],"label_agreement":null},{"id":"W6976563761","doi":"10.60692/y4znf-a9281","title":"Machine Learning and Knowledge Discovery in Databases","year":2020,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; University of Alberta; Dalhousie University","funders":"","keywords":"Publication; Knowledge extraction; Analytics; Set (abstract data type); Training set","score_opus":0.04763776876880155,"score_gpt":0.24156517286069246,"score_spread":0.1939274040918909,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6976563761","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013329858,0.24019241,0.5343326,0.08298692,0.01710884,0.0008175579,0.0029250106,0.0025788583,0.10572794],"genre_scores_gemma":[0.17503354,0.14563918,0.4759372,0.016626157,0.016782168,0.0012917549,0.011096125,0.0012326553,0.15636116],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98613507,0.0057933824,0.0009476682,0.0024635158,0.003980198,0.00068017974],"domain_scores_gemma":[0.98410183,0.010216657,0.00045602166,0.0020031831,0.0020827998,0.0011394976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019401703,0.0008649135,0.0020544913,0.0039426344,0.001335925,0.008730053,0.0025839624,0.002934222,0.016298028],"category_scores_gemma":[0.017283477,0.0009295617,0.0016294493,0.007197205,0.0027676537,0.008688031,0.005648517,0.0056954366,0.007785408],"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":[0.00017173674,0.00019489593,0.0011229754,0.0017093649,0.00020409575,0.00019638818,0.00067638065,0.0036360277,0.0021002572,0.1818111,0.20230167,0.60587525],"study_design_scores_gemma":[0.000038697035,0.00013150538,0.0011575359,0.00079438614,0.00005015071,0.00032750546,0.00039471049,0.012970751,0.0021019962,0.21385098,0.76812565,0.000056150653],"about_ca_topic_score_codex":0.0009011753,"about_ca_topic_score_gemma":0.0010111867,"teacher_disagreement_score":0.019401703,"about_ca_system_score_codex":0.0031518165,"about_ca_system_score_gemma":0.0036732506,"threshold_uncertainty_score":0.10260719},"labels":[],"label_agreement":null},{"id":"W6977360176","doi":"10.6084/m9.figshare.26793778.v1","title":"Additional file 1 of Level of patient contact and Impact of Event scores among Canadian healthcare providers during the COVID-19 pandemic","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Pandemic; Event (particle physics); Health care; Event data; Coronavirus disease 2019 (COVID-19); MEDLINE","score_opus":0.08254469509803984,"score_gpt":0.3125930652158131,"score_spread":0.23004837011777324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977360176","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020373585,0.000009598873,0.000048399535,0.000057385554,0.000012717725,0.000042847812,0.9989197,0.00004785478,0.0006577934],"genre_scores_gemma":[0.019608632,0.00020556567,0.0025846292,0.0006288738,0.00007808131,0.0014699735,0.96287465,0.00029952472,0.012250049],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9989588,0.000108976674,0.00016364783,0.00021962894,0.0002816388,0.0002672939],"domain_scores_gemma":[0.9689006,0.019530268,0.0017964885,0.0014862496,0.0069201547,0.001366101],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015229644,0.00095456204,0.0013572179,0.0039565046,0.002292546,0.0021895969,0.002138083,0.001237753,0.8225664],"category_scores_gemma":[0.0431997,0.00065735163,0.001496223,0.0076042283,0.0004634422,0.0015067023,0.0011662112,0.0010918352,0.06748393],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020704594,0.00008089167,0.007130107,0.0013449496,0.00005740911,0.00004148864,0.000082747676,0.00047515775,0.000025293986,0.00055940915,0.9823262,0.007669305],"study_design_scores_gemma":[0.005404941,0.00029971,0.21284464,0.006657196,0.00045818105,0.00056409434,0.0018565643,0.004103117,0.0005187872,0.0086810775,0.7582513,0.0003603342],"about_ca_topic_score_codex":0.61315465,"about_ca_topic_score_gemma":0.6999891,"teacher_disagreement_score":0.8225664,"about_ca_system_score_codex":0.0066962885,"about_ca_system_score_gemma":0.017900722,"threshold_uncertainty_score":0.7782471},"labels":[],"label_agreement":null},{"id":"W6990196959","doi":"","title":"Data mining with relational database management systems","year":2005,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Research Council Canada; McGill University","keywords":"Relational database; Scalability; Field (mathematics); SQL; Raw data; Database model; Data modeling; Database design; Data stream mining","score_opus":0.03962733426962285,"score_gpt":0.2661730680136683,"score_spread":0.22654573374404546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6990196959","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036652496,0.0018280342,0.93582106,0.0014828742,0.000281055,0.0005188764,0.0029299287,0.042120658,0.011352325],"genre_scores_gemma":[0.08176186,0.0031590846,0.8868948,0.0012094813,0.0004965948,0.00090818864,0.010324432,0.0029326745,0.012312856],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9901782,0.0022938796,0.0018540042,0.0017841342,0.003514769,0.00037501773],"domain_scores_gemma":[0.9902417,0.0022704187,0.00062914984,0.0047710207,0.0016806514,0.00040707912],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007498424,0.0009870623,0.0011475141,0.0026209722,0.0012002965,0.007539388,0.0043280134,0.0012426836,0.01021899],"category_scores_gemma":[0.021220926,0.0015687048,0.0016487805,0.0055972748,0.00074857887,0.010359001,0.0043913545,0.002832888,0.01265847],"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":[0.00071273674,0.00036400565,0.0048518814,0.0012594914,0.00043668432,0.0008413864,0.0012287933,0.016138842,0.015199304,0.16740827,0.14159328,0.6499654],"study_design_scores_gemma":[0.00028416977,0.00020706092,0.0016167657,0.00038446113,0.00027802892,0.0014332825,0.0004974675,0.13088694,0.030416625,0.15416938,0.6796306,0.00019522638],"about_ca_topic_score_codex":0.0023948823,"about_ca_topic_score_gemma":0.0014161059,"teacher_disagreement_score":0.01021899,"about_ca_system_score_codex":0.0010174051,"about_ca_system_score_gemma":0.0024500182,"threshold_uncertainty_score":0.039655924},"labels":[],"label_agreement":null},{"id":"W6995881666","doi":"","title":"Preface of Special Issue on Rules Systems","year":2005,"lang":"en","type":"article","venue":"NPARC","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Conjunction (astronomy); Ontology; Semantics of Business Vocabulary and Business Rules; Semantics (computer science); Description logic; Knowledge-based systems","score_opus":0.016038289566094172,"score_gpt":0.254647858775898,"score_spread":0.23860956920980383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6995881666","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000653484,0.052224718,0.024474973,0.06652129,0.6825266,0.00039018542,0.00207363,0.0007954155,0.17033975],"genre_scores_gemma":[0.006342506,0.062410463,0.011215599,0.020033635,0.55086684,0.0003900648,0.0057396595,0.0012954385,0.34170574],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99795794,0.00031560578,0.00024846572,0.00046481725,0.0008854415,0.00012762661],"domain_scores_gemma":[0.9889465,0.003688845,0.00034826915,0.000998,0.005112819,0.0009055228],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033398785,0.0014206439,0.0015550088,0.004300952,0.0019131947,0.006356862,0.0018772777,0.0031799357,0.11936459],"category_scores_gemma":[0.014035872,0.0006571202,0.0016340883,0.0041181543,0.0012522367,0.0077695926,0.0022035597,0.006822824,0.07271309],"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":[0.000020920017,0.000033661294,0.000072231865,0.00023836915,0.00001097786,0.000044652403,0.000030051368,0.00020293874,0.00014464259,0.007943801,0.93628186,0.054975852],"study_design_scores_gemma":[0.000008461758,0.00002221566,0.00025209787,0.00025727434,0.000009630528,0.000095399635,0.000026072305,0.00027632745,0.00011429019,0.010750597,0.98817724,0.0000104579685],"about_ca_topic_score_codex":0.0021081835,"about_ca_topic_score_gemma":0.002075714,"teacher_disagreement_score":0.11936459,"about_ca_system_score_codex":0.0021808397,"about_ca_system_score_gemma":0.001968717,"threshold_uncertainty_score":0.39931434},"labels":[],"label_agreement":null},{"id":"W6997356821","doi":"","title":"XAR-Miner: Efficient Association Rules Mining for XML Data","year":2005,"lang":"en","type":"article","venue":"University of Southern Queensland ePrints (University of Southern Queensland)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"XML database; XML validation; XML; Streaming XML; Efficient XML Interchange; Document Structure Description; Constraint (computer-aided design); XML Schema Editor; Association rule