{"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8618708,0.0005463003,0.115065865,0.0022315164,0.0040842784,0.00038713554,0.000013200925,0.00032215615,0.015478725],"genre_scores_gemma":[0.9904431,0.000010889153,0.009240357,0.000032343745,0.0000047578733,0.000005916742,0.0000016777018,0.0000040524656,0.0002569164],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993364,0.000011009796,0.00017204383,0.00014162509,0.00016717537,0.00017172704],"domain_scores_gemma":[0.9990013,0.00016412332,0.00007641076,0.0006411078,0.00006853579,0.000048494127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005376376,0.000055169763,0.00006432358,0.00002495423,0.00015725166,0.000054913187,0.0009334622,0.000025379613,0.0000015702382],"category_scores_gemma":[0.00002847059,0.000040321705,0.0000304926,0.00030591566,0.000055757304,0.00012614328,0.0001788838,0.000071922586,0.000024489676],"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":[5.7193813e-7,0.000038788756,0.0016933746,5.4907304e-7,0.00000333203,0.0000013912852,0.000080081874,2.4197715e-7,0.00013192791,0.9454814,0.0025177018,0.05005065],"study_design_scores_gemma":[0.0007633813,0.00016334666,0.26351887,0.0000218451,0.000013940783,0.000016583092,0.00018265139,0.0046303873,0.016419644,0.6484353,0.065512,0.00032204093],"about_ca_topic_score_codex":0.000037313413,"about_ca_topic_score_gemma":0.000015513815,"teacher_disagreement_score":0.29704607,"about_ca_system_score_codex":0.000013258177,"about_ca_system_score_gemma":0.000026805797,"threshold_uncertainty_score":0.17346205},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000004323051,0.0011601818,0.016440595,0.00012197624,0.00043856684,0.00024333393,0.000051348583,0.00021889756,0.9813208],"genre_scores_gemma":[0.000177312,0.00006733134,0.060627565,0.00047465359,0.00039754005,0.000068188325,0.000042969394,0.000056419212,0.938088],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99841964,0.000010227831,0.00033804082,0.0005730745,0.00029312866,0.00036587557],"domain_scores_gemma":[0.99810475,0.000059155576,0.00024308161,0.0013508643,0.00006363352,0.00017848997],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00017608619,0.00033948338,0.00033047312,0.0001034952,0.00014406434,0.0001366972,0.0012487456,0.00017874643,0.000082334715],"category_scores_gemma":[0.000005395154,0.00033154179,0.00013295755,0.000016938338,0.000060174676,0.00018964008,0.0005645251,0.00029598625,0.0007459722],"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":[2.4874623e-7,0.0000046338555,0.000001536905,0.000013431581,0.000020936306,0.0000059824706,0.0002156772,1.4811296e-7,0.000012142639,0.0127059,0.00027879953,0.9867406],"study_design_scores_gemma":[0.00010495555,0.00002695732,0.000011137019,0.00017222203,0.000023991492,0.000019974721,0.0000031420595,0.0002658547,0.000028436569,0.0025166254,0.9964113,0.00041536824],"about_ca_topic_score_codex":2.868239e-7,"about_ca_topic_score_gemma":0.000003362289,"teacher_disagreement_score":0.99613255,"about_ca_system_score_codex":0.00004544367,"about_ca_system_score_gemma":0.00006550664,"threshold_uncertainty_score":0.99991363},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000017557124,0.00021235633,0.118771054,0.00031183264,0.00013288888,0.0002359333,0.007753318,0.00030398896,0.87227684],"genre_scores_gemma":[0.0006053334,0.000013743775,0.9315026,0.0016180035,0.00066863874,0.000011840966,0.0025628435,0.000060697606,0.06295633],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970695,0.000011639529,0.00036474277,0.0016598103,0.0005241025,0.00037021658],"domain_scores_gemma":[0.98965615,0.00004609752,0.00028168413,0.009750761,0.00007585598,0.0001894267],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00024097154,0.00041802556,0.00039945665,0.000055022687,0.0001901575,0.00049604115,0.011089408,0.00017325349,0.0000079850115],"category_scores_gemma":[0.000013365238,0.0003716473,0.000032364253,0.00004840133,0.00010800435,0.00047865842,0.005618244,0.00026070443,0.00017745594],"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":[0.0000021242138,0.0000064234478,0.0000011372623,0.0000051738207,0.00003895671,0.00004886862,0.000010161256,6.15564e-7,5.448425e-7,0.6246581,0.028255872,0.34697202],"study_design_scores_gemma":[0.0002569916,0.000099731296,0.000028971119,0.00025131754,0.00007343197,0.0001943058,0.0000038900503,0.019940102,0.000001007575,0.05861969,0.91988987,0.0006406866],"about_ca_topic_score_codex":0.00006778027,"about_ca_topic_score_gemma":0.00018239544,"teacher_disagreement_score":0.891634,"about_ca_system_score_codex":0.00006453912,"about_ca_system_score_gemma":0.00036138794,"threshold_uncertainty_score":0.9998735},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012311806,0.00024093516,0.041051734,0.000036018595,0.0003379677,0.00015195507,0.00064021384,0.00009656259,0.95732147],"genre_scores_gemma":[0.41303456,0.00013814284,0.14744219,0.0012878901,0.0015571192,0.00013366967,0.00023098467,0.00012232037,0.4360531],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984546,0.00000690104,0.00033722786,0.0004713725,0.0005347794,0.00019515559],"domain_scores_gemma":[0.99887663,0.000029367535,0.00022918431,0.0007039941,0.00008673634,0.000074109164],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0000669545,0.00025266517,0.00027368555,0.000055776385,0.00012262477,0.00009970968,0.0008249839,0.00015589308,0.000009980696],"category_scores_gemma":[0.0000058180935,0.00024687604,0.0001599413,0.000026573296,0.00014607026,0.00023370044,0.00056773284,0.00016016945,0.000103567414],"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":[0.0000033894505,0.000012992787,0.000009264687,0.000009664232,0.000047002737,0.000013763483,0.00002550834,0.0000019670854,0.000048242255,0.9780225,0.009217148,0.012588533],"study_design_scores_gemma":[0.0012578268,0.00042468405,0.00217754,0.0006029701,0.0001552106,0.0009781945,0.00004501173,0.0009908518,0.0015112625,0.82860285,0.161173,0.002080621],"about_ca_topic_score_codex":0.00010655398,"about_ca_topic_score_gemma":0.00003232415,"teacher_disagreement_score":0.52126837,"about_ca_system_score_codex":0.00013082717,"about_ca_system_score_gemma":0.00028512662,"threshold_uncertainty_score":0.99999833},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6815801,0.00027819388,0.30711326,0.0015221443,0.0012624701,0.0002948888,0.00008541158,0.00028553474,0.0075780046],"genre_scores_gemma":[0.9873067,0.0000068526756,0.012481667,0.00006720575,0.0000028904942,0.0000073049314,0.000033458415,0.0000055210567,0.00008836312],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99919444,0.000013595467,0.0002069963,0.0002152257,0.0001800589,0.0001896795],"domain_scores_gemma":[0.9992001,0.000071660485,0.00010056189,0.00050565734,0.000054120588,0.000067894165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046263728,0.00006882613,0.00009161996,0.000046410772,0.000072226445,0.000032537268,0.00059722713,0.00004785029,0.000005753672],"category_scores_gemma":[0.000019510213,0.000070049246,0.000027768676,0.00037633275,0.000026798762,0.00022793241,0.00007745656,0.00007414257,0.000029519419],"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":[7.3567037e-7,0.00017030037,0.00058712857,0.0000036546087,0.000005152413,6.6957523e-7,0.00017134873,6.905149e-8,0.00395557,0.9547423,0.015777448,0.024585629],"study_design_scores_gemma":[0.0028045338,0.00031675023,0.19291157,0.000055960103,0.000027663104,0.000018206196,0.00032513772,0.052808408,0.069199696,0.4738383,0.20686543,0.00082834775],"about_ca_topic_score_codex":0.000011846757,"about_ca_topic_score_gemma":0.0000015346499,"teacher_disagreement_score":0.48090398,"about_ca_system_score_codex":0.000022490856,"about_ca_system_score_gemma":0.000024272578,"threshold_uncertainty_score":0.28565255},"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.957985e-7,0.00012339815,0.08080117,0.00006270411,0.00030212407,0.00013187774,0.00014112752,0.0002722234,0.9181645],"genre_scores_gemma":[0.0038470214,0.000014961879,0.15667984,0.001438748,0.000642949,0.00006107202,0.000020815907,0.000064986285,0.8372296],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987365,0.000004693696,0.00022927963,0.00055625394,0.00023240432,0.00024084291],"domain_scores_gemma":[0.99837315,0.000013127525,0.00014010664,0.0012609891,0.00006674734,0.00014589672],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000067593384,0.00026386516,0.00023142781,0.000036491863,0.00009634819,0.0001479756,0.0015305931,0.00020666113,0.000036980015],"category_scores_gemma":[0.000003856171,0.000257868,0.0001205493,0.000017060804,0.00006539545,0.00008106617,0.00056190934,0.00018000726,0.0015569719],"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":[4.7901557e-7,0.0000040347963,4.4373456e-7,0.0000033046747,0.000019018049,0.00001537805,0.00002342378,4.5589978e-8,9.4480674e-7,0.86830014,0.010472772,0.12116002],"study_design_scores_gemma":[0.000056743345,0.000026022104,0.000009068507,0.000036995596,0.0000129484615,0.000031887404,4.356838e-7,0.000094857736,0.000013066894,0.6195534,0.3799332,0.00023135712],"about_ca_topic_score_codex":0.00006796806,"about_ca_topic_score_gemma":0.000013812336,"teacher_disagreement_score":0.36946046,"about_ca_system_score_codex":0.00006691537,"about_ca_system_score_gemma":0.00013567926,"threshold_uncertainty_score":0.99998736},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44047606,0.0001758851,0.55459726,0.00060242304,0.00023458549,0.00007651024,0.0000033037375,0.00013678233,0.003697163],"genre_scores_gemma":[0.50865436,0.000025440382,0.49064037,0.00033436183,0.00012235991,0.000011472528,0.000008026244,0.000010599957,0.00019303623],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99886906,0.000020960026,0.00023904581,0.00037115274,0.00016309317,0.0003366903],"domain_scores_gemma":[0.99919057,0.00015893418,0.00006632416,0.00046576528,0.000025590256,0.0000928212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063899864,0.00011007288,0.00012365167,0.0002654335,0.00019412351,0.00011074157,0.00061758916,0.000085594394,0.0000034774318],"category_scores_gemma":[0.0000553369,0.000113426206,0.000041799067,0.00094430667,0.00008085862,0.00029511526,0.00009834217,0.00021916715,0.000017246879],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026110665,0.00008846034,0.0038926727,0.000013200619,0.000013615856,0.00007344688,0.0050840448,0.00002503756,0.00088840525,0.3589674,0.0024970316,0.6284541],"study_design_scores_gemma":[0.00570851,0.0005582537,0.4817489,0.00076560874,0.00008064529,0.00063520396,0.01289527,0.17280689,0.019780388,0.10833236,0.19157496,0.005112987],"about_ca_topic_score_codex":0.00015272968,"about_ca_topic_score_gemma":0.000026255813,"teacher_disagreement_score":0.6233411,"about_ca_system_score_codex":0.00007335426,"about_ca_system_score_gemma":0.000026079091,"threshold_uncertainty_score":0.46253866},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11228289,0.000007400149,0.88407314,0.000029068664,0.000010123873,0.00006495101,0.0000017232002,0.000045630433,0.0034850952],"genre_scores_gemma":[0.23027912,5.377556e-7,0.76959825,0.000024725263,0.000009830086,0.000004070421,0.0000027848057,0.0000023602463,0.0000783134],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915224,0.0000059387376,0.00024726472,0.0002825284,0.00018867936,0.0001233182],"domain_scores_gemma":[0.99929315,0.000020763862,0.000049713537,0.0005341958,0.00005176691,0.000050419636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003001726,0.000066650166,0.00009039578,0.0000451917,0.000089139336,0.00003809929,0.00056318485,0.000026650854,0.0000058419273],"category_scores_gemma":[0.0000089467585,0.000055055178,0.000023988123,0.00021189012,0.000021165115,0.00030236124,0.00026999367,0.000037907208,0.00001141528],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.225e-7,0.00015703803,0.000043453783,0.0000031509178,0.0000030005635,3.0501702e-8,0.0005048659,0.014132912,0.0022573832,0.009311511,0.00013465827,0.9734512],"study_design_scores_gemma":[0.000088083645,0.0000031166503,0.00027827924,0.0000042867664,0.000001277266,0.0000010080026,0.000024620676,0.99466294,0.0036151938,0.00051903975,0.00073116017,0.000071013805],"about_ca_topic_score_codex":0.000007757336,"about_ca_topic_score_gemma":0.000018187353,"teacher_disagreement_score":0.98053,"about_ca_system_score_codex":0.000042643624,"about_ca_system_score_gemma":0.0001072748,"threshold_uncertainty_score":0.22450851},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0647785,0.00010770524,0.93207294,0.002073115,0.0006374817,0.00015720306,0.000039478353,0.00004022155,0.00009335701],"genre_scores_gemma":[0.118287235,0.000020618285,0.8811685,0.00017926446,0.00021341692,0.000016918266,0.0000090973335,0.0000100422985,0.00009492894],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987324,0.0000050911244,0.00019675113,0.00037115416,0.00031855953,0.00037603936],"domain_scores_gemma":[0.9988165,0.00004469562,0.000037284237,0.00054224586,0.00012173041,0.00043757778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017156112,0.000095867166,0.00011114009,0.00026081016,0.00016406749,0.000577811,0.0017543085,0.000022155666,4.867319e-7],"category_scores_gemma":[0.00033328708,0.000087362525,0.000012325615,0.0008893204,0.00003725817,0.0017478566,0.00042710727,0.0001271761,0.000006203106],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010133887,0.000018585934,0.00016209602,0.0000032726568,0.0000028003399,0.000009673644,0.0005974576,0.0009312867,0.0007858046,0.0012075951,0.0021456608,0.9941347],"study_design_scores_gemma":[0.00029894465,0.00007673933,0.0031949705,0.00004302544,0.0000021863827,0.00012560155,0.00011387425,0.9687789,0.00029293832,0.0003778168,0.02653458,0.00016044006],"about_ca_topic_score_codex":0.000017867475,"about_ca_topic_score_gemma":0.000008280041,"teacher_disagreement_score":0.9939743,"about_ca_system_score_codex":0.000056611447,"about_ca_system_score_gemma":0.0001972823,"threshold_uncertainty_score":0.55718446},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038714423,0.000009220245,0.98034275,0.014718581,0.00013091284,0.00024902174,0.00022458988,0.00024446123,0.00020900992],"genre_scores_gemma":[0.107757226,1.9635425e-7,0.8893286,0.0015983628,0.00015247328,0.000042880147,0.00035467301,0.000008868826,0.00075673143],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999034,0.000012686764,0.000092651855,0.0005200577,0.00014883139,0.00019176696],"domain_scores_gemma":[0.9989166,0.00011510693,0.000052036743,0.00078362314,0.000060598042,0.00007202982],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018688648,0.000099675155,0.00007756779,0.00006112271,0.00027615562,0.00014924626,0.0006001935,0.00005862603,0.000013404214],"category_scores_gemma":[0.0000297586,0.00008411343,0.00002206984,0.00021084509,0.00001575938,0.0004509594,0.0001471636,0.000110882465,0.000028979955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007896577,0.0001413143,0.000008953029,0.000009477567,0.000012533234,0.0000063413086,0.00001476471,0.0011400639,0.0013200222,0.019992815,0.21720397,0.76014185],"study_design_scores_gemma":[0.00029445585,0.000070284266,0.00003963252,0.0000045107636,0.0000077418135,0.00005958715,0.0000047346243,0.96228683,0.0026853515,0.00006289725,0.034368694,0.00011527519],"about_ca_topic_score_codex":0.00007337507,"about_ca_topic_score_gemma":0.000110591216,"teacher_disagreement_score":0.9611468,"about_ca_system_score_codex":0.000049601324,"about_ca_system_score_gemma":0.00010437057,"threshold_uncertainty_score":0.3430046},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000040827526,0.00019005546,0.08294826,0.00038140875,0.00018340886,0.00021024984,0.0010883241,0.00036566987,0.91462857],"genre_scores_gemma":[0.009879641,0.0000074241275,0.7994238,0.0044230516,0.0019430697,0.000102718455,0.0006549878,0.00013618483,0.18342909],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99783003,0.000006593514,0.0003417371,0.0010580409,0.0004406823,0.00032289865],"domain_scores_gemma":[0.9964591,0.000037025682,0.00023533951,0.003004085,0.00009779725,0.00016661093],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00015554455,0.00034761094,0.00029769324,0.00005579087,0.00014735846,0.00028858017,0.004192958,0.00022042837,0.00002098801],"category_scores_gemma":[0.000016181164,0.0003519117,0.00006777134,0.00003799364,0.00007762896,0.00021765364,0.00090649363,0.00020796839,0.0003153935],"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":[0.0000012751689,0.000009593658,0.0000015775172,0.000013958662,0.000020167248,0.000016086628,0.00001904455,0.0000063785787,7.5384276e-7,0.73721385,0.010316824,0.25238046],"study_design_scores_gemma":[0.0004351365,0.00007521683,0.000013465945,0.00036590666,0.000077342935,0.00005912071,0.0000067387446,0.07759773,0.000030608968,0.10059087,0.81970453,0.0010433181],"about_ca_topic_score_codex":0.000015997986,"about_ca_topic_score_gemma":0.000035276335,"teacher_disagreement_score":0.80938774,"about_ca_system_score_codex":0.00008469302,"about_ca_system_score_gemma":0.0005179315,"threshold_uncertainty_score":0.9998933},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009192007,0.00015555676,0.98107207,0.00028630803,0.00023196671,0.00020530597,0.00005438648,0.0002705182,0.008531866],"genre_scores_gemma":[0.36856747,0.000035116926,0.6296679,0.0009198419,0.00011646378,0.00016925424,0.00016339596,0.0000202464,0.000340342],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983248,0.000021713886,0.00031867734,0.0006064267,0.00037673322,0.0003516476],"domain_scores_gemma":[0.998304,0.00014846155,0.00011118903,0.0011147449,0.000079571626,0.00024200357],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003837695,0.00018865122,0.00017280305,0.00009360284,0.000120735465,0.00017251828,0.0013744624,0.00004278448,0.000045471355],"category_scores_gemma":[0.00004375766,0.00017356628,0.000032568892,0.0006660427,0.000084621905,0.00040656404,0.000480543,0.00013473275,0.000514332],"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":[0.0000066237267,0.0001468313,0.0002197222,0.000009975877,0.00002654608,0.000031858825,0.001695971,0.00020818437,0.00053943373,0.6095864,0.031566374,0.35596204],"study_design_scores_gemma":[0.00040164133,0.00016553723,0.00052485085,0.00009387451,0.000028173421,0.00011623449,0.0018219795,0.44320196,0.03263914,0.03306725,0.4866111,0.0013282591],"about_ca_topic_score_codex":0.00021734266,"about_ca_topic_score_gemma":0.000014986869,"teacher_disagreement_score":0.5765192,"about_ca_system_score_codex":0.00006334453,"about_ca_system_score_gemma":0.00012882207,"threshold_uncertainty_score":0.70778275},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020193572,0.00012595535,0.85747033,0.11048081,0.0005021722,0.001022353,0.00009265177,0.001165455,0.027120916],"genre_scores_gemma":[0.14236403,0.00010321719,0.7859685,0.018877273,0.00056894193,0.00085473794,0.000112217895,0.0000796068,0.05107151],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99891376,0.000047713886,0.00023730402,0.00034987414,0.00015233562,0.0002990194],"domain_scores_gemma":[0.99816537,0.0005447602,0.00007916832,0.0011192737,0.000011368859,0.00008006346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015201556,0.00014908674,0.00013920025,0.000035972473,0.0008542321,0.00038827327,0.0020708963,0.000040434363,0.00005865442],"category_scores_gemma":[0.000023988005,0.00006940776,0.00011141657,0.00036037804,0.00010921249,0.0017301374,0.0005841216,0.00013619552,0.00013948856],"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":[0.0000058017004,0.000121398174,0.0029648924,0.000006946652,0.00005755346,0.000007249545,0.0016223462,0.000036468347,0.00003016961,0.37525478,0.5657068,0.054185633],"study_design_scores_gemma":[0.0004425471,0.00003091543,0.018397931,0.000010761064,0.000010481256,0.00003721482,0.0001384939,0.13418126,0.0010242893,0.0035936823,0.84188706,0.0002453963],"about_ca_topic_score_codex":0.000019629015,"about_ca_topic_score_gemma":0.0000012167524,"teacher_disagreement_score":0.3716611,"about_ca_system_score_codex":0.0000041894536,"about_ca_system_score_gemma":0.00009692907,"threshold_uncertainty_score":0.6570149},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000075927994,0.000039515984,0.9980216,0.00022762462,0.00024587172,0.00038668583,0.00022278368,0.000084241234,0.0006957647],"genre_scores_gemma":[0.19843136,0.000016411033,0.8004877,0.00036622473,0.00020889062,0.000034240198,0.00037993063,0.000030300354,0.000044928624],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965871,0.00003542735,0.00047543226,0.0015344319,0.00082798564,0.0005396307],"domain_scores_gemma":[0.9974599,0.00049351866,0.00025363057,0.0015165746,0.000119147706,0.00015723398],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006693725,0.00041727812,0.00042116753,0.0004949906,0.0001856784,0.0006994248,0.0025058533,0.0001401416,0.000008826127],"category_scores_gemma":[0.00009819024,0.00035249666,0.000029150477,0.00045396294,0.0005681164,0.0005022951,0.0006692382,0.0005321561,0.00004282763],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007604244,0.000043860276,0.0000400958,0.000043167805,0.0000061438213,0.00006945605,0.0003971124,0.013245743,0.000068116504,0.03691236,0.000034409364,0.9491319],"study_design_scores_gemma":[0.0003731947,0.00025406366,0.0018867828,0.00057759346,0.000008088925,0.000033103708,4.7391484e-7,0.9660043,0.0004169453,0.028544042,0.0011929037,0.0007084838],"about_ca_topic_score_codex":0.0002772147,"about_ca_topic_score_gemma":0.000674578,"teacher_disagreement_score":0.95275855,"about_ca_system_score_codex":0.00019855652,"about_ca_system_score_gemma":0.00062179525,"threshold_uncertainty_score":0.9998927},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.062180355,0.0001694092,0.93630725,0.00025503332,0.00003335525,0.00025079207,0.000091828944,0.000039585895,0.0006723845],"genre_scores_gemma":[0.38301048,0.000008770488,0.61663383,0.00009293417,0.00002357181,0.00007464586,0.00014199062,0.000007800464,0.0000060010266],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99893314,0.00011343828,0.0002427647,0.00038882214,0.000118342796,0.00020351977],"domain_scores_gemma":[0.9988586,0.00047285756,0.00010081532,0.00030039612,0.00015681874,0.00011053783],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003694758,0.00011029468,0.00011783381,0.00010037878,0.0001402368,0.000069691036,0.00022109832,0.00010395952,0.0000010252921],"category_scores_gemma":[0.00054735213,0.00011070686,0.000010597946,0.00035955582,0.00005584434,0.000038858117,0.00011080654,0.0001565374,0.00002167516],"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":[0.0000018212734,0.00008748969,0.011314934,0.0000061239325,0.000009581974,0.0000022970673,0.00013359069,0.0006468386,0.004172294,0.92017907,0.00005462112,0.06339133],"study_design_scores_gemma":[0.00044962254,0.000208416,0.07716059,0.000013452899,0.00003156579,0.000010641461,0.000065791544,0.39879027,0.0004566656,0.518001,0.004447208,0.00036477693],"about_ca_topic_score_codex":0.00004694272,"about_ca_topic_score_gemma":0.000010428241,"teacher_disagreement_score":0.40217808,"about_ca_system_score_codex":0.000102504,"about_ca_system_score_gemma":0.00009557184,"threshold_uncertainty_score":0.45144945},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022410979,0.0000046406853,0.9695966,0.011643746,0.00016414802,0.00012840958,0.000035618297,0.0003463255,0.01583939],"genre_scores_gemma":[0.07192744,8.9427886e-7,0.9128998,0.0014498868,0.00012929236,0.000019572964,0.00007785908,0.0000114090735,0.013483861],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983959,0.000010704046,0.00024409773,0.0004261502,0.0004830302,0.00044011243],"domain_scores_gemma":[0.998602,0.00009680894,0.000033403547,0.0007378555,0.00024095572,0.00028903264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009109754,0.000117349206,0.00011588736,0.00009791229,0.00018377439,0.0002908182,0.001083565,0.000051600848,0.00006091038],"category_scores_gemma":[0.00011987594,0.000105857645,0.00003745884,0.0007374736,0.00002731515,0.00028693565,0.0006128638,0.00014258671,0.00050229963],"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":[0.00000852145,0.00021016801,0.0003720134,0.000010933764,0.000024393326,0.000031771815,0.0005541226,0.0004202911,0.0027153413,0.112642795,0.18176071,0.70124894],"study_design_scores_gemma":[0.00029539314,0.0000730914,0.008010758,0.000015335521,0.0000041883045,0.00003330901,0.000058417852,0.24654959,0.0031998116,0.0016662293,0.7397357,0.0003581262],"about_ca_topic_score_codex":0.00009583004,"about_ca_topic_score_gemma":0.000054315322,"teacher_disagreement_score":0.70089084,"about_ca_system_score_codex":0.000041932228,"about_ca_system_score_gemma":0.000037357524,"threshold_uncertainty_score":0.6456213},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000041858866,0.00030600443,0.2756355,0.00044176038,0.0005487073,0.00072280463,0.0053804833,0.00025999473,0.71670055],"genre_scores_gemma":[0.0049725436,0.000082956874,0.60654384,0.0056837574,0.0062258397,0.00024324197,0.0014306139,0.00019139638,0.37462583],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99829584,0.0000056845743,0.00027776966,0.00094166293,0.00021788149,0.00026117498],"domain_scores_gemma":[0.9974934,0.00004266395,0.00016997282,0.0020830028,0.00006448537,0.00014649086],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00014661915,0.00028995573,0.00029772593,0.000031510932,0.00012363445,0.0003808477,0.0021510597,0.00020170002,0.0000021109447],"category_scores_gemma":[0.000012871744,0.00028375132,0.00005629459,0.000011966436,0.000052360305,0.0001625494,0.0007975192,0.00013249638,0.000037467864],"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":[0.000001226721,0.0000041101366,5.9405573e-7,0.0000101717,0.000016449067,0.0000027096291,0.000011372591,9.388446e-8,0.0000012744316,0.52942353,0.009492278,0.4610362],"study_design_scores_gemma":[0.0002717586,0.00008686733,0.000028655948,0.0000836038,0.000040066436,0.000024866267,7.3298224e-7,0.0040742457,0.0000039900783,0.21602708,0.7790035,0.0003546269],"about_ca_topic_score_codex":0.000050864975,"about_ca_topic_score_gemma":0.000055184904,"teacher_disagreement_score":0.7695112,"about_ca_system_score_codex":0.000048729748,"about_ca_system_score_gemma":0.0001390984,"threshold_uncertainty_score":0.99996144},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000014649,0.0011998658,0.85504943,0.0043325624,0.00064017787,0.0014734659,0.033248678,0.00047852733,0.10357582],"genre_scores_gemma":[0.000036243477,0.0014837222,0.6778337,0.0019719861,0.0008039689,0.000073414216,0.07803339,0.000107928354,0.23965567],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953253,0.000023097577,0.000656579,0.003178342,0.00045682775,0.00035980917],"domain_scores_gemma":[0.98256695,0.00013475493,0.0002316034,0.016711658,0.00020169633,0.00015331621],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00043503422,0.00041993705,0.0004502454,0.00039106506,0.00016001161,0.0007325502,0.019274078,0.00017349795,0.0002061797],"category_scores_gemma":[0.00026915644,0.0003917548,0.000024064024,0.00036880726,0.00006725346,0.0020675615,0.029934376,0.0005259488,0.00063094735],"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":[0.0000013084659,0.00005517767,0.0000015919496,0.000011832075,0.00004430185,0.000023767823,0.00040346535,0.00000140001,0.0000014154433,0.0027293519,0.4587695,0.5379569],"study_design_scores_gemma":[0.0000574808,0.0000112329335,0.00000880478,0.00028388237,0.000033326076,0.000010673313,0.0000813614,0.3111574,0.000002129438,0.0005595415,0.6874519,0.00034225767],"about_ca_topic_score_codex":0.002594927,"about_ca_topic_score_gemma":0.0017590607,"teacher_disagreement_score":0.53761464,"about_ca_system_score_codex":0.00008837834,"about_ca_system_score_gemma":0.0003116053,"threshold_uncertainty_score":0.99985343},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004072968,0.00002826238,0.99427146,0.00027574442,0.000055957615,0.000109570974,0.00011726715,0.00006256898,0.0010062021],"genre_scores_gemma":[0.13502091,0.00001027181,0.8644885,0.00014012361,0.00007896681,0.000006637983,0.000027852517,0.0000063020907,0.00022046149],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992994,0.000012360361,0.000146029,0.00026264793,0.00008281918,0.0001967397],"domain_scores_gemma":[0.9994693,0.00018744472,0.000028568702,0.00020418302,0.000026642632,0.00008385934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013524399,0.00007629711,0.00009449615,0.00002287449,0.00026489003,0.00017975534,0.00025116745,0.000021332178,0.000011462505],"category_scores_gemma":[0.000015938855,0.00007461207,0.0000151953245,0.00009156992,0.00003735823,0.000056527577,0.000082055005,0.00006930769,0.000006628136],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.1444096e-7,0.000011122847,0.000027855242,0.000006955777,0.0000033413883,0.0000017593453,0.00023132123,0.000026488078,0.000007638004,0.22218992,0.0011239748,0.7763691],"study_design_scores_gemma":[0.00016314439,0.000053576485,0.0014038858,0.000011291677,0.00000412166,0.000010389242,0.000017355967,0.9562016,0.000014264135,0.016760373,0.02525387,0.00010609998],"about_ca_topic_score_codex":0.000015213937,"about_ca_topic_score_gemma":0.0000023273826,"teacher_disagreement_score":0.95617515,"about_ca_system_score_codex":0.0000062095996,"about_ca_system_score_gemma":0.000025534848,"threshold_uncertainty_score":0.3042592},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012928442,0.00017320414,0.99540204,0.0006863258,0.0007921195,0.00036164356,0.00016225968,0.00011263054,0.001016928],"genre_scores_gemma":[0.10683301,0.00003199269,0.8908738,0.0013311623,0.0005470431,0.000025191755,0.00017597913,0.00003765056,0.00014419816],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966164,0.000027382215,0.00030149697,0.0018507874,0.00079858163,0.00040529968],"domain_scores_gemma":[0.99615216,0.0014092176,0.00029361845,0.0019162454,0.00010385303,0.00012491073],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008684541,0.00034726597,0.0003500909,0.0003254493,0.00029542096,0.00068398734,0.0025798618,0.00022489496,0.00000802452],"category_scores_gemma":[0.00023919932,0.00032260953,0.00003706006,0.00036031235,0.00021006397,0.000370353,0.0023732032,0.0005143393,0.00004392296],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023330706,0.000042481963,0.000036697467,0.0000087945855,0.000017385093,0.000022402794,0.0006958613,0.01500159,0.00003711724,0.015843667,0.000060241833,0.96823144],"study_design_scores_gemma":[0.00035633112,0.000114557886,0.0009535332,0.00046034082,0.000014762329,0.000008528497,2.627266e-7,0.8899711,0.00028636103,0.10672563,0.0006201094,0.0004884824],"about_ca_topic_score_codex":0.00008276342,"about_ca_topic_score_gemma":0.00002785358,"teacher_disagreement_score":0.9677429,"about_ca_system_score_codex":0.000509574,"about_ca_system_score_gemma":0.00027176985,"threshold_uncertainty_score":0.9999226},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000038224374,0.00014294824,0.99240905,0.0019190968,0.0010851818,0.0003908481,0.000045580302,0.00017091955,0.0037981526],"genre_scores_gemma":[0.0037741775,0.000043281525,0.99164057,0.0012583686,0.0007530901,0.000056405384,0.000029386794,0.0000315725,0.0024131308],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99685913,0.000014796922,0.00044103587,0.0013261668,0.0007355821,0.0006232938],"domain_scores_gemma":[0.9973328,0.00078850525,0.00038262096,0.0010102302,0.00035120113,0.00013462277],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00076673157,0.000366164,0.00039133578,0.00045620426,0.00037149916,0.0007809184,0.0022925434,0.00029946264,0.000020030793],"category_scores_gemma":[0.0002271915,0.00035813608,0.00012527622,0.000525913,0.00015259124,0.00060003175,0.00073653075,0.00039231693,0.00005687326],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011551186,0.000034434117,0.00010632147,0.000027469421,0.000015205547,0.000009161165,0.000622351,0.00095005,0.000042997584,0.02843718,0.0011272314,0.96862644],"study_design_scores_gemma":[0.00033880898,0.00013250708,0.00012421266,0.0002083406,0.000015661408,0.000024535448,3.080924e-7,0.8761788,0.00078356045,0.101744995,0.019713588,0.00073469215],"about_ca_topic_score_codex":0.000018036813,"about_ca_topic_score_gemma":0.000014186846,"teacher_disagreement_score":0.96789175,"about_ca_system_score_codex":0.00044497388,"about_ca_system_score_gemma":0.00022409674,"threshold_uncertainty_score":0.99988705},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001163359,0.0004393656,0.99566567,0.0018730214,0.00076251634,0.0005460611,0.00030740615,0.00009056752,0.0001990767],"genre_scores_gemma":[0.047057383,0.00005940974,0.95043105,0.001312087,0.0008457701,0.000026137059,0.00019489219,0.000025393729,0.00004789617],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99628794,0.0000464538,0.00066906516,0.0020068102,0.0004322779,0.0005574739],"domain_scores_gemma":[0.99534297,0.0009772247,0.00036825024,0.0026040415,0.00041081998,0.00029668276],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0022225063,0.00038356654,0.00050259166,0.00029581113,0.0003664305,0.00054602645,0.004469513,0.00028208556,0.0000030697838],"category_scores_gemma":[0.00018088537,0.0003467622,0.000036894235,0.0005268788,0.0010086055,0.0014439542,0.0020112086,0.0005811483,0.000005075925],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003555216,0.000035659752,0.00017558668,0.000020606538,0.000008575815,0.0000040265,0.00079588644,0.000016254937,0.000005345497,0.035302237,0.00005545062,0.9635768],"study_design_scores_gemma":[0.0005337446,0.0009848628,0.0016675254,0.00036888247,0.000017691198,0.00007612265,0.0000037754337,0.9237269,0.0001271535,0.05114169,0.020293418,0.0010582465],"about_ca_topic_score_codex":0.000017065004,"about_ca_topic_score_gemma":0.00008896027,"teacher_disagreement_score":0.9625186,"about_ca_system_score_codex":0.000055374836,"about_ca_system_score_gemma":0.00074603077,"threshold_uncertainty_score":0.99989843},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034329959,0.0000061183846,0.9714922,0.0015349223,0.0001040484,0.000052336156,0.0000070051406,0.00019481027,0.023175608],"genre_scores_gemma":[0.3466588,0.0000023986029,0.6456619,0.00075641763,0.0001638936,0.00004195416,0.00006341088,0.0000069936077,0.0066442345],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994537,0.000012888576,0.000077760305,0.00019964552,0.00017059453,0.00008540696],"domain_scores_gemma":[0.99954116,0.000039542574,0.000025474199,0.00025481652,0.00006525749,0.000073734736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012712467,0.000048400572,0.000036913138,0.000049288552,0.00006247025,0.000051637617,0.00021419411,0.000014764205,0.000016657528],"category_scores_gemma":[0.00004152538,0.000041787443,0.000010871711,0.00028533992,0.0000099157105,0.0004012411,0.00007113589,0.00005630026,0.00039031717],"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":[0.0000019880079,0.00008636353,0.0012294739,7.5865506e-7,0.0000046686946,5.8149897e-7,0.00009547795,0.0005543428,0.000055459568,0.85154575,0.088675976,0.057749145],"study_design_scores_gemma":[0.00031167196,0.000084242674,0.015304278,0.000009384899,0.0000024580415,0.000020726753,0.00003262456,0.70751655,0.0016649824,0.006396892,0.26846427,0.0001919068],"about_ca_topic_score_codex":0.00011864004,"about_ca_topic_score_gemma":0.0000102265585,"teacher_disagreement_score":0.84514886,"about_ca_system_score_codex":0.000027947399,"about_ca_system_score_gemma":0.0000707676,"threshold_uncertainty_score":0.50168675},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000014949883,0.00029143426,0.99774104,0.0005243275,0.00055702333,0.0005991174,0.000056952533,0.000110395704,0.000104728875],"genre_scores_gemma":[0.000559867,0.000008372399,0.99821484,0.000339301,0.00028139137,0.00002534762,0.00007318036,0.0000249368,0.0004727702],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99752665,0.000021990249,0.0003785087,0.0012688888,0.0004328059,0.00037118714],"domain_scores_gemma":[0.9979363,0.00052770786,0.0003295906,0.00070200197,0.00037573965,0.00012864471],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00094131584,0.0003308109,0.00027659335,0.0006523399,0.00053748226,0.00041607127,0.0008269886,0.00034041464,0.0000027089934],"category_scores_gemma":[0.00010476879,0.0003256455,0.00007963891,0.0005454778,0.00030482124,0.0006690772,0.00036283716,0.00043943292,0.0000057763586],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002544841,0.000050995124,0.00002055395,0.00001772718,0.000009238877,0.0000016018089,0.00026316303,0.006056442,0.0010182186,0.01806238,0.000018545554,0.9744786],"study_design_scores_gemma":[0.0003502843,0.00005655247,0.00033495048,0.00014333779,0.000017023913,0.000049261318,5.9897366e-7,0.9888592,0.0003138955,0.006411904,0.0031108917,0.00035214442],"about_ca_topic_score_codex":0.000020186599,"about_ca_topic_score_gemma":0.00008705131,"teacher_disagreement_score":0.9828027,"about_ca_system_score_codex":0.00027803078,"about_ca_system_score_gemma":0.00027702926,"threshold_uncertainty_score":0.99991953},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003197316,0.000065726024,0.9920288,0.0023855723,0.0011817265,0.00037874444,0.00010852701,0.00022329485,0.0033079316],"genre_scores_gemma":[0.020975748,0.00002723976,0.97438794,0.0021597217,0.0007507783,0.000055772423,0.000034071254,0.000041248008,0.0015674498],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99645555,0.000015394417,0.00042498726,0.0017731665,0.0007545164,0.0005763709],"domain_scores_gemma":[0.9969962,0.0003297641,0.00018179607,0.0020355955,0.00015290183,0.00030372993],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002782667,0.00043748165,0.00038323738,0.0006141259,0.00031284342,0.0007518431,0.0040323474,0.00022985964,0.00009503354],"category_scores_gemma":[0.00005457692,0.00042348134,0.00009326135,0.00066641136,0.00019454944,0.0005255638,0.0016101449,0.0005560248,0.00031836078],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.5547107e-7,0.0000204268,0.00013480628,0.000005902439,0.0000072617413,0.000021047324,0.0008924932,0.0023047437,0.0000393708,0.0056071877,0.00030313258,0.990663],"study_design_scores_gemma":[0.00034699956,0.0002704616,0.0030813771,0.0008171018,0.0000235243,0.000065864195,0.0000011393416,0.9020487,0.0013695871,0.041919865,0.04819908,0.0018562932],"about_ca_topic_score_codex":0.000101621816,"about_ca_topic_score_gemma":0.000092547125,"teacher_disagreement_score":0.98880666,"about_ca_system_score_codex":0.00021155021,"about_ca_system_score_gemma":0.00018930806,"threshold_uncertainty_score":0.9998217},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018678521,0.00006277092,0.99690664,0.00022946164,0.0013306403,0.00026775786,0.000010309356,0.00017727561,0.000828348],"genre_scores_gemma":[0.18796988,0.000014281415,0.8096615,0.0011686927,0.0008625846,0.000015574755,0.000012711586,0.000051774954,0.00024297129],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968035,0.00002609433,0.0004371884,0.0014594921,0.0007318445,0.00054185896],"domain_scores_gemma":[0.99761564,0.00016413035,0.0003085763,0.0015810513,0.00016176446,0.00016881627],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005977993,0.00042354918,0.00036991012,0.0004809663,0.00034616725,0.0006482832,0.0027502228,0.00023839588,0.000012822842],"category_scores_gemma":[0.000029889163,0.00040898402,0.0001032116,0.0004764207,0.00038956053,0.0004349923,0.001070783,0.00060122926,0.00008050953],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.9951675e-7,0.00001007046,0.000019991146,0.000010241412,0.000005313433,0.000009478734,0.0001911346,0.0056097237,0.00038481617,0.00129013,0.0000039076513,0.9924648],"study_design_scores_gemma":[0.00012729087,0.00006843661,0.000083401654,0.0002024362,0.000008164196,0.0000927869,1.0648434e-7,0.9800646,0.0026744874,0.014257378,0.0018952707,0.00052569795],"about_ca_topic_score_codex":0.00021435246,"about_ca_topic_score_gemma":0.0001368312,"teacher_disagreement_score":0.99193907,"about_ca_system_score_codex":0.0003569123,"about_ca_system_score_gemma":0.00026141744,"threshold_uncertainty_score":0.9998362},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000019040814,0.00018592709,0.98892784,0.004608754,0.0011388854,0.00039169626,0.000051397645,0.00011334825,0.0045802556],"genre_scores_gemma":[0.0007142113,0.000058170564,0.99316317,0.0043511116,0.00041502295,0.00005857058,0.000021895898,0.000031648764,0.00118622],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964867,0.000024845049,0.00043125547,0.0013754052,0.0010825469,0.000599246],"domain_scores_gemma":[0.9972254,0.0009657307,0.00026593808,0.0010295438,0.00026853892,0.00024484211],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013458644,0.00037260173,0.00042995258,0.00036383327,0.00033046515,0.000493393,0.003470652,0.00037076854,0.000023340986],"category_scores_gemma":[0.0004376381,0.00033747716,0.00013396176,0.00044592176,0.00064847147,0.00043385313,0.00072234194,0.0006389798,0.000028628583],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.824411e-7,0.000025949836,0.000008677997,0.000013380797,0.000013738972,0.000015476988,0.00023333765,0.00018273087,0.000011747305,0.059147213,0.0016759636,0.9386708],"study_design_scores_gemma":[0.00046796555,0.00017337852,0.000058177204,0.00027541473,0.000013398851,0.00004509824,4.0850378e-7,0.6411299,0.00069560634,0.30930725,0.04698234,0.00085104717],"about_ca_topic_score_codex":0.0000083253435,"about_ca_topic_score_gemma":0.000019555178,"teacher_disagreement_score":0.9378198,"about_ca_system_score_codex":0.00028112208,"about_ca_system_score_gemma":0.0007870099,"threshold_uncertainty_score":0.99990773},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000058323516,0.0008119701,0.18282042,0.000058636357,0.0010970162,0.0007239565,0.0068944846,0.0001927439,0.80734247],"genre_scores_gemma":[0.0011349686,0.0014983015,0.4288721,0.00013811045,0.002852597,0.00030830415,0.0067075565,0.00025002522,0.558238],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99737346,0.000030086936,0.0007240854,0.00088516384,0.0006561879,0.00033098925],"domain_scores_gemma":[0.99638593,0.00017145222,0.0007447285,0.0022367034,0.00025401986,0.00020715898],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00043784562,0.00043514278,0.0006032454,0.00021869746,0.00011157698,0.0001208449,0.0014822254,0.00017722079,0.00019553355],"category_scores_gemma":[0.00003051362,0.00036890942,0.00007800463,0.00010844113,0.00039214047,0.00045262117,0.00045585213,0.000247161,0.00032701658],"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":[0.000012192806,0.00012067137,0.000084199164,0.0008019675,0.00047020425,0.0002606316,0.0014689456,0.000009946783,0.0000513794,0.62834525,0.32163128,0.04674336],"study_design_scores_gemma":[0.0003262004,0.00017760013,0.000008649033,0.001834407,0.000068242065,0.00016089116,0.00009744488,0.0018227799,0.000018339479,0.00022334079,0.9946391,0.0006229992],"about_ca_topic_score_codex":0.00010329029,"about_ca_topic_score_gemma":0.000024175688,"teacher_disagreement_score":0.67300785,"about_ca_system_score_codex":0.00005068275,"about_ca_system_score_gemma":0.00035979,"threshold_uncertainty_score":0.99987626},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035398514,0.000054368884,0.99073577,0.0018287719,0.00007077836,0.00008316825,0.00018384158,0.00026824092,0.0032352135],"genre_scores_gemma":[0.15959531,0.0000057503003,0.838917,0.000603266,0.00009136093,0.000006326741,0.00057408155,0.0000094229135,0.00019744594],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865127,0.000009513343,0.00023146653,0.00054914464,0.00024230818,0.00031632851],"domain_scores_gemma":[0.9976329,0.00012234841,0.00008589683,0.0019720534,0.00005762536,0.00012912594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057021837,0.00011278587,0.000104184524,0.000049740673,0.00017398264,0.00029134649,0.0025068428,0.000042309803,0.000009141031],"category_scores_gemma":[0.000038644965,0.00009791273,0.000021280448,0.0005112815,0.000039588038,0.0011256874,0.0012722267,0.00008514881,0.000019883466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020189684,0.00012924723,0.00046258513,0.000008054182,0.000027410742,0.00002402458,0.0009505023,0.000198716,0.00012979223,0.0926313,0.08251745,0.8229189],"study_design_scores_gemma":[0.00012029501,0.000011737956,0.00047211585,0.000018510573,0.0000042904126,0.000015242935,0.00022960114,0.9811539,0.00026177787,0.0016450395,0.015901988,0.0001654802],"about_ca_topic_score_codex":0.00015500846,"about_ca_topic_score_gemma":0.0000319574,"teacher_disagreement_score":0.9809552,"about_ca_system_score_codex":0.000016540716,"about_ca_system_score_gemma":0.000034024957,"threshold_uncertainty_score":0.46583793},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007941475,0.000030205665,0.9887905,0.0011364012,0.00008634671,0.00021805163,0.000029265102,0.00013320631,0.0016345349],"genre_scores_gemma":[0.08568987,0.000015539068,0.91353506,0.0002340758,0.00008967371,0.00013008462,0.000012050317,0.00000665942,0.00028699372],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993464,0.000008544684,0.00009724786,0.00028268955,0.00010205041,0.00016307291],"domain_scores_gemma":[0.9994677,0.00017331532,0.0000628256,0.00015766663,0.000095317235,0.000043175274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000221391,0.000071417795,0.00008370755,0.000044019485,0.00018761947,0.00016257926,0.00019222172,0.00004045428,9.60999e-7],"category_scores_gemma":[0.00008562302,0.000066158536,0.000025743715,0.00014511055,0.000013086498,0.00045916883,0.000087935405,0.000048425576,0.00001195549],"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":[0.000002241753,0.00009212663,0.00044243882,0.000008248001,0.0000549168,7.975902e-7,0.0023542813,0.000034617908,0.0003776299,0.7422189,0.00033613716,0.25407764],"study_design_scores_gemma":[0.0034720988,0.00047344007,0.08522903,0.000060113165,0.00004637656,0.00003098448,0.0011413537,0.24184442,0.01378783,0.6458532,0.0071196877,0.00094144203],"about_ca_topic_score_codex":0.00015283527,"about_ca_topic_score_gemma":0.000023329449,"teacher_disagreement_score":0.25313622,"about_ca_system_score_codex":0.00013592743,"about_ca_system_score_gemma":0.00003923672,"threshold_uncertainty_score":0.2697867},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000025077166,0.000106031046,0.99667835,0.00055401487,0.0005628273,0.00078855467,0.00006879794,0.00020446889,0.0010118558],"genre_scores_gemma":[0.0025969208,0.0000036926356,0.9944499,0.0006999195,0.00044376252,0.0001624014,0.00029377508,0.000033851848,0.0013157747],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99620503,0.0000504429,0.00045106537,0.001683642,0.0008684675,0.0007413298],"domain_scores_gemma":[0.9969475,0.0011013164,0.0005017796,0.000823388,0.00047742476,0.00014859007],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001529452,0.00046700283,0.00049573166,0.00049545756,0.000691801,0.0010516979,0.0026217191,0.00033745507,0.0000015558719],"category_scores_gemma":[0.000502063,0.0004491562,0.00013573932,0.0009411015,0.00022472253,0.0006004449,0.00064737006,0.00072693283,0.000008636388],"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":[0.000003308911,0.00015884494,0.000042272706,0.000068042275,0.000021396781,0.0000030485937,0.001800192,0.71749306,0.00015177055,0.0023751615,0.0002562753,0.27762663],"study_design_scores_gemma":[0.00066910643,0.00014357119,0.000067040746,0.00020813479,0.000012918542,0.000005809671,0.0000011542354,0.99167114,0.00054378825,0.0020188915,0.0041228053,0.0005356481],"about_ca_topic_score_codex":0.000019421399,"about_ca_topic_score_gemma":0.000013238078,"teacher_disagreement_score":0.27709097,"about_ca_system_score_codex":0.0020740733,"about_ca_system_score_gemma":0.0032259938,"threshold_uncertainty_score":0.9999853},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62600243,0.00014011339,0.37010932,0.00080895826,0.00011527458,0.00011529319,0.0005018067,0.0000844774,0.0021223368],"genre_scores_gemma":[0.81616294,0.00001754138,0.18333058,0.00020212262,0.00002419099,0.000007016183,0.00003850528,0.000004131549,0.00021299304],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992536,0.000013021276,0.00018536585,0.0002449822,0.00013069643,0.00017234111],"domain_scores_gemma":[0.99928534,0.000046968795,0.00004954227,0.00055678224,0.000021204158,0.00004015326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000073797055,0.00007509217,0.000105309395,0.000072140545,0.000031898468,0.000028985825,0.0005221895,0.000020479725,0.00032409938],"category_scores_gemma":[0.000019461806,0.00006391941,0.00001893079,0.00026451214,0.000013197727,0.00028395272,0.00021431019,0.000062980514,0.000014318937],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015818198,0.00093604217,0.32731047,0.00009900915,0.00003257857,0.000046597444,0.004267426,0.00009564373,0.006373751,0.1513895,0.027715972,0.4817314],"study_design_scores_gemma":[0.0013679565,0.00009910355,0.14683025,0.00017819412,0.000012638288,0.00006555641,0.0006681827,0.7808631,0.013629933,0.00041604956,0.05515053,0.00071849144],"about_ca_topic_score_codex":0.00017604808,"about_ca_topic_score_gemma":0.00023251005,"teacher_disagreement_score":0.7807675,"about_ca_system_score_codex":0.000009410926,"about_ca_system_score_gemma":0.0000072835937,"threshold_uncertainty_score":0.3548661},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000026510006,0.00050684426,0.9920004,0.0010267746,0.001000068,0.00032027139,0.000037841444,0.00023884272,0.004842424],"genre_scores_gemma":[0.0075077526,0.00030274116,0.98678195,0.0030860153,0.00075596565,0.00004200735,0.00004755237,0.000055427277,0.0014205986],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960545,0.000021640637,0.00053182396,0.0017342566,0.000995735,0.0006620717],"domain_scores_gemma":[0.9969459,0.0002943334,0.00026229853,0.0020683173,0.0001992949,0.00022983665],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004883879,0.00050840474,0.00047578017,0.000638643,0.00037782383,0.0005489742,0.004336214,0.00027281436,0.00003412976],"category_scores_gemma":[0.000053987722,0.0004676162,0.00013431264,0.0007064834,0.0006850904,0.0006244933,0.0015710061,0.0006904516,0.0002202353],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012187814,0.00004804408,0.000014984792,0.000016646802,0.000011516107,0.00012673449,0.0007864888,0.0017056605,0.00006075758,0.021529093,0.001482227,0.97421664],"study_design_scores_gemma":[0.00037217658,0.00020587673,0.00016114881,0.00039569344,0.000010212572,0.0004050063,1.512267e-7,0.7792737,0.0008158314,0.06706072,0.14994071,0.0013588007],"about_ca_topic_score_codex":0.00005213058,"about_ca_topic_score_gemma":0.00003117881,"teacher_disagreement_score":0.97285783,"about_ca_system_score_codex":0.00024353534,"about_ca_system_score_gemma":0.0005570653,"threshold_uncertainty_score":0.99977756},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000016950851,0.000020190439,0.97963583,0.007830408,0.0006099223,0.00052721216,0.0000262966,0.00013059992,0.011202555],"genre_scores_gemma":[0.008163584,0.000020813317,0.9802631,0.008210736,0.000515904,0.000077752426,0.00002102692,0.00004022786,0.0026868144],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963032,0.00007985211,0.00041188073,0.0013511836,0.001231317,0.00062258623],"domain_scores_gemma":[0.99674255,0.00088822196,0.00039203407,0.0016260374,0.0002323895,0.00011877414],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002339544,0.0004149243,0.00034865123,0.0003253211,0.00050177914,0.0007635095,0.0037209566,0.00020679679,0.000036082347],"category_scores_gemma":[0.00021623967,0.00024951066,0.00011574637,0.00078537833,0.00023978736,0.00035462694,0.0008223462,0.00081721623,0.00008283252],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000039702877,0.00007040827,0.00003933971,0.000011229771,0.00001076972,0.000018163797,0.0002248719,0.008901211,0.00013714458,0.016217902,0.00080693245,0.97355807],"study_design_scores_gemma":[0.00019777846,0.0001032753,0.00010698831,0.0002852483,0.0000067639244,0.00001299818,2.768528e-7,0.9621443,0.0010849898,0.019923156,0.015726414,0.0004077849],"about_ca_topic_score_codex":0.00009047031,"about_ca_topic_score_gemma":0.00005496634,"teacher_disagreement_score":0.97315025,"about_ca_system_score_codex":0.0009357178,"about_ca_system_score_gemma":0.00055510196,"threshold_uncertainty_score":0.9999957},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004747161,0.0014575341,0.9949104,0.00094484503,0.00025146897,0.00020363338,0.000012701638,0.00008784327,0.0020840869],"genre_scores_gemma":[0.02419083,0.00019141463,0.9730683,0.0016546841,0.00029060335,0.000010724616,0.00000889526,0.000017539915,0.00056701514],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978718,0.00002636583,0.0002669482,0.0011524794,0.00034796196,0.00033445354],"domain_scores_gemma":[0.9985916,0.0003472752,0.00012444203,0.0007146066,0.00009588911,0.00012618251],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004840876,0.00031749357,0.00028260765,0.0003185609,0.0003428837,0.0005876844,0.0011099733,0.0001479067,0.000004454927],"category_scores_gemma":[0.000037097816,0.00028759253,0.000032288022,0.00025273548,0.00058463385,0.00073283486,0.001257149,0.0004192627,0.000006268767],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016280368,0.000008743613,0.000007987543,0.000009797412,0.000003996412,0.00001636654,0.00076734775,0.00078438746,0.000017239876,0.050059043,0.000024036257,0.9482994],"study_design_scores_gemma":[0.0001336116,0.000109397806,0.0005649727,0.00021565979,0.0000055123505,0.00016309826,3.5130648e-7,0.6655185,0.000044730456,0.3303015,0.002560403,0.0003822342],"about_ca_topic_score_codex":0.000008300389,"about_ca_topic_score_gemma":0.00001025795,"teacher_disagreement_score":0.94791716,"about_ca_system_score_codex":0.00008213897,"about_ca_system_score_gemma":0.00013651619,"threshold_uncertainty_score":0.9999576},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003417349,0.0004984626,0.99487126,0.00069788186,0.00093665766,0.0006669083,0.00016541591,0.00022772526,0.0019015303],"genre_scores_gemma":[0.0037758672,0.00007757278,0.9937743,0.0010849648,0.00059227436,0.00008374182,0.000109458444,0.00005092135,0.00045091473],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957771,0.000015445497,0.0006056854,0.0020030283,0.0008034526,0.00079533184],"domain_scores_gemma":[0.9966231,0.00079395896,0.00029028536,0.0017829806,0.00027220984,0.0002374917],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00065916125,0.00054904073,0.0005422843,0.0010680928,0.00044063845,0.0009911016,0.004494594,0.00031614522,0.00004435672],"category_scores_gemma":[0.0001279286,0.00052505394,0.00015646948,0.0013544793,0.00036349733,0.0006426918,0.0008291065,0.00049950206,0.00007042751],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010262971,0.000026224969,0.000008124835,0.000018839679,0.000009131501,0.000018249015,0.00022349933,0.004908505,0.0000061403816,0.006644955,0.00019341012,0.9879419],"study_design_scores_gemma":[0.0003042905,0.000176265,0.0000742362,0.00034166643,0.000012826445,0.00007764261,1.8848495e-7,0.9037161,0.0002540932,0.06593687,0.028272653,0.00083320134],"about_ca_topic_score_codex":0.00002851885,"about_ca_topic_score_gemma":0.000013343354,"teacher_disagreement_score":0.9871087,"about_ca_system_score_codex":0.0002543298,"about_ca_system_score_gemma":0.00048496737,"threshold_uncertainty_score":0.9997201},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004224105,0.00014835103,0.99609005,0.00021861865,0.0008810899,0.00048387202,0.000066037144,0.00023957768,0.001830147],"genre_scores_gemma":[0.03466648,0.000090625515,0.96251404,0.00055946974,0.000989214,0.00013526563,0.00015539853,0.00006822202,0.00082125806],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973171,0.000018128614,0.0004389882,0.0011101507,0.00065365375,0.00046202578],"domain_scores_gemma":[0.99816173,0.00036862024,0.00037187064,0.0008354481,0.00017050555,0.000091843845],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006568819,0.0003265661,0.0003608663,0.00040049973,0.00035258217,0.000876501,0.00184436,0.0002146882,0.0000056303556],"category_scores_gemma":[0.000055807828,0.00031854544,0.00010237026,0.0004623137,0.00009505778,0.0007296334,0.00039256155,0.00023503305,0.000050128652],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022476058,0.000021525948,0.000020951855,0.000063322725,0.000012850597,0.000004034465,0.00045984634,0.008898785,0.00005002783,0.08472805,0.000048702543,0.90568966],"study_design_scores_gemma":[0.00019097679,0.00006864984,0.00005890746,0.00044026258,0.000012766765,0.000015518308,3.3009616e-7,0.962137,0.00037181034,0.029183866,0.007064973,0.00045494759],"about_ca_topic_score_codex":0.000032813514,"about_ca_topic_score_gemma":0.000017134558,"teacher_disagreement_score":0.9532382,"about_ca_system_score_codex":0.0007205187,"about_ca_system_score_gemma":0.0002738156,"threshold_uncertainty_score":0.9999267},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6585048,0.00000880609,0.3387102,0.0009186975,0.000066214256,0.00011328662,0.00014555153,0.000067609224,0.0014648839],"genre_scores_gemma":[0.89556336,0.0000022658617,0.1032751,0.0000808329,0.000057449175,5.423239e-7,0.000097565055,0.0000037025625,0.0009191622],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99920976,0.00001707689,0.00010047149,0.00024021896,0.00032035977,0.00011211811],"domain_scores_gemma":[0.9993617,0.000023719254,0.00010105102,0.00017691813,0.00028579214,0.0000508026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012764822,0.000068901514,0.00008144188,0.00012243283,0.00019289003,0.000043308108,0.00042599236,0.00004281314,0.000017650817],"category_scores_gemma":[0.000013653403,0.00008371494,0.000032584234,0.000289922,0.000022675651,0.00037329592,0.00012696153,0.000057909532,0.00001954416],"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":[0.00006286735,0.0021029608,0.06730192,0.00014296896,0.00015176181,0.000065338616,0.0032613124,0.01634229,0.030824423,0.62083894,0.17036201,0.08854322],"study_design_scores_gemma":[0.0017099802,0.00016828447,0.58064115,0.00015073144,0.00003337543,0.000017200204,0.00077802816,0.13646586,0.010234704,0.0050512287,0.26396376,0.00078570814],"about_ca_topic_score_codex":0.00017908242,"about_ca_topic_score_gemma":0.00009366084,"teacher_disagreement_score":0.6157877,"about_ca_system_score_codex":0.00010593769,"about_ca_system_score_gemma":0.00008934271,"threshold_uncertainty_score":0.3413796},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005880407,0.00014574351,0.99452597,0.0012951457,0.00037197725,0.00034294624,0.000036730442,0.00010303143,0.0031196354],"genre_scores_gemma":[0.0060377247,0.000034523386,0.99148554,0.0013470832,0.00036855953,0.00003201737,0.00001762934,0.000026311878,0.00065062585],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976395,0.000013979389,0.00028939766,0.0011614818,0.0004463708,0.00044931413],"domain_scores_gemma":[0.99777937,0.0010483605,0.00024695238,0.0006669227,0.00013418251,0.00012423044],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00066462194,0.00032749132,0.00033081343,0.00041111305,0.00042809997,0.0005858276,0.0015539816,0.00019614637,0.0000032321307],"category_scores_gemma":[0.0001452274,0.000305165,0.00006393881,0.00023101324,0.0003735388,0.0004374538,0.0006324289,0.0004756119,0.000011215835],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014004657,0.000010391124,0.0000053266913,0.000008097552,0.000007558962,0.0000028194008,0.0005566582,0.0011567948,0.000022166634,0.13864456,0.00007484921,0.85950935],"study_design_scores_gemma":[0.00020866127,0.0001420213,0.00008891519,0.00027205894,0.0000065369095,0.000009034426,5.01195e-7,0.8263487,0.00011436758,0.16632967,0.0060767713,0.00040276654],"about_ca_topic_score_codex":0.000006049033,"about_ca_topic_score_gemma":0.000015673699,"teacher_disagreement_score":0.8591066,"about_ca_system_score_codex":0.00022882834,"about_ca_system_score_gemma":0.00023568788,"threshold_uncertainty_score":0.99994004},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9105026,0.000014693185,0.085278116,0.00028510744,0.000010507005,0.00003430769,0.000027473083,0.000025857578,0.0038213406],"genre_scores_gemma":[0.70391667,0.000008778189,0.2958988,0.00002102995,0.0000090688045,0.0000038513917,0.00003459811,0.0000011361993,0.00010607746],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99939054,0.00001156219,0.00020801055,0.00013049936,0.00017592139,0.0000834661],"domain_scores_gemma":[0.99948615,0.00003551669,0.00018198248,0.00023989828,0.000038402828,0.000018073088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003072018,0.000043997246,0.00012722697,0.00013473199,0.000034121564,0.000019088355,0.00033512915,0.000020817939,0.000021342943],"category_scores_gemma":[0.000009220438,0.000039565726,0.000045463476,0.00058939547,0.000012717127,0.0003221413,0.00010564929,0.00002245571,0.0000074928157],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002366235,0.00029783178,0.13795075,0.000018857718,0.00085708086,6.6079394e-8,0.0016076206,0.0068732714,0.001508408,0.02642566,0.0013155979,0.82314247],"study_design_scores_gemma":[0.000060726292,0.00001102436,0.05138854,0.000002751204,0.00007026506,1.10731534e-7,0.000059458576,0.94249785,0.0053176014,0.0000066699513,0.0005387058,0.000046286477],"about_ca_topic_score_codex":0.000027282062,"about_ca_topic_score_gemma":0.000016819016,"teacher_disagreement_score":0.9356246,"about_ca_system_score_codex":0.000029092478,"about_ca_system_score_gemma":0.000013572839,"threshold_uncertainty_score":0.16134435},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020918582,0.00006850541,0.96656173,0.004690755,0.000037173482,0.00014094339,0.000069182046,0.000213229,0.0072999136],"genre_scores_gemma":[0.028744379,0.0000043890473,0.9693526,0.00076286215,0.00016785425,0.000033168173,0.000023975328,0.0000071100244,0.00090365665],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99927163,0.000021305787,0.00009976405,0.0002822954,0.00014016373,0.00018484624],"domain_scores_gemma":[0.9993386,0.00003713503,0.000050125833,0.0003729862,0.00012497217,0.000076158176],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000075099124,0.00009998601,0.00008633815,0.000041028263,0.00038106108,0.00027949686,0.00028738024,0.000027631046,0.000025701238],"category_scores_gemma":[0.000009753096,0.00007668911,0.000016419739,0.00059137086,0.0000360003,0.0006686216,0.00007972983,0.00007803711,0.00003746783],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008697603,0.0007990899,0.0012237122,0.00002139522,0.00015885198,0.0000329196,0.0055378876,0.17015895,0.023253055,0.3128879,0.12773935,0.35817817],"study_design_scores_gemma":[0.00019785494,0.000040705043,0.00014171899,0.000020799107,0.00001084093,0.00002752081,0.00026664144,0.9395276,0.004004166,0.00019205312,0.055352267,0.00021789025],"about_ca_topic_score_codex":0.000029142546,"about_ca_topic_score_gemma":0.00013231245,"teacher_disagreement_score":0.7693686,"about_ca_system_score_codex":0.000030572723,"about_ca_system_score_gemma":0.000118133015,"threshold_uncertainty_score":0.31272912},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000021536057,0.0011245429,0.9794897,0.00012986847,0.00015370028,0.0011556669,0.00010104482,0.0002437378,0.017599571],"genre_scores_gemma":[0.00013237544,0.00015799332,0.9939919,0.00023694616,0.00012120218,0.001302389,0.0003566875,0.000024897765,0.0036756094],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998802,0.0000061398578,0.00046459888,0.0003744816,0.000116171854,0.00023657421],"domain_scores_gemma":[0.9982293,0.0002996739,0.00047574908,0.00041084868,0.00048224555,0.00010218549],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027254355,0.00029726906,0.00026320934,0.00023392905,0.0008328385,0.00042711542,0.000473047,0.00026466607,0.000002349038],"category_scores_gemma":[0.00013876738,0.00030085235,0.00005332577,0.00014266587,0.0000867854,0.002443193,0.00027678578,0.0004697501,0.000053391694],"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":[0.0000018288347,0.000006539813,3.2274934e-7,0.00027233828,0.000006924943,5.501467e-8,0.001095727,9.2724855e-7,0.000021034894,0.2770216,0.000021508096,0.7215512],"study_design_scores_gemma":[0.0005127024,0.00002898531,0.000009040111,0.0010166328,0.000028129176,0.000013413192,0.00012300347,0.061520033,0.00049492205,0.03835316,0.8973001,0.0005998712],"about_ca_topic_score_codex":4.7124502e-7,"about_ca_topic_score_gemma":0.0000050709505,"teacher_disagreement_score":0.8972786,"about_ca_system_score_codex":0.000059140137,"about_ca_system_score_gemma":0.0002710267,"threshold_uncertainty_score":0.9999444},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7214713,0.000017070222,0.23387699,0.0012474632,0.00009478763,0.00014096405,0.00022854816,0.00014263898,0.04278023],"genre_scores_gemma":[0.70723367,0.0000053642366,0.29188743,0.00009266677,0.000022993987,5.6848368e-8,0.000069946705,0.0000032521305,0.00068461866],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99935234,0.000011882668,0.00008830265,0.00017939447,0.00027083379,0.00009726802],"domain_scores_gemma":[0.99953824,0.000037864374,0.00006641151,0.00012817146,0.00017885151,0.000050478797],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013587483,0.000054393287,0.00007342546,0.000073687326,0.00018527736,0.000024290508,0.00039270546,0.00003618549,0.0005411279],"category_scores_gemma":[0.00001210376,0.00006917723,0.00003060255,0.00025286232,0.00013189124,0.00034340774,0.00005526046,0.000049056736,0.000029689141],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010961162,0.0004680767,0.0031955403,0.000031721152,0.00012667503,0.000115014765,0.0055156127,0.0032143064,0.003964598,0.12751356,0.024239717,0.83160424],"study_design_scores_gemma":[0.0032853982,0.00021600856,0.036277603,0.00027652355,0.00008312835,0.00056579034,0.0029452469,0.5886593,0.002837295,0.0049272673,0.35855427,0.0013721557],"about_ca_topic_score_codex":0.000049614442,"about_ca_topic_score_gemma":0.000002509682,"teacher_disagreement_score":0.8302321,"about_ca_system_score_codex":0.00006148295,"about_ca_system_score_gemma":0.00020443038,"threshold_uncertainty_score":0.59249717},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001919394,0.00065131387,0.9892708,0.00044802108,0.00046577555,0.00043569604,0.000026176755,0.00009574239,0.008587296],"genre_scores_gemma":[0.015583843,0.00016966158,0.9799994,0.00040096615,0.0005609145,0.000073268864,0.00001944496,0.000023536497,0.003168922],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99784476,0.000007503062,0.00028738755,0.001149301,0.00028953308,0.00042151735],"domain_scores_gemma":[0.99860746,0.00021658733,0.00012197925,0.00087625236,0.00008858454,0.00008914683],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00040191566,0.0003102724,0.00026225887,0.00037056874,0.0003010033,0.001352897,0.0017047571,0.00012009404,0.0000036884906],"category_scores_gemma":[0.000007745072,0.0002832886,0.00006186405,0.00025050927,0.00039569076,0.0012381279,0.0012283751,0.00022197735,0.000018771056],"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":[7.6103396e-7,0.000016962556,0.0000015355598,0.000031871765,0.0000055983837,0.0000024012038,0.00026459363,0.000706421,0.000008476332,0.27854154,0.00007459881,0.72034526],"study_design_scores_gemma":[0.0003467977,0.000114672686,0.0001733334,0.00030163093,0.000016544387,0.000029295163,0.000002031107,0.4091111,0.00008980128,0.5465711,0.04254723,0.0006964998],"about_ca_topic_score_codex":0.0000038982457,"about_ca_topic_score_gemma":0.00003177786,"teacher_disagreement_score":0.7196488,"about_ca_system_score_codex":0.00010618386,"about_ca_system_score_gemma":0.00019620272,"threshold_uncertainty_score":0.9999619},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22865391,0.00019933151,0.08030681,0.028746646,0.0009537881,0.00053730595