learning","score_opus":0.020379133090292236,"score_gpt":0.21014560174108357,"score_spread":0.18976646865079133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6997356821","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006268787,0.0008017683,0.98111606,0.00024272385,0.000046224395,0.0002783578,0.0015924354,0.009256886,0.0003968543],"genre_scores_gemma":[0.022280017,0.00035499834,0.9736897,0.00012352108,0.000040133946,0.00022296137,0.002566058,0.00016722525,0.0005555346],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99591285,0.0012219755,0.0005744433,0.0007303513,0.0014240236,0.00013617914],"domain_scores_gemma":[0.9935389,0.004173765,0.00062758854,0.000902054,0.00060151704,0.00015607796],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063276803,0.0011846641,0.001915662,0.0047140224,0.0008669726,0.0022841773,0.0033600961,0.0011781652,0.0025455456],"category_scores_gemma":[0.013961046,0.0010409753,0.0017545385,0.0034073342,0.0006195847,0.003852508,0.0020762526,0.0015776774,0.002352643],"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":[0.0008281956,0.0005952307,0.01340889,0.0018021096,0.0010312862,0.0011263685,0.0005050419,0.048408117,0.018608475,0.016434541,0.026607117,0.87064475],"study_design_scores_gemma":[0.00041479946,0.00050568423,0.0038055663,0.00029000506,0.00034895126,0.003014542,0.00026950438,0.8573623,0.032252673,0.045491517,0.05608624,0.00015824017],"about_ca_topic_score_codex":0.0013305892,"about_ca_topic_score_gemma":0.0022169456,"teacher_disagreement_score":0.0063276803,"about_ca_system_score_codex":0.00028852778,"about_ca_system_score_gemma":0.0013642943,"threshold_uncertainty_score":0.033464313},"labels":[],"label_agreement":null},{"id":"W7001833021","doi":"","title":"Lazy Learning for Impoving Ranking of Decision Trees","year":2006,"lang":"en","type":"article","venue":"NPARC","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Ranking (information retrieval); Estimator; Decision tree; Benchmark (surveying); Sample (material); Set (abstract data type); Suite; Tree (set theory)","score_opus":0.01156430468284741,"score_gpt":0.2547930073656242,"score_spread":0.2432287026827768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7001833021","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017399885,0.00035574686,0.97966444,0.00015645109,0.000032374242,0.00008156841,0.00009714547,0.0015824458,0.0006299288],"genre_scores_gemma":[0.47509122,0.00026550665,0.5210211,0.00029147955,0.00015000733,0.00034067628,0.00073031115,0.0003074911,0.001802304],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946854,0.0024659194,0.00037801388,0.0008509962,0.0012883145,0.00033133445],"domain_scores_gemma":[0.9816395,0.012647437,0.001135131,0.0021460992,0.0019920033,0.00043987142],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0073449533,0.0011401897,0.0022169899,0.0024945566,0.00090019277,0.0020222438,0.0028088388,0.0014612909,0.0021367325],"category_scores_gemma":[0.027480094,0.0006289347,0.0010403576,0.0022903515,0.0009728951,0.004069185,0.0017528773,0.0024211188,0.0011512438],"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":[0.00032760925,0.00023606824,0.0053487835,0.00021453484,0.00013443659,0.00011782286,0.00016308783,0.50191,0.002258632,0.02291982,0.004797809,0.46157143],"study_design_scores_gemma":[0.000015381229,0.00004525566,0.00015411882,0.00000774623,0.000011622037,0.000021253563,0.00000802051,0.9841159,0.0007144319,0.014427884,0.00047196014,0.0000064124742],"about_ca_topic_score_codex":0.0039540925,"about_ca_topic_score_gemma":0.0058405087,"teacher_disagreement_score":0.0073449533,"about_ca_system_score_codex":0.0017729003,"about_ca_system_score_gemma":0.0022051707,"threshold_uncertainty_score":0.038844228},"labels":[],"label_agreement":null},{"id":"W7018287819","doi":"","title":"Data mining using relational database management system","year":2005,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Relational database; Confidentiality; The Internet; Data collection","score_opus":0.059567602156264256,"score_gpt":0.2882674354092295,"score_spread":0.22869983325296525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7018287819","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043163903,0.0046123317,0.818916,0.003579794,0.00047308442,0.0021040305,0.028561104,0.08228248,0.016307311],"genre_scores_gemma":[0.16109851,0.0031477115,0.79394644,0.0006814464,0.00019759238,0.0011459652,0.030739602,0.00078601815,0.008256668],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99636495,0.00063803326,0.0008489559,0.0007243142,0.0012900898,0.0001335131],"domain_scores_gemma":[0.99626833,0.0010529229,0.00040985396,0.0011063747,0.00096002204,0.00020252397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037581176,0.0005611757,0.0013960765,0.0039286967,0.0010398186,0.0043676975,0.0023042087,0.000789694,0.0050904443],"category_scores_gemma":[0.009676227,0.0005938952,0.0010599217,0.005128746,0.00023136346,0.0037661295,0.001581558,0.0011477672,0.005489977],"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":[0.0006097256,0.00044075656,0.012026241,0.0011148913,0.00036244065,0.0012472499,0.000706599,0.008654848,0.016411986,0.016568003,0.07923127,0.86262596],"study_design_scores_gemma":[0.00042807957,0.0005704307,0.012206604,0.0005419654,0.00063422276,0.0044526584,0.0015305503,0.31426302,0.075922035,0.055737063,0.53340113,0.00031224135],"about_ca_topic_score_codex":0.0024956674,"about_ca_topic_score_gemma":0.0019177756,"teacher_disagreement_score":0.0050904443,"about_ca_system_score_codex":0.0007164461,"about_ca_system_score_gemma":0.002616566,"threshold_uncertainty_score":0.01987505},"labels":[],"label_agreement":null},{"id":"W7020245921","doi":"","title":"KDD 2002 proceedings of the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining ; July 23 - 26, 2002, Edmonton, Alberta, Canada","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Knowledge extraction; Association rule learning; Web mining; Software mining","score_opus":0.05070213935716859,"score_gpt":0.26773727995577107,"score_spread":0.2170351405986025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7020245921","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040591177,0.05310766,0.48617053,0.058023587,0.11664539,0.002852918,0.077673964,0.04125614,0.12367854],"genre_scores_gemma":[0.07320253,0.04219769,0.30967838,0.0068711475,0.004609108,0.000743746,0.17457588,0.00477813,0.3833433],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99624795,0.00059713563,0.00030820418,0.00038027804,0.0021932402,0.00027311288],"domain_scores_gemma":[0.98726416,0.0013538221,0.000224487,0.0015479828,0.0077989753,0.0018105228],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0070515783,0.0020488075,0.0059617576,0.0036231691,0.003266111,0.013309879,0.004559941,0.0023667016,0.026832731],"category_scores_gemma":[0.011395904,0.0015705454,0.0018584719,0.0038166943,0.0017815001,0.0041980096,0.002987964,0.004826193,0.030263513],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026697916,0.00038670682,0.001286229,0.00033768933,0.00019236573,0.0001545593,0.00016289522,0.0022691756,0.0007546745,0.002946091,0.88009,0.11115259],"study_design_scores_gemma":[0.00025086303,0.00012931634,0.005747563,0.000279589,0.00039331536,0.00047998628,0.00054037094,0.032883953,0.0062594223,0.013033899,0.93985415,0.00014754059],"about_ca_topic_score_codex":0.13639826,"about_ca_topic_score_gemma":0.23504245,"teacher_disagreement_score":0.86360174,"about_ca_system_score_codex":0.0039247526,"about_ca_system_score_gemma":0.015454597,"threshold_uncertainty_score":0.27120864},"labels":[],"label_agreement":null},{"id":"W7023982934","doi":"","title":"A Practical Data-Driven Framework for Parallel Data Mining","year":2005,"lang":"en","type":"article","venue":"NPARC","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Rewriting; Java; Quality (philosophy); Data stream mining; Sequential Pattern Mining; Data quality","score_opus":0.15529997970426682,"score_gpt":0.3942524661878142,"score_spread":0.23895248648354736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7023982934","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00040329172,0.00003798125,0.9973061,0.0000995885,0.000015886848,0.00008885656,0.000053903073,0.001699138,0.00029530688],"genre_scores_gemma":[0.009852089,0.00007073302,0.98878586,0.00006374772,0.000023017323,0.00034895923,0.00024162664,0.00018582215,0.00042816033],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99575585,0.0012099419,0.00041541527,0.0008696511,0.0015683785,0.00018066229],"domain_scores_gemma":[0.99549246,0.0017727783,0.00021837813,0.0013700054,0.00097151636,0.00017482151],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00688426,0.0010746113,0.0012073634,0.0014836737,0.0014604963,0.0027391827,0.0039782776,0.0010221082,0.0033622764],"category_scores_gemma":[0.012206418,0.0011776322,0.0022136664,0.0026394527,0.0015442417,0.0030157964,0.0031017899,0.0029909315,0.0022637954],"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":[0.0004924321,0.0004866101,0.0029782313,0.0009564133,0.00027926164,0.0008048992,0.00073513296,0.13892451,0.015604749,0.3077832,0.028932946,0.5020217],"study_design_scores_gemma":[0.00015926918,0.00008901024,0.00029975965,0.000066114946,0.00006365772,0.00047342532,0.000089871646,0.7455883,0.009911787,0.18680878,0.05638976,0.000060286933],"about_ca_topic_score_codex":0.003433511,"about_ca_topic_score_gemma":0.0050626732,"teacher_disagreement_score":0.00688426,"about_ca_system_score_codex":0.0010627238,"about_ca_system_score_gemma":0.003924344,"threshold_uncertainty_score":0.036407888},"labels":[],"label_agreement":null},{"id":"W7030296701","doi":"","title":"Mémoire présenté à la Commission de l'éducation chargée de faire le point sur l'enseignement collégial québécois, 28 septembre 1992 : le rôle de la philosophie dans le renouveau du DEC /","year":2015,"lang":"fr","type":"other","venue":"Bibliothèque et Archives nationales du Québec (Québec government)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Dysgeusia; Liquation; Diafiltration; Emperipolesis; Triacetin; Durvalumab","score_opus":0.01406909223012202,"score_gpt":0.23992883769908227,"score_spread":0.22585974546896026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7030296701","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020018345,0.04137847,0.0033521766,0.54000366,0.04056632,0.0004413189,0.011748989,0.0005879845,0.3419027],"genre_scores_gemma":[0.05955521,0.0074556735,0.0023204428,0.026264837,0.002444909,0.00016610323,0.0016815932,0.00023800065,0.8998733],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974541,0.000241285,0.0000798145,0.0002130269,0.0012689915,0.0007428763],"domain_scores_gemma":[0.99417144,0.00060678594,0.0001867224,0.00024951,0.0035164075,0.0012690488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037237727,0.00053319073,0.00048052185,0.0026065973,0.010717989,0.009583759,0.0012554636,0.005329202,0.039521527],"category_scores_gemma":[0.007372648,0.00044051072,0.00055510254,0.0029985714,0.002872782,0.0022582673,0.0020319982,0.005071676,0.0043542837],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026690614,0.000025635089,0.0010496245,0.00007819338,0.0000074011214,0.00009699672,0.0014772185,0.00010613883,0.00017728168,0.01684224,0.9644073,0.015705176],"study_design_scores_gemma":[0.000008057643,0.0000046033038,0.00677605,0.00011003598,0.000006271643,0.000022880282,0.0010478745,0.000050436596,0.00017264184,0.0006112577,0.99117106,0.000018807674],"about_ca_topic_score_codex":0.9559284,"about_ca_topic_score_gemma":0.97672117,"teacher_disagreement_score":0.94327015,"about_ca_system_score_codex":0.056729864,"about_ca_system_score_gemma":0.12291277,"threshold_uncertainty_score":0.41160595},"labels":[],"label_agreement":null},{"id":"W7033199827","doi":"","title":"Planification de la récolte et allocation des produits aux usines","year":2010,"lang":"fr","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Divestment; Processor scheduling; Round table","score_opus":0.007694751838175574,"score_gpt":0.18537683130078444,"score_spread":0.17768207946260886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7033199827","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11563105,0.0015739861,0.79629016,0.00083289505,0.00018032403,0.0009721209,0.0010507976,0.0032399797,0.08022868],"genre_scores_gemma":[0.516351,0.0030399766,0.407688,0.0001562357,0.00003533047,0.00089056895,0.001399283,0.0005626189,0.069877036],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99952006,0.000106956664,0.000020991734,0.00011959459,0.00013861881,0.00009385018],"domain_scores_gemma":[0.9995989,0.00010946745,0.000058522557,0.00006314234,0.00011969165,0.000050288392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008486822,0.0012731828,0.00046998812,0.00072770426,0.0008358,0.0024252855,0.00091867405,0.0008158657,0.011809982],"category_scores_gemma":[0.0008259703,0.00052390026,0.0010092922,0.0006436909,0.0007209332,0.0014538864,0.00091969734,0.0013688789,0.002255921],"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":[0.0004048751,0.00025290705,0.004429717,0.00076333625,0.000063373,0.000439121,0.00084014813,0.5895809,0.0676196,0.038008485,0.006065307,0.29153228],"study_design_scores_gemma":[0.000098423254,0.0009936974,0.010392227,0.00035781605,0.00010568895,0.0002832294,0.0018878386,0.6891474,0.07190105,0.030816654,0.19385315,0.00016284114],"about_ca_topic_score_codex":0.023845216,"about_ca_topic_score_gemma":0.03487937,"teacher_disagreement_score":0.023845216,"about_ca_system_score_codex":0.0021679094,"about_ca_system_score_gemma":0.004888615,"threshold_uncertainty_score":0.047412872},"labels":[],"label_agreement":null},{"id":"W7066661158","doi":"","title":"Higgs search in H$\\\\rightarrow$ZZ/WW decay channels with the CMS detector","year":2009,"lang":"en","type":"other","venue":"CERN Document Server (European Organization for Nuclear Research)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakes Environmental (Canada)","funders":"","keywords":"Higgs boson; Large Hadron Collider; Luminosity; Context (archaeology); Detector; Vector boson","score_opus":0.022144922053229852,"score_gpt":0.2615489368746525,"score_spread":0.23940401482142268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7066661158","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91936964,0.0008678757,0.05613766,0.00045378885,0.00005569274,0.00010241177,0.0057648453,0.0016451098,0.015603002],"genre_scores_gemma":[0.9523594,0.00020412158,0.039416917,0.00009662281,0.000037549522,0.000050108618,0.00499269,0.00010761572,0.0027350823],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993781,0.00021704948,0.00002716211,0.00009832461,0.00018714048,0.00009219089],"domain_scores_gemma":[0.99944764,0.0002229215,0.00008557618,0.00007579229,0.00009986462,0.00006827975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001745344,0.00054196926,0.00059321575,0.0013919472,0.00045768727,0.0010696806,0.0009924836,0.00039058673,0.003192668],"category_scores_gemma":[0.0010067812,0.00016703889,0.0005075681,0.0023153916,0.00024366574,0.00046646837,0.0008090671,0.00026509783,0.0007840277],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010313532,0.0012860047,0.25286448,0.0006915551,0.0010665003,0.0051057213,0.00036129498,0.04459698,0.34038338,0.090818696,0.02764154,0.22487026],"study_design_scores_gemma":[0.0009784872,0.0010347657,0.06320529,0.00003839903,0.00042582906,0.0025240416,0.00028691426,0.4666253,0.4173699,0.030100185,0.01724002,0.00017084678],"about_ca_topic_score_codex":0.001896084,"about_ca_topic_score_gemma":0.001995589,"teacher_disagreement_score":0.003192668,"about_ca_system_score_codex":0.0003431593,"about_ca_system_score_gemma":0.00076016993,"threshold_uncertainty_score":0.010680497},"labels":[],"label_agreement":null},{"id":"W7094047021","doi":"","title":"Agents and data mining interaction 6th International Workshop on Agents and Data Mining Interaction, ADMI 2010, Toronto, On, Canada, May 11, 2010 : revised selected papers","year":2010,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Field (mathematics); Association rule learning; Knowledge extraction; Sequential Pattern Mining; Data stream mining","score_opus":0.061025462426246437,"score_gpt":0.3368174663631325,"score_spread":0.275792003936886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7094047021","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014553291,0.03783427,0.8464701,0.029022595,0.014645614,0.00050191995,0.0020247505,0.0034388585,0.051508605],"genre_scores_gemma":[0.13667212,0.03378239,0.50839984,0.003344731,0.0056771236,0.0005532251,0.010495809,0.0018853312,0.29918936],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99708384,0.00096000003,0.00026347357,0.00050277787,0.0009352859,0.00025458532],"domain_scores_gemma":[0.99183124,0.0023335812,0.00018298706,0.0011433506,0.0036116717,0.0008971409],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006554623,0.001339181,0.0019660213,0.0016596833,0.0020946057,0.008828321,0.0020517118,0.0017933123,0.01947257],"category_scores_gemma":[0.009568682,0.0011079303,0.0012135613,0.0021509738,0.0014967787,0.0043384833,0.003426084,0.003802274,0.005329348],"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":[0.0006471186,0.00032544223,0.0037226675,0.0008301596,0.00038855654,0.00048296503,0.0015387421,0.011044133,0.0061071804,0.054542463,0.47770202,0.44266862],"study_design_scores_gemma":[0.00010572387,0.00016287135,0.0038645605,0.00041486154,0.0002553802,0.0006103795,0.00094809645,0.06570616,0.008376391,0.0534594,0.86598146,0.00011469018],"about_ca_topic_score_codex":0.028189493,"about_ca_topic_score_gemma":0.059539773,"teacher_disagreement_score":0.028189493,"about_ca_system_score_codex":0.003234035,"about_ca_system_score_gemma":0.006335295,"threshold_uncertainty_score":0.065142214},"labels":[],"label_agreement":null},{"id":"W7097606403","doi":"","title":"Copyright by","year":2005,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Gratitude; Privilege (computing); Quarter (Canadian coin); Advice (programming); Class (philosophy); Work (physics)","score_opus":0.005113597120623605,"score_gpt":0.22407510738826736,"score_spread":0.21896151026764377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7097606403","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006592048,0.0019546621,0.0016961219,0.005066539,0.00470603,0.00014093457,0.003954648,0.0020727008,0.97974914],"genre_scores_gemma":[0.0026627209,0.0017749146,0.0011221893,0.0024376581,0.00060501293,0.00010500301,0.004302575,0.0008786292,0.9861113],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998596,0.000132886,0.00008542461,0.0005575021,0.00043994948,0.00018813867],"domain_scores_gemma":[0.996702,0.0003920811,0.00015840602,0.0011418262,0.0011485855,0.00045712414],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0015560492,0.0011778146,0.0010358967,0.0018332475,0.0017994522,0.008848438,0.0016956086,0.0033501273,0.84330046],"category_scores_gemma":[0.0058264416,0.00051764015,0.0009930482,0.0020459918,0.0014534171,0.004607542,0.0036696224,0.0031301705,0.87092805],"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":[0.00005290343,0.000051793533,0.00057805184,0.00022380064,0.000010351635,0.00012590659,0.000099618745,0.00009299668,0.00065819273,0.009454985,0.8378971,0.15075424],"study_design_scores_gemma":[0.000007352934,0.000010136903,0.00036985328,0.00013307582,0.0000023918906,0.0000942025,0.00004255416,0.00005294274,0.000092850794,0.00091651635,0.99827313,0.000004923484],"about_ca_topic_score_codex":0.0037453333,"about_ca_topic_score_gemma":0.0025410797,"teacher_disagreement_score":0.15669954,"about_ca_system_score_codex":0.0013845466,"about_ca_system_score_gemma":0.0027259674,"threshold_uncertainty_score":0.22351277},"labels":[],"label_agreement":null},{"id":"W7100129246","doi":"","title":"Association