,0.00037197783,0.00022630757,0.6600039],"genre_scores_gemma":[0.8999442,0.00005305398,0.09195472,0.0001536735,0.00006543886,0.0000092226,0.0000085142665,0.0000042807715,0.007806918],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99940884,0.0000030999133,0.000106559135,0.00028252383,0.00012281937,0.00007615919],"domain_scores_gemma":[0.9992151,0.00005241128,0.000057378173,0.000595756,0.00005524703,0.0000241085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000099477205,0.000058021647,0.000058041598,0.000027331698,0.0000662389,0.0002194393,0.0026797757,0.00001653075,0.000026636224],"category_scores_gemma":[0.000055660388,0.00003672913,0.0000099436475,0.00014280251,0.00005816026,0.00076799287,0.001921159,0.000051292383,0.00000972552],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011806114,0.0001905945,0.0018491632,0.000011380122,0.000020764279,2.421669e-7,0.0014524389,3.2491005e-7,0.0011795016,0.7417497,0.07808691,0.17545779],"study_design_scores_gemma":[0.00031819392,0.000058442616,0.008268351,0.00011883117,0.00000892619,0.000014337987,0.00036993038,0.95477,0.0019626934,0.0026048203,0.03130316,0.00020231001],"about_ca_topic_score_codex":0.000007076924,"about_ca_topic_score_gemma":0.0000033436013,"teacher_disagreement_score":0.9547697,"about_ca_system_score_codex":0.000006071718,"about_ca_system_score_gemma":0.000011290686,"threshold_uncertainty_score":0.49797347},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008455006,0.00070045516,0.99570125,0.00020042932,0.0008546669,0.0002631136,0.000028672777,0.00009492877,0.0013109922],"genre_scores_gemma":[0.06377203,0.00002729733,0.9355007,0.00031595098,0.00026544233,0.000007093086,0.000014419664,0.000033129054,0.00006395834],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967175,0.000023292905,0.00061674754,0.0011523226,0.0008501493,0.00064000353],"domain_scores_gemma":[0.9969814,0.00031298219,0.0004921058,0.0017585754,0.00025955105,0.0001954306],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00073528115,0.0004355335,0.000520008,0.00062093395,0.00021757587,0.00028742696,0.003351198,0.00024972693,0.000015703099],"category_scores_gemma":[0.00006754598,0.00041024224,0.00010619003,0.0007149594,0.0005276582,0.00074108643,0.001689999,0.00044108136,0.000020270738],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.934852e-7,0.00004894739,0.00022861926,0.000046285273,0.000014599077,0.000014032146,0.0009555106,0.004819452,0.00079276983,0.007269497,0.000028995759,0.9857803],"study_design_scores_gemma":[0.00027049126,0.000093104296,0.00052670256,0.0009217883,0.000027851167,0.00014587908,5.280535e-7,0.97402173,0.0040711844,0.016739942,0.0022634617,0.0009173446],"about_ca_topic_score_codex":0.000059113096,"about_ca_topic_score_gemma":0.00002098092,"teacher_disagreement_score":0.984863,"about_ca_system_score_codex":0.00020424805,"about_ca_system_score_gemma":0.00045340374,"threshold_uncertainty_score":0.99983495},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000003156861,0.0016284693,0.9906341,0.0046538836,0.0006446166,0.0009849833,0.00006569866,0.00013446934,0.0012506496],"genre_scores_gemma":[0.0010749866,0.00013815575,0.995365,0.0018166952,0.00070158177,0.00012416717,0.000014256892,0.00003388716,0.000731256],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967429,0.000017307822,0.000512927,0.0014868365,0.0006002842,0.0006397573],"domain_scores_gemma":[0.9967808,0.00103925,0.000258604,0.0015351372,0.00023114528,0.00015502928],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009314031,0.0004687174,0.000436128,0.00029790375,0.0007412715,0.0010605804,0.0030608468,0.00021572357,0.000009409382],"category_scores_gemma":[0.000035040677,0.00034856456,0.0001262945,0.0004047306,0.0011127606,0.0005168633,0.0009068348,0.0005512204,0.000027716771],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.3589583e-7,0.000018663004,0.0000015661369,0.000015908263,0.000012314579,0.0000035815335,0.00034796097,0.0003417091,0.000011083825,0.027697066,0.00010662271,0.9714427],"study_design_scores_gemma":[0.00028531722,0.00014129984,0.000030079167,0.0001532984,0.000019348425,0.0001162874,4.520915e-7,0.73884255,0.00007968323,0.21818206,0.041674193,0.0004754195],"about_ca_topic_score_codex":0.000045797045,"about_ca_topic_score_gemma":0.000114700466,"teacher_disagreement_score":0.9709673,"about_ca_system_score_codex":0.0001208409,"about_ca_system_score_gemma":0.00049570925,"threshold_uncertainty_score":0.9999764},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13654678,0.0016334386,0.8278234,0.0003497444,0.003872914,0.00064710516,0.0042655007,0.001160498,0.0237006],"genre_scores_gemma":[0.054475155,0.00019270866,0.81619203,0.00095162337,0.00070475537,0.0002283087,0.10958346,0.00011602907,0.01755593],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99798316,0.000020498956,0.00035712172,0.0008708451,0.00041076905,0.00035762906],"domain_scores_gemma":[0.9981974,0.00012514336,0.00020320527,0.0012417156,0.00010725064,0.00012532479],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001422866,0.00028766808,0.00026784267,0.0001472168,0.00025043488,0.00035215923,0.0013918863,0.00011922508,0.00015422751],"category_scores_gemma":[0.00005631003,0.00027512058,0.00007894063,0.00043664256,0.000013496953,0.0004521038,0.00021226959,0.00020624232,0.0003896756],"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":[0.000022871402,0.0030015165,0.00091367384,0.00035683627,0.00057603413,0.0002949689,0.0136172855,0.00026669126,0.0036741646,0.39523277,0.21806648,0.3639767],"study_design_scores_gemma":[0.0052974485,0.00032356387,0.04786143,0.004361071,0.0005073884,0.000045182915,0.008886014,0.111973,0.041832767,0.004465621,0.76694256,0.0075039635],"about_ca_topic_score_codex":0.0011922669,"about_ca_topic_score_gemma":0.0005631158,"teacher_disagreement_score":0.54887605,"about_ca_system_score_codex":0.00007505464,"about_ca_system_score_gemma":0.0003019973,"threshold_uncertainty_score":0.9999701},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019103043,0.00019171565,0.9654648,0.0024111455,0.0005009854,0.0001593842,0.0292683,0.000039581686,0.00005383015],"genre_scores_gemma":[0.020229038,0.0002494069,0.97430706,0.00017310957,0.0006208663,0.000013834052,0.0043697665,0.000012296934,0.000024625951],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99523616,0.00017079194,0.00077741063,0.001741008,0.0014469689,0.0006276463],"domain_scores_gemma":[0.99103487,0.0017240809,0.0010162082,0.005064225,0.0008421538,0.00031844582],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.019297792,0.0002778236,0.0005499746,0.00040394688,0.0022243334,0.007570941,0.015764963,0.00010010822,0.000015552168],"category_scores_gemma":[0.009649204,0.0001855086,0.00006985463,0.0011860963,0.0006971346,0.0024257817,0.02033588,0.00060548994,0.0000052639575],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023008117,0.000117322474,0.005174021,0.000057074296,0.0017311022,0.00001213862,0.0011794847,0.00008570164,0.000049822378,0.015845276,0.10771348,0.8680116],"study_design_scores_gemma":[0.00015125066,0.000048666967,0.008948904,0.00010081334,0.0013448073,0.000028475608,0.00028783813,0.9661919,0.000008738364,0.011005937,0.011557314,0.00032537585],"about_ca_topic_score_codex":0.0001555048,"about_ca_topic_score_gemma":0.00013949502,"teacher_disagreement_score":0.9661062,"about_ca_system_score_codex":0.00014596934,"about_ca_system_score_gemma":0.0009227794,"threshold_uncertainty_score":0.99907464},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009114846,0.000015810661,0.98753446,0.0020940853,0.00009708681,0.00004723702,0.00052325445,0.0002697968,0.00030343133],"genre_scores_gemma":[0.16464499,0.000003339694,0.834594,0.00018901203,0.000060280086,0.0000051724246,0.0004862635,0.0000036655283,0.000013238056],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99917287,0.000005911267,0.00012523119,0.00039547,0.00014799918,0.00015252299],"domain_scores_gemma":[0.9983549,0.00004747991,0.000020280326,0.0014621958,0.000021138414,0.0000940053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008252116,0.00006470047,0.00006464429,0.00001643737,0.000081152306,0.00017837193,0.0021129304,0.000025711595,0.000017771936],"category_scores_gemma":[0.000055202923,0.00005480697,0.000011876875,0.0002258139,0.000025223932,0.0005975531,0.0009903802,0.000060893584,0.000085725784],"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":[0.0000015912468,0.00022546167,0.00059445685,0.0000023190712,0.000050117967,0.000014103296,0.00011804017,0.0002611442,0.0023113727,0.8447612,0.013993636,0.13766658],"study_design_scores_gemma":[0.0011426487,0.000070195165,0.031922705,0.00004894118,0.000032432265,0.000011035309,0.00003019864,0.7457108,0.00605567,0.08829442,0.12613076,0.00055022456],"about_ca_topic_score_codex":0.00032817555,"about_ca_topic_score_gemma":0.0000128554975,"teacher_disagreement_score":0.75646675,"about_ca_system_score_codex":0.00002209219,"about_ca_system_score_gemma":0.00005624987,"threshold_uncertainty_score":0.39263856},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00048811204,0.0005371153,0.9959957,0.0005598092,0.00012255246,0.00025875858,0.000009161516,0.00015192662,0.0018768375],"genre_scores_gemma":[0.14320964,0.000024016961,0.8556736,0.0005926457,0.00023170665,0.000014710298,0.000010881296,0.000031838445,0.00021094624],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99720335,0.000020965981,0.00032659838,0.0013534224,0.000568744,0.00052690704],"domain_scores_gemma":[0.99841,0.00043128306,0.00024292275,0.00062539714,0.00011904294,0.00017134009],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00073425594,0.00042237595,0.00037395212,0.00037386644,0.0005387554,0.0009908298,0.0014946961,0.00016541859,0.0000061086557],"category_scores_gemma":[0.00005704196,0.0003618573,0.0000278598,0.00045437992,0.0011046486,0.00083129236,0.0007808128,0.0006768244,0.000005403189],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012261916,0.000010032762,0.000030696177,0.000023620238,0.0000048224942,0.000014905519,0.0010743956,0.0008057574,0.00019547349,0.0018944738,0.000031817992,0.9959128],"study_design_scores_gemma":[0.0004206999,0.0002033458,0.000055164903,0.0013508967,0.000013906674,0.00036025103,0.0000025645327,0.9880051,0.0010382792,0.003110604,0.0045323544,0.0009068565],"about_ca_topic_score_codex":0.000006196479,"about_ca_topic_score_gemma":0.000015269285,"teacher_disagreement_score":0.9950059,"about_ca_system_score_codex":0.000113110946,"about_ca_system_score_gemma":0.0003646694,"threshold_uncertainty_score":0.99988335},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008454815,0.00008495407,0.9969191,0.00062359666,0.0006637477,0.0007856795,0.000034919107,0.00021577766,0.00058766914],"genre_scores_gemma":[0.009649567,0.0000017653321,0.9886514,0.0009846374,0.00026240104,0.0000840163,0.00003205991,0.000041179614,0.00029297665],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962392,0.000013365068,0.00057704083,0.0016385512,0.0008183788,0.0007134927],"domain_scores_gemma":[0.99645823,0.00071910047,0.00036406965,0.0014717376,0.00083345425,0.00015343353],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00190152,0.00046774166,0.0004330753,0.0006894669,0.00039783563,0.00065202336,0.0036383127,0.0002443867,0.0000036243669],"category_scores_gemma":[0.00031252953,0.00043814283,0.00010276445,0.0008453351,0.00041616661,0.00048284096,0.0009702931,0.0004661368,0.000013429707],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000046205723,0.000019424298,0.000008068768,0.00006483979,0.000003650732,0.000005427011,0.00021373702,0.16604462,0.000092294365,0.010033927,0.000014257111,0.82349515],"study_design_scores_gemma":[0.00029049732,0.00007147835,0.000036948866,0.00046040144,0.000008993452,0.0000131700845,8.770889e-8,0.9358248,0.00039389898,0.062259927,0.00014938685,0.0004903879],"about_ca_topic_score_codex":0.000018897914,"about_ca_topic_score_gemma":0.000040416293,"teacher_disagreement_score":0.8230047,"about_ca_system_score_codex":0.0002369996,"about_ca_system_score_gemma":0.0012610082,"threshold_uncertainty_score":0.99980706},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000619184,0.00004443623,0.7631595,0.0023139992,0.00016434061,0.000036115634,0.0000048441866,0.0002696246,0.23338796],"genre_scores_gemma":[0.1699037,0.000030912237,0.7938112,0.0007653389,0.0002275387,0.00002059364,0.000007689156,0.0000052124165,0.035227787],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996493,0.000005652873,0.000059979666,0.000109991925,0.00009054996,0.000084548796],"domain_scores_gemma":[0.999661,0.000049406586,0.000026515292,0.00020461474,0.00003272007,0.000025733647],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000072167546,0.000028591028,0.000031234515,0.000017573599,0.00005908962,0.000102253915,0.0002672579,0.000015878913,0.00009769021],"category_scores_gemma":[0.00008794314,0.000025570456,0.0000121724825,0.00009994256,0.0000029419662,0.00009420177,0.000051127223,0.000029412355,0.0013177379],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.392969e-8,0.00006684133,0.00044011007,0.0000015287231,0.0000074428062,0.0000014879669,0.00052008353,0.00000259214,0.000042765652,0.62283397,0.059801966,0.31628114],"study_design_scores_gemma":[0.000063707936,0.000009660678,0.001598013,0.000002166438,0.0000020014702,0.0000015442263,0.0000029749272,0.6869198,0.000115601084,0.0042357333,0.3069694,0.00007937885],"about_ca_topic_score_codex":0.000013261805,"about_ca_topic_score_gemma":0.0000012492881,"teacher_disagreement_score":0.6869172,"about_ca_system_score_codex":0.000022438644,"about_ca_system_score_gemma":0.0000026192504,"threshold_uncertainty_score":0.99945986},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009885774,0.00065464433,0.9593404,0.008412078,0.0004519052,0.0006371631,0.00000878307,0.0005913728,0.0200179],"genre_scores_gemma":[0.16953813,0.000007204744,0.82588583,0.00008758789,0.00048699792,0.000058398797,0.000026475036,0.000023922265,0.0038854636],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99886334,0.00006977452,0.00010238744,0.00039655046,0.00029384356,0.00027409595],"domain_scores_gemma":[0.9980015,0.00026208776,0.00005283241,0.001533668,0.00008312399,0.00006676806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025085928,0.00007380505,0.00007670421,0.000050482537,0.0007091798,0.00038534816,0.0017599541,0.000023059865,8.127032e-7],"category_scores_gemma":[0.000108438115,0.00004973156,0.000005764858,0.0003501349,0.00018659447,0.0003180617,0.00077555835,0.00017519941,0.000011794317],"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":[0.0000012726958,0.0000141870405,0.000103850114,0.000006333011,0.0000060860452,0.0000010798476,0.002002546,0.0000010524844,0.000018740146,0.05941648,0.0019416197,0.9364868],"study_design_scores_gemma":[0.00009554604,0.00006311575,0.00008836047,0.00002363162,0.000005493233,0.000014981193,0.00014110845,0.0455516,0.000005806165,0.00068452046,0.9532401,0.000085733525],"about_ca_topic_score_codex":0.00013427026,"about_ca_topic_score_gemma":0.00009011491,"teacher_disagreement_score":0.9512985,"about_ca_system_score_codex":0.000039381765,"about_ca_system_score_gemma":0.00006139365,"threshold_uncertainty_score":0.5454509},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20404805,0.000029244491,0.795208,0.000013827964,0.00002588328,0.0002100066,0.0000013294812,0.000031553947,0.0004321396],"genre_scores_gemma":[0.811803,0.0000078813155,0.18807292,0.000024679357,0.000009992883,0.00007216952,0.0000012297883,0.000006496821,0.0000016644428],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991576,0.000034594184,0.00017903438,0.00032880504,0.00014088371,0.0001590967],"domain_scores_gemma":[0.9976804,0.0016414393,0.00009921911,0.00046914667,0.000065409884,0.00004433051],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063749944,0.00011379753,0.00013213654,0.00005439429,0.00017155091,0.00009399579,0.00042226343,0.000026988313,0.0000023244143],"category_scores_gemma":[0.00004640171,0.00007556641,0.000017315331,0.00040284081,0.00009465897,0.0001824258,0.00020306655,0.00011763101,0.0000047096432],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018684831,0.000060187547,0.0006988901,0.00004483751,0.000024542487,0.00008873978,0.00091299857,0.0063172188,0.0036410766,0.036219228,0.0000043064806,0.9518011],"study_design_scores_gemma":[0.00031947807,0.00024834764,0.0067760707,0.000827592,0.00002451182,0.0014260939,0.0008795159,0.7488399,0.23163423,0.008411502,0.0002395589,0.00037317624],"about_ca_topic_score_codex":0.00012992104,"about_ca_topic_score_gemma":0.00021389956,"teacher_disagreement_score":0.95142794,"about_ca_system_score_codex":0.000024067966,"about_ca_system_score_gemma":0.00003243578,"threshold_uncertainty_score":0.3081509},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015901369,0.000064030304,0.9965024,0.00023328565,0.0008530225,0.0002901723,0.00019531441,0.000066287124,0.0002053777],"genre_scores_gemma":[0.26699045,0.000008945985,0.73222965,0.00034935836,0.0002880765,0.000008789499,0.00003449868,0.000020167921,0.000070075046],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968493,0.000025482388,0.0006310229,0.0013642659,0.00072804175,0.00040185958],"domain_scores_gemma":[0.9965853,0.00036899123,0.0004490023,0.002090779,0.00035212067,0.00015379713],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006513996,0.0003513108,0.0004887932,0.00033729148,0.00023101785,0.000296914,0.0027423347,0.00019341396,0.000019586249],"category_scores_gemma":[0.00008440224,0.00033924857,0.00010212578,0.00049884943,0.0005301881,0.00036475048,0.0012620129,0.00038688272,0.00000930723],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028775066,0.00009237887,0.0003878401,0.00007917045,0.000023390265,0.000014522904,0.0006405183,0.023008436,0.0031691995,0.04880367,0.000057223915,0.9237208],"study_design_scores_gemma":[0.00022915321,0.00004841892,0.0007998417,0.000210067,0.000012489893,0.000041534546,1.8995524e-7,0.9799621,0.003831007,0.013840066,0.00061522645,0.0004099112],"about_ca_topic_score_codex":0.00036854943,"about_ca_topic_score_gemma":0.00008032339,"teacher_disagreement_score":0.95695364,"about_ca_system_score_codex":0.00010872119,"about_ca_system_score_gemma":0.0004245661,"threshold_uncertainty_score":0.99990594},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000085847896,0.0005071407,0.993881,0.0008481403,0.001047902,0.00083321607,0.00026154393,0.00028239455,0.0022528183],"genre_scores_gemma":[0.011417175,0.00007992335,0.9852025,0.0017992659,0.00074547174,0.00013588562,0.0002657811,0.00007721505,0.00027678645],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9951175,0.000022743643,0.0008116935,0.0021661962,0.0008962123,0.0009856436],"domain_scores_gemma":[0.99642193,0.0006928598,0.0004008257,0.0018253166,0.0003589723,0.0003000929],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00087811385,0.00068960845,0.0006796927,0.00073365116,0.0005722973,0.0011229919,0.0044282717,0.00036416284,0.000054928492],"category_scores_gemma":[0.00011134557,0.000677285,0.00018053532,0.00068243855,0.00044480828,0.0008505995,0.0009518675,0.0006168591,0.000060333583],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030871356,0.000028488113,0.0000184178,0.000026844595,0.000016868962,0.000054278447,0.0009229994,0.0035772596,0.000037637907,0.010999643,0.00012842365,0.98418605],"study_design_scores_gemma":[0.0007057315,0.00036251245,0.00010358577,0.000953122,0.000023306498,0.00021210578,0.0000011130916,0.8787906,0.00057987595,0.07963644,0.03716614,0.0014654587],"about_ca_topic_score_codex":0.000053572785,"about_ca_topic_score_gemma":0.00004822239,"teacher_disagreement_score":0.9827206,"about_ca_system_score_codex":0.000400229,"about_ca_system_score_gemma":0.0006294445,"threshold_uncertainty_score":0.99991393},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004118717,0.00023966035,0.99464107,0.00023816348,0.0003587396,0.0006032842,0.000015186837,0.00021725651,0.0032747919],"genre_scores_gemma":[0.1632485,0.000050541385,0.8344321,0.00057979516,0.00038482976,0.00008000194,0.000016510096,0.000059989085,0.001147691],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967064,0.00002306367,0.0003948201,0.0015016879,0.0008498093,0.0005242124],"domain_scores_gemma":[0.9976247,0.0002443461,0.00018132891,0.0016958686,0.00011822176,0.0001355326],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039783772,0.000464723,0.00041727902,0.0005223521,0.00037911543,0.0009411918,0.003374011,0.0001279626,0.000027047145],"category_scores_gemma":[0.000012285514,0.00039040452,0.00005756251,0.0005290968,0.0005252456,0.0007337057,0.0013354066,0.00053519185,0.00003536698],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011265962,0.00011857933,0.000090659116,0.000020699103,0.00001885495,0.0001518007,0.0024020642,0.024088684,0.0000049733844,0.0023883926,0.00002695627,0.9706771],"study_design_scores_gemma":[0.00056543236,0.0015438331,0.00093354634,0.0006252795,0.000027851016,0.00021705267,0.000004793754,0.9705679,0.00011222438,0.020945236,0.0033238283,0.0011330266],"about_ca_topic_score_codex":0.000066943314,"about_ca_topic_score_gemma":0.00018499709,"teacher_disagreement_score":0.96954405,"about_ca_system_score_codex":0.0001332918,"about_ca_system_score_gemma":0.0003355082,"threshold_uncertainty_score":0.9998548},"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.947065e-7,0.00027131173,0.007870016,0.00020743722,0.00032806097,0.000219971,0.000048545433,0.00023198384,0.99082226],"genre_scores_gemma":[0.00003122939,0.000038540173,0.054186847,0.0004400327,0.000239278,0.00003525208,0.000030148125,0.00003696868,0.9449617],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99864066,0.000005068767,0.00027573833,0.00056645146,0.0002837957,0.00022828682],"domain_scores_gemma":[0.998311,0.000026375947,0.00015833024,0.0013123767,0.000066861016,0.00012510257],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00011873279,0.00027847683,0.00027279503,0.000096223914,0.00012860584,0.00017077773,0.0013450687,0.00017798724,0.000096785225],"category_scores_gemma":[0.0000043762298,0.00026857288,0.00013076648,0.000017319488,0.00008238256,0.00008769082,0.00043803087,0.00032294472,0.001029303],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.4949784e-7,0.000002604827,5.8385893e-8,0.0000064534706,0.000011403839,0.000009977501,0.000041002833,2.3758649e-7,0.0000014112916,0.36087763,0.0002780988,0.63877094],"study_design_scores_gemma":[0.00009329691,0.000026331489,0.0000032021694,0.00012990313,0.0000146854245,0.000018460178,5.309494e-7,0.00012150423,0.000013409292,0.12697993,0.8723225,0.00027625763],"about_ca_topic_score_codex":7.339503e-7,"about_ca_topic_score_gemma":0.0000033151957,"teacher_disagreement_score":0.8720444,"about_ca_system_score_codex":0.00008023731,"about_ca_system_score_gemma":0.0002309066,"threshold_uncertainty_score":0.99997663},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000082138875,0.00035132247,0.995473,0.00070439186,0.0017276669,0.00034790128,0.00005149093,0.00021124263,0.0010508137],"genre_scores_gemma":[0.030030254,0.00008333243,0.96464056,0.0030335442,0.0016706445,0.000056292894,0.00010937348,0.00006943177,0.00030656977],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961647,0.000037684953,0.000524095,0.0015505465,0.0009969207,0.00072606886],"domain_scores_gemma":[0.9958365,0.00024248697,0.00029296058,0.0030655782,0.00020468,0.00035782342],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00081836194,0.0004885143,0.0003988369,0.0005401416,0.00033955293,0.0006684057,0.0050661233,0.00024370382,0.000073761614],"category_scores_gemma":[0.000053964595,0.0004561844,0.00009832468,0.0005344154,0.0004750692,0.0014985404,0.0015802365,0.00055409316,0.00014320196],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.660169e-7,0.000050478273,0.00008279685,0.000010276552,0.0000066867465,0.000014257116,0.00089798786,0.0004896389,0.000043355663,0.03469237,0.00008682288,0.96362466],"study_design_scores_gemma":[0.0008121276,0.00035557247,0.0013407433,0.00031783257,0.000033101573,0.00014323133,9.587426e-7,0.75604403,0.0013125087,0.20562051,0.031996645,0.0020227586],"about_ca_topic_score_codex":0.00012329087,"about_ca_topic_score_gemma":0.00009813407,"teacher_disagreement_score":0.9616019,"about_ca_system_score_codex":0.00024157584,"about_ca_system_score_gemma":0.0003560145,"threshold_uncertainty_score":0.999789},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000062999316,0.0007347859,0.99295324,0.00015866497,0.0010254687,0.0007186138,0.00004903059,0.00016846559,0.0041287066],"genre_scores_gemma":[0.12399617,0.000108299035,0.87380654,0.00055561826,0.00084474677,0.0002089657,0.00009652943,0.00007799681,0.00030515276],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953224,0.00005144814,0.0006835908,0.0023613311,0.00088988384,0.00069132535],"domain_scores_gemma":[0.9955964,0.00065695855,0.0002939656,0.0031660344,0.00014061517,0.0001460379],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0015641701,0.00049994065,0.00057904073,0.00094556593,0.0002617875,0.0011476376,0.008390818,0.00024392988,0.0000058262567],"category_scores_gemma":[0.00015217147,0.00048109662,0.000048335427,0.0009988586,0.00041948052,0.0011443328,0.0031726572,0.00080839824,0.000033266988],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002175023,0.000022578135,0.00005116628,0.000023555982,0.000007037634,0.000061248786,0.00074846926,0.014784621,0.000015040114,0.0032693658,0.000030028525,0.9809847],"study_design_scores_gemma":[0.00018966444,0.000041121428,0.0000962637,0.0011962013,0.0000064061087,0.000102435544,0.000001988392,0.9822849,0.000039798197,0.010387706,0.0050330195,0.0006204901],"about_ca_topic_score_codex":0.00026226824,"about_ca_topic_score_gemma":0.00034082175,"teacher_disagreement_score":0.9803642,"about_ca_system_score_codex":0.00027993476,"about_ca_system_score_gemma":0.00057173846,"threshold_uncertainty_score":0.99988925},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008140318,0.00001888097,0.98422927,0.00037595365,0.00013722069,0.00006850819,0.0000013309822,0.00010548579,0.0069230613],"genre_scores_gemma":[0.14966084,0.0000037402317,0.8496949,0.00030947203,0.000023894918,0.000008290268,0.0000021922228,0.0000050434414,0.00029159448],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992689,0.0000261975,0.0001352514,0.0002503507,0.0001347805,0.00018450625],"domain_scores_gemma":[0.9994065,0.000028252227,0.000025927588,0.00042920923,0.000022498232,0.0000876153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016557082,0.00007049591,0.00006650003,0.00003925569,0.00012803458,0.000194262,0.00037853862,0.000021868049,0.000049463997],"category_scores_gemma":[0.000017821307,0.00006135506,0.000021533739,0.00022126085,0.000017839358,0.00026846948,0.00015367592,0.00006676271,0.000053633798],"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":[2.8139098e-7,0.000077173725,0.00024191638,0.0000068917184,0.000014334227,0.00001149882,0.00028262776,0.0006000337,0.0023854303,0.8996252,0.0010732369,0.09568136],"study_design_scores_gemma":[0.000487368,0.00005517537,0.0007746704,0.000034767883,0.000008476417,0.00021765272,0.000058089554,0.8474373,0.0076028965,0.018202832,0.12458481,0.00053591264],"about_ca_topic_score_codex":0.000053868975,"about_ca_topic_score_gemma":0.0000034537275,"teacher_disagreement_score":0.8814224,"about_ca_system_score_codex":0.000036680438,"about_ca_system_score_gemma":0.000038338552,"threshold_uncertainty_score":0.25019866},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.092100464,0.000311004,0.8102695,0.007844061,0.00030389323,0.00012204116,0.0000592573,0.0006028242,0.088386975],"genre_scores_gemma":[0.112391055,0.000007071512,0.8830434,0.0019506846,0.00024764068,0.000016120472,0.000048419657,0.0000071819454,0.0022884074],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992884,0.000011025112,0.00014540843,0.00030253822,0.00010002239,0.00015264368],"domain_scores_gemma":[0.99921596,0.00006432782,0.000037065147,0.00057393423,0.000026676873,0.00008200725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000894879,0.00007693139,0.0000773485,0.000035613477,0.000098597826,0.00015358275,0.00068951305,0.000029759402,0.0003838673],"category_scores_gemma":[0.000009649486,0.00006960519,0.000023787034,0.00015639991,0.000017714134,0.00050993555,0.00020751914,0.00007204532,0.0005317786],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.1851362e-7,0.00003143548,0.000047342888,7.0331686e-7,0.000007778101,0.000002394831,0.000452691,0.000012803395,0.0005897939,0.009186512,0.04820183,0.94146657],"study_design_scores_gemma":[0.00063967344,0.000037740327,0.0086849425,0.000026218251,0.000010332818,0.00002490518,0.000310264,0.30191755,0.021874126,0.002348915,0.663537,0.00058830064],"about_ca_topic_score_codex":0.00020135584,"about_ca_topic_score_gemma":0.000042938234,"teacher_disagreement_score":0.9408783,"about_ca_system_score_codex":0.00002107125,"about_ca_system_score_gemma":0.000045533892,"threshold_uncertainty_score":0.68351156},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034238074,0.0003103097,0.9936925,0.0003099925,0.0012372048,0.00030387728,0.000044394343,0.000041214204,0.00063668564],"genre_scores_gemma":[0.56141937,0.0007550572,0.434769,0.00084331026,0.0012603318,0.000173903,0.0002065708,0.000031348936,0.0005411003],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.997988,0.000025703865,0.0012204947,0.000095931726,0.00045759734,0.00021228277],"domain_scores_gemma":[0.9971772,0.00021276239,0.0011028802,0.00031166757,0.001051312,0.00014418385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092432805,0.00012636557,0.00024121559,0.0005403329,0.00013524151,0.0006680596,0.00087598525,0.000066048524,0.000008147574],"category_scores_gemma":[0.0002594293,0.000102618185,0.00011837698,0.00084562047,0.00001290925,0.002786483,0.00006725811,0.00011553746,0.000077326586],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017905026,0.00015110249,0.0007825643,0.00016168381,0.00016349234,0.00001183492,0.0042784205,0.013183459,0.00002701987,0.025738193,0.050217442,0.9052669],"study_design_scores_gemma":[0.00033843127,0.00020884677,0.00018378916,0.00017949902,0.000013195389,0.0007555599,0.001303194,0.4096332,0.00027657748,0.00009646975,0.5868299,0.00018136569],"about_ca_topic_score_codex":0.000017525563,"about_ca_topic_score_gemma":2.4810114e-7,"teacher_disagreement_score":0.9050855,"about_ca_system_score_codex":0.00012482944,"about_ca_system_score_gemma":0.0000988204,"threshold_uncertainty_score":0.6442115},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020706926,0.000020580117,0.9946074,0.0011453709,0.0001574761,0.00024163819,0.00006835621,0.00015090345,0.0015375753],"genre_scores_gemma":[0.01876015,0.000003617682,0.98033375,0.00012586024,0.00006704281,0.00011334987,0.0001241588,0.000010073965,0.00046202898],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901235,0.000019516347,0.0002743622,0.00028876393,0.00021259808,0.00019239607],"domain_scores_gemma":[0.99898505,0.00017830657,0.0001949859,0.00034268686,0.00024022372,0.00005873583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024329856,0.00009945365,0.0001263495,0.00011496614,0.00016072155,0.00008989618,0.00033878794,0.00007276528,0.000023770257],"category_scores_gemma":[0.00007135028,0.00009737483,0.000065604356,0.00041194735,0.000016383041,0.0002790177,0.000041607436,0.00004063238,0.000012401984],"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":[0.000016375972,0.0009260717,0.0016354698,0.000094905845,0.00019419979,0.0000016021959,0.0012098971,0.69856083,0.00080840377,0.09119026,0.009020326,0.19634163],"study_design_scores_gemma":[0.00074654585,0.00007776694,0.0008201261,0.000017312528,0.000025915584,0.0000011079915,0.000053140957,0.9935,0.0011977722,0.0021454643,0.0012730972,0.00014172646],"about_ca_topic_score_codex":0.00005993366,"about_ca_topic_score_gemma":0.00001236717,"teacher_disagreement_score":0.29493916,"about_ca_system_score_codex":0.00010795077,"about_ca_system_score_gemma":0.00012473976,"threshold_uncertainty_score":0.39708304},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002872014,0.000079087506,0.9946459,0.0020768682,0.00065798935,0.00069295435,0.000019563427,0.00015426359,0.0013861705],"genre_scores_gemma":[0.01445569,0.0000071139193,0.98230076,0.0026084061,0.00035384003,0.000065938635,0.000015908705,0.000030583404,0.00016177114],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953972,0.000023449895,0.0006761465,0.002128069,0.0010094655,0.00076564634],"domain_scores_gemma":[0.99704117,0.00039939996,0.00019267514,0.001768501,0.00022984864,0.00036840487],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001846983,0.000452602,0.00045976508,0.0013869453,0.00024841478,0.00037334824,0.0032857182,0.0002204738,0.000006572741],"category_scores_gemma":[0.000096146505,0.000468458,0.00006856066,0.002103293,0.00018407096,0.0004358582,0.001985888,0.0005707189,0.00012012513],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018239172,0.00002678886,0.000016026204,0.0000064103097,0.000002497579,0.000018539964,0.000570706,0.011471049,0.00045623098,0.008857727,0.00004666646,0.9785255],"study_design_scores_gemma":[0.00019124016,0.000095308606,0.00060756877,0.00039476,0.0000041673256,0.000037315327,8.100392e-7,0.9651362,0.001552011,0.016626537,0.014547062,0.0008070775],"about_ca_topic_score_codex":0.00010511331,"about_ca_topic_score_gemma":0.00017548504,"teacher_disagreement_score":0.9777185,"about_ca_system_score_codex":0.00047382578,"about_ca_system_score_gemma":0.00043462325,"threshold_uncertainty_score":0.9997767},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020591664,0.0005518734,0.9964323,0.00047997813,0.0012647457,0.0001825018,0.00027197937,0.00015126973,0.00045941977],"genre_scores_gemma":[0.032269903,0.00007309635,0.9652814,0.0008052048,0.0010472286,0.00001949151,0.00024538214,0.000035641155,0.00022260463],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967971,0.000019672892,0.00042358926,0.001372157,0.0008137798,0.0005737445],"domain_scores_gemma":[0.9975492,0.00032588353,0.000206908,0.0016057357,0.00009675897,0.00021554733],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000418561,0.00042410428,0.0003735051,0.00039574617,0.00028645233,0.00040646343,0.0028673606,0.00015597265,0.00010081452],"category_scores_gemma":[0.000023709896,0.00040655202,0.00010084223,0.0002731362,0.00026538616,0.0011040271,0.0007435057,0.0005328071,0.000077284334],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010789313,0.000033666704,0.00018328846,0.000009994911,0.0000120720415,0.000020960882,0.00041536964,0.0008252141,0.000063111765,0.010383597,0.0000365005,0.9880152],"study_design_scores_gemma":[0.00051952817,0.0001093771,0.002157915,0.0009933959,0.000052487623,0.00013732501,9.977009e-7,0.88211364,0.0021311892,0.05993964,0.04976878,0.0020757506],"about_ca_topic_score_codex":0.00020305706,"about_ca_topic_score_gemma":0.0000949065,"teacher_disagreement_score":0.9859394,"about_ca_system_score_codex":0.00013659339,"about_ca_system_score_gemma":0.00023190895,"threshold_uncertainty_score":0.99983865},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009390381,0.00007809748,0.9885571,0.00006811978,0.00006868607,0.000082421655,0.00013811328,0.00011242886,0.0015046656],"genre_scores_gemma":[0.5718447,0.00011100173,0.4254104,0.00008376363,0.00008915033,0.000034167544,0.0019337115,0.000015179974,0.00047794555],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984049,0.000051719246,0.0002881438,0.00081405416,0.00021903412,0.00022212902],"domain_scores_gemma":[0.99667877,0.00005357014,0.00013213148,0.002903828,0.00012875645,0.00010293967],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029191724,0.00013547919,0.00020429124,0.00031945796,0.00012584912,0.00020130425,0.0021391062,0.000033322744,0.00015524267],"category_scores_gemma":[0.00002437206,0.00011322969,0.00006911889,0.0018123558,0.000040496016,0.0008973203,0.0008676334,0.00007559659,0.00013817978],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022162405,0.0008322028,0.07954892,0.00002504595,0.0038729839,0.00010411017,0.009627842,0.00034832317,0.00019094317,0.014650111,0.0063383556,0.884439],"study_design_scores_gemma":[0.00015037137,0.00008392611,0.013984191,0.00003061825,0.001281113,0.000015398657,0.00089089776,0.96620387,0.007628311,0.00033593355,0.008933334,0.00046205564],"about_ca_topic_score_codex":0.0011450456,"about_ca_topic_score_gemma":0.00074353645,"teacher_disagreement_score":0.96585554,"about_ca_system_score_codex":0.000020769303,"about_ca_system_score_gemma":0.000046347017,"threshold_uncertainty_score":0.46173728},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004153959,0.000047234083,0.9891789,0.0019574852,0.0018744492,0.0003100208,0.00007822677,0.00015437251,0.006357801],"genre_scores_gemma":[0.008382059,0.000011594575,0.9870694,0.0030962655,0.0007351874,0.000015120998,0.00008150788,0.00003780582,0.00057101174],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958466,0.000023825853,0.00045222568,0.0023266214,0.00079839263,0.0005522945],"domain_scores_gemma":[0.99380136,0.00091191987,0.00031023764,0.004635285,0.00016133842,0.00017988021],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0009412728,0.00047977225,0.00040942253,0.0006328246,0.00032217233,0.0009316064,0.009440475,0.0003008357,0.000025990297],"category_scores_gemma":[0.00019075761,0.00042566584,0.0000658954,0.00046837627,0.00054694765,0.001136077,0.005112799,0.0013791637,0.00015920027],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003352983,0.00003579888,0.000004722684,0.000007788257,0.000009132723,0.000027980315,0.0005839099,0.00049599574,0.000073549185,0.004955477,0.00025854312,0.99354374],"study_design_scores_gemma":[0.00024913243,0.00015800468,0.00005379585,0.00040383273,0.000009219534,0.00008574684,3.4491114e-7,0.93756175,0.00065458217,0.024470337,0.03563812,0.0007151086],"about_ca_topic_score_codex":0.000024849474,"about_ca_topic_score_gemma":0.00012571881,"teacher_disagreement_score":0.99282867,"about_ca_system_score_codex":0.00013125478,"about_ca_system_score_gemma":0.00041719602,"threshold_uncertainty_score":0.9998195},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011183438,0.0006950139,0.99546254,0.0002938994,0.00082060817,0.00023692695,0.0003913183,0.000101712605,0.0008796507],"genre_scores_gemma":[0.051205885,0.000090341295,0.9477469,0.0002924558,0.00032686,0.0000053351423,0.00023765104,0.000029563102,0.00006501172],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959705,0.000020280679,0.0006309416,0.0019223528,0.0009984545,0.00045746268],"domain_scores_gemma":[0.9943685,0.00056243944,0.00043382272,0.004270627,0.00020494856,0.00015964023],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00048357193,0.00040858777,0.000515625,0.00043839845,0.00021975028,0.00024208557,0.0081952615,0.00020437327,0.000016491807],"category_scores_gemma":[0.00010049496,0.00037821324,0.0000655918,0.0006425868,0.00069044967,0.00029515303,0.0041642324,0.00043031553,0.000028755097],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.0379e-7,0.00005917028,0.000050831804,0.000011377385,0.000015241068,0.000045436424,0.00087033154,0.018634507,0.00010068518,0.0013613628,0.00023197656,0.9786182],"study_design_scores_gemma":[0.00016727445,0.000053584015,0.00023676513,0.00036390414,0.000009659478,0.000035894733,3.4190901e-7,0.99247634,0.00063770864,0.0028807914,0.0026918715,0.00044586844],"about_ca_topic_score_codex":0.00023324623,"about_ca_topic_score_gemma":0.00004451265,"teacher_disagreement_score":0.9781723,"about_ca_system_score_codex":0.00012338333,"about_ca_system_score_gemma":0.00056605565,"threshold_uncertainty_score":0.99986696},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009244574,0.0000021062754,0.8057759,0.0022879238,0.00019168257,0.002549678,0.000077613186,0.00018872975,0.1796818],"genre_scores_gemma":[0.4660418,0.0000048767242,0.51576316,0.0033908836,0.000071617345,0.0004853253,0.00012972865,0.000026226622,0.014086365],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99857104,0.000067410816,0.00020808214,0.00077555154,0.0001799303,0.00019800288],"domain_scores_gemma":[0.99587774,0.000069985974,0.00007545124,0.0038326958,0.000025272167,0.00011883253],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0012332525,0.00012092823,0.00014313559,0.00006279726,0.00030556234,0.0023959754,0.012289814,0.000014871345,0.000034545257],"category_scores_gemma":[0.00001542801,0.00010046477,0.0000099377,0.00018672227,0.000018267496,0.0017262095,0.025590263,0.00006958433,0.000079397425],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018725909,0.00039265963,0.000031903062,0.0000054681777,0.000030392926,0.00038220306,0.00041759483,0.0000031857332,0.0000011815862,0.06680969,0.016029907,0.9158939],"study_design_scores_gemma":[0.0023653265,0.0008738391,0.00038043212,0.000040301376,0.000051363477,0.0003114407,0.026856247,0.6691153,0.000026179736,0.0008402061,0.2985007,0.00063867733],"about_ca_topic_score_codex":0.0032385092,"about_ca_topic_score_gemma":0.0001906013,"teacher_disagreement_score":0.91525525,"about_ca_system_score_codex":0.000019851346,"about_ca_system_score_gemma":0.0000427616,"threshold_uncertainty_score":0.99863964},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005449638,0.00023694268,0.9952088,0.000991953,0.0012825633,0.0004301242,0.00014567914,0.00005723186,0.0011017564],"genre_scores_gemma":[0.06623097,0.00010163245,0.93072,0.0016340269,0.0006712919,0.00005339764,0.0003394594,0.000047587113,0.00020163914],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99653727,0.000032153686,0.00068891514,0.0015130043,0.00082969334,0.0003989661],"domain_scores_gemma":[0.99677694,0.00025854204,0.0005046179,0.0019190456,0.00038565104,0.00015519289],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00037232184,0.0004077025,0.00045720558,0.00048730153,0.00022840104,0.00035828608,0.0024923626,0.00022859403,0.000033032797],"category_scores_gemma":[0.000060366154,0.00039718163,0.000117450334,0.00059658865,0.00041337087,0.0005609849,0.0005961081,0.00044196352,0.00003661628],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.7268655e-7,0.00008210037,0.0002509084,0.000014744993,0.000031936204,0.000030305762,0.0013687949,0.0077414545,0.002148246,0.007555238,0.0005967847,0.98017883],"study_design_scores_gemma":[0.0005897067,0.00020070562,0.001902993,0.0004927334,0.00004357073,0.000039567603,0.0000013958504,0.86186844,0.027029255,0.10457713,0.00206073,0.0011937872],"about_ca_topic_score_codex":0.0005239549,"about_ca_topic_score_gemma":0.00027484918,"teacher_disagreement_score":0.978985,"about_ca_system_score_codex":0.00022155856,"about_ca_system_score_gemma":0.00034196218,"threshold_uncertainty_score":0.999848},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00028456212,0.00015867485,0.99841243,0.0004433207,0.000043418353,0.000024910618,0.000108421074,0.000036235222,0.00048801245],"genre_scores_gemma":[0.047719248,0.0013867668,0.9478138,0.00013326155,0.000083190695,0.000009568955,0.0025806266,0.000009163794,0.00026438292],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989823,0.000022278984,0.00023489968,0.0004965309,0.00012846425,0.0001355116],"domain_scores_gemma":[0.99829245,0.000017166096,0.00007370434,0.0014905802,0.00006578691,0.00006029468],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023533152,0.00009581228,0.00016598636,0.0006846287,0.000049923266,0.00012588888,0.00126439,0.000040545037,0.000090681424],"category_scores_gemma":[0.000016228052,0.00008657197,0.00002886109,0.005050231,0.00002809753,0.0006371397,0.00055865827,0.00006144115,0.0000084948415],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027394049,0.0001892392,0.0068272017,0.0000047805406,0.00035506923,0.0000128234315,0.00076912594,0.015708724,0.000001996605,0.009920275,0.00080104475,0.96540695],"study_design_scores_gemma":[0.000035480112,0.0000055192045,0.014888316,0.0000026885054,0.00018007736,0.0000012746526,0.000077133256,0.9792087,0.000018325823,0.00011079533,0.005362681,0.00010897167],"about_ca_topic_score_codex":0.00046090328,"about_ca_topic_score_gemma":0.00037782636,"teacher_disagreement_score":0.965298,"about_ca_system_score_codex":0.000013928332,"about_ca_system_score_gemma":0.000013526063,"threshold_uncertainty_score":0.35303026},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009625756,0.00026890798,0.99513793,0.0008532366,0.0019896997,0.0005341812,0.00004575673,0.00013400558,0.0010266518],"genre_scores_gemma":[0.0004902474,0.0000240715,0.99682635,0.0017536175,0.00037110155,0.000067184024,0.000026061416,0.000036808182,0.00040456853],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965481,0.000047521833,0.0005377715,0.0017088845,0.00047304184,0.0006846372],"domain_scores_gemma":[0.99702394,0.0006729478,0.00029580016,0.001600024,0.0002215979,0.00018568992],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015284303,0.00047095522,0.00047742284,0.0005057807,0.0003444716,0.00072059233,0.0033138662,0.00026042975,0.000018477172],"category_scores_gemma":[0.00010629503,0.00044988733,0.00016805728,0.0003931405,0.0003103428,0.00047528927,0.00087745895,0.00043109152,0.000012287848],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.3512543e-7,0.000017246424,0.000007741018,0.000024495705,0.000010899128,0.000007929607,0.00029775474,0.0011369566,0.0001340952,0.02498415,0.00009550793,0.9732824],"study_design_scores_gemma":[0.00033449143,0.00017254576,0.000019990366,0.00028740114,0.000020103573,0.00008325583,3.347378e-7,0.8102114,0.0033014014,0.14121516,0.04344239,0.0009115024],"about_ca_topic_score_codex":0.000019130699,"about_ca_topic_score_gemma":0.00002103079,"teacher_disagreement_score":0.97237086,"about_ca_system_score_codex":0.00023829678,"about_ca_system_score_gemma":0.00037794939,"threshold_uncertainty_score":0.99979526},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47090355,0.0001456587,0.28596488,0.022160413,0.0041748905,0.0006281594,0.0012896959,0.00027013718,0.21446262],"genre_scores_gemma":[0.9088693,0.000041006304,0.08699906,0.00013405633,0.00028275218,0.0000068906124,0.000044286364,0.0000044822887,0.0036181381],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993707,0.000017432061,0.00011976576,0.00028355155,0.00013035536,0.000078172336],"domain_scores_gemma":[0.9984969,0.0001897204,0.000036730147,0.0012232132,0.00002971127,0.00002372027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013032317,0.00006165754,0.00006630816,0.000018441935,0.00006927048,0.0001908336,0.0025480667,0.000020111696,0.000071105416],"category_scores_gemma":[0.00008290363,0.00004013161,0.0000126287205,0.00010744471,0.00006441767,0.0005184096,0.0011214002,0.000051908686,0.000013605899],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008381978,0.00016818265,0.00068920857,0.0000051055104,0.00002460733,5.101115e-7,0.0009199578,0.000012256843,0.00074653083,0.18587947,0.01027028,0.8012755],"study_design_scores_gemma":[0.0011497419,0.00015094224,0.021415286,0.00018673006,0.000023698309,0.000015804468,0.00020585174,0.8400331,0.004236909,0.006972991,0.12512542,0.00048353503],"about_ca_topic_score_codex":0.00005428928,"about_ca_topic_score_gemma":0.000022505114,"teacher_disagreement_score":0.84002084,"about_ca_system_score_codex":0.0000061991336,"about_ca_system_score_gemma":0.000057283374,"threshold_uncertainty_score":0.47349843},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000038763756,0.0011962105,0.985071,0.00031163145,0.0006876481,0.00041060345,0.0002346212,0.000120597244,0.011963837],"genre_scores_gemma":[0.0010914025,0.00016439774,0.994317,0.00024470827,0.00014474355,0.0000699368,0.00013469787,0.00002849116,0.0038045973],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99752265,0.00003848181,0.00086732197,0.00082095456,0.00037145673,0.0003791482],"domain_scores_gemma":[0.9896392,0.009047998,0.00033733877,0.00033025726,0.0005771893,0.000067982655],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012228794,0.00035634424,0.00054996833,0.00028365938,0.00021887955,0.00012034726,0.000998241,0.00014861558,0.00001309233],"category_scores_gemma":[0.0011617452,0.0003573349,0.00009972619,0.000114648865,0.00046386305,0.00017119756,0.0007162779,0.0003234865,0.000028387365],"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":[0.0000072107114,0.00001074011,0.0000026953774,0.000054376935,0.000091770366,0.000025615953,0.0004752651,0.0053562783,4.7866064e-7,0.58548635,0.001035571,0.40745366],"study_design_scores_gemma":[0.00011866269,0.00014753545,0.000053792428,0.000560322,0.0000325352,0.000046377478,0.00043010048,0.20807073,0.000020131856,0.78150386,0.008500241,0.00051570445],"about_ca_topic_score_codex":0.000007828887,"about_ca_topic_score_gemma":0.000039085855,"teacher_disagreement_score":0.40693796,"about_ca_system_score_codex":0.00015132662,"about_ca_system_score_gemma":0.00014378858,"threshold_uncertainty_score":0.9998879},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00051051856,0.00026147804,0.9949323,0.00027374155,0.0007524271,0.00037073356,0.00003100967,0.00019999914,0.002667782],"genre_scores_gemma":[0.017639313,0.000016666429,0.9805515,0.000737325,0.000698683,0.0000133575495,0.000045921235,0.000037193975,0.00026004118],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956215,0.000028212697,0.0006123607,0.0019024145,0.0010337224,0.00080180157],"domain_scores_gemma":[0.997393,0.0001994017,0.00033196597,0.0016500436,0.00019945376,0.00022613893],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00087753433,0.00056377216,0.0005201597,0.00071049464,0.0005013312,0.00064370217,0.003648473,0.00028972537,0.00001686894],"category_scores_gemma":[0.000046109286,0.00055100827,0.00012364153,0.0009452395,0.0006098239,0.0009035463,0.0023844838,0.0006972171,0.00003260368],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030296467,0.00009635034,0.00021782341,0.000032911186,0.000027399637,0.000041928568,0.0010843464,0.025528636,0.00040149942,0.023600936,0.00011422848,0.9488509],"study_design_scores_gemma":[0.00026799567,0.000069047936,0.00009647052,0.0001919357,0.000013016661,0.00015357292,9.040051e-7,0.99143237,0.0005062198,0.002611811,0.003954782,0.0007019011],"about_ca_topic_score_codex":0.00005277056,"about_ca_topic_score_gemma":0.000022238251,"teacher_disagreement_score":0.9659037,"about_ca_system_score_codex":0.0005048967,"about_ca_system_score_gemma":0.0004966032,"threshold_uncertainty_score":0.99969417},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014453079,0.00039557318,0.969682,0.013468015,0.0011478601,0.00011887354,0.000076131226,0.0000420244,0.000616457],"genre_scores_gemma":[0.8306322,0.0006540286,0.1564756,0.004605508,0.006877043,0.00004939178,0.000071602546,0.00005857254,0.00057600666],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99541813,0.00014446043,0.0008715392,0.00035017193,0.0029008281,0.00031488805],"domain_scores_gemma":[0.99736726,0.00023199902,0.0003671372,0.00092110934,0.000083661485,0.0010288119],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0040756683,0.00013019,0.0003719637,0.0001275537,0.00010077321,0.00032307213,0.00563595,0.00015112714,0.00009319274],"category_scores_gemma":[0.0008873841,0.00009598916,0.000052707,0.0003375531,0.000034855904,0.00056785747,0.0010174048,0.0004605039,0.000054619057],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000055282203,0.001136883,0.0018579159,0.0002700924,0.00019797037,0.0008931821,0.0034578315,0.000015835643,0.00012572753,0.0036858153,0.2729937,0.7153595],"study_design_scores_gemma":[0.00041475968,0.00007613844,0.00070551154,0.0007599995,0.000011219804,0.002310034,0.00020648444,0.79576707,0.000003822694,0.0000029184453,0.19959323,0.00014880189],"about_ca_topic_score_codex":0.000034387034,"about_ca_topic_score_gemma":0.0000028880745,"teacher_disagreement_score":0.81617916,"about_ca_system_score_codex":0.000037712634,"about_ca_system_score_gemma":0.000118074575,"threshold_uncertainty_score":0.99974406},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011202567,0.00022226281,0.9920714,0.0006925585,0.0011816153,0.00028945992,0.00012651466,0.00025075642,0.0040451926],"genre_scores_gemma":[0.12632047,0.00018181895,0.86791927,0.003550573,0.001267127,0.000041406518,0.00013879476,0.00008310095,0.0004974282],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99560386,0.000024964304,0.0005580064,0.0021423853,0.0009535808,0.00071720587],"domain_scores_gemma":[0.9966633,0.00050475524,0.0002857361,0.0021964456,0.00012361424,0.00022615276],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.00043042251,0.00055422634,0.00050727994,0.0006521121,0.0003464683,0.00177496,0.007815873,0.00028549283,0.00012212784],"category_scores_gemma":[0.00003156486,0.00052298943,0.00012319365,0.0006917982,0.00042692455,0.00092258834,0.0023496978,0.0006686245,0.00015128887],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016102537,0.000033414606,0.00011281131,0.000007795138,0.000009079245,0.000053025244,0.00041108383,0.005895467,0.00003202228,0.0023962713,0.00008806815,0.99095935],"study_design_scores_gemma":[0.00028741182,0.00007819184,0.0005349938,0.0004991368,0.00001265445,0.000031679887,2.3530502e-7,0.94633394,0.000475535,0.040122982,0.010743073,0.000880179],"about_ca_topic_score_codex":0.00015079847,"about_ca_topic_score_gemma":0.0001479181,"teacher_disagreement_score":0.99007916,"about_ca_system_score_codex":0.00017433705,"about_ca_system_score_gemma":0.0005303473,"threshold_uncertainty_score":0.9997222},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00060984894,0.0001579497,0.9918583,0.00084304594,0.00046520695,0.00026746455,0.000021791619,0.00018041022,0.0055960054],"genre_scores_gemma":[0.006462094,0.000044243,0.9906436,0.00088675035,0.00044248035,0.000023525208,0.000035997447,0.000032115968,0.0014291948],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99659044,0.00002595601,0.00040535338,0.0012870872,0.0011188543,0.0005723004],"domain_scores_gemma":[0.99787706,0.00028972604,0.0004104302,0.0010927912,0.00019019566,0.00013978186],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006409412,0.00042034825,0.00040390374,0.00046143273,0.00034122393,0.0008154651,0.0024902325,0.0002221256,0.00003491597],"category_scores_gemma":[0.00004639952,0.00036503188,0.000073364325,0.00049796305,0.00023313813,0.0006789421,0.00088223105,0.00045461077,0.000075997625],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024257733,0.000041089108,0.0002697709,0.000012600944,0.000027705239,0.00003698768,0.0006268972,0.0014752258,0.00008903081,0.015049655,0.00034023687,0.98202837],"study_design_scores_gemma":[0.0006963487,0.0002374208,0.0005104731,0.00038433098,0.000025748208,0.00007534528,5.4744356e-7,0.9670764,0.0010313236,0.020059008,0.008827381,0.0010756273],"about_ca_topic_score_codex":0.000045151417,"about_ca_topic_score_gemma":0.00010648076,"teacher_disagreement_score":0.98095274,"about_ca_system_score_codex":0.00053931464,"about_ca_system_score_gemma":0.00021616138,"threshold_uncertainty_score":0.99988014},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7532843,0.0001027002,0.23738553,0.00031972482,0.00048262096,0.0014743035,0.00069883076,0.000098692624,0.006153303],"genre_scores_gemma":[0.8382751,0.0014172759,0.04578998,0.000010940546,0.00031621553,0.00004764155,0.0059647467,0.000084705265,0.10809345],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99830085,0.000103540144,0.00016554286,0.00057586527,0.00039587804,0.00045834904],"domain_scores_gemma":[0.9985595,0.00022305231,0.000121689554,0.0006307637,0.00035537663,0.00010963556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045112876,0.00015355468,0.0002933048,0.0005770878,0.00036762957,0.000090052155,0.0017603415,0.00023035183,0.000010019976],"category_scores_gemma":[0.000015436934,0.00019467887,0.0001268913,0.00076232845,0.0001085849,0.0005996312,0.00026905132,0.0005217549,0.000014344285],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007162486,0.0041316724,0.034536425,0.0013096101,0.0001926599,0.00048955786,0.021096304,0.00025016206,0.0010495457,0.110945255,0.064844064,0.7610831],"study_design_scores_gemma":[0.004772207,0.0014093098,0.44675732,0.0016522194,0.0000931227,0.000025927644,0.028177954,0.4066951,0.001060148,0.00064137916,0.10642026,0.002295055],"about_ca_topic_score_codex":0.00064299745,"about_ca_topic_score_gemma":0.007045606,"teacher_disagreement_score":0.75878805,"about_ca_system_score_codex":0.00012994577,"about_ca_system_score_gemma":0.0002974536,"threshold_uncertainty_score":0.7938774},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000054100507,0.00017699994,0.9971034,0.0006803484,0.00030358578,0.0005464404,0.000023691548,0.00011228307,0.000999167],"genre_scores_gemma":[0.106291756,0.000026166357,0.89262474,0.00029652772,0.00030825654,0.00009132296,0.00003953318,0.000023217553,0.00029848047],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99768007,0.000010664315,0.00036406534,0.0012147691,0.00037486386,0.00035557052],"domain_scores_gemma":[0.9978939,0.00070331653,0.000217594,0.00091317855,0.00019179953,0.0000801571],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00052985596,0.00029604926,0.00029100094,0.00034569367,0.00028959638,0.00066022767,0.001614247,0.00016384134,0.0000017218516],"category_scores_gemma":[0.000118402306,0.00027245097,0.00004930988,0.00031483188,0.00049129064,0.00044065661,0.000510159,0.00026778312,0.0000050110875],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011452947,0.000016291748,0.000029593046,0.00003062184,0.0000027491894,0.0000016870086,0.00014237681,0.0027709848,0.00009239684,0.10250337,0.00004437923,0.8943644],"study_design_scores_gemma":[0.00013528427,0.000059557933,0.0007125301,0.00014292839,0.0000061247706,0.000009745981,6.6306754e-8,0.789461,0.000057567966,0.206829,0.0023005742,0.00028563512],"about_ca_topic_score_codex":0.000021606082,"about_ca_topic_score_gemma":0.00007555119,"teacher_disagreement_score":0.8940788,"about_ca_system_score_codex":0.000113005095,"about_ca_system_score_gemma":0.00026784753,"threshold_uncertainty_score":0.99997276},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002733797,0.00028889737,0.9960565,0.0011018058,0.00082192273,0.00027343526,0.00003436927,0.00020182761,0.0011939098],"genre_scores_gemma":[0.007904635,0.000037092053,0.98850733,0.0023436071,0.00037467945,0.000013512568,0.000020420033,0.00002837224,0.0007703527],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962488,0.000018369694,0.0005219948,0.0017338399,0.0008023954,0.00067459396],"domain_scores_gemma":[0.99723417,0.0002219206,0.00027755497,0.0018760046,0.00017834573,0.00021202219],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00060630817,0.00050978235,0.00044322954,0.00057879416,0.00030269244,0.0007106826,0.0044914857,0.00025458555,0.000016675804],"category_scores_gemma":[0.000047309797,0.0004790828,0.000115108596,0.00050359016,0.00036701825,0.000576202,0.0012100424,0.0006270832,0.000097834876],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.997125e-7,0.000030721403,0.000017805223,0.0000073162023,0.0000047152207,0.000045542354,0.0003721783,0.0012706794,0.00006104141,0.0013844001,0.000049007125,0.9967563],"study_design_scores_gemma":[0.00030647672,0.00012684191,0.0009793278,0.00041554216,0.000008017207,0.0000894093,2.1018495e-7,0.97436553,0.00041402655,0.01698263,0.0054382836,0.0008736829],"about_ca_topic_score_codex":0.000043345153,"about_ca_topic_score_gemma":0.00008672769,"teacher_disagreement_score":0.99588263,"about_ca_system_score_codex":0.0002276205,"about_ca_system_score_gemma":0.00037801338,"threshold_uncertainty_score":0.9997661},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000086950095,0.000080158774,0.9972173,0.0004464378,0.0005700787,0.0007411975,0.00006774867,0.00009317651,0.0006969803],"genre_scores_gemma":[0.20268358,0.00004903865,0.7962233,0.0001980013,0.0002488152,0.00014407719,0.00026296804,0.000041673833,0.00014853291],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99738383,0.000056930312,0.00047136302,0.0010354877,0.00071577186,0.00033659118],"domain_scores_gemma":[0.99618983,0.0015845923,0.00062160764,0.00096132525,0.00056766265,0.00007498144],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013433354,0.00029209274,0.0004023021,0.0004856532,0.00023737508,0.00018368845,0.0016034722,0.00029597717,0.0000015187504],"category_scores_gemma":[0.00024106422,0.0002857134,0.00012215239,0.00060650846,0.00025369474,0.0004302481,0.00023255272,0.00027139374,0.0000061320407],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002654243,0.0001463635,0.00044631734,0.00035827683,0.000031246433,0.0000029528417,0.0003455723,0.047020048,0.0025152497,0.072748415,0.00012673554,0.87623227],"study_design_scores_gemma":[0.00041782839,0.00012928054,0.0019867704,0.00039461715,0.000013087165,0.0000033573308,8.709305e-8,0.9514627,0.0050493544,0.039139003,0.0010449362,0.0003589843],"about_ca_topic_score_codex":0.000012116622,"about_ca_topic_score_gemma":0.0000072006205,"teacher_disagreement_score":0.90444267,"about_ca_system_score_codex":0.00054796593,"about_ca_system_score_gemma":0.00057198474,"threshold_uncertainty_score":0.9999595},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000029635497,0.00007058486,0.98593986,0.00023063285,0.0011973456,0.00031586437,0.00001610016,0.00032204,0.011877965],"genre_scores_gemma":[0.11607587,0.000012650568,0.88229984,0.0005812959,0.00069273834,0.000022262526,0.000041207153,0.000036514994,0.00023764043],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99663365,0.00002589257,0.00050225825,0.0015998151,0.0007520623,0.00048631444],"domain_scores_gemma":[0.997099,0.00030233638,0.0003520278,0.0017219129,0.00031616722,0.00020855168],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010180043,0.00038944898,0.00035076885,0.0007586666,0.00028881952,0.00075539947,0.0034425964,0.00026386965,0.000006703925],"category_scores_gemma":[0.000028184937,0.00036702122,0.0000740417,0.00061181776,0.0003969442,0.0011889323,0.0007989529,0.000694294,0.000115607785],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018025816,0.000025364743,0.0000058951127,0.000016511669,0.0000050556996,0.00001705162,0.0004430456,0.00047363443,0.00008013904,0.11621901,0.0000128114825,0.88269967],"study_design_scores_gemma":[0.0001170999,0.00011544175,0.00017288116,0.000302584,0.0000064383485,0.00008581938,0.0000022291279,0.98095334,0.0005000358,0.014616931,0.002642865,0.0004843566],"about_ca_topic_score_codex":0.00003576312,"about_ca_topic_score_gemma":0.00005078415,"teacher_disagreement_score":0.98047966,"about_ca_system_score_codex":0.000540101,"about_ca_system_score_gemma":0.00035652408,"threshold_uncertainty_score":0.99987817},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009197163,0.00012571711,0.9746654,0.015565476,0.00023509141,0.00005281477,4.2695893e-7,0.00005405754,0.00010384598],"genre_scores_gemma":[0.088344164,0.00002150546,0.91099966,0.00049027643,0.00010968804,0.0000013779901,3.6603424e-8,0.0000026720782,0.000030625797],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99886656,0.000014279782,0.00027397193,0.00027463326,0.00036031278,0.0002102598],"domain_scores_gemma":[0.998937,0.00005116467,0.00018630692,0.000401381,0.00025328074,0.00017088273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077730685,0.00008097257,0.00015899223,0.0008030077,0.00018080552,0.000280549,0.0015883216,0.000049053408,0.000004914336],"category_scores_gemma":[0.000053194082,0.000067248424,0.000022824397,0.0023741333,0.00008872697,0.0009576447,0.00042371653,0.00018332426,0.000011859687],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.3375076e-7,0.000019458614,0.00010049393,0.0000010000081,0.0000030992549,0.0000039733095,0.00021101342,0.000010470404,0.0045509436,0.050041575,0.0029542227,0.9421034],"study_design_scores_gemma":[0.00048292696,0.000597986,0.008305082,0.00005928701,0.000008890665,0.0010544475,0.000029050358,0.88249403,0.0033900698,0.02566945,0.07766232,0.00024647408],"about_ca_topic_score_codex":0.0000051870875,"about_ca_topic_score_gemma":4.93866e-7,"teacher_disagreement_score":0.9418569,"about_ca_system_score_codex":0.00004182549,"about_ca_system_score_gemma":0.00009935366,"threshold_uncertainty_score":0.29515234},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009163881,0.00009306266,0.9904234,0.00046870555,0.0005323002,0.00021631832,0.000096388256,0.00011527762,0.007962904],"genre_scores_gemma":[0.063792616,0.0000064550177,0.93501973,0.00077419815,0.00017445053,0.0000063062466,0.00003712389,0.000020285019,0.00016885858],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971172,0.000018274819,0.0005972734,0.0009714884,0.00081242115,0.0004833384],"domain_scores_gemma":[0.9971083,0.0007854849,0.00047243232,0.0012035444,0.00029411528,0.00013617174],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011996379,0.0003238481,0.00043129013,0.0007728236,0.00021126089,0.0002480341,0.0026053584,0.00025307864,0.000022910834],"category_scores_gemma":[0.00011318941,0.00032256258,0.00011932627,0.0007951435,0.00077201833,0.00029809927,0.0005636916,0.00046177948,0.000017293316],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.860183e-7,0.000049931103,0.0001147346,0.000018006138,0.000013102815,0.000025447871,0.0003476104,0.0034606284,0.00040243607,0.040362388,0.00009413108,0.9551106],"study_design_scores_gemma":[0.00029656015,0.00010300241,0.00021589811,0.00026364866,0.000012050416,0.000015266936,4.541773e-7,0.9794309,0.0014354329,0.015306576,0.0024023305,0.00051785656],"about_ca_topic_score_codex":0.000018215682,"about_ca_topic_score_gemma":0.000068188194,"teacher_disagreement_score":0.97597027,"about_ca_system_score_codex":0.00018333443,"about_ca_system_score_gemma":0.0010230141,"threshold_uncertainty_score":0.99992263},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.757973,0.000055565033,0.11915598,0.02075476,0.00092570664,0.0009790004,0.00052257394,0.00032946662,0.099303916],"genre_scores_gemma":[0.98383707,0.0000035767455,0.014800623,0.00091082504,0.00030959304,0.00001929125,0.000050189203,0.0000056479857,0.00006319377],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99860156,0.000045182336,0.00012739252,0.00058411673,0.00030427577,0.00033747763],"domain_scores_gemma":[0.9989697,0.00006902041,0.00009449207,0.0005527781,0.000054982083,0.00025906487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016519501,0.00007422057,0.00008826622,0.00018408855,0.0006344809,0.0004916029,0.001859224,0.00005707829,0.0000020110958],"category_scores_gemma":[0.0002476109,0.000082535225,0.0000067042874,0.0007329043,0.000119401026,0.0013907561,0.00019812796,0.00010537667,0.000012932626],"study_design_candidate":"design_other","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":[6.062104e-7,0.00002575517,0.016318165,0.000002985988,0.0000017341899,9.41284e-7,0.0027465338,0.0000018877265,0.00014901107,0.15991282,0.0021343357,0.8187052],"study_design_scores_gemma":[0.00035164232,0.000053167572,0.42617652,0.000024885016,0.0000071115514,0.0000020700027,0.000890957,0.36539757,0.00006719122,0.004666764,0.20182954,0.0005325857],"about_ca_topic_score_codex":0.0076408912,"about_ca_topic_score_gemma":0.05385502,"teacher_disagreement_score":0.81817263,"about_ca_system_score_codex":0.00044501096,"about_ca_system_score_gemma":0.00034011895,"threshold_uncertainty_score":0.9989673},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002408671,0.00027695185,0.99514556,0.00027278627,0.0004373489,0.00025428867,0.00074629276,0.000050002465,0.00040810741],"genre_scores_gemma":[0.13347203,0.000056002318,0.8657519,0.00018108072,0.00018375904,0.000008940861,0.00025739794,0.00002255377,0.000066288645],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966268,0.000025053401,0.0007291748,0.0014607799,0.00077977276,0.00037844887],"domain_scores_gemma":[0.994678,0.0006956529,0.00060380873,0.0036713455,0.00022886672,0.00012232449],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0005129005,0.00037186616,0.0005719874,0.00035474583,0.00008890537,0.00019679399,0.0076062256,0.00019916688,0.000051072006],"category_scores_gemma":[0.00006995096,0.0003322533,0.00007156673,0.00033463215,0.0004889603,0.0006852947,0.0032913787,0.00034013772,0.000013056348],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015078168,0.000047278198,0.00016883564,0.000030180148,0.000031661977,0.000009253069,0.0007912658,0.0023643754,0.00033999767,0.0032263813,0.00010199853,0.99288726],"study_design_scores_gemma":[0.00021029374,0.00014170694,0.00062204135,0.00069311296,0.000022780903,0.00000867226,0.0000018902111,0.9597427,0.0031574643,0.03439527,0.00050156156,0.0005024691],"about_ca_topic_score_codex":0.0016594523,"about_ca_topic_score_gemma":0.000226868,"teacher_disagreement_score":0.9923848,"about_ca_system_score_codex":0.00007693914,"about_ca_system_score_gemma":0.00037673916,"threshold_uncertainty_score":0.999913},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009177262,0.00025471247,0.99622744,0.0005950584,0.0007218946,0.00040851283,0.000067033514,0.00015521042,0.00065240805],"genre_scores_gemma":[0.05880113,0.00007200789,0.9395185,0.0006386266,0.000567108,0.00004774199,0.000036721347,0.000026998103,0.00029115478],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973369,0.000019123114,0.00043910183,0.0013464593,0.00043699908,0.000421371],"domain_scores_gemma":[0.9976052,0.00094075955,0.00023216213,0.0009403598,0.00014652922,0.00013500801],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008221812,0.00032993805,0.0003667875,0.000337553,0.00043778663,0.0005894424,0.0013581287,0.00018923124,0.000004212742],"category_scores_gemma":[0.00013353642,0.00030756573,0.000059691964,0.00029493493,0.0003236092,0.0006602661,0.00074626773,0.00030049644,0.000003955386],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002612778,0.00001606359,0.00004445478,0.00002820032,0.0000067698156,0.000010491521,0.0003874719,0.0011983331,0.00008404161,0.02034808,0.000043276297,0.97783023],"study_design_scores_gemma":[0.0005657217,0.00035877476,0.000872249,0.00051813584,0.00002477423,0.00036070755,0.0000012671748,0.8514928,0.000534118,0.13241784,0.011948484,0.00090509653],"about_ca_topic_score_codex":0.00007247328,"about_ca_topic_score_gemma":0.000055261393,"teacher_disagreement_score":0.97692513,"about_ca_system_score_codex":0.00011273957,"about_ca_system_score_gemma":0.0001902536,"threshold_uncertainty_score":0.99993765},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006426435,0.000091801616,0.998427,0.0002720006,0.00048823594,0.00039625287,0.00015312411,0.000039293307,0.000068045745],"genre_scores_gemma":[0.0007761059,0.00001645757,0.9985058,0.00037146595,0.00019657321,0.000011647025,0.00007388848,0.000015036802,0.00003302451],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978315,0.000020869233,0.00040892497,0.0009843679,0.0003957855,0.0003585554],"domain_scores_gemma":[0.9974777,0.0015082674,0.0003113078,0.00044572493,0.00018005703,0.000076926975],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015507401,0.00024504343,0.00028586495,0.0005874567,0.00016237715,0.00036259554,0.0006198395,0.0001672597,0.0000026501077],"category_scores_gemma":[0.0002734649,0.0002503925,0.000032506217,0.00039706798,0.00010039486,0.000716474,0.0004290454,0.00041554458,0.0000017946622],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000053918275,0.000034575114,0.00007890734,0.00003686438,0.000007144931,0.000004572516,0.00038708592,0.00293333,0.0013080637,0.024268523,0.000018059918,0.97091746],"study_design_scores_gemma":[0.0002632296,0.000042540058,0.00018846255,0.00026039034,0.000009205099,0.000053498658,5.839354e-7,0.98103654,0.00082516356,0.01509624,0.0019457086,0.00027843833],"about_ca_topic_score_codex":0.00017692216,"about_ca_topic_score_gemma":0.00036098636,"teacher_disagreement_score":0.9781032,"about_ca_system_score_codex":0.0005243536,"about_ca_system_score_gemma":0.0002211388,"threshold_uncertainty_score":0.9999948},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002256317,0.00009378438,0.9961382,0.0004923455,0.00024420395,0.00058297254,0.0001401301,0.00010738863,0.0019753077],"genre_scores_gemma":[0.010568342,0.000015658532,0.98819745,0.0005805162,0.00027933717,0.000049636048,0.00012449796,0.000023232207,0.00016133644],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972646,0.00002544025,0.0003498726,0.0013893684,0.0005090142,0.00046167854],"domain_scores_gemma":[0.99776083,0.0007323358,0.00036633376,0.000666713,0.00032325296,0.00015054918],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00079035666,0.00036989062,0.0004081206,0.00035222643,0.00041324407,0.0008193811,0.0014897446,0.0002654531,0.0000028322365],"category_scores_gemma":[0.00014035437,0.00035448867,0.00006461191,0.00024028817,0.00034233654,0.0007689181,0.00051185983,0.0003340911,0.0000043260634],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000046572486,0.000051837418,0.000020999876,0.000028948323,0.00002359865,0.000004141839,0.0033252758,0.0023216351,0.000053711094,0.107503384,0.000015754478,0.88664603],"study_design_scores_gemma":[0.00051747484,0.0002510114,0.00051098753,0.00020348883,0.000018903045,0.00001930383,0.0000026928458,0.8203733,0.00052775786,0.17673321,0.00024278922,0.00059906574],"about_ca_topic_score_codex":0.00005526694,"about_ca_topic_score_gemma":0.000017292365,"teacher_disagreement_score":0.886047,"about_ca_system_score_codex":0.00038255382,"about_ca_system_score_gemma":0.00042424462,"threshold_uncertainty_score":0.9998907},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001428893,0.00028989618,0.9956691,0.0010972974,0.00074799714,0.0007527011,0.00067531643,0.00008892584,0.0005358246],"genre_scores_gemma":[0.057589073,0.000019999863,0.94053286,0.00073064584,0.00047837922,0.000019659115,0.0003633974,0.000047365917,0.0002185947],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99584055,0.000025064843,0.000717648,0.0019446193,0.0008165932,0.0006555207],"domain_scores_gemma":[0.9943343,0.000734627,0.0005730249,0.003863272,0.00030384382,0.00019093938],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0006206453,0.0005486108,0.0006941505,0.00050447875,0.00022580268,0.00052997493,0.008845815,0.00027045497,0.000032520686],"category_scores_gemma":[0.00010754872,0.0004734515,0.00011230713,0.0004924236,0.00055313105,0.000893076,0.0021121828,0.00046368653,0.000010934875],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016189364,0.000025183952,0.000054251588,0.00005847182,0.000021276108,0.0000064866454,0.0003827537,0.0019550966,0.00021059696,0.0029491496,0.0007699376,0.9935652],"study_design_scores_gemma":[0.00034613642,0.00017358943,0.00028217732,0.00040931604,0.000020145688,0.00003525572,7.5622665e-7,0.9587175,0.00070319936,0.034256823,0.0044625006,0.0005925881],"about_ca_topic_score_codex":0.0002104723,"about_ca_topic_score_gemma":0.00038102877,"teacher_disagreement_score":0.9929726,"about_ca_system_score_codex":0.00015027224,"about_ca_system_score_gemma":0.0005327724,"threshold_uncertainty_score":0.9997717},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.101186395,0.00018494998,0.8821443,0.0026444867,0.00034373408,0.00014763867,0.000036826154,0.00063247164,0.01267923],"genre_scores_gemma":[0.4327633,0.0000023534394,0.56535226,0.00038162153,0.00007026018,0.000010209429,0.000016319429,0.0000060659463,0.0013976402],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989344,0.000019508587,0.00021790517,0.00039562062,0.00017467025,0.00025788543],"domain_scores_gemma":[0.999365,0.000051885363,0.00005396534,0.00038373843,0.0000441346,0.000101311656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018524149,0.000117802316,0.00010229564,0.000061800456,0.00017207189,0.00018870713,0.0006288615,0.00004115167,0.00007474194],"category_scores_gemma":[0.000015590333,0.000107776184,0.000039067694,0.00019126969,0.000027799299,0.000557891,0.00040152096,0.0001029471,0.00019529136],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032327912,0.00032106737,0.00022710455,0.000008381157,0.00004667294,0.0000069585803,0.0013004927,0.00026283064,0.17566916,0.020182628,0.117539965,0.6844315],"study_design_scores_gemma":[0.00029893842,0.000019220586,0.00009816588,0.000019473075,0.0000037157156,0.000019536155,0.000093702125,0.96284086,0.006418286,0.00004387814,0.029957172,0.00018704863],"about_ca_topic_score_codex":0.00004152503,"about_ca_topic_score_gemma":0.000039447605,"teacher_disagreement_score":0.96257806,"about_ca_system_score_codex":0.00004026114,"about_ca_system_score_gemma":0.00006132958,"threshold_uncertainty_score":0.4394985},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00045175772,0.00009595052,0.9942271,0.00091848226,0.0004954165,0.0004230415,0.00003357223,0.00020964202,0.0031450281],"genre_scores_gemma":[0.12118149,0.000046631274,0.8765412,0.0013472192,0.00050842384,0.000031309217,0.00004909463,0.00005242637,0.00024218603],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99594253,0.00002214356,0.000521579,0.0017584799,0.0010880467,0.00066721876],"domain_scores_gemma":[0.9974314,0.00015438945,0.0003441305,0.0016892153,0.00016989767,0.00021095226],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005722699,0.00056171656,0.0004844794,0.00056236447,0.0003342666,0.0009101329,0.0038429063,0.00020347438,0.000044550023],"category_scores_gemma":[0.000021189424,0.0004819924,0.00009685461,0.00059567724,0.0004939866,0.00072474626,0.0013944877,0.0005933176,0.000040791383],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006722088,0.000054952434,0.00014682244,0.00005808363,0.000027795793,0.00019137656,0.00072038476,0.0051672324,0.00033372408,0.017853307,0.000038951617,0.9754006],"study_design_scores_gemma":[0.0028157935,0.001236257,0.00082802936,0.004966435,0.00007957838,0.0005485807,0.0000021982214,0.9204497,0.003983122,0.05451907,0.0070424476,0.0035288164],"about_ca_topic_score_codex":0.00006121132,"about_ca_topic_score_gemma":0.00026174798,"teacher_disagreement_score":0.97187185,"about_ca_system_score_codex":0.00041060027,"about_ca_system_score_gemma":0.0011228304,"threshold_uncertainty_score":0.9997632},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000023998415,0.00034406348,0.9960002,0.0006900139,0.0014101929,0.00045835527,0.000027740196,0.00015279984,0.00089266535],"genre_scores_gemma":[0.05763238,0.000024565443,0.93863493,0.00076626346,0.0025859782,0.00007801822,0.000045401724,0.00004777919,0.00018467623],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99678415,0.000016626127,0.00046338217,0.0013150154,0.0005517495,0.0008690747],"domain_scores_gemma":[0.99780595,0.00054930977,0.00030460596,0.000976784,0.00017773987,0.00018561065],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009607954,0.00043824993,0.0004485928,0.00035036806,0.00061617454,0.0006225276,0.0031805756,0.00031517338,0.000013293085],"category_scores_gemma":[0.000040625946,0.000416843,0.00014522867,0.00046629863,0.000511011,0.0006094965,0.0010816104,0.000487615,0.000016348706],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019490094,0.000023682225,0.000008112975,0.000013720153,0.000008548124,0.0000045780725,0.0008588299,0.0023265216,0.0000246722,0.06380815,0.00024869115,0.93267256],"study_design_scores_gemma":[0.00022626578,0.00009667615,0.00008512113,0.00010448919,0.00001582265,0.000019356514,7.9033805e-7,0.9439571,0.0001332386,0.041151,0.013504369,0.00070577074],"about_ca_topic_score_codex":0.0000078045405,"about_ca_topic_score_gemma":0.000011052347,"teacher_disagreement_score":0.9416306,"about_ca_system_score_codex":0.00016420362,"about_ca_system_score_gemma":0.000249669,"threshold_uncertainty_score":0.99982834},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007019914,0.00038349864,0.98595834,0.0013006037,0.00071304006,0.0002907417,0.000017887,0.00014990107,0.011115808],"genre_scores_gemma":[0.03541567,0.00005236315,0.960707,0.002587457,0.00057682575,0.000029411724,0.00001035381,0.000040427392,0.00058050564],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965413,0.000030868316,0.0005025078,0.0015035574,0.00073202245,0.00068972405],"domain_scores_gemma":[0.997651,0.0006340572,0.0003065574,0.0011339717,0.00012639434,0.00014804617],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008795962,0.00044259155,0.00049514865,0.00079238106,0.00024294246,0.0006506356,0.0027521863,0.0003094085,0.000013465171],"category_scores_gemma":[0.0001585584,0.00043987806,0.0000936822,0.00074988394,0.0004472769,0.0007532132,0.0010509373,0.0011769198,0.000032008713],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000134104,0.000024952406,0.00017582865,0.000012325994,0.000009874995,0.00006159589,0.0019217947,0.0079719005,0.000039596187,0.022493823,0.00014654794,0.96714044],"study_design_scores_gemma":[0.00062998745,0.00011290786,0.002227968,0.0011377168,0.000011960672,0.00007679142,0.0000046865557,0.8763993,0.0008975095,0.10060322,0.016256517,0.0016414473],"about_ca_topic_score_codex":0.00005710756,"about_ca_topic_score_gemma":0.00050137384,"teacher_disagreement_score":0.965499,"about_ca_system_score_codex":0.0006145433,"about_ca_system_score_gemma":0.0004763724,"threshold_uncertainty_score":0.9998053},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000025775727,0.00010757969,0.13408087,0.000056719782,0.0002790191,0.0013146086,0.0009897643,0.00033233323,0.86281335],"genre_scores_gemma":[0.02093508,0.000008557296,0.81883985,0.00072327064,0.0012615334,0.00059046404,0.0005015694,0.00018947621,0.15695018],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976513,0.0000062584513,0.00038563338,0.0012023044,0.00032844854,0.00042607565],"domain_scores_gemma":[0.99704474,0.000035713678,0.0003260894,0.0022537382,0.00019564251,0.00014406737],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027560876,0.0003907706,0.0003634859,0.00006731266,0.0002619504,0.00025620975,0.0036668791,0.00023815097,0.0000046104265],"category_scores_gemma":[0.00003638866,0.00036401083,0.00008281522,0.000037896658,0.00007796421,0.00035837095,0.0011360989,0.00017947044,0.000047790854],"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":[0.0000063008665,0.0000134327,0.0000018456913,0.00011141404,0.00004272156,0.000007686744,0.0003172567,1.6013917e-7,0.000004005192,0.8166337,0.0024851675,0.18037628],"study_design_scores_gemma":[0.0015709251,0.00074101455,0.00001591285,0.001954433,0.0003521629,0.000336025,0.00014418765,0.07147181,0.0003722027,0.55448616,0.36560008,0.00295508],"about_ca_topic_score_codex":0.000031595395,"about_ca_topic_score_gemma":0.000026784528,"teacher_disagreement_score":0.7058631,"about_ca_system_score_codex":0.00007375424,"about_ca_system_score_gemma":0.00070443697,"threshold_uncertainty_score":0.9998812},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019003332,0.00008336231,0.9789182,0.00033641348,0.0009917095,0.00028865002,0.000119642624,0.000039122297,0.00021959313],"genre_scores_gemma":[0.58327156,0.00006476751,0.4138349,0.000549441,0.00090595376,0.00008792336,0.00096250453,0.000021759073,0.00030122205],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981339,0.00003477291,0.0010914037,0.00012081144,0.00044379794,0.00017531599],"domain_scores_gemma":[0.9977998,0.00012485558,0.0007533046,0.0006262164,0.0005912597,0.00010457263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013332798,0.00010956964,0.00019235273,0.00025056268,0.00015469122,0.00036212493,0.0010766049,0.000057476416,0.000013822929],"category_scores_gemma":[0.00011043773,0.00009026984,0.00006799845,0.00041887836,0.000017826025,0.0014597541,0.00006405912,0.00010922556,0.000075100455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054138163,0.00017752121,0.00008699469,0.00010944281,0.000074748714,0.000001420114,0.0019059363,0.16050242,0.00004545675,0.004263864,0.022006346,0.8107717],"study_design_scores_gemma":[0.00027391934,0.00008338335,0.000039637835,0.000095855146,0.000009683981,0.00006200447,0.0004122002,0.74442255,0.00027053137,0.00000471127,0.25424334,0.00008215604],"about_ca_topic_score_codex":0.000015182267,"about_ca_topic_score_gemma":2.201921e-7,"teacher_disagreement_score":0.81068957,"about_ca_system_score_codex":0.00009311083,"about_ca_system_score_gemma":0.00015301724,"threshold_uncertainty_score":0.3681097},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005876537,0.00022243199,0.99698967,0.00044119896,0.00045264408,0.00021645403,0.00005219015,0.00013266785,0.00090507243],"genre_scores_gemma":[0.050655592,0.0000736026,0.94733876,0.0010208413,0.00047642642,0.00001959787,0.00007054102,0.000040502022,0.00030412394],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99687576,0.000013486508,0.0004125351,0.0015917579,0.00060096756,0.00050551246],"domain_scores_gemma":[0.99787277,0.00021351464,0.00017196783,0.0014647916,0.00012633522,0.00015061566],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005025612,0.00040326812,0.00034613765,0.0005210633,0.00030649084,0.0014807433,0.0034736858,0.00016170231,0.0000069883586],"category_scores_gemma":[0.000026962607,0.00038125357,0.00004935122,0.0003745747,0.00024557454,0.0014223128,0.0032260579,0.00040523073,0.0000069302514],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001123812,0.000026173138,0.00026519725,0.000047237092,0.000007487942,0.000059703983,0.0002619833,0.049633168,0.0000346595,0.0064235074,0.00015553996,0.94308424],"study_design_scores_gemma":[0.00012689069,0.00002478155,0.00006790662,0.00032505006,0.0000065147988,0.000042937307,1.367702e-7,0.989112,0.00011336388,0.0087232655,0.0009977671,0.00045936208],"about_ca_topic_score_codex":0.00016733928,"about_ca_topic_score_gemma":0.00015971504,"teacher_disagreement_score":0.94262487,"about_ca_system_score_codex":0.00008608143,"about_ca_system_score_gemma":0.00021289868,"threshold_uncertainty_score":0.9998639},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00092067814,0.000043505563,0.9411012,0.0010697615,0.00013176186,0.00007031271,0.000010639658,0.00016988731,0.05648223],"genre_scores_gemma":[0.022374827,0.000004358267,0.97466725,0.00019210181,0.000033000542,0.0000074709633,0.000024459074,0.0000033394547,0.002693213],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99930835,0.000014028905,0.00008279234,0.00038021794,0.000090385656,0.0001242389],"domain_scores_gemma":[0.9981317,0.000023842458,0.00002166929,0.001759161,0.000020472396,0.000043168515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017584278,0.000047920217,0.000047194066,0.000022092458,0.00007754901,0.000115648356,0.0013734729,0.0000091714155,0.000030611],"category_scores_gemma":[0.000060430484,0.000040720468,0.000006663973,0.00022976787,0.000013959336,0.0005034519,0.00035559855,0.000032347358,0.00014310739],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.3315679e-7,0.000080245634,0.0005634084,0.0000034308193,0.000010779733,0.000003504354,0.00027075456,0.0000097656475,0.00038244404,0.36631846,0.2050628,0.42729425],"study_design_scores_gemma":[0.00009185551,0.00001048564,0.00037151005,0.0000039910706,0.0000026522384,0.000021938047,0.00004066498,0.15910356,0.0009973785,0.00049556076,0.83872205,0.00013834726],"about_ca_topic_score_codex":0.000010186038,"about_ca_topic_score_gemma":0.0000040717514,"teacher_disagreement_score":0.63365924,"about_ca_system_score_codex":0.000004166131,"about_ca_system_score_gemma":0.000041577736,"threshold_uncertainty_score":0.2552277},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11640051,0.000039024726,0.86611354,0.0048944666,0.000100346704,0.0007854618,0.00005629044,0.0002220839,0.011388286],"genre_scores_gemma":[0.98352057,0.0000037611014,0.01586985,0.00025651944,0.000009509234,0.00014261463,0.00003190851,0.000004680525,0.00016058634],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990145,0.000056677396,0.00019407798,0.0003146305,0.0002633437,0.00015679741],"domain_scores_gemma":[0.998967,0.000110192384,0.000095629075,0.00060855807,0.00013153594,0.00008707953],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018036933,0.000098783894,0.00009975581,0.00007803125,0.00023996149,0.00015403825,0.0007425806,0.000026004978,0.0000067440865],"category_scores_gemma":[0.000024964469,0.00006800323,0.000022794948,0.00066170207,0.00005396166,0.00037567582,0.000029064899,0.000059610295,0.000024233017],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003369069,0.0028963143,0.0006633516,0.000048591817,0.00003668459,6.7551645e-7,0.026210943,0.0010690748,0.021592658,0.5107591,0.052178804,0.38451007],"study_design_scores_gemma":[0.00017629474,0.00023788509,0.005409665,0.00001833014,0.0000048962984,4.4875048e-7,0.0008813701,0.9794753,0.011818012,0.00095245335,0.0008993226,0.00012598748],"about_ca_topic_score_codex":0.000025299032,"about_ca_topic_score_gemma":0.000035971414,"teacher_disagreement_score":0.97840625,"about_ca_system_score_codex":0.000020517224,"about_ca_system_score_gemma":0.00001798211,"threshold_uncertainty_score":0.27730912},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18031922,0.00003089102,0.8181231,0.000057419373,0.00024755474,0.000156032,0.000045820725,0.00024077613,0.00077915785],"genre_scores_gemma":[0.98947644,0.00003014207,0.009443489,0.000078534475,0.00012780109,0.000003871565,0.000052332147,0.000017851868,0.00076955213],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985546,0.000051933985,0.0001372138,0.00084813207,0.000088647284,0.000319496],"domain_scores_gemma":[0.99815464,0.00006903994,0.00021919742,0.0012634272,0.00013071384,0.00016296106],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00015924608,0.0002462555,0.0002030892,0.0001968871,0.00019950228,0.00016933918,0.0013350189,0.0001696405,0.00002161678],"category_scores_gemma":[0.000012459916,0.00025345114,0.00007760331,0.00052474375,0.000056961195,0.00050708506,0.0012740041,0.0003604959,0.00011035418],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007037237,0.00065340265,0.055963498,0.0005294397,0.00081869843,0.0008623257,0.0057326783,0.0526152,0.00034499908,0.04468986,0.004082368,0.8336372],"study_design_scores_gemma":[0.00050627836,0.00007926128,0.007885436,0.00022445472,0.00012133116,0.000036763897,0.0002735303,0.98298955,0.0004561785,0.0012571039,0.0052917446,0.0008783415],"about_ca_topic_score_codex":0.0001548976,"about_ca_topic_score_gemma":0.000055006003,"teacher_disagreement_score":0.9303744,"about_ca_system_score_codex":0.00010405253,"about_ca_system_score_gemma":0.00007874704,"threshold_uncertainty_score":0.9999918},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5922421,0.0005622102,0.38286722,0.014631331,0.00014961792,0.00023815877,0.0006581232,0.000712147,0.0079390695],"genre_scores_gemma":[0.96984196,0.00016885255,0.02872034,0.00029436802,0.000031867243,0.000044791082,0.00005852221,0.000010657425,0.00082866265],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989044,0.000008367072,0.00012534224,0.0006385358,0.000106618914,0.00021675321],"domain_scores_gemma":[0.9988942,0.000056489294,0.00005053912,0.0009261679,0.000007862039,0.00006472572],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000098177195,0.00012279401,0.00012225364,0.00016867036,0.00016838592,0.00048944517,0.0013323552,0.000052648393,0.000026753136],"category_scores_gemma":[0.000009712523,0.000107265456,0.000007166667,0.00037412308,0.00005425822,0.0009339131,0.0019442878,0.00010688267,0.000006606624],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.144815e-7,0.000034332068,0.0033187855,0.000006564373,0.000008262596,0.0000032807516,0.00008366803,0.0000012307621,0.00044251262,0.0016557244,0.015346893,0.97909844],"study_design_scores_gemma":[0.0004197436,0.00006345351,0.001418481,0.000042720727,0.000009429963,0.0000369932,0.00021170704,0.9252347,0.0003548955,0.000052365518,0.0718363,0.0003192318],"about_ca_topic_score_codex":0.00003522551,"about_ca_topic_score_gemma":0.000047000558,"teacher_disagreement_score":0.9787792,"about_ca_system_score_codex":0.000007812323,"about_ca_system_score_gemma":0.000004579785,"threshold_uncertainty_score":0.47197312},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013555579,0.00022285545,0.99643874,0.000369092,0.00018727324,0.00029478312,0.0003245783,0.00010034628,0.0007067973],"genre_scores_gemma":[0.06978646,0.00010528896,0.9286947,0.00043070212,0.00035457095,0.000020445843,0.00032314425,0.000042336866,0.0002422986],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99676394,0.000016327882,0.00031351484,0.0018609248,0.0005904202,0.0004548592],"domain_scores_gemma":[0.9966937,0.00032545454,0.000197658,0.002536834,0.00007272442,0.00017365984],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00032036318,0.00042287994,0.0003895852,0.00022376857,0.00022609146,0.0012106793,0.004024579,0.00013567545,0.000023119348],"category_scores_gemma":[0.000013694893,0.0003298352,0.000026376903,0.00020139944,0.00030016887,0.0017694089,0.003140715,0.0004393182,0.000027198143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016183564,0.00001772086,0.000092314585,0.000015410484,0.000021743723,0.00003432838,0.00061700534,0.024332099,0.000042978092,0.004817045,0.00004309485,0.9699646],"study_design_scores_gemma":[0.00015535008,0.00005332885,0.00008599916,0.00045651675,0.000010593393,0.00002407584,4.607035e-7,0.9477169,0.000060366525,0.050658397,0.0003441859,0.00043382825],"about_ca_topic_score_codex":0.0010469159,"about_ca_topic_score_gemma":0.00017655967,"teacher_disagreement_score":0.9695308,"about_ca_system_score_codex":0.00011823232,"about_ca_system_score_gemma":0.00023246718,"threshold_uncertainty_score":0.99991536},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46777833,0.00708356,0.48485848,0.0006732441,0.0010438403,0.00070312165,0.0033373602,0.0006667371,0.033855345],"genre_scores_gemma":[0.77973634,0.00015239597,0.2164375,0.00016046155,0.00014645502,0.000057842106,0.0020872147,0.000042700474,0.001179089],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983446,0.0000616669,0.00025163623,0.0008269906,0.00017155908,0.00034354755],"domain_scores_gemma":[0.9978484,0.00019750955,0.00012156072,0.0016190928,0.00006933257,0.00014411283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004665361,0.00021261965,0.00019399915,0.00008807794,0.00032678808,0.0008588638,0.001137236,0.000054238502,0.000010306642],"category_scores_gemma":[0.0001899791,0.00017482995,0.00001786299,0.00042154785,0.000071838826,0.0028062842,0.0005901269,0.00014185364,0.00003576881],"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":[0.000012699968,0.00094519067,0.028595945,0.0002336326,0.0002340454,0.00016833257,0.00875432,0.000013783685,0.0010327646,0.09543027,0.055614725,0.8089643],"study_design_scores_gemma":[0.0047527514,0.00064177334,0.03096133,0.0023414209,0.00028551798,0.0019293164,0.009515189,0.10529615,0.0050465553,0.0012192692,0.83328146,0.0047292695],"about_ca_topic_score_codex":0.00004510021,"about_ca_topic_score_gemma":0.0000810554,"teacher_disagreement_score":0.80423504,"about_ca_system_score_codex":0.000026949807,"about_ca_system_score_gemma":0.0002010904,"threshold_uncertainty_score":0.8282044},"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000013055946,0.000011528697,0.21565005,0.00011268322,0.00056597864,0.00039457294,0.000062542786,0.00017576062,0.7830138],"genre_scores_gemma":[0.0020589896,0.000009449259,0.038537882,0.00081496243,0.005684149,0.00013218811,0.00011413912,0.000056896377,0.95259136],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974812,0.00003319525,0.00033365877,0.001097913,0.00071156106,0.0003424203],"domain_scores_gemma":[0.9984011,0.00026180514,0.0001938624,0.0006739976,0.00029879616,0.00017045581],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00027379952,0.0003209798,0.00026512484,0.00053130987,0.00060457765,0.00040339743,0.001106799,0.00014203951,0.000077349825],"category_scores_gemma":[0.000023021275,0.0003410911,0.00012399745,0.00023110028,0.00033974525,0.0002189003,0.000064743566,0.00052498153,0.0014137574],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008978581,0.00011973787,1.6381723e-7,0.000009259396,0.000021110001,0.000009230752,0.0008033231,0.00021531967,0.0000071191525,0.066593744,0.012409174,0.91980284],"study_design_scores_gemma":[0.0014657782,0.0009547064,0.00071130705,0.0013773498,0.00011802972,0.00003983992,0.00006891175,0.044099916,0.0033461002,0.07818305,0.86782366,0.001811366],"about_ca_topic_score_codex":0.0000049051287,"about_ca_topic_score_gemma":0.000006037572,"teacher_disagreement_score":0.91799146,"about_ca_system_score_codex":0.00029424683,"about_ca_system_score_gemma":0.0009461231,"threshold_uncertainty_score":0.9999041},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014092315,0.000009130504,0.9706802,0.0020467846,0.00005751113,0.00004920001,0.00001034464,0.00020233371,0.012852206],"genre_scores_gemma":[0.20952791,0.000015142943,0.78892905,0.0009928991,0.000027373399,0.000030162251,0.000085901804,0.0000024637022,0.00038913186],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99927115,0.00000843807,0.00019375439,0.00014028829,0.00022957004,0.00015679708],"domain_scores_gemma":[0.9993612,0.000039361053,0.00011741627,0.0003602273,0.00008515384,0.000036599424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018945088,0.00006455469,0.00009353646,0.00016422772,0.00014749911,0.0003002193,0.00033486303,0.000040274645,0.0000201352],"category_scores_gemma":[0.000032650812,0.00005963636,0.00007717994,0.0021825829,0.000008382363,0.0020805532,0.00008856181,0.00004851942,0.00015283056],"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":[0.0000012205347,0.0001953344,0.029181002,0.000010942674,0.0010027795,0.0000027027586,0.008483679,0.0077233436,0.00005109213,0.8046315,0.011480542,0.13723591],"study_design_scores_gemma":[0.0027331286,0.0001533768,0.25865304,0.000035837427,0.00076300575,0.00001756799,0.0016861716,0.34229523,0.0024032537,0.0777636,0.31178877,0.001707014],"about_ca_topic_score_codex":0.0002944197,"about_ca_topic_score_gemma":0.000043373297,"teacher_disagreement_score":0.72686785,"about_ca_system_score_codex":0.00006297018,"about_ca_system_score_gemma":0.00003574691,"threshold_uncertainty_score":0.28950217},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004741702,0.00015282408,0.98279035,0.0008264266,0.000046712452,0.000058049085,0.000027366736,0.00020753931,0.011149018],"genre_scores_gemma":[0.1640431,0.000008299814,0.8338823,0.0005524048,0.00006928285,0.000014624285,0.000042849926,0.000006767565,0.0013803793],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910897,0.000019103005,0.00012659846,0.00039645657,0.00018703322,0.00016185819],"domain_scores_gemma":[0.9982341,0.000060195,0.0000377797,0.0015983151,0.000019770634,0.000049819268],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028223151,0.00006618241,0.00006412014,0.00003173929,0.00009241054,0.0001863403,0.0017635061,0.00001774321,0.0001246394],"category_scores_gemma":[0.000027761756,0.000057923204,0.000011746067,0.0001853937,0.000010446603,0.0008511609,0.00090362283,0.00005016857,0.00017689337],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.9395174e-8,0.000021152306,0.000011140927,0.0000015652018,0.0000032749297,0.0000024424226,0.0011256159,0.000055513552,0.000057675446,0.0009993918,0.007312625,0.99040955],"study_design_scores_gemma":[0.00008581187,0.000012584169,0.000021242013,0.0000075401426,0.0000026576763,0.000008137173,0.00015659616,0.9985861,0.000029988954,0.00013016796,0.0008746177,0.00008455646],"about_ca_topic_score_codex":0.000091814465,"about_ca_topic_score_gemma":0.00001277111,"teacher_disagreement_score":0.99853057,"about_ca_system_score_codex":0.000006905185,"about_ca_system_score_gemma":0.000007734874,"threshold_uncertainty_score":0.32770625},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8699944,0.00051254156,0.12654087,0.0011045977,0.00018329646,0.00028001357,0.0002577546,0.00032456766,0.0008019778],"genre_scores_gemma":[0.84742427,0.000045144418,0.1513785,0.000105912615,0.000072286864,4.2681353e-7,0.000069603615,0.00002565926,0.0008782075],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976621,0.00013458048,0.00026001822,0.00090900034,0.0005555848,0.00047870714],"domain_scores_gemma":[0.99676853,0.00014135771,0.0003325633,0.0023620531,0.00015444118,0.0002410566],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00064442406,0.00024454933,0.00033062798,0.00029518385,0.0009098796,0.00016379409,0.003966814,0.00018149936,0.00020507853],"category_scores_gemma":[0.00012627301,0.0002994754,0.00009576206,0.0010872327,0.00019967237,0.0032220886,0.0026321704,0.00040460247,0.0001874124],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013042719,0.0019834726,0.54443604,0.00039331606,0.00088559435,0.0007177484,0.022532362,0.004137973,0.02847655,0.0074609425,0.009337958,0.37950763],"study_design_scores_gemma":[0.0018823403,0.00008791456,0.045373335,0.00022489303,0.00010568353,0.00010516632,0.00067708455,0.9390724,0.0007594067,0.0005140261,0.010350315,0.0008474866],"about_ca_topic_score_codex":0.00034184658,"about_ca_topic_score_gemma":0.00012511178,"teacher_disagreement_score":0.9349344,"about_ca_system_score_codex":0.000106269326,"about_ca_system_score_gemma":0.000058617134,"threshold_uncertainty_score":0.99994576},"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020136114,0.00037096548,0.77411574,0.066475146,0.001531355,0.022614107,0.0012145141,0.009948181,0.1217164],"genre_scores_gemma":[0.03138927,0.0004950051,0.0784056,0.002469448,0.013931019,0.000081679544,0.110001005,0.003802416,0.75942457],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99676204,0.00016043721,0.00033892202,0.0015773348,0.0007439925,0.0004172957],"domain_scores_gemma":[0.99400747,0.000029180721,0.00018176189,0.004667212,0.0007696276,0.00034476322],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00082290435,0.0002895278,0.00021945302,0.00035468893,0.0011575634,0.002211278,0.0068011764,0.00009933531,0.00089625636],"category_scores_gemma":[0.00006122161,0.0002779816,0.000026778416,0.000953372,0.00011550703,0.0014547551,0.0028321752,0.00039009843,0.0016859714],"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":[0.000010558856,0.00009258821,0.0000015290581,0.00005402761,0.000058118978,0.0000048819006,0.00026983244,0.000106883665,0.000012617488,0.6862479,0.28914168,0.023999417],"study_design_scores_gemma":[0.00021643536,0.00025213472,0.00008701751,0.000023649516,0.000026875667,0.00004140275,0.000042155058,0.0001244759,0.000027047367,0.020960303,0.9778422,0.00035627506],"about_ca_topic_score_codex":0.000014501584,"about_ca_topic_score_gemma":0.000006392587,"teacher_disagreement_score":0.6957101,"about_ca_system_score_codex":0.00032811402,"about_ca_system_score_gemma":0.00010785112,"threshold_uncertainty_score":0.9999672},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000020831198,0.0003387311,0.9970247,0.0005356879,0.0013215495,0.00030075523,0.0003094749,0.000020766684,0.00012750272],"genre_scores_gemma":[0.4035323,0.000089561414,0.59243405,0.00059235917,0.0025099344,0.00002695945,0.00029382,0.00005897705,0.00046204662],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99769664,0.000014091845,0.00048237346,0.0008426761,0.0006515683,0.0003126726],"domain_scores_gemma":[0.99628955,0.000758707,0.0004292864,0.002259674,0.00021285418,0.000049909322],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.001261087,0.0002452986,0.00042846493,0.00019772668,0.00017341725,0.00025147045,0.0070334626,0.00014846007,8.770263e-7],"category_scores_gemma":[0.00008620865,0.00017783826,0.00012900954,0.00045205868,0.0004634644,0.00045742208,0.0028199651,0.00029551238,6.82215e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029265543,0.000031421598,0.000046567555,0.000030074189,0.000045044206,0.0000025042398,0.0003594389,0.01703608,0.000010342087,0.016679918,0.00039376362,0.9653619],"study_design_scores_gemma":[0.00016016651,0.00006543732,0.00013640469,0.000114170776,0.00003812208,0.0000031652728,6.443801e-7,0.98168015,0.00005380767,0.014489993,0.0030391586,0.00021874855],"about_ca_topic_score_codex":0.00004363969,"about_ca_topic_score_gemma":0.00007868173,"teacher_disagreement_score":0.96514314,"about_ca_system_score_codex":0.00005443887,"about_ca_system_score_gemma":0.00046832184,"threshold_uncertainty_score":0.99833894},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000026284788,0.00093684124,0.99427265,0.0011447982,0.0012672758,0.00057211856,0.000017492124,0.00014271274,0.0016198435],"genre_scores_gemma":[0.0003579756,0.00004185121,0.99594945,0.0020055575,0.00021634421,0.0000708232,0.000016615675,0.000034145196,0.0013072527],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996154,0.000051275234,0.0005613619,0.0019335382,0.0005256402,0.0007741505],"domain_scores_gemma":[0.9959239,0.001618931,0.00035792,0.0016439126,0.00024443885,0.00021093142],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001874692,0.00050908525,0.00054745324,0.0005224476,0.0005497836,0.0006608434,0.0038095305,0.00027586095,0.000018418952],"category_scores_gemma":[0.00021941127,0.0004683008,0.00016261992,0.0006298294,0.0007145199,0.00059019035,0.001215184,0.000381388,0.000025145138],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018841876,0.000016023838,0.00004454888,0.00003138049,0.000010991175,0.00001328566,0.00045987885,0.0013275193,0.00007518898,0.0134492535,0.0001980424,0.984372],"study_design_scores_gemma":[0.00036545316,0.00024358401,0.000072909184,0.00039157804,0.000023490327,0.00016324077,5.52398e-7,0.8109776,0.0034186943,0.13745044,0.04566135,0.0012311363],"about_ca_topic_score_codex":0.000012986203,"about_ca_topic_score_gemma":0.00006392775,"teacher_disagreement_score":0.9831409,"about_ca_system_score_codex":0.0003522271,"about_ca_system_score_gemma":0.00044494928,"threshold_uncertainty_score":0.99977684},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14365557,0.00009233162,0.8515123,0.002429892,0.00012847145,0.00012919874,0.0013129683,0.00007867834,0.00066055654],"genre_scores_gemma":[0.80516654,0.000017326287,0.19417386,0.000027297212,0.000033498058,2.4415226e-7,0.00052470627,0.0000055372466,0.00005099485],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9991278,0.000042302912,0.000109860106,0.0002657772,0.00021619821,0.00023806159],"domain_scores_gemma":[0.9984961,0.000111764326,0.00019344258,0.0010285341,0.00007767193,0.00009244505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024684306,0.00009903214,0.00017832938,0.00007787029,0.00013069368,0.000023251181,0.0015212075,0.00005460961,0.000010989943],"category_scores_gemma":[0.000022870718,0.00012037945,0.00003796026,0.0003531838,0.00022319728,0.000761714,0.0008589228,0.00007343965,0.000021525162],"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":[0.00003542531,0.0014203739,0.18459652,0.00019713952,0.00040666226,0.000035848534,0.0016531268,0.00056911283,0.007380928,0.6392995,0.122186325,0.04221904],"study_design_scores_gemma":[0.0022329823,0.00017074966,0.75879925,0.00022186169,0.00020410203,0.00005117869,0.035778403,0.095658675,0.0009888918,0.001300283,0.103629,0.00096463104],"about_ca_topic_score_codex":0.001673275,"about_ca_topic_score_gemma":0.0050357417,"teacher_disagreement_score":0.66151094,"about_ca_system_score_codex":0.000046054414,"about_ca_system_score_gemma":0.00006692522,"threshold_uncertainty_score":0.49089316},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000006517418,0.000019690606,0.4984346,0.00066320103,0.0001555205,0.0001046137,0.000039756305,0.00019911808,0.500377],"genre_scores_gemma":[0.0015046931,0.00004450294,0.27821305,0.007493618,0.00027874412,0.000049831855,0.0002500624,0.00008785689,0.7120777],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99854,0.0000059749987,0.00024432535,0.0006465544,0.00033606665,0.00022708769],"domain_scores_gemma":[0.9985171,0.00013573277,0.00013298808,0.0010619281,0.00004123657,0.00011103346],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00006838439,0.00028230067,0.00022294624,0.00015711373,0.0001427117,0.0001241763,0.0010982609,0.00015601813,0.00020672358],"category_scores_gemma":[0.0000051723173,0.0002592886,0.00011447852,0.000038084687,0.00005758206,0.00010235063,0.00020649409,0.00022082329,0.0007608298],"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":[0.0000022012366,0.000035328794,0.0000021138449,0.000012102414,0.000026608659,0.00008041441,0.00009655324,0.00007491403,0.0000011171057,0.10105487,0.1609516,0.7376622],"study_design_scores_gemma":[0.00047929375,0.00024669935,0.000041186755,0.00023395572,0.00001692759,0.000042909644,0.000004107004,0.26691636,0.00004535581,0.001686191,0.7293649,0.0009221314],"about_ca_topic_score_codex":0.000015650614,"about_ca_topic_score_gemma":0.0000051235643,"teacher_disagreement_score":0.73674005,"about_ca_system_score_codex":0.00004748051,"about_ca_system_score_gemma":0.00009679148,"threshold_uncertainty_score":0.99998593},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005210405,0.00020702924,0.9969506,0.0002483844,0.0007842241,0.00028931373,0.000047173027,0.00026369066,0.0006884914],"genre_scores_gemma":[0.03420764,0.000014889115,0.96456546,0.000472507,0.00023716368,0.0000057027814,0.00010497843,0.00004572081,0.00034596265],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952925,0.000031715397,0.00066432275,0.0024251875,0.00088837865,0.00069789676],"domain_scores_gemma":[0.9945025,0.0005193002,0.0004381826,0.004137026,0.00019856311,0.00020443935],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0011785025,0.00052867195,0.0005289564,0.0006325232,0.00053010276,0.00066231494,0.007406285,0.00031667677,0.0000061666756],"category_scores_gemma":[0.00020769534,0.0005051285,0.00007836073,0.00078435463,0.0006048727,0.0008836917,0.005152666,0.0006960083,0.000027931444],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022489903,0.00003081977,0.00008023818,0.000024531631,0.000020421561,0.000021172373,0.0011743857,0.2644558,0.00022353687,0.010995593,0.00007131029,0.7229],"study_design_scores_gemma":[0.00022066849,0.00003740406,0.0000138127225,0.00028340612,0.0000140280845,0.000054521424,3.117447e-7,0.9860438,0.00018661366,0.010691501,0.0018743838,0.0005795255],"about_ca_topic_score_codex":0.000049189257,"about_ca_topic_score_gemma":0.000045966663,"teacher_disagreement_score":0.72232044,"about_ca_system_score_codex":0.00016501576,"about_ca_system_score_gemma":0.00058400095,"threshold_uncertainty_score":0.99974},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051861424,0.0000019779143,0.9915033,0.00055300357,0.00014171339,0.00042383815,0.000018318082,0.00020903967,0.0019626934],"genre_scores_gemma":[0.5220642,4.5631117e-7,0.47698304,0.00032666163,0.0002046542,0.00025739093,0.000049398233,0.000016330858,0.000097863616],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988263,0.00003797565,0.00012807497,0.00045322702,0.00032700947,0.00022738327],"domain_scores_gemma":[0.9988493,0.000030680127,0.00003568376,0.00047937277,0.00026701132,0.0003379775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003532768,0.000108390646,0.000096839685,0.000087415574,0.00012584314,0.0001835551,0.00058196386,0.000042502266,0.000006002052],"category_scores_gemma":[0.000019524605,0.00009555757,0.000011359843,0.0005888445,0.0000858255,0.0002894969,0.0000755461,0.00012108688,0.0002317936],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006204778,0.00020732603,0.000070939765,0.0000022768706,0.000008969462,0.0000016295795,0.0005875463,0.0004034052,0.00012060238,0.19112863,0.0015771289,0.8058853],"study_design_scores_gemma":[0.0032153227,0.0040123924,0.0015164412,0.00007118085,0.000015782905,0.00018642528,0.00037426627,0.9054545,0.0034263132,0.049609672,0.031150423,0.00096725166],"about_ca_topic_score_codex":0.00005317425,"about_ca_topic_score_gemma":0.000007846762,"teacher_disagreement_score":0.9050511,"about_ca_system_score_codex":0.00006474156,"about_ca_system_score_gemma":0.00022591335,"threshold_uncertainty_score":0.38967246},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006756244,0.000022893464,0.99579525,0.0016885259,0.000107265114,0.00039996477,0.00008554673,0.000199716,0.0010252189],"genre_scores_gemma":[0.13608155,1.7866886e-7,0.8628694,0.0003288686,0.00009137891,0.0003020392,0.000047188136,0.0000065499253,0.00027283627],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991215,0.000011498113,0.00017805073,0.00034760332,0.0001174342,0.00022393953],"domain_scores_gemma":[0.99864805,0.000606704,0.000055716402,0.00053026585,0.000113203,0.00004604327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003591888,0.00009070395,0.00010736626,0.00004055599,0.00019286694,0.00016404963,0.00052671094,0.00005897382,0.000006183509],"category_scores_gemma":[0.00012908924,0.00008078426,0.000066764034,0.00020092247,0.0000226024,0.00014604782,0.00004459799,0.00003810575,0.0000034069833],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010315261,0.000149585,0.0003060207,0.000025684056,0.000009172567,2.7349816e-7,0.00006523746,0.000057066234,0.00017284162,0.74255705,0.038713213,0.21793355],"study_design_scores_gemma":[0.00031447102,0.000045018536,0.0011301883,0.000014683318,0.0000063245193,5.2166763e-7,0.000019727264,0.8161157,0.0020154084,0.0659022,0.11428746,0.0001483104],"about_ca_topic_score_codex":0.0000617903,"about_ca_topic_score_gemma":0.00002682324,"teacher_disagreement_score":0.81605864,"about_ca_system_score_codex":0.000011589566,"about_ca_system_score_gemma":0.00006288359,"threshold_uncertainty_score":0.32942864},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025268015,0.00018103945,0.9734752,0.0001633832,0.0003146095,0.00020491141,0.00004955862,0.00028102985,0.00006225089],"genre_scores_gemma":[0.40323424,6.546367e-7,0.5963082,0.00014666861,0.0001859638,0.000022946839,0.000057522495,0.000016836337,0.000027021313],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985326,0.00005752506,0.00028470988,0.00055943255,0.00016177908,0.0004039316],"domain_scores_gemma":[0.99856627,0.00056248764,0.000115374656,0.00040944075,0.00011586909,0.00023055341],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006238125,0.00018810111,0.00020254782,0.00009120308,0.00043505788,0.00064526254,0.00057778833,0.00005537791,2.2118249e-7],"category_scores_gemma":[0.000097890326,0.00019178091,0.000050142615,0.0002105278,0.000109249326,0.00088213256,0.00035266788,0.00008971081,0.0000014706649],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032531793,0.00007647274,0.0005979636,0.000029992634,0.000009312619,0.0000026531627,0.0027608695,0.0014883509,0.000022165668,0.00066827756,0.0005513934,0.9937893],"study_design_scores_gemma":[0.000752607,0.00010557961,0.00022019286,0.00008379719,0.000008527009,0.000008028126,0.0028826222,0.9932531,0.00022495075,0.0001887542,0.0020139844,0.00025783794],"about_ca_topic_score_codex":0.000038388782,"about_ca_topic_score_gemma":0.00001558508,"teacher_disagreement_score":0.99353147,"about_ca_system_score_codex":0.00004972188,"about_ca_system_score_gemma":0.00015256098,"threshold_uncertainty_score":0.7820599},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9329686,0.0000046615446,0.065677956,0.00016197347,0.000026348178,0.00025020234,0.00067103794,0.000020300084,0.0002189252],"genre_scores_gemma":[0.9986532,0.000007841458,0.001236688,0.000056438093,0.000005118379,0.000025159412,0.000009809982,0.0000022665595,0.000003494639],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993967,0.000010783175,0.0002303889,0.00012210714,0.000119582466,0.000120452205],"domain_scores_gemma":[0.9993734,0.000057980415,0.00008249329,0.00043576717,0.000009270063,0.000041137537],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013189527,0.00006583087,0.000090145,0.000084725085,0.00006146674,0.00004532251,0.00022587684,0.000012878501,0.000004415343],"category_scores_gemma":[0.000019215307,0.000045113295,0.0000057377915,0.00015932893,0.000017997483,0.0007021716,0.00012105259,0.000037554568,0.00000878953],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012672844,0.0003677666,0.0038094753,0.000117018004,0.00003267329,0.000116220544,0.026366698,0.00023890374,0.000019434632,0.005718939,0.0003447439,0.96285546],"study_design_scores_gemma":[0.014341418,0.0031831104,0.21239498,0.0035112312,0.000064297135,0.0031067363,0.05835158,0.6987442,0.0011054297,0.0011025488,0.0022422671,0.0018522122],"about_ca_topic_score_codex":0.0011167331,"about_ca_topic_score_gemma":0.0005510444,"teacher_disagreement_score":0.96100324,"about_ca_system_score_codex":0.00003450955,"about_ca_system_score_gemma":0.000026107582,"threshold_uncertainty_score":0.18396668},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00039151378,0.00030053148,0.99641967,0.00033395595,0.0011702097,0.0004086412,0.000024542716,0.00016633765,0.0007846258],"genre_scores_gemma":[0.01021607,0.000087652516,0.9881258,0.00114615,0.0002599031,0.000013499696,0.000009161295,0.000033310396,0.00010842676],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99548167,0.000020340083,0.00053807965,0.0019768956,0.0012432947,0.0007397085],"domain_scores_gemma":[0.99647504,0.00054569816,0.00021587373,0.0021560034,0.00025035307,0.00035704652],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00063391303,0.00051178253,0.0004783908,0.0007220242,0.0005265029,0.00071964174,0.005004993,0.0002721851,0.000012692539],"category_scores_gemma":[0.00014406968,0.00048151446,0.00011323597,0.0010838972,0.0003878208,0.0007512605,0.00281074,0.0006364815,0.00015643111],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018440111,0.000022200717,0.00003732529,0.0000055810387,0.0000037886753,0.000079137106,0.00032326442,0.01466629,0.00007392951,0.0013652656,0.0000901563,0.9833312],"study_design_scores_gemma":[0.00017934231,0.00010034926,0.00029454232,0.00046993708,0.000006725926,0.00027211182,1.2889967e-7,0.94560117,0.00054790836,0.044817876,0.0068372516,0.0008726339],"about_ca_topic_score_codex":0.000088654386,"about_ca_topic_score_gemma":0.00009298384,"teacher_disagreement_score":0.9824586,"about_ca_system_score_codex":0.0003260067,"about_ca_system_score_gemma":0.00060224306,"threshold_uncertainty_score":0.99976367},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000063826847,0.00022242058,0.996393,0.00064193795,0.0008319595,0.0004946738,0.0006362743,0.00012817438,0.0006451758],"genre_scores_gemma":[0.00387619,0.000026286094,0.9930801,0.001367412,0.0008350905,0.00006683421,0.00047262385,0.000034725974,0.00024077969],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968348,0.000028079037,0.00038730446,0.0014074503,0.0006264636,0.0007159106],"domain_scores_gemma":[0.9967812,0.0005951984,0.00030983734,0.0018637911,0.0001990983,0.0002508957],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011657652,0.0004091037,0.00040209276,0.00036096503,0.00038005438,0.00062726287,0.0040986184,0.00027920533,0.000014051619],"category_scores_gemma":[0.000083783685,0.00037434182,0.00008992662,0.0004023808,0.0003924951,0.0012665882,0.0008010942,0.00048275178,0.000042488475],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015423442,0.000046519966,0.000016818056,0.000011553597,0.000009827966,0.0000041363405,0.00044788094,0.0006004003,0.00005273523,0.045952816,0.0003417353,0.95251405],"study_design_scores_gemma":[0.00025698086,0.00018423398,0.00017890305,0.000111133,0.000015975244,0.000016371167,3.9432305e-7,0.8189052,0.00040376838,0.13481213,0.04437252,0.0007424294],"about_ca_topic_score_codex":0.00003060553,"about_ca_topic_score_gemma":0.00006785839,"teacher_disagreement_score":0.9517716,"about_ca_system_score_codex":0.0002898992,"about_ca_system_score_gemma":0.00045693546,"threshold_uncertainty_score":0.99987084},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048753317,0.0010177124,0.92818296,0.018177122,0.0010220123,0.002112791,0.00004923968,0.00006196814,0.0006228965],"genre_scores_gemma":[0.3825572,0.000016736405,0.61673844,0.0003536764,0.00016831732,0.00006176885,0.000049760216,0.000014049148,0.00004003611],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984563,0.00007858829,0.00036856395,0.0002935963,0.00046947683,0.0003334993],"domain_scores_gemma":[0.9973851,0.000042056505,0.00021471849,0.00089737325,0.00071750756,0.00074323534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016194509,0.00011051935,0.00013608538,0.00037901278,0.00021528597,0.0008154922,0.0018582651,0.000046197267,0.00010630261],"category_scores_gemma":[0.00022271191,0.00010249776,0.000038559545,0.0007719915,0.00004146163,0.0015452661,0.00009602058,0.00014987553,0.00007997597],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.6335962e-7,0.0000210361,0.00013118697,0.0000027909118,0.000021093616,0.000003325123,0.00036031002,0.00019610187,0.00006126161,0.0053763236,0.04893087,0.9448953],"study_design_scores_gemma":[0.00083379535,0.0005832935,0.014490597,0.00017551445,0.000120142606,0.00018920781,0.00072473986,0.72411364,0.0001215156,0.04493378,0.21317035,0.0005433975],"about_ca_topic_score_codex":0.005273566,"about_ca_topic_score_gemma":0.007081229,"teacher_disagreement_score":0.9443519,"about_ca_system_score_codex":0.00019350577,"about_ca_system_score_gemma":0.0012977946,"threshold_uncertainty_score":0.79720896},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004176474,0.0005099998,0.9875334,0.0053645135,0.00006612826,0.000063687905,0.00002386204,0.00020995348,0.0020519695],"genre_scores_gemma":[0.06560611,0.00007859342,0.93245244,0.0013293043,0.000053969925,0.00001497127,0.00010923783,0.000005606172,0.00034977522],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999121,0.000013752011,0.00016417191,0.0004348066,0.00010714296,0.00015911036],"domain_scores_gemma":[0.99872637,0.00009416608,0.000047274647,0.0010710629,0.000024219169,0.00003693102],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016012898,0.0000846795,0.00009254009,0.00003440245,0.000110644,0.0002141899,0.0010680051,0.000029085495,0.0000056842905],"category_scores_gemma":[0.000023114415,0.00007051932,0.0000089190635,0.0002086397,0.0000542589,0.0006309745,0.00078490516,0.00004925162,0.000010836845],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.4514744e-7,0.000057866004,0.0017519098,0.0000053094927,0.000007912059,0.000005196382,0.00009047993,0.0000063614066,0.00045884377,0.016827958,0.066071264,0.91471606],"study_design_scores_gemma":[0.00017841852,0.000037965016,0.03425266,0.000022317294,0.00000966267,0.000023206185,0.00016367885,0.5261663,0.0011208539,0.0038085557,0.4338572,0.0003591705],"about_ca_topic_score_codex":0.00035078614,"about_ca_topic_score_gemma":0.00038066236,"teacher_disagreement_score":0.9143569,"about_ca_system_score_codex":0.000009938472,"about_ca_system_score_gemma":0.000008743333,"threshold_uncertainty_score":0.28756946},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01331204,0.000018041643,0.98420995,0.00018806079,0.000033998906,0.0004759577,0.00014007263,0.00022870846,0.0013931759],"genre_scores_gemma":[0.16324575,0.000047707617,0.83614624,0.00003334342,0.00009372351,0.00012291736,0.0002331812,0.000014761506,0.00006237315],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980565,0.00004005445,0.0007439477,0.00064742775,0.00029025922,0.00022181483],"domain_scores_gemma":[0.9965473,0.00024577032,0.00043930917,0.0019298011,0.00078420545,0.00005361296],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047004706,0.00016842634,0.00021713699,0.00027250836,0.00036611047,0.000057888283,0.0021251175,0.00008116627,0.000022107655],"category_scores_gemma":[0.00011198446,0.00018034798,0.000026987214,0.0032562565,0.0003326679,0.00090197433,0.00066044094,0.00013379172,0.00007711785],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004583271,0.0002936596,0.00030384734,0.000008327349,0.000021600255,0.0000016880662,0.0007062903,0.00015033734,0.050069515,0.15888774,0.0008329882,0.7887194],"study_design_scores_gemma":[0.000020070891,0.000069458445,0.00041481174,0.00004727911,0.000011934505,0.000032315293,0.0002804229,0.8064706,0.17909724,0.010578883,0.0026154341,0.00036158905],"about_ca_topic_score_codex":0.00026551736,"about_ca_topic_score_gemma":0.000005151067,"teacher_disagreement_score":0.80632025,"about_ca_system_score_codex":0.00004777192,"about_ca_system_score_gemma":0.00021871063,"threshold_uncertainty_score":0.73543775},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000014179452,0.0003771312,0.99635726,0.00068522285,0.00053607917,0.00061336346,0.00060665427,0.00017031666,0.0006398078],"genre_scores_gemma":[0.0047432627,0.000022997549,0.991785,0.0016131448,0.0005849696,0.00006754476,0.001056319,0.000040983385,0.00008578104],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952518,0.000025423677,0.000548336,0.0027254734,0.00080623606,0.00064277084],"domain_scores_gemma":[0.9944163,0.0008182245,0.0003305102,0.004081486,0.00016312349,0.00019036494],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00065146014,0.0005329186,0.0005363923,0.00043470302,0.0003887699,0.000577975,0.009000313,0.00026254653,0.000008164827],"category_scores_gemma":[0.00008298396,0.0004935115,0.00010935209,0.0004534086,0.00050803367,0.0006069536,0.0020321615,0.00045531584,0.0000115268695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021191997,0.000049813796,0.00003018959,0.000018233317,0.000012505414,0.00001941725,0.00032830678,0.008714082,0.000019090674,0.0003100834,0.00054469367,0.9899515],"study_design_scores_gemma":[0.00037798626,0.00008340554,0.000038319406,0.0001655398,0.0000123512555,0.000013501926,3.4405082e-7,0.9888149,0.00015000433,0.0038009216,0.005961888,0.0005808215],"about_ca_topic_score_codex":0.00022708387,"about_ca_topic_score_gemma":0.00010415343,"teacher_disagreement_score":0.98937064,"about_ca_system_score_codex":0.00016185142,"about_ca_system_score_gemma":0.00080234156,"threshold_uncertainty_score":0.9997516},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011900429,0.0001649381,0.9909258,0.0046741567,0.00058216637,0.00048710458,0.000037572718,0.00014038986,0.0017978611],"genre_scores_gemma":[0.1974792,0.000009942602,0.79847217,0.003116589,0.00061636255,0.000037059763,0.000010986583,0.000028833758,0.0002288907],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967046,0.00004302141,0.0003762343,0.0011810883,0.0009338054,0.00076126866],"domain_scores_gemma":[0.99702877,0.0008234252,0.00025116932,0.0014753377,0.00016430575,0.00025697518],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009100443,0.0004915333,0.0004307619,0.00024230927,0.00057274505,0.0010051522,0.0042306026,0.00016739118,0.00002669738],"category_scores_gemma":[0.000039724506,0.00032714457,0.00008004341,0.00053185737,0.0012891797,0.0006390553,0.0014024569,0.00062665436,0.00006168785],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000053786734,0.000025694986,0.00007217405,0.000014283363,0.000023641489,0.000046733418,0.0027216573,0.00892701,0.00019909642,0.027310442,0.00011836628,0.9605355],"study_design_scores_gemma":[0.0017260537,0.0017199953,0.0038921605,0.002693016,0.00016784384,0.002653314,0.0000247608,0.80415016,0.006044365,0.102107294,0.06821015,0.006610892],"about_ca_topic_score_codex":0.00008597023,"about_ca_topic_score_gemma":0.00019849301,"teacher_disagreement_score":0.95392466,"about_ca_system_score_codex":0.00017697924,"about_ca_system_score_gemma":0.00055361923,"threshold_uncertainty_score":0.99991804},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019904213,0.00029690142,0.9964243,0.00020296246,0.0005842394,0.00021222439,0.00034415227,0.0000983327,0.0016378262],"genre_scores_gemma":[0.03772532,0.000046831035,0.9607994,0.0004446903,0.00042511022,0.000008463475,0.00029596034,0.000040000385,0.00021424433],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962821,0.000026119298,0.0006123461,0.0018782895,0.0007227168,0.00047845233],"domain_scores_gemma":[0.99479103,0.00050305645,0.00046607084,0.0039443937,0.0001445385,0.00015089157],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00069555035,0.00042754514,0.00052758964,0.00040906767,0.00016019745,0.00028861617,0.008830017,0.0002133528,0.00007656631],"category_scores_gemma":[0.000061857536,0.00039755157,0.000069924834,0.00041683973,0.00049132144,0.00077424356,0.004168669,0.00043248662,0.000065629916],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.3775814e-7,0.000025487147,0.00006203579,0.0000100999705,0.00001639971,0.000022761675,0.0007178531,0.0007083215,0.00012439865,0.0011443283,0.000084385036,0.99708307],"study_design_scores_gemma":[0.0001771289,0.00008415549,0.00011207245,0.0006001397,0.000018330327,0.000015692593,4.0142126e-7,0.9505338,0.0009893161,0.045558672,0.0013644886,0.00054576754],"about_ca_topic_score_codex":0.0006792919,"about_ca_topic_score_gemma":0.00010719827,"teacher_disagreement_score":0.9965373,"about_ca_system_score_codex":0.000123332,"about_ca_system_score_gemma":0.00043589302,"threshold_uncertainty_score":0.99984765},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006430034,0.021513749,0.9394872,0.00436705,0.0019557653,0.00061558315,0.000087167995,0.0001255719,0.031783618],"genre_scores_gemma":[0.02533241,0.013989754,0.9367164,0.0050375424,0.0010960381,0.000097602475,0.0004780849,0.00013650717,0.017115705],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99708724,0.000035340698,0.00091289124,0.0010699363,0.0005162741,0.0003783462],"domain_scores_gemma":[0.9953487,0.0029245662,0.00037577318,0.0011070168,0.00020733874,0.00003662806],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014308078,0.0003585704,0.00040427875,0.0003977975,0.0003195415,0.00041373726,0.0031060497,0.00011988049,0.000020313686],"category_scores_gemma":[0.00022034493,0.00030194316,0.000056805915,0.00036909254,0.00038183734,0.0013134287,0.003059698,0.00066137506,0.00006661321],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031731981,0.000030140676,0.00004200497,0.00006297708,0.00010211561,0.000101714955,0.007993192,0.0075847986,2.1484152e-7,0.31211182,0.0022456313,0.6697222],"study_design_scores_gemma":[0.00010547307,0.00003456529,0.00009834883,0.0058799204,0.000022446417,0.000084993815,0.002694026,0.75207347,0.000016961712,0.20170945,0.036513653,0.0007667192],"about_ca_topic_score_codex":0.000022954386,"about_ca_topic_score_gemma":0.00019891103,"teacher_disagreement_score":0.74448866,"about_ca_system_score_codex":0.00023165262,"about_ca_system_score_gemma":0.000120303455,"threshold_uncertainty_score":0.99994326},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008434635,0.00008711931,0.93907315,0.00036153165,0.0011485482,0.00013836799,0.000043035277,0.00017773187,0.058962084],"genre_scores_gemma":[0.0052701477,0.00011605999,0.9721733,0.00087475707,0.0012657443,0.000015692982,0.00011647077,0.000043109925,0.020124724],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952849,0.000017947687,0.000575409,0.0025583496,0.0009873253,0.00057606254],"domain_scores_gemma":[0.9915637,0.00014652823,0.00031434008,0.0075921766,0.0001463889,0.00023690365],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.002001601,0.00037487748,0.0005421963,0.001353974,0.0002294256,0.0009837231,0.013999655,0.00014938842,0.000034458306],"category_scores_gemma":[0.00003847181,0.0003910462,0.0001204354,0.0017008093,0.0005828257,0.0006761603,0.009085531,0.00045919573,0.00021395742],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.041218e-7,0.000012833159,0.000030832995,0.000008392796,0.0000425574,0.00001557519,0.000052279247,0.00032518173,0.0000039213246,0.27553052,0.00058751646,0.7233901],"study_design_scores_gemma":[0.00009866441,0.000029375562,0.0008279755,0.00006923856,0.000056228688,0.000010237023,2.3276334e-7,0.8202478,0.000020386937,0.005951713,0.1721567,0.00053139986],"about_ca_topic_score_codex":0.000088620945,"about_ca_topic_score_gemma":0.00011017727,"teacher_disagreement_score":0.8199227,"about_ca_system_score_codex":0.00011762994,"about_ca_system_score_gemma":0.0004309131,"threshold_uncertainty_score":0.99985415},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012184982,0.0003991799,0.992866,0.00032575146,0.0005954786,0.00040670368,0.000032953856,0.00009969029,0.0040557384],"genre_scores_gemma":[0.25818378,0.000039592895,0.7400543,0.00066037616,0.0007651354,0.000065571585,0.000034610803,0.00003445458,0.0001622039],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967074,0.000067149245,0.00056436204,0.0012960719,0.0009676404,0.00039740754],"domain_scores_gemma":[0.99681044,0.0002724488,0.00037762185,0.0022480343,0.00016516597,0.00012629954],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011577833,0.00037141988,0.00039652167,0.00023392892,0.0003984232,0.00048471885,0.004414597,0.00020130575,0.000020136631],"category_scores_gemma":[0.000051254636,0.00027393817,0.00010990186,0.0004829011,0.0009432979,0.00093550683,0.00086585066,0.0006080099,0.000013865458],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004929115,0.000121216974,0.0000050671247,0.000010503337,0.000008691704,0.0000016459214,0.0015761878,0.0019447595,0.00151061,0.019184269,0.000013806189,0.9756183],"study_design_scores_gemma":[0.00089626707,0.0007746072,0.00088676007,0.00026126727,0.00003139049,0.00018752614,0.000018769193,0.6770244,0.06495643,0.24410172,0.008621839,0.002239014],"about_ca_topic_score_codex":0.0001498487,"about_ca_topic_score_gemma":0.000010080624,"teacher_disagreement_score":0.9733793,"about_ca_system_score_codex":0.00011902817,"about_ca_system_score_gemma":0.0004030847,"threshold_uncertainty_score":0.9999713},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000116635754,0.00016817328,0.99794847,0.0001682672,0.0004910239,0.0006778903,0.000030511093,0.0001860902,0.00021293714],"genre_scores_gemma":[0.0041815485,0.000019158813,0.99474305,0.00024291818,0.00061191875,0.000016469698,0.00004849406,0.000039561084,0.00009688276],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99615735,0.000018348746,0.0005262699,0.0020426214,0.00059140514,0.00066403067],"domain_scores_gemma":[0.9977468,0.00039881532,0.00037608962,0.0010207256,0.00030354096,0.00015403306],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017170071,0.000436268,0.00039184635,0.00092847063,0.00069882645,0.00088886614,0.002386792,0.00031452972,0.0000024576316],"category_scores_gemma":[0.000073673255,0.0004444369,0.000038592207,0.0010426552,0.00027442805,0.0013809007,0.0016725375,0.0005490329,0.000001944648],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029772032,0.000017409939,0.00008876964,0.000040688778,0.000012743006,0.0000029127814,0.00028022518,0.0074050613,0.00024851426,0.0022193384,0.000022734697,0.98965865],"study_design_scores_gemma":[0.00021858753,0.00013310825,0.00006218752,0.0002823174,0.000016497923,0.00016062202,5.0874206e-7,0.98485744,0.0003320236,0.010518981,0.0029224665,0.0004952873],"about_ca_topic_score_codex":0.00008292932,"about_ca_topic_score_gemma":0.00019573624,"teacher_disagreement_score":0.98916334,"about_ca_system_score_codex":0.00025640687,"about_ca_system_score_gemma":0.0005405019,"threshold_uncertainty_score":0.99980074},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19243835,0.00006259339,0.558555,0.012836463,0.0024889777,0.0003950722,0.00004498739,0.0006320177,0.23254655],"genre_scores_gemma":[0.3895449,0.0000019633035,0.58802617,0.00028424256,0.0004298151,0.000038586215,0.0000070851315,0.000009286063,0.021657951],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994148,0.0000016937275,0.00013685065,0.00016932395,0.00019812766,0.00007923116],"domain_scores_gemma":[0.99957114,0.000047231486,0.000083880244,0.00018306526,0.00010210437,0.000012570626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006772508,0.00005249197,0.000047684924,0.000027900644,0.000088548164,0.00013353111,0.0008023195,0.000021529577,0.000004599206],"category_scores_gemma":[0.000037279464,0.00003483029,0.000028383,0.00023997345,0.000031113974,0.00021466502,0.0001975176,0.00004526135,0.000004069271],"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":[0.000003123935,0.00018484221,0.021264534,0.0000083244395,0.000017699174,7.5848345e-7,0.00043228635,0.