Mining without Support Thresholds","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Association rule learning; Database transaction; Probabilistic logic; Association (psychology); Register (sociolinguistics); Affinity analysis","score_opus":0.017070608784517466,"score_gpt":0.2805385695810688,"score_spread":0.2634679607965513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7100129246","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033218093,0.0018244784,0.96008444,0.0014964723,0.00009108778,0.00018990044,0.00061968225,0.0005740209,0.0019018655],"genre_scores_gemma":[0.39026555,0.0019419993,0.6022765,0.00061435293,0.00053150527,0.00044217575,0.0014587994,0.00015283648,0.002316232],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98569643,0.004979771,0.0014413858,0.0028582546,0.004419272,0.0006049072],"domain_scores_gemma":[0.9250701,0.05861814,0.004873005,0.0074662603,0.0032652176,0.0007073144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010853904,0.0010980713,0.0029589564,0.004525374,0.0016735068,0.0047759274,0.0045232824,0.0028067145,0.0030532775],"category_scores_gemma":[0.07122466,0.001214955,0.0017968392,0.009428782,0.001928441,0.010924197,0.0039191456,0.0037359348,0.0017853057],"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":[0.0007533682,0.00045172937,0.030095289,0.0013011177,0.00044986745,0.0013253497,0.0009990248,0.15316232,0.0065510785,0.11445958,0.009052217,0.68139905],"study_design_scores_gemma":[0.000103296436,0.0004441155,0.002472515,0.00019999818,0.00017647407,0.002255285,0.0003314174,0.70893055,0.004527315,0.26849732,0.011980019,0.000081697995],"about_ca_topic_score_codex":0.0010142714,"about_ca_topic_score_gemma":0.001100125,"teacher_disagreement_score":0.010853904,"about_ca_system_score_codex":0.0006086827,"about_ca_system_score_gemma":0.0014405842,"threshold_uncertainty_score":0.057401597},"labels":[],"label_agreement":null},{"id":"W7100724052","doi":"","title":"Improved Intention Discovery with Classified Emotions in A Modified","year":2012,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Permission; Windsor; Legislation; Data collection; Intellectual property","score_opus":0.0287493518005986,"score_gpt":0.25521822825419854,"score_spread":0.22646887645359995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7100724052","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30780226,0.0026566784,0.6415918,0.0020712502,0.0012323889,0.0008284215,0.014995225,0.011896719,0.016925223],"genre_scores_gemma":[0.7196466,0.00045387447,0.23898637,0.000553817,0.0005834506,0.0006485561,0.02175425,0.00037215324,0.01700098],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989384,0.00024468818,0.000070014205,0.0004351738,0.00017956966,0.00013210805],"domain_scores_gemma":[0.99747604,0.0014094044,0.000097277145,0.0004277493,0.0004897276,0.000099713914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015415987,0.0010371375,0.0013579439,0.0021179395,0.0005480502,0.002007904,0.002183861,0.0013515629,0.013161089],"category_scores_gemma":[0.0074342005,0.00041971033,0.002047749,0.0015097405,0.0002939162,0.0014808478,0.0013082263,0.0017291156,0.005694511],"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":[0.003295958,0.0014430365,0.019380152,0.0004941465,0.00074778165,0.0006886634,0.00041736217,0.024560696,0.012179293,0.0043151327,0.032878015,0.89959973],"study_design_scores_gemma":[0.0002781318,0.00046439172,0.012925589,0.000065680215,0.00045259402,0.0003328664,0.00025894414,0.96222067,0.005379307,0.011152132,0.0063852314,0.000084480766],"about_ca_topic_score_codex":0.007766046,"about_ca_topic_score_gemma":0.0106215635,"teacher_disagreement_score":0.013161089,"about_ca_system_score_codex":0.0005623078,"about_ca_system_score_gemma":0.0009842226,"threshold_uncertainty_score":0.044028223},"labels":[],"label_agreement":null},{"id":"W7101129976","doi":"","title":"Match-making in bartering scenarios","year":2005,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Barter; Delegate; Tree (set theory); Representation (politics); Search engine indexing; Control (management); Process (computing)","score_opus":0.014612284097720023,"score_gpt":0.2667090663113607,"score_spread":0.2520967822136407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7101129976","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08816065,0.0006613442,0.8922484,0.00070529425,0.0001298954,0.00027907005,0.00037367677,0.0020345312,0.015407246],"genre_scores_gemma":[0.5883909,0.00049904804,0.4014494,0.00015707054,0.00007001728,0.00012780794,0.00085140235,0.00024358854,0.00821085],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9949196,0.0018635794,0.0004258514,0.0011292611,0.0011794115,0.00048219957],"domain_scores_gemma":[0.9926312,0.0035053357,0.0007676872,0.001820472,0.0006459234,0.0006292802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004820094,0.0007379572,0.0012418405,0.0016730847,0.0021670475,0.0048501207,0.0032744375,0.0033380445,0.0075814663],"category_scores_gemma":[0.013474701,0.00085262395,0.0011485716,0.0023730157,0.001516701,0.011278211,0.0051589184,0.0020070835,0.0025917473],"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":[0.0013850366,0.0005219181,0.0063556326,0.00058689277,0.00019039995,0.00257191,0.0026440884,0.37283716,0.009784114,0.23234019,0.012062924,0.35871977],"study_design_scores_gemma":[0.000054550306,0.00017252531,0.0009796312,0.00007132854,0.0000445654,0.00084018597,0.0010309541,0.8297711,0.006767987,0.13137086,0.028830137,0.000066273],"about_ca_topic_score_codex":0.0025453714,"about_ca_topic_score_gemma":0.0020623186,"teacher_disagreement_score":0.0075814663,"about_ca_system_score_codex":0.0012155761,"about_ca_system_score_gemma":0.001095079,"threshold_uncertainty_score":0.025491416},"labels":[],"label_agreement":null},{"id":"W7116675242","doi":"10.1007/978-3-032-13509-4_15","title":"Profit-Oriented High Utility Sequential Recommendation in Big Dataset with MapReduce","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in social networks","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":"University of Guelph; University of Windsor","funders":"","keywords":"Big data; Terabyte; Petabyte; Focus (optics); Partition (number theory); Recommender system","score_opus":0.022944798297530697,"score_gpt":0.2722641798608832,"score_spread":0.24931938156335248,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7116675242","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059366707,0.001086028,0.9142819,0.0011180418,0.00045035948,0.00032804944,0.0014759137,0.010657523,0.011235357],"genre_scores_gemma":[0.5580354,0.00043530884,0.42576692,0.0003580372,0.000284852,0.00017700548,0.0025042188,0.0005868969,0.011851423],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989121,0.0001812994,0.000054902102,0.00021866859,0.00045183103,0.00018122871],"domain_scores_gemma":[0.9981863,0.0005354813,0.000053237603,0.00068365905,0.00039752517,0.00014383298],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012724688,0.0007620927,0.0013928654,0.0008724926,0.0009891014,0.0015676462,0.0024454657,0.0007051078,0.00491079],"category_scores_gemma":[0.0034095906,0.0005792517,0.00095147034,0.002438233,0.000495637,0.0022718862,0.0015223047,0.0011578569,0.0017540916],"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":[0.001150933,0.00082578236,0.0039406884,0.00032336163,0.00023122906,0.000289972,0.00018317507,0.22653332,0.008294186,0.034177467,0.08065094,0.64339894],"study_design_scores_gemma":[0.000058088324,0.000051397234,0.0004027085,0.000005568149,0.000022268412,0.000075016615,0.00006323548,0.9620208,0.0018934262,0.03263849,0.0027566114,0.000012275873],"about_ca_topic_score_codex":0.013323456,"about_ca_topic_score_gemma":0.026674788,"teacher_disagreement_score":0.013323456,"about_ca_system_score_codex":0.0009286189,"about_ca_system_score_gemma":0.002314242,"threshold_uncertainty_score":0.02649182},"labels":[],"label_agreement":null},{"id":"W7139291034","doi":"","title":"Introduction: Special Issue on Open Source Intelligence and Web Mining","year":2011,"lang":"en","type":"article","venue":"University of Southern Denmark Research Portal (University of Southern Denmark)","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":"University of Calgary","funders":"","keywords":"Open source; Web mining; Web intelligence; The Internet; Data source; Key (lock)","score_opus":0.05620703028843711,"score_gpt":0.2614851913048113,"score_spread":0.2052781610163742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7139291034","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00082828826,0.05764112,0.008733792,0.044983048,0.82578385,0.00015737415,0.0018333616,0.00090137956,0.059137844],"genre_scores_gemma":[0.003240096,0.03800253,0.003414435,0.011471067,0.64153546,0.00012265625,0.0043220753,0.001160625,0.29673108],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99808645,0.00018688774,0.00019654167,0.00038144845,0.0009829015,0.00016575109],"domain_scores_gemma":[0.9916794,0.002139578,0.00059971196,0.0008521618,0.0030790935,0.0016500567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026080704,0.0017437182,0.002513623,0.0070044096,0.0015706859,0.006944367,0.0019443942,0.0032208336,0.10122354],"category_scores_gemma":[0.0066197533,0.000711512,0.0014607281,0.005617604,0.0008815205,0.0070696576,0.0024200699,0.0039141094,0.060558178],"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":[0.0000207151,0.00004031463,0.000111241476,0.00026113258,0.000013050056,0.000038317856,0.000012605054,0.000057676054,0.00021012449,0.0010976148,0.9532474,0.0448898],"study_design_scores_gemma":[0.000007424428,0.000025937637,0.000675092,0.00017334895,0.000015609694,0.00013711187,0.000020393001,0.00017739955,0.00013859163,0.0027533534,0.99586487,0.000010788745],"about_ca_topic_score_codex":0.0010244367,"about_ca_topic_score_gemma":0.0032186513,"teacher_disagreement_score":0.10122354,"about_ca_system_score_codex":0.0012866252,"about_ca_system_score_gemma":0.0019640808,"threshold_uncertainty_score":0.3386265},"labels":[],"label_agreement":null},{"id":"W7165127355","doi":"10.34727/2025/isbn.978-3-85448-084-6_33</div","title":"A Tale of Two Case Studies: A Unified Exploration of Rust Verification with SEABMC","year":2025,"lang":"en","type":"article","venue":"Open MIND","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Waterloo","keywords":"Rust (programming language)","score_opus":0.09953016587427034,"score_gpt":0.3796513863410952,"score_spread":0.28012122046682486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7165127355","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23619886,0.004373691,0.7078974,0.007663022,0.00024380324,0.00068029825,0.00037102628,0.00621097,0.036360867],"genre_scores_gemma":[0.5369309,0.0015757716,0.45305339,0.0012468483,0.000087717985,0.00035548763,0.00033067472,0.0015486926,0.0048705684],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.973625,0.0145218475,0.001072113,0.0020417883,0.0071202503,0.0016189549],"domain_scores_gemma":[0.9574924,0.027732491,0.0014832624,0.009999793,0.002660227,0.0006318632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015977291,0.0012052688,0.001464071,0.004015561,0.001757581,0.0051974067,0.0037749491,0.003608232,0.0034176789],"category_scores_gemma":[0.04311352,0.0016347948,0.002104241,0.0024152477,0.0068694297,0.009357733,0.0071254987,0.0049746092,0.00066662196],"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":[0.0012247582,0.0014574967,0.023297442,0.0019611404,0.00032520667,0.00863115,0.012009187,0.110370934,0.02354856,0.54631746,0.018111458,0.25274518],"study_design_scores_gemma":[0.0004014391,0.0010327403,0.0038388507,0.0017977598,0.00021567839,0.004866104,0.0055512246,0.59988177,0.096107036,0.20638853,0.07957019,0.00034875737],"about_ca_topic_score_codex":0.007075012,"about_ca_topic_score_gemma":0.008681856,"teacher_disagreement_score":0.015977291,"about_ca_system_score_codex":0.002679553,"about_ca_system_score_gemma":0.0031035908,"threshold_uncertainty_score":0.084497035},"labels":[],"label_agreement":null},{"id":"W74065687","doi":"10.1007/978-1-4757-3283-2_3","title":"A Data Mining Technique","year":2001,"lang":"en","type":"book-chapter","venue":"","topic":"Data Mining Algorithms 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 Regina","funders":"","keywords":"Automatic summarization; Data mining; Computer science; Task (project management); Software; Artificial intelligence; Engineering","score_opus":0.07984447117148008,"score_gpt":0.2939448779643407,"score_spread":0.21410040679286063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W74065687","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037641288,0.00556099,0.9299674,0.0034195208,0.0013542671,0.00039590814,0.0014591952,0.0017223028,0.052356392],"genre_scores_gemma":[0.035984997,0.0076005086,0.8905218,0.001996773,0.0010694023,0.0004928308,0.0021590556,0.0002405498,0.059933983],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998643,0.00017852717,0.00012284337,0.00037604515,0.00064519205,0.000034353336],"domain_scores_gemma":[0.9989085,0.0005096092,0.000068878384,0.00026071368,0.00022183021,0.000030459345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001046134,0.0009939967,0.00080597494,0.0030270894,0.00096461654,0.0024343901,0.001564615,0.00091109244,0.009375271],"category_scores_gemma":[0.0035054402,0.00043111257,0.001307213,0.0044474527,0.0009708988,0.003362962,0.0016808705,0.0017956294,0.008958202],"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":[0.000056449804,0.000087566186,0.0009479045,0.00081235374,0.000111449284,0.00025510826,0.00026672744,0.0012753886,0.0060805967,0.10004001,0.04126968,0.84879684],"study_design_scores_gemma":[0.00003408003,0.00012712528,0.0019919449,0.00054743397,0.00019947118,0.0024242685,0.00028591586,0.022165654,0.016634189,0.23465946,0.720865,0.00006543948],"about_ca_topic_score_codex":0.00045951613,"about_ca_topic_score_gemma":0.0005869763,"teacher_disagreement_score":0.009375271,"about_ca_system_score_codex":0.00042519072,"about_ca_system_score_gemma":0.0009068374,"threshold_uncertainty_score":0.031363428},"labels":[],"label_agreement":null},{"id":"W77251134","doi":"10.4018/978-1-60566-010-3.ch123","title":"Evaluation of Decision Rules by Qualities for Decision-Making Systems","year":2009,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Decision rule; Computer science; Data mining; Contingency table; Machine learning; Consistency (knowledge bases); Artificial intelligence; Expert system; Decision table; Classifier (UML); Association rule learning; Decision tree; Rough set","score_opus":0.046062603244152525,"score_gpt":0.33539682062766346,"score_spread":0.28933421738351095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W77251134","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06745899,0.0029072454,0.90010154,0.0014014533,0.0003253204,0.00086260005,0.00083222473,0.0010993285,0.025011266],"genre_scores_gemma":[0.46311867,0.0011104693,0.532201,0.00014160456,0.00017249887,0.0005538789,0.001005091,0.00018539911,0.0015113608],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97258556,0.011485207,0.0029719803,0.0019058712,0.010329359,0.0007220104],"domain_scores_gemma":[0.9207239,0.061858095,0.003933835,0.004539442,0.007936348,0.0010083768],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023404276,0.0014551128,0.001447107,0.0044571944,0.0007297405,0.007656554,0.0014695724,0.0013675772,0.0063019725],"category_scores_gemma":[0.10962241,0.0005327208,0.0013377195,0.003605677,0.0028928446,0.0067251483,0.0020313892,0.0021263598,0.0010835702],"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":[0.00070437475,0.00021878388,0.013649206,0.0015173198,0.0003675447,0.0003207467,0.0019323719,0.20907961,0.0032199137,0.4493699,0.004654144,0.3149661],"study_design_scores_gemma":[0.00008141464,0.00058705313,0.0042377166,0.00053477596,0.00016023613,0.00029908816,0.001139218,0.616057,0.0054849284,0.3539263,0.017417472,0.00007482194],"about_ca_topic_score_codex":0.0011331113,"about_ca_topic_score_gemma":0.00075163326,"teacher_disagreement_score":0.023404276,"about_ca_system_score_codex":0.0033141137,"about_ca_system_score_gemma":0.0013424098,"threshold_uncertainty_score":0.123775065},"labels":[],"label_agreement":null},{"id":"W77960026","doi":"10.1609/aaai.v27i1.8553","title":"Towards Cohesive Anomaly Mining","year":2013,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Data Mining Algorithms and Applications","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":"Simon Fraser University","funders":"Office of International Science and Engineering; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; National Science Foundation","keywords":"Cluster analysis; Computer science; Task (project management); Data mining; Set (abstract data type); Anomaly detection; Anomaly (physics); Data set; Big data; Artificial intelligence; Engineering; Physics","score_opus":0.06691446556035674,"score_gpt":0.2859611338256471,"score_spread":0.21904666826529035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W77960026","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010586541,0.00033773298,0.98769647,0.00024407815,0.000030970303,0.00008885897,0.000078001874,0.0004473911,0.0004900064],"genre_scores_gemma":[0.24023354,0.00056664634,0.7556237,0.00045106126,0.00028112892,0.00034940743,0.0009274632,0.000208702,0.0013583213],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99278283,0.0022387505,0.00039904122,0.0018983003,0.0023350515,0.00034599676],"domain_scores_gemma":[0.98595375,0.006771447,0.0017018286,0.0026991102,0.0024786857,0.0003952169],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006332002,0.002019874,0.002829867,0.006546276,0.0020392411,0.0034570962,0.004551879,0.0025938854,0.00082844496],"category_scores_gemma":[0.024421023,0.0012206296,0.001910374,0.006526904,0.0027876308,0.0046699233,0.007605898,0.0038784812,0.00070550106],"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":[0.00029528173,0.0005586751,0.027179448,0.0007490765,0.00091544446,0.0010354891,0.00245912,0.2080688,0.016519835,0.13310358,0.010129781,0.59898555],"study_design_scores_gemma":[0.000026242838,0.000095188465,0.0017829288,0.00005700096,0.00008276192,0.00044174748,0.0002808992,0.8066686,0.002975051,0.18101765,0.0065314104,0.000040485545],"about_ca_topic_score_codex":0.0017743136,"about_ca_topic_score_gemma":0.002266593,"teacher_disagreement_score":0.006546276,"about_ca_system_score_codex":0.0006710632,"about_ca_system_score_gemma":0.0015655265,"threshold_uncertainty_score":0.0334872},"labels":[],"label_agreement":null},{"id":"W78181647","doi":"10.4018/978-1-59140-557-3.ch105","title":"Hierarchical