00010055212,0.0014984645,0.6545541,0.23649935,0.085435905],"study_design_scores_gemma":[0.0010693378,0.00014654275,0.2791775,0.00061412825,0.000033008568,0.00009042163,0.0011667002,0.0848407,0.13084741,0.02565787,0.47527462,0.0010817505],"about_ca_topic_score_codex":0.000040357325,"about_ca_topic_score_gemma":0.0000036658125,"teacher_disagreement_score":0.6288963,"about_ca_system_score_codex":0.000013326907,"about_ca_system_score_gemma":0.00001534413,"threshold_uncertainty_score":0.14909226},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.091979966,0.00033846367,0.9020885,0.0029895348,0.0015904777,0.00005147278,0.0009173334,0.000020209816,0.000024022698],"genre_scores_gemma":[0.17161296,0.00044877824,0.82555807,0.00023121116,0.0011749783,0.000003710602,0.0009371926,0.000009894805,0.000023232393],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99811035,0.000031763186,0.0005849033,0.0004378916,0.00064866093,0.00018643026],"domain_scores_gemma":[0.99637115,0.0010222512,0.0005931228,0.0008842449,0.0010079397,0.00012128521],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013582539,0.0001354166,0.00022784111,0.00016036052,0.000100397694,0.0006217599,0.005084197,0.00008574934,0.0000071121312],"category_scores_gemma":[0.002876563,0.000120753495,0.000019920615,0.00021915747,0.000051536907,0.0034570259,0.0018668215,0.00018650017,0.000007818242],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055783734,0.00009579079,0.004538039,0.000008612716,0.00016804728,0.000014661322,0.0011942075,0.00042752354,0.000022485336,0.006158267,0.0068811723,0.98043543],"study_design_scores_gemma":[0.0004287147,0.00010300253,0.008056318,0.0005805872,0.00006327922,0.00010887312,0.0007946468,0.9446382,0.00034014042,0.01667931,0.02788513,0.00032179707],"about_ca_topic_score_codex":0.00009661994,"about_ca_topic_score_gemma":0.000008334973,"teacher_disagreement_score":0.9801136,"about_ca_system_score_codex":0.000063625805,"about_ca_system_score_gemma":0.00025101678,"threshold_uncertainty_score":0.94477874},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004031193,0.000065799824,0.98573345,0.0045763496,0.00002008102,0.00011441915,0.000048694495,0.00007617302,0.0053338404],"genre_scores_gemma":[0.014723201,0.000074862386,0.97479194,0.00046201632,0.000033408112,0.000032638014,0.000043185635,0.0000047584613,0.00983396],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995086,0.000004441621,0.000077640114,0.00023872888,0.00005467205,0.00011589933],"domain_scores_gemma":[0.9988962,0.00012668598,0.000013475867,0.0009159552,0.000013101502,0.000034607132],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020151485,0.000042857926,0.000037991864,0.000007571191,0.00024767796,0.0002392004,0.0011000668,0.000013145708,0.0000055539713],"category_scores_gemma":[0.000011142324,0.000027785456,0.000006448275,0.000073904645,0.00002747909,0.0003101641,0.00024206593,0.0000221815,0.000009882826],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.165188e-7,0.0000062737645,0.0000020873163,7.654509e-7,0.0000031496484,6.779959e-8,0.00011407952,0.000044621418,0.000009481206,0.07508235,0.021992698,0.9027437],"study_design_scores_gemma":[0.00007472454,0.000006813689,0.000035263885,0.00000136403,0.000001907551,0.0000018118928,0.00002339133,0.90765435,0.0000131652205,0.003841297,0.0883031,0.00004279929],"about_ca_topic_score_codex":0.000012279845,"about_ca_topic_score_gemma":0.000013114368,"teacher_disagreement_score":0.90760976,"about_ca_system_score_codex":0.0000019897693,"about_ca_system_score_gemma":0.000026780715,"threshold_uncertainty_score":0.2306615},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000007696333,0.00019300025,0.9949437,0.0018854138,0.000558958,0.0005269197,0.000008880427,0.00025252235,0.0016229353],"genre_scores_gemma":[0.0016286259,0.000022025259,0.99524194,0.0017748871,0.00070847286,0.00002523405,0.000031670366,0.000024564066,0.0005425755],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964264,0.000019626548,0.0005171888,0.0016293013,0.0009162549,0.0004912337],"domain_scores_gemma":[0.99710596,0.00027097325,0.00025491702,0.0019520862,0.00018209378,0.0002339481],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007067271,0.00046867557,0.00039451697,0.0008113188,0.00029728233,0.0008416186,0.0035335135,0.0003373877,0.00001651342],"category_scores_gemma":[0.00007387471,0.00043172718,0.00012056632,0.000810128,0.00022833719,0.00058268267,0.0005837963,0.00059191365,0.000060796425],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001535716,0.000022941533,0.0000016140141,0.0000033421027,0.0000018191903,0.000016960166,0.00004963164,0.008416855,0.0005874035,0.006260356,0.00043026224,0.9842073],"study_design_scores_gemma":[0.00023873536,0.00015777709,0.000048078535,0.00026398446,0.000006008742,0.000040073348,1.6433907e-8,0.8438459,0.0052028345,0.1383422,0.011306963,0.0005474266],"about_ca_topic_score_codex":0.00003531372,"about_ca_topic_score_gemma":0.00008616665,"teacher_disagreement_score":0.98365986,"about_ca_system_score_codex":0.00026693312,"about_ca_system_score_gemma":0.0010678004,"threshold_uncertainty_score":0.99981344},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000039206832,0.00017895605,0.994161,0.0016843941,0.0008222504,0.0003621755,0.00006440316,0.00004533789,0.0026422406],"genre_scores_gemma":[0.0054550096,0.00002557863,0.99288934,0.0008030962,0.0002580361,0.00003455657,0.00003099383,0.00002323685,0.0004801369],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99768263,0.000011482712,0.00043730915,0.0010037433,0.00047312997,0.00039168567],"domain_scores_gemma":[0.9977165,0.00057094323,0.00027331957,0.0010671732,0.0002626104,0.00010949386],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00052127056,0.0003022524,0.00034167807,0.00047200837,0.00019963236,0.00024868993,0.0023811192,0.00015323923,0.000010862596],"category_scores_gemma":[0.00009087898,0.00029580042,0.00011113683,0.00043867202,0.00039436354,0.00040445896,0.00053995807,0.00025924286,0.000010599343],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004648399,0.00010888619,0.000115018775,0.00016321482,0.00003076029,0.0000034726131,0.0009317317,0.038407635,0.0010622176,0.1878378,0.001014002,0.7703206],"study_design_scores_gemma":[0.0002284538,0.00010432033,0.00005864642,0.00022097482,0.000009556924,0.000027224145,2.977013e-7,0.82894516,0.00064132374,0.16167781,0.0076228227,0.0004634137],"about_ca_topic_score_codex":0.000008354119,"about_ca_topic_score_gemma":0.00005246535,"teacher_disagreement_score":0.79053754,"about_ca_system_score_codex":0.00012621704,"about_ca_system_score_gemma":0.0005982508,"threshold_uncertainty_score":0.9999494},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.947792,0.00010668903,0.048610207,0.0008547166,0.00015459913,0.00018703833,0.000105643696,0.000116397074,0.0020727357],"genre_scores_gemma":[0.9191025,0.000040356383,0.07773275,0.00006622892,0.00005096172,8.8314596e-7,0.000034061803,0.000015713462,0.0029565704],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9981936,0.000104080864,0.00026739185,0.0005675033,0.00050408614,0.00036330512],"domain_scores_gemma":[0.998133,0.00009923744,0.000327944,0.0010294603,0.00023216862,0.00017821167],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00038289954,0.00019907833,0.00031964327,0.00025157473,0.00034157975,0.000060825972,0.0019440177,0.00017530164,0.0004853682],"category_scores_gemma":[0.000053879103,0.00024705692,0.00016110434,0.00074857747,0.00016807704,0.0012896945,0.00087722205,0.00028026232,0.00010942287],"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":[0.00016973141,0.0022017146,0.4037522,0.00052160496,0.0008060887,0.00023656839,0.04243399,0.00037167504,0.053338666,0.010404581,0.009408597,0.47635457],"study_design_scores_gemma":[0.004695351,0.00059534126,0.8913229,0.00045666145,0.0002296095,0.00008447345,0.0019523291,0.071406245,0.00939693,0.00079099735,0.01759504,0.0014741283],"about_ca_topic_score_codex":0.00012374617,"about_ca_topic_score_gemma":0.00011875226,"teacher_disagreement_score":0.48757067,"about_ca_system_score_codex":0.000058931575,"about_ca_system_score_gemma":0.000045633416,"threshold_uncertainty_score":0.99999815},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37906694,0.00004645154,0.6204153,0.00023457583,0.000013921251,0.00007125236,0.000002404773,0.000036671176,0.000112485475],"genre_scores_gemma":[0.52498466,0.00015446734,0.47451606,0.00002550545,0.000009315738,0.000009070673,0.0000018244448,0.0000037374712,0.00029537163],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994567,0.000011484451,0.00009930344,0.000249358,0.00009780429,0.00008537149],"domain_scores_gemma":[0.99971277,0.000021592192,0.00004628335,0.00013629244,0.000046389705,0.000036663696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000046040852,0.00006337379,0.00007721917,0.000052624993,0.00010071159,0.000026860605,0.000072736606,0.000018305507,0.0000033649026],"category_scores_gemma":[0.000004179151,0.00004964164,0.0000054572147,0.00020526026,0.000081289145,0.00021547185,0.00003929354,0.00003696288,0.0000010908682],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010207098,0.00014708725,0.0068344306,0.00005609846,0.000048454418,0.0000057026004,0.0013371753,0.00014702561,0.011710131,0.006006463,0.0008967258,0.9728005],"study_design_scores_gemma":[0.0002718029,0.00024233734,0.21987352,0.000012871547,0.00001089603,0.00050992816,0.00006428892,0.77575415,0.0019361516,0.0005799309,0.0006029317,0.00014117065],"about_ca_topic_score_codex":0.000088976536,"about_ca_topic_score_gemma":0.000022297269,"teacher_disagreement_score":0.97265935,"about_ca_system_score_codex":0.000008433955,"about_ca_system_score_gemma":0.000029724517,"threshold_uncertainty_score":0.20243272},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009442994,0.000058034384,0.9868234,0.0031490424,0.00017545854,0.00024977096,0.0000015494409,0.00006923301,0.000030538158],"genre_scores_gemma":[0.48387274,0.0000030956592,0.5153179,0.000617742,0.00016268967,0.000019873247,0.0000013237402,0.0000036410731,9.367317e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99824816,0.000026794149,0.00022615067,0.0006992259,0.00025383945,0.0005458316],"domain_scores_gemma":[0.9987734,0.0003817825,0.00005027043,0.00065163645,0.000052480435,0.00009040948],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009390131,0.00012881894,0.00014391988,0.0002810104,0.00015805192,0.0004188009,0.0020121972,0.00004854771,0.0000010939934],"category_scores_gemma":[0.0000766445,0.00011799734,0.000034369412,0.0018253281,0.00020808076,0.0007385749,0.0005257335,0.00023396869,0.00000903698],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.878e-7,0.000027051798,0.00009202599,0.0000018551021,4.1032928e-7,0.0000011116889,0.00047154631,0.39546573,0.00006854608,0.0011495397,0.000012070106,0.6027094],"study_design_scores_gemma":[0.00025530267,0.000044576373,0.0016617015,0.000034335862,5.23903e-7,0.0000036431707,5.423099e-7,0.9913114,0.0006723685,0.005266343,0.0006012577,0.0001480288],"about_ca_topic_score_codex":0.00004120092,"about_ca_topic_score_gemma":0.00029749554,"teacher_disagreement_score":0.6025614,"about_ca_system_score_codex":0.00009873834,"about_ca_system_score_gemma":0.00012526872,"threshold_uncertainty_score":0.48117918},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77738017,0.000020395246,0.21252474,0.0012209282,0.00041638402,0.0005251771,0.00015135942,0.0002472885,0.0075135524],"genre_scores_gemma":[0.9681097,0.000013250963,0.031454366,0.00008592389,0.00003573736,4.1376188e-7,0.000028134546,0.000012302543,0.0002601165],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99801266,0.00020391992,0.000314619,0.00057631714,0.00056080095,0.00033169898],"domain_scores_gemma":[0.9982598,0.000109550965,0.00035160282,0.0008093934,0.00032366667,0.00014598704],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003109507,0.00028833057,0.00032616497,0.00059269316,0.0009905369,0.00007135214,0.0016677687,0.00013393183,0.000006383689],"category_scores_gemma":[0.000038208807,0.0002828206,0.00020856451,0.0011489476,0.0005026551,0.00093277066,0.00095853873,0.0003199422,0.0000062737304],"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":[0.00052279443,0.0011480569,0.0010847586,0.00031923156,0.00048400517,0.0009816083,0.0025405916,0.5084564,0.028588695,0.45445547,0.00025396963,0.0011644008],"study_design_scores_gemma":[0.0043783886,0.00059832085,0.0018072806,0.0016433964,0.00033407458,0.00023202065,0.0037128672,0.940646,0.023775404,0.00045258948,0.021115512,0.001304156],"about_ca_topic_score_codex":0.0019693368,"about_ca_topic_score_gemma":0.000045709665,"teacher_disagreement_score":0.4540029,"about_ca_system_score_codex":0.0018578145,"about_ca_system_score_gemma":0.0011251862,"threshold_uncertainty_score":0.9999624},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1387585,0.00005346678,0.81300616,0.0010720607,0.00015563275,0.00011650786,0.00001596695,0.00022958875,0.046592105],"genre_scores_gemma":[0.7411985,0.0000014026774,0.25819862,0.00006306231,0.0000042342904,0.0000036766517,0.0000020323744,0.000002051325,0.00052648346],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994792,0.00000832774,0.00014432825,0.0001572987,0.00010258575,0.00010830033],"domain_scores_gemma":[0.99950325,0.000058474398,0.0000493072,0.00030855963,0.000037153462,0.000043249653],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000769618,0.00004952822,0.000072434865,0.000040417934,0.00004344401,0.000025319252,0.00033504688,0.000021994336,0.00014164734],"category_scores_gemma":[0.000016932223,0.00004280731,0.000021120704,0.0002887263,0.0000425488,0.000036571102,0.00008391819,0.000033159333,0.000081484955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011140098,0.00056272466,0.00033641796,0.0000148217105,0.000042274518,0.000013934472,0.0036462594,0.003016324,0.003450692,0.19316703,0.036072902,0.7596755],"study_design_scores_gemma":[0.00013569192,0.000020742465,0.00020916904,0.000007725932,0.0000019302322,0.000010735686,0.000042710974,0.99803793,0.0004849439,0.000028323806,0.00096472335,0.00005537225],"about_ca_topic_score_codex":0.000008636453,"about_ca_topic_score_gemma":4.3004445e-7,"teacher_disagreement_score":0.9950216,"about_ca_system_score_codex":0.0000050826125,"about_ca_system_score_gemma":0.00000786254,"threshold_uncertainty_score":0.17456314},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009543767,0.0005015799,0.9916508,0.0010235582,0.0012306212,0.00017810629,0.000015674343,0.00017244434,0.005131752],"genre_scores_gemma":[0.009782519,0.00006569112,0.98685026,0.0009497806,0.0009848678,0.000016928783,0.00002434115,0.00002835966,0.0012972305],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970938,0.00001941831,0.00038801992,0.0010071109,0.0008463765,0.00064526347],"domain_scores_gemma":[0.9976457,0.00048361006,0.0003544528,0.0011752772,0.00017818269,0.00016278401],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010828228,0.00034013294,0.00034070993,0.00044066433,0.00028036922,0.000637003,0.0026841166,0.00028456157,0.000027548931],"category_scores_gemma":[0.000109168584,0.00032753748,0.000086880194,0.000406183,0.00016696849,0.0008276812,0.0011443864,0.0004922853,0.00019652909],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.3804835e-7,0.00001648145,0.0001650929,0.000007784806,0.0000070589567,0.0000050687313,0.00049285183,0.0003646659,0.000030712166,0.021592502,0.0001393617,0.9771781],"study_design_scores_gemma":[0.00040298427,0.0001404656,0.0015061271,0.0005175424,0.000033761236,0.00007432685,5.8352856e-7,0.7616234,0.0015411015,0.1449481,0.08741847,0.0017931678],"about_ca_topic_score_codex":0.000018410181,"about_ca_topic_score_gemma":0.000017378106,"teacher_disagreement_score":0.9753849,"about_ca_system_score_codex":0.0004543098,"about_ca_system_score_gemma":0.00027947885,"threshold_uncertainty_score":0.9999177},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00031253076,0.000007729651,0.9954537,0.0010008656,0.00020185788,0.0015965977,0.0009072386,0.00016196418,0.0003575254],"genre_scores_gemma":[0.40758765,0.000016288759,0.5896578,0.00020796037,0.00045900827,0.0010827373,0.00076955796,0.00002886622,0.00019017752],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997937,0.000015852653,0.0005608232,0.0007887656,0.00023225053,0.00046527086],"domain_scores_gemma":[0.9971915,0.00057434215,0.0002972442,0.0014496126,0.00035621427,0.00013112235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011679922,0.00017926792,0.0001851299,0.00012625709,0.0005505187,0.0004178203,0.0019831345,0.000106738014,0.000019135878],"category_scores_gemma":[0.00018282062,0.00018945016,0.000072694434,0.00037903848,0.00004014194,0.00046171527,0.00031052151,0.00012243121,0.00004835427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000097724815,0.00012008669,0.000041672807,0.000019148363,0.000017199662,1.2334276e-7,0.00014976172,0.00023935865,0.001964972,0.53334653,0.00016290549,0.4639285],"study_design_scores_gemma":[0.000044767123,0.000059900154,0.000065482345,0.000027326982,0.000023646611,0.0000011963745,0.00024567443,0.9308589,0.008111969,0.048875246,0.011432605,0.00025325044],"about_ca_topic_score_codex":0.000040304723,"about_ca_topic_score_gemma":0.00023151579,"teacher_disagreement_score":0.9306196,"about_ca_system_score_codex":0.00014428343,"about_ca_system_score_gemma":0.00011045893,"threshold_uncertainty_score":0.77255535},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62922627,0.064497,0.3037721,0.0003194239,0.0010327883,0.0003295267,0.000011772528,0.00010295651,0.0007081459],"genre_scores_gemma":[0.980672,0.00068407634,0.018178541,0.00002445892,0.00040715814,0.000006459163,5.1952003e-7,0.0000071062873,0.000019698226],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988068,0.000020724186,0.0006281548,0.00013238376,0.00017311948,0.00023883983],"domain_scores_gemma":[0.9992997,0.00008411489,0.00031817492,0.00011675605,0.000031229025,0.00015004934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000686386,0.00013282755,0.0003854028,0.000109995664,0.00010194858,0.000018419945,0.00036219045,0.000071202325,3.2161256e-7],"category_scores_gemma":[0.000007522073,0.00009992279,0.000038332102,0.0002534229,0.000040118477,0.00030172634,0.000098262055,0.0003244706,0.0000040185846],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000278792,0.0003395127,0.008856619,0.0025464522,0.00077561557,0.000019421599,0.07140311,0.0003058863,0.0082086455,0.13194536,0.029833544,0.74573797],"study_design_scores_gemma":[0.010276953,0.00072936894,0.025826462,0.02130879,0.001869297,0.0064458437,0.28091925,0.4783583,0.031323608,0.001592144,0.13638946,0.0049605095],"about_ca_topic_score_codex":0.0000056450526,"about_ca_topic_score_gemma":3.188358e-7,"teacher_disagreement_score":0.74077743,"about_ca_system_score_codex":0.0001223552,"about_ca_system_score_gemma":0.00005584625,"threshold_uncertainty_score":0.40747333},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00025818084,0.000024128623,0.9952404,0.0017858357,0.000100401056,0.00011907341,0.00028123008,0.0002096631,0.0019810856],"genre_scores_gemma":[0.0015792435,0.0000074945674,0.99403584,0.00018430491,0.00009667273,0.00010333271,0.00012675079,0.000005544859,0.003860843],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99927145,0.000009528515,0.00013790201,0.00023750107,0.00013617182,0.00020744545],"domain_scores_gemma":[0.9993829,0.00014577646,0.000076015014,0.00026205555,0.00007994281,0.000053289736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015252433,0.000071339804,0.00008387313,0.000032300664,0.00015871394,0.0002066986,0.00039842867,0.000041345174,0.00003446989],"category_scores_gemma":[0.00005186651,0.00006649027,0.00004094078,0.00019958842,0.000006965747,0.0003076141,0.00008153892,0.000035491845,0.00010833439],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.019108e-8,0.000044171255,0.000044289693,0.0000012118063,0.000010231459,2.9343e-7,0.00012717105,0.0000031946347,0.000016089987,0.008945186,0.05060082,0.9402073],"study_design_scores_gemma":[0.00018072975,0.000021529879,0.0003387683,0.0000034530772,0.0000042373817,0.00000177841,0.0000325753,0.9299083,0.00013454058,0.0004414526,0.068836875,0.00009577954],"about_ca_topic_score_codex":0.000009921973,"about_ca_topic_score_gemma":0.000002040714,"teacher_disagreement_score":0.9401115,"about_ca_system_score_codex":0.00005691497,"about_ca_system_score_gemma":0.0000071193767,"threshold_uncertainty_score":0.27113947},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12140186,0.000053072392,0.8776129,0.00015208399,0.000044430883,0.00005319215,0.0000057613147,0.00009571634,0.00058097055],"genre_scores_gemma":[0.20520484,0.0000070489627,0.79460174,0.000023311828,0.0000649274,0.0000065609706,0.000007189957,0.000004980471,0.00007939428],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99933594,0.000011763465,0.0001601156,0.00027334024,0.000079414494,0.00013943369],"domain_scores_gemma":[0.9995962,0.00003320391,0.00006174142,0.0002512948,0.000024562289,0.00003301319],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007225891,0.00007734473,0.000063884785,0.000046299432,0.00014652645,0.0003685277,0.00026829835,0.000020845871,0.0000023300822],"category_scores_gemma":[0.0000060810635,0.00006975753,0.000012860923,0.00014131762,0.000030265208,0.0004615532,0.0001965727,0.000044996363,0.000009715294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.8965314e-7,0.00003621041,0.0006579782,0.000008676211,0.000005476915,0.0000035000464,0.00010420926,0.00093328004,0.0051635974,0.064841494,0.0001901981,0.9280551],"study_design_scores_gemma":[0.00005864256,0.0000058220844,0.021093331,0.000012876644,0.0000029528537,0.00002195411,0.000027592043,0.9761747,0.0003406316,0.0016114557,0.0005529825,0.000097032884],"about_ca_topic_score_codex":0.00031932644,"about_ca_topic_score_gemma":0.000007821708,"teacher_disagreement_score":0.9752414,"about_ca_system_score_codex":0.000018153878,"about_ca_system_score_gemma":0.000016962256,"threshold_uncertainty_score":0.3553721},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006939746,0.00092719926,0.9943528,0.0015723286,0.0005285991,0.00043993798,0.00001928921,0.000052989115,0.0020374435],"genre_scores_gemma":[0.006762617,0.00082911225,0.99035686,0.001060545,0.00033523145,0.000037983016,0.000015372934,0.000029271005,0.00057300366],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997786,0.000016747052,0.00037726684,0.0010130092,0.0005135072,0.0002935013],"domain_scores_gemma":[0.9977388,0.00037025154,0.00031702092,0.0011651835,0.00030969546,0.00009907081],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003826776,0.00031748443,0.0004338401,0.00038623257,0.00013287498,0.00025498754,0.0018861565,0.00014136457,0.000016014103],"category_scores_gemma":[0.00011402934,0.0002593331,0.000051773422,0.0004762615,0.0006861383,0.0004159727,0.00080443214,0.00033517653,0.000044384808],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.2069644e-7,0.000019625659,0.000009509188,0.00007222547,0.000005291318,0.000004895216,0.00019464197,0.0002952355,0.000040039035,0.049934052,0.00027575283,0.9491478],"study_design_scores_gemma":[0.0006592646,0.00096706575,0.0011087683,0.007301636,0.00004715529,0.00014865858,0.0000015739342,0.3840822,0.0049989563,0.5454272,0.05289176,0.002365783],"about_ca_topic_score_codex":0.000023854796,"about_ca_topic_score_gemma":0.0000035878527,"teacher_disagreement_score":0.94678205,"about_ca_system_score_codex":0.0000555405,"about_ca_system_score_gemma":0.00022220307,"threshold_uncertainty_score":0.9999859},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001346683,0.00011221865,0.99334717,0.00022376177,0.0009283109,0.00017860149,0.000014578972,0.00006833892,0.004992331],"genre_scores_gemma":[0.024474151,0.00007867543,0.9749599,0.00015591188,0.0001882703,0.0000062890986,0.0000075303024,0.00001442656,0.00011485579],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99769974,0.000012347681,0.00044946105,0.00096674997,0.0005901905,0.00028149848],"domain_scores_gemma":[0.99767274,0.00051748095,0.00033969022,0.0011375146,0.00024401207,0.0000885759],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036072088,0.00027772438,0.00036147286,0.00064259267,0.00012824954,0.00021769127,0.002253252,0.00016415514,0.000024229357],"category_scores_gemma":[0.00007274964,0.0002507164,0.00008675856,0.0006087125,0.00063184346,0.0006255719,0.00089885655,0.00040567218,0.000024652274],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027787737,0.000017564318,0.000018597082,0.000004387355,0.000004984608,0.0000124544595,0.00020651746,0.0015653658,0.000059476486,0.026315868,0.000018350185,0.9717737],"study_design_scores_gemma":[0.00026602185,0.00018779852,0.00023873281,0.0006378049,0.000009579818,0.0002447653,6.4094644e-7,0.6055972,0.0022162641,0.3841335,0.005960843,0.0005068797],"about_ca_topic_score_codex":0.00002995806,"about_ca_topic_score_gemma":0.000047982157,"teacher_disagreement_score":0.97126675,"about_ca_system_score_codex":0.0001372111,"about_ca_system_score_gemma":0.00025359783,"threshold_uncertainty_score":0.9999945},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030518153,0.00000943924,0.97895557,0.0024492443,0.00008836476,0.00018177232,0.00001413343,0.00015848826,0.015091186],"genre_scores_gemma":[0.022962997,6.7366017e-7,0.96011215,0.0019278754,0.000089912755,0.00017108142,0.000014141416,0.000008646575,0.014712513],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993341,0.00000691853,0.000109619126,0.00025750283,0.00010373401,0.00018811115],"domain_scores_gemma":[0.9991783,0.00007475604,0.00002418448,0.00043020584,0.000095246025,0.00019733049],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001969477,0.00007058235,0.00008216575,0.000056369372,0.000050801358,0.00014722033,0.00061635306,0.000022948958,0.000009087541],"category_scores_gemma":[0.000054633867,0.00006117939,0.000021364913,0.00022062147,0.000011616838,0.0002152233,0.00020628642,0.000026056883,0.00021652677],"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":[0.000008705448,0.00008913455,0.00014879109,0.000007029435,0.000020742878,0.0000041086805,0.0029887836,0.00019937826,0.00024282301,0.33249673,0.4080583,0.2557355],"study_design_scores_gemma":[0.00037745087,0.00018050888,0.00017236575,0.000011364516,0.0000047037224,0.0000091417,0.00017259465,0.17397828,0.0011400022,0.0036063208,0.8201611,0.00018615893],"about_ca_topic_score_codex":0.00004678731,"about_ca_topic_score_gemma":0.000011986982,"teacher_disagreement_score":0.41210282,"about_ca_system_score_codex":0.00001423488,"about_ca_system_score_gemma":0.000067335124,"threshold_uncertainty_score":0.27830857},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030439056,0.000468045,0.96759856,0.00040776964,0.000021485897,0.00010212098,0.0008498186,0.000051825144,0.00006133694],"genre_scores_gemma":[0.29659516,0.00019791709,0.6995202,0.00015837801,0.0000758347,0.000009577376,0.003416339,0.000009043268,0.000017567425],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978362,0.00008104364,0.00038545494,0.0011621284,0.00025999954,0.00027520972],"domain_scores_gemma":[0.99474275,0.0006372747,0.00016256107,0.0042745643,0.000047267567,0.00013560218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012117579,0.0001684589,0.00032663962,0.00024998788,0.0005989929,0.00031270037,0.0027675286,0.00005454775,0.00000857856],"category_scores_gemma":[0.00020970215,0.00012745666,0.000038229115,0.0011308605,0.00018543238,0.0006768423,0.002950959,0.00013723878,0.0000051747097],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025882398,0.000040726434,0.019439118,0.000006195103,0.00039640025,0.00018821226,0.00060647685,0.00012795485,0.0000024906358,0.00025243525,0.0042562447,0.97468114],"study_design_scores_gemma":[0.00008333003,0.000016890472,0.0021796864,0.0000092308355,0.0004965622,0.00048140978,0.0001857362,0.9913164,0.000015437965,0.000040786228,0.0050159595,0.00015861126],"about_ca_topic_score_codex":0.00089911034,"about_ca_topic_score_gemma":0.0002902352,"teacher_disagreement_score":0.9911884,"about_ca_system_score_codex":0.000014377188,"about_ca_system_score_gemma":0.000066619636,"threshold_uncertainty_score":0.5197532},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002315634,0.0017818274,0.99053484,0.00054334017,0.0032015226,0.00036271164,0.000052249023,0.00005465734,0.0011532394],"genre_scores_gemma":[0.09106833,0.00014883945,0.9039839,0.00027343348,0.0029192234,0.00011059089,0.000030672367,0.00006343898,0.0014015709],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99750954,0.00008128479,0.0010821158,0.0003033857,0.0006521271,0.0003715355],"domain_scores_gemma":[0.9967509,0.00020037078,0.0008662182,0.0005427824,0.001197818,0.00044193518],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016906935,0.00021531718,0.00044500743,0.00027191456,0.00012506369,0.0005258284,0.001441144,0.00009104287,0.0000016877319],"category_scores_gemma":[0.00016664685,0.0001744664,0.00018580642,0.00045676657,0.00003751362,0.0006492297,0.00015933509,0.00019197623,0.000052076033],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013764182,0.00040506665,0.0003012707,0.00007924578,0.00028092277,0.00008928209,0.004507276,0.0017476423,0.0002596954,0.017327245,0.103271574,0.87171704],"study_design_scores_gemma":[0.0019728707,0.0021371646,0.00014577765,0.0011058331,0.00012833947,0.0034344872,0.009092502,0.48655677,0.0026474271,0.0036463358,0.48807192,0.0010605911],"about_ca_topic_score_codex":0.000066298315,"about_ca_topic_score_gemma":0.0000022524987,"teacher_disagreement_score":0.87065643,"about_ca_system_score_codex":0.00021283171,"about_ca_system_score_gemma":0.0003120672,"threshold_uncertainty_score":0.7114534},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0069250828,0.0000050383296,0.9531507,0.00008283398,0.00008480823,0.00008009648,0.000025263194,0.0000858123,0.03956036],"genre_scores_gemma":[0.7666899,0.000005399211,0.23157597,0.00013831118,0.000020590878,0.000034828678,0.000004299951,0.0000040806385,0.0015266122],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994964,0.000010650313,0.00014464134,0.00015859482,0.00008442975,0.00010528209],"domain_scores_gemma":[0.99946624,0.000023024528,0.00004733127,0.00035144863,0.00006248031,0.000049501185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007526113,0.00005107572,0.000072614304,0.00005369556,0.00007939336,0.000035424637,0.0004305981,0.000013725116,0.00017125503],"category_scores_gemma":[0.000005691455,0.000044186658,0.000027477128,0.00028348668,0.000022618286,0.00015696704,0.000091205984,0.00003499862,0.000028131692],"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":[0.0000020223374,0.0006173636,0.002873519,0.000008584219,0.00005193536,0.0000041722105,0.001992668,0.0000040765863,0.0023062348,0.8820403,0.009263517,0.100835614],"study_design_scores_gemma":[0.0048015523,0.0014571272,0.15688458,0.00016709555,0.0001111757,0.00016710206,0.0016035789,0.42016777,0.301029,0.052033488,0.05954276,0.0020347647],"about_ca_topic_score_codex":0.0008345521,"about_ca_topic_score_gemma":0.00017203286,"teacher_disagreement_score":0.8300068,"about_ca_system_score_codex":0.000008747021,"about_ca_system_score_gemma":0.00003549858,"threshold_uncertainty_score":0.18751225},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00043353703,0.000030008501,0.99461687,0.0019112959,0.00024336063,0.00016120811,0.0008313909,0.00018904339,0.001583308],"genre_scores_gemma":[0.004550452,0.000004010541,0.9922361,0.00072165474,0.00031474265,0.00006740109,0.0015026013,0.000010925432,0.00059212063],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986473,0.000024036019,0.00021808801,0.00068775495,0.00017009744,0.0002527756],"domain_scores_gemma":[0.9973745,0.00035624436,0.00007286124,0.002039141,0.000051524163,0.000105769665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004118796,0.000121814766,0.00014194893,0.00004012251,0.00016128416,0.00029075646,0.0025916186,0.00004298976,0.000024456433],"category_scores_gemma":[0.00008766601,0.0001053433,0.000028366112,0.00017545621,0.000028100105,0.00055237487,0.00072621787,0.000053820637,0.00006956821],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.243144e-7,0.000044647404,0.00006854263,0.000003599762,0.00001795801,5.566379e-7,0.0001992969,0.0000324932,0.00018780438,0.030359305,0.067564726,0.9015204],"study_design_scores_gemma":[0.00019860575,0.000027988895,0.00015339708,0.000009011947,0.0000055189257,0.0000013953228,0.00005483256,0.7820416,0.0001837092,0.0025058503,0.21468243,0.00013567707],"about_ca_topic_score_codex":0.00054989796,"about_ca_topic_score_gemma":0.00005977038,"teacher_disagreement_score":0.90138465,"about_ca_system_score_codex":0.000015797288,"about_ca_system_score_gemma":0.00003971127,"threshold_uncertainty_score":0.48159152},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0054132794,0.0000023923194,0.99298376,0.00057240337,0.00039406063,0.000249364,0.0000033861147,0.00024962798,0.00013172638],"genre_scores_gemma":[0.30723703,0.000004936877,0.6914653,0.00091681315,0.00019051046,0.00013326325,0.000042914493,0.000004439487,0.000004778068],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988288,0.000009496441,0.00020894314,0.00034375553,0.00028743673,0.0003215398],"domain_scores_gemma":[0.99903244,0.000054148106,0.00012774668,0.00038597584,0.0002989929,0.000100679776],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007314922,0.00009911479,0.00009046742,0.00027188633,0.0003998441,0.00082719675,0.0012890007,0.000025315032,4.7399004e-7],"category_scores_gemma":[0.00006869914,0.00009458088,0.000029434346,0.0013675841,0.00008568909,0.003923855,0.00022591594,0.000053284366,0.000020131665],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.26962e-7,0.000016254477,0.00008533485,0.000014979627,0.0000013089824,1.8620664e-8,0.0002616475,0.000011527172,0.0049130963,0.15214723,0.00009883108,0.8424491],"study_design_scores_gemma":[0.00013404219,0.00009900022,0.0057836864,0.000009721453,0.000001453811,0.000006302692,0.0000013237725,0.971228,0.0029761253,0.0025528022,0.017067058,0.00014047703],"about_ca_topic_score_codex":0.0000013389657,"about_ca_topic_score_gemma":3.261639e-7,"teacher_disagreement_score":0.9712165,"about_ca_system_score_codex":0.000022814902,"about_ca_system_score_gemma":0.000093466,"threshold_uncertainty_score":0.7976677},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00093167846,0.0000065948752,0.51617223,0.4758727,0.0006168491,0.00069631374,0.0001309938,0.0002681296,0.0053045233],"genre_scores_gemma":[0.0112359375,0.00003559257,0.7524106,0.022443635,0.19326705,0.0032426391,0.0038736486,0.00009291311,0.013398022],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978976,0.000073646224,0.00039806427,0.0009443877,0.00035877878,0.00032749926],"domain_scores_gemma":[0.99390376,0.00024532623,0.00014318635,0.005519689,0.0001066958,0.00008136641],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00035467194,0.00020247974,0.00015686931,0.00024662868,0.00074485247,0.0006953455,0.003949926,0.00003456088,0.00010867927],"category_scores_gemma":[0.00008774236,0.00016626329,0.00003728142,0.0018792045,0.00007766521,0.0012483933,0.0010439291,0.00019077367,0.0028253032],"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":[0.0000018728387,0.000071820934,0.00008404116,0.0000012647122,0.0000067974447,8.364476e-7,0.00018133916,0.00043664454,0.00010748858,0.015517133,0.8766944,0.106896356],"study_design_scores_gemma":[0.00009453623,0.000028861296,0.0012457431,0.000005073036,0.000013324541,0.0000028435984,0.000088601344,0.004151499,0.0004977924,0.0009199587,0.9927419,0.00020989944],"about_ca_topic_score_codex":0.00037897253,"about_ca_topic_score_gemma":0.0019327798,"teacher_disagreement_score":0.45342907,"about_ca_system_score_codex":0.00006296162,"about_ca_system_score_gemma":0.000049663435,"threshold_uncertainty_score":0.9979511},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00081892597,0.0001689767,0.9793909,0.01712461,0.00024754135,0.0010326251,0.000114641014,0.0005020141,0.00059972424],"genre_scores_gemma":[0.08051668,0.0005168115,0.916527,0.0005690307,0.0002672076,0.0010224902,0.00011990934,0.00003729917,0.00042360873],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99774164,0.00010556044,0.0005719508,0.00089698937,0.00024636975,0.0004375152],"domain_scores_gemma":[0.9908253,0.0007413342,0.00017395377,0.007612838,0.0002529316,0.00039365143],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00038380933,0.000329834,0.0002789328,0.0003680071,0.0015202763,0.00021265361,0.0046841744,0.00013506394,0.00008800896],"category_scores_gemma":[0.00012489958,0.00034277292,0.00009195294,0.0012379584,0.0002842942,0.0005446683,0.0005407048,0.00053860596,0.00078712695],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000053884864,0.0008110337,0.00009034618,0.000008836762,0.000051833627,3.5288886e-7,0.002242988,0.000057186404,0.0012207836,0.0037507094,0.0016672802,0.99009323],"study_design_scores_gemma":[0.0015915283,0.0005178866,0.00796693,0.00013751931,0.00023702919,0.000102066806,0.0013563678,0.38415214,0.0054043075,0.008229588,0.5883789,0.0019257161],"about_ca_topic_score_codex":0.00049881724,"about_ca_topic_score_gemma":0.0001575346,"teacher_disagreement_score":0.9881675,"about_ca_system_score_codex":0.000068771835,"about_ca_system_score_gemma":0.00007897156,"threshold_uncertainty_score":0.9999909},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030982883,0.0000071374557,0.95290065,0.00066344626,0.0000339338,0.000015540365,6.730203e-7,0.00014368379,0.04313665],"genre_scores_gemma":[0.19561689,0.000010622576,0.7984175,0.000508006,0.000030010076,0.000008881753,0.0000017917182,0.0000016566479,0.0054046162],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9997701,0.0000019477557,0.00003398507,0.00009038992,0.00004774534,0.000055852975],"domain_scores_gemma":[0.99970245,0.000009264278,0.0000061556884,0.00024731198,0.000009527091,0.000025309639],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000020229516,0.000020113306,0.000020825122,0.000011100299,0.00007128371,0.000015967167,0.00030740805,0.000005922766,0.000020708772],"category_scores_gemma":[0.00000275263,0.000016132724,0.000008538669,0.00010753967,0.000012122805,0.00014272364,0.000074756594,0.000016511283,0.00034778402],"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":[9.6211174e-8,0.000049060836,0.00050939823,6.0244764e-7,0.0000028462118,0.000013603423,0.00022743699,0.0000027325507,0.0002592062,0.6667692,0.102323204,0.22984257],"study_design_scores_gemma":[0.00023497466,0.000040943494,0.020623265,0.0000022764482,0.0000012560615,0.0003352501,0.000012163809,0.2880213,0.004215351,0.006411288,0.6798279,0.00027397717],"about_ca_topic_score_codex":0.000010398789,"about_ca_topic_score_gemma":3.1307667e-7,"teacher_disagreement_score":0.66035795,"about_ca_system_score_codex":0.0000022529484,"about_ca_system_score_gemma":0.000010667546,"threshold_uncertainty_score":0.44701758},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03664747,0.0000059315053,0.9600275,0.00059080584,0.00016307272,0.00006764969,0.000027727649,0.00015166186,0.0023181813],"genre_scores_gemma":[0.7579988,0.0000043720775,0.24055783,0.001025823,0.00014622748,0.000060592643,0.00017062246,0.000009303027,0.00002639726],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925435,0.000034624816,0.00013705024,0.00028012137,0.00015565219,0.00013819033],"domain_scores_gemma":[0.9993088,0.00014801402,0.000055553766,0.00037368076,0.000053667824,0.00006026587],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00021764406,0.00007887998,0.000074229574,0.000071255825,0.00010035471,0.00014204458,0.00034603404,0.000034856857,0.00003956242],"category_scores_gemma":[0.000040818297,0.00007384618,0.00003594346,0.00015865431,0.000012842274,0.00026344764,0.000063790976,0.000059048507,0.0010681861],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.286644e-7,0.000035369478,0.00028685652,0.0000023920747,0.0000013243541,4.5001434e-7,0.000018342687,0.000004320545,0.00014793652,0.00007621582,0.00078434503,0.9986418],"study_design_scores_gemma":[0.0011576641,0.00017241652,0.050254054,0.00017758258,0.000018012683,0.0000146486345,0.000015700605,0.8500295,0.007940124,0.06693062,0.022741925,0.0005476908],"about_ca_topic_score_codex":0.00003107706,"about_ca_topic_score_gemma":0.000017822944,"teacher_disagreement_score":0.99809414,"about_ca_system_score_codex":0.000012218168,"about_ca_system_score_gemma":0.000010316293,"threshold_uncertainty_score":0.9997096},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036788292,0.000022236922,0.9611819,0.0010078766,0.00055171445,0.00009620023,0.00007618362,0.000032534797,0.00024309817],"genre_scores_gemma":[0.39831853,0.00001593304,0.6010215,0.00006120419,0.00045779336,0.000006721088,0.000025999525,0.000010261539,0.000082041246],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988722,0.000016775344,0.00039602176,0.00025664346,0.00022364933,0.00023467699],"domain_scores_gemma":[0.9980999,0.000100190504,0.0004252133,0.00076758704,0.0004937068,0.00011337689],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003428316,0.00013884214,0.00025911193,0.00005044388,0.0001866062,0.0005330707,0.0021296279,0.000047942558,0.00001091479],"category_scores_gemma":[0.00010886091,0.000121752295,0.000059934115,0.00023893743,0.00009025629,0.0019605062,0.00028461672,0.00024825943,0.0000039462006],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007984194,0.00004306937,0.00006047872,0.000011242532,0.00004266594,0.0000040392006,0.001911939,0.000018350907,0.018132888,0.031247951,0.0012823656,0.947237],"study_design_scores_gemma":[0.0026663004,0.0014453321,0.0070766043,0.00031168357,0.0002473545,0.00080198445,0.0041521396,0.62674636,0.1298563,0.096942306,0.12809148,0.001662142],"about_ca_topic_score_codex":0.0000053913195,"about_ca_topic_score_gemma":0.000010655822,"teacher_disagreement_score":0.9455749,"about_ca_system_score_codex":0.000006846772,"about_ca_system_score_gemma":0.0004442624,"threshold_uncertainty_score":0.5140413},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004055239,0.000082500774,0.98626477,0.00014909256,0.0003580807,0.00040366474,0.008426124,0.00012208078,0.00013843954],"genre_scores_gemma":[0.33107996,0.000005790021,0.6659688,0.000036372017,0.00009165509,0.0002497769,0.0023307153,0.00002191763,0.00021501088],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851424,0.00004759452,0.0003683181,0.00061611267,0.00023632051,0.00021742148],"domain_scores_gemma":[0.9948097,0.000276077,0.00015554162,0.0045970688,0.00008547681,0.00007614528],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035919674,0.00014044449,0.00018945993,0.00012616652,0.00020467355,0.00012672748,0.0026053933,0.00004701279,0.0000091201955],"category_scores_gemma":[0.000031862884,0.00013413896,0.00004006085,0.00029540487,0.000041501044,0.0012561426,0.00006890023,0.000077576486,0.000012674595],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001548535,0.0064767944,0.00008766302,0.00084008777,0.00054158,0.00005567795,0.0027321,0.009246011,0.047039393,0.11308687,0.10017843,0.71956056],"study_design_scores_gemma":[0.001605773,0.00041153101,0.00014565632,0.0003625962,0.000093164985,0.00008052662,0.0011100565,0.88527346,0.016097445,0.00050724414,0.09357873,0.0007337999],"about_ca_topic_score_codex":0.00065141247,"about_ca_topic_score_gemma":0.000041105817,"teacher_disagreement_score":0.87602746,"about_ca_system_score_codex":0.000015901518,"about_ca_system_score_gemma":0.00006219418,"threshold_uncertainty_score":0.5470028},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005335314,0.000010387521,0.99319035,0.00096444815,0.0000988666,0.00032663773,0.0000120907325,0.000021174035,0.00004074345],"genre_scores_gemma":[0.42240652,0.000030142302,0.57689464,0.0006317805,0.000018831815,0.0000075114804,0.000008571161,8.7158065e-7,0.0000011475408],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99930423,0.0000062250315,0.00028072487,0.0000770273,0.00018848744,0.00014329773],"domain_scores_gemma":[0.9992408,0.00014356156,0.00018484906,0.00023273485,0.00015890725,0.00003912478],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008280693,0.00005675422,0.000055811946,0.00004853525,0.0008613898,0.00057534175,0.00062145764,0.000012134341,1.0089779e-7],"category_scores_gemma":[0.000023472152,0.000032282485,0.000014350874,0.00046010973,0.00016896582,0.003631163,0.00021741993,0.000034491575,5.0867277e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.214825e-7,0.0000021337569,0.000025683956,0.0000044633966,0.0000010055289,2.9170557e-9,0.001279515,0.00020060728,0.000015117918,0.10007231,0.00037554762,0.898023],"study_design_scores_gemma":[0.00017347514,0.00006312825,0.021022646,0.000008090441,0.0000016841628,0.0000062763174,0.00017483735,0.97232544,0.00069546246,0.0014191741,0.004061249,0.000048540736],"about_ca_topic_score_codex":0.0000022537517,"about_ca_topic_score_gemma":2.01363e-7,"teacher_disagreement_score":0.9721248,"about_ca_system_score_codex":0.0000128397305,"about_ca_system_score_gemma":0.00007403121,"threshold_uncertainty_score":0.66252005},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11553466,0.00010722751,0.7677879,0.058921188,0.00030152194,0.00036609755,0.00010559969,0.0008277765,0.056048065],"genre_scores_gemma":[0.663508,0.00004753177,0.3271768,0.003645012,0.00011034465,0.0000672177,0.00003802954,0.000013803894,0.0053932536],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99909294,0.000012753797,0.00016565595,0.00035140882,0.00016182115,0.0002154033],"domain_scores_gemma":[0.99919367,0.000029893457,0.000029100618,0.0005963206,0.000026510756,0.00012449357],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000081742386,0.000105345825,0.00009556079,0.000036646637,0.000113218164,0.00015571255,0.00077916303,0.000034804725,0.001037698],"category_scores_gemma":[0.0000043881623,0.000092082846,0.000031757438,0.00019239786,0.00010186338,0.00017597726,0.00009808085,0.00006684255,0.00028521995],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.2037829e-7,0.000029377112,0.00029251253,0.0000021521644,0.000005708405,0.0000073341703,0.0011624419,0.0000037545658,0.000033583983,0.0024156407,0.0076526864,0.9883947],"study_design_scores_gemma":[0.0016497695,0.00026269426,0.012969286,0.00018792516,0.0000321016,0.00029257953,0.00199956,0.41673547,0.0036728703,0.014951181,0.5453707,0.0018758458],"about_ca_topic_score_codex":0.00062894024,"about_ca_topic_score_gemma":0.000111594,"teacher_disagreement_score":0.98651886,"about_ca_system_score_codex":0.000024067365,"about_ca_system_score_gemma":0.000053641063,"threshold_uncertainty_score":0.9998755},"labels":[],"label_agreement":null},{"id":"W1973249903","doi":"10.1007/s10115-012-0585-7","title":"Models of distributed data clustering in peer-to-peer environments","year":2012,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; D2L (Canada)","funders":"","keywords":"Cluster analysis; Computer science; Automatic summarization; Scalability; Data mining; Distributed computing; Process (computing); Data stream clustering; Node (physics); Correlation clustering; Set (abstract data type); CURE data clustering algorithm; Machine learning; Artificial intelligence; Database; Engineering","score_opus":0.04619821659333672,"score_gpt":0.2805203146211613,"score_spread":0.23432209802782455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973249903","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029425414,0.00016233373,0.99233896,0.00011376448,0.00020170271,0.0001864368,0.00027876842,0.000019134342,0.0037563923],"genre_scores_gemma":[0.9926476,0.000013642219,0.006543067,0.000022324488,0.000040496045,0.000031705567,0.000507163,0.0000024142519,0.00019157915],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992382,0.000017240465,0.00032856726,0.00009060482,0.00018424274,0.00014117607],"domain_scores_gemma":[0.99923444,0.000022235365,0.000086442386,0.00052437524,0.0000518299,0.00008065182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006625629,0.00006355355,0.00010552718,0.000096486125,0.00004014586,0.00008986786,0.00048464027,0.00003223629,7.924266e-7],"category_scores_gemma":[0.000028192168,0.000058143432,0.0000070125016,0.00021754458,0.000010232363,0.0057384027,0.0005571681,0.000041062744,0.00008275505],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015031877,0.00057899195,0.007792468,0.00072453835,0.000074747324,4.891171e-7,0.07850846,0.011652478,0.000349345,0.17586589,0.08008521,0.6443524],"study_design_scores_gemma":[0.00012696853,0.000007175678,0.0021684365,0.00002940879,0.0000014446633,0.000003177016,0.00021916222,0.70765674,0.000026786012,0.000008675582,0.2896893,0.00006273994],"about_ca_topic_score_codex":0.00004162135,"about_ca_topic_score_gemma":0.0000024946755,"teacher_disagreement_score":0.9897051,"about_ca_system_score_codex":0.00002333253,"about_ca_system_score_gemma":0.000012697406,"threshold_uncertainty_score":0.41602036},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037057646,0.000040926687,0.89947915,0.0128164105,0.00011608187,0.00020648388,0.000036132897,0.00013028404,0.050116874],"genre_scores_gemma":[0.58002883,0.0000032553899,0.41682103,0.00068720296,0.00007102354,0.000008338277,0.000002635794,0.0000035925611,0.002374071],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995151,0.0000111289355,0.00012491595,0.00011292097,0.0001046706,0.00013123511],"domain_scores_gemma":[0.9994494,0.000042628784,0.000052185373,0.00041389844,0.000023250117,0.000018667703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022395265,0.000035823,0.000043793225,0.000013644302,0.000092104056,0.000040701776,0.0006684188,0.000010010974,0.000045272598],"category_scores_gemma":[0.000010099266,0.000023423097,0.000026808037,0.00018412803,0.000016390879,0.00018286047,0.0002716295,0.000033516695,0.000033304746],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.9765932e-7,0.000052120722,0.0006307745,0.000004767018,0.000012127682,1.1697089e-7,0.00078721053,0.00002912956,0.0020675433,0.4362968,0.016222082,0.54389715],"study_design_scores_gemma":[0.00020988887,0.000014684724,0.0074648196,0.000010303521,0.000008242014,0.000006065956,0.0001696474,0.18357803,0.026282074,0.0009805307,0.781152,0.0001236896],"about_ca_topic_score_codex":0.000049705402,"about_ca_topic_score_gemma":0.000032653104,"teacher_disagreement_score":0.76492995,"about_ca_system_score_codex":0.0000056751032,"about_ca_system_score_gemma":0.000016832302,"threshold_uncertainty_score":0.12420996},"labels":[],"label_agreement":null},{"id":"W1974256760","doi":"10.1007/s10115-009-0237-8","title":"A general measure of similarity for categorical sequences","year":2009,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Categorical variable; Similarity (geometry); Computer science; Data mining; Matching (statistics); Similarity measure; Pattern recognition (psychology); Artificial intelligence; Range (aeronautics); Domain (mathematical analysis); Measure (data warehouse); Process (computing); Sequence (biology); Noise (video); Mathematics; Machine learning; Statistics; Image (mathematics)","score_opus":0.024416134772725646,"score_gpt":0.2734250690558867,"score_spread":0.24900893428316107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1974256760","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018932987,0.00048663758,0.98596627,0.0003157705,0.00019652079,0.0002968145,0.000031695112,0.000059997226,0.010752988],"genre_scores_gemma":[0.9850036,0.00002513041,0.014595366,0.00008393449,0.000092029084,0.000046930054,0.000035167697,0.0000012673715,0.000116584924],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99945873,0.000013727977,0.00026808365,0.00007819594,0.00009018845,0.00009107185],"domain_scores_gemma":[0.99943876,0.000028088147,0.00009913321,0.00017046959,0.00021740298,0.000046138433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028696927,0.000057927304,0.00011311485,0.00006209648,0.0000870053,0.00012098805,0.0002171129,0.000041601124,3.2087493e-7],"category_scores_gemma":[0.000023112825,0.00004692666,0.000023657465,0.00017999666,0.00001536625,0.0015689016,0.000025067855,0.000031747713,0.000008311342],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002200736,0.000030211842,0.00004546435,0.00007122772,0.000007106214,5.779373e-8,0.0020756342,0.000027782866,0.00012298264,0.75161684,0.0076129423,0.23838754],"study_design_scores_gemma":[0.00039223395,0.00016685156,0.0015492189,0.000030002746,0.000007004767,0.000020480667,0.00014843507,0.6643068,0.00044864835,0.0015402831,0.33123484,0.00015516192],"about_ca_topic_score_codex":0.000016326658,"about_ca_topic_score_gemma":7.9554957e-7,"teacher_disagreement_score":0.9831103,"about_ca_system_score_codex":0.000012375438,"about_ca_system_score_gemma":0.00005029297,"threshold_uncertainty_score":0.19136137},"labels":[],"label_agreement":null},{"id":"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037241592,0.000004941719,0.9790049,0.0024340507,0.000030958337,0.000017794728,0.0000013112134,0.0001511209,0.014630714],"genre_scores_gemma":[0.75645846,0.0000038375115,0.24144004,0.0013203333,0.00003190928,0.0000019845863,0.0000025601714,9.107135e-7,0.00073993794],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99971324,0.0000024451028,0.000040957293,0.00011222785,0.00005452098,0.0000765781],"domain_scores_gemma":[0.9996975,0.000006933601,0.000009107624,0.0002496655,0.000008621942,0.000028142867],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000033553093,0.000027191361,0.000024941923,0.000016118665,0.000050568597,0.00007968313,0.00037157556,0.00000690508,0.000017820454],"category_scores_gemma":[0.0000019376198,0.000022550726,0.000010437972,0.00008590116,0.0000022892305,0.00019733915,0.000054686603,0.000021275357,0.00009062146],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.6378654e-8,0.000012854126,0.00014719804,1.718199e-7,5.3600274e-7,0.0000011116238,0.000052518833,0.0000018174649,0.00005351203,0.22556601,0.001940875,0.77222335],"study_design_scores_gemma":[0.00040180565,0.00013758636,0.21222962,0.000022762217,0.0000046614864,0.000029612427,0.00007676063,0.5933958,0.005057227,0.043906856,0.14418896,0.0005483162],"about_ca_topic_score_codex":0.000011490092,"about_ca_topic_score_gemma":6.572719e-7,"teacher_disagreement_score":0.77167505,"about_ca_system_score_codex":0.000003653516,"about_ca_system_score_gemma":0.0000042560237,"threshold_uncertainty_score":0.11647858},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12091319,0.00032164328,0.43391764,0.43040198,0.0056367763,0.0017298263,0.002945855,0.0005901469,0.0035429387],"genre_scores_gemma":[0.5047298,0.00016446388,0.4583522,0.022302486,0.004049383,0.00092365895,0.0038993831,0.00016778738,0.005410825],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99792427,0.0000793913,0.00045420724,0.00086325174,0.00035307553,0.00032581552],"domain_scores_gemma":[0.986958,0.0013564479,0.00021081638,0.011288213,0.00009734762,0.000089132736],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0002917747,0.00026419453,0.0002366237,0.00010961533,0.0004920158,0.00048117427,0.01011466,0.00013456639,0.000043319415],"category_scores_gemma":[0.00083119917,0.00019641028,0.00009644545,0.00088808127,0.00020492269,0.0024098763,0.004830461,0.00057095545,0.0003129413],"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":[0.000009514864,0.0005399824,0.0011907947,0.000012223302,0.00007791811,0.0000046287314,0.0022456194,0.00016089441,0.00787264,0.013875176,0.9097424,0.06426821],"study_design_scores_gemma":[0.00081846456,0.0000607579,0.008407855,0.00024194736,0.00008254375,0.0000054640977,0.00033356543,0.035154402,0.0066960673,0.016204964,0.9311208,0.0008731411],"about_ca_topic_score_codex":0.00018409996,"about_ca_topic_score_gemma":0.0011217617,"teacher_disagreement_score":0.4080995,"about_ca_system_score_codex":0.000029239165,"about_ca_system_score_gemma":0.00015679283,"threshold_uncertainty_score":0.9952411},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049342573,0.00027064662,0.92719126,0.016901093,0.000028407532,0.000066064924,0.000004816725,0.00013254845,0.006062587],"genre_scores_gemma":[0.8072804,0.000038827948,0.19126995,0.0008144408,0.00002777834,0.0000067820683,0.0000032091486,0.000001728323,0.00055684854],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996366,0.000007992314,0.00007244613,0.0001537372,0.000031704523,0.00009751965],"domain_scores_gemma":[0.9997075,0.000024017238,0.0000112610505,0.00022171052,0.000008034559,0.0000274604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000081877595,0.00004152139,0.000047423346,0.00004205527,0.00004993908,0.000079170604,0.00021489363,0.00001389647,0.0000040102327],"category_scores_gemma":[0.0000059865174,0.00003229144,0.0000066960033,0.00015565449,0.000010870032,0.00018898885,0.00006170248,0.000026828307,0.0000062651898],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.656699e-8,0.000023658376,0.00060840126,4.2015182e-7,6.634651e-7,9.417301e-7,0.0009340147,0.0000016454734,0.00012213683,0.01200594,0.0030162998,0.9832858],"study_design_scores_gemma":[0.0003459805,0.00012157483,0.18788415,0.000045963003,0.0000013865746,0.000027194461,0.00071144593,0.73814094,0.00090624206,0.011325034,0.060169835,0.00032022424],"about_ca_topic_score_codex":0.0000725932,"about_ca_topic_score_gemma":0.000049253853,"teacher_disagreement_score":0.9829656,"about_ca_system_score_codex":0.0000045405372,"about_ca_system_score_gemma":0.0000062906856,"threshold_uncertainty_score":0.13168065},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016726635,0.000016616264,0.9816795,0.000044880973,0.0000926271,0.00026293885,0.0000050928697,0.000046214336,0.0011254853],"genre_scores_gemma":[0.7059064,0.000009423311,0.2939737,0.000030987212,0.000020307125,0.000052207597,0.000003605051,0.0000012436732,0.000002122658],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908066,0.0000072788866,0.00027152404,0.00021425055,0.00025825694,0.0001680097],"domain_scores_gemma":[0.9985483,0.00006150335,0.00011602913,0.00034258896,0.0008544436,0.00007709333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013685216,0.000059806745,0.0000854666,0.00030061477,0.00030855215,0.0002083211,0.00069229724,0.000023490427,2.8843297e-7],"category_scores_gemma":[0.000025707064,0.00005265251,0.00000783594,0.0010379561,0.00032207146,0.0037283236,0.0004954717,0.000051539133,0.0000048832203],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002894468,0.000016255126,0.00031207895,0.00010195074,0.000001683574,9.372984e-8,0.004459517,0.000071520895,0.00009054237,0.54244757,0.00005255636,0.45244336],"study_design_scores_gemma":[0.00007240481,0.00006850059,0.027501423,0.00006304581,0.0000011621264,0.000017690594,0.0005586325,0.9663236,0.0026042056,0.0016321955,0.0010708283,0.00008630084],"about_ca_topic_score_codex":0.000031223477,"about_ca_topic_score_gemma":2.199595e-7,"teacher_disagreement_score":0.9662521,"about_ca_system_score_codex":0.00001869385,"about_ca_system_score_gemma":0.00007826491,"threshold_uncertainty_score":0.27029446},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5613441,0.000185114,0.11974859,0.01244895,0.0014859794,0.00047725003,0.00031158526,0.0001766151,0.30382186],"genre_scores_gemma":[0.9220988,0.00001245111,0.07579423,0.00009244999,0.000082439416,0.000006704272,0.000008949632,0.0000028286775,0.0019011571],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99949247,0.0000034113536,0.00009605941,0.00019564583,0.00011296989,0.000099426834],"domain_scores_gemma":[0.9992654,0.000055098208,0.000057193567,0.0005398369,0.000048568003,0.000033954515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019793048,0.000054201995,0.00005392332,0.000023400758,0.000057952093,0.00015676695,0.002266037,0.00001583506,0.000007742083],"category_scores_gemma":[0.000067826324,0.000034197215,0.000008988945,0.00011608777,0.00005180699,0.0012491149,0.0023565073,0.00004787098,0.000006339179],"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":[0.0000015217322,0.00015509884,0.010583825,0.00000967562,0.000016037799,3.3998624e-8,0.0015228846,1.1323013e-7,0.0016876768,0.8706052,0.023638912,0.09177908],"study_design_scores_gemma":[0.0012482263,0.00018083546,0.26923165,0.00050237624,0.00005346271,0.000061215374,0.0036800285,0.53753775,0.020195916,0.00842165,0.15790802,0.0009788437],"about_ca_topic_score_codex":0.000009510537,"about_ca_topic_score_gemma":0.0000022898528,"teacher_disagreement_score":0.8621835,"about_ca_system_score_codex":0.0000064596393,"about_ca_system_score_gemma":0.000024034758,"threshold_uncertainty_score":0.42108983},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041215595,0.000094682844,0.94329995,0.011346513,0.00049524446,0.00063082867,0.0013989983,0.0002476075,0.0012705612],"genre_scores_gemma":[0.96325296,0.000023362543,0.034969702,0.0007010628,0.00024069601,0.00016683803,0.000562213,0.000023043813,0.00006012656],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961356,0.0003376168,0.00044738845,0.00091032905,0.0013159201,0.0008531625],"domain_scores_gemma":[0.9967143,0.0006310889,0.000060209422,0.0016902123,0.00042285325,0.00048131563],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0033979581,0.0001944628,0.00018812179,0.0003111298,0.0003918465,0.00059067854,0.002471665,0.00009120298,0.00007164688],"category_scores_gemma":[0.00061025185,0.00017846542,0.00004664987,0.0012750779,0.00039856133,0.00051981857,0.0005595878,0.000512497,0.0024313035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024765422,0.0005235113,0.00022445481,0.000014896037,0.00001092152,0.0001414838,0.0011157844,0.00064186036,0.0023316443,0.04638697,0.03704319,0.9115405],"study_design_scores_gemma":[0.00005811261,0.00060001254,0.000028878056,0.00009186089,0.000002851675,0.000011070568,0.0012007634,0.92283046,0.034672167,0.0108893765,0.029265797,0.00034867445],"about_ca_topic_score_codex":0.0010242738,"about_ca_topic_score_gemma":0.0001789538,"teacher_disagreement_score":0.9221886,"about_ca_system_score_codex":0.0001819065,"about_ca_system_score_gemma":0.0006792873,"threshold_uncertainty_score":0.99834543},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031127121,0.00007358086,0.8936186,0.033913244,0.0020734635,0.00036358432,0.019555772,0.000052294643,0.019222358],"genre_scores_gemma":[0.11767175,0.00023460544,0.8744082,0.00096787827,0.005273317,0.0000058989767,0.0009789165,0.0000145799595,0.00044489102],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99756324,0.00007368195,0.00041193637,0.00072823453,0.0008906614,0.0003322436],"domain_scores_gemma":[0.993993,0.0011104584,0.0002689922,0.0042750156,0.00013522788,0.00021729506],"candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.005474205,0.00013378695,0.00022902768,0.0001772536,0.0013119549,0.0013741861,0.011377611,0.000028048551,0.0006736707],"category_scores_gemma":[0.0022249413,0.00006687651,0.00003080604,0.0018908336,0.0014840986,0.001392966,0.0038303395,0.00044139966,0.000043240205],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008257555,0.00013667594,0.00081776635,0.0000025454185,0.00016957345,0.000011271338,0.00038282957,0.000008594852,0.0005312032,0.08287826,0.119661614,0.7953914],"study_design_scores_gemma":[0.00020387035,0.00016852387,0.02143108,0.000025179943,0.00062496425,0.000122025325,0.0016691576,0.62074,0.00008011592,0.0016561202,0.35296363,0.00031533086],"about_ca_topic_score_codex":0.00009097179,"about_ca_topic_score_gemma":0.0001366399,"teacher_disagreement_score":0.7950761,"about_ca_system_score_codex":0.000007496026,"about_ca_system_score_gemma":0.00022332849,"threshold_uncertainty_score":0.9999882},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007404731,0.0001839734,0.9901897,0.0005489181,0.00009197386,0.000782373,0.00012762148,0.00024414208,0.00042656725],"genre_scores_gemma":[0.085150845,0.000019360368,0.9138973,0.00026449433,0.00020101591,0.00021162466,0.00017384102,0.000042526575,0.000039018716],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99787277,0.00003178367,0.0004501012,0.0006130599,0.0004477788,0.00058448524],"domain_scores_gemma":[0.99567825,0.00027608147,0.00035034673,0.0033496637,0.00011146634,0.0002341982],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050775305,0.0003050471,0.00026912006,0.00010444622,0.0006989922,0.0004691733,0.0033206074,0.00006925215,0.000005836405],"category_scores_gemma":[0.000016564814,0.00022613244,0.000047437068,0.0008095216,0.00010152995,0.0010888996,0.0014185486,0.00021040144,0.000033988632],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000044072294,0.0021250134,0.0018860329,0.00024154589,0.0004114785,0.000004538908,0.011592466,0.017685907,0.001754845,0.69949114,0.012979655,0.25182298],"study_design_scores_gemma":[0.00020810998,0.000010471548,0.00017498936,0.0000732933,0.00006959697,0.000085612315,0.00022343732,0.9930758,0.00011434088,0.0015609545,0.0040931082,0.00031029954],"about_ca_topic_score_codex":0.00002013568,"about_ca_topic_score_gemma":0.0000029480884,"teacher_disagreement_score":0.9753899,"about_ca_system_score_codex":0.000090292466,"about_ca_system_score_gemma":0.00011927764,"threshold_uncertainty_score":0.9221413},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032464813,0.00007545909,0.94446635,0.02026837,0.000286302,0.00024320022,0.000027106664,0.00043135017,0.0017370374],"genre_scores_gemma":[0.47567862,0.000020799524,0.5189343,0.0044301767,0.00043572093,0.00012621003,0.000038229908,0.000029416013,0.0003064811],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983338,0.000062146806,0.00038206048,0.00054486265,0.00027300345,0.0004041172],"domain_scores_gemma":[0.9978729,0.0002036635,0.00013112676,0.0015674612,0.000097581426,0.00012728029],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00016220106,0.00021074887,0.00017931394,0.00017212314,0.0005220603,0.0005072649,0.0013643987,0.00006757799,0.0003183651],"category_scores_gemma":[0.00016796232,0.00021191195,0.000077567835,0.000653903,0.00012544073,0.0020287656,0.000453727,0.00019116815,0.0008853036],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025480388,0.00065495685,0.002313134,0.00002598022,0.00015553385,0.00013478879,0.010429923,0.0015137445,0.053110488,0.060536098,0.28411305,0.5870098],"study_design_scores_gemma":[0.0013024649,0.0001173687,0.0010748705,0.0001351538,0.000067685614,0.0002432443,0.001198638,0.8644307,0.010126384,0.00726872,0.112382844,0.0016519199],"about_ca_topic_score_codex":0.000030293228,"about_ca_topic_score_gemma":0.000011648975,"teacher_disagreement_score":0.86291695,"about_ca_system_score_codex":0.000049215683,"about_ca_system_score_gemma":0.000026511487,"threshold_uncertainty_score":0.99989265},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5060909,0.0000029977489,0.49264407,0.0005402529,0.000036778147,0.00007657466,0.0000013202916,0.000056794244,0.00055034837],"genre_scores_gemma":[0.7991061,3.8865326e-7,0.20061709,0.00006608649,0.000016319078,0.000026639304,0.0000027291792,0.0000039138395,0.00016072599],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992967,0.000043384116,0.00013401375,0.0002495906,0.000103362385,0.0001729358],"domain_scores_gemma":[0.99940103,0.000085632,0.000047156638,0.0003838386,0.000025366622,0.000057000223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021342287,0.00007188724,0.000082331484,0.00009320151,0.00011057224,0.0001901158,0.0003485379,0.000036541467,0.000028870494],"category_scores_gemma":[0.00001767973,0.00006669731,0.000018505909,0.00037683538,0.00001684484,0.0009695447,0.00017444052,0.00012091583,0.0001368181],"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":[4.4859814e-7,0.00015239017,0.48286504,0.00000759864,0.0000072847215,0.0000050387657,0.0010583556,0.00007798517,0.0010201777,0.002920965,0.0013482204,0.5105365],"study_design_scores_gemma":[0.00009594743,0.0000073318524,0.28256452,0.00001097274,8.223331e-7,0.000005336391,0.000062192914,0.7162834,0.000076206576,0.00056759844,0.00022305013,0.000102625454],"about_ca_topic_score_codex":0.0027307116,"about_ca_topic_score_gemma":0.00021617637,"teacher_disagreement_score":0.7162054,"about_ca_system_score_codex":0.00003183682,"about_ca_system_score_gemma":0.000034270157,"threshold_uncertainty_score":0.4128037},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07965271,0.000057087047,0.8564917,0.0613567,0.00020689047,0.0002710413,0.00013475947,0.00044927804,0.001379858],"genre_scores_gemma":[0.6903612,0.00020210861,0.25105074,0.05034975,0.00091768993,0.0011929864,0.001130294,0.00010067247,0.0046945564],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981863,0.00006391955,0.00038111059,0.0006405247,0.00031312005,0.0004150621],"domain_scores_gemma":[0.99788076,0.00012932769,0.000081510945,0.0016896973,0.00006922123,0.0001495148],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001337912,0.00023529098,0.00017480752,0.00009736033,0.0003345378,0.00050161773,0.0018365806,0.00007490819,0.00068797823],"category_scores_gemma":[0.000036892397,0.00023057776,0.00007552326,0.00043170984,0.000043155662,0.0014982685,0.0002511895,0.00017510788,0.0014284027],"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":[0.0000010984022,0.00016537678,0.0019095851,0.0000072635676,0.00003179656,0.000015313452,0.0016985992,0.000026242511,0.0019000482,0.00096226955,0.6575571,0.33572534],"study_design_scores_gemma":[0.0017247061,0.0002854518,0.005215254,0.00013986761,0.000067323555,0.000082399645,0.00044498744,0.044501483,0.019164953,0.0046053715,0.9215177,0.0022504856],"about_ca_topic_score_codex":0.00016371098,"about_ca_topic_score_gemma":0.00002027323,"teacher_disagreement_score":0.6107085,"about_ca_system_score_codex":0.000043036194,"about_ca_system_score_gemma":0.000031815052,"threshold_uncertainty_score":0.9993491},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.118319094,0.0020760223,0.8671757,0.0010301459,0.0025421048,0.0010058444,0.00028506797,0.0004453482,0.007120683],"genre_scores_gemma":[0.9816916,9.168997e-7,0.016894007,0.00012614224,0.0003874742,0.00015706627,0.00010412594,0.000016238546,0.00062245264],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99841666,0.00027229873,0.0003213049,0.00035469778,0.0002473121,0.00038770965],"domain_scores_gemma":[0.99801296,0.00080865057,0.00029945266,0.0003862809,0.00028944455,0.00020320583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009756249,0.00018839234,0.00026134483,0.00013172576,0.00028261836,0.00029578194,0.0002716303,0.000107016276,0.000007824348],"category_scores_gemma":[0.0001680623,0.00018212544,0.00005353139,0.00040832104,0.000039938375,0.00057928334,0.00007755412,0.00011761107,0.00014052371],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008188814,0.0026691875,0.52760863,0.0006243034,0.00047105443,0.000018753495,0.035499614,0.00039603646,0.0013815253,0.062279146,0.100292996,0.26867685],"study_design_scores_gemma":[0.0020500747,0.00017136941,0.035489574,0.00039716568,0.00005290051,0.000008468798,0.001000883,0.90021086,0.0044467426,0.000051519564,0.05540738,0.00071304163],"about_ca_topic_score_codex":0.00033174816,"about_ca_topic_score_gemma":0.000066833614,"teacher_disagreement_score":0.89981484,"about_ca_system_score_codex":0.0002524882,"about_ca_system_score_gemma":0.00017003907,"threshold_uncertainty_score":0.742686},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3149021,0.000034772467,0.6794532,0.003467524,0.000025736905,0.00003240065,0.00000914056,0.00015203764,0.0019230983],"genre_scores_gemma":[0.70882505,0.000025841886,0.28958926,0.0013424058,0.000024708464,0.0000016373368,0.000017274673,0.0000015433334,0.00017230421],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996786,0.000009003194,0.00007602366,0.00008876853,0.000053300813,0.000094274816],"domain_scores_gemma":[0.9996009,0.00004028416,0.000017202303,0.0002917037,0.000014703141,0.0000351934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005973943,0.000047683392,0.000052613574,0.000031929238,0.00011140025,0.00013926925,0.00033460886,0.000012808768,0.0000073138563],"category_scores_gemma":[0.0000027154683,0.000042091,0.00000833785,0.00007464436,0.000012370696,0.00023777825,0.00012062777,0.000044882938,0.00000264988],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.6803989e-7,0.000048063666,0.0020189653,0.000002163246,0.000002896943,0.0000014322575,0.00132974,0.000003855797,0.00006520656,0.036416266,0.00071659917,0.95939463],"study_design_scores_gemma":[0.000316274,0.00015318314,0.16385359,0.000083336876,0.000005705273,0.00005746937,0.004459529,0.81401527,0.0001996215,0.0016717516,0.014816823,0.00036744378],"about_ca_topic_score_codex":0.00007931492,"about_ca_topic_score_gemma":0.000058095706,"teacher_disagreement_score":0.9590272,"about_ca_system_score_codex":0.0000034335,"about_ca_system_score_gemma":0.0000060986217,"threshold_uncertainty_score":0.17164212},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003907581,0.000022000117,0.9873999,0.0070913574,0.00006256594,0.00015893494,0.00013912549,0.00016051038,0.00457488],"genre_scores_gemma":[0.033262726,0.0000024354124,0.9647056,0.0013648982,0.000041906,0.000014674965,0.00027786737,0.0000026463554,0.00032727735],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992254,0.0000069748944,0.00013366397,0.0003682389,0.00008938201,0.00017635993],"domain_scores_gemma":[0.99863493,0.00008844077,0.00003639007,0.0011432413,0.000033487988,0.000063515145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002303055,0.00006926635,0.00007789036,0.000027783393,0.00010256549,0.00014588652,0.001438479,0.000022539978,0.000011360331],"category_scores_gemma":[0.00004578606,0.00005963391,0.000016511427,0.00014220309,0.0000194703,0.0003751754,0.00015757882,0.000028869035,0.000013666054],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.853479e-7,0.0000403688,0.000006072867,0.0000018277333,0.000005395579,0.0000016474156,0.000080956765,0.000009242671,0.00028265547,0.18916765,0.05155446,0.75884914],"study_design_scores_gemma":[0.00029168706,0.000078037185,0.00018922698,0.00000970064,0.0000047682493,0.000013329448,0.00006515526,0.905904,0.00027793532,0.0073961634,0.08561606,0.00015395481],"about_ca_topic_score_codex":0.00001552235,"about_ca_topic_score_gemma":0.0000050625,"teacher_disagreement_score":0.90589476,"about_ca_system_score_codex":0.00000964269,"about_ca_system_score_gemma":0.00006152924,"threshold_uncertainty_score":0.26730758},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0353111,0.0001423088,0.9635736,0.00016228168,0.0000879976,0.00031379182,0.000007600539,0.000118200056,0.0002831533],"genre_scores_gemma":[0.66796434,0.000012021904,0.33162215,0.000009689621,0.00008112388,0.00020752529,0.000014140799,0.000025870953,0.000063140185],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891293,0.000008687383,0.00033628408,0.0003543165,0.000098018274,0.00028975992],"domain_scores_gemma":[0.99903864,0.00026336394,0.00002649953,0.00059275044,0.000008766866,0.00006995359],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042156407,0.00013710518,0.00019414454,0.00017152987,0.000017004833,0.0002634715,0.00075728627,0.00006925156,0.0000047159842],"category_scores_gemma":[0.00024027683,0.00013088457,0.000010885813,0.0004250536,0.000013527435,0.0012435516,0.0008394716,0.00020133286,0.000015428526],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021507062,0.0013530962,0.003856168,0.002830649,0.00009538277,0.000047246365,0.011116885,0.12431673,0.009910386,0.30062506,0.0035293582,0.5423169],"study_design_scores_gemma":[0.00022126097,0.000008381857,0.0003397172,0.00035482386,0.0000014694149,0.000008915792,0.000021725991,0.9975625,0.0000313124,0.00091977016,0.00037186642,0.00015820996],"about_ca_topic_score_codex":0.000020926498,"about_ca_topic_score_gemma":0.000006091226,"teacher_disagreement_score":0.87324584,"about_ca_system_score_codex":0.000032662494,"about_ca_system_score_gemma":0.000019734376,"threshold_uncertainty_score":0.53373176},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007653084,0.000018258585,0.99007344,0.00026651824,0.00012283617,0.00006777842,0.0000058021074,0.00006687278,0.0017254306],"genre_scores_gemma":[0.05288191,0.00003389839,0.9462879,0.0007190206,0.00004631813,0.0000028788058,0.000013100331,0.0000015140364,0.000013514425],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889404,0.000012459939,0.0002560598,0.00033300347,0.0003134903,0.00019097442],"domain_scores_gemma":[0.99895984,0.00008060526,0.00009377275,0.0006972983,0.00006317979,0.00010530154],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085898384,0.00007972096,0.00008815291,0.00026498866,0.0003488367,0.0004890437,0.0014993016,0.0000202209,0.0000017636256],"category_scores_gemma":[0.000054184206,0.00007062568,0.0000074279405,0.001090228,0.00006928192,0.012654342,0.00084940786,0.000080906735,0.000019197065],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.030719e-7,0.000008110527,0.00023411677,0.000005247826,5.9980306e-7,9.018799e-7,0.0035476072,0.00076461065,0.000028509387,0.0051007904,0.0015380462,0.9887708],"study_design_scores_gemma":[0.00015483168,0.00002245249,0.005230539,0.000039452643,4.3942816e-7,0.00003832056,0.00003469851,0.98268753,0.00010367349,0.00008316925,0.0115100015,0.000094906616],"about_ca_topic_score_codex":0.000013688308,"about_ca_topic_score_gemma":6.5190574e-7,"teacher_disagreement_score":0.98867583,"about_ca_system_score_codex":0.000018539089,"about_ca_system_score_gemma":0.00029923668,"threshold_uncertainty_score":0.91740924},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43470162,0.0018580881,0.51306576,0.011804661,0.00165667,0.0009276677,0.00055779016,0.0013208492,0.034106895],"genre_scores_gemma":[0.39759445,0.0009353328,0.5795273,0.00067508174,0.00057294714,0.00012838621,0.0003384858,0.000051412997,0.020176597],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99895406,0.000029927396,0.00018350244,0.00052439224,0.00009032308,0.00021779932],"domain_scores_gemma":[0.99674237,0.00016323906,0.000028360306,0.0030039912,0.000012007572,0.000050060007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018545311,0.000097245866,0.00011764176,0.000061995685,0.00006903027,0.00019881573,0.0039517465,0.000036345118,0.000069877395],"category_scores_gemma":[0.000073422845,0.00008785834,0.000019251476,0.00045172023,0.000028748598,0.0015173933,0.0010747908,0.0001110289,0.00045289777],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013658276,0.000096135685,0.0005452315,0.000002829607,0.0000032679775,0.0000040844593,0.00015028863,0.000004802955,0.000021074446,0.00093237875,0.012524241,0.9857143],"study_design_scores_gemma":[0.00038841012,0.00005029528,0.008430415,0.0000550423,0.0000055415553,0.00001345269,0.000028612194,0.1085044,0.00012344396,0.0050352463,0.87699777,0.00036735606],"about_ca_topic_score_codex":0.00021678487,"about_ca_topic_score_gemma":0.00034793178,"teacher_disagreement_score":0.9853469,"about_ca_system_score_codex":0.000020338215,"about_ca_system_score_gemma":0.00006811039,"threshold_uncertainty_score":0.7343394},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003596159,0.000017886507,0.9711591,0.000944138,0.00007966962,0.000029894794,0.0000045071724,0.00019271763,0.02721249],"genre_scores_gemma":[0.061994687,0.0000016519471,0.93700933,0.00040035136,0.000080598584,6.483858e-7,0.00003349364,0.0000039836095,0.00047526107],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993284,0.000004344561,0.00011334436,0.0002835287,0.00010532498,0.00016509322],"domain_scores_gemma":[0.99855506,0.00006967256,0.000026756681,0.0012627504,0.00001653834,0.00006924072],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047668704,0.000046177025,0.00004423049,0.000030096702,0.00011910434,0.000169809,0.0015785736,0.000015289397,0.000014657516],"category_scores_gemma":[0.00003384468,0.00004004705,0.000008344291,0.00022394917,0.000014617587,0.0005087659,0.00068261276,0.00004742685,0.00008050973],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.2440052e-7,0.000015845675,0.0000735961,9.004484e-7,0.0000020554585,0.0000034695495,0.00006418243,6.594563e-7,0.00035468378,0.05225283,0.0068750596,0.9403565],"study_design_scores_gemma":[0.00018729511,0.000014362545,0.006385021,0.000013824022,0.00000388651,0.000018806904,0.000101103586,0.7079058,0.0019260277,0.0025244222,0.28069487,0.00022454376],"about_ca_topic_score_codex":0.00003266996,"about_ca_topic_score_gemma":0.000008783695,"teacher_disagreement_score":0.94013196,"about_ca_system_score_codex":0.0000074003874,"about_ca_system_score_gemma":0.000018586386,"threshold_uncertainty_score":0.29334086},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13987073,0.00010979008,0.8596365,0.00006453551,0.00017291974,0.000045302186,0.0000014297531,0.000029570747,0.00006924232],"genre_scores_gemma":[0.38852698,0.0000023241373,0.6112799,0.000024772928,0.00016031269,2.188739e-7,6.322012e-7,0.0000032414466,0.0000015972249],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875224,0.0000036847432,0.00033084842,0.00024842608,0.00034745285,0.0003173474],"domain_scores_gemma":[0.9989301,0.00024218907,0.00022195933,0.00027099845,0.00020928058,0.00012546396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0057891808,0.00008184959,0.00013758507,0.00033276874,0.00029320538,0.0003803286,0.0014962347,0.00002217513,7.326821e-8],"category_scores_gemma":[0.0004420934,0.00007183111,0.000016117909,0.00096519536,0.00004935499,0.0011236413,0.00039899308,0.00013346063,1.2000095e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000041615126,0.00007692638,0.0010216984,0.000105591855,0.000036643658,0.00000875248,0.0037053996,0.011971539,0.034145527,0.004870687,0.00048578595,0.9435673],"study_design_scores_gemma":[0.00012835891,0.00005499519,0.002661124,0.000054546446,0.0000053982485,0.00019576923,0.00019988613,0.9947516,0.0005846323,0.000017122908,0.0012521725,0.000094404495],"about_ca_topic_score_codex":0.000002218735,"about_ca_topic_score_gemma":3.1276744e-7,"teacher_disagreement_score":0.98278004,"about_ca_system_score_codex":0.000029901088,"about_ca_system_score_gemma":0.00012726453,"threshold_uncertainty_score":0.36675173},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003174739,0.00006901939,0.95199597,0.0075319475,0.034595285,0.00017493362,0.000013105956,0.0021964977,0.00024849403],"genre_scores_gemma":[0.001644549,0.0000048523566,0.611892,0.0004076793,0.38538793,0.000028720007,0.000038026432,0.000027353368,0.00056893006],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99833965,0.00001428651,0.0003203386,0.0005899723,0.00036691973,0.00036881768],"domain_scores_gemma":[0.9987952,0.00020078591,0.000068567686,0.00068537996,0.00007302989,0.00017704596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015090748,0.00023093399,0.00021119406,0.000111361005,0.00022201205,0.00027096068,0.0006512321,0.00010468785,0.000029201565],"category_scores_gemma":[0.0007870589,0.00022875289,0.00007153706,0.00062613894,0.000021170998,0.00045099345,0.00012061492,0.00026610764,0.00011734478],"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":[0.000003856412,0.00009959805,0.0010055848,0.000010190056,0.000014576052,0.000030034531,0.00047291507,0.0018775125,0.000027660364,0.0004423961,0.89495623,0.101059444],"study_design_scores_gemma":[0.000111467765,0.00016345698,0.0064461804,0.000030489537,0.000005881554,0.000030268146,0.000009546988,0.0029027294,0.00069105433,0.00006105864,0.9892403,0.0003075947],"about_ca_topic_score_codex":0.0000029894873,"about_ca_topic_score_gemma":2.3839135e-7,"teacher_disagreement_score":0.35079265,"about_ca_system_score_codex":0.000097583325,"about_ca_system_score_gemma":0.000035061992,"threshold_uncertainty_score":0.9328272},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004597755,0.000027139617,0.9815297,0.0033944605,0.000049126476,0.00007446397,0.000021246711,0.0001787968,0.010127274],"genre_scores_gemma":[0.017496297,0.0000044264193,0.98165494,0.00038639936,0.00003205031,0.000009771174,0.000038663904,0.0000035773148,0.00037384746],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99938744,0.0000041594644,0.00010513096,0.00033706124,0.00003911343,0.00012710881],"domain_scores_gemma":[0.99872065,0.000018494027,0.000027839658,0.0011796388,0.000009753292,0.000043629476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001691018,0.000050739138,0.000051705825,0.000027309787,0.00006825973,0.0001638019,0.001765176,0.000014314469,0.000011613016],"category_scores_gemma":[0.000005786747,0.00004598689,0.000008882622,0.00011244966,0.000015014641,0.0006132266,0.00074140757,0.00003144534,0.00029102966],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.181543e-7,0.00011886406,0.000099343786,0.0000069120683,0.00001927907,0.000005696823,0.0005747805,0.00010422333,0.0012118501,0.29048008,0.027733823,0.67964447],"study_design_scores_gemma":[0.0019762965,0.00013097125,0.0025601962,0.00007560891,0.000017800525,0.00023336077,0.00029735334,0.32184118,0.0061084693,0.032949425,0.6327393,0.0010700332],"about_ca_topic_score_codex":0.00008649392,"about_ca_topic_score_gemma":0.000024744297,"teacher_disagreement_score":0.6785744,"about_ca_system_score_codex":0.000016004851,"about_ca_system_score_gemma":0.00006776637,"threshold_uncertainty_score":0.37406945},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026426317,0.00006304311,0.96496266,0.00041538995,0.0002635219,0.000116539304,0.000051064322,0.00017362482,0.0075278445],"genre_scores_gemma":[0.36504504,0.00005402299,0.6339647,0.00065609766,0.000045879202,0.000047938993,0.00008008024,0.00000362618,0.00010259554],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866796,0.00009283007,0.00030356963,0.00022658193,0.000457655,0.00025140258],"domain_scores_gemma":[0.99920225,0.00009959064,0.00023029922,0.0002650615,0.00012180389,0.00008099181],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001386247,0.0001187113,0.00011529593,0.00016947756,0.00070818316,0.00087037386,0.00077766663,0.000028823519,0.000027847804],"category_scores_gemma":[0.00017488936,0.00009529002,0.000033494118,0.0006217095,0.0001649161,0.0056391354,0.00014530458,0.00014579787,0.00024233531],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.447427e-7,0.000032644504,0.0027391205,0.0000059328313,0.000008627049,7.010022e-7,0.0019280398,0.00045395925,0.000037730693,0.113735296,0.0008059521,0.8802515],"study_design_scores_gemma":[0.00021392525,0.00007814147,0.0022435852,0.000011074323,0.0000033847955,0.000036040376,0.0006635471,0.83310765,0.006986105,0.009786139,0.14655451,0.0003158975],"about_ca_topic_score_codex":0.00014845675,"about_ca_topic_score_gemma":0.0000030437313,"teacher_disagreement_score":0.8799357,"about_ca_system_score_codex":0.00002702898,"about_ca_system_score_gemma":0.00011920695,"threshold_uncertainty_score":0.8393035},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05546614,0.000075933836,0.9351161,0.007359612,0.0003101541,0.00027854706,0.0006934431,0.00040792112,0.00029211844],"genre_scores_gemma":[0.2787158,0.000024507162,0.67090595,0.022585563,0.00051635795,0.00021690414,0.026974836,0.000033643657,0.00002642223],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99832207,0.000025712714,0.000529285,0.00033838855,0.00038942913,0.00039511558],"domain_scores_gemma":[0.99820054,0.000096236225,0.0003890876,0.0010776774,0.000107696294,0.00012877633],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00021308007,0.00019658095,0.00016077209,0.00007555139,0.0003407216,0.0016833323,0.0017173729,0.00006829967,0.000046931807],"category_scores_gemma":[0.000062837826,0.00018486867,0.000027763364,0.0004540899,0.000048713704,0.010048699,0.000578495,0.00016302237,0.00021031885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012176812,0.000022102704,0.001043113,0.000022841867,0.000022087765,0.0000010520516,0.001201973,0.00077687454,0.000118284624,0.00013123515,0.26329875,0.73336047],"study_design_scores_gemma":[0.00032913516,0.000008693269,0.012832004,0.00013810044,0.0000136460785,0.0000052206647,0.00014779794,0.90380555,0.00008131885,0.00025189752,0.08206351,0.00032312542],"about_ca_topic_score_codex":0.0004447568,"about_ca_topic_score_gemma":0.000008349013,"teacher_disagreement_score":0.90302867,"about_ca_system_score_codex":0.00007150385,"about_ca_system_score_gemma":0.000075916076,"threshold_uncertainty_score":0.999353},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017680584,0.14730968,0.76388806,0.00140081,0.003500306,0.0018483542,0.0049188975,0.0008444527,0.058608837],"genre_scores_gemma":[0.043811835,0.015923658,0.9242844,0.00042608846,0.0011189934,0.00027048547,0.009617159,0.00011777852,0.0044295783],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.996368,0.00020375423,0.00082714274,0.0019087724,0.00017627963,0.00051603274],"domain_scores_gemma":[0.99190104,0.00021100625,0.0003132478,0.0072959904,0.000049701262,0.00022901305],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0019085425,0.0004201336,0.0006201417,0.00016136144,0.00050061033,0.0005521415,0.007952281,0.000095519244,0.000030999305],"category_scores_gemma":[0.00019642623,0.00034381897,0.00006931986,0.0005886029,0.00021862265,0.0060684895,0.029120442,0.0002111112,0.00016463285],"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":[0.000009015727,0.00023996325,0.00047048106,0.00014361611,0.0000482912,0.000024279201,0.0069999653,7.4100406e-8,0.000024662117,0.0013058387,0.16632254,0.8244113],"study_design_scores_gemma":[0.00095790054,0.00046272803,0.0018255471,0.0053468747,0.0003007074,0.00049928157,0.005342634,0.28315327,0.00006195145,0.0012048528,0.6987407,0.0021035357],"about_ca_topic_score_codex":0.0000252897,"about_ca_topic_score_gemma":0.00010563793,"teacher_disagreement_score":0.8223077,"about_ca_system_score_codex":0.000029016572,"about_ca_system_score_gemma":0.00015536799,"threshold_uncertainty_score":0.99990135},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023588825,0.00005803823,0.9721396,0.0006055839,0.00012558521,0.00025016212,0.0000056688764,0.0001594024,0.0030671647],"genre_scores_gemma":[0.43972543,0.00020094511,0.5595246,0.00039161323,0.00004313244,0.00005650383,0.00002783641,0.0000025227641,0.000027437023],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991733,0.000016949107,0.0002304178,0.00024411235,0.00016896028,0.00016627413],"domain_scores_gemma":[0.99927056,0.0000566771,0.00008241007,0.0004248828,0.000090482055,0.00007497852],"candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.00069470255,0.00006992646,0.00007885056,0.00021857853,0.00020891614,0.0014245013,0.0009720285,0.000022129703,0.0000013226029],"category_scores_gemma":[0.000025968491,0.000060378603,0.0000030857018,0.00052958174,0.00010830745,0.017553087,0.0012870145,0.00009029934,0.000012777766],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.2523901e-7,0.000004106033,0.00068261276,0.000010675494,5.528031e-7,9.7539846e-8,0.0008852007,0.00001960569,0.000013510209,0.006738482,0.00082690537,0.99081814],"study_design_scores_gemma":[0.00007122953,0.000026028802,0.0102934055,0.000036815916,3.8315093e-7,0.000022724736,0.00013269777,0.9576572,0.000024802795,0.00006778004,0.031577613,0.00008930336],"about_ca_topic_score_codex":0.00006171166,"about_ca_topic_score_gemma":6.561324e-7,"teacher_disagreement_score":0.9907288,"about_ca_system_score_codex":0.000013249486,"about_ca_system_score_gemma":0.000048269536,"threshold_uncertainty_score":0.9996121},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37368438,0.0000019703593,0.62496823,0.000059853668,0.00054775213,0.000062486935,0.000002881276,0.00003704103,0.0006354072],"genre_scores_gemma":[0.81490266,0.0000063052144,0.18490992,0.00012598919,0.00004309796,0.0000073001406,0.0000015333329,5.750802e-7,0.0000026396467],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991354,0.0000081717,0.0003674034,0.00015114035,0.00023061817,0.00010731477],"domain_scores_gemma":[0.9991725,0.000044215478,0.00016279506,0.00032402776,0.00020736626,0.00008906758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093434926,0.00005077628,0.00008522888,0.00014446891,0.00017968385,0.00028095354,0.0006831215,0.000031438514,0.000002195147],"category_scores_gemma":[0.000046249486,0.00004221783,0.000021399612,0.000568322,0.00037625848,0.0073670824,0.0002496093,0.00010972458,0.000015982394],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.4786916e-7,0.000013263947,0.0018285816,0.0000026188256,5.7406044e-7,8.370292e-8,0.00020656885,0.000002458556,0.0019163035,0.02299113,0.000020241934,0.9730178],"study_design_scores_gemma":[0.00016254574,0.000106891115,0.40782434,0.0000050579984,0.000002655048,0.00003758299,0.000018091827,0.57211894,0.006864779,0.00021977157,0.012529763,0.000109581786],"about_ca_topic_score_codex":0.000017951234,"about_ca_topic_score_gemma":0.0000021460626,"teacher_disagreement_score":0.97290826,"about_ca_system_score_codex":0.0000030954043,"about_ca_system_score_gemma":0.000099736324,"threshold_uncertainty_score":0.5340957},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44481474,0.00015418655,0.5325711,0.011775118,0.00031641207,0.00041276278,0.000037052054,0.0002540759,0.00966457],"genre_scores_gemma":[0.20439014,0.000009878538,0.79464626,0.00025587052,0.00004827534,0.000012696849,0.000025062696,0.0000028086577,0.00060899183],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99955326,0.000006084771,0.000077393146,0.00022348498,0.000050873114,0.00008889546],"domain_scores_gemma":[0.9992846,0.000021316298,0.000015539812,0.00063816225,0.0000075283724,0.000032853848],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005500312,0.000040970943,0.000048070346,0.000028927363,0.0000306993,0.0001622582,0.00070354453,0.000017290004,0.00001788469],"category_scores_gemma":[0.0000130828375,0.00003207396,0.0000028072525,0.00009991167,0.000018775021,0.00056059106,0.00054815394,0.00003364114,0.000009896053],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.7039245e-8,0.000008067366,0.004820269,0.0000023910834,0.0000018351427,9.829712e-7,0.00031202144,0.0000010687388,0.00009949154,0.016895896,0.008664442,0.96919346],"study_design_scores_gemma":[0.00023431124,0.000017358401,0.24511723,0.000012302773,0.0000015870288,0.000015278118,0.00016115529,0.7135066,0.00014298644,0.0057202266,0.03488791,0.0001830504],"about_ca_topic_score_codex":0.00023273975,"about_ca_topic_score_gemma":0.000056999277,"teacher_disagreement_score":0.9690104,"about_ca_system_score_codex":0.000003618364,"about_ca_system_score_gemma":0.000008857492,"threshold_uncertainty_score":0.15646596},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017372305,0.00008574947,0.99512666,0.00036269182,0.000023959561,0.0002161999,0.000019599463,0.0001794314,0.0022484642],"genre_scores_gemma":[0.14687268,0.0000095206615,0.8521985,0.00013228679,0.00004294341,0.0001239822,0.00009879709,0.000010402617,0.00051090115],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875814,0.000017939521,0.00018024365,0.00060395873,0.0002030507,0.00023669399],"domain_scores_gemma":[0.9986977,0.00006490235,0.000048598482,0.0011060904,0.00001271332,0.00006999154],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032974005,0.00010614588,0.00010598552,0.000051739276,0.0002399582,0.00022227789,0.0016479732,0.000029925928,0.000025102336],"category_scores_gemma":[0.000018805205,0.00009818166,0.00002869053,0.00012696935,0.00001480166,0.0003801446,0.00057862827,0.00007970086,0.000039922375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026058663,0.0009674853,0.00043663217,0.00003958121,0.000060613653,0.0000025047382,0.0017454235,0.26118603,0.00040982146,0.009742612,0.009735745,0.71567094],"study_design_scores_gemma":[0.0003693145,0.000030178522,0.000012680568,0.000005198918,0.0000076746865,0.000001744024,0.00011145255,0.97564286,0.000009655156,0.000017758486,0.023659512,0.00013198887],"about_ca_topic_score_codex":0.000006201576,"about_ca_topic_score_gemma":4.4616738e-7,"teacher_disagreement_score":0.715539,"about_ca_system_score_codex":0.000018637167,"about_ca_system_score_gemma":0.000012705941,"threshold_uncertainty_score":0.4003732},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0070919218,0.00010057548,0.9902507,0.001533042,0.00026468703,0.00016724502,0.00020283878,0.000013913635,0.00037509878],"genre_scores_gemma":[0.0112876585,0.000024919233,0.98807585,0.00013026115,0.00018061469,0.000013739008,0.00015960146,0.0000060742973,0.000121300625],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987951,0.000025253446,0.00041448517,0.00022948107,0.00034342278,0.0001922366],"domain_scores_gemma":[0.99854,0.00019322884,0.00041365146,0.0007552861,0.00006128294,0.000036582624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015557735,0.00007518072,0.00013104042,0.00018265093,0.00006468289,0.0001612673,0.0010790324,0.000024132352,0.00000355546],"category_scores_gemma":[0.00010523348,0.00006979881,0.000032727625,0.00035404236,0.000006083902,0.00044327218,0.0006556073,0.00010288913,0.000006623441],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000308001,0.0010158805,0.002099405,0.00017317622,0.00018592572,0.00019385981,0.00028203893,0.0048070326,0.00016595001,0.5119956,0.21548496,0.26356533],"study_design_scores_gemma":[0.0019792959,0.000101377016,0.011063413,0.0005521879,0.00011031664,0.000023234506,0.0003744716,0.73785514,0.00017373731,0.010796464,0.23659624,0.00037413955],"about_ca_topic_score_codex":0.000020610063,"about_ca_topic_score_gemma":0.000007380497,"teacher_disagreement_score":0.7330481,"about_ca_system_score_codex":0.00011922275,"about_ca_system_score_gemma":0.000024879893,"threshold_uncertainty_score":0.28463125},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11948749,0.0003784098,0.8750373,0.0041913614,0.0004803753,0.00003377598,0.00009761994,0.00003907957,0.00025457452],"genre_scores_gemma":[0.5607445,0.00004122365,0.43826652,0.00046616173,0.00041189865,0.0000010114153,0.00004122799,0.000007006657,0.000020416368],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99870425,0.000029772484,0.00042048804,0.00026460714,0.00042845393,0.00015240458],"domain_scores_gemma":[0.99873376,0.00014980305,0.00035628284,0.00042797546,0.00023350347,0.000098671],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005136557,0.00010989095,0.00014136179,0.00019057977,0.00009517387,0.00040980396,0.0020480843,0.00003453549,0.0000119505185],"category_scores_gemma":[0.00008929371,0.00009812839,0.000031168536,0.00009837413,0.00003747204,0.0015856939,0.00051680784,0.00013140845,0.0000044709795],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037239668,0.000051626044,0.0009972539,0.0000027122335,0.000041640542,0.000024553825,0.00058461406,0.00019824039,0.0001454486,0.00009331469,0.0021956132,0.99566126],"study_design_scores_gemma":[0.0015424658,0.00014953493,0.0026134597,0.0006835218,0.000043806784,0.0006620946,0.00042037907,0.82935995,0.00077486393,0.00011776972,0.16325334,0.00037880024],"about_ca_topic_score_codex":0.000028198201,"about_ca_topic_score_gemma":0.000014913032,"teacher_disagreement_score":0.9952825,"about_ca_system_score_codex":0.00004607409,"about_ca_system_score_gemma":0.0001445982,"threshold_uncertainty_score":0.40015596},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.110045955,0.019654782,0.80810404,0.023858896,0.0030236337,0.0070975297,0.0015887736,0.002904227,0.023722187],"genre_scores_gemma":[0.8910903,0.0004265549,0.091304466,0.0031350683,0.0009311554,0.00029059514,0.00013761478,0.00009395149,0.012590337],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953084,0.00006956999,0.0011875477,0.0011036505,0.0008323833,0.001498464],"domain_scores_gemma":[0.9961524,0.00021962442,0.0005161261,0.0018324321,0.000414766,0.0008646708],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00062068756,0.0007277296,0.0006266254,0.00027314547,0.0007706893,0.0023381785,0.0027965608,0.00042996407,0.00016945173],"category_scores_gemma":[0.0003358513,0.0007132042,0.00027324312,0.0011024162,0.00024191053,0.0018593626,0.0005582152,0.00070746854,0.0015290761],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011313528,0.003731184,0.0051252297,0.0009017484,0.00064597646,0.00026849526,0.042255837,0.00026758795,0.0054252776,0.035722215,0.10587328,0.79967004],"study_design_scores_gemma":[0.006857962,0.0022768348,0.03683705,0.0026915625,0.000688423,0.0006799421,0.007253774,0.59471697,0.031636193,0.0039210613,0.30674985,0.005690373],"about_ca_topic_score_codex":0.00006164087,"about_ca_topic_score_gemma":0.00000524847,"teacher_disagreement_score":0.79397964,"about_ca_system_score_codex":0.00032341594,"about_ca_system_score_gemma":0.0005631121,"threshold_uncertainty_score":0.9995319},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.775223,0.0004504337,0.22367492,0.00014063076,0.00022374642,0.000032659664,0.000090458234,0.000010020136,0.00015409212],"genre_scores_gemma":[0.8651454,0.00012519679,0.13454902,0.000007627864,0.00011538367,8.288611e-7,0.000044338125,0.000005268759,0.000006960558],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99900234,0.000060180853,0.00039135292,0.00017947094,0.00027124243,0.00009541069],"domain_scores_gemma":[0.9987956,0.00044791918,0.00028661126,0.00025078276,0.00017320452,0.000045841785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006330763,0.000075736,0.00017927082,0.00025893547,0.00007182961,0.0000588835,0.0010089444,0.000034704062,9.0089316e-7],"category_scores_gemma":[0.00010595615,0.000070250004,0.000026216543,0.00013327865,0.00006411576,0.0010813787,0.00041465103,0.00012527224,8.6904925e-7],"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":[0.00003787706,0.00019237073,0.18943909,0.00005178293,0.00027337304,0.00020594975,0.0039465236,0.0015244709,0.0026729256,0.0027636033,0.00032747549,0.79856455],"study_design_scores_gemma":[0.0037229334,0.00023313929,0.87488043,0.0032048258,0.000097220574,0.0023755434,0.0009155516,0.100298174,0.0033008454,0.0031135338,0.0071818684,0.0006759494],"about_ca_topic_score_codex":0.000074569514,"about_ca_topic_score_gemma":0.000004389824,"teacher_disagreement_score":0.79788864,"about_ca_system_score_codex":0.000030198786,"about_ca_system_score_gemma":0.00010633177,"threshold_uncertainty_score":0.2864712},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.114855334,0.000043704917,0.8828668,0.0011259699,0.00007059825,0.000136733,0.000009553297,0.00010014705,0.0007911433],"genre_scores_gemma":[0.22270212,0.0000075487933,0.7766988,0.00038956932,0.00005540167,0.00000977246,0.0000064051674,0.0000029021826,0.00012746555],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99936754,0.000012177532,0.00012972347,0.0002651302,0.000059282578,0.00016612989],"domain_scores_gemma":[0.9995918,0.000060075803,0.000039863713,0.00023821609,0.000020475303,0.000049566337],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017740157,0.00006825747,0.00008906388,0.00005124604,0.00016703199,0.00014287943,0.00019840497,0.00003766343,0.0000032277842],"category_scores_gemma":[0.000012051044,0.00006219981,0.000018136609,0.00012864624,0.000021672307,0.00039571087,0.000051295876,0.000028492803,0.0000016034929],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006825613,0.0001485701,0.0007113397,0.000023159697,0.000023682647,0.000008877712,0.0022171317,0.000042713327,0.05735713,0.113574885,0.005076789,0.8208089],"study_design_scores_gemma":[0.00028689462,0.00010465341,0.0015847507,0.000012473537,0.0000073483293,0.00004912324,0.000097162934,0.98676693,0.00021774268,0.0031420891,0.0076377993,0.000093043906],"about_ca_topic_score_codex":0.000008670684,"about_ca_topic_score_gemma":0.000010396346,"teacher_disagreement_score":0.9867242,"about_ca_system_score_codex":0.000012105342,"about_ca_system_score_gemma":0.000023378905,"threshold_uncertainty_score":0.25364345},"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":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88357264,0.00012677115,0.115078546,0.0006027703,0.00006563999,0.00032363654,0.00009206344,0.000028273977,0.00010966468],"genre_scores_gemma":[0.18412913,0.000016346707,0.81566006,0.000019456882,0.000042080996,0.000092394446,0.000020653122,0.000013834142,0.000006032359],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983983,2.6116574e-8,0.00072354445,0.00034175406,0.00032348334,0.00021286691],"domain_scores_gemma":[0.998253,0.00025169295,0.00047961494,0.000084242245,0.0008737359,0.000057716887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008661589,0.00017278294,0.00043433852,0.00024335514,0.000046135312,0.00005561505,0.000992418,0.000068909634,0.0000016469255],"category_scores_gemma":[0.00043229767,0.00015403183,0.00047505743,0.0009073417,0.00014418075,0.0006988621,0.00019798815,0.000100075486,7.83385e-8],"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":[0.000016943464,0.0001845442,0.00008281881,0.00015524385,0.00039318355,1.2416078e-8,0.00049693097,0.00095289684,0.5192831,0.47518837,0.00006745143,0.0031784764],"study_design_scores_gemma":[0.00068808574,0.0001718967,0.00089395425,0.00017179709,0.00020881064,0.000002351197,0.0009443866,0.38338703,0.60983247,0.0033853254,0.0001505763,0.00016332034],"about_ca_topic_score_codex":0.00004121462,"about_ca_topic_score_gemma":1.5045633e-7,"teacher_disagreement_score":0.70058155,"about_ca_system_score_codex":0.00010194667,"about_ca_system_score_gemma":0.000043360258,"threshold_uncertainty_score":0.62812364},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7876935,0.0008398109,0.18836561,0.01246155,0.0018182254,0.0033662606,0.00021854501,0.00060893677,0.0046275347],"genre_scores_gemma":[0.9329337,0.00009321036,0.06498047,0.00009990918,0.00016320363,0.00032919573,0.000011567745,0.000018684994,0.0013700759],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99891824,0.000006334805,0.00024696894,0.00028128084,0.00022494348,0.00032222198],"domain_scores_gemma":[0.9990567,0.00007127695,0.00029692787,0.0003005978,0.00019821983,0.000076308424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062210683,0.00012341753,0.00013127761,0.00007071628,0.00023877677,0.000095141484,0.00097094104,0.000036373902,0.0000037097977],"category_scores_gemma":[0.000042344993,0.000094084855,0.000087004024,0.00028709412,0.00006796048,0.0006674593,0.00027032127,0.00007253347,0.000019318],"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":[0.000012922139,0.00041721473,0.0021344253,0.00011582593,0.000091724665,5.4653196e-8,0.0018796637,0.000008658285,0.34711704,0.55318564,0.048699833,0.046337],"study_design_scores_gemma":[0.001516584,0.0001499862,0.07202521,0.00032760913,0.00020200337,0.000037022048,0.001259285,0.034459542,0.79720616,0.04403552,0.047816083,0.0009650009],"about_ca_topic_score_codex":0.000018345174,"about_ca_topic_score_gemma":6.2982417e-7,"teacher_disagreement_score":0.50915015,"about_ca_system_score_codex":0.000077047065,"about_ca_system_score_gemma":0.000021820086,"threshold_uncertainty_score":0.3836669},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38449404,0.000017606337,0.6146268,0.00022508162,0.0004163818,0.00010267169,0.000005834775,0.00003688957,0.00007466108],"genre_scores_gemma":[0.6488993,0.000001139285,0.35098314,0.000061584265,0.000044094675,0.0000040579635,0.000002353416,0.0000031484976,0.0000011554934],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99748707,0.000021411106,0.0014793387,0.00012772813,0.0007264778,0.00015797034],"domain_scores_gemma":[0.99591845,0.0005382297,0.0014098923,0.00031331542,0.0017685831,0.00005150758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021062393,0.00011169075,0.00026038144,0.0015182669,0.00009464468,0.0001740957,0.0022729158,0.00010714476,0.0000046826663],"category_scores_gemma":[0.001294976,0.00009668667,0.00007817645,0.0005299681,0.000061053266,0.001849754,0.00030524805,0.00020521013,0.000003597211],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008461743,0.00028466585,0.034432422,0.00000251435,0.00005070243,0.0000047637022,0.0018852194,0.00024089805,0.0002525113,0.0032737514,0.0005153778,0.9589726],"study_design_scores_gemma":[0.008218654,0.0056802724,0.16626164,0.0012257149,0.00011880677,0.0012378857,0.03858743,0.6710799,0.01398659,0.037354637,0.05525647,0.0009920383],"about_ca_topic_score_codex":0.0000010118895,"about_ca_topic_score_gemma":0.000008417823,"teacher_disagreement_score":0.9579805,"about_ca_system_score_codex":0.00007574129,"about_ca_system_score_gemma":0.000104190534,"threshold_uncertainty_score":0.42236808},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004228424,0.0000265386,0.985132,0.0011026295,0.00014998349,0.00008185801,0.000026044863,0.00020020847,0.009052344],"genre_scores_gemma":[0.24153204,0.0000010760808,0.7574894,0.00059710024,0.00008173473,0.000027836568,0.00006336758,0.0000040601826,0.00020341332],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99941593,0.000010335503,0.00009585617,0.00015093085,0.00010281877,0.00022409722],"domain_scores_gemma":[0.99924743,0.00006527456,0.000015193222,0.00053608627,0.000013442592,0.00012254223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001710219,0.00005231711,0.000049142538,0.000019104258,0.00006733525,0.00008244913,0.00051538605,0.000016150208,0.000039718318],"category_scores_gemma":[0.00005751876,0.00004240978,0.000011845739,0.00015658242,0.00001944481,0.0005701474,0.0002438132,0.000033276072,0.00033521673],"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":[4.6060728e-7,0.00018417972,0.00073801464,0.0000062551826,0.00000734416,0.0000011405702,0.0003540934,0.0000033754666,0.00020884002,0.7308866,0.073145725,0.19446398],"study_design_scores_gemma":[0.00032009286,0.00006811869,0.020454181,0.000019942148,0.000018443698,0.00006506346,0.00007370368,0.29385263,0.001305161,0.0032154692,0.68007356,0.0005336531],"about_ca_topic_score_codex":0.000008843467,"about_ca_topic_score_gemma":0.0000013706452,"teacher_disagreement_score":0.72767115,"about_ca_system_score_codex":0.000012013428,"about_ca_system_score_gemma":0.000016980473,"threshold_uncertainty_score":0.43086445},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09851932,0.00001698491,0.88297206,0.0005343046,0.0001741418,0.00012391448,0.00014181566,0.000044331882,0.017473143],"genre_scores_gemma":[0.90137494,0.000003024596,0.09841989,0.000066132816,0.000010021036,0.000007644223,0.00010000849,6.038818e-7,0.000017717888],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988796,0.000021783007,0.00042939474,0.00011524636,0.00044461494,0.00010933646],"domain_scores_gemma":[0.99926716,0.000076886055,0.00026707439,0.00022072585,0.00012878579,0.00003937624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078906567,0.000059689635,0.00014063947,0.00049945316,0.00008443646,0.00009865855,0.00081722863,0.000023561995,0.000034934834],"category_scores_gemma":[0.000033137665,0.000050578252,0.00008862687,0.0019761221,0.00024188602,0.0031344392,0.00014012464,0.000036906877,0.00001157608],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010995721,0.0005497945,0.014419555,0.00014132579,0.0012328959,2.8137384e-7,0.031238794,0.1340852,0.00019327756,0.20221984,0.014431577,0.6013775],"study_design_scores_gemma":[0.0002333696,0.000039545415,0.002567315,0.0000044131193,0.000028839908,8.749511e-7,0.0009413452,0.9914207,0.00012283592,0.000017005597,0.0045621893,0.00006158678],"about_ca_topic_score_codex":0.0000765214,"about_ca_topic_score_gemma":0.0000082302795,"teacher_disagreement_score":0.8573355,"about_ca_system_score_codex":0.000017731021,"about_ca_system_score_gemma":0.00008276773,"threshold_uncertainty_score":0.22723928},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12476537,0.00022026927,0.87372386,0.00081015675,0.000049713915,0.0002978957,0.000052531628,0.000039098963,0.000041076026],"genre_scores_gemma":[0.25619358,0.00011117995,0.7433957,0.000121266654,0.00011908898,0.000025212827,0.000010596403,0.00001077575,0.000012619976],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985803,0.000018617158,0.000584206,0.0003565886,0.00017301159,0.00028731517],"domain_scores_gemma":[0.9983253,0.00070861407,0.0002664497,0.00031658882,0.00025627302,0.00012680456],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049823936,0.00016686237,0.0003070215,0.00008243743,0.00024478784,0.00038511798,0.00045041644,0.000090926565,0.0000037971706],"category_scores_gemma":[0.000085108404,0.0001532937,0.00004780552,0.00020183604,0.00016515896,0.0003176595,0.00027653752,0.00011280961,0.0000064435176],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.6492316e-7,0.00007465586,0.00003867721,0.0000773248,0.000020380263,4.3602742e-7,0.0011394573,0.000010935352,0.0006867506,0.047981877,0.00024937434,0.94971985],"study_design_scores_gemma":[0.000025291296,0.00012780527,0.000116571864,0.00014640152,0.000011111832,0.0000059790777,0.00083671784,0.9096373,0.023804178,0.064764455,0.00031239263,0.00021180519],"about_ca_topic_score_codex":0.000040915864,"about_ca_topic_score_gemma":0.0000025304373,"teacher_disagreement_score":0.9495081,"about_ca_system_score_codex":0.0000031224295,"about_ca_system_score_gemma":0.0000269914,"threshold_uncertainty_score":0.62511355},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014708025,0.000013148051,0.9956971,0.0012179919,0.00006511047,0.00027648083,0.000041083455,0.00006588546,0.0011524274],"genre_scores_gemma":[0.08985879,0.000003427696,0.90794975,0.00013076545,0.00002243701,0.00024985097,0.000026861633,0.000004027713,0.0017540645],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99927944,0.0000115940875,0.00018442799,0.00022540349,0.0001576858,0.00014143111],"domain_scores_gemma":[0.99923265,0.00014473866,0.00006769348,0.0003288607,0.0001601063,0.00006592759],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001287155,0.000064834596,0.00007930332,0.00007021067,0.000106439904,0.00006925266,0.00048724367,0.000047965255,0.00010137583],"category_scores_gemma":[0.000045023662,0.00005626018,0.000042296215,0.00019107544,0.00005392704,0.0006047307,0.000109906585,0.0000674342,0.0000858771],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.2699434e-7,0.00012269699,0.0014061632,0.000008222707,0.000018772593,9.026627e-8,0.00019541214,0.000100692276,0.00089129014,0.88389575,0.015165058,0.0981952],"study_design_scores_gemma":[0.00025815715,0.000031503227,0.03699021,0.0000073393844,0.000003318142,0.0000020875962,0.00003699323,0.94772613,0.00032560207,0.009447894,0.005071604,0.000099166966],"about_ca_topic_score_codex":0.000112048336,"about_ca_topic_score_gemma":0.000013903782,"teacher_disagreement_score":0.94762546,"about_ca_system_score_codex":0.000012641494,"about_ca_system_score_gemma":0.00006781789,"threshold_uncertainty_score":0.22942236},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.068113886,0.000012044865,0.8803125,0.009456673,0.0001502465,0.00044666705,0.0000054659045,0.00029779828,0.041204717],"genre_scores_gemma":[0.51330495,4.4160893e-7,0.48332676,0.0024895296,0.00009965306,0.00026921922,0.000012653832,0.000008528276,0.00048822342],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990215,0.00004006762,0.00016497976,0.00034853548,0.00019898708,0.0002259852],"domain_scores_gemma":[0.998795,0.00021468155,0.000062676314,0.000799349,0.00005960945,0.000068718306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022860599,0.00011242476,0.0000809184,0.000036535144,0.00029793862,0.00063569006,0.0010993916,0.000030854037,0.00008938572],"category_scores_gemma":[0.000044641765,0.00006916476,0.000031642106,0.0003260938,0.000029812843,0.0002586589,0.00015548663,0.00011191702,0.0002625505],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.0192397e-7,0.00040783882,0.00028020152,0.000014633884,0.000029384059,0.0000018162947,0.0015104512,0.0012124904,0.002910474,0.51566106,0.13463666,0.3433343],"study_design_scores_gemma":[0.00011356066,0.000032579464,0.00075373834,0.000015170411,0.0000020585132,0.0000039325437,0.00024419592,0.9915915,0.0026318673,0.00044239857,0.00400682,0.00016215935],"about_ca_topic_score_codex":0.00015007085,"about_ca_topic_score_gemma":8.562324e-7,"teacher_disagreement_score":0.99037904,"about_ca_system_score_codex":0.00001984306,"about_ca_system_score_gemma":0.00004295637,"threshold_uncertainty_score":0.6129974},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022832782,0.00007549033,0.9924269,0.0012447168,0.000014754528,0.000047293972,0.0000030886574,0.00019373499,0.0037107498],"genre_scores_gemma":[0.02394698,0.000010267881,0.97223526,0.00024302652,0.000053242045,0.000016289547,0.00003928141,0.00000501532,0.003450625],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99936414,0.000014320932,0.0001069415,0.00024875926,0.00013636389,0.00012945707],"domain_scores_gemma":[0.9995051,0.00007692152,0.000041699586,0.00028902193,0.000035127017,0.000052101695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012980016,0.00006750563,0.000060780745,0.000035803263,0.0001688021,0.00007084675,0.00027835733,0.000010889426,0.00006313636],"category_scores_gemma":[0.000021515225,0.00005183778,0.000012093518,0.00021201088,0.000021170536,0.0007182434,0.00012768105,0.000079821046,0.00017547859],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011065113,0.00010680833,0.003976837,0.000004680301,0.000015310914,0.000003287233,0.00042460582,0.0027611111,0.000073149575,0.18323888,0.0033887099,0.80600554],"study_design_scores_gemma":[0.00017796518,0.000017681936,0.0033886742,0.00001907673,0.0000028280608,0.000020112448,0.000039522405,0.62044835,0.00012221394,0.0000060512525,0.3756474,0.00011010711],"about_ca_topic_score_codex":0.000020370544,"about_ca_topic_score_gemma":0.00003184966,"teacher_disagreement_score":0.8058954,"about_ca_system_score_codex":0.000011480654,"about_ca_system_score_gemma":0.000036629095,"threshold_uncertainty_score":0.22554809},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0070353043,0.0000020379737,0.91206324,0.002252769,0.00020558502,0.000025682866,0.0000011259325,0.00019166905,0.07822258],"genre_scores_gemma":[0.121672235,7.874073e-7,0.8754837,0.0003834395,0.000057255274,0.00000791284,0.0000014319095,0.0000015127946,0.002391724],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9997624,0.0000013655616,0.00003570026,0.00009880959,0.000042700573,0.00005900926],"domain_scores_gemma":[0.99957067,0.000011843498,0.0000074034115,0.00036676502,0.000011974322,0.000031330113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000052101495,0.000021633521,0.00001960783,0.000011701974,0.00003794584,0.00006877575,0.00044087815,0.000011718126,0.00005719465],"category_scores_gemma":[0.000006441903,0.00001706012,0.000008679574,0.00009054866,0.000009468124,0.00014944607,0.000087137305,0.00005385917,0.00040174162],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.2993163e-8,0.00000830277,0.000032040178,1.518238e-7,4.3176544e-7,2.472782e-7,0.000018887771,4.557245e-8,0.0018564174,0.6776304,0.0071767448,0.31327626],"study_design_scores_gemma":[0.00006784301,0.000009959715,0.0038871071,6.4494674e-7,6.9185216e-7,0.000014728849,0.000004723266,0.08046306,0.004953936,0.012557852,0.89793915,0.000100313584],"about_ca_topic_score_codex":0.000009928303,"about_ca_topic_score_gemma":0.000007599139,"teacher_disagreement_score":0.8907624,"about_ca_system_score_codex":7.1423e-7,"about_ca_system_score_gemma":0.000009571144,"threshold_uncertainty_score":0.516371},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64500964,0.000029637633,0.11088057,0.016778234,0.00020580174,0.0010383299,0.00008514437,0.00020314947,0.22576948],"genre_scores_gemma":[0.8561574,0.000018040082,0.13523285,0.00043502316,0.0000824507,0.00007026767,0.000006794537,0.000008995831,0.007988181],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988442,0.000014635003,0.00016752875,0.00030357487,0.00049103505,0.00017904978],"domain_scores_gemma":[0.9986463,0.00017310027,0.00006124042,0.0005537757,0.0005312226,0.000034336277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006642535,0.00006224635,0.00007826448,0.0000912109,0.00027097564,0.00005447591,0.0014286796,0.000023926763,0.000019414056],"category_scores_gemma":[0.00020970103,0.000037674054,0.000017771266,0.0025836076,0.00017815428,0.00033913067,0.00067506783,0.00023613265,0.000037501562],"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":[0.0000044325097,0.0002221568,0.00039195432,0.000006425603,0.000008896745,0.0000012360964,0.0016614882,0.0000026781338,0.0041202726,0.7643114,0.19578533,0.03348379],"study_design_scores_gemma":[0.0019153234,0.00063534116,0.090035394,0.0005966721,0.000008861107,0.00011539221,0.0043037455,0.15611711,0.4019761,0.01892958,0.32416415,0.0012023001],"about_ca_topic_score_codex":0.000032713084,"about_ca_topic_score_gemma":0.000002156598,"teacher_disagreement_score":0.7453818,"about_ca_system_score_codex":0.000017551434,"about_ca_system_score_gemma":0.000077595636,"threshold_uncertainty_score":0.26548657},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70721835,0.00009220052,0.28752446,0.0038449187,0.0008227129,0.00016075646,0.000039239956,0.000018057604,0.00027928618],"genre_scores_gemma":[0.96297187,0.000017945298,0.03659316,0.00019601831,0.00019186916,0.0000052123837,0.000005647595,0.000010366408,0.000007903182],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99813956,0.00009524613,0.0007040223,0.0002356191,0.0006343268,0.00019121522],"domain_scores_gemma":[0.99820524,0.0004782098,0.0005272213,0.0002928914,0.00041885293,0.00007756843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010224234,0.0001637725,0.00020567638,0.00019024836,0.00015817473,0.00045468705,0.0013145076,0.00005622653,0.00002842041],"category_scores_gemma":[0.0004073474,0.00011644552,0.00010297427,0.00022212308,0.00022144703,0.0008113187,0.00017513247,0.0002351808,0.000007975276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014183179,0.0011366224,0.00032434138,0.000026624928,0.000479945,0.00015326946,0.008089473,0.26627192,0.07326298,0.2826014,0.00017263787,0.3660625],"study_design_scores_gemma":[0.00042852902,0.00045139602,0.00024383308,0.0005806229,0.000041140018,0.00007397459,0.0011778303,0.84790754,0.12463134,0.023839587,0.00029420323,0.00032997568],"about_ca_topic_score_codex":0.00007615377,"about_ca_topic_score_gemma":0.000015867958,"teacher_disagreement_score":0.58163565,"about_ca_system_score_codex":0.0000935197,"about_ca_system_score_gemma":0.0003118209,"threshold_uncertainty_score":0.47485104},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00048222183,0.00008349654,0.9959632,0.00067614374,0.0016916848,0.0006192312,0.000027427091,0.00014672785,0.00030987858],"genre_scores_gemma":[0.010222082,0.0000043454565,0.9875529,0.0009522843,0.0008385597,0.000013779031,0.00001952618,0.000037006415,0.00035955358],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960757,0.00003928788,0.00082475354,0.0015684034,0.00080485054,0.0006869881],"domain_scores_gemma":[0.9955834,0.0017620673,0.0007866432,0.0012026642,0.00049097755,0.0001742235],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0025048559,0.00039882414,0.0005429791,0.00042964594,0.00044838796,0.0010411747,0.002068641,0.0004528435,0.0000118496355],"category_scores_gemma":[0.00065683597,0.00038905753,0.00019729705,0.0005085155,0.00025214444,0.00066958746,0.0007772448,0.00059030316,0.00003504007],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000045061465,0.000045735167,0.00016300808,0.000052278716,0.000015131617,0.0000070921137,0.00014688402,0.0069583044,0.00027389967,0.0026645246,0.0001117467,0.9895569],"study_design_scores_gemma":[0.00033931644,0.000114619164,0.0001587961,0.00018174748,0.000020707756,0.000008174978,1.9057438e-7,0.9863002,0.00046196423,0.010774789,0.001173284,0.00046626138],"about_ca_topic_score_codex":0.000034051656,"about_ca_topic_score_gemma":0.000010053048,"teacher_disagreement_score":0.9890906,"about_ca_system_score_codex":0.0004936973,"about_ca_system_score_gemma":0.00092785904,"threshold_uncertainty_score":0.9999958},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007113668,0.00007266576,0.99378264,0.0005513928,0.00004210493,0.00045040646,0.000063657615,0.00041108357,0.0039147055],"genre_scores_gemma":[0.017492713,0.00004080809,0.9812584,0.0000923258,0.000059894057,0.00034223407,0.00056601566,0.000023695437,0.00012389754],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837726,0.000044540207,0.0003305058,0.0007300745,0.0002731026,0.00024453254],"domain_scores_gemma":[0.99628335,0.00035419746,0.00024305243,0.0028797928,0.00010544523,0.00013413426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002811959,0.00019188877,0.0001957234,0.00008147622,0.00038384437,0.00038271048,0.0023249008,0.00005478993,0.000011532361],"category_scores_gemma":[0.00003171033,0.00017028782,0.000026767704,0.0005163327,0.00008047063,0.00051438215,0.00035765464,0.00019474127,0.0003413076],"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":[5.1531913e-7,0.00029984734,0.00012020133,0.000020560987,0.000049639737,0.0000010363009,0.00062314305,0.00013410636,0.00019679395,0.8576693,0.0025923676,0.13829248],"study_design_scores_gemma":[0.00029509902,0.000034083652,0.0005190107,0.000046272093,0.000039404516,0.000024513163,0.00025335903,0.7640107,0.0001334553,0.039412454,0.19487019,0.00036140537],"about_ca_topic_score_codex":0.000011631257,"about_ca_topic_score_gemma":0.0000034018062,"teacher_disagreement_score":0.81825686,"about_ca_system_score_codex":0.00003237553,"about_ca_system_score_gemma":0.000097533986,"threshold_uncertainty_score":0.6944136},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037898194,0.0003843765,0.9592495,0.0001193911,0.0010597658,0.00076123717,0.00004728819,0.0001286972,0.00035155858],"genre_scores_gemma":[0.9746692,0.000035880104,0.02444479,0.00006197579,0.00023905383,0.00012305928,0.000027496319,0.000016107722,0.00038240422],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99798703,0.000056476758,0.00056522817,0.0005880087,0.00047935318,0.0003239068],"domain_scores_gemma":[0.996826,0.00011518266,0.0003413293,0.0024916937,0.00012622494,0.00009956653],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070651155,0.00019778052,0.00024235094,0.00009363542,0.0001790584,0.00030957925,0.0032577338,0.000049826784,0.0000040151735],"category_scores_gemma":[0.00003078236,0.00013075053,0.000043791,0.00043824103,0.00005776079,0.0004767117,0.0002909436,0.00014983669,0.000030483345],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009164105,0.00038871454,0.0010651685,0.00006948677,0.000083580795,0.000036400368,0.0030738509,0.0012598013,0.0042359335,0.0050567845,0.0036074591,0.9811137],"study_design_scores_gemma":[0.00020556008,0.00041943294,0.001120072,0.0004994102,0.00010594056,0.0001895882,0.0017852123,0.93228287,0.033470865,0.000028603692,0.029304229,0.00058822834],"about_ca_topic_score_codex":0.00042775483,"about_ca_topic_score_gemma":0.000010744908,"teacher_disagreement_score":0.98052543,"about_ca_system_score_codex":0.00005473687,"about_ca_system_score_gemma":0.00007603156,"threshold_uncertainty_score":0.60537344},"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":"methods","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.394114e-7,0.00010486618,0.5039654,0.00016483809,0.4921254,0.00067206204,0.0025726778,0.00019715789,0.0001968828],"genre_scores_gemma":[0.00006977963,0.00024543557,0.16633749,0.000044279957,0.82696986,0.0006204682,0.0052915253,0.00007795578,0.00034321652],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99414235,0.00028013502,0.0010314118,0.002262998,0.0016242495,0.0006588539],"domain_scores_gemma":[0.99305856,0.0038381224,0.0005678124,0.0015606773,0.00079217117,0.00018267974],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008218749,0.0007097812,0.00070196704,0.00093518145,0.0008242454,0.00022992402,0.0022421242,0.00089925074,0.000012643196],"category_scores_gemma":[0.00024122409,0.0008148865,0.00020257621,0.0010052207,0.00016519743,0.002153243,0.00004420935,0.0011850502,0.00019117739],"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":[0.00010546187,0.00054947124,3.7029736e-7,0.000056420726,0.00004130725,0.0000026161247,0.00015000228,0.041375883,0.0000016054702,0.000060811486,0.8198394,0.13781662],"study_design_scores_gemma":[0.0010218469,0.0004043664,0.000013757545,0.00019907823,0.000037142432,0.0000030386113,0.000030960742,0.4157942,0.000008563105,0.0005397873,0.5814624,0.00048485733],"about_ca_topic_score_codex":0.00013005939,"about_ca_topic_score_gemma":0.000120922305,"teacher_disagreement_score":0.37441832,"about_ca_system_score_codex":0.0009522512,"about_ca_system_score_gemma":0.0008167782,"threshold_uncertainty_score":0.9994302},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00031509905,0.0000078054845,0.9230529,0.004598753,0.000021984924,0.000015471693,3.6069147e-7,0.00014685027,0.07184079],"genre_scores_gemma":[0.1549923,0.0000027102797,0.8401249,0.0021525577,0.000032357133,0.0000022195236,0.0000015421213,7.7061713e-7,0.0026906554],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99977463,0.0000017137133,0.00003419353,0.00008975903,0.000041609695,0.000058086513],"domain_scores_gemma":[0.9997028,0.0000054329057,0.0000062137046,0.00025248955,0.000008287275,0.000024749923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000031668125,0.00002037929,0.000019965852,0.0000117829595,0.000031223717,0.000057185418,0.00032909872,0.0000066153266,0.000014065927],"category_scores_gemma":[0.0000024222772,0.000016337648,0.000007986554,0.00011075145,0.000003049735,0.00014994103,0.00002524357,0.000016284146,0.0002068611],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.6801215e-8,0.000009324857,0.0000028915929,4.3018392e-8,2.1163356e-7,3.1920996e-7,0.0000147883775,4.7742276e-7,0.00009854164,0.4650217,0.010762678,0.52408904],"study_design_scores_gemma":[0.00019664479,0.0001141958,0.019294014,0.0000040773652,0.0000016405602,0.000022572263,0.000015057812,0.30352452,0.0041848384,0.09370978,0.5786814,0.00025122173],"about_ca_topic_score_codex":0.000003060667,"about_ca_topic_score_gemma":2.4688205e-7,"teacher_disagreement_score":0.5679188,"about_ca_system_score_codex":0.000002288284,"about_ca_system_score_gemma":0.0000059538734,"threshold_uncertainty_score":0.265885},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027766757,0.00000970968,0.91443676,0.0015687484,0.00005810178,0.000014787597,4.947231e-7,0.000121745856,0.08351197],"genre_scores_gemma":[0.04348555,7.143614e-7,0.9519757,0.0005129021,0.00003844364,0.000008352033,0.0000018187259,0.0000015052087,0.003975006],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9997724,0.0000027040248,0.00003199568,0.00008218927,0.0000582865,0.00005238697],"domain_scores_gemma":[0.9996552,0.0000062670174,0.000006302861,0.00025229255,0.00002137366,0.00005860447],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000069037436,0.0000186052,0.000019217585,0.000010586662,0.000015874368,0.000055004533,0.00033314482,0.00000636953,0.000005260191],"category_scores_gemma":[0.000007990613,0.00001467928,0.000005587936,0.00010306868,0.0000051983566,0.00016679923,0.00010051363,0.000013986364,0.0004530932],"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":[5.6479816e-8,0.000013556375,0.000043894113,1.746645e-7,9.16258e-7,7.340562e-7,0.00010291171,0.0000023925588,0.000015999003,0.62715834,0.1160211,0.2566399],"study_design_scores_gemma":[0.00013481961,0.00002657157,0.0004008024,0.0000010407001,6.6876254e-7,0.000010447829,0.00004123101,0.22006957,0.00061660854,0.024460493,0.7541495,0.00008825099],"about_ca_topic_score_codex":0.000019068813,"about_ca_topic_score_gemma":0.0000012259184,"teacher_disagreement_score":0.6381284,"about_ca_system_score_codex":0.0000043514456,"about_ca_system_score_gemma":0.000020612924,"threshold_uncertainty_score":0.58237475},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014202517,0.00006463203,0.99562514,0.0006099704,0.00020787376,0.00017768687,0.00006299091,0.0003332691,0.0014982105],"genre_scores_gemma":[0.14073595,0.00011383224,0.8570901,0.00027294626,0.00007014115,0.000048940354,0.00057193724,0.000020351796,0.0010758027],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99845356,0.00001967361,0.00025774984,0.00085624395,0.00019597204,0.00021682294],"domain_scores_gemma":[0.9981184,0.00005160067,0.000089687994,0.0016529567,0.000038355243,0.000048976213],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004599676,0.00014466835,0.00014884397,0.00024539718,0.00004766703,0.00025208356,0.0032951175,0.00015987796,0.000013846494],"category_scores_gemma":[0.000026618904,0.00014192637,0.000019234854,0.00045535155,0.000019882022,0.00035450366,0.0051171063,0.00046657448,0.000053238902],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020547361,0.00025965096,0.0023587244,0.000055134497,0.00002823902,0.000011831646,0.00023993371,0.002629526,0.000036015877,0.00944447,0.009552384,0.97538203],"study_design_scores_gemma":[0.00006458292,0.0000047153535,0.011593843,0.00003102172,0.0000023108505,0.0000063129423,0.000009518591,0.9762294,0.000013176776,0.0020040597,0.009862863,0.00017816329],"about_ca_topic_score_codex":0.0010295536,"about_ca_topic_score_gemma":0.0024262215,"teacher_disagreement_score":0.9752039,"about_ca_system_score_codex":0.000091139125,"about_ca_system_score_gemma":0.00018690016,"threshold_uncertainty_score":0.6378107},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43084913,0.00014078748,0.56596637,0.0003386375,0.002535738,0.00007288753,0.00004375025,0.000022256603,0.000030444982],"genre_scores_gemma":[0.9571083,0.000058369085,0.042037547,0.00008789908,0.0006528626,0.0000013697834,0.000033799923,0.00001150759,0.000008327721],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99814,0.0000926426,0.0007476352,0.0002721585,0.0005801671,0.00016741912],"domain_scores_gemma":[0.99777913,0.00023216545,0.00090943906,0.00024460407,0.0007222827,0.0001123789],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006419974,0.00016203505,0.00026158598,0.00018442057,0.0001547007,0.00066468515,0.0010648828,0.000088528606,0.000005032998],"category_scores_gemma":[0.00009239392,0.00013989344,0.00010318223,0.00012101042,0.000044523906,0.0005424296,0.00018137175,0.0003493219,0.000005746776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050493873,0.0008270587,0.13656229,0.0000530801,0.0011799328,0.0002042584,0.012060796,0.002182135,0.03093256,0.10181082,0.001428345,0.71270823],"study_design_scores_gemma":[0.00033116993,0.00004862262,0.023911176,0.00021592561,0.000028031616,0.00027184328,0.00038141114,0.9681529,0.0007529033,0.0014994841,0.0042009023,0.00020567726],"about_ca_topic_score_codex":0.00054155494,"about_ca_topic_score_gemma":0.000010596269,"teacher_disagreement_score":0.9659707,"about_ca_system_score_codex":0.00006871528,"about_ca_system_score_gemma":0.000060105678,"threshold_uncertainty_score":0.6409574},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09066476,0.00009522323,0.88099533,0.00048336014,0.00014162989,0.00009302608,0.00004823348,0.00004630963,0.02743215],"genre_scores_gemma":[0.89180684,0.0000062811596,0.10803441,0.000009617933,0.000013374355,0.00000524973,0.0000052100863,0.0000011511407,0.000117886644],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99963385,0.000012318311,0.00014035552,0.00005192416,0.00008149876,0.00008004375],"domain_scores_gemma":[0.99962944,0.00009946552,0.00007351243,0.00014835688,0.000033435008,0.000015806248],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016242615,0.000026098667,0.00006109969,0.000052299863,0.00001609929,0.00000921246,0.00014828001,0.000019702731,0.000010530216],"category_scores_gemma":[0.00002778258,0.000024982102,0.000014621405,0.00017941448,0.000013274467,0.0005411694,0.000040808136,0.000032993154,0.0000021338974],"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":[4.3969968e-7,0.00031959885,0.054816734,0.000009748982,0.000008742911,5.4932855e-8,0.00074863,0.000052437026,0.0018696948,0.9118954,0.0011459222,0.029132575],"study_design_scores_gemma":[0.00021177912,0.000045581848,0.93334