Document Clustering","year":2005,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Cluster analysis; Document clustering; Hierarchy; Hierarchical clustering; Directory; Computer science; Tree (set theory); Complete-linkage clustering; Information retrieval; Subject (documents); Similarity (geometry); Cluster (spacecraft); Fuzzy clustering; Artificial intelligence; World Wide Web; Canopy clustering algorithm; Mathematics; Combinatorics","score_opus":0.018012883968384654,"score_gpt":0.2617875641419577,"score_spread":0.24377468017357304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W78181647","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004242405,0.021822145,0.8560191,0.0013909069,0.00086956896,0.0010260546,0.012564012,0.01218408,0.08988167],"genre_scores_gemma":[0.033854034,0.011800821,0.8535339,0.0005766616,0.00049378467,0.0005191383,0.025407502,0.0015949296,0.072219245],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979127,0.0003776257,0.00014914242,0.00052352785,0.00093223614,0.000104691295],"domain_scores_gemma":[0.99763846,0.00065916067,0.00012214298,0.0005232258,0.00095490227,0.000102159756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014835416,0.0012707235,0.001310813,0.008322293,0.0014649795,0.004061158,0.0027346523,0.0011562769,0.03069563],"category_scores_gemma":[0.004875119,0.0005605534,0.0014352622,0.012539859,0.00053678825,0.0028388167,0.0019247961,0.001215231,0.038429562],"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":[0.000049370483,0.000061958126,0.0006438035,0.0011300774,0.00013957622,0.000119886274,0.00035464094,0.005750896,0.0027225919,0.027415302,0.18431215,0.7772997],"study_design_scores_gemma":[0.000034660363,0.000058358295,0.001823168,0.0004655656,0.00014397854,0.00091946864,0.0003332206,0.050670084,0.0061706845,0.06923957,0.8700439,0.00009728688],"about_ca_topic_score_codex":0.0043184734,"about_ca_topic_score_gemma":0.007087165,"teacher_disagreement_score":0.03069563,"about_ca_system_score_codex":0.0015149509,"about_ca_system_score_gemma":0.0023124195,"threshold_uncertainty_score":0.10268706},"labels":[],"label_agreement":null},{"id":"W78303509","doi":"","title":"Subdivision of Edges and Matching Size.","year":2007,"lang":"en","type":"article","venue":"Ars Combinatoria","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Subdivision; Mathematics; Matching (statistics); Combinatorics; Statistics; Geography","score_opus":0.011272839103012763,"score_gpt":0.25503551952794085,"score_spread":0.24376268042492807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W78303509","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47621456,0.004741331,0.46092755,0.0033824681,0.00035122441,0.0002717888,0.0032115919,0.0023517807,0.048547782],"genre_scores_gemma":[0.87373734,0.001136334,0.11265217,0.0003153938,0.00026406778,0.00016438458,0.0022091325,0.00040802185,0.009113241],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99655116,0.00088011345,0.00035331506,0.00087930594,0.0007720408,0.000564005],"domain_scores_gemma":[0.9572842,0.02904915,0.003517563,0.0065866592,0.0018597218,0.0017026596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044377893,0.0004932313,0.0013597886,0.0028043091,0.0008642862,0.004396192,0.002418483,0.0014279948,0.009077305],"category_scores_gemma":[0.050069764,0.00064824225,0.00087620044,0.003777943,0.00211471,0.007606464,0.002323232,0.0018163007,0.001649677],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016284095,0.00051449775,0.058712598,0.00057513226,0.00023387121,0.00036616807,0.0008002576,0.067826636,0.010873425,0.50743586,0.02684878,0.32418445],"study_design_scores_gemma":[0.0001403834,0.00028334194,0.012460046,0.0001655257,0.00021992637,0.0015813737,0.00055495824,0.22600439,0.009729646,0.72998387,0.018810824,0.000065771535],"about_ca_topic_score_codex":0.0015289248,"about_ca_topic_score_gemma":0.0018691969,"teacher_disagreement_score":0.009077305,"about_ca_system_score_codex":0.0014466308,"about_ca_system_score_gemma":0.0009890778,"threshold_uncertainty_score":0.0303666},"labels":[],"label_agreement":null},{"id":"W80315153","doi":"10.1137/1.9781611972740.51","title":"A Foundational Approach to Mining Itemset Utilities from Databases","year":2004,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":552,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Database transaction; Association rule learning; Computer science; Data mining; Database; Information retrieval","score_opus":0.0640315864945909,"score_gpt":0.28672391233604644,"score_spread":0.22269232584145554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W80315153","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038603875,0.00043726154,0.99309045,0.00043309727,0.00003546718,0.00012943953,0.000303426,0.0002468966,0.0014635432],"genre_scores_gemma":[0.18677056,0.0021561696,0.8051761,0.0005577474,0.00068713585,0.0006952624,0.0017651578,0.00014710636,0.0020447006],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99229187,0.0021387814,0.00058464,0.001052062,0.0036102866,0.00032239963],"domain_scores_gemma":[0.9822238,0.012064224,0.0007564473,0.0029407896,0.0017532737,0.0002614197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0061926,0.0012009563,0.0016380217,0.006577279,0.0016701261,0.0046005165,0.0052177366,0.0017315701,0.0027652096],"category_scores_gemma":[0.040518172,0.0010023735,0.002395754,0.008819396,0.0023142924,0.00933635,0.0038140537,0.0045671305,0.0011961324],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014151391,0.00033984918,0.0041825473,0.00063547125,0.0002426446,0.00037761018,0.00050956453,0.047767676,0.0013529888,0.63690627,0.008712232,0.29883158],"study_design_scores_gemma":[0.0000254241,0.00006815109,0.00066361326,0.00012987954,0.00006075089,0.0004992475,0.000071565046,0.23221064,0.0013447931,0.75795805,0.006934163,0.000033750817],"about_ca_topic_score_codex":0.0012091012,"about_ca_topic_score_gemma":0.0012363667,"teacher_disagreement_score":0.006577279,"about_ca_system_score_codex":0.0010420945,"about_ca_system_score_gemma":0.0017966485,"threshold_uncertainty_score":0.03274995},"labels":[],"label_agreement":null},{"id":"W82815039","doi":"10.1007/0-306-47542-1_19","title":"Knowledge Discovery in Databases and Decision Support","year":2006,"lang":"en","type":"book-chapter","venue":"Kluwer Academic Publishers eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Computer science; Construct (python library); Decision support system; Data mining; Knowledge extraction; Machine learning; Artificial intelligence","score_opus":0.03369944827362448,"score_gpt":0.28420571088488494,"score_spread":0.25050626261126047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W82815039","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022474143,0.5207295,0.33842915,0.027381204,0.011229572,0.00022914179,0.0015933695,0.0009189079,0.09724183],"genre_scores_gemma":[0.0565177,0.47048488,0.33079812,0.012650067,0.01174165,0.0005259558,0.005107668,0.0005640239,0.11160997],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9938263,0.001917104,0.0006665342,0.00055937096,0.00279074,0.00023983404],"domain_scores_gemma":[0.9915799,0.0061286483,0.00028167848,0.0008991003,0.0009678494,0.00014282724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005844478,0.001058975,0.0029864744,0.0053240354,0.0010443452,0.013020312,0.0031521013,0.003104457,0.010233638],"category_scores_gemma":[0.013223912,0.0011282676,0.0010428235,0.015200552,0.00352146,0.015342661,0.0031864434,0.0041909073,0.0051001087],"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":[0.00002502879,0.000051685878,0.00019182236,0.0021783293,0.00008435891,0.00015001057,0.0004205468,0.0018196162,0.00033790222,0.527054,0.16035666,0.30732998],"study_design_scores_gemma":[0.000014543254,0.00001850937,0.00022091613,0.00097150274,0.000042111806,0.00033879784,0.00018773277,0.006065587,0.00064308563,0.47501835,0.51644623,0.000032631728],"about_ca_topic_score_codex":0.0023169972,"about_ca_topic_score_gemma":0.0017789672,"teacher_disagreement_score":0.013020312,"about_ca_system_score_codex":0.0025680696,"about_ca_system_score_gemma":0.0028819402,"threshold_uncertainty_score":0.03423494},"labels":[],"label_agreement":null},{"id":"W82889883","doi":"10.1007/978-3-642-22922-0_2","title":"SSCP: Mining Statistically Significant Co-location Patterns","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":22,"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; Pruning; Data mining; Computation; Feature (linguistics); Pattern recognition (psychology); Dependency (UML); Artificial