097,0.0000206742,0.0000076927145,0.0000016929757,0.0008923717,0.041457612,0.01746799,0.0017883243,0.0046317438,0.00013355038],"about_ca_topic_score_codex":0.00013875312,"about_ca_topic_score_gemma":0.000032732816,"teacher_disagreement_score":0.9101071,"about_ca_system_score_codex":0.000009569805,"about_ca_system_score_gemma":0.000018211513,"threshold_uncertainty_score":0.10187405},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026331793,0.0050051818,0.24523622,0.00076445093,0.002177342,0.0053858636,0.005266101,0.0022276219,0.73130405],"genre_scores_gemma":[0.03496369,0.0020759057,0.025547257,0.00051882403,0.00077604805,0.0012068488,0.009143558,0.00041069326,0.92535716],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962641,0.000096823576,0.0011946914,0.0013421208,0.0006009122,0.00050133123],"domain_scores_gemma":[0.996558,0.00029722904,0.0004950128,0.0023144758,0.000065184795,0.00027010412],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00030256945,0.0006031347,0.0007422038,0.0003090992,0.000099927696,0.00091333105,0.0029473563,0.00036660006,0.0009072729],"category_scores_gemma":[0.000023022758,0.00056069536,0.00009614223,0.00018720274,0.00007590045,0.0022876926,0.0016718631,0.00076365075,0.0028685003],"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":[0.000046466583,0.00075626315,0.0005248948,0.0017285468,0.00036635576,0.00010989343,0.001565172,0.00007143878,0.004211309,0.40745455,0.24876578,0.33439934],"study_design_scores_gemma":[0.00018229678,0.0001133903,0.00004243139,0.0018764704,0.000015246866,0.000020874708,0.000060384467,0.06586036,0.0015154314,0.0016445614,0.9272831,0.0013854274],"about_ca_topic_score_codex":0.000518264,"about_ca_topic_score_gemma":0.000010237951,"teacher_disagreement_score":0.67851734,"about_ca_system_score_codex":0.00011077106,"about_ca_system_score_gemma":0.0002004639,"threshold_uncertainty_score":0.99968445},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035929903,0.0000037828997,0.95479834,0.005290512,0.0001434465,0.00038756637,0.00007243834,0.000074810356,0.003299201],"genre_scores_gemma":[0.72663593,0.000008208872,0.26407993,0.009130785,0.0000761384,0.000013075515,0.000039470266,0.0000021681344,0.0000142837225],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890035,0.00004076263,0.00017438199,0.00027258933,0.0004578308,0.00015406124],"domain_scores_gemma":[0.9987289,0.0003809563,0.00013487895,0.0005546708,0.00013799954,0.00006261053],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0012192328,0.0000910007,0.000078864,0.00014136451,0.0006158113,0.001125629,0.00094305596,0.000017951928,8.2302705e-7],"category_scores_gemma":[0.00011539867,0.00006236189,0.0000075462954,0.0004868453,0.00007554264,0.00405407,0.00031674444,0.00008872892,0.000016542164],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013988739,0.000059281545,0.0001453627,5.8014535e-7,0.0000029406433,3.776877e-7,0.00401054,0.000055142333,0.0000022369916,0.0073732203,0.0015676387,0.9867813],"study_design_scores_gemma":[0.00018668165,0.00029574236,0.12958737,0.0000152343,0.0000022393767,0.0000017732003,0.00025793992,0.8686747,0.000038511018,0.0001732887,0.00068745867,0.00007909819],"about_ca_topic_score_codex":0.0000047745957,"about_ca_topic_score_gemma":2.2641818e-7,"teacher_disagreement_score":0.9867022,"about_ca_system_score_codex":0.000037581634,"about_ca_system_score_gemma":0.000057196747,"threshold_uncertainty_score":0.9999113},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014667082,0.00004202765,0.9660219,0.00019304288,0.0000723775,0.00016325453,0.0000045091515,0.00021237963,0.01862345],"genre_scores_gemma":[0.36538428,0.00001423596,0.6340763,0.00021552375,0.000081569684,0.000044294044,0.000013499213,0.000008827321,0.00016148445],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99869615,0.000010147271,0.00028562994,0.0003929189,0.00026257487,0.00035258205],"domain_scores_gemma":[0.9989055,0.00024028895,0.00021295383,0.00046621443,0.00009792999,0.000077152814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007575506,0.0001351908,0.00013562184,0.00007786447,0.0002307722,0.00025752583,0.0007422378,0.000055902827,0.000028187656],"category_scores_gemma":[0.000049430026,0.00011976702,0.000024990863,0.00039393295,0.00003247214,0.00034602388,0.00016727971,0.0001357508,0.00023092228],"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":[0.0000048864836,0.00004394396,0.0007879325,0.000006328151,0.000028039989,0.000002529413,0.00071830116,0.00013455856,0.0017243893,0.5851562,0.0010236625,0.4103692],"study_design_scores_gemma":[0.00095043774,0.00030394673,0.019727077,0.00018818886,0.0000911355,0.00006106879,0.0044835396,0.36461735,0.42173633,0.06488315,0.11981693,0.0031408677],"about_ca_topic_score_codex":0.00006449032,"about_ca_topic_score_gemma":0.000028345938,"teacher_disagreement_score":0.5202731,"about_ca_system_score_codex":0.00012656828,"about_ca_system_score_gemma":0.00004005033,"threshold_uncertainty_score":0.48839575},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042787973,0.00001050227,0.9537348,0.00040122893,0.00006853234,0.00016840901,0.00057810225,0.00014793118,0.0021024921],"genre_scores_gemma":[0.6569363,0.0000029332975,0.33568862,0.00025124606,0.00012244046,0.000037813403,0.006846951,0.000010530062,0.000103186474],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989009,0.000013528494,0.000293708,0.0002563928,0.0003091694,0.00022628559],"domain_scores_gemma":[0.9982384,0.00006159151,0.00014917197,0.001435876,0.00005339473,0.000061587634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013787372,0.00012248404,0.00011767287,0.00005022495,0.00016350855,0.00021366209,0.0013659399,0.00003586995,0.000034204768],"category_scores_gemma":[0.000010503609,0.000102277874,0.000012270006,0.00018659637,0.000019259849,0.0015519711,0.00037689725,0.000073050265,0.00025484973],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001345264,0.00025126312,0.017747024,0.00009587676,0.000076855096,0.000014614089,0.0036905385,0.0005677676,0.00002190392,0.0036787204,0.04621836,0.9276236],"study_design_scores_gemma":[0.0005043377,0.00004282749,0.06796412,0.0000993516,0.00001604717,0.00001737934,0.0002127779,0.9153977,0.00013232477,0.00038386168,0.014964348,0.00026493066],"about_ca_topic_score_codex":0.0015116492,"about_ca_topic_score_gemma":0.00021786457,"teacher_disagreement_score":0.9273587,"about_ca_system_score_codex":0.000018618857,"about_ca_system_score_gemma":0.00007402697,"threshold_uncertainty_score":0.41707706},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019945027,0.40230688,0.59377694,0.00013624634,0.000116169445,0.0003138922,0.00010599572,0.000107788495,0.0011415912],"genre_scores_gemma":[0.90274984,0.028164562,0.066903174,0.000059091035,0.00029945135,0.00021743255,0.0004055205,0.00007908728,0.0011218429],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990568,0.0000477771,0.00030396745,0.0003359775,0.000087338754,0.00016809814],"domain_scores_gemma":[0.99822134,0.00028009727,0.000082356615,0.0012843814,0.000096911754,0.00003492817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012073743,0.00013809465,0.00027394464,0.00003887047,0.00005948018,0.00007155499,0.0016751899,0.000022386785,8.151715e-7],"category_scores_gemma":[0.000116093506,0.00009742666,0.000021872662,0.00066097203,0.000035845384,0.0006403925,0.00072456535,0.0000871629,0.0000076027554],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019479544,0.0004680764,0.00048604712,0.012652938,0.000100605735,0.0000018934174,0.0013493142,0.0016379533,0.00013643889,0.05433729,0.020447569,0.9083799],"study_design_scores_gemma":[0.00007448395,0.000009716853,0.0037923935,0.002019385,0.000028395638,0.000009555325,0.0000027245576,0.9863476,0.000027827065,0.0001191453,0.0074002245,0.00016851393],"about_ca_topic_score_codex":0.00005455256,"about_ca_topic_score_gemma":0.00003670966,"teacher_disagreement_score":0.9847097,"about_ca_system_score_codex":0.000009341035,"about_ca_system_score_gemma":0.00006915636,"threshold_uncertainty_score":0.3972944},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30840704,0.00046787437,0.64443237,0.04009342,0.0004003402,0.00078711077,0.00021991516,0.00037962606,0.004812312],"genre_scores_gemma":[0.61449873,0.0006758735,0.3705802,0.0055297855,0.0006758542,0.000808151,0.0018787313,0.00007802594,0.0052746567],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99854195,0.000052622207,0.0002898689,0.0006521598,0.00016832085,0.00029508636],"domain_scores_gemma":[0.9964285,0.00009535511,0.000041767096,0.0033578712,0.0000071483814,0.00006935592],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00019263933,0.00015295246,0.00012712459,0.00015942148,0.00018261689,0.00026332476,0.0029823573,0.000047588805,0.00013343223],"category_scores_gemma":[0.000025764775,0.00015264026,0.000025850131,0.0007174892,0.000052645682,0.002675874,0.0009630269,0.00016996326,0.0013707065],"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":[0.000007642443,0.0014942716,0.008502877,0.000019221909,0.00008321429,0.000049328642,0.0061788294,0.0018998762,0.003834649,0.0075111235,0.16755109,0.8028679],"study_design_scores_gemma":[0.0006696104,0.000033639488,0.017721988,0.000041710784,0.000016333892,0.000011483449,0.000115596435,0.08759618,0.00045596628,0.002310041,0.89041954,0.00060788775],"about_ca_topic_score_codex":0.00005165968,"about_ca_topic_score_gemma":0.000109700195,"teacher_disagreement_score":0.80226,"about_ca_system_score_codex":0.000027349814,"about_ca_system_score_gemma":0.000025701218,"threshold_uncertainty_score":0.9994068},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24352598,0.0000101465075,0.75479347,0.00040324053,0.000071631024,0.00015623265,0.000020887961,0.00006505155,0.0009533896],"genre_scores_gemma":[0.9523427,0.0000037950688,0.04723215,0.00008304665,0.00007728617,0.00006502209,0.000008653138,0.0000056741087,0.00018166256],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904037,0.000021339127,0.00023607115,0.0002724603,0.00013090644,0.0002988457],"domain_scores_gemma":[0.9993837,0.00010369056,0.00010811496,0.00030811148,0.000045396017,0.000051000454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019734554,0.000087512446,0.00016227113,0.000041223655,0.00016479321,0.00013635233,0.0006516818,0.00005924988,0.000028882816],"category_scores_gemma":[0.0000140777765,0.00007769424,0.000038522798,0.00047491008,0.000057082096,0.00038781602,0.00029927157,0.00011010366,0.000021427548],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009110092,0.0010104225,0.16016084,0.000059755406,0.00008167636,0.000021051103,0.01727349,0.0022827128,0.0043392275,0.29070708,0.05307554,0.4709791],"study_design_scores_gemma":[0.000377469,0.000018883584,0.17286657,0.000020483525,0.0000014084686,9.633787e-7,0.000943617,0.8239094,0.00023809867,0.0008894162,0.0005745046,0.00015921581],"about_ca_topic_score_codex":0.00036277936,"about_ca_topic_score_gemma":0.000096928896,"teacher_disagreement_score":0.82162666,"about_ca_system_score_codex":0.000016321716,"about_ca_system_score_gemma":0.000013138051,"threshold_uncertainty_score":0.31682792},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30720302,0.000056552555,0.69098175,0.0011888875,0.0004309855,0.000049796286,0.000013972021,0.000031881344,0.000043161013],"genre_scores_gemma":[0.972796,0.000017032648,0.027052429,0.000057082714,0.00004890868,0.000011809601,0.0000040736927,0.000002221303,0.0000104175015],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99953806,0.0000017262646,0.00026788688,0.000045910478,0.000071000344,0.00007540533],"domain_scores_gemma":[0.9995957,0.0000586409,0.00012152003,0.00008429399,0.000119954195,0.000019898394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018189481,0.00005401778,0.00008023782,0.0007139591,0.000017008684,0.000107071835,0.00045966927,0.000059980215,0.0000012407121],"category_scores_gemma":[0.00013395626,0.00004900712,0.000023944593,0.00016442925,0.00001678205,0.0013570406,0.00008531639,0.00019629947,0.0000032409146],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005588851,0.00004261358,0.0013278825,0.000023760982,0.00004180984,0.000007115138,0.0011497571,0.0001162607,0.010612026,0.15610422,0.00018646098,0.8303825],"study_design_scores_gemma":[0.0015054871,0.0000691633,0.0019557779,0.00014609103,0.0000053505983,0.00046887217,0.0004806308,0.9504056,0.004992797,0.0010685425,0.03873637,0.00016533447],"about_ca_topic_score_codex":0.0000022181964,"about_ca_topic_score_gemma":0.000012054589,"teacher_disagreement_score":0.9502893,"about_ca_system_score_codex":0.000015058961,"about_ca_system_score_gemma":0.000044808163,"threshold_uncertainty_score":0.19984524},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030379028,0.00008785419,0.97732824,0.00045705057,0.00021964076,0.00024127269,0.000008258137,0.0002488747,0.018370906],"genre_scores_gemma":[0.9114412,0.00005346057,0.08708638,0.00072889234,0.00016756929,0.00008247949,0.000019367983,0.000018685858,0.00040198324],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9979762,0.000011311421,0.00043998915,0.0006626625,0.00040222745,0.0005076284],"domain_scores_gemma":[0.99827087,0.00017164511,0.00013070901,0.0011673897,0.000058073216,0.00020130654],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005201776,0.00021313067,0.00017295033,0.00010858118,0.00018035069,0.00020055452,0.0018667128,0.000073103605,0.000064875785],"category_scores_gemma":[0.000018901681,0.00019863047,0.000063539395,0.00054032705,0.00009390236,0.00023513075,0.0004358603,0.0002093752,0.0011146261],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015150412,0.000060315782,0.00016512029,0.000004562808,0.000009341159,0.000010546055,0.0005168103,0.000016610487,0.0013647109,0.11004349,0.0013986166,0.8864084],"study_design_scores_gemma":[0.00056206406,0.00035075707,0.041362166,0.00015424499,0.000064716885,0.00010963427,0.0021247754,0.08656609,0.61910105,0.09852551,0.14812118,0.0029578074],"about_ca_topic_score_codex":0.00023135247,"about_ca_topic_score_gemma":0.00022387372,"teacher_disagreement_score":0.9084033,"about_ca_system_score_codex":0.00007184008,"about_ca_system_score_gemma":0.000042710006,"threshold_uncertainty_score":0.9996631},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021507325,0.0071582603,0.9388771,0.0016738792,0.00017767545,0.000104188555,0.00006335961,0.0001439785,0.030294219],"genre_scores_gemma":[0.68457735,0.00057127915,0.31457227,0.000054226704,0.000057986937,0.00001873616,0.0000070272,0.0000029479916,0.00013815876],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994888,0.000011988061,0.00009732572,0.00012608789,0.00007994636,0.00019585322],"domain_scores_gemma":[0.99956024,0.00006009558,0.00003654216,0.00024911232,0.00002080295,0.00007321782],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002627469,0.000047081085,0.000071023096,0.000033353714,0.000085783766,0.000018403802,0.00023351549,0.000020831678,0.0000119234855],"category_scores_gemma":[0.000009470663,0.00003990111,0.0000133957265,0.00007784409,0.000037614212,0.0003908152,0.0001501896,0.000029049937,0.0000121735075],"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":[2.7516546e-7,0.00021459137,0.0011454014,0.00001633901,0.0000103567545,1.052199e-7,0.013202505,6.5597527e-7,0.00012915218,0.60286295,0.0032701222,0.3791475],"study_design_scores_gemma":[0.0012125577,0.00028304692,0.17029741,0.00015679192,0.000049442304,0.000077198245,0.026936216,0.30154622,0.0040084585,0.00578592,0.48851737,0.0011293462],"about_ca_topic_score_codex":0.00000499168,"about_ca_topic_score_gemma":0.000008051272,"teacher_disagreement_score":0.66307,"about_ca_system_score_codex":0.0000028270504,"about_ca_system_score_gemma":0.000011700015,"threshold_uncertainty_score":0.16271202},"labels":[],"label_agreement":null},{"id":"W2032469362","doi":"10.1007/s10115-006-0032-8","title":"CanTree: a canonical-order tree for incremental frequent-pattern mining","year":2006,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":140,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Data mining; Tree (set theory); GSP Algorithm; Database transaction; Tree structure; A priori and a posteriori; Association rule learning; Apriori algorithm; Database; Mathematics; Algorithm; Binary tree","score_opus":0.01329467542214002,"score_gpt":0.24506175368626992,"score_spread":0.2317670782641299,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032469362","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01007841,0.00050167483,0.9589057,0.00025646706,0.00046091652,0.0005374212,0.0001284529,0.00013962634,0.028991306],"genre_scores_gemma":[0.9777804,0.000016692109,0.0198578,0.00019148548,0.0003567098,0.00045784653,0.0003961672,0.000009487901,0.00093340187],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99917144,0.000015405747,0.00038460028,0.0001368479,0.000108579,0.00018310377],"domain_scores_gemma":[0.9993578,0.00005801074,0.00013030306,0.00023777153,0.0001589832,0.00005708275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022892568,0.00010171769,0.00012683554,0.00009636548,0.00019205954,0.00036397306,0.0002646018,0.00004684648,0.0000021242558],"category_scores_gemma":[0.000013193586,0.0000911038,0.00002537921,0.00021305935,0.000020645917,0.001855865,0.00009218301,0.000037528906,0.000054959623],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000042444613,0.00010159576,0.0027019286,0.00028258844,0.000039664934,6.9701804e-7,0.0038941521,0.000060196096,0.00026068193,0.1270139,0.09229397,0.77334636],"study_design_scores_gemma":[0.00072689954,0.00005013138,0.0019741175,0.000056023844,0.000007778801,0.000021734184,0.00034840626,0.44389325,0.00014369606,0.000040107985,0.55253977,0.00019807507],"about_ca_topic_score_codex":0.0008626219,"about_ca_topic_score_gemma":0.00023280122,"teacher_disagreement_score":0.967702,"about_ca_system_score_codex":0.000044093555,"about_ca_system_score_gemma":0.00008177441,"threshold_uncertainty_score":0.3715105},"labels":[],"label_agreement":null},{"id":"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0058105947,0.000043103937,0.98311096,0.0018013512,0.00018028167,0.00006005043,0.00013962053,0.00021468538,0.008639375],"genre_scores_gemma":[0.0980664,0.00000708233,0.89868414,0.0006088477,0.00018231128,0.000010224686,0.0003910024,0.00000828702,0.0020416789],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989281,0.000028159502,0.0001461944,0.0005385899,0.00017902376,0.0001798762],"domain_scores_gemma":[0.9975588,0.00016763688,0.00005504126,0.0021134703,0.00001991595,0.000085152475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027892145,0.00009128038,0.00010063214,0.00003241099,0.00012417465,0.00037594247,0.0025857224,0.000026867687,0.00018575297],"category_scores_gemma":[0.000040572504,0.00007947517,0.000013759795,0.00015258405,0.000022994343,0.00091448956,0.0013611943,0.000057461897,0.00046353784],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.553604e-7,0.000045087876,0.00027317103,0.0000022362385,0.000018905332,0.000001887145,0.00026411252,0.000006608298,0.00030918245,0.04603641,0.13040383,0.82263803],"study_design_scores_gemma":[0.00021575954,0.000025997646,0.0015740672,0.000011479313,0.000007191927,0.0000021980509,0.00009087984,0.4573022,0.00040039571,0.0017514962,0.53841555,0.00020275064],"about_ca_topic_score_codex":0.00030296712,"about_ca_topic_score_gemma":0.000055913777,"teacher_disagreement_score":0.82243526,"about_ca_system_score_codex":0.000008441666,"about_ca_system_score_gemma":0.000020739684,"threshold_uncertainty_score":0.59579957},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008331308,0.000044925822,0.9820904,0.0005309812,0.00016118637,0.00003434035,0.0000010517806,0.00007937478,0.008726401],"genre_scores_gemma":[0.8985308,0.0000019743427,0.10062684,0.00018965492,0.00025973696,0.00001396397,0.0000065499166,0.000003127924,0.0003673785],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994986,0.000010951193,0.000085314845,0.00010919555,0.000066481574,0.00022946944],"domain_scores_gemma":[0.9997629,0.000012071863,0.000018937877,0.00015856331,0.0000059510207,0.00004159725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019268203,0.000042972588,0.0000508166,0.000038831637,0.000098930155,0.00005698261,0.00032548443,0.00003029595,0.000017840202],"category_scores_gemma":[0.0000033216538,0.0000395525,0.000015511945,0.000314796,0.000008532306,0.00041176972,0.00014602675,0.00006794596,0.000038181257],"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":[2.1040265e-7,0.00006565067,0.0116601335,9.276445e-7,0.0000031045643,8.8586495e-7,0.0007798183,0.000031869935,0.000017266608,0.7990099,0.008206678,0.18022354],"study_design_scores_gemma":[0.00034288078,0.00001765632,0.13463603,0.000009202808,0.0000049539344,0.000010882394,0.00018890492,0.75184065,0.000111494846,0.0029774318,0.109449774,0.0004101433],"about_ca_topic_score_codex":0.000027215325,"about_ca_topic_score_gemma":0.000003954762,"teacher_disagreement_score":0.8901995,"about_ca_system_score_codex":0.000015544509,"about_ca_system_score_gemma":0.0000056727945,"threshold_uncertainty_score":0.1612904},"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":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5988075,0.00017324962,0.18015702,0.0054210275,0.002861525,0.0035469166,0.00076196145,0.00082570873,0.20744509],"genre_scores_gemma":[0.17760076,0.000048817197,0.8199278,0.00033871358,0.00043807022,0.0005855733,0.00021659871,0.000044205804,0.0007994397],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99893725,1.5351574e-8,0.00040199986,0.0001311016,0.0003506297,0.00017902431],"domain_scores_gemma":[0.99869525,0.000054115782,0.00024618703,0.00006278816,0.0008877867,0.000053853964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043716977,0.00012937904,0.00015209742,0.000090519025,0.00006763016,0.00019692817,0.0005235451,0.0000943465,0.000017586253],"category_scores_gemma":[0.00022367561,0.00011344806,0.00018124291,0.00022528347,0.0000416072,0.0011514303,0.000042093932,0.0000841247,0.000030828523],"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":[0.000004575786,0.000020681842,0.0000118807975,0.0001792105,0.000038268587,5.3542717e-9,0.000050555358,0.000103597944,0.006671297,0.9501071,0.04050405,0.0023087573],"study_design_scores_gemma":[0.0005912679,0.00009380768,0.000120475226,0.00007544068,0.00003635787,0.000005218047,0.0000776856,0.46391505,0.004824395,0.001076328,0.5289882,0.00019579752],"about_ca_topic_score_codex":0.0000010249807,"about_ca_topic_score_gemma":1.726033e-8,"teacher_disagreement_score":0.9490308,"about_ca_system_score_codex":0.00007569243,"about_ca_system_score_gemma":0.000054078737,"threshold_uncertainty_score":0.46262777},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61757475,0.00035220303,0.33613077,0.0029001613,0.0008648675,0.001935575,0.0018677504,0.0005833824,0.037790515],"genre_scores_gemma":[0.66767305,0.000007705149,0.33193833,0.00011268758,0.000038803773,0.00009576897,0.000026363963,0.000008159477,0.000099112185],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991634,0.0000029467567,0.0001888617,0.00027856315,0.00017963226,0.00018663202],"domain_scores_gemma":[0.9993396,0.000033039214,0.00021358456,0.00030026448,0.00006446063,0.000049075454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014846135,0.00010580423,0.00011388073,0.00004388915,0.00020379266,0.000076776436,0.001091684,0.000022849004,0.00001759401],"category_scores_gemma":[0.000025198246,0.000070886446,0.00003169089,0.00025469984,0.00004917832,0.00052823755,0.0005648265,0.000077822886,0.00001079039],"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":[0.00005595723,0.0014404126,0.119315445,0.00010054048,0.00054343627,0.0000032485602,0.03410815,0.00003404407,0.01173665,0.66816187,0.08725122,0.07724899],"study_design_scores_gemma":[0.0064002154,0.00088913634,0.19831,0.0019088099,0.0005879712,0.00013477936,0.014354211,0.18360846,0.29067704,0.02751804,0.27284214,0.0027692094],"about_ca_topic_score_codex":0.00016390347,"about_ca_topic_score_gemma":0.000010235194,"teacher_disagreement_score":0.64064384,"about_ca_system_score_codex":0.000022697917,"about_ca_system_score_gemma":0.00002359841,"threshold_uncertainty_score":0.28906652},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0073000975,0.0002989787,0.99142,0.00039290224,0.00034352054,0.00015035806,0.000046020345,0.000027902439,0.000020237825],"genre_scores_gemma":[0.09210707,0.000012922248,0.9076421,0.000074318035,0.00010146591,0.000017383614,0.000012653108,0.000013865487,0.000018212553],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992874,0.0000029690439,0.0002704417,0.00017137088,0.000088896704,0.0001788869],"domain_scores_gemma":[0.9991626,0.00016470352,0.00012712862,0.00029929343,0.00016692697,0.000079321464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031612397,0.000108782246,0.00016062536,0.00009457575,0.00005838989,0.00007875945,0.0006499817,0.000036013036,0.0000017714705],"category_scores_gemma":[0.000121677185,0.00008915135,0.00004740349,0.00010574787,0.00001096932,0.000519994,0.00009699518,0.000058161328,2.256365e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047684298,0.0014356136,0.0026135386,0.0026410404,0.0015019132,0.000117720505,0.011122329,0.1080882,0.0028687196,0.34165272,0.11684428,0.41063708],"study_design_scores_gemma":[0.0004452643,0.00020374949,0.0003467456,0.00013215745,0.000025846935,0.00004661015,0.000015746042,0.9749941,0.00022065824,0.0011214083,0.022294799,0.00015291144],"about_ca_topic_score_codex":0.0000018605879,"about_ca_topic_score_gemma":4.9974045e-7,"teacher_disagreement_score":0.86690587,"about_ca_system_score_codex":0.000010538615,"about_ca_system_score_gemma":0.00007587109,"threshold_uncertainty_score":0.36354864},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89938956,0.0024579056,0.0435728,0.031893548,0.009907593,0.00042902652,0.000040329884,0.00022865152,0.012080601],"genre_scores_gemma":[0.943535,0.0012423286,0.04836187,0.0022448197,0.0004701137,0.0007614447,0.00012206564,0.000014069244,0.0032482888],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9987997,0.000038449874,0.00032610176,0.00039286318,0.00029258084,0.00015034173],"domain_scores_gemma":[0.9986613,0.000097485456,0.00014325722,0.0003734287,0.00067132147,0.000053248394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001579165,0.00013289537,0.00014043218,0.00035399522,0.00016363214,0.00011889844,0.0011188928,0.00003342483,0.000022562297],"category_scores_gemma":[0.0001257017,0.00013091616,0.00003964637,0.0004859024,0.000078618534,0.0010250483,0.00035286378,0.00010595696,0.0001023047],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000063825396,0.0018327177,0.053959634,0.000021462882,0.000102711085,0.000006427885,0.0058404547,0.000037996317,0.0003536391,0.0233044,0.18682262,0.72771156],"study_design_scores_gemma":[0.0010576587,0.00007693832,0.49665228,0.00030931726,0.0000139090225,0.00018717436,0.0051145256,0.012720295,0.0005205026,0.026733615,0.45577654,0.0008372296],"about_ca_topic_score_codex":0.00017549375,"about_ca_topic_score_gemma":0.00010610308,"teacher_disagreement_score":0.72687435,"about_ca_system_score_codex":0.00021309975,"about_ca_system_score_gemma":0.0007335413,"threshold_uncertainty_score":0.53386056},"labels":[],"label_agreement":null},{"id":"W2038021410","doi":"10.1007/s10115-010-0290-3","title":"Study of select items in different data sources by grouping","year":2010,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Measure (data warehouse); Computer science; Set (abstract data type); Data mining; Database; Association rule learning; Information retrieval","score_opus":0.022332729292336054,"score_gpt":0.2703498052012024,"score_spread":0.24801707590886635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038021410","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96143913,0.00021160798,0.03539631,0.00003281262,0.00035196636,0.00041525616,0.000049951268,0.000053279146,0.0020496813],"genre_scores_gemma":[0.9995604,0.00001029188,0.00023010821,0.000006649251,0.000040237373,0.000034802626,0.00008261005,0.0000019768001,0.000032895947],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992467,0.000027405456,0.0003816398,0.00013277268,0.00011304501,0.00009844799],"domain_scores_gemma":[0.9991495,0.000054517714,0.00013869895,0.00055956695,0.00005851563,0.000039174654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037795838,0.000075559125,0.00014070523,0.0001187594,0.000068147725,0.00020636177,0.00064527686,0.000033803844,6.809406e-7],"category_scores_gemma":[0.000022358798,0.00005884976,0.000006439524,0.00026684185,0.000013814559,0.002433174,0.00031586457,0.00009941851,0.000013519682],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010132869,0.0023859574,0.11085185,0.00073584664,0.00012181887,0.0000011064819,0.15874697,0.00004520517,0.003536385,0.050632186,0.04361092,0.62932163],"study_design_scores_gemma":[0.0013168177,0.00021275728,0.03455165,0.00009345416,0.00000954542,0.0000192043,0.0060026455,0.7510009,0.0003228385,0.00002037471,0.20612545,0.00032439484],"about_ca_topic_score_codex":0.0001480675,"about_ca_topic_score_gemma":0.00007214032,"teacher_disagreement_score":0.75095564,"about_ca_system_score_codex":0.000005898893,"about_ca_system_score_gemma":0.000015730686,"threshold_uncertainty_score":0.23998235},"labels":[],"label_agreement":null},{"id":"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3166452,0.002657536,0.6793615,0.0005368698,0.00044260887,0.00026303044,0.000008672177,0.000012456149,0.000072125644],"genre_scores_gemma":[0.9831377,0.0015111163,0.01518792,0.000026877588,0.00007936301,0.000010019184,4.0975817e-7,0.0000044284798,0.000042115007],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922806,0.000047757614,0.00033859772,0.00012148992,0.0001649245,0.000099165976],"domain_scores_gemma":[0.9993264,0.00018685333,0.0002033495,0.00010319853,0.00010821571,0.00007199338],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078321167,0.000070648435,0.00017215079,0.00012909698,0.00008918279,0.00007874054,0.00014544747,0.000037719434,6.115728e-7],"category_scores_gemma":[0.000072032635,0.000057158733,0.000029490706,0.00010521287,0.000035721667,0.00031662924,0.000026422056,0.00009120483,5.8102523e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002795152,0.0003424846,0.34014416,0.0005549876,0.0003680381,0.00010496552,0.015861524,0.003481857,0.0022010175,0.008864528,0.032976158,0.59482074],"study_design_scores_gemma":[0.0035366581,0.0012419363,0.23599957,0.0011070466,0.00008555666,0.0053360704,0.005753343,0.61406213,0.0031110113,0.0017529003,0.12697819,0.0010356182],"about_ca_topic_score_codex":0.0001274018,"about_ca_topic_score_gemma":0.00004304735,"teacher_disagreement_score":0.6664925,"about_ca_system_score_codex":0.000038713806,"about_ca_system_score_gemma":0.00003818091,"threshold_uncertainty_score":0.23308654},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.100955755,6.922608e-7,0.88815004,0.0013217942,0.00044209082,0.0004965013,0.000015384667,0.0002164177,0.008401304],"genre_scores_gemma":[0.88936996,6.510105e-8,0.10953472,0.0001897572,0.000062330895,0.00018941617,0.0000021283035,0.000004975053,0.0006466139],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99936074,0.00001572101,0.00009829334,0.00025983588,0.00013108017,0.00013432023],"domain_scores_gemma":[0.9992058,0.00023792461,0.000049265436,0.00036995695,0.00008867385,0.00004835865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034967143,0.00006697253,0.00007623431,0.00003797695,0.00013845417,0.00015235473,0.00060732436,0.000026180935,0.0000028408026],"category_scores_gemma":[0.00024211728,0.000052326315,0.000026824155,0.00014181045,0.000016838569,0.00013561237,0.00009519187,0.00011800307,0.000023013523],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000063326283,0.0010763971,0.004466906,0.0000025577178,0.00006807045,0.0000025905701,0.0057637496,0.0000023935647,0.0016703387,0.38187933,0.018068941,0.5869924],"study_design_scores_gemma":[0.0070904,0.0052326806,0.41005436,0.00006678884,0.00010342927,0.000019124465,0.01949227,0.3640799,0.015746994,0.049147304,0.12652913,0.0024376211],"about_ca_topic_score_codex":0.000021186534,"about_ca_topic_score_gemma":0.00009499964,"teacher_disagreement_score":0.78841424,"about_ca_system_score_codex":0.000012193405,"about_ca_system_score_gemma":0.000030206143,"threshold_uncertainty_score":0.21338052},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04547563,0.0003918545,0.9526654,0.00040052322,0.00033771264,0.0004161795,0.000018065299,0.00009268758,0.00020198381],"genre_scores_gemma":[0.8516961,0.00003632649,0.14765899,0.00006361504,0.00011977031,0.0002428725,0.0001046264,0.000006253729,0.00007145341],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866855,0.00009162277,0.0003206852,0.0003847778,0.00039135345,0.00014300206],"domain_scores_gemma":[0.9987296,0.00022163149,0.00013436835,0.00022294662,0.00062657386,0.000064919885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011535106,0.00010094026,0.000108997214,0.0000911403,0.00025728534,0.00031045693,0.00028518785,0.00004845317,0.0000050159733],"category_scores_gemma":[0.00015779672,0.0001027539,0.000029620875,0.00028469448,0.000051476225,0.0006829968,0.00006342063,0.0000638106,0.00003420974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011725088,0.000084571766,0.00034867466,0.000025401809,0.000019802585,3.224029e-7,0.00054598297,0.09161925,0.00024763562,0.2237473,0.00047767095,0.68287164],"study_design_scores_gemma":[0.00008432165,0.000043417018,0.006114673,0.000020030147,0.000008652376,0.000025434667,0.00016420826,0.88955903,0.00011930923,0.10192691,0.0018097638,0.00012424504],"about_ca_topic_score_codex":0.000082991864,"about_ca_topic_score_gemma":0.000004716892,"teacher_disagreement_score":0.8062205,"about_ca_system_score_codex":0.0000786726,"about_ca_system_score_gemma":0.000086300766,"threshold_uncertainty_score":0.41901824},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008999943,0.0001348016,0.9963052,0.00060663105,0.00015042104,0.0018242738,0.000101458376,0.00042249224,0.0003646758],"genre_scores_gemma":[0.02640398,0.00001111856,0.9607859,0.00013729963,0.0005187458,0.010963714,0.00026182603,0.000042485393,0.00087491376],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99797624,0.0000922275,0.00041018485,0.0007601101,0.00037572457,0.0003854984],"domain_scores_gemma":[0.9978433,0.00033964633,0.00042761906,0.00083668897,0.00039126634,0.00016148316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047578767,0.00024319906,0.0003158233,0.000112315254,0.00059931335,0.00040213706,0.0006956013,0.00012143623,0.0000014513375],"category_scores_gemma":[0.00007720875,0.00020836957,0.000064339554,0.0005392017,0.000037884838,0.0004834445,0.00009418249,0.00010520069,0.000054800003],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017194092,0.0010723721,0.0043642176,0.00009729586,0.00035833544,7.0684524e-7,0.008719229,0.0008333765,0.0016184167,0.1414595,0.010590135,0.8308692],"study_design_scores_gemma":[0.0006475669,0.00008447253,0.0008444462,0.000043876742,0.00001769684,0.000010058335,0.00031083316,0.86638355,0.00013776957,0.000110256966,0.13109513,0.0003143673],"about_ca_topic_score_codex":0.00014708009,"about_ca_topic_score_gemma":0.000009329987,"teacher_disagreement_score":0.86555016,"about_ca_system_score_codex":0.00022894463,"about_ca_system_score_gemma":0.00009600529,"threshold_uncertainty_score":0.8497065},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001698553,0.000035697052,0.9636351,0.0120427245,0.00063501124,0.000051598945,0.0000065386284,0.0003791066,0.021515712],"genre_scores_gemma":[0.020358857,0.000011412654,0.9609401,0.0010434549,0.000718646,0.000026180696,0.000017249748,0.0000068425275,0.016877213],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99920696,0.000007158108,0.00014454093,0.00028390103,0.00020136898,0.0001560731],"domain_scores_gemma":[0.9993008,0.00010049233,0.000045359426,0.00044728717,0.000043684486,0.00006238552],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010086588,0.00007758374,0.00005926554,0.000054427685,0.00012006178,0.000280509,0.00079098984,0.000031167783,0.000066894674],"category_scores_gemma":[0.000055594606,0.000068432986,0.000027075735,0.00013301289,0.000018050052,0.00047238194,0.000193234,0.0000689254,0.00019242334],"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":[0.0000015352928,0.00007516217,0.00023485355,7.78566e-7,0.000013401386,0.0000032532241,0.00034580316,0.00021779888,0.000042591833,0.05142516,0.112595014,0.8350446],"study_design_scores_gemma":[0.00016046103,0.000017142114,0.0010957645,0.000029491583,0.0000025512477,0.000020660442,0.000108566615,0.08719036,0.0013811834,0.00026929632,0.90952754,0.00019696479],"about_ca_topic_score_codex":0.000006561437,"about_ca_topic_score_gemma":0.000011200797,"teacher_disagreement_score":0.8348477,"about_ca_system_score_codex":0.000037531165,"about_ca_system_score_gemma":0.000027099337,"threshold_uncertainty_score":0.27906162},"labels":[],"label_agreement":null},{"id":"W2043301550","doi":"10.1007/s10115-003-0101-1","title":"Data Mining: How Research Meets Practical Development?","year":2003,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Data science; Computer science; Data mining; Panel discussion; Development (topology); Business","score_opus":0.19245540659425892,"score_gpt":0.3901175826814103,"score_spread":0.19766217608715136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043301550","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018996216,0.001131186,0.807824,0.0022670538,0.0008733597,0.0006441115,0.000055397464,0.00022895979,0.1850763],"genre_scores_gemma":[0.5824712,0.00016189329,0.41234243,0.00013039362,0.00021147744,0.00025213198,0.0004768486,0.0000146865605,0.0039389497],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99890655,0.000122013094,0.00026542044,0.00020397089,0.00027871775,0.00022334566],"domain_scores_gemma":[0.9985375,0.00018879533,0.00008404316,0.0007758656,0.00029703008,0.00011676453],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002260996,0.00007971915,0.00010130421,0.00016561859,0.00035500113,0.0010227808,0.0005974293,0.00005617317,0.0000022414406],"category_scores_gemma":[0.00038082208,0.000068751244,0.0000066747966,0.0004813038,0.000038485745,0.006693568,0.00041588282,0.000115737486,0.00034394357],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011225246,0.00006175315,0.00012174135,0.00011008176,0.000022343178,0.0000012107516,0.0070681097,7.3464383e-7,0.000015057299,0.54492664,0.26123646,0.18643473],"study_design_scores_gemma":[0.00012879937,0.000013193598,0.00013225923,0.0000273623,0.0000012396031,0.000045626042,0.0009234733,0.051142298,0.000063049985,0.000014535045,0.94741935,0.00008880736],"about_ca_topic_score_codex":0.000003171998,"about_ca_topic_score_gemma":0.0000026048513,"teacher_disagreement_score":0.6861829,"about_ca_system_score_codex":0.000027136532,"about_ca_system_score_gemma":0.00029712686,"threshold_uncertainty_score":0.98626983},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007530511,0.00006043923,0.91633564,0.07278986,0.00027719786,0.0002006276,0.000028852888,0.00037741315,0.0023994565],"genre_scores_gemma":[0.48987183,0.000033390956,0.48828405,0.019532802,0.0005169626,0.0004371201,0.00010270821,0.00003444347,0.0011867016],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986045,0.000045084496,0.00031846244,0.00047319027,0.00023603028,0.00032272883],"domain_scores_gemma":[0.9979687,0.00016106541,0.00009386214,0.0015890902,0.0000705095,0.000116796524],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00011383035,0.00017483343,0.00014347618,0.00012620982,0.00029436365,0.00036685335,0.0013601776,0.00005798034,0.00034322654],"category_scores_gemma":[0.00009434052,0.00017088666,0.000063848245,0.00045524817,0.00007311427,0.0011320596,0.0003261844,0.00013910796,0.0014439062],"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":[3.931375e-7,0.00019547078,0.0006060497,0.0000067020296,0.00004190476,0.000038198337,0.0042448714,0.000065533095,0.0032116794,0.00869386,0.45526764,0.5276277],"study_design_scores_gemma":[0.0016957351,0.0002245147,0.0015346489,0.000092382164,0.000053951175,0.00015114977,0.000771306,0.46535555,0.0048505124,0.0053600604,0.5182254,0.0016848466],"about_ca_topic_score_codex":0.00002311195,"about_ca_topic_score_gemma":0.000010825362,"teacher_disagreement_score":0.52594286,"about_ca_system_score_codex":0.000030892646,"about_ca_system_score_gemma":0.000016646887,"threshold_uncertainty_score":0.99933356},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017835973,0.000053723583,0.9763784,0.0008762252,0.00007028737,0.00006804854,0.0000013264711,0.00012551884,0.0045904885],"genre_scores_gemma":[0.34196216,0.000006650357,0.6559995,0.0003037053,0.00008243139,0.000024942068,0.0000062618064,0.0000050965054,0.0016093119],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99944127,0.000009798209,0.00006855456,0.00014227389,0.00014887302,0.0001892176],"domain_scores_gemma":[0.99956006,0.000019341558,0.000015919188,0.00029607597,0.000017792458,0.00009079943],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014033845,0.000060710034,0.000054192777,0.000022781573,0.00008665403,0.00010798312,0.00023237866,0.000013262501,0.00008202283],"category_scores_gemma":[0.0000021186627,0.00004109782,0.000013715593,0.00012885255,0.000016241089,0.00067505566,0.00019082484,0.0000356056,0.00011613658],"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":[0.000010508,0.00028431,0.0021896143,0.000019801766,0.000042996464,0.000008331146,0.0054044127,0.00003984235,0.0014345405,0.4023612,0.007775355,0.5804291],"study_design_scores_gemma":[0.0026068501,0.00041170346,0.01997472,0.00008996167,0.000032057735,0.0005400541,0.0013180422,0.3877166,0.0049134684,0.0008646476,0.5803123,0.0012195717],"about_ca_topic_score_codex":0.00004066944,"about_ca_topic_score_gemma":0.0000037514849,"teacher_disagreement_score":0.5792095,"about_ca_system_score_codex":0.000013969864,"about_ca_system_score_gemma":0.0000111804875,"threshold_uncertainty_score":0.16759205},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002573441,0.000027804112,0.9961993,0.00018067975,0.00024440174,0.00011027603,0.00013977085,0.00029346795,0.00023086103],"genre_scores_gemma":[0.09617008,0.000004986043,0.9034837,0.00010411301,0.0000322664,0.000042415028,0.00010999983,0.000015997106,0.000036462632],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989878,0.0000072830708,0.00019183588,0.00043711672,0.00011200218,0.00026396062],"domain_scores_gemma":[0.99862754,0.00016797369,0.000042250365,0.0010788931,0.000020144016,0.00006316836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020429236,0.00012507783,0.00011312946,0.00012904842,0.00003836193,0.000027197262,0.00087156263,0.00004234268,0.0000042274014],"category_scores_gemma":[0.00018400114,0.00012852428,0.00001595642,0.0003931833,0.000007050302,0.00065240025,0.0002063066,0.00013866718,0.000009495482],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011429166,0.00046730883,0.0016356804,0.00005621812,0.000020195977,0.0000264113,0.0007260595,0.29926318,0.03521806,0.005309547,0.0012510533,0.65601486],"study_design_scores_gemma":[0.00024992312,0.00007932397,0.0014982442,0.00006056823,0.0000024127148,0.000003562429,0.000023491166,0.9887171,0.004013795,0.000047624922,0.0051744627,0.00012948825],"about_ca_topic_score_codex":0.000014911561,"about_ca_topic_score_gemma":0.000004931594,"teacher_disagreement_score":0.6894539,"about_ca_system_score_codex":0.0000328014,"about_ca_system_score_gemma":0.000021571055,"threshold_uncertainty_score":0.52410674},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33734378,0.00001876394,0.6616148,0.00028050476,0.000042237672,0.00029161855,0.00008118602,0.00004091875,0.00028618693],"genre_scores_gemma":[0.57807034,0.000010970086,0.42160705,0.000063560256,0.000015687698,0.000105162,0.00002350837,0.000005734323,0.000098012875],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988819,0.000017179893,0.00033057813,0.00035569642,0.00018448175,0.00023016638],"domain_scores_gemma":[0.9992143,0.00013942698,0.00009646153,0.00045533196,0.000024148547,0.00007033957],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017765716,0.00011441739,0.00017226239,0.00011081814,0.00006596172,0.00001548486,0.00043371107,0.000038538037,0.000022462373],"category_scores_gemma":[0.000015866775,0.000104747975,0.000054340708,0.00016085741,0.00007310743,0.000054393255,0.00013019083,0.000048676327,0.0000057572456],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024631861,0.0044317134,0.009818974,0.00013639846,0.00014441175,0.000103673025,0.014135911,0.032610476,0.011864373,0.02186604,0.002353589,0.9025098],"study_design_scores_gemma":[0.00086275866,0.00013682462,0.0061566853,0.000029133356,0.0000046710065,0.000021828251,0.0003538366,0.9865123,0.005347842,0.0000400769,0.0003593428,0.00017472477],"about_ca_topic_score_codex":0.00010855035,"about_ca_topic_score_gemma":0.000007212952,"teacher_disagreement_score":0.9539018,"about_ca_system_score_codex":0.000040588096,"about_ca_system_score_gemma":0.000050383645,"threshold_uncertainty_score":0.42714986},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02203212,0.000012245624,0.96112496,0.0019122709,0.00012322472,0.00021937453,0.0000068094164,0.00049633963,0.014072661],"genre_scores_gemma":[0.3544986,5.4219447e-7,0.6428737,0.00049867673,0.000032015443,0.00015528199,0.000005518264,0.0000061220376,0.0019295403],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990452,0.0000162446,0.00018237325,0.0003496989,0.00013261393,0.00027389397],"domain_scores_gemma":[0.9990882,0.00006906823,0.000030737214,0.00059335574,0.0000626377,0.00015597377],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00014673956,0.000096506395,0.00010654661,0.00008404217,0.00014125677,0.00033251767,0.0007818606,0.000024461919,0.000051022504],"category_scores_gemma":[0.000016039776,0.000081696926,0.000025969166,0.00035555044,0.000011288021,0.00043746567,0.00030277407,0.00004891052,0.00235514],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.2957227e-7,0.000017737964,0.00015679169,0.000014104823,0.000010466844,0.0000025150491,0.0010233403,0.00004840981,0.0005918753,0.017507724,0.053009797,0.92761713],"study_design_scores_gemma":[0.00015787539,0.00006204382,0.0027014469,0.000054208664,0.000004404465,0.000033092645,0.0008504059,0.91161186,0.00095464796,0.00019546511,0.083000906,0.00037364673],"about_ca_topic_score_codex":0.0006335746,"about_ca_topic_score_gemma":0.000013046852,"teacher_disagreement_score":0.9272435,"about_ca_system_score_codex":0.00003371154,"about_ca_system_score_gemma":0.000023965058,"threshold_uncertainty_score":0.99842167},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010265849,0.00007493906,0.9276432,0.058523163,0.00031856485,0.00020386372,0.000018103054,0.00048391815,0.0024684002],"genre_scores_gemma":[0.11913334,0.00011936485,0.85886055,0.016744027,0.0007241712,0.00047996832,0.00014745911,0.000036455596,0.0037546493],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987483,0.000035368914,0.00025538987,0.00043096757,0.0002444575,0.00028550188],"domain_scores_gemma":[0.99775344,0.00010791281,0.00006823026,0.0018747628,0.0000861102,0.0001095665],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00009131375,0.00015016586,0.00012863765,0.00012416071,0.0005236179,0.00014225353,0.001569447,0.000053848824,0.000079138255],"category_scores_gemma":[0.00009057507,0.00014374351,0.00006161067,0.0006272701,0.0000870205,0.0014797566,0.00041526818,0.0001525293,0.0024770172],"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":[8.723085e-7,0.00010844616,0.0003528106,0.0000020265318,0.000016224145,0.000034496046,0.0013722066,0.000054755616,0.0019942163,0.015017623,0.96312726,0.017919093],"study_design_scores_gemma":[0.00048543853,0.000068043075,0.0032650428,0.000011870335,0.000010530563,0.00017840437,0.00006679335,0.015713891,0.004100855,0.005662871,0.969869,0.0005672364],"about_ca_topic_score_codex":0.000026595475,"about_ca_topic_score_gemma":0.0000070395395,"teacher_disagreement_score":0.108867496,"about_ca_system_score_codex":0.000025480893,"about_ca_system_score_gemma":0.00007354696,"threshold_uncertainty_score":0.99829966},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012531227,0.0000044194567,0.98229533,0.00029982952,0.00012784661,0.000058538997,0.000020483554,0.00011294157,0.015827497],"genre_scores_gemma":[0.29813752,5.605356e-7,0.7014985,0.00014472353,0.00008953187,0.000002346846,0.000056207475,0.0000032730804,0.000067316956],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99929005,0.00002864133,0.00013088911,0.0003277057,0.000100077494,0.00012262797],"domain_scores_gemma":[0.9988329,0.000100455974,0.000065516804,0.0009084699,0.000048524493,0.00004415673],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026503782,0.00006179773,0.00007328216,0.000029011639,0.00014037428,0.00020067228,0.00090040924,0.000023700864,0.00001630202],"category_scores_gemma":[0.00006462508,0.0000563051,0.000009312338,0.00015646406,0.00004331676,0.0007980456,0.00038969342,0.000053079733,0.000042825974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.8863775e-7,0.000008661425,0.00006807978,0.0000010499513,0.0000045252964,2.864599e-7,0.0000550976,0.000015568517,0.00062927924,0.6167608,0.0007025682,0.38175383],"study_design_scores_gemma":[0.00008319979,0.00001114553,0.00007956529,0.0000054794327,0.0000034433901,0.000011853949,0.000072775736,0.9930126,0.001237777,0.001891652,0.003503992,0.00008648999],"about_ca_topic_score_codex":0.00016472234,"about_ca_topic_score_gemma":0.000020227364,"teacher_disagreement_score":0.99299705,"about_ca_system_score_codex":0.000014216493,"about_ca_system_score_gemma":0.000038216906,"threshold_uncertainty_score":0.22960553},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000323286,0.00009049882,0.9976969,0.00077162747,0.00036185593,0.00015167148,0.0002593442,0.00019153135,0.00015333177],"genre_scores_gemma":[0.01797912,0.0000022839147,0.98017126,0.00026921765,0.00037493257,0.000043109274,0.00069297384,0.000008905351,0.00045816528],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900484,0.0000166853,0.00012977526,0.0003789112,0.00016508593,0.00030469068],"domain_scores_gemma":[0.9982533,0.0000741591,0.00003974451,0.0014177089,0.000054208016,0.00016089685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003392427,0.000093189126,0.00008359989,0.00004173613,0.00020927828,0.00008624557,0.001362831,0.000035850433,0.000023069297],"category_scores_gemma":[0.000010739584,0.00008392575,0.000015605638,0.00015569261,0.000024131798,0.0021499384,0.0007224648,0.000050806295,0.00006074056],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001221685,0.00026345075,0.00009201302,0.000004380533,0.000014790439,5.115057e-7,0.0000824444,0.00006378511,0.00031720888,0.077506065,0.04825278,0.87340134],"study_design_scores_gemma":[0.00014778954,0.000029127386,0.0022531506,0.0000032048,0.0000048162365,0.000018436827,0.000014677003,0.9715245,0.000120730314,0.00041042696,0.02533841,0.0001347637],"about_ca_topic_score_codex":0.00009577401,"about_ca_topic_score_gemma":0.0000058751993,"teacher_disagreement_score":0.9714607,"about_ca_system_score_codex":0.000021094493,"about_ca_system_score_gemma":0.000040891944,"threshold_uncertainty_score":0.34223926},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21294737,0.000092417205,0.78518575,0.000014101319,0.00016424306,0.00005760756,0.0014599231,0.000051750674,0.00002679902],"genre_scores_gemma":[0.9726999,0.00019597157,0.026966684,0.000010686461,0.000027651768,0.000015118706,0.000059748923,0.000009466268,0.000014803591],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921966,0.0000107921815,0.00017368246,0.0003918775,0.000070701884,0.00013328837],"domain_scores_gemma":[0.9990593,0.000084898056,0.00003512103,0.0007328745,0.000024841576,0.00006294543],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000082200226,0.00012621337,0.00014012282,0.00008788722,0.00006611582,0.00007266929,0.00056529936,0.00004339957,0.000005742747],"category_scores_gemma":[0.000002830996,0.00011865254,0.00001856895,0.00011105419,0.000021948592,0.0009402006,0.000028144792,0.00011358203,0.0000035438736],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016029982,0.000660152,0.0012638138,0.00022685269,0.00027354844,0.00001880547,0.0063498663,0.00016364297,0.01894037,0.0019816298,0.00012015768,0.9699851],"study_design_scores_gemma":[0.0007972752,0.00019536527,0.024033811,0.00042180324,0.000104744446,0.000024419467,0.00022230175,0.8538889,0.11902941,0.00016486984,0.00045214497,0.00066490535],"about_ca_topic_score_codex":0.0006231207,"about_ca_topic_score_gemma":0.0001251101,"teacher_disagreement_score":0.96932024,"about_ca_system_score_codex":0.000007019673,"about_ca_system_score_gemma":0.000020526792,"threshold_uncertainty_score":0.48385102},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022140542,0.000009250946,0.9763601,0.0005512847,0.00015561812,0.00014445289,0.00008847564,0.00016036726,0.00038990102],"genre_scores_gemma":[0.7572133,0.0000054931284,0.24192137,0.00054525235,0.00008881199,0.000023053537,0.00016277627,0.0000099344525,0.00003003623],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998382,0.00009152808,0.00029167795,0.00054445537,0.000451428,0.00023896279],"domain_scores_gemma":[0.9983481,0.00055161386,0.00009830904,0.00056211726,0.00027608985,0.00016373378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016965372,0.00017741673,0.00015877186,0.00015765405,0.0002935485,0.00016113781,0.0009863214,0.00004828482,0.00003494152],"category_scores_gemma":[0.00006108749,0.00016739365,0.000054260145,0.00048261991,0.00014198036,0.00032000782,0.000116171504,0.00032243616,0.00016244216],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003193426,0.0006101115,0.00055272557,0.000010201551,0.00001703297,0.00007159942,0.001053451,0.186186,0.000050749022,0.030026745,0.00032949424,0.78106],"study_design_scores_gemma":[0.00006108353,0.00023174872,0.023752159,0.000037272326,0.0000023746234,0.000046362937,0.000035084835,0.97101426,0.0006606682,0.0032998614,0.0006526882,0.00020642526],"about_ca_topic_score_codex":0.000023622404,"about_ca_topic_score_gemma":0.0000021247606,"teacher_disagreement_score":0.78482825,"about_ca_system_score_codex":0.00008376784,"about_ca_system_score_gemma":0.00026680055,"threshold_uncertainty_score":0.6826115},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000724841,0.0010408763,0.9943326,0.00059636286,0.000025161853,0.0017181049,0.00022779657,0.00013934578,0.001194893],"genre_scores_gemma":[0.3231931,0.000046054418,0.67106056,0.000084535066,0.00020888771,0.0049084984,0.0001317314,0.000019229901,0.00034740815],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99851805,0.00003150382,0.0005637953,0.00043546493,0.00023395916,0.00021722235],"domain_scores_gemma":[0.9976804,0.00031541102,0.00045359536,0.0011246203,0.00033332163,0.00009261455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003454324,0.00015639229,0.00029767372,0.00015496454,0.00018996137,0.0000473187,0.000948435,0.0000595802,0.0000016779833],"category_scores_gemma":[0.000022570013,0.00013721776,0.000065001244,0.00063937315,0.00007622449,0.00018052713,0.00005809431,0.000056444413,0.0000025137426],"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":[0.000038738603,0.0013183611,0.00036991606,0.00030866545,0.00011745577,3.9704128e-7,0.0017491216,0.0003357369,0.026627338,0.37754723,0.011748005,0.57983905],"study_design_scores_gemma":[0.0013374974,0.0004006474,0.0018324638,0.0004203708,0.000051397976,0.00004400102,0.0020741425,0.18359211,0.0036059767,0.0008337071,0.80509526,0.0007124411],"about_ca_topic_score_codex":0.000034567747,"about_ca_topic_score_gemma":0.000006690504,"teacher_disagreement_score":0.79334724,"about_ca_system_score_codex":0.000027848384,"about_ca_system_score_gemma":0.00014434739,"threshold_uncertainty_score":0.5595578},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014512908,0.00008646582,0.99511534,0.00066179375,0.0016026977,0.00017344525,0.000013528624,0.00003141509,0.00086400536],"genre_scores_gemma":[0.91499007,0.000015007345,0.08360515,0.0010362469,0.00028658783,0.000010162961,0.000017494325,0.0000075657485,0.000031693387],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99776924,0.00012259596,0.0013413974,0.000083860614,0.0004592095,0.00022367398],"domain_scores_gemma":[0.9972278,0.00041775606,0.0012124147,0.00035500102,0.00068114506,0.000105919244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043184906,0.00013161825,0.0001998215,0.00026875926,0.0001439289,0.0005916406,0.0010780619,0.00006285728,0.000012460206],"category_scores_gemma":[0.00012346746,0.000085355416,0.00013003223,0.0003424875,0.000055572404,0.0012484695,0.00007966897,0.00021887553,0.000069718546],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000047264193,0.000037892398,0.00037671454,0.000043108037,0.00006198786,0.0000055561018,0.0027920238,0.00068335194,0.00011705641,0.0035876706,0.0039104186,0.9883795],"study_design_scores_gemma":[0.0011069379,0.00043846914,0.0011822326,0.00051557634,0.00006754164,0.0016405502,0.011587834,0.55915153,0.03624678,0.0001237932,0.38733628,0.0006024632],"about_ca_topic_score_codex":0.000052932843,"about_ca_topic_score_gemma":0.0000013490951,"teacher_disagreement_score":0.98777705,"about_ca_system_score_codex":0.00008995743,"about_ca_system_score_gemma":0.00014603799,"threshold_uncertainty_score":0.5705204},"labels":[],"label_agreement":null},{"id":"W2054521721","doi":"10.1007/s10115-009-0245-8","title":"Mining incomplete survey data through classification","year":2009,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint Mary's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Missing data; Data mining; Computer science; Classifier (UML); Complete information; Data set; Artificial intelligence; Machine learning; Mathematics","score_opus":0.11564483165384673,"score_gpt":0.3234492842129648,"score_spread":0.20780445255911809,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054521721","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019228609,0.00051022734,0.95118356,0.0003523874,0.00039017378,0.00025843864,0.00014575032,0.0001982892,0.045038328],"genre_scores_gemma":[0.9741927,0.000110731606,0.023534935,0.0002604011,0.0001259238,0.000021672005,0.0015899357,0.000003533229,0.00016016008],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990896,0.000062942854,0.00038671313,0.00019397514,0.00013050946,0.00013628909],"domain_scores_gemma":[0.99862367,0.00008506371,0.00016546506,0.000908927,0.00016256663,0.000054317617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076240284,0.000092617076,0.00012388726,0.00007432222,0.00019991024,0.0005544264,0.000829316,0.000047179223,0.0000010063633],"category_scores_gemma":[0.00006347284,0.00008305009,0.000009601961,0.0003940124,0.000018485616,0.007777039,0.0002056111,0.00005653798,0.00018531192],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028034056,0.000053656466,0.0007877338,0.00004946192,0.000014331264,2.0131475e-7,0.00693646,0.000009888283,0.00004569829,0.25161406,0.072211854,0.66827387],"study_design_scores_gemma":[0.00015019129,0.000026955582,0.034887843,0.000027303073,0.0000022641977,0.000011116078,0.00021622956,0.54174864,0.0000069789107,0.00006968384,0.4227348,0.000118013704],"about_ca_topic_score_codex":0.00006196569,"about_ca_topic_score_gemma":0.000006809192,"teacher_disagreement_score":0.97226983,"about_ca_system_score_codex":0.000018022833,"about_ca_system_score_gemma":0.00004826876,"threshold_uncertainty_score":0.56381655},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023475265,0.0000067573637,0.97264653,0.0003615473,0.000074835494,0.00006268395,0.000029779374,0.00013656456,0.0032060395],"genre_scores_gemma":[0.6846798,0.000001931633,0.3144177,0.00020320289,0.00004274224,0.000024952913,0.000063971194,0.000004526654,0.00056119246],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99917835,0.000024600797,0.00015747348,0.00030277862,0.00016687442,0.00016993724],"domain_scores_gemma":[0.9990692,0.0003041383,0.00005457694,0.0004411419,0.000053608153,0.00007734799],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001718589,0.00007935504,0.000079983576,0.000025422096,0.00018981342,0.00018167756,0.00046328764,0.000021734942,0.000034118297],"category_scores_gemma":[0.00008232629,0.00006894698,0.000014331154,0.00012057992,0.000033485932,0.00024277682,0.00012255096,0.00003438909,0.00017100575],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035870166,0.00012514024,0.056938205,0.00003475415,0.000017016442,0.0000020010698,0.0009195084,0.00010612067,0.00039189396,0.40321562,0.013784834,0.5244613],"study_design_scores_gemma":[0.00026205156,0.00005447538,0.05255712,0.000015470609,0.0000042607307,0.0000052588935,0.000072428695,0.90093964,0.00057193614,0.0030749904,0.0422144,0.0002279681],"about_ca_topic_score_codex":0.00005322493,"about_ca_topic_score_gemma":0.00028928666,"teacher_disagreement_score":0.90083355,"about_ca_system_score_codex":0.00002654425,"about_ca_system_score_gemma":0.000014019103,"threshold_uncertainty_score":0.28115764},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00046580675,0.000016245034,0.98354715,0.004329015,0.00016121555,0.00020403625,0.00002365786,0.0003311334,0.010921757],"genre_scores_gemma":[0.1473191,0.000003065685,0.8501379,0.00040002164,0.0002587522,0.00021844728,0.00014370852,0.000009564141,0.0015094313],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990544,0.000025053187,0.00021806943,0.00035344844,0.00017185726,0.00017718082],"domain_scores_gemma":[0.99883235,0.00038960006,0.00014971178,0.0004445235,0.00012759813,0.000056195706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036801127,0.00009074396,0.00008347236,0.00006390043,0.00049966824,0.00018117264,0.000414324,0.00005501311,0.00000741278],"category_scores_gemma":[0.0003266884,0.00008375994,0.000048706337,0.00026897225,0.00003021788,0.0004933949,0.000081387254,0.00009478852,0.00003472208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.7818853e-7,0.000025374631,0.00019594046,0.0000059455488,0.000007139325,3.7842007e-8,0.00013911516,0.00020494933,0.00030016905,0.7638538,0.012647788,0.22261888],"study_design_scores_gemma":[0.00019398164,0.000040076924,0.010057337,0.000023951741,0.0000059917074,0.000010228567,0.000028708911,0.94209296,0.0002717095,0.006555648,0.04060279,0.00011660549],"about_ca_topic_score_codex":0.00001602267,"about_ca_topic_score_gemma":0.0000069684356,"teacher_disagreement_score":0.94188803,"about_ca_system_score_codex":0.000027041884,"about_ca_system_score_gemma":0.000038466824,"threshold_uncertainty_score":0.38430944},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004101153,0.000019883777,0.98336047,0.011394406,0.00059295644,0.00011953028,0.000012917735,0.000014320631,0.00038436468],"genre_scores_gemma":[0.5969922,0.00019475633,0.4006291,0.001677231,0.0002915308,0.000023863939,0.00009361452,0.000009096777,0.000088590685],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988598,0.000018778372,0.000400808,0.00022221245,0.0003948757,0.00010350399],"domain_scores_gemma":[0.99821866,0.00013499841,0.0004852879,0.00024244211,0.0008817404,0.000036856927],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068043073,0.00009425688,0.00013849701,0.00027998714,0.000049261387,0.00037238092,0.0013288193,0.000050057748,0.0000041395665],"category_scores_gemma":[0.00048606185,0.00007997889,0.000019052895,0.00038800293,0.0000104381725,0.0010331192,0.00021314813,0.00009894462,0.0000012486431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035670506,0.00010852851,0.0009505735,0.000072160656,0.00012751452,0.0000051348616,0.0008201549,0.00087822106,0.000030261675,0.2786204,0.0010133031,0.7173381],"study_design_scores_gemma":[0.0015567015,0.000060327977,0.022244647,0.0007020211,0.000060929902,0.000041982166,0.0007518242,0.7991972,0.00022401282,0.1497876,0.02509979,0.00027297926],"about_ca_topic_score_codex":0.000015224522,"about_ca_topic_score_gemma":0.000044031633,"teacher_disagreement_score":0.798319,"about_ca_system_score_codex":0.00007587688,"about_ca_system_score_gemma":0.00003819943,"threshold_uncertainty_score":0.3590878},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016229575,0.00017204993,0.9777445,0.00016927155,0.0007680521,0.00023306363,0.00002595973,0.000054421536,0.0046030763],"genre_scores_gemma":[0.7208874,0.000040953375,0.2779057,0.00024285163,0.0006313148,0.000036952824,0.00015240902,0.000011952066,0.000090431065],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974163,0.000050396622,0.0015178676,0.00014408855,0.0006123146,0.00025901786],"domain_scores_gemma":[0.99739945,0.00021836117,0.001375314,0.00044934367,0.00044230075,0.00011521989],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009290083,0.00017285046,0.00031054963,0.0007341002,0.00019157442,0.0013421789,0.0013073146,0.00009031247,0.000006138812],"category_scores_gemma":[0.00008977762,0.00014000869,0.00014257354,0.00079576595,0.000030332521,0.0047639017,0.00020781919,0.00017710238,0.000034796285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009405106,0.00046181903,0.0004567591,0.00015089552,0.000273661,0.000019331468,0.025571179,0.09854322,0.00025947444,0.0840896,0.06782195,0.72225803],"study_design_scores_gemma":[0.00065415323,0.00007495996,0.0002805672,0.00042141593,0.000025411415,0.00038740956,0.0051221214,0.9573712,0.0005472272,0.00070452574,0.034137618,0.00027338765],"about_ca_topic_score_codex":0.00013051524,"about_ca_topic_score_gemma":0.0000037033597,"teacher_disagreement_score":0.858828,"about_ca_system_score_codex":0.000116390635,"about_ca_system_score_gemma":0.000110231136,"threshold_uncertainty_score":0.9996945},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00594314,0.000009873077,0.9907328,0.00122839,0.00013393282,0.00023709678,0.0010976446,0.00017880196,0.0004383414],"genre_scores_gemma":[0.5061181,0.000004750497,0.49251047,0.00026990904,0.00005641468,0.00004900195,0.000949941,0.000007564893,0.000033809996],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865687,0.000028801318,0.00025149307,0.00060594856,0.000142939,0.00031393333],"domain_scores_gemma":[0.99793583,0.00029458816,0.000094743344,0.0015209614,0.000053381853,0.000100511636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050690764,0.00012753592,0.00015906432,0.000040145398,0.00019803617,0.00027886394,0.0017985761,0.000040556086,0.000021579335],"category_scores_gemma":[0.00012419076,0.00011522235,0.0000301612,0.0001640189,0.000054416756,0.0004416531,0.000576938,0.0000611556,0.000018566881],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.8553624e-7,0.00005746917,0.0030834966,0.000025121333,0.00003044317,0.0000017817986,0.0001374304,0.000059847156,0.00037668212,0.07690285,0.008244242,0.91107994],"study_design_scores_gemma":[0.0003764416,0.000035659275,0.0043031913,0.000036435482,0.0000101937485,0.000010406906,0.000085112835,0.97411674,0.00035274905,0.00069193135,0.01975562,0.00022550457],"about_ca_topic_score_codex":0.000101812,"about_ca_topic_score_gemma":0.000035964666,"teacher_disagreement_score":0.9740569,"about_ca_system_score_codex":0.000025199974,"about_ca_system_score_gemma":0.000060668997,"threshold_uncertainty_score":0.4698631},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007077262,0.000051338873,0.9921492,0.00011648136,0.0001131526,0.00014682638,0.00016049613,0.00012389067,0.00006138504],"genre_scores_gemma":[0.8807807,0.00007153591,0.1188743,0.000022714064,0.000027521746,0.000069964684,0.00008167647,0.000011368979,0.000060195838],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992233,0.000012224949,0.00015937124,0.00037636838,0.00008048425,0.00014824641],"domain_scores_gemma":[0.9991368,0.00015517845,0.000024930017,0.00052364334,0.000051179246,0.000108255874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011727288,0.000114962895,0.00009376403,0.00009814605,0.00013033334,0.00022394022,0.00030636482,0.00003731944,0.000011627266],"category_scores_gemma":[0.000008127247,0.00011407876,0.000007502587,0.0001695901,0.000019341596,0.0008171042,0.000011441905,0.0000997757,0.00003845317],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.605554e-7,0.00008008433,0.000034210585,0.00008493797,0.000020791433,0.0000011765535,0.0005016862,0.00062279555,0.0016212736,0.0026253646,0.0005480857,0.99385864],"study_design_scores_gemma":[0.00014625283,0.000037917078,0.0019614056,0.000047600268,0.000011971602,0.0000072552252,0.000039687326,0.99557483,0.0011556799,0.000042123687,0.00082246534,0.00015280042],"about_ca_topic_score_codex":0.000049297883,"about_ca_topic_score_gemma":0.000009099314,"teacher_disagreement_score":0.994952,"about_ca_system_score_codex":0.000013878166,"about_ca_system_score_gemma":0.000022228054,"threshold_uncertainty_score":0.46519968},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004778486,0.0000071481127,0.97802985,0.002177563,0.000016324326,0.00015121054,0.00010295873,0.00008616852,0.014650285],"genre_scores_gemma":[0.21651627,0.0000044385697,0.78278196,0.00021759555,0.00001819263,0.000041701558,0.00003246141,0.000005345392,0.0003820091],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992031,0.00005040712,0.00010914822,0.0002997258,0.0002029817,0.00013462659],"domain_scores_gemma":[0.9990591,0.00026448618,0.00007759332,0.00019944446,0.0002536424,0.00014577841],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019405838,0.00008622043,0.00009799677,0.00003278895,0.00008728132,0.00018600392,0.00021924033,0.000025117066,0.0000031009167],"category_scores_gemma":[0.0000983101,0.0000625246,0.000006952851,0.00017568578,0.00009794924,0.00037563525,0.000087565306,0.00006783313,0.000039012637],"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":[0.0000062782447,0.00006109996,0.00041806055,0.0000012144487,0.000025510388,0.0000036104832,0.0021571892,0.0000012270606,0.00009867547,0.89132446,0.0019350684,0.103967614],"study_design_scores_gemma":[0.0012965782,0.0008757982,0.25391376,0.00003723655,0.00003700227,0.000019039046,0.0041875597,0.65812606,0.0014681063,0.07765202,0.0017923161,0.0005944972],"about_ca_topic_score_codex":0.00013285826,"about_ca_topic_score_gemma":0.0000166082,"teacher_disagreement_score":0.8136724,"about_ca_system_score_codex":0.000049179253,"about_ca_system_score_gemma":0.00011296492,"threshold_uncertainty_score":0.25496793},"labels":[],"label_agreement":null},{"id":"W2063529879","doi":"10.1145/358108.358114","title":"Beyond