intelligence; Algorithm","score_opus":0.02911516233681273,"score_gpt":0.26625622506671986,"score_spread":0.23714106272990715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W82889883","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16020365,0.003380706,0.7317611,0.0009818539,0.0004552722,0.0007827806,0.06660558,0.025935872,0.009893128],"genre_scores_gemma":[0.3416227,0.0013652772,0.5482928,0.00028941862,0.00034957062,0.0009360679,0.09633783,0.0008577411,0.009948614],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991228,0.000092243485,0.00008230214,0.0002427897,0.0003873934,0.00007245344],"domain_scores_gemma":[0.99829084,0.00082494895,0.00018476129,0.000343471,0.00027135212,0.000084634186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007451391,0.0014000855,0.0011151333,0.0053292196,0.000828136,0.0013858778,0.0018073149,0.0009865321,0.006548875],"category_scores_gemma":[0.0050105434,0.00049303577,0.0015264235,0.0075715748,0.0004455568,0.0011403956,0.0014312855,0.00082742295,0.0055390536],"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":[0.0005622094,0.0003597457,0.047770526,0.0013835924,0.00062708766,0.0012343473,0.0002796313,0.01957622,0.015160435,0.006412167,0.09522164,0.8114124],"study_design_scores_gemma":[0.0003326818,0.0006484315,0.049729984,0.00030358316,0.0007408798,0.006038075,0.0010501329,0.75608575,0.028595423,0.07451357,0.08182751,0.00013401713],"about_ca_topic_score_codex":0.0028847149,"about_ca_topic_score_gemma":0.005373193,"teacher_disagreement_score":0.006548875,"about_ca_system_score_codex":0.00032677612,"about_ca_system_score_gemma":0.0013509619,"threshold_uncertainty_score":0.021908164},"labels":[],"label_agreement":null},{"id":"W86313711","doi":"10.1007/978-1-4757-3283-2_2","title":"Background and Related Work","year":2001,"lang":"en","type":"book-chapter","venue":"","topic":"Data Mining Algorithms and Applications","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 Regina","funders":"","keywords":"Relevance (law); Contingency table; Computer science; Data mining; Domain knowledge; Domain (mathematical analysis); Association rule learning; Data science; Artificial intelligence; Machine learning; Mathematics","score_opus":0.03647075531992792,"score_gpt":0.2511165885242724,"score_spread":0.21464583320434447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W86313711","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0049322504,0.20633017,0.20649573,0.012732874,0.005296002,0.00037325497,0.0059260027,0.0032164182,0.5546973],"genre_scores_gemma":[0.050923835,0.253113,0.1709608,0.00937289,0.0075074383,0.0005192829,0.018092573,0.0017631582,0.48774704],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989644,0.00010432537,0.00007023774,0.0003712257,0.00038267704,0.00010709424],"domain_scores_gemma":[0.9985719,0.0006244511,0.000064603664,0.0002660974,0.0003599412,0.00011290852],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000876294,0.0009173974,0.0008907074,0.0045636916,0.001933891,0.00477146,0.0024641964,0.0015408281,0.099102594],"category_scores_gemma":[0.0037319914,0.0006193922,0.00091428385,0.008932786,0.001133481,0.006055383,0.002068986,0.0017861521,0.06742282],"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":[0.00006439442,0.00020142412,0.00055642246,0.0019013059,0.000022495944,0.00011970812,0.0002661919,0.001727036,0.0012982606,0.11094668,0.18007162,0.7028245],"study_design_scores_gemma":[0.000006947616,0.000029799212,0.00038859682,0.00080225867,0.000028684364,0.00042881188,0.00015433678,0.0017686128,0.0011223129,0.08705511,0.90819275,0.000021841754],"about_ca_topic_score_codex":0.0031027647,"about_ca_topic_score_gemma":0.0035447483,"teacher_disagreement_score":0.9008974,"about_ca_system_score_codex":0.0013472025,"about_ca_system_score_gemma":0.0022970233,"threshold_uncertainty_score":0.33153117},"labels":[],"label_agreement":null},{"id":"W88109437","doi":"","title":"A Tutorial on Social Network Analysis for Database Practitioners.","year":2009,"lang":"en","type":"article","venue":"Brazilian Symposium on Databases","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Visibility; Social network analysis; Data science; Social network (sociolinguistics); Network analysis; Network science; World Wide Web; Complex network; Social media","score_opus":0.03519003957862123,"score_gpt":0.31631496417117805,"score_spread":0.28112492459255684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W88109437","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032367434,0.29992893,0.47623628,0.037786514,0.010786117,0.0006202356,0.006836742,0.007814896,0.15675353],"genre_scores_gemma":[0.025022024,0.3257626,0.41458997,0.0217528,0.017579176,0.0018512957,0.012622501,0.002850481,0.17796911],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99918896,0.00032123865,0.00007547244,0.00009529417,0.00026006912,0.000059019752],"domain_scores_gemma":[0.9969194,0.0022932664,0.000115866984,0.00012487234,0.00035884898,0.00018765985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015854179,0.0018128314,0.0010286523,0.004326598,0.00081938773,0.002769464,0.0012967933,0.0021031396,0.04737416],"category_scores_gemma":[0.0065610535,0.0007522208,0.0009775572,0.0060641714,0.000713609,0.008258161,0.0019043828,0.0022851797,0.026109178],"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":[0.000025028661,0.00010045665,0.0004946215,0.0013746558,0.00004084007,0.00028822554,0.0006925737,0.0013484001,0.0012661562,0.06636751,0.6867603,0.24124123],"study_design_scores_gemma":[0.000007181883,0.000023283064,0.0004913235,0.0004125623,0.00001274051,0.0006081454,0.00025099923,0.001894837,0.00016513605,0.055674516,0.94044346,0.00001574738],"about_ca_topic_score_codex":0.001066645,"about_ca_topic_score_gemma":0.0019751827,"teacher_disagreement_score":0.04737416,"about_ca_system_score_codex":0.0010061978,"about_ca_system_score_gemma":0.0010586476,"threshold_uncertainty_score":0.15848237},"labels":[],"label_agreement":null},{"id":"W92525427","doi":"10.4018/978-1-60566-010-3.ch230","title":"Pattern Discovery as Event Association","year":2009,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Pattern Discovery Technologies (Canada); University of Waterloo","funders":"","keywords":"Event (particle physics); Association (psychology); Task (project management); Mathematics; Binary number; Computer science; Artificial intelligence; Combinatorics; Algorithm; Natural language processing; Arithmetic; Psychology; Physics","score_opus":0.011833458808762272,"score_gpt":0.24946878101245804,"score_spread":0.23763532220369576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W92525427","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010571811,0.0077003934,0.9542015,0.0069310777,0.00087978365,0.00058628526,0.00510888,0.0021156834,0.011904659],"genre_scores_gemma":[0.20104288,0.0077219573,0.752078,0.003627794,0.0023382916,0.0017944057,0.017092573,0.00040725278,0.013896925],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98498166,0.0042217546,0.0010810042,0.0054480312,0.003790215,0.00047739188],"domain_scores_gemma":[0.96723425,0.020851143,0.0036589608,0.0049012876,0.0026361707,0.0007182131],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008186597,0.0023971254,0.002476479,0.0072279647,0.0017163255,0.0069727106,0.004639714,0.0034467673,0.011310608],"category_scores_gemma":[0.042632543,0.0015366137,0.0031462498,0.01115354,0.0040505715,0.0138826575,0.0068087666,0.004956485,0.0043874034],"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":[0.0006091633,0.00031704752,0.011441121,0.002115439,0.0006058344,0.0017171734,0.0011202956,0.036358956,0.0018629557,0.56341445,0.04783433,0.33260328],"study_design_scores_gemma":[0.000071198214,0.000075284835,0.0011787586,0.0002410121,0.00011958258,0.0010188335,0.00021160819,0.13474952,0.0015360384,0.8149632,0.045770373,0.00006464965],"about_ca_topic_score_codex":0.0029618305,"about_ca_topic_score_gemma":0.001987393,"teacher_disagreement_score":0.011310608,"about_ca_system_score_codex":0.0022828204,"about_ca_system_score_gemma":0.002353832,"threshold_uncertainty_score":0.043295383},"labels":[],"label_agreement":null},{"id":"W960842831","doi":"10.1007/978-3-319-10160-6_11","title":"BLIMP: A Compact Tree Structure for Uncertain Frequent Pattern Mining","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","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 Manitoba","funders":"","keywords":"Compact space; Tree (set theory); Computer science; Tree structure; Data structure; Data mining; Upper and lower bounds; Algorithm; Mathematics; Binary