intratransaction association analysis","year":2000,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":153,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Badan Riset dan Inovasi Nasional; Helsingin Yliopisto","keywords":"Association rule learning; Apriori algorithm; Database transaction; Computer science; Association (psychology); Transaction data; Affinity analysis; Data mining; Data science; Psychology; Database","score_opus":0.007761500766622136,"score_gpt":0.22556361950399387,"score_spread":0.21780211873737174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063529879","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015007339,0.000010560898,0.98804486,0.0008291939,0.0003739925,0.00023863722,0.00015510058,0.00036351517,0.008483386],"genre_scores_gemma":[0.96814173,0.00009958945,0.028510453,0.0005184757,0.000071976436,0.0003180427,0.00023308664,0.000009193347,0.002097438],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984878,0.00006256729,0.0005343498,0.00020282112,0.0004873721,0.00022509458],"domain_scores_gemma":[0.99853873,0.000121660145,0.00018499605,0.00090714113,0.00015250593,0.00009493841],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00044545846,0.00014241681,0.00019168301,0.00045098594,0.0003719051,0.0006408253,0.0006646636,0.00012170147,0.00022739782],"category_scores_gemma":[0.000011826205,0.00014243719,0.00014295486,0.0019708816,0.000011363486,0.0036280658,0.000003173706,0.00018603315,0.0014623494],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008188953,0.000088817236,0.000059677008,0.00001586168,0.00043040194,3.1112816e-7,0.0013480736,0.078483604,0.000012349273,0.003929523,0.0012321192,0.9143911],"study_design_scores_gemma":[0.00083048415,0.00013870944,0.002892619,0.00002539555,0.00039002832,0.000018420966,0.00046111434,0.7025983,0.00055506214,0.00060145,0.29088488,0.0006035568],"about_ca_topic_score_codex":0.00020368795,"about_ca_topic_score_gemma":0.000013786857,"teacher_disagreement_score":0.966641,"about_ca_system_score_codex":0.00020994928,"about_ca_system_score_gemma":0.000040362615,"threshold_uncertainty_score":0.99931514},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6896045,0.000032956486,0.30711597,0.0013411596,0.0002875429,0.0001334093,0.000022108952,0.00018356844,0.0012787537],"genre_scores_gemma":[0.61931324,0.00010506283,0.37640244,0.00069368235,0.00044217455,0.00009794698,0.000100548634,0.000017819668,0.0028270532],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989803,0.000030291929,0.00019902976,0.00040919226,0.00015403325,0.00022714857],"domain_scores_gemma":[0.9987328,0.000033455995,0.00005686031,0.001060004,0.00002970633,0.00008713994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013474518,0.00011607864,0.00011255265,0.00004543518,0.00017097693,0.00020534584,0.0009652141,0.00004245195,0.00023793364],"category_scores_gemma":[0.000019658053,0.00010761141,0.000034411893,0.00017630044,0.0000151309405,0.0004159127,0.00013660324,0.00007983806,0.00018090845],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.213145e-7,0.00002687723,0.0035855346,0.0000020625841,0.000008742509,0.0000038066444,0.00028930217,0.000028365346,0.00074799557,0.00037522844,0.0048564244,0.99007475],"study_design_scores_gemma":[0.0008090095,0.00023111899,0.011326788,0.000070521855,0.00002738519,0.000061190796,0.00005418539,0.75206536,0.00656089,0.0016767756,0.2262554,0.0008614005],"about_ca_topic_score_codex":0.0005004618,"about_ca_topic_score_gemma":0.00019154405,"teacher_disagreement_score":0.98921335,"about_ca_system_score_codex":0.000029781557,"about_ca_system_score_gemma":0.00003698879,"threshold_uncertainty_score":0.4388266},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39697894,0.000005476501,0.6020342,0.000097541924,0.00010954601,0.00004349958,0.0000050595404,0.00012718653,0.000598538],"genre_scores_gemma":[0.80765295,0.0000062171916,0.19162527,0.00021168365,0.00009484975,0.000010430594,0.000004115061,0.00000841752,0.00038606778],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896634,0.000033386666,0.00018810909,0.00031921573,0.00022780088,0.00026516092],"domain_scores_gemma":[0.99930215,0.00009808614,0.0001380026,0.0003160027,0.000083443825,0.000062320156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021838023,0.000099653356,0.00010457716,0.00006680464,0.00036631004,0.00012067827,0.00040345578,0.00004879288,0.00001701868],"category_scores_gemma":[0.000056104414,0.00009863216,0.000040209547,0.0002639197,0.000009426854,0.0007191701,0.00019140329,0.0000958333,0.000037197482],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001149696,0.00014919076,0.3575202,0.000013624886,0.00008651222,0.00005434443,0.014439231,0.00019995954,0.0047952463,0.00073800003,0.002160764,0.61984175],"study_design_scores_gemma":[0.0003113935,0.000041317428,0.03502951,0.000037721693,0.000011179772,0.00009457269,0.0006817494,0.95663357,0.005260848,0.000061964,0.0014651407,0.0003710371],"about_ca_topic_score_codex":0.00056621234,"about_ca_topic_score_gemma":0.000043661585,"teacher_disagreement_score":0.9564336,"about_ca_system_score_codex":0.0001652355,"about_ca_system_score_gemma":0.000041101368,"threshold_uncertainty_score":0.4022103},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3027301,0.00037917146,0.6943437,0.0008136738,0.00047388775,0.00019069981,0.00001094978,0.00017794849,0.0008799085],"genre_scores_gemma":[0.6214295,0.000001824499,0.3781925,0.000071313494,0.0001486965,0.0000041838207,0.00008303341,0.000003080097,0.00006581853],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991825,0.000034368597,0.00020878408,0.00027563772,0.00016599969,0.00013271117],"domain_scores_gemma":[0.99918675,0.00011101951,0.00014492223,0.00036455193,0.00015829263,0.000034472374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010134212,0.00008494516,0.00010810258,0.000052046318,0.00013674499,0.00017451616,0.0005074826,0.00005272384,0.00001427049],"category_scores_gemma":[0.000029420007,0.00007234881,0.000026866814,0.0003407545,0.000019551648,0.00042926756,0.00013324799,0.00013666926,0.000027496377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.1115994e-7,0.000050921608,0.00032911132,0.000004883851,0.000023163942,2.4885307e-7,0.00039770367,0.00012276902,0.25494424,0.070835695,0.012432673,0.66085786],"study_design_scores_gemma":[0.00010118076,0.000010919391,0.03959621,0.0000141659375,0.000003691079,0.0000015112912,0.000020328744,0.94978416,0.007995626,0.0017993818,0.0005816422,0.00009116162],"about_ca_topic_score_codex":0.0005155662,"about_ca_topic_score_gemma":0.0000073898377,"teacher_disagreement_score":0.94966143,"about_ca_system_score_codex":0.000020734837,"about_ca_system_score_gemma":0.000024683775,"threshold_uncertainty_score":0.29502988},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040279995,0.000017179384,0.9864359,0.0069270954,0.00040279215,0.0003300407,0.0015796812,0.000093143906,0.00018616197],"genre_scores_gemma":[0.08988326,0.0000027648584,0.90592104,0.0003816197,0.0010735806,0.000066192275,0.002335032,0.000016521242,0.00031997202],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984445,0.000043920016,0.00020695645,0.00085900596,0.0001465393,0.00029908278],"domain_scores_gemma":[0.9931252,0.002140257,0.000076643686,0.004532464,0.00006257057,0.00006284164],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0015422966,0.00010831429,0.00011895897,0.000032928583,0.00035672804,0.0005290019,0.00657079,0.000029120436,0.0000033428798],"category_scores_gemma":[0.0006138979,0.00007576597,0.00001944847,0.00013347517,0.000031112522,0.00051710993,0.0037271893,0.00008459516,0.0000063500934],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020366085,0.00001849467,0.00012716344,0.000013455097,0.000018185254,1.5083891e-7,0.00050292845,0.000045260284,0.0002204297,0.004941035,0.035165302,0.9589456],"study_design_scores_gemma":[0.00017660114,0.000028075992,0.00018438746,0.000053700725,0.000010449638,0.0000015813887,0.00037173298,0.944854,0.00030430785,0.0006400919,0.053261623,0.00011343374],"about_ca_topic_score_codex":0.0016957929,"about_ca_topic_score_gemma":0.0002772386,"teacher_disagreement_score":0.95883214,"about_ca_system_score_codex":0.000012016683,"about_ca_system_score_gemma":0.00006571897,"threshold_uncertainty_score":0.99880415},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008877703,0.00050250406,0.98822105,0.00082714856,0.0005941869,0.00036052224,0.00021067297,0.0001232661,0.00028291915],"genre_scores_gemma":[0.048975173,0.000016991136,0.9501262,0.00019135783,0.00030680632,0.00020716136,0.000051857693,0.000014609798,0.00010988603],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988362,0.00003086764,0.00025588623,0.00037120236,0.00022774302,0.00027808503],"domain_scores_gemma":[0.9990239,0.00024123174,0.00016948773,0.00036748854,0.00009461342,0.00010324737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003758098,0.0001287138,0.00018595069,0.00006319172,0.0002648887,0.00046907933,0.0003291845,0.00011904567,6.8351176e-7],"category_scores_gemma":[0.00007252519,0.000118295924,0.00004545382,0.00016707079,0.000014714804,0.00017727455,0.000057629262,0.000075516924,0.00001912815],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000046522564,0.00022899691,0.0022124737,0.00022373967,0.00012394435,0.000013794872,0.002351976,0.0026071072,0.0001027541,0.26527992,0.008249524,0.7186011],"study_design_scores_gemma":[0.0016809703,0.0002918801,0.014702875,0.0004470787,0.000052365318,0.00003367157,0.0004245103,0.8733344,0.00008106945,0.059081584,0.04909187,0.0007776875],"about_ca_topic_score_codex":0.000094565534,"about_ca_topic_score_gemma":0.00000265331,"teacher_disagreement_score":0.8707273,"about_ca_system_score_codex":0.0000804346,"about_ca_system_score_gemma":0.000065705884,"threshold_uncertainty_score":0.48239678},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35007855,0.000095425545,0.641925,0.0049559553,0.0005269002,0.0002676456,0.000097581375,0.00001642031,0.0020365473],"genre_scores_gemma":[0.95203835,0.00019555588,0.04750534,0.00011914167,0.000069972884,0.000002776809,0.000026701235,0.0000028009113,0.00003933894],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99795765,0.000056788038,0.0005674978,0.00006882946,0.0012249815,0.00012426668],"domain_scores_gemma":[0.99516886,0.00043643411,0.0003888334,0.00014634752,0.0037557085,0.00010379608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011397286,0.00005843041,0.00010916084,0.0006489212,0.000051013856,0.00034070047,0.00084139046,0.000025062567,0.0000611139],"category_scores_gemma":[0.0011170312,0.000047667472,0.00003825428,0.00038689506,0.00009328511,0.004571362,0.0003813587,0.000276137,0.000046897563],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016770544,0.00032892075,0.0018434555,0.0000485597,0.0003770616,0.00001699936,0.00376258,0.00016036248,0.003578845,0.07240752,0.017766032,0.899542],"study_design_scores_gemma":[0.0028812508,0.001388177,0.07505229,0.00061409967,0.000023211245,0.00068826147,0.0046079643,0.7919377,0.051534742,0.013609044,0.05720884,0.00045441915],"about_ca_topic_score_codex":0.00009291768,"about_ca_topic_score_gemma":9.2904287e-7,"teacher_disagreement_score":0.89908755,"about_ca_system_score_codex":0.000086242144,"about_ca_system_score_gemma":0.00019231292,"threshold_uncertainty_score":0.3314127},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01588852,0.000008161607,0.9535711,0.00018708126,0.000052278217,0.00015425759,0.0000037968477,0.0001992858,0.02993556],"genre_scores_gemma":[0.7207851,0.0000020753528,0.27835533,0.0007144814,0.000011802251,0.000045398854,0.000002023089,0.00000796339,0.00007581225],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974977,0.000007740079,0.00020423156,0.00086337293,0.0009454418,0.00048152258],"domain_scores_gemma":[0.9985003,0.00008710446,0.00007595711,0.0010548494,0.00009384924,0.00018793394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043577864,0.00016627516,0.00013447992,0.0003704883,0.0010699689,0.00022480011,0.0018524216,0.000045706074,0.0000061287456],"category_scores_gemma":[0.000025327863,0.00015087584,0.000041986572,0.0018237892,0.000194591,0.000503717,0.00021937474,0.00017407561,0.00024739653],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002716141,0.0004421712,0.000031824995,0.0000025709146,0.0000035328892,0.000014310179,0.0010792196,0.22130087,0.29128274,0.09732078,0.0022248742,0.38626996],"study_design_scores_gemma":[0.00023945804,0.000033000677,0.0005624774,0.000007054598,0.0000015839488,0.000010624939,0.0000025585734,0.9875297,0.006253455,0.0050384304,0.00012423749,0.0001974499],"about_ca_topic_score_codex":0.000004002629,"about_ca_topic_score_gemma":4.730644e-7,"teacher_disagreement_score":0.7662288,"about_ca_system_score_codex":0.00011544842,"about_ca_system_score_gemma":0.00034884264,"threshold_uncertainty_score":0.8229444},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21439926,0.041283466,0.69667166,0.0029851436,0.0020833355,0.0064104013,0.0023116516,0.0007227068,0.03313234],"genre_scores_gemma":[0.6774543,0.006834169,0.3069936,0.0005601042,0.0010804996,0.003097192,0.0018585281,0.000119456374,0.0020021703],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99686205,0.0003425706,0.0006987105,0.0014275984,0.00022856629,0.00044052265],"domain_scores_gemma":[0.9969053,0.00066336215,0.0006116478,0.0014235242,0.00016226899,0.00023386814],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0021003755,0.00038289354,0.00059913134,0.00019711434,0.00057495706,0.0004116947,0.0012315974,0.0002021172,0.0000033227175],"category_scores_gemma":[0.0007779156,0.00035079618,0.00007446211,0.0007755583,0.00005512388,0.0027488074,0.004140799,0.0002787736,0.00015562115],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002343047,0.00031433292,0.0044449386,0.00017035054,0.000112708294,0.0000027005963,0.030411886,1.9952465e-7,0.00039440242,0.010152288,0.014061409,0.93991137],"study_design_scores_gemma":[0.0038538438,0.003199786,0.46138605,0.020399002,0.0018127788,0.00023167118,0.028122233,0.28143704,0.0015359931,0.051222723,0.13801853,0.008780336],"about_ca_topic_score_codex":0.0000098188975,"about_ca_topic_score_gemma":0.000039234816,"teacher_disagreement_score":0.931131,"about_ca_system_score_codex":0.000204167,"about_ca_system_score_gemma":0.00007020217,"threshold_uncertainty_score":0.9998944},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3128001,0.0000072284415,0.68251246,0.0005090814,0.00036621542,0.00017961605,0.0000066652356,0.00006746393,0.003551188],"genre_scores_gemma":[0.9476888,0.000002647476,0.04953232,0.000015043655,0.0000109938655,0.000057367615,0.000003910426,0.0000019504728,0.0026869385],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99943745,0.00000701522,0.00021153365,0.00014939686,0.000115459916,0.00007916878],"domain_scores_gemma":[0.99946404,0.00003611599,0.000058688413,0.00036397768,0.000054674976,0.00002250294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023223598,0.00003821728,0.000055546217,0.0001282504,0.0000728704,0.0000934211,0.00032187806,0.000019246168,0.0000443836],"category_scores_gemma":[0.000021698736,0.00003575648,0.0000171951,0.00060516223,0.000032176205,0.00007848416,0.00007347702,0.000058925387,0.000020860403],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012461509,0.00041494987,0.0003766732,0.000011675242,0.000008746243,6.0367626e-7,0.0010289784,0.0016373121,0.10490837,0.8779941,0.002007753,0.011609571],"study_design_scores_gemma":[0.00018488191,0.000014410551,0.007417671,0.000004399514,0.0000023064688,0.0000028016966,0.000104343264,0.9687631,0.018631164,0.0029349527,0.0018599281,0.00008004548],"about_ca_topic_score_codex":0.00024834322,"about_ca_topic_score_gemma":0.00018330399,"teacher_disagreement_score":0.9671258,"about_ca_system_score_codex":0.000011605925,"about_ca_system_score_gemma":0.000036800706,"threshold_uncertainty_score":0.14581068},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01290823,0.00002029453,0.9802346,0.0003582075,0.000075276505,0.00009580721,0.00031378967,0.00009249587,0.0059012747],"genre_scores_gemma":[0.4542046,0.000003950682,0.54523444,0.00014290262,0.000012103407,0.000007174681,0.00036767847,0.0000036129338,0.000023512112],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907064,0.00002495301,0.0002634927,0.00031392105,0.00018969848,0.00013731894],"domain_scores_gemma":[0.99840814,0.00007457987,0.00009398885,0.0013091872,0.000056864374,0.000057217818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024629198,0.000081073966,0.00010187814,0.000050367893,0.00005558142,0.000042614447,0.0018628007,0.000034262564,0.000118647964],"category_scores_gemma":[0.000018885708,0.00007135912,0.00001818159,0.0002687505,0.000037565154,0.00093349034,0.00018875679,0.00004669878,0.000024037618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010434609,0.0005563309,0.0022898742,0.00005841352,0.00006776814,0.000008482727,0.009955445,0.00012953863,0.007856865,0.14094684,0.012455019,0.825665],"study_design_scores_gemma":[0.00024188893,0.000037859754,0.0035200499,0.000037797592,0.000010553493,0.0000012054932,0.00018791932,0.9786508,0.012675309,0.0009064948,0.0035774477,0.00015265978],"about_ca_topic_score_codex":0.0011035235,"about_ca_topic_score_gemma":0.000036251855,"teacher_disagreement_score":0.9785213,"about_ca_system_score_codex":0.000011862904,"about_ca_system_score_gemma":0.00006954,"threshold_uncertainty_score":0.34615782},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026216403,0.0000013313926,0.9670757,0.0059639052,0.00017737932,0.00005588615,0.000040835323,0.00008222585,0.00038630492],"genre_scores_gemma":[0.13160308,9.913331e-7,0.8675951,0.0001623852,0.0004240829,0.000004593682,0.00007588244,0.0000026945065,0.00013123742],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99938023,0.0000056804947,0.00006832825,0.000389482,0.000073450276,0.0000828237],"domain_scores_gemma":[0.99854195,0.000017792818,0.000016587113,0.001291143,0.000035140754,0.00009737589],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020715632,0.00004240629,0.000042446998,0.00004339819,0.00007688756,0.0001769739,0.0007638397,0.00001841764,0.000011132048],"category_scores_gemma":[0.00004428423,0.00003748367,0.0000028006286,0.00020271601,0.000019750134,0.00074161834,0.00039998718,0.000052651936,0.0000069473876],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015577293,0.00007323201,0.0006470963,0.0000017912722,0.00001069464,7.7547173e-7,0.00068790204,0.000027500819,0.006482872,0.030341731,0.08400758,0.87771726],"study_design_scores_gemma":[0.00003567453,0.00004973903,0.004232501,5.844177e-7,0.000003840191,0.000009102669,0.00007507055,0.95241106,0.00032737118,0.00015603137,0.04263629,0.00006276578],"about_ca_topic_score_codex":0.000013933395,"about_ca_topic_score_gemma":0.000047689842,"teacher_disagreement_score":0.9523835,"about_ca_system_score_codex":0.0000024409078,"about_ca_system_score_gemma":0.000015226331,"threshold_uncertainty_score":0.17065635},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08875743,0.0014709776,0.9033168,0.0005699631,0.0002847929,0.00037514602,0.0040439824,0.00025142846,0.00092949154],"genre_scores_gemma":[0.1743089,0.00008017158,0.81623673,0.00021230691,0.0008675541,0.00008900134,0.0066037513,0.000037461694,0.0015641352],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99811995,0.00003639669,0.00032358535,0.0010644912,0.00013542335,0.00032013608],"domain_scores_gemma":[0.9972936,0.000545241,0.00013728077,0.0018063417,0.00010918533,0.000108382286],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00069982145,0.00019567765,0.00019770193,0.00011097407,0.00069774076,0.001429673,0.0012900729,0.00006419804,0.0000040371633],"category_scores_gemma":[0.00024838504,0.00017862432,0.000017992803,0.0002800479,0.000115798444,0.0052845646,0.0011106314,0.00010190102,0.00000985934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005386461,0.0007510928,0.017438281,0.00024608758,0.00032036158,0.000008500019,0.008280898,0.0002714825,0.0005611802,0.024737516,0.2393409,0.7079898],"study_design_scores_gemma":[0.00055723544,0.00007047879,0.0005858307,0.00010678493,0.00004367554,0.000054722637,0.00036507583,0.89634115,0.00014626265,0.00007499569,0.10133401,0.00031979644],"about_ca_topic_score_codex":0.000019220372,"about_ca_topic_score_gemma":0.000543781,"teacher_disagreement_score":0.89606965,"about_ca_system_score_codex":0.000026954038,"about_ca_system_score_gemma":0.0002938526,"threshold_uncertainty_score":0.99960697},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006725533,0.000038537048,0.9873517,0.0032701269,0.000167255,0.00027565495,0.001347497,0.00021875145,0.00060493394],"genre_scores_gemma":[0.11531693,0.000003140152,0.88243985,0.0010558144,0.00014806227,0.000030551684,0.0008777568,0.0000064693604,0.00012141073],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984875,0.000016557207,0.00026386505,0.0007276822,0.00020037845,0.00030405517],"domain_scores_gemma":[0.9979336,0.00020205951,0.00007886141,0.0016088194,0.000056584024,0.000120036035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027759702,0.00014411993,0.00015591763,0.000048572507,0.00015547419,0.0002449417,0.0020302315,0.000044344484,0.00003131576],"category_scores_gemma":[0.000044583558,0.00012537508,0.00003790018,0.0001520486,0.00002763931,0.00017023094,0.00029680374,0.000060388687,0.00002039698],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018199836,0.00017913144,0.00004845365,0.0000029563541,0.000021885737,0.000006516974,0.00035304533,0.00034734557,0.00045353684,0.029270327,0.0074153165,0.96189964],"study_design_scores_gemma":[0.00039457178,0.00006582279,0.0007526639,0.000019426903,0.000009171422,0.0000042927036,0.00011247787,0.99069744,0.0002921559,0.0014317965,0.00602904,0.00019116273],"about_ca_topic_score_codex":0.000217703,"about_ca_topic_score_gemma":0.0000128426045,"teacher_disagreement_score":0.99035007,"about_ca_system_score_codex":0.00002567819,"about_ca_system_score_gemma":0.00007412005,"threshold_uncertainty_score":0.51126474},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022499064,0.000020103544,0.9725134,0.0011142371,0.000035178,0.00005317405,0.00013715052,0.000018733843,0.003608982],"genre_scores_gemma":[0.6097563,0.000011834503,0.38656795,0.0024844538,0.00011608124,0.000020557545,0.0006977926,0.000005797004,0.0003392649],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99959284,0.00000613265,0.000075763324,0.0001258466,0.00008574728,0.000113654445],"domain_scores_gemma":[0.9994743,0.00006643478,0.000012116708,0.00042669591,0.0000037222546,0.000016739677],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003856253,0.000034675562,0.000029213912,0.00002469276,0.0000709025,0.0002152477,0.0006753309,0.000009167068,0.000006657245],"category_scores_gemma":[0.0000073764713,0.000020740152,0.0000066754824,0.00015216647,0.000021132748,0.00028854978,0.00014050168,0.000043747532,0.00006528734],"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":[0.0000014440693,0.00014712973,0.0012335848,0.0000043191544,0.000005166121,0.00003160295,0.0019982366,0.000021261254,0.00053949794,0.52232265,0.07734851,0.3963466],"study_design_scores_gemma":[0.0003188739,0.000029162546,0.10132495,0.000015584254,0.0000029586968,0.000038958766,0.00061486906,0.046884265,0.0017896995,0.004708542,0.84401447,0.00025764175],"about_ca_topic_score_codex":0.00022263022,"about_ca_topic_score_gemma":0.00019683561,"teacher_disagreement_score":0.766666,"about_ca_system_score_codex":0.000004607704,"about_ca_system_score_gemma":0.0000070169576,"threshold_uncertainty_score":0.20756385},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003974,0.000017250297,0.9518491,0.00026539448,0.00033285213,0.00010722764,0.000036120615,0.00044662468,0.04297145],"genre_scores_gemma":[0.011451447,0.000005234364,0.9817613,0.00027027773,0.00013706494,0.00004663497,0.000027575246,0.000010294339,0.0062901964],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998934,0.000022078118,0.00019787173,0.00033493043,0.00024495434,0.0002661824],"domain_scores_gemma":[0.99916106,0.000062514104,0.000114667346,0.00047145187,0.0000895126,0.000100763056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027756568,0.00010439974,0.00010559976,0.00005934168,0.00013699304,0.00013541742,0.0005763398,0.000063380474,0.00011391496],"category_scores_gemma":[0.00003627806,0.000096277,0.000038824623,0.00030567986,0.000014155217,0.00043578364,0.00022587455,0.000080681355,0.00028388767],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.122796e-7,0.00019427543,0.005313088,0.0000030775136,0.000038619342,0.00000680629,0.0021974577,9.751213e-7,0.00014644198,0.020802565,0.016004596,0.9552915],"study_design_scores_gemma":[0.0009548562,0.00023536288,0.090876296,0.000030568102,0.00004036257,0.000037380847,0.0005246738,0.8085617,0.0054410296,0.0055793575,0.086869754,0.0008486777],"about_ca_topic_score_codex":0.00011834968,"about_ca_topic_score_gemma":0.000010109962,"teacher_disagreement_score":0.9544428,"about_ca_system_score_codex":0.000060434322,"about_ca_system_score_gemma":0.000042779997,"threshold_uncertainty_score":0.39260623},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009734278,0.000018878225,0.98291165,0.0031863223,0.00052288885,0.00030701084,0.0004986999,0.00022445833,0.002595789],"genre_scores_gemma":[0.13738473,0.000005112633,0.861248,0.00046499813,0.000091363094,0.000046837944,0.0003915829,0.0000096085905,0.00035773122],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884725,0.000010902301,0.00016989825,0.00055397593,0.00015498513,0.0002630138],"domain_scores_gemma":[0.99765134,0.00022889242,0.00008931335,0.0018532655,0.00006107198,0.00011612214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041831602,0.00011513622,0.00011642301,0.000045797136,0.00018529942,0.00031497542,0.0021742494,0.000054839344,0.0000708139],"category_scores_gemma":[0.00013000211,0.000098965116,0.000022929346,0.00017167132,0.00011046292,0.0005972378,0.00058151595,0.00010772583,0.00004341094],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.895018e-7,0.00003558055,0.0005541102,0.000007614315,0.000017124026,0.000003693943,0.0001473531,0.0000017627403,0.0019624727,0.117310286,0.029992444,0.84996706],"study_design_scores_gemma":[0.0009928802,0.000066106244,0.0028995604,0.00005565959,0.000023082303,0.0001312536,0.00024223846,0.6356229,0.006430681,0.006218904,0.3466055,0.0007112302],"about_ca_topic_score_codex":0.00010668697,"about_ca_topic_score_gemma":0.00011973917,"teacher_disagreement_score":0.84925586,"about_ca_system_score_codex":0.000008128263,"about_ca_system_score_gemma":0.000097603624,"threshold_uncertainty_score":0.40403324},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0573638,0.0029430047,0.31021187,0.17527705,0.0071178745,0.0006856674,0.00011442477,0.0002626918,0.4460236],"genre_scores_gemma":[0.177718,0.0017547258,0.66843706,0.0043235137,0.114177465,0.000025357254,0.000009955754,0.00006956575,0.03348438],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.999222,0.000029347553,0.00021488777,0.00011044435,0.00024621177,0.0001771418],"domain_scores_gemma":[0.9993014,0.00004365264,0.00013406249,0.00038639095,0.00005554119,0.00007899155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037992458,0.00007173858,0.00009362105,0.00004415265,0.00024092749,0.00013726774,0.0011593692,0.000023436603,0.0004003565],"category_scores_gemma":[0.000019829386,0.000046618152,0.00005713786,0.00022302689,0.00006789793,0.0002652276,0.000120803124,0.00020236424,0.00029927574],"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":[0.0000020321797,0.000070878115,0.000028195685,0.0000011399104,0.000015074799,0.0000030721378,0.0007742054,0.00019643297,0.0004742358,0.0051049404,0.13746569,0.8558641],"study_design_scores_gemma":[0.00019913571,0.000050555365,0.00048795654,0.000017155262,0.000010134446,0.00022618877,0.00012204866,0.003871036,0.0007705681,0.00078023435,0.9933832,0.00008176363],"about_ca_topic_score_codex":0.000009797195,"about_ca_topic_score_gemma":0.000005982624,"teacher_disagreement_score":0.8559176,"about_ca_system_score_codex":0.000024168332,"about_ca_system_score_gemma":0.00006805162,"threshold_uncertainty_score":0.43836233},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048356894,0.0003178061,0.98710215,0.000022780301,0.0000555286,0.00012898266,0.0000025183008,0.000040761555,0.007493775],"genre_scores_gemma":[0.0315905,0.00039345317,0.9679439,0.000018833467,0.000011221426,0.000028324252,0.0000013727321,0.0000053928593,0.0000069759994],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993341,0.000008224009,0.00025986606,0.00018967946,0.0000932583,0.000114852504],"domain_scores_gemma":[0.99933183,0.00016959873,0.0001319012,0.00032446577,0.0000142918525,0.000027900029],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015905913,0.00008584201,0.00017433304,0.00007251983,0.000034083667,0.000027240776,0.00027616313,0.000032202315,0.0000012377664],"category_scores_gemma":[0.00002155553,0.000079058016,0.000012493029,0.00030728237,0.00007725536,0.00019030897,0.00014331851,0.0000644154,9.60615e-7],"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":[0.0000011597573,0.000017996566,0.00004530171,0.00004670153,0.0000021125027,4.550447e-7,0.0003978943,0.0000916756,0.0028705443,0.2328793,0.0000023062435,0.7636446],"study_design_scores_gemma":[0.00066570396,0.000036235084,0.0009408743,0.00008559618,0.00001233737,0.00008845223,0.0012757394,0.43521068,0.004533737,0.55081975,0.006039643,0.00029126508],"about_ca_topic_score_codex":0.0000019766255,"about_ca_topic_score_gemma":0.000014213858,"teacher_disagreement_score":0.7633533,"about_ca_system_score_codex":0.000010980051,"about_ca_system_score_gemma":0.00000979897,"threshold_uncertainty_score":0.32238925},"labels":[],"label_agreement":null},{"id":"W2077378918","doi":"10.1007/s10115-009-0252-9","title":"A binary decision diagram based approach for mining frequent subsequences","year":2009,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Bottleneck; Data mining; Prefix; Sequence (biology); Binary decision diagram; Representation (politics); Theoretical computer science","score_opus":0.022212111231806726,"score_gpt":0.2688086613249732,"score_spread":0.2465965500931665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077378918","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023427026,0.0005378344,0.98941094,0.00010422267,0.00018089531,0.0004238867,0.00002169666,0.00011503381,0.0068628127],"genre_scores_gemma":[0.76550484,0.000026059073,0.23372617,0.00018063265,0.00009135356,0.00023867152,0.00015581852,0.0000030859117,0.000073366966],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918854,0.000018644381,0.0003473122,0.00015836339,0.00012768187,0.00015944528],"domain_scores_gemma":[0.9992609,0.00009758542,0.00012557895,0.00028300667,0.00015147027,0.00008147467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044678836,0.00010247224,0.00013411939,0.00015318675,0.00021863934,0.0004587353,0.00033551033,0.000054771073,4.845606e-7],"category_scores_gemma":[0.000037252263,0.0000833743,0.000034450146,0.00030844778,0.00001787585,0.002438879,0.000034566685,0.000039334165,0.000017851076],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000056299905,0.00008091303,0.00008453787,0.00009213775,0.000006432008,2.0459797e-7,0.0021498883,0.0005966033,0.000049260387,0.07816522,0.011430918,0.90733826],"study_design_scores_gemma":[0.0003070518,0.00012039115,0.000554992,0.00005017618,0.0000032855578,0.000007034547,0.0001866865,0.91639864,0.00004663195,0.000100969606,0.08210491,0.00011924623],"about_ca_topic_score_codex":0.0000068030695,"about_ca_topic_score_gemma":3.5168276e-7,"teacher_disagreement_score":0.915802,"about_ca_system_score_codex":0.000025348456,"about_ca_system_score_gemma":0.000059472924,"threshold_uncertainty_score":0.4423595},"labels":[],"label_agreement":null},{"id":"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0049862657,0.000009181553,0.99182934,0.001103641,0.0003815909,0.00011844598,0.0010585459,0.00014501836,0.0003679828],"genre_scores_gemma":[0.2234548,0.0000019020287,0.7746732,0.00027242393,0.00031492228,0.000015092572,0.0012157942,0.0000061201304,0.000045704714],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99818856,0.000019922889,0.00020937799,0.0010620849,0.00022064464,0.00029940167],"domain_scores_gemma":[0.9951888,0.00037491167,0.00009600876,0.004177676,0.00007003768,0.00009262292],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0013568056,0.0000961986,0.00010028083,0.00007388084,0.0003615796,0.0005564771,0.008207768,0.000022999991,0.0000038821686],"category_scores_gemma":[0.0006479081,0.00008500826,0.000010033063,0.000304517,0.00008433422,0.001946678,0.0056686304,0.000057033965,0.000016159294],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.8781706e-7,0.000021398113,0.00030724113,0.0000040413124,0.0000037792877,2.0601178e-7,0.000108803535,0.000004553914,0.0010093558,0.0050495802,0.0042085988,0.98928183],"study_design_scores_gemma":[0.00013447415,0.000020938485,0.00091090845,0.00003717446,0.0000055373057,0.0000019837396,0.000049424732,0.975168,0.00019619855,0.0006512811,0.022700088,0.00012402947],"about_ca_topic_score_codex":0.00090631924,"about_ca_topic_score_gemma":0.00033994942,"teacher_disagreement_score":0.9891578,"about_ca_system_score_codex":0.000021069212,"about_ca_system_score_gemma":0.00012053897,"threshold_uncertainty_score":0.9971583},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6607854,0.0027477907,0.32470787,0.0012573604,0.00091499323,0.0003636606,0.0015207056,0.00028103823,0.0074211974],"genre_scores_gemma":[0.87221664,0.00011215274,0.1262277,0.0001939572,0.000117547934,0.000029898445,0.0008815663,0.000018697156,0.00020183649],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99828464,0.000039980343,0.0003458346,0.00080896134,0.00014167384,0.00037893825],"domain_scores_gemma":[0.99839956,0.00017511212,0.00008984292,0.0011868125,0.00002910577,0.00011957618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006001483,0.00019144762,0.00023389122,0.00016794694,0.00017714754,0.00065966754,0.001370053,0.00006857543,0.000004163047],"category_scores_gemma":[0.00014292051,0.00018805717,0.000023018925,0.00044367544,0.00017196177,0.00269697,0.0012495891,0.0001384632,0.000029680255],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012813191,0.00073985674,0.0132841505,0.00015885325,0.00008887381,0.00016944093,0.021570122,0.000057247977,0.0015872726,0.06512616,0.010792939,0.88641226],"study_design_scores_gemma":[0.022787392,0.0010621059,0.077966504,0.009119489,0.0002618,0.0014824314,0.045048676,0.64900684,0.0069622556,0.011909976,0.16587628,0.00851623],"about_ca_topic_score_codex":0.00020480421,"about_ca_topic_score_gemma":0.0003767018,"teacher_disagreement_score":0.877896,"about_ca_system_score_codex":0.000050416453,"about_ca_system_score_gemma":0.00026076796,"threshold_uncertainty_score":0.7668749},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022160228,0.0010517694,0.97383106,0.00010526374,0.001999658,0.00008750457,0.00002025162,0.000015641657,0.0007285989],"genre_scores_gemma":[0.8596598,0.000012419465,0.14013876,0.000016194097,0.0001397559,0.000005881149,0.000006873857,0.0000053878084,0.000014959524],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99818677,0.00006347864,0.0008322149,0.00018164763,0.0006276952,0.000108209024],"domain_scores_gemma":[0.99789864,0.0002559332,0.00067375344,0.00012570767,0.0009645017,0.00008143873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000252623,0.00012141259,0.00022846281,0.00022714246,0.00006285664,0.00011306724,0.00091081037,0.00004011763,0.000018521096],"category_scores_gemma":[0.000047714915,0.00011346745,0.00007210392,0.00015142516,0.0001030982,0.000840224,0.00021307207,0.00013044673,0.000008098649],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00062980264,0.0017160872,0.0029106273,0.000056748846,0.0010873551,0.00009080906,0.038055852,0.28763852,0.0011353758,0.5755897,0.001950043,0.08913903],"study_design_scores_gemma":[0.00041146524,0.0004995081,0.0018848503,0.00017314976,0.000011570958,0.00033583955,0.0022128168,0.98481935,0.0049215523,0.003960438,0.00059793686,0.00017152891],"about_ca_topic_score_codex":0.00006502239,"about_ca_topic_score_gemma":0.0000010005202,"teacher_disagreement_score":0.83749956,"about_ca_system_score_codex":0.00008440911,"about_ca_system_score_gemma":0.00009620983,"threshold_uncertainty_score":0.46270683},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008263542,0.000059529164,0.98734,0.00031663312,0.00038293138,0.0002669984,0.000059724305,0.00028907033,0.0030216172],"genre_scores_gemma":[0.6887084,9.812262e-7,0.3108265,0.00013919602,0.00011580793,0.00009835843,0.000014936524,0.0000066393654,0.00008917002],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998959,0.00001757252,0.0002388769,0.00025929994,0.00012240447,0.00040284568],"domain_scores_gemma":[0.999131,0.00015600836,0.0001009215,0.00038372583,0.00006244689,0.00016589549],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041468724,0.000119859535,0.00014732062,0.000051672265,0.00017827043,0.0001617062,0.00045104462,0.000042179054,0.000015095482],"category_scores_gemma":[0.000026589201,0.00010443752,0.00005621093,0.00012413913,0.00007149859,0.00038951042,0.00010405918,0.00004622198,0.000047801335],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.1505416e-7,0.0000633622,0.0010863374,0.00006191295,0.00003988545,0.0000026357632,0.0009823323,0.000004460075,0.00092428055,0.11736631,0.00097068085,0.8784969],"study_design_scores_gemma":[0.0032479542,0.00018647192,0.0015685154,0.00068576756,0.00008219317,0.00059130025,0.0044039357,0.93656546,0.027215447,0.00042044112,0.0236107,0.0014218088],"about_ca_topic_score_codex":0.00003106096,"about_ca_topic_score_gemma":0.0000028418788,"teacher_disagreement_score":0.936561,"about_ca_system_score_codex":0.000035939604,"about_ca_system_score_gemma":0.000046718425,"threshold_uncertainty_score":0.42588383},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018272245,0.000037725742,0.97401124,0.00009320778,0.0005085863,0.00017672052,0.000022868302,0.00004477329,0.006832646],"genre_scores_gemma":[0.85864294,0.0000028239085,0.14085278,0.0001243722,0.00024786667,0.000019415864,0.000043688142,0.000004908475,0.00006121481],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982288,0.000049735958,0.000966255,0.00008186974,0.0005129919,0.00016037775],"domain_scores_gemma":[0.99823165,0.000058483056,0.0007770959,0.00028301147,0.00053039956,0.00011937875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011020298,0.000093231065,0.00018465747,0.00039856433,0.00013838978,0.0006735576,0.0007156791,0.000046667337,0.0000010868653],"category_scores_gemma":[0.00005296486,0.00007788761,0.00006367611,0.00059432077,0.000007921882,0.0014352662,0.000047151712,0.000099975594,0.00007118774],"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":[0.0000060723687,0.0005030095,0.00070037175,0.000037096666,0.000060522845,0.0000014203277,0.011249524,0.80166656,0.00013224172,0.102964185,0.02287667,0.059802357],"study_design_scores_gemma":[0.00017854122,0.00014606895,0.0028716286,0.000062733205,0.000011860018,0.00012808829,0.0022098399,0.9259662,0.00070609065,0.00004288682,0.06746917,0.00020688462],"about_ca_topic_score_codex":0.00005085617,"about_ca_topic_score_gemma":6.185173e-7,"teacher_disagreement_score":0.8403707,"about_ca_system_score_codex":0.0001492942,"about_ca_system_score_gemma":0.000084676474,"threshold_uncertainty_score":0.6495131},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017981793,0.000020787727,0.615755,0.0022115568,0.0000295687,0.00003251642,0.000001989481,0.0002725036,0.37987787],"genre_scores_gemma":[0.035902638,0.000032511365,0.91990453,0.002712982,0.00006390945,0.00002006814,0.0000049064693,0.000003910995,0.041354556],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.999706,0.000003173878,0.00004583174,0.00011853882,0.000051793733,0.00007466278],"domain_scores_gemma":[0.9996227,0.000009112351,0.0000045518655,0.00032537628,0.0000063359253,0.000031914737],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00003750114,0.000027034092,0.000025608535,0.000008358926,0.000044193323,0.000067664456,0.00040583807,0.000008238078,0.00063399115],"category_scores_gemma":[0.0000010067852,0.000022044831,0.000011106546,0.00013005832,0.000007499942,0.00018836127,0.000030296442,0.000020359505,0.0020446996],"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":[4.3978577e-8,0.000010011847,0.0000062521412,1.7370074e-7,6.026451e-7,4.3716562e-7,0.000018351866,0.0000018899831,0.000019551591,0.073109284,0.01848789,0.9083455],"study_design_scores_gemma":[0.00004976828,0.000008156143,0.00047658983,0.0000011413739,4.859685e-7,0.000007225329,0.0000018338975,0.053463545,0.00036551917,0.002565447,0.94299984,0.000060433103],"about_ca_topic_score_codex":0.000015575593,"about_ca_topic_score_gemma":8.285037e-7,"teacher_disagreement_score":0.92451197,"about_ca_system_score_codex":0.0000023361117,"about_ca_system_score_gemma":0.0000071440454,"threshold_uncertainty_score":0.9987323},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030982883,0.0000071374557,0.95290065,0.00066344626,0.0000339338,0.000015540365,6.730203e-7,0.00014368379,0.04313665],"genre_scores_gemma":[0.19561689,0.000010622576,0.7984175,0.000508006,0.000030010076,0.000008881753,0.0000017917182,0.0000016566479,0.0054046162],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9997701,0.0000019477557,0.00003398507,0.00009038992,0.00004774534,0.000055852975],"domain_scores_gemma":[0.99970245,0.000009264278,0.0000061556884,0.00024731198,0.000009527091,0.000025309639],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000020229516,0.000020113306,0.000020825122,0.000011100299,0.00007128371,0.000015967167,0.00030740805,0.000005922766,0.000020708772],"category_scores_gemma":[0.00000275263,0.000016132724,0.000008538669,0.00010753967,0.000012122805,0.00014272364,0.000074756594,0.000016511283,0.00034778402],"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":[9.6211174e-8,0.000049060836,0.00050939823,6.0244764e-7,0.0000028462118,0.000013603423,0.00022743699,0.0000027325507,0.0002592062,0.6667692,0.102323204,0.22984257],"study_design_scores_gemma":[0.00023497466,0.000040943494,0.020623265,0.0000022764482,0.0000012560615,0.0003352501,0.000012163809,0.2880213,0.004215351,0.006411288,0.6798279,0.00027397717],"about_ca_topic_score_codex":0.000010398789,"about_ca_topic_score_gemma":3.1307667e-7,"teacher_disagreement_score":0.66035795,"about_ca_system_score_codex":0.0000022529484,"about_ca_system_score_gemma":0.000010667546,"threshold_uncertainty_score":0.44701758},"labels":[],"label_agreement":null},{"id":"W2081024207","doi":"10.1016/j.datak.2007.05.006","title":"A tree-projection-based algorithm for multi-label recurrent-item associative-classification rule generation","year":2007,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Association rule learning; Associative property; Computer science; Data mining; Apriori algorithm; Artificial intelligence; Classifier (UML); Pattern recognition (psychology); Machine learning; Projection (relational algebra); Algorithm; Mathematics","score_opus":0.15268889256032656,"score_gpt":0.35595682947668167,"score_spread":0.2032679369163551,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081024207","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002651029,0.00030579508,0.9971143,0.00007208563,0.00080846547,0.00038509682,0.00062673754,0.00034790966,0.00007452199],"genre_scores_gemma":[0.000090947986,0.000011041523,0.9960799,0.000017493367,0.00052884244,0.00016040876,0.0029284954,0.000026203254,0.00015662707],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984755,0.000020550655,0.00034383437,0.0006513313,0.00015877708,0.0003500273],"domain_scores_gemma":[0.99850404,0.00027110748,0.00012650911,0.0007930297,0.00019837527,0.00010693332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009966115,0.00019132342,0.00016164713,0.00020338154,0.00022236566,0.0002040927,0.0010585246,0.00009183252,0.0000023028488],"category_scores_gemma":[0.0002478801,0.00020901633,0.000038654405,0.0006390592,0.000014391672,0.00075540517,0.00019713098,0.00014964069,0.000041758554],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.4686795e-7,0.00018080177,0.000017030952,0.000013400416,0.000017127571,3.4579077e-7,0.00012504504,2.3353338e-7,0.0029925152,0.00097514415,0.0021375297,0.9935401],"study_design_scores_gemma":[0.00059237663,0.000033926633,0.0010023123,0.000024902152,0.000015090736,0.0000013399036,0.000025366662,0.9871152,0.001640552,0.000005175317,0.009304229,0.00023954788],"about_ca_topic_score_codex":0.000012690521,"about_ca_topic_score_gemma":0.00004722614,"teacher_disagreement_score":0.99330056,"about_ca_system_score_codex":0.00014981473,"about_ca_system_score_gemma":0.00009879238,"threshold_uncertainty_score":0.8523439},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14587997,0.00007600533,0.8481065,0.0012243133,0.000046040328,0.000091898095,0.000012234805,0.00017982951,0.004383209],"genre_scores_gemma":[0.6248273,0.000009238709,0.37428936,0.0005267981,0.000025777315,0.000009521375,0.000024472934,0.0000028440347,0.0002846598],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9991887,0.00001271891,0.00012079381,0.00030432834,0.0001432568,0.00023016948],"domain_scores_gemma":[0.99941176,0.000050293216,0.000033102464,0.00043648083,0.000018412238,0.00004996287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017469733,0.00008081074,0.00008852613,0.00007556835,0.000077833116,0.00012304515,0.0005086253,0.000013346801,0.000013416602],"category_scores_gemma":[0.000011677356,0.000061366285,0.000010706908,0.00046091762,0.000018186445,0.0009137742,0.000089573296,0.00006141319,0.0000200795],"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":[0.000010422398,0.0006620589,0.08354156,0.00001636192,0.00002084399,0.00040008052,0.001998334,0.00024823385,0.000467263,0.33416167,0.006730007,0.5717432],"study_design_scores_gemma":[0.0019746874,0.0005895117,0.5047813,0.00045008367,0.000017131792,0.00022976786,0.0014196715,0.45712376,0.00601455,0.0014567691,0.024527129,0.0014156243],"about_ca_topic_score_codex":0.00008610705,"about_ca_topic_score_gemma":0.00032793035,"teacher_disagreement_score":0.5703275,"about_ca_system_score_codex":0.000013238663,"about_ca_system_score_gemma":0.000048586535,"threshold_uncertainty_score":0.25024444},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09914906,0.00005404596,0.89882904,0.00083060114,0.00024946118,0.00006814084,0.00004180244,0.00029976811,0.00047804668],"genre_scores_gemma":[0.53202057,0.0000016892672,0.4675631,0.00017289915,0.00017032937,0.0000039319293,0.000019353689,0.0000074789973,0.000040653267],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988184,0.00004051132,0.0002550863,0.00043134842,0.00018106405,0.00027362132],"domain_scores_gemma":[0.9991172,0.0002533066,0.00010012766,0.00039130464,0.000052521213,0.00008554253],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016702714,0.00013008261,0.00013573574,0.00006668896,0.0003525994,0.00023790379,0.0006396514,0.000042571268,0.000030987496],"category_scores_gemma":[0.000015240292,0.00013879302,0.00006606442,0.00021837781,0.000029082394,0.00045195094,0.00010065731,0.00015065641,0.000119122655],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013423847,0.000080376434,0.00033442565,0.0000043347727,0.00004213544,0.0000049727387,0.0055221375,0.0046976916,0.0006771126,0.008568263,0.00036258297,0.9797046],"study_design_scores_gemma":[0.00023855007,0.000026636091,0.0017018599,0.000046280173,0.000011856669,0.0000083006125,0.0003151171,0.99099356,0.00094803324,0.0006206406,0.0048597995,0.00022934366],"about_ca_topic_score_codex":0.00020767217,"about_ca_topic_score_gemma":0.000049563943,"teacher_disagreement_score":0.9862959,"about_ca_system_score_codex":0.00003825346,"about_ca_system_score_gemma":0.000044566666,"threshold_uncertainty_score":0.5659815},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011166817,0.00019306251,0.97306174,0.0011672255,0.003501212,0.0005349375,0.013939395,0.0002314283,0.006254312],"genre_scores_gemma":[0.17095383,0.00041166804,0.75595564,0.00071867876,0.0015368286,0.00008622689,0.06907818,0.000056524674,0.0012024189],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99529344,0.00023175086,0.0015006643,0.0011689615,0.0008935589,0.0009116407],"domain_scores_gemma":[0.98880446,0.00027906682,0.001392205,0.008448685,0.0006914733,0.00038413104],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.004196449,0.0005257064,0.0005757914,0.00040683508,0.0012160316,0.0047346586,0.010965409,0.00035771469,0.000023468248],"category_scores_gemma":[0.0016713568,0.0005901031,0.000071100185,0.0011971386,0.0007722378,0.008931948,0.012008888,0.0006632191,0.00057187985],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008663092,0.000090348236,0.00020646078,0.00082758203,0.00013664487,0.000008278823,0.003993233,0.004682585,0.000014128496,0.10010553,0.101803675,0.7881229],"study_design_scores_gemma":[0.00025087633,0.000032970558,0.0023154358,0.00036525395,0.00009015068,0.00006980366,0.00051327585,0.6822588,0.000019564752,0.0037350683,0.30989435,0.0004544594],"about_ca_topic_score_codex":0.004605596,"about_ca_topic_score_gemma":0.00030473265,"teacher_disagreement_score":0.7876684,"about_ca_system_score_codex":0.0006114669,"about_ca_system_score_gemma":0.0027776978,"threshold_uncertainty_score":0.999655},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019873313,0.054586742,0.91429365,0.018580154,0.0003775077,0.0010392343,0.000023419041,0.00026508974,0.008846879],"genre_scores_gemma":[0.6140272,0.22897443,0.1396033,0.002314544,0.0016926463,0.00087824074,0.00032659984,0.000092268034,0.012090749],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99870116,0.000119254655,0.00046202584,0.00026464043,0.0002349367,0.00021798303],"domain_scores_gemma":[0.99884075,0.00024568522,0.00030661564,0.00045729717,0.00012076612,0.000028874132],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069156836,0.000117453455,0.00021423369,0.000028502081,0.00022901314,0.00009869505,0.000585358,0.00003931451,0.000047023703],"category_scores_gemma":[0.00015541576,0.000079031735,0.00010948902,0.0005155929,0.00004301774,0.00021010562,0.00008690767,0.00012520888,0.0006259166],"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":[2.8433374e-7,0.0000682259,0.00006787245,0.000038290265,0.000010065043,6.95977e-7,0.00009070626,0.00011874388,0.00009186808,0.21133941,0.0009954168,0.7871784],"study_design_scores_gemma":[0.000025174966,0.00016634804,0.00034100327,0.0006905498,0.000120352655,0.000009918617,0.00013142644,0.051643066,0.010557576,0.02003448,0.91592,0.00036006162],"about_ca_topic_score_codex":0.00046164522,"about_ca_topic_score_gemma":0.000031535033,"teacher_disagreement_score":0.9149246,"about_ca_system_score_codex":0.00008125895,"about_ca_system_score_gemma":0.000051475006,"threshold_uncertainty_score":0.80451},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30144128,0.0000048128336,0.69725186,0.00027699012,0.00018538558,0.000082700484,0.000009803164,0.00019506658,0.0005520945],"genre_scores_gemma":[0.42396536,6.307662e-7,0.57504797,0.0006209603,0.0001172488,0.0000127739,0.0000066565303,0.000011141348,0.00021728319],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875873,0.000035408277,0.00021523598,0.0004886807,0.00018876014,0.00031321027],"domain_scores_gemma":[0.9989174,0.0001115927,0.000069038826,0.000663994,0.000060393457,0.00017757545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024195737,0.00014240977,0.00016197163,0.00008475483,0.0002149055,0.00036455115,0.0007665631,0.000050238406,0.000015314024],"category_scores_gemma":[0.00006941585,0.00013645785,0.00004271294,0.0003757318,0.000010762601,0.0003901449,0.00071913697,0.0000686727,0.00017254152],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000075010303,0.00016018783,0.006829739,0.000013658957,0.00008532976,0.0000057189945,0.0024232578,0.009550324,0.5278314,0.007929753,0.0059988443,0.43916434],"study_design_scores_gemma":[0.0001993489,0.000019422463,0.0015636205,0.000013966583,0.00000436352,0.0000015003444,0.000021175692,0.9723325,0.015502559,0.00027860873,0.0098497905,0.00021315344],"about_ca_topic_score_codex":0.0013358133,"about_ca_topic_score_gemma":0.00010033139,"teacher_disagreement_score":0.96278214,"about_ca_system_score_codex":0.00006490056,"about_ca_system_score_gemma":0.000023750243,"threshold_uncertainty_score":0.55645895},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5523202,0.0043319394,0.30220118,0.11712139,0.008281159,0.0061598537,0.0006527442,0.00087808043,0.008053464],"genre_scores_gemma":[0.9167228,0.00021223942,0.045773588,0.0035256916,0.0023202628,0.0019473485,0.000083361665,0.00009096097,0.029323783],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99796283,0.00006781796,0.00030364117,0.00032835352,0.0006188566,0.0007185219],"domain_scores_gemma":[0.99493384,0.00070170494,0.00016748453,0.0039704265,0.000113967704,0.000112545116],"candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0019729638,0.00021211602,0.00014601112,0.000021692871,0.002430857,0.0015132872,0.012338007,0.000051107556,0.000009632259],"category_scores_gemma":[0.00043179476,0.000096670476,0.00013026375,0.00027974526,0.00028226836,0.00048476332,0.004213247,0.00023262616,0.0003727872],"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":[0.00003733473,0.0006680351,0.033825863,0.000018873152,0.00034083732,0.000001624184,0.010121268,0.000021397822,0.00063007773,0.06897606,0.5730439,0.31231475],"study_design_scores_gemma":[0.0005355678,0.00007487993,0.12815143,0.000009181118,0.00004187464,0.00001944466,0.0001751776,0.0028912935,0.00025773284,0.00764845,0.8599654,0.00022956896],"about_ca_topic_score_codex":0.00002360612,"about_ca_topic_score_gemma":0.00003097316,"teacher_disagreement_score":0.3644026,"about_ca_system_score_codex":0.000036834554,"about_ca_system_score_gemma":0.00004165169,"threshold_uncertainty_score":0.9995232},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06418004,0.000018717583,0.9289244,0.0032189768,0.00021943264,0.00027869362,0.000041809086,0.000093959505,0.003024006],"genre_scores_gemma":[0.5561528,4.4896026e-7,0.44325396,0.00040367784,0.000098228535,0.000024128609,0.00003879485,0.000005265291,0.000022692182],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988399,0.00003701156,0.00024822282,0.00040917407,0.00022302708,0.00024264083],"domain_scores_gemma":[0.998471,0.00023952867,0.00008692873,0.0011083435,0.000042977255,0.000051200794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031270584,0.00009312075,0.00013356862,0.000062374,0.000093426956,0.00009872813,0.0015534271,0.000058816393,0.00006166221],"category_scores_gemma":[0.000059387545,0.00008312951,0.00001892348,0.0006364099,0.000034735785,0.000110849054,0.00045182303,0.0001175941,0.000060483486],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005595072,0.0014360446,0.007230493,0.000046245605,0.000031084135,0.000007988423,0.0019511479,0.09788688,0.0002908577,0.2777012,0.17471862,0.43869385],"study_design_scores_gemma":[0.00010948658,0.00002051957,0.0140022235,0.00005653437,0.0000016904119,3.6985162e-7,0.00003460875,0.9838626,0.000062893465,0.001019593,0.00072428695,0.00010518653],"about_ca_topic_score_codex":0.00021859781,"about_ca_topic_score_gemma":0.0000051610805,"teacher_disagreement_score":0.8859757,"about_ca_system_score_codex":0.00002138355,"about_ca_system_score_gemma":0.000055930606,"threshold_uncertainty_score":0.3389923},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00040470166,0.000009694146,0.99536425,0.0008164153,0.000104824656,0.0001654255,0.000017132867,0.00022242092,0.0028951447],"genre_scores_gemma":[0.02222069,0.0000025898378,0.974963,0.00034843932,0.00016659035,0.000088579625,0.00004053954,0.000009925174,0.0021596418],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992016,0.000014408435,0.0001501468,0.00031102286,0.00013334327,0.00018949014],"domain_scores_gemma":[0.99919355,0.00018648937,0.000062897,0.0004261455,0.000043907254,0.00008699802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015706761,0.0001011989,0.00010729406,0.000056712055,0.00012732635,0.00022664719,0.0004514091,0.0000371621,0.000010660593],"category_scores_gemma":[0.000015219954,0.00009132851,0.000038017544,0.00012837978,0.000012014375,0.00071085885,0.000093232324,0.00003587194,0.000010745269],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.1177726e-7,0.000015560934,0.000014229751,0.0000026097598,0.0000053649474,7.386611e-8,0.00024041538,0.00011694745,0.000097440075,0.021207742,0.0040742937,0.9742251],"study_design_scores_gemma":[0.0002217258,0.000057585454,0.000121142075,0.0000113667775,0.0000050760923,0.0000027715137,0.000048925747,0.9816533,0.001237996,0.00954276,0.006967781,0.00012958041],"about_ca_topic_score_codex":0.00027884304,"about_ca_topic_score_gemma":0.000016860757,"teacher_disagreement_score":0.9815363,"about_ca_system_score_codex":0.00002139757,"about_ca_system_score_gemma":0.000044451386,"threshold_uncertainty_score":0.37242684},"labels":[],"label_agreement":null},{"id":"W2084144913","doi":"10.1007/s10115-011-0399-z","title":"Best papers from the Fifth International Conference on Advanced Data Mining and Applications (ADMA 2009)","year":2011,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Data science; Data