tree; Combinatorics","score_opus":0.026099494289884506,"score_gpt":0.2715890096923017,"score_spread":0.2454895154024172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W960842831","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0073944204,0.0009561953,0.9656154,0.00034215624,0.0001375381,0.00022682147,0.008577473,0.015193795,0.0015562274],"genre_scores_gemma":[0.053946793,0.0007072275,0.9241646,0.00022688363,0.0001324178,0.00039074285,0.017403878,0.00091643614,0.0021110652],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893326,0.00016800607,0.00015273162,0.00017113061,0.000514542,0.00006029697],"domain_scores_gemma":[0.996651,0.0015190257,0.00030528678,0.0006800734,0.0006685817,0.0001760587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014799084,0.00085543055,0.0012145778,0.0030042,0.0008391016,0.0022311034,0.0021296416,0.0012728615,0.007842291],"category_scores_gemma":[0.010899818,0.00077766454,0.0011213901,0.004704691,0.00039156163,0.0038298757,0.0020658693,0.0017913372,0.0050362735],"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":[0.0011212236,0.00027340685,0.0026823096,0.0011431142,0.00017264632,0.000640022,0.00038294095,0.024053622,0.013039936,0.022010528,0.07348588,0.8609943],"study_design_scores_gemma":[0.00030447583,0.0004111951,0.0016930244,0.00031346473,0.00017042155,0.0013886447,0.00022615159,0.7470873,0.012950802,0.14990497,0.08544158,0.00010798594],"about_ca_topic_score_codex":0.0012766686,"about_ca_topic_score_gemma":0.0019252223,"teacher_disagreement_score":0.007842291,"about_ca_system_score_codex":0.0004196737,"about_ca_system_score_gemma":0.0011189944,"threshold_uncertainty_score":0.026235104},"labels":[],"label_agreement":null},{"id":"W96919113","doi":"10.4018/978-1-60566-010-3.ch321","title":"Web Usage Mining with Web Logs","year":2009,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Web mining; Computer science; Web log analysis software; World Wide Web; Data Web; Web modeling; Web navigation; Web intelligence; Web analytics; Web development; Web server; Web mapping; Web standards; Web page; Web API; The Internet","score_opus":0.018021705537921522,"score_gpt":0.24085895472682076,"score_spread":0.22283724918889924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W96919113","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0351131,0.0023730297,0.9395609,0.00047364642,0.00011955027,0.0004834694,0.0038386497,0.009893688,0.008144065],"genre_scores_gemma":[0.27322778,0.0032921906,0.7012987,0.00025688275,0.00024513257,0.001132945,0.01257184,0.0007145261,0.007259981],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982292,0.00060569245,0.00017014878,0.0002937108,0.00062644517,0.00007486685],"domain_scores_gemma":[0.9963697,0.002226613,0.00025883692,0.0006456514,0.00043721142,0.00006202662],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016640004,0.0011183077,0.0010102825,0.0059578433,0.00053978746,0.002535227,0.0014519528,0.0008967842,0.0020310355],"category_scores_gemma":[0.010262328,0.00068347075,0.0010793698,0.007067194,0.00035846213,0.0034106534,0.0014013862,0.0011400599,0.0026358725],"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":[0.00018537419,0.0004927929,0.015901256,0.00059113215,0.00020069495,0.000653412,0.0004122142,0.057973213,0.0030585446,0.010572433,0.015723249,0.8942356],"study_design_scores_gemma":[0.000036593192,0.00010104322,0.007211082,0.00026063947,0.000076087104,0.001050804,0.00039333288,0.89215595,0.0062031974,0.05703201,0.035419058,0.00006018096],"about_ca_topic_score_codex":0.0022756378,"about_ca_topic_score_gemma":0.0024923198,"teacher_disagreement_score":0.0059578433,"about_ca_system_score_codex":0.0004269164,"about_ca_system_score_gemma":0.0006378441,"threshold_uncertainty_score":0.008800149},"labels":[],"label_agreement":null},{"id":"W96984066","doi":"10.4018/978-1-59140-557-3.ch093","title":"Explanation-Oriented Data Mining","year":2005,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Knowledge extraction; Computer science; Data science; Data mining","score_opus":0.04206539177969704,"score_gpt":0.28117225850048266,"score_spread":0.23910686672078563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W96984066","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033512786,0.015881259,0.86627144,0.0073869205,0.0005951164,0.00069751684,0.0022788614,0.0018214062,0.1017162],"genre_scores_gemma":[0.08119957,0.02613778,0.83665335,0.0037479051,0.0009973586,0.0009823081,0.007487112,0.00047336298,0.042321265],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.998104,0.00065438554,0.00011206282,0.0003650564,0.00067767955,0.000086754975],"domain_scores_gemma":[0.99633956,0.0024718274,0.00017817688,0.0006052687,0.00031702817,0.00008817931],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003163518,0.001587667,0.0011193964,0.003519933,0.00069310557,0.004221391,0.003683141,0.0014477225,0.019908903],"category_scores_gemma":[0.006228419,0.00052837137,0.0015720101,0.0049102055,0.001857983,0.0046889205,0.0030988615,0.0020573433,0.0072277226],"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":[0.000039563743,0.00008183222,0.001303884,0.0015415787,0.000180965,0.00022140177,0.00047857504,0.0054580057,0.00055845757,0.5530629,0.054886814,0.382186],"study_design_scores_gemma":[0.000030969455,0.000028566992,0.0004927616,0.00037486217,0.00004873834,0.00037689146,0.00019741833,0.020401377,0.00091255544,0.7527421,0.22436847,0.000025326483],"about_ca_topic_score_codex":0.00085495756,"about_ca_topic_score_gemma":0.0011912987,"teacher_disagreement_score":0.019908903,"about_ca_system_score_codex":0.001092853,"about_ca_system_score_gemma":0.0014658518,"threshold_uncertainty_score":0.06660193},"labels":[],"label_agreement":null},{"id":"W97034364","doi":"10.4018/978-1-60566-010-3.ch049","title":"Constraint-Based Association Rule Mining","year":2009,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Association rule learning; Constraint (computer-aided design); Computer science; Data mining; Key (lock); Focus (optics); Association (psychology); Isolation (microbiology); Mathematics; Bioinformatics; Psychology","score_opus":0.01695478703771377,"score_gpt":0.2451768686861051,"score_spread":0.22822208164839133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W97034364","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030950578,0.005341676,0.97940135,0.001211024,0.00029654434,0.00075343036,0.0026166728,0.0013518243,0.005932352],"genre_scores_gemma":[0.0541793,0.006657375,0.9270991,0.0010567784,0.00045606517,0.00092324015,0.006730001,0.00019754507,0.0027005153],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9757117,0.0071158377,0.0028379231,0.005242963,0.00848747,0.0006041166],"domain_scores_gemma":[0.9586825,0.027900325,0.0028701723,0.0046903435,0.005368804,0.0004878788],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012238502,0.0026725894,0.005841636,0.010481077,0.0020146864,0.007551257,0.008547369,0.0031362858,0.008818408],"category_scores_gemma":[0.05160222,0.0012854688,0.0038753615,0.020023042,0.0026359665,0.00781509,0.0052570784,0.004296529,0.006807351],"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":[0.0003233202,0.00046431736,0.006533163,0.0034189122,0.001352644,0.0016103322,0.00048051597,0.06984982,0.0027680886,0.115703546,0.039592396,0.7579029],"study_design_scores_gemma":[0.00015230222,0.00021954163,0.0018870459,0.0009568648,0.00041303065,0.0032008835,0.00042964326,0.5739542,0.0065290392,0.3072289,0.10481075,0.00021775525],"about_ca_topic_score_codex":0.005106074,"about_ca_topic_score_gemma":0.004818772,"teacher_disagreement_score":0.012238502,"about_ca_system_score_codex":0.0018210444,"about_ca_system_score_gemma":0.00510893,"threshold_uncertainty_score":0.06472415},"labels":[],"label_agreement":null},{"id":"W982122077","doi":"10.1007/978-3-319-03449-2_26","title":"Association Rules Mining Based on Minimal Generator of Frequent Closed Itemset","year":2014,"lang":"en","type":"book-chapter","venue":"Advances in intelligent systems and computing","topic":"Data Mining Algorithms 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 Ottawa","funders":"","keywords":"Association rule learning; Redundancy (engineering); Generator (circuit theory); Computer science; Data mining; Association (psychology); Process (computing); Algorithm; Power (physics); Programming language","score_opus":0.017059316732547836,"score_gpt":0.2582533365922064,"score_spread":0.24119401985965855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W982122077","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061297975,0.0011871037,0.9311055,0.00031215692,0.00020557166,0.00028499702,0.0012939853,0.0024659568,0.0018467674],"genre_scores_gemma":[0.3007331,0.0008574934,0.68733305,0.00017774802,0.00019658015,0.0004311398,0.0074647185,0.00016892214,0.0026372625],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852127,0.0002520508,0.00017691168,0.0004797442,0.00047125228,0.00009876506],"domain_scores_gemma":[0.99748236,0.0014454562,0.00015299022,0.00028050816,0.00055260013,0.00008611291],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011624985,0.00069733197,0.0014976263,0.0032338568,0.0008408814,0.0013204664,0.00206955,0.00065930473,0.0025379055],"category_scores_gemma":[0.005253945,0.00051122793,0.0014078765,0.0028349215,0.00043909327,0.00184134,0.0010977807,0.0010893564,0.0011027509],"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":[0.0007588294,0.00048725805,0.009847968,0.0006693303,0.00034982234,0.0017891662,0.00034491226,0.030926574,0.018196108,0.020476025,0.015114414,0.90103954],"study_design_scores_gemma":[0.00014337622,0.00039946058,0.0044102105,0.00010783219,0.00023851969,0.0036529799,0.00018604423,0.8927983,0.014217095,0.07537863,0.008374933,0.00009261277],"about_ca_topic_score_codex":0.0009695354,"about_ca_topic_score_gemma":0.00090996845,"teacher_disagreement_score":0.0032338568,"about_ca_system_score_codex":0.00034376048,"about_ca_system_score_gemma":0.0010883409,"threshold_uncertainty_score":0.008490145},"labels":[],"label_agreement":null}]}