mining","score_opus":0.06692820956384166,"score_gpt":0.2819794512247109,"score_spread":0.21505124166086925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084144913","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060180025,0.0020546927,0.49459255,0.0012336044,0.00127745,0.0013913962,0.0019870617,0.00028361264,0.49116164],"genre_scores_gemma":[0.9594375,0.001408681,0.035178557,0.00063723244,0.00045157637,0.00056928507,0.0015459994,0.00001256359,0.00075861666],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99932367,0.000020428099,0.0002516057,0.00019489221,0.00011372471,0.00009565454],"domain_scores_gemma":[0.99895996,0.000084014704,0.00013127255,0.0006604892,0.00010453655,0.000059739377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019837011,0.00009031381,0.00008497977,0.000045603763,0.00021212963,0.0003255632,0.00088292395,0.000035558303,0.000011843397],"category_scores_gemma":[0.00002094603,0.000065874956,0.000008537462,0.00012922587,0.00004749372,0.0022197596,0.0003598263,0.000060042137,0.00013178107],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032810074,0.000034980814,0.00026134215,0.000013010237,0.000022810818,1.2426041e-7,0.00894243,0.0000017338922,0.000018896013,0.14675385,0.0041027684,0.83984476],"study_design_scores_gemma":[0.0002698275,0.00003232867,0.0020951196,0.00008080361,0.000007723397,0.0000077362265,0.0026836467,0.15189959,0.0000133400545,0.000105856845,0.84266746,0.00013658551],"about_ca_topic_score_codex":0.00007538775,"about_ca_topic_score_gemma":0.00001587261,"teacher_disagreement_score":0.9534195,"about_ca_system_score_codex":0.000009500447,"about_ca_system_score_gemma":0.000034900935,"threshold_uncertainty_score":0.31394133},"labels":[],"label_agreement":null},{"id":"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04361106,0.0000024584601,0.9474314,0.007537043,0.00011742883,0.00013287095,0.000023066681,0.00013456064,0.0010101082],"genre_scores_gemma":[0.30979174,1.627185e-7,0.688107,0.0016784995,0.000028898648,0.000018064917,0.000039228493,0.0000057025813,0.0003306699],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884915,0.00007589952,0.00018153308,0.00051636435,0.00016515919,0.00021187786],"domain_scores_gemma":[0.9976865,0.00022568142,0.000034944092,0.0019321626,0.000016459298,0.00010423801],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082326314,0.0000913549,0.0001011261,0.00013491651,0.000058765312,0.00023250881,0.002366983,0.000029096082,0.00002799897],"category_scores_gemma":[0.00018716934,0.000078786645,0.000011178351,0.00048204343,0.000017169114,0.00040238668,0.0007079352,0.000055740475,0.0000895963],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000063951375,0.00007833085,0.0015970813,0.00000807831,0.000007428424,0.000010127261,0.00066952757,0.0005840494,0.005778948,0.02885928,0.030229015,0.9321142],"study_design_scores_gemma":[0.00071104534,0.00009905842,0.019061094,0.000032347583,0.000002659231,0.0000051882243,0.00003712348,0.82669836,0.0021973744,0.0010121643,0.14984694,0.000296659],"about_ca_topic_score_codex":0.000076114884,"about_ca_topic_score_gemma":0.000064250045,"teacher_disagreement_score":0.93181753,"about_ca_system_score_codex":0.000020411006,"about_ca_system_score_gemma":0.000050538245,"threshold_uncertainty_score":0.43984827},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8861339,0.00034166675,0.10687141,0.0045923055,0.0009359983,0.00013316779,0.00007791004,0.000034862744,0.00087879156],"genre_scores_gemma":[0.8260651,0.000021720376,0.17216688,0.00032293805,0.00034599483,0.0000044454096,0.000013087272,0.0000096894955,0.0010501405],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987172,0.00017305474,0.00022952244,0.00030121385,0.00035170192,0.00022734259],"domain_scores_gemma":[0.99870044,0.0004744523,0.0003043588,0.00027470954,0.0001351227,0.00011093531],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0017877244,0.00010320233,0.000119396085,0.000138788,0.001317945,0.0022542158,0.0004381468,0.000023270488,0.000010060933],"category_scores_gemma":[0.00013258614,0.00007348926,0.000027966136,0.00035705944,0.00015559346,0.0006114482,0.00023713434,0.00020444373,0.000011323143],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011848973,0.00015580832,0.010138411,0.000008932518,0.00027911953,0.0000135037535,0.032739356,0.00030428972,0.03265233,0.049513515,0.01750177,0.8566811],"study_design_scores_gemma":[0.0011422926,0.00007535982,0.116833255,0.00039231588,0.000121066885,0.00019786257,0.00094783434,0.770666,0.004933666,0.08787749,0.016180702,0.0006321732],"about_ca_topic_score_codex":0.000121781755,"about_ca_topic_score_gemma":0.000064481865,"teacher_disagreement_score":0.85604894,"about_ca_system_score_codex":0.00010260165,"about_ca_system_score_gemma":0.000051998297,"threshold_uncertainty_score":0.9999822},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012913476,0.00016329005,0.8694026,0.11766384,0.00036270526,0.00022791745,0.000020493691,0.00054330647,0.010324523],"genre_scores_gemma":[0.064365305,0.00012769687,0.8908682,0.026654605,0.0009823841,0.0006612905,0.00006880781,0.000050193023,0.016221538],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99875677,0.00003602663,0.0002511246,0.00043478142,0.00022605983,0.00029526243],"domain_scores_gemma":[0.9977036,0.00010940734,0.00006701175,0.0019462118,0.0000668754,0.00010688079],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00009465607,0.0001505933,0.00011891373,0.00012154481,0.00030574732,0.00036582188,0.0016171412,0.00005447474,0.0007991404],"category_scores_gemma":[0.00009062627,0.00014464713,0.000058441237,0.00063059514,0.00004911833,0.0015122447,0.000381909,0.00015278596,0.009211446],"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":[1.868557e-7,0.00008768721,0.000036956044,0.0000016903076,0.000010327788,0.0000067009773,0.00067036296,0.000027961789,0.0008553639,0.015129661,0.92101,0.062163077],"study_design_scores_gemma":[0.00026876127,0.000039552095,0.0002452775,0.00000933591,0.000009227774,0.000020299361,0.000044274737,0.074081324,0.0011077833,0.0029977679,0.9208354,0.0003410088],"about_ca_topic_score_codex":0.000010831199,"about_ca_topic_score_gemma":0.0000060447555,"teacher_disagreement_score":0.09100924,"about_ca_system_score_codex":0.000024493414,"about_ca_system_score_gemma":0.000011389334,"threshold_uncertainty_score":0.99156},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00044946204,0.0000097509965,0.9092397,0.0013331989,0.00024537003,0.00013866588,0.000022786691,0.00060805684,0.08795301],"genre_scores_gemma":[0.4150824,0.0000010736977,0.5812376,0.00079956127,0.00011348006,0.00010797487,0.000031191925,0.000015836944,0.002610903],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989058,0.00006364696,0.00018241814,0.00039641917,0.00022638043,0.0002253714],"domain_scores_gemma":[0.9988678,0.00016998184,0.000054982018,0.0007585464,0.000049852864,0.00009881046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060765824,0.000115428025,0.000098058226,0.00009840954,0.00027076015,0.00017808766,0.00055356364,0.00004042844,0.00006827981],"category_scores_gemma":[0.00005842517,0.000100020436,0.000051582367,0.0005030259,0.000019286586,0.00020408082,0.0000919484,0.00009753521,0.00028524804],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056514717,0.00097084465,0.00042910318,0.00022943404,0.00008513951,0.00006002157,0.00023800555,0.039546233,0.0011310165,0.65846574,0.1235822,0.17520577],"study_design_scores_gemma":[0.000441234,0.000052987627,0.0043895408,0.00012409096,0.000006727912,0.000010677356,0.00010626641,0.9805773,0.00022107338,0.00013899144,0.013731195,0.00019992619],"about_ca_topic_score_codex":0.00007524989,"about_ca_topic_score_gemma":0.0000032334253,"teacher_disagreement_score":0.94103104,"about_ca_system_score_codex":0.000104545645,"about_ca_system_score_gemma":0.00009297652,"threshold_uncertainty_score":0.4078715},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0064262054,0.000011423854,0.989484,0.00014958353,0.00009994723,0.00020445076,0.002129381,0.00021765516,0.0012773549],"genre_scores_gemma":[0.27443773,7.406715e-7,0.72442174,0.000153427,0.000043492455,0.00009073596,0.00074160565,0.000008625594,0.00010192069],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885416,0.000016865379,0.0002049182,0.00057392137,0.0001347671,0.00021538259],"domain_scores_gemma":[0.9978736,0.000116565134,0.00007642026,0.0017972195,0.000043112657,0.00009308937],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023274196,0.00011696207,0.0001316266,0.000037193266,0.00010177655,0.00012177011,0.0019811983,0.00003990985,0.000018458873],"category_scores_gemma":[0.000014239904,0.00009619891,0.000030358051,0.00007988864,0.000011939834,0.00036625235,0.00038057793,0.00004014806,0.000016297343],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003147938,0.00070955604,0.008690179,0.00019898421,0.00019552019,0.000030973628,0.0035352707,0.0007388384,0.00054451014,0.122440256,0.04136746,0.821517],"study_design_scores_gemma":[0.00030269468,0.00002430121,0.00023506806,0.000046404235,0.000012989063,9.894624e-7,0.00016811301,0.9975591,0.0004519084,0.00030061635,0.00075773074,0.00014012857],"about_ca_topic_score_codex":0.0021319943,"about_ca_topic_score_gemma":0.00017856287,"teacher_disagreement_score":0.9968202,"about_ca_system_score_codex":0.000028591692,"about_ca_system_score_gemma":0.000085124855,"threshold_uncertainty_score":0.39228776},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015952423,0.00000468985,0.99652547,0.0006484349,0.000039682523,0.00029085926,0.00008737368,0.00019359133,0.0006146303],"genre_scores_gemma":[0.050001852,0.0000044866606,0.9485509,0.00095865614,0.00007983089,0.00011590238,0.00011727728,0.0000072902108,0.0001638473],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871385,0.00001141121,0.0004219696,0.00023832211,0.00028406558,0.00033039186],"domain_scores_gemma":[0.9984499,0.00044953753,0.0003809055,0.0005377884,0.000090278816,0.00009159684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006607753,0.00015071411,0.00022391407,0.00020382613,0.00024796085,0.00026311626,0.00075048197,0.00009008508,0.000005619111],"category_scores_gemma":[0.000076226795,0.00014367416,0.00012169081,0.00090187084,0.000015860047,0.0004985969,0.00022060466,0.00008314075,0.000096544005],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013574873,0.00003735458,0.00058516586,0.000014753986,0.00018336158,8.41601e-8,0.002365438,0.0024042781,0.00013405031,0.002359171,0.0016761901,0.9902388],"study_design_scores_gemma":[0.000266775,0.000013619628,0.00029448592,0.0000036212843,0.00013113747,0.0000010059574,0.00040027584,0.9738513,0.0011920625,0.00007481472,0.023576802,0.00019405647],"about_ca_topic_score_codex":0.000026205347,"about_ca_topic_score_gemma":0.000035896268,"teacher_disagreement_score":0.9900447,"about_ca_system_score_codex":0.00013225782,"about_ca_system_score_gemma":0.000033750697,"threshold_uncertainty_score":0.58588624},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03044612,0.000011197983,0.96153194,0.00022343987,0.000051008115,0.0002269595,0.000026915535,0.0001643588,0.007318041],"genre_scores_gemma":[0.08925706,0.0000018754716,0.91019624,0.00011345664,0.00003457873,0.000046621666,0.0000061863507,0.0000060906063,0.00033788235],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990694,0.000006999767,0.00016653992,0.0003702795,0.0001633708,0.00022339671],"domain_scores_gemma":[0.999205,0.00021561868,0.000037499463,0.00039683335,0.00006149036,0.000083557985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016194218,0.00010170876,0.00011012182,0.000041591902,0.0001774125,0.00016512083,0.00045394766,0.000027937218,0.00016333249],"category_scores_gemma":[0.000013718253,0.00007368175,0.000031755942,0.00024005029,0.00012488847,0.00009441901,0.000042526422,0.000046886467,0.000055960543],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031213785,0.000031965592,0.000023186745,0.0000010833601,0.0000055801092,0.0000013049989,0.000072109346,0.0005152464,0.00003257933,0.019481685,0.0002955002,0.97953665],"study_design_scores_gemma":[0.00094424427,0.00013476363,0.00035102124,0.000039288127,0.000007846703,0.000136498,0.00018531727,0.9826866,0.00095092313,0.0010746095,0.013239989,0.0002489266],"about_ca_topic_score_codex":0.000010619865,"about_ca_topic_score_gemma":0.000005301281,"teacher_disagreement_score":0.9821713,"about_ca_system_score_codex":0.00001319172,"about_ca_system_score_gemma":0.000050809256,"threshold_uncertainty_score":0.3004655},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022654725,0.000014325496,0.9765104,0.00015932269,0.00013037019,0.0002639185,0.000036955204,0.000075727665,0.00015426507],"genre_scores_gemma":[0.54289395,6.2414216e-7,0.45694512,0.00008118149,0.000025161567,0.000033857476,0.000011938537,0.000003057847,0.000005130521],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982905,0.000059288155,0.00026406415,0.00068205665,0.0003388845,0.0003652518],"domain_scores_gemma":[0.9987412,0.0003671735,0.00007840797,0.0004597449,0.00016694979,0.00018649363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014442758,0.00013001155,0.00014872367,0.00031755934,0.0010463685,0.00048561385,0.00041085287,0.000030023923,0.000054510365],"category_scores_gemma":[0.000050852523,0.00011775814,0.00006696717,0.0019942762,0.0005389951,0.0003883661,0.0002487792,0.00008338256,0.000010104067],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.045801e-7,0.00003178411,0.000114085444,0.0000014381602,0.000017916851,0.000008475731,0.00020465702,0.0015918019,0.000020504725,0.85723346,0.000033130866,0.14074224],"study_design_scores_gemma":[0.0002687487,0.000068175905,0.0011374672,0.000002207896,0.00004360487,0.00019425388,0.000047373524,0.9656219,0.00023028681,0.032013156,0.00022062982,0.00015220525],"about_ca_topic_score_codex":0.000010632539,"about_ca_topic_score_gemma":0.000003099499,"teacher_disagreement_score":0.9640301,"about_ca_system_score_codex":0.00005923216,"about_ca_system_score_gemma":0.000089707864,"threshold_uncertainty_score":0.80479264},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018068464,0.00001147547,0.9788257,0.0017386279,0.00014890399,0.00026595505,0.0000012521073,0.00025990885,0.00067971105],"genre_scores_gemma":[0.31213367,0.0000028204402,0.68721455,0.00042115583,0.00008475422,0.00009073906,0.0000035164176,0.0000053836134,0.000043404692],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984002,0.000008839985,0.00014593975,0.00062840903,0.0004609772,0.00035562925],"domain_scores_gemma":[0.99875164,0.000032921536,0.000057806184,0.0006562759,0.0003148657,0.00018650267],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00021245512,0.00012322409,0.00009453529,0.00012983089,0.00032728413,0.0010462984,0.0019939786,0.000019889043,0.000012961407],"category_scores_gemma":[0.00001557377,0.00009068734,0.000015458847,0.0016711628,0.00025456137,0.0028044004,0.0004875557,0.00007650401,0.00023028725],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.419281e-7,0.00012042865,0.002817485,0.000019067027,0.0000055704986,0.0000026961086,0.0016642761,0.00025622794,0.001991652,0.08428378,0.0025584619,0.90627944],"study_design_scores_gemma":[0.00013804199,0.000081612765,0.01424407,0.000017088167,0.0000015166861,0.00002529665,0.00000952729,0.9816602,0.0012783337,0.0016403417,0.0007164898,0.00018752272],"about_ca_topic_score_codex":0.00003229254,"about_ca_topic_score_gemma":0.0000017848464,"teacher_disagreement_score":0.98140395,"about_ca_system_score_codex":0.000027788456,"about_ca_system_score_gemma":0.00020707358,"threshold_uncertainty_score":0.9999907},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018843172,0.00012230559,0.97786,0.0014984289,0.0010903951,0.00008640221,0.00030518425,0.00002054325,0.00017361787],"genre_scores_gemma":[0.546435,0.0002416671,0.45116827,0.0006717508,0.0012358621,0.000010577664,0.00011438154,0.000019184372,0.000103295126],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986674,0.00007087148,0.0005634572,0.00026901052,0.00028143267,0.00014778157],"domain_scores_gemma":[0.9984275,0.00040678214,0.00038090118,0.00022014651,0.00047850478,0.00008615726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009172479,0.00010441758,0.00012583272,0.00020134552,0.00014752748,0.00036501716,0.0009392273,0.00004025964,0.00023990482],"category_scores_gemma":[0.00041123605,0.00010240452,0.000057571644,0.00014512788,0.000046471683,0.00090471335,0.00022092927,0.00011742913,0.000019260917],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013646186,0.0000825482,0.000074166644,0.0000053236035,0.000049687125,0.000008995517,0.0001791568,0.00003681673,0.00062166806,0.00009910198,0.001394262,0.9974346],"study_design_scores_gemma":[0.000080796664,0.00005144929,0.0001405297,0.00015081909,0.000025587344,0.00023253924,0.0003781716,0.991759,0.0012346645,0.0027686448,0.0030266852,0.0001511314],"about_ca_topic_score_codex":0.000014314827,"about_ca_topic_score_gemma":0.000006016847,"teacher_disagreement_score":0.9972835,"about_ca_system_score_codex":0.000028462806,"about_ca_system_score_gemma":0.000024108047,"threshold_uncertainty_score":0.4175935},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016880877,0.0000022668419,0.97889817,0.00016646218,0.00020975957,0.00023711947,0.0000029546409,0.000053527256,0.0035488887],"genre_scores_gemma":[0.65998775,0.000010422237,0.33982956,0.00011349118,0.000018205288,0.000024115596,0.000006337641,0.0000010354466,0.000009041762],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99888813,0.000012117102,0.00029172515,0.00013259305,0.00046781797,0.00020762428],"domain_scores_gemma":[0.99903,0.000029250845,0.000070630405,0.00038943032,0.0003868343,0.00009385522],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020756759,0.00006409725,0.000075092445,0.00047065076,0.0003766648,0.0007425686,0.0006745052,0.000026580532,0.0000012457077],"category_scores_gemma":[0.000006914404,0.00004666202,0.0000072320436,0.00060473895,0.0003290312,0.01243122,0.00071417005,0.00011001973,0.00004330944],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026193286,0.0000129735445,0.00008157287,0.0001175031,0.000003896628,3.7676273e-7,0.0036533107,0.00015998138,0.0003540184,0.5250591,0.00077649276,0.46977815],"study_design_scores_gemma":[0.00022909541,0.00008845145,0.008612264,0.000029428847,0.0000015829279,0.000044008204,0.0002943487,0.9726343,0.0033520486,0.0005856523,0.014016271,0.00011253391],"about_ca_topic_score_codex":0.000006274638,"about_ca_topic_score_gemma":8.064373e-8,"teacher_disagreement_score":0.97247434,"about_ca_system_score_codex":0.0000129936125,"about_ca_system_score_gemma":0.00003991152,"threshold_uncertainty_score":0.9012335},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7007981,0.00056368374,0.26996112,0.021403085,0.005164893,0.000068043126,0.0018809792,0.00006305564,0.00009706076],"genre_scores_gemma":[0.6934393,0.0004055799,0.30266348,0.0004706776,0.002378265,0.0000022120366,0.00059262966,0.000012408265,0.000035454876],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99887425,0.00002985214,0.00027350915,0.0002535826,0.00046491218,0.000103873994],"domain_scores_gemma":[0.9978569,0.00055322563,0.00035537255,0.0009606755,0.00018985308,0.000083985964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009613545,0.00007343852,0.00008797278,0.000054577336,0.00014902362,0.00065696414,0.0042397403,0.00002016461,0.000005606701],"category_scores_gemma":[0.00082712213,0.000054091553,0.000016906222,0.00008437615,0.000025598087,0.0037567636,0.0018150846,0.00023680415,0.0000034167506],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009065144,0.00004946234,0.0069354377,0.0000014783457,0.00013144611,0.00003722268,0.0010641896,0.0000129640675,0.00073705084,0.0005415835,0.01013059,0.9803495],"study_design_scores_gemma":[0.001082025,0.00003582091,0.061326403,0.00039107024,0.00016491108,0.00019667041,0.001050139,0.29268166,0.0002360948,0.0013197936,0.64108914,0.00042625796],"about_ca_topic_score_codex":0.00011175907,"about_ca_topic_score_gemma":0.000042771462,"teacher_disagreement_score":0.97992325,"about_ca_system_score_codex":0.000018373505,"about_ca_system_score_gemma":0.0001046622,"threshold_uncertainty_score":0.7878563},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.106688306,0.00017913892,0.8361285,0.01040216,0.00019112033,0.00038624593,0.00009039597,0.00080072315,0.045133453],"genre_scores_gemma":[0.24841653,0.000011054255,0.74937093,0.001003084,0.000062559026,0.000005420204,0.00025642003,0.0000058999476,0.0008680812],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907345,0.000013159534,0.00016751797,0.00040539974,0.00015290278,0.00018759278],"domain_scores_gemma":[0.99857783,0.00004723731,0.000035095956,0.0012665195,0.00001531122,0.000057989015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023433902,0.000075693846,0.000086797016,0.00006533286,0.000059155143,0.00021388428,0.0020583216,0.000025922885,0.000028285602],"category_scores_gemma":[0.00002709769,0.000069194284,0.0000089267105,0.00040578793,0.000009352554,0.00072890276,0.0004416005,0.00006294478,0.00013386065],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.2500714e-7,0.00012431605,0.0010479387,0.0000012713697,0.0000032776993,0.000014864542,0.0002091766,0.000034934237,0.00061531056,0.007290569,0.015496912,0.9751611],"study_design_scores_gemma":[0.00033356296,0.000047996065,0.008140816,0.000049055416,0.0000030992862,0.000022127113,0.000028769644,0.9751263,0.00091434905,0.0011263768,0.013919601,0.00028791255],"about_ca_topic_score_codex":0.00008560359,"about_ca_topic_score_gemma":0.0000065665736,"teacher_disagreement_score":0.9750914,"about_ca_system_score_codex":0.000017100678,"about_ca_system_score_gemma":0.000030641688,"threshold_uncertainty_score":0.38249078},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14855991,0.00013067167,0.8481073,0.00038954342,0.00042906305,0.00015366646,0.0011828194,0.00019693724,0.0008500995],"genre_scores_gemma":[0.71403795,0.00000808796,0.2844194,0.00012481402,0.00022164006,0.000030012881,0.0009029907,0.000026159205,0.00022896584],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99830467,0.00002539285,0.00026563247,0.000870384,0.00016472011,0.00036919166],"domain_scores_gemma":[0.99728674,0.00052350655,0.00014556835,0.0018116947,0.00007240327,0.00016007671],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041293225,0.00024380982,0.00022274221,0.00010418146,0.00039270372,0.0009338866,0.0015067251,0.00007905204,0.0000062139984],"category_scores_gemma":[0.00022359753,0.00020581947,0.00002323355,0.00028491032,0.0002275072,0.0013081743,0.0009342375,0.0002123608,0.0000127474195],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013899571,0.00026089913,0.010996693,0.00020070608,0.000057949183,0.000055922323,0.0027467755,0.0000071847,0.0007232859,0.0020319852,0.009862135,0.97304255],"study_design_scores_gemma":[0.0012247729,0.00017984059,0.0026369016,0.00025167456,0.000064624386,0.00008856204,0.00090461154,0.9715059,0.00036372727,0.000024449013,0.022022717,0.00073221687],"about_ca_topic_score_codex":0.0000931056,"about_ca_topic_score_gemma":0.001069177,"teacher_disagreement_score":0.97231036,"about_ca_system_score_codex":0.000009311581,"about_ca_system_score_gemma":0.0003362652,"threshold_uncertainty_score":0.90054905},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01211357,0.0000124001135,0.98544997,0.000084261475,0.00005926268,0.00043731567,0.000040207855,0.00006374745,0.0017392423],"genre_scores_gemma":[0.2101124,0.0000021157869,0.789595,0.000063205785,0.00008018689,0.00006821976,0.000054989105,0.000009998935,0.000013876614],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990478,0.0000025735471,0.0003534345,0.00021096715,0.00019647437,0.00018875953],"domain_scores_gemma":[0.9989937,0.00020152584,0.00019220501,0.00051385886,0.000044813885,0.000053913885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046938437,0.00010383152,0.00015648271,0.000056149962,0.00008979691,0.00005510872,0.000458206,0.000062680396,0.000004438179],"category_scores_gemma":[0.000038425358,0.00009491238,0.000047346934,0.00020991087,0.000032126245,0.000096683696,0.00011053408,0.00005939463,0.00001045292],"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":[0.0000017877129,0.000068714406,0.0000020100335,0.00004292657,0.000012686978,1.6937405e-7,0.0008305239,0.000004556822,0.02524448,0.94761366,0.00035142837,0.025827076],"study_design_scores_gemma":[0.00078095455,0.00011600963,0.00014647967,0.00007527941,0.000046762405,0.000006179191,0.0008242079,0.3140174,0.268293,0.41249245,0.002727314,0.0004739802],"about_ca_topic_score_codex":0.0000023547661,"about_ca_topic_score_gemma":0.000002112614,"teacher_disagreement_score":0.5351212,"about_ca_system_score_codex":0.000018033918,"about_ca_system_score_gemma":0.000019483941,"threshold_uncertainty_score":0.38704145},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8605956,0.00009107634,0.12751,0.0026580063,0.00029580877,0.0016330715,0.00004541938,0.00008298996,0.0070880493],"genre_scores_gemma":[0.9912106,0.000012928565,0.008287321,0.00033502327,0.000012481221,0.00010160197,0.000033035387,0.0000011967858,0.0000058204882],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.999235,0.000015941652,0.00032818224,0.00006558806,0.00024492477,0.00011040115],"domain_scores_gemma":[0.99917036,0.000014867572,0.00025698458,0.0005149993,0.000023782815,0.000018979055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045610516,0.000046859124,0.000057286958,0.00008286496,0.00006799787,0.00007734199,0.00047459634,0.00001340205,0.000001859484],"category_scores_gemma":[0.0000071278296,0.00003031924,0.000017173616,0.00027077104,0.000030145779,0.0008750234,0.00006137855,0.000042843043,0.000012870785],"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":[0.0000021388353,0.00006688175,0.00008957535,0.000021408816,0.000004897856,0.0000040754926,0.0510748,0.000046183777,0.0000019625365,0.21383886,0.00021030924,0.7346389],"study_design_scores_gemma":[0.0016119863,0.00068328896,0.784341,0.00012849856,0.000027185062,0.000034803856,0.037499283,0.01274356,0.00041030633,0.026576903,0.13555245,0.00039074742],"about_ca_topic_score_codex":0.0006545012,"about_ca_topic_score_gemma":0.000077996156,"teacher_disagreement_score":0.7842514,"about_ca_system_score_codex":0.000019221601,"about_ca_system_score_gemma":0.000026176005,"threshold_uncertainty_score":0.12363827},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12685503,0.0002472845,0.86010736,0.003020163,0.00007725646,0.00022801146,0.00007357762,0.00007382011,0.009317516],"genre_scores_gemma":[0.9535188,0.00013446223,0.046071067,0.00013896063,0.000040601783,0.000008323888,0.000046122896,0.0000021489197,0.000039512528],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9995099,0.000033700122,0.00013253285,0.00014679662,0.00008424743,0.00009284902],"domain_scores_gemma":[0.99947757,0.0001266445,0.00006203081,0.00028272215,0.000022492008,0.000028553726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011915967,0.0000525277,0.00008638721,0.00004264617,0.0000751309,0.000051581403,0.00039927443,0.000015557282,0.0000016664811],"category_scores_gemma":[0.000025726267,0.000033095792,0.000016134603,0.00044024712,0.00004538488,0.00015988408,0.000092088085,0.00008076647,0.0000059989043],"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":[2.4285103e-7,0.00003678553,0.16901852,0.0000049929586,0.000010084171,2.2551467e-7,0.004416654,0.000045052213,0.000010764944,0.025922507,0.00087296346,0.7996612],"study_design_scores_gemma":[0.00015900651,0.000046186397,0.9033119,0.000011818943,0.000013423129,0.000001779995,0.00089325325,0.052124333,0.000012885194,0.0005558761,0.04274264,0.00012688787],"about_ca_topic_score_codex":0.00012779066,"about_ca_topic_score_gemma":0.000040840107,"teacher_disagreement_score":0.8266638,"about_ca_system_score_codex":0.0000035159292,"about_ca_system_score_gemma":0.000008784001,"threshold_uncertainty_score":0.13496073},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1556384,0.0006291304,0.8376899,0.001169843,0.00036970407,0.00031716505,0.0003212291,0.00026645235,0.003598199],"genre_scores_gemma":[0.59499496,0.0004548771,0.4028235,0.00044178186,0.00024378028,0.00014148069,0.00020679021,0.000030014664,0.00066279084],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974506,0.00013531475,0.0008421737,0.00032149453,0.00039437905,0.0008560758],"domain_scores_gemma":[0.99809295,0.00015297582,0.0004745646,0.0006480996,0.00035171595,0.00027968382],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00090249634,0.00039493057,0.00031468712,0.00023913507,0.001227298,0.0011048381,0.0010458898,0.0003128914,0.000052209416],"category_scores_gemma":[0.0003868556,0.00042052314,0.00014952097,0.00066083565,0.00038421873,0.0065382957,0.00030699503,0.00033865657,0.00020331099],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000106804055,0.00019992593,0.0049470942,0.000595271,0.00008926896,0.000015562022,0.035949517,0.012188981,0.0004985829,0.1450609,0.0019351959,0.798509],"study_design_scores_gemma":[0.0022091328,0.00029729505,0.066530034,0.0026278219,0.00017970083,0.0009202514,0.0136682335,0.7768366,0.022702146,0.07486394,0.037653904,0.0015109592],"about_ca_topic_score_codex":0.006573019,"about_ca_topic_score_gemma":0.00037886362,"teacher_disagreement_score":0.7969981,"about_ca_system_score_codex":0.0014081738,"about_ca_system_score_gemma":0.00089367497,"threshold_uncertainty_score":0.9999321},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8707883,0.001459458,0.09385632,0.00075110054,0.0015139312,0.0004888476,0.0034782863,0.00040219107,0.02726158],"genre_scores_gemma":[0.94988525,0.00003749686,0.046143163,0.00019238384,0.00026327392,0.000036922956,0.002762854,0.000027366596,0.0006512644],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99772906,0.00009899704,0.00042566878,0.0010879126,0.00019767242,0.0004606584],"domain_scores_gemma":[0.9976689,0.00024698264,0.00012849104,0.0017822993,0.00003984534,0.0001334686],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007052582,0.0002672709,0.00028988518,0.0002233728,0.00022646239,0.0009284169,0.0016539773,0.000102774255,0.00000848193],"category_scores_gemma":[0.00007541623,0.00025594182,0.000027831757,0.00041542167,0.00020013266,0.0027848957,0.0006467846,0.0001863521,0.000039111863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045046418,0.0026498875,0.027226582,0.0001597415,0.000081414255,0.00015028105,0.008243206,0.00007103648,0.0054181023,0.07735839,0.21603122,0.6625651],"study_design_scores_gemma":[0.005213499,0.0010599416,0.08772157,0.00214328,0.00010193425,0.00023981769,0.0076231235,0.7843979,0.0019431373,0.0031885367,0.102662414,0.00370485],"about_ca_topic_score_codex":0.00036556093,"about_ca_topic_score_gemma":0.0006125271,"teacher_disagreement_score":0.78432685,"about_ca_system_score_codex":0.000040887902,"about_ca_system_score_gemma":0.00018145371,"threshold_uncertainty_score":0.9999893},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07185902,0.00012312566,0.91555595,0.011329517,0.00033023662,0.00032411027,0.00007418611,0.00023715834,0.00016667023],"genre_scores_gemma":[0.36322558,0.000014328145,0.63530993,0.0005844923,0.00037562518,0.0002669396,0.0000991763,0.000014674626,0.00010924073],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987613,0.000016063907,0.00019050037,0.0004953501,0.00022227521,0.0003145034],"domain_scores_gemma":[0.998292,0.00036268757,0.00012371181,0.00104035,0.00008444188,0.00009675352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002210485,0.00013779536,0.00013602844,0.00006483645,0.00026240453,0.00023493344,0.0012775199,0.00008061025,0.000023384799],"category_scores_gemma":[0.00038112444,0.00013680827,0.00007004939,0.0002506195,0.000027771162,0.00037549675,0.0005300463,0.00013444592,0.000082206374],"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":[0.00001891485,0.0004947947,0.008461533,0.00015278498,0.00011695795,0.00004231899,0.010273526,0.00019482565,0.0011663449,0.6880295,0.0043592667,0.28668922],"study_design_scores_gemma":[0.001030217,0.00035215804,0.009319742,0.0003537414,0.000021127376,0.000080647944,0.0007091414,0.006155841,0.0071736784,0.9558035,0.01826857,0.00073160836],"about_ca_topic_score_codex":0.0002497753,"about_ca_topic_score_gemma":0.00007399392,"teacher_disagreement_score":0.29136658,"about_ca_system_score_codex":0.000035571513,"about_ca_system_score_gemma":0.00006890111,"threshold_uncertainty_score":0.5578879},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00081590953,0.00004642912,0.9894293,0.0019982832,0.0001333171,0.00012094617,0.00005422276,0.0002207733,0.0071808207],"genre_scores_gemma":[0.11258746,0.0000017801955,0.8837433,0.00031589248,0.00008543864,0.000021034752,0.0026122348,0.000007077038,0.0006258122],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889594,0.00002776644,0.00025661467,0.00043561682,0.00024360692,0.00014045055],"domain_scores_gemma":[0.9983879,0.00033788983,0.000100920304,0.001077361,0.00006928836,0.000026680373],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023728125,0.00009124808,0.00008029195,0.000039133258,0.0002140442,0.00015341259,0.00084146246,0.00004190111,0.000060353872],"category_scores_gemma":[0.00006359723,0.00008662473,0.000020481537,0.0003812339,0.00002550021,0.0013412503,0.0002140799,0.00006034126,0.00017081303],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027394221,0.00031959417,0.019851064,0.000013695385,0.000016745063,0.0000030119072,0.0001475403,0.030052982,0.00020830167,0.72184056,0.12988335,0.0976604],"study_design_scores_gemma":[0.00021186803,0.000006787922,0.0054412005,0.000010613964,0.0000044623557,0.0000020720406,0.0000063888124,0.8962526,0.00019697375,0.0016861499,0.09606882,0.00011209618],"about_ca_topic_score_codex":0.00024351025,"about_ca_topic_score_gemma":0.00003014009,"teacher_disagreement_score":0.8661996,"about_ca_system_score_codex":0.000021580996,"about_ca_system_score_gemma":0.00008354217,"threshold_uncertainty_score":0.35324538},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012472598,0.00042671373,0.98059565,0.0014078666,0.00052384665,0.00017446764,0.0030557145,0.00034462538,0.0009985437],"genre_scores_gemma":[0.6445814,0.0003035009,0.35063124,0.0006728818,0.0002588474,0.000062475316,0.0021565172,0.000031048414,0.0013021133],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.997773,0.00006394223,0.00039921017,0.0011404849,0.00025285778,0.00037052232],"domain_scores_gemma":[0.9936654,0.00032689545,0.000099170255,0.0056838365,0.00007367355,0.00015105026],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00025767714,0.0002756208,0.0002505935,0.00016847078,0.00045294897,0.0010065353,0.0054776412,0.00010263589,0.00004795776],"category_scores_gemma":[0.00005580661,0.0002644818,0.000105453546,0.0006260281,0.000094126175,0.0039624446,0.00014439914,0.00027201508,0.0002608568],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020532716,0.0021144429,0.00015572525,0.0000092581395,0.000113127746,0.000013167568,0.0011025767,0.00008252992,0.0008425939,0.006032854,0.009839436,0.97967374],"study_design_scores_gemma":[0.0075096297,0.0034051384,0.074288696,0.0015124219,0.0007096319,0.00011749928,0.0014798366,0.30309513,0.052909065,0.18510486,0.36235136,0.0075167445],"about_ca_topic_score_codex":0.0001861997,"about_ca_topic_score_gemma":0.00014733316,"teacher_disagreement_score":0.972157,"about_ca_system_score_codex":0.000053744723,"about_ca_system_score_gemma":0.0001393637,"threshold_uncertainty_score":0.99998075},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016804729,0.00016645371,0.98639405,0.00018024872,0.00088598934,0.00057644676,0.000040255625,0.00026170345,0.011326796],"genre_scores_gemma":[0.050899647,0.000022785696,0.945926,0.0017375873,0.00027252824,0.00006838146,0.000043602795,0.000046323818,0.0009831215],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99556327,0.00003099186,0.00058681803,0.002205163,0.00078124827,0.00083252817],"domain_scores_gemma":[0.99686354,0.00029588607,0.00027498495,0.0019793555,0.00020286352,0.0003833842],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0006710158,0.00061834167,0.00059857545,0.0008357196,0.00034953855,0.0006704769,0.0053874324,0.00032383765,0.000019160427],"category_scores_gemma":[0.00007122941,0.0005629013,0.00010701482,0.0010017741,0.0004997169,0.00035629648,0.0020163255,0.0007452026,0.0001288612],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004697824,0.00008156611,0.000040440184,0.000022640603,0.000017663551,0.000027161452,0.0032971774,0.0013880278,0.00008563613,0.06171502,0.0001786982,0.9331413],"study_design_scores_gemma":[0.0003467142,0.00028553393,0.0007084993,0.0004483853,0.000019247338,0.00015741396,0.0000011532785,0.9546876,0.00015628463,0.03846909,0.003415831,0.0013042316],"about_ca_topic_score_codex":0.000065513545,"about_ca_topic_score_gemma":0.000026628017,"teacher_disagreement_score":0.9532996,"about_ca_system_score_codex":0.00017779977,"about_ca_system_score_gemma":0.00028876777,"threshold_uncertainty_score":0.9999939},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018178836,0.000014095243,0.9811357,0.000107384665,0.000032709504,0.00007040261,0.000084969695,0.000057584508,0.00031830947],"genre_scores_gemma":[0.60732883,0.0000011601139,0.39246404,0.000010913472,0.000004072169,0.000007803006,0.0001342518,0.0000016555525,0.000047288857],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988225,0.0000994011,0.00032273197,0.00039011147,0.00024610697,0.000119138356],"domain_scores_gemma":[0.99843174,0.0000930593,0.00008046919,0.0013018532,0.00004212569,0.000050721217],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085841666,0.00006316401,0.00017204964,0.00018912967,0.00003340521,0.000037651615,0.0008993158,0.000036598605,0.000019944275],"category_scores_gemma":[0.00014455224,0.00005122929,0.0000338927,0.0011707682,0.000034544264,0.0003488246,0.00023376764,0.00004954302,0.000009915588],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000045570337,0.0014987565,0.041836493,0.0003013859,0.00027985408,0.000007322767,0.0037493862,0.00019848997,0.0011729951,0.43653485,0.0018134547,0.51260245],"study_design_scores_gemma":[0.0003244435,0.000026740512,0.12030079,0.000027234993,0.00006994136,0.0000026147839,0.001318893,0.8760312,0.00019293887,0.000121416946,0.0014079809,0.00017577091],"about_ca_topic_score_codex":0.00071344955,"about_ca_topic_score_gemma":0.00024135501,"teacher_disagreement_score":0.87583274,"about_ca_system_score_codex":0.000033460306,"about_ca_system_score_gemma":0.000041137242,"threshold_uncertainty_score":0.20890698},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0396184,0.0005577809,0.95611477,0.0016601619,0.0015566482,0.000048997677,0.000023048166,0.00007697219,0.00034325314],"genre_scores_gemma":[0.45957115,0.000058657683,0.53996915,0.00023885719,0.00014100596,0.000002583554,0.0000063324646,0.0000027058556,0.000009578953],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983887,0.000015183784,0.0008135203,0.00010285521,0.0005031723,0.00017654929],"domain_scores_gemma":[0.9972487,0.00031112434,0.000826331,0.00060643785,0.0009578108,0.000049589155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011367331,0.00010131183,0.00016155456,0.0010168693,0.00012825929,0.0002166632,0.0027925402,0.000084025545,0.000027673952],"category_scores_gemma":[0.0014553021,0.00008441986,0.00004215798,0.0004729257,0.000057573005,0.007103345,0.0014950542,0.00019543435,0.00008807665],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000068433123,0.000025261717,0.00042187847,0.0000017605875,0.000077949335,0.00008286707,0.0006444442,0.000035899626,0.000009113491,0.013777105,0.0092585515,0.9756583],"study_design_scores_gemma":[0.0024226618,0.00027659812,0.0012021387,0.0010653716,0.00009857241,0.12341207,0.014872892,0.19049056,0.0014410574,0.032463532,0.63139683,0.00085772976],"about_ca_topic_score_codex":7.159464e-7,"about_ca_topic_score_gemma":6.328003e-7,"teacher_disagreement_score":0.9748006,"about_ca_system_score_codex":0.000084683816,"about_ca_system_score_gemma":0.0000615482,"threshold_uncertainty_score":0.5189281},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03725997,0.00021984325,0.95769775,0.0008172377,0.0007616499,0.00023201018,0.0024521474,0.00015615748,0.0004032056],"genre_scores_gemma":[0.28716868,0.00004404531,0.7077588,0.00020903791,0.00060587336,0.00019479552,0.0031103867,0.000029415005,0.0008789708],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865085,0.000028220697,0.0002435612,0.00062810665,0.00016577265,0.0002835028],"domain_scores_gemma":[0.99874645,0.00020002117,0.00012917636,0.00077222695,0.000063737585,0.00008840838],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006619374,0.00014071536,0.00014804919,0.00009334278,0.0003466206,0.0006887125,0.00078759465,0.00007417669,0.0000016691909],"category_scores_gemma":[0.00017427307,0.00014009695,0.000039281447,0.0002345738,0.000033944303,0.0018874296,0.00045567725,0.000078076744,0.000007613485],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057186335,0.0010611799,0.0055026263,0.0003286495,0.00045382578,0.000010164423,0.0032436466,0.00054902874,0.0106354905,0.1440742,0.14220876,0.6918753],"study_design_scores_gemma":[0.0047617694,0.00026069753,0.0036802618,0.00038544642,0.00018359399,0.0000125044635,0.00054476113,0.77513784,0.0029148152,0.0045830463,0.20668305,0.0008522011],"about_ca_topic_score_codex":0.000029676181,"about_ca_topic_score_gemma":0.00002908777,"teacher_disagreement_score":0.7745888,"about_ca_system_score_codex":0.00016137528,"about_ca_system_score_gemma":0.0003562304,"threshold_uncertainty_score":0.66412705},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00030522465,0.000020182419,0.9942149,0.0014915598,0.000105789055,0.00011949096,0.00011428787,0.000070904534,0.0035576555],"genre_scores_gemma":[0.0003559684,0.0000098878245,0.99840736,0.0002974601,0.000047632504,0.000049595943,0.00015653177,0.00000540701,0.00067016383],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889106,0.000033292537,0.00019804222,0.00037425107,0.00028015883,0.00022321317],"domain_scores_gemma":[0.99890596,0.0002846334,0.000061907245,0.0006275674,0.000046088746,0.00007387268],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012023756,0.00006907859,0.00010137554,0.000054272186,0.00007081504,0.00015628451,0.0011073744,0.000061289524,0.000038609327],"category_scores_gemma":[0.0005485429,0.00006389482,0.00001667045,0.00023275918,0.000012483678,0.0005963154,0.0002533414,0.000069878835,0.000038298887],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.360402e-7,0.0000759217,0.0001866759,0.000002452325,0.0000068355866,0.000002758485,0.000120848184,4.011435e-7,0.000014034764,0.021628989,0.020558536,0.9574024],"study_design_scores_gemma":[0.00037363096,0.000013059223,0.0004463682,0.000011052672,0.000002677225,0.0000060514553,0.00008442474,0.94333845,0.00009893498,0.0010880014,0.05442808,0.00010926695],"about_ca_topic_score_codex":0.000038446637,"about_ca_topic_score_gemma":0.000043326887,"teacher_disagreement_score":0.95729315,"about_ca_system_score_codex":0.000044365013,"about_ca_system_score_gemma":0.0001171,"threshold_uncertainty_score":0.2605555},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017360489,0.00013643151,0.9971232,0.0003466486,0.0005689287,0.00019282776,0.000015351616,0.00007436148,0.0013686892],"genre_scores_gemma":[0.13199633,0.00015787907,0.86639917,0.0008861804,0.00032123012,0.000019824574,0.000020155674,0.000035724508,0.00016351805],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975984,0.000016077332,0.0004726375,0.0009743013,0.00057183334,0.00036677014],"domain_scores_gemma":[0.99799806,0.00015628406,0.00015593984,0.0013998813,0.00016376532,0.0001260623],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004971847,0.00028862932,0.0003671644,0.00038851285,0.000096743206,0.00013576094,0.0026825967,0.00018586061,0.000041490217],"category_scores_gemma":[0.00003291471,0.00025869242,0.000097063814,0.0003043167,0.00041958157,0.00038558937,0.0010579221,0.0004162188,0.00006190866],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014008389,0.000037047947,0.000056277895,0.000029976105,0.0000056722943,0.000010783772,0.0003697851,0.00019492758,0.00011679734,0.07671561,0.000012424654,0.9224493],"study_design_scores_gemma":[0.0004230726,0.0004317678,0.0034418874,0.0011480955,0.00002871201,0.000109004766,2.0702625e-7,0.55158734,0.011792284,0.42557007,0.0042047603,0.0012628047],"about_ca_topic_score_codex":0.000044653843,"about_ca_topic_score_gemma":0.0000325666,"teacher_disagreement_score":0.9211865,"about_ca_system_score_codex":0.000090644244,"about_ca_system_score_gemma":0.00021059622,"threshold_uncertainty_score":0.9999865},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037835287,0.000010016899,0.96648455,0.014540771,0.000031140196,0.00007609941,0.0000026652258,0.00033651275,0.014734697],"genre_scores_gemma":[0.2163177,0.0000019521901,0.7750439,0.0009132471,0.00013609548,0.000031157426,0.0000041063654,0.0000046146147,0.007547191],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99940705,0.000011297265,0.00009176339,0.0002228428,0.0001144989,0.00015254793],"domain_scores_gemma":[0.9995613,0.000028069326,0.000015231475,0.00028137612,0.000019658919,0.00009432682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013558601,0.000055509594,0.000051735646,0.000044192922,0.000099298064,0.00014730498,0.0005446011,0.000017676251,0.000057234676],"category_scores_gemma":[0.000023484905,0.000047981594,0.000018453207,0.00021096837,0.000008766317,0.00029088653,0.00014600357,0.00007077835,0.00050398655],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.3024259e-7,0.000021940758,0.00005398782,7.375485e-7,0.0000028784475,5.026802e-7,0.00083152344,0.00066448224,0.00037372374,0.032841645,0.029838523,0.93536985],"study_design_scores_gemma":[0.000069873735,0.000043916585,0.0010544924,0.0000037096534,9.728927e-7,0.000004176125,0.00008232841,0.25781113,0.0005419694,0.00013315193,0.7401678,0.00008646848],"about_ca_topic_score_codex":0.000032541888,"about_ca_topic_score_gemma":0.000023914037,"teacher_disagreement_score":0.93528336,"about_ca_system_score_codex":0.000011494056,"about_ca_system_score_gemma":0.00001810207,"threshold_uncertainty_score":0.64778954},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023060231,0.00075656123,0.95604575,0.03923559,0.00006363491,0.00024738288,0.00011983337,0.00036387637,0.00086134963],"genre_scores_gemma":[0.047799215,0.00019149615,0.9499408,0.00014036917,0.0005897279,0.00009823155,0.00084153656,0.000022703829,0.0003759012],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99842334,0.00006180941,0.00022257288,0.00088583975,0.000175914,0.00023050178],"domain_scores_gemma":[0.9985419,0.00011806924,0.00014846587,0.0010192298,0.000075095726,0.00009725693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037013442,0.00015426576,0.00016673232,0.00007918526,0.00070874783,0.00045471409,0.00096996233,0.000048818496,0.000019514677],"category_scores_gemma":[0.000102973776,0.00015599553,0.000014582864,0.00067891466,0.00006860532,0.0008125189,0.0010231368,0.0002936498,0.000041980333],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034891718,0.000088474764,0.0006760365,0.000013118218,0.000053644348,0.0000043154155,0.0035807132,0.0037457168,0.0016338844,0.040025238,0.0013158985,0.94885945],"study_design_scores_gemma":[0.0008853387,0.00008307632,0.0013414364,0.000051491024,0.000040394672,0.000030557723,0.001040142,0.30015573,0.0003424087,0.0109295035,0.6845813,0.00051865814],"about_ca_topic_score_codex":0.00029452774,"about_ca_topic_score_gemma":0.000094333824,"teacher_disagreement_score":0.94834083,"about_ca_system_score_codex":0.000035529407,"about_ca_system_score_gemma":0.000098128905,"threshold_uncertainty_score":0.6361313},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11838296,0.00014486202,0.8786974,0.0019670487,0.00014167503,0.00019307584,0.00010885849,0.00011294782,0.000251169],"genre_scores_gemma":[0.36692134,0.000018619663,0.63250214,0.00020632123,0.00021765105,0.000028094051,0.000036114525,0.0000094174075,0.00006034442],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99854267,0.000048458354,0.00042831193,0.00043159473,0.00028019585,0.00026877184],"domain_scores_gemma":[0.99739283,0.00015473718,0.00018895144,0.0019453746,0.000092387876,0.00022574094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042162059,0.00013819474,0.0002557992,0.00014250986,0.0001372546,0.00015212657,0.002636224,0.000034620058,0.00006769428],"category_scores_gemma":[0.00008013789,0.00012810246,0.000049391914,0.0004885262,0.000034356766,0.00073726074,0.0005249441,0.00015559816,0.00013797829],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030474573,0.0003000172,0.0038122218,0.0000059683352,0.000013748337,0.0000011661521,0.0004431227,0.00035437892,0.023466172,0.0043025557,0.019812029,0.94748557],"study_design_scores_gemma":[0.0012907767,0.0005956946,0.011781091,0.00017732683,0.000049674032,0.000042757787,0.00036045405,0.53893304,0.07373147,0.002934264,0.36907297,0.0010305021],"about_ca_topic_score_codex":0.00016541446,"about_ca_topic_score_gemma":0.0001346712,"teacher_disagreement_score":0.94645506,"about_ca_system_score_codex":0.000021947257,"about_ca_system_score_gemma":0.000053388292,"threshold_uncertainty_score":0.52238667},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012069492,0.000039917195,0.98246205,0.004548266,0.00009324319,0.0006201181,0.000011422686,0.000068297355,0.00008719973],"genre_scores_gemma":[0.16609254,0.000024049654,0.8333191,0.000060267434,0.0001505645,0.00019146276,0.0000418083,0.00001094773,0.00010921267],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99766964,0.00006168181,0.0006965384,0.00069623993,0.00046981356,0.00040607413],"domain_scores_gemma":[0.9964699,0.001531776,0.00019694355,0.0012748151,0.0003725588,0.00015398061],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003789553,0.0000923316,0.00012744336,0.00018637112,0.00043278505,0.001070901,0.0011693356,0.000053447096,0.000039669845],"category_scores_gemma":[0.0047760513,0.000085305066,0.000023237391,0.0007317806,0.000072651834,0.0016121642,0.0006741449,0.00014834166,0.00013013132],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000047525523,0.00002093393,0.00004315162,0.0000059249824,0.0000026054506,0.0000014405356,0.0002164249,0.00005381408,0.0019202243,0.008570006,0.008132363,0.9810284],"study_design_scores_gemma":[0.000023220366,0.000069990274,0.000058512444,0.000048473587,0.0000017378454,0.00000272508,0.00052470417,0.95000094,0.005163921,0.04022636,0.0037743847,0.0001050058],"about_ca_topic_score_codex":0.00032267984,"about_ca_topic_score_gemma":0.000079913305,"teacher_disagreement_score":0.98092335,"about_ca_system_score_codex":0.00002797425,"about_ca_system_score_gemma":0.00033134926,"threshold_uncertainty_score":0.9999661},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001026559,0.00010837722,0.9968,0.00074042316,0.00034090204,0.00032355616,0.000049821807,0.00011538299,0.0004949891],"genre_scores_gemma":[0.20806713,0.000106431595,0.789721,0.0012293042,0.00043474,0.0000446102,0.00012362802,0.00004564317,0.00022748916],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967581,0.000023217306,0.00044253247,0.0014835973,0.0007458964,0.00054665946],"domain_scores_gemma":[0.99801654,0.00022008595,0.00020354093,0.0013457831,0.00007226447,0.00014176735],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003363924,0.0004838995,0.00044693923,0.00065384933,0.00016724244,0.00039561998,0.0020617617,0.00012385006,0.000015575066],"category_scores_gemma":[0.000011371968,0.00037898688,0.000055552115,0.00046030688,0.0002150108,0.0007122986,0.00029762712,0.00058865023,0.000009809083],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034895036,0.00006608089,0.00020687754,0.000020094918,0.0000055675364,0.00007082086,0.00048667495,0.004559022,0.000055230834,0.0022640226,0.000012003917,0.9922501],"study_design_scores_gemma":[0.000934408,0.0006259112,0.0070771426,0.0024003503,0.000025711986,0.00021797618,0.000001909797,0.9690218,0.0022439782,0.0117501,0.00393091,0.0017698201],"about_ca_topic_score_codex":0.00012266527,"about_ca_topic_score_gemma":0.0007501058,"teacher_disagreement_score":0.9904803,"about_ca_system_score_codex":0.00025314197,"about_ca_system_score_gemma":0.00021575896,"threshold_uncertainty_score":0.9998662},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016503904,0.00007348708,0.9805263,0.0002067171,0.0006310102,0.000723813,0.0003148335,0.00012342229,0.0008964554],"genre_scores_gemma":[0.9839448,0.00015985416,0.010961013,0.000055072785,0.00014959506,0.00036864303,0.000108716486,0.00003487113,0.004217481],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980485,0.000074661846,0.0007022387,0.0005528296,0.00032203944,0.00029972006],"domain_scores_gemma":[0.9985407,0.00012463043,0.0003049426,0.0007040203,0.00021329353,0.000112400405],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00029763955,0.00024380865,0.0003289925,0.00017918815,0.00018709527,0.00020382417,0.00041666432,0.00014493211,0.000014128464],"category_scores_gemma":[0.0000033607992,0.0002468912,0.0001073709,0.0002621965,0.000083631974,0.00016877233,0.000006470546,0.00011087344,0.00002365092],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023421727,0.004494775,0.0018973419,0.0014787556,0.0005989974,0.000012848497,0.0032360505,0.06012291,0.03798206,0.5758094,0.053441163,0.26069146],"study_design_scores_gemma":[0.0030005137,0.0005202587,0.002668378,0.00018846987,0.00019467958,0.000043694832,0.00020845814,0.89551264,0.022099484,0.0011372918,0.073587336,0.00083878695],"about_ca_topic_score_codex":0.0003207327,"about_ca_topic_score_gemma":0.00008218973,"teacher_disagreement_score":0.96956533,"about_ca_system_score_codex":0.000044857443,"about_ca_system_score_gemma":0.000050133836,"threshold_uncertainty_score":0.99999833},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.2649057e-7,0.45809528,0.54044616,0.000024780915,0.0004838525,0.00034366085,0.00025425997,0.0002554727,0.000096075244],"genre_scores_gemma":[0.0000055483683,0.2733306,0.72207355,0.000026228749,0.00067457056,0.00005778322,0.0035780475,0.00007559685,0.00017809201],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99593186,0.00068766513,0.00093652867,0.0015475288,0.00030895873,0.0005874268],"domain_scores_gemma":[0.9888154,0.0043515884,0.00070415996,0.0058484524,0.00017747465,0.00010290584],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.006375656,0.00049981097,0.0012695425,0.00020406302,0.00039429453,0.00073256367,0.012923072,0.00020172092,9.628759e-7],"category_scores_gemma":[0.0020717923,0.00045128027,0.00021723294,0.0007908252,0.00005796782,0.00032638697,0.0065852995,0.00030671974,0.000033443986],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.038353e-8,0.000030703653,0.0000075163716,0.0012756452,0.00004684846,0.0000027888204,0.000022460084,0.0000031642694,2.1327013e-8,0.00027955562,0.014628282,0.98370296],"study_design_scores_gemma":[0.00009443065,0.000019862942,0.000023879547,0.0036550425,0.00010732909,0.000035143108,0.0000026612638,0.06218503,1.4310656e-7,0.000122055004,0.93324715,0.0005072849],"about_ca_topic_score_codex":0.00021044856,"about_ca_topic_score_gemma":0.00004462467,"teacher_disagreement_score":0.98319566,"about_ca_system_score_codex":0.000058329264,"about_ca_system_score_gemma":0.0003495356,"threshold_uncertainty_score":0.9997939},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026711675,0.00007556439,0.9773219,0.002250181,0.000103192455,0.00011179052,0.000004481524,0.00041242884,0.01704928],"genre_scores_gemma":[0.3508743,0.000043751927,0.6116766,0.00083230925,0.00021705273,0.00012285894,0.000021943419,0.000018537572,0.03619268],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99927026,0.00001548112,0.00011660752,0.00028170442,0.00014413965,0.00017181275],"domain_scores_gemma":[0.99957174,0.000035653884,0.000034228262,0.00026814584,0.00003648967,0.000053736516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012124023,0.00007083416,0.000064111286,0.000039744747,0.00018013494,0.00020390283,0.00042966002,0.00003444424,0.00013302139],"category_scores_gemma":[0.000014524296,0.00006455558,0.000022037799,0.00045002892,0.000011930101,0.00043401058,0.00008596833,0.000083491934,0.00030782548],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.9430643e-7,0.00006802029,0.00078496285,0.0000052485293,0.000009662579,8.7723504e-7,0.00028515633,0.0000043378104,0.002335021,0.086255,0.233368,0.6768834],"study_design_scores_gemma":[0.0001405726,0.000030948697,0.00039442,0.00000564933,0.0000030299711,0.000015629359,0.000012190862,0.84258705,0.0039027575,0.0006683864,0.15207969,0.00015968223],"about_ca_topic_score_codex":0.00003943709,"about_ca_topic_score_gemma":0.0000029247935,"teacher_disagreement_score":0.8425827,"about_ca_system_score_codex":0.000019813522,"about_ca_system_score_gemma":0.0000055460528,"threshold_uncertainty_score":0.39565763},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02302212,0.000040130184,0.95505,0.0026363104,0.00016410013,0.00009332949,0.000006463567,0.00021797026,0.018769572],"genre_scores_gemma":[0.25873888,0.000030142864,0.71697354,0.0006794615,0.0003018285,0.00006158106,0.00003707056,0.0000090316025,0.023168473],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992342,0.000019727991,0.00014069528,0.00024213213,0.00019059042,0.00017263296],"domain_scores_gemma":[0.9994894,0.000026352891,0.00008132775,0.00029674688,0.000050435192,0.0000557356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014708922,0.00007183685,0.000074667914,0.000037860627,0.00017846968,0.00026049305,0.0002450903,0.000039521594,0.000105821484],"category_scores_gemma":[0.0000272014,0.00006649844,0.000022749118,0.0001986156,0.000006022083,0.0004722478,0.00006993323,0.000049141057,0.00027220737],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.7417856e-7,0.00021970023,0.016196022,0.0000045640586,0.000047074707,0.0000040226228,0.0030239325,0.00058787444,0.0021484683,0.03842347,0.28846934,0.650875],"study_design_scores_gemma":[0.00017858563,0.000014312526,0.0021282248,0.0000025822408,0.0000037367704,0.0000039161464,0.000023305063,0.98061806,0.00027498318,0.00010081985,0.016532216,0.00011923399],"about_ca_topic_score_codex":0.00008111332,"about_ca_topic_score_gemma":0.0000420004,"teacher_disagreement_score":0.9800302,"about_ca_system_score_codex":0.000068341404,"about_ca_system_score_gemma":0.0000106758225,"threshold_uncertainty_score":0.34987658},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42107296,0.00008210234,0.57766455,0.00016387919,0.0008718222,0.00008258787,0.000020174564,0.000035737365,0.0000061753994],"genre_scores_gemma":[0.92594177,0.00006784201,0.072319046,0.0001906084,0.0013992732,0.000011879824,0.000032514636,0.000014925562,0.000022169008],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998575,0.00006924753,0.0005920063,0.00030155916,0.00017649379,0.0002857367],"domain_scores_gemma":[0.99844956,0.00030924013,0.00053148356,0.00032583624,0.00024702877,0.00013683706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015326115,0.00018869035,0.00035549022,0.00009988548,0.00024533077,0.00014616961,0.00074136443,0.00018945137,0.000030639807],"category_scores_gemma":[0.000020267633,0.0001558691,0.00019904863,0.00017258916,0.000055528908,0.00047786933,0.00012434962,0.0004379388,0.0000010336139],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035733107,0.0008532516,0.0145763615,0.000016260166,0.00046583085,0.0002591396,0.0028417516,0.16235092,0.0026300761,0.0007801965,0.035624072,0.77924484],"study_design_scores_gemma":[0.00094843446,0.00049590576,0.009089072,0.0001019285,0.000036473266,0.0005123077,0.00018359983,0.98654217,0.00030687885,0.00009822532,0.0014751559,0.00020983658],"about_ca_topic_score_codex":0.000040247203,"about_ca_topic_score_gemma":0.000052848616,"teacher_disagreement_score":0.8241913,"about_ca_system_score_codex":0.00007352995,"about_ca_system_score_gemma":0.00003583239,"threshold_uncertainty_score":0.63561577},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058662996,0.00015666404,0.93357825,0.0010660327,0.0013515427,0.00035818547,0.000011529536,0.000013865833,0.004800908],"genre_scores_gemma":[0.48684788,0.000019199497,0.51304686,0.000018677745,0.0000385475,0.0000037053856,0.000014621546,0.0000014643805,0.000009007796],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987132,0.00008386548,0.00079403905,0.000076088174,0.00024378394,0.00008903521],"domain_scores_gemma":[0.9987299,0.00007245642,0.00051891484,0.0005473978,0.000108983615,0.0000223529],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027492035,0.0000658588,0.00014533728,0.00028735204,0.00004624502,0.00010035924,0.0012619423,0.000027047276,0.000004765708],"category_scores_gemma":[0.000053633685,0.000045702258,0.000027449349,0.0004964261,0.000021775279,0.0016010265,0.00043595026,0.000256054,0.0000040971454],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000135008695,0.0002673316,0.0010054384,0.00009949996,0.00003309423,0.000001379432,0.0064365063,0.004534418,0.00043303132,0.16830981,0.0048070867,0.8140589],"study_design_scores_gemma":[0.0014840787,0.00012615675,0.18384752,0.00017574558,0.00004756831,0.000084907,0.0061007994,0.65742034,0.0016793357,0.0154880425,0.13326174,0.00028376738],"about_ca_topic_score_codex":0.000013830716,"about_ca_topic_score_gemma":0.000014572324,"teacher_disagreement_score":0.8137751,"about_ca_system_score_codex":0.0000330573,"about_ca_system_score_gemma":0.000032554843,"threshold_uncertainty_score":0.23450238},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023064127,0.000011290604,0.9725104,0.0008741829,0.0000515512,0.000026047146,0.000015027597,0.000041959735,0.0034054285],"genre_scores_gemma":[0.844787,0.000013688586,0.15136582,0.00015235279,0.000019074561,0.00000585351,0.0000032901712,0.0000021120236,0.0036508164],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996479,0.0000040861496,0.00007939226,0.00012282377,0.00007597847,0.00006980272],"domain_scores_gemma":[0.999549,0.000019310555,0.000023659302,0.00037156438,0.000021433416,0.000015075628],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000025551717,0.000033981538,0.000048063353,0.000019592526,0.000021042735,0.000050951214,0.00037824173,0.000010691022,0.00008178175],"category_scores_gemma":[0.000004138605,0.000026603246,0.000012588159,0.00016125904,0.0000106685975,0.00034686946,0.000113314716,0.000021643118,0.000066812325],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.2306526e-7,0.0001837637,0.00068814104,0.0000073828965,0.000010836238,0.0000018211085,0.00023152004,0.000014389357,0.00033206932,0.50323623,0.014048618,0.4812451],"study_design_scores_gemma":[0.0009127483,0.00020071017,0.053344402,0.000053645526,0.000015822276,0.000023329336,0.00012825798,0.84100825,0.029268287,0.010884188,0.06342236,0.0007380306],"about_ca_topic_score_codex":0.00016111466,"about_ca_topic_score_gemma":0.000006272691,"teacher_disagreement_score":0.8409938,"about_ca_system_score_codex":0.0000027175502,"about_ca_system_score_gemma":0.0000031881198,"threshold_uncertainty_score":0.10848489},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037881888,0.000010062858,0.9818691,0.00009990067,0.00004044772,0.00018318134,0.000015284106,0.00013811185,0.013855725],"genre_scores_gemma":[0.029292513,0.0000010048522,0.96950567,0.00009088052,0.000009301815,0.00012348502,0.00004773003,0.0000041277845,0.00092528167],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99940085,0.000015949789,0.00011470121,0.00021095076,0.000120097764,0.00013746702],"domain_scores_gemma":[0.99950325,0.00006135404,0.00007762188,0.0002517096,0.00007649534,0.000029534569],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004247513,0.000053169802,0.00006488836,0.000028941286,0.00012351485,0.000080183076,0.000405124,0.00002835156,0.000004738568],"category_scores_gemma":[0.000029379124,0.000047422367,0.000030882176,0.0001025552,0.000005682359,0.0002318562,0.00008734956,0.000034188794,0.000026989543],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000048820134,0.00042731166,0.0012418736,0.000029630477,0.000076960416,2.3869288e-7,0.0028013214,0.00006124832,0.0025574274,0.34748146,0.0029921,0.6423255],"study_design_scores_gemma":[0.00013127712,0.000032137366,0.0034454362,0.0000019607064,0.0000063100215,9.739238e-7,0.000024071705,0.9922673,0.00022144975,0.003545618,0.00025115436,0.00007232713],"about_ca_topic_score_codex":0.000031367897,"about_ca_topic_score_gemma":0.0000015511827,"teacher_disagreement_score":0.99220604,"about_ca_system_score_codex":0.000044531393,"about_ca_system_score_gemma":0.000018487288,"threshold_uncertainty_score":0.1933828},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056417402,0.0002617834,0.61033726,0.0016268857,0.00038336447,0.0004390951,0.000009375156,0.0010251049,0.32949972],"genre_scores_gemma":[0.1809955,0.000008897424,0.8134237,0.0004630229,0.000050528324,0.00013691031,0.0000047370336,0.000008598798,0.0049081016],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99919826,0.000018656488,0.00012353067,0.00033331625,0.00014082984,0.00018543554],"domain_scores_gemma":[0.99927366,0.000042335512,0.000057516463,0.00050315436,0.000060096703,0.00006321465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014961317,0.00009512006,0.00009043149,0.000054342127,0.000075583266,0.00008860485,0.0012196106,0.00002447354,0.00014335492],"category_scores_gemma":[0.0000080909585,0.00006726759,0.00001666634,0.00017603779,0.00014368327,0.00092658575,0.00020421256,0.000049264534,0.000025591848],"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":[0.000010309417,0.00026325308,0.011812687,0.000058930935,0.000051228897,0.000036422847,0.01538922,0.00003836391,0.0001769997,0.8011799,0.056473877,0.1145088],"study_design_scores_gemma":[0.0014423025,0.0014026106,0.019066693,0.00027722225,0.00006210643,0.00026497833,0.0051523275,0.2786514,0.004671103,0.033703852,0.6525133,0.0027921104],"about_ca_topic_score_codex":0.0004145397,"about_ca_topic_score_gemma":0.00011661496,"teacher_disagreement_score":0.767476,"about_ca_system_score_codex":0.00007159786,"about_ca_system_score_gemma":0.00021351858,"threshold_uncertainty_score":0.27430928},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.072511435,0.00026700227,0.92469454,0.00014879201,0.00022059775,0.00031802384,0.0006693034,0.00006739095,0.0011029463],"genre_scores_gemma":[0.5328502,0.0000748783,0.46486303,0.000044434193,0.00015698472,0.00025820197,0.0006999473,0.000010372919,0.0010419404],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894816,0.000027880653,0.00023430448,0.0003464371,0.00028293685,0.00016026763],"domain_scores_gemma":[0.99867135,0.00020363789,0.00009252752,0.00069555675,0.00029298462,0.00004395027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041528372,0.00009546771,0.00012779463,0.000055646553,0.00010725076,0.000053283915,0.00048774452,0.000022157104,0.000064359796],"category_scores_gemma":[0.00009044195,0.000082377366,0.000042245785,0.00033088613,0.000034049317,0.0011996167,0.0001799305,0.000038661485,0.00004417973],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020163234,0.0004062198,0.00082026876,0.0000137207835,0.000032695632,9.747042e-8,0.00046915247,0.000095379335,0.0005101353,0.012403289,0.016157199,0.9690898],"study_design_scores_gemma":[0.0004800236,0.000044305318,0.0028901028,0.000021316657,0.00002604578,6.3289866e-7,0.000041340492,0.9782483,0.0055126618,0.00007526162,0.012549273,0.00011076544],"about_ca_topic_score_codex":0.00006384033,"about_ca_topic_score_gemma":0.0000122376205,"teacher_disagreement_score":0.9781529,"about_ca_system_score_codex":0.000031404645,"about_ca_system_score_gemma":0.000040155086,"threshold_uncertainty_score":0.33592513},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007027647,0.000019984225,0.96271867,0.0025437465,0.000023763958,0.000041991276,5.814743e-7,0.00014460934,0.033803906],"genre_scores_gemma":[0.20293298,0.000010009769,0.7916515,0.00055825594,0.00002541155,0.000023627106,0.0000010631659,0.0000036632214,0.004793514],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996269,0.0000042238185,0.000053822998,0.00013568823,0.00008409831,0.000095298376],"domain_scores_gemma":[0.99957085,0.000014275507,0.000014238891,0.00035291474,0.000011427787,0.000036293495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00003517041,0.00004241969,0.000037837075,0.000017479233,0.00006973233,0.0001386337,0.00038050863,0.000007522528,0.00010333587],"category_scores_gemma":[9.858884e-7,0.000029747049,0.000007516062,0.00012307952,0.000012428786,0.00024650054,0.00012759096,0.000029043174,0.00018823227],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.9635364e-7,0.000078575686,0.00025103442,0.000004703493,0.000013700371,0.000007714984,0.0006664769,0.00012011825,0.000052951542,0.11903495,0.033578064,0.8461913],"study_design_scores_gemma":[0.00023844579,0.00008200607,0.0007999474,0.000011947171,0.0000024599908,0.00003540661,0.000046926656,0.8317521,0.0003950968,0.0005360868,0.1659216,0.00017792877],"about_ca_topic_score_codex":0.000025111192,"about_ca_topic_score_gemma":0.000013493677,"teacher_disagreement_score":0.84601337,"about_ca_system_score_codex":0.0000068751533,"about_ca_system_score_gemma":0.0000019136094,"threshold_uncertainty_score":0.24194078},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004945277,0.00005683874,0.99082786,0.0013700682,0.00003241964,0.00012100698,0.0000031321276,0.00007052168,0.0025728776],"genre_scores_gemma":[0.5415019,0.000014093599,0.45804355,0.00019314399,0.00011743621,0.000017617389,0.0000016461644,0.0000048601987,0.00010575591],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99944246,0.0000152385155,0.000085753694,0.00022450146,0.000085643085,0.00014639048],"domain_scores_gemma":[0.9995685,0.000043814252,0.00003233484,0.0003120522,0.000006112605,0.00003718075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017609439,0.00006982519,0.00005919902,0.000029276505,0.00027270135,0.00026600444,0.00032337636,0.000018259443,0.0000022491424],"category_scores_gemma":[0.000005434782,0.000044505585,0.000014988985,0.00018352903,0.000035151068,0.00067762134,0.00024563473,0.000058873098,0.000002996447],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015091773,0.000095216856,0.0002312211,0.000010058916,0.000028105907,0.0000011137855,0.008716587,0.00072629045,0.00095883623,0.7372961,0.00022211346,0.25171283],"study_design_scores_gemma":[0.00009541078,0.000005331878,0.0005778122,0.000007732452,0.000003587494,0.000012168911,0.00062258024,0.99607664,0.000052195675,0.00057203125,0.0018942807,0.00008022122],"about_ca_topic_score_codex":0.00021612397,"about_ca_topic_score_gemma":0.000024888519,"teacher_disagreement_score":0.99535036,"about_ca_system_score_codex":0.000045360346,"about_ca_system_score_gemma":0.000008555492,"threshold_uncertainty_score":0.2565087},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00033825045,0.000038082035,0.98053586,0.0010795086,0.000053945536,0.0000903001,0.000024388912,0.00007841917,0.017761229],"genre_scores_gemma":[0.9339129,0.000015366675,0.063586585,0.0009767853,0.000103267645,0.000038487095,0.00013054263,0.000006192243,0.001229921],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994742,0.000027926664,0.00009614699,0.00019926483,0.00012243909,0.00007997385],"domain_scores_gemma":[0.9987844,0.000037873,0.000021723825,0.0011348531,0.000008836322,0.000012312895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023635186,0.000036722115,0.000035899335,0.000025306868,0.000055559456,0.00019621717,0.0016638888,0.000012424972,0.000015988984],"category_scores_gemma":[0.000009501836,0.000022905535,0.000005494551,0.00035987902,0.000008549394,0.0005664224,0.00025472004,0.000029602552,0.0001783004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.0465035e-8,0.00006367502,0.00011122362,0.0000059434406,0.0000018664134,0.0000027926933,0.000531763,0.000018941493,0.00000734786,0.88156545,0.062416065,0.055274837],"study_design_scores_gemma":[0.000047760914,0.000005481269,0.00047633683,0.000005928505,9.309192e-7,0.000007448199,0.00013849366,0.9534606,0.000006134908,0.000063776584,0.045749113,0.000038001144],"about_ca_topic_score_codex":0.000060250502,"about_ca_topic_score_gemma":0.00002459597,"teacher_disagreement_score":0.9534417,"about_ca_system_score_codex":0.000008726912,"about_ca_system_score_gemma":0.000004892258,"threshold_uncertainty_score":0.3091947},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020114027,0.000008950567,0.97529674,0.00020590231,0.00018122447,0.00008976294,0.0000018327131,0.00009396532,0.0040076063],"genre_scores_gemma":[0.33218268,0.000117532094,0.66700786,0.0005298311,0.00008802383,0.00001682047,0.0000075817393,0.0000025639604,0.000047113317],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984671,0.000022902574,0.00020478417,0.00024909698,0.0007749864,0.00028115523],"domain_scores_gemma":[0.9988793,0.00018814909,0.000051817966,0.00038281543,0.00035338177,0.00014453992],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0012885339,0.00007383148,0.00007234338,0.000524651,0.0014556785,0.00059338997,0.00097055937,0.000026410593,0.000002396138],"category_scores_gemma":[0.00005633367,0.000061540675,0.000014970484,0.0016792632,0.00037336093,0.007385445,0.00062225026,0.00021657966,0.00025783674],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.1734314e-7,0.000010832303,0.000113878166,0.0000013027806,4.9501506e-7,9.3282125e-7,0.0007802389,0.0005600849,0.0000035268913,0.044573773,0.001673783,0.95228046],"study_design_scores_gemma":[0.00014899777,0.00013289759,0.025063766,0.000015442418,2.0084916e-7,0.000055190525,0.00003898226,0.91332155,0.000076085664,0.00056346285,0.060499582,0.00008382869],"about_ca_topic_score_codex":0.000009965557,"about_ca_topic_score_gemma":1.8018736e-7,"teacher_disagreement_score":0.9521966,"about_ca_system_score_codex":0.000033820044,"about_ca_system_score_gemma":0.00012423084,"threshold_uncertainty_score":0.9998443},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48380858,0.0010353011,0.49695697,0.007087819,0.0004393926,0.0012068319,0.0065066232,0.00035702865,0.002601437],"genre_scores_gemma":[0.59538144,0.0000055392297,0.40398932,0.00006690396,0.00019081337,0.000036146885,0.00026207377,0.000009360727,0.000058399837],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990915,0.0000015484835,0.00018999407,0.00038336238,0.00017032887,0.00016324497],"domain_scores_gemma":[0.99909496,0.00011667861,0.00014433054,0.0005229378,0.000092742695,0.000028320497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000119599215,0.00009825675,0.000110005516,0.000026505115,0.00012414203,0.00016284948,0.0019701282,0.00003742129,0.0000051928546],"category_scores_gemma":[0.00004136396,0.00006861955,0.000025213443,0.00020949513,0.000043080618,0.00042698422,0.0004195703,0.00005949001,0.0000012838636],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000505573,0.000072501505,0.0028418142,0.000030613504,0.000048392158,4.299276e-7,0.00094685605,0.000009957803,0.009650298,0.036557183,0.0752696,0.8745673],"study_design_scores_gemma":[0.00079211476,0.0000878819,0.019621497,0.00008814884,0.00009546349,0.000009952766,0.00066190143,0.8553546,0.019511033,0.033116866,0.07027428,0.00038628065],"about_ca_topic_score_codex":0.00045338558,"about_ca_topic_score_gemma":0.00006692428,"teacher_disagreement_score":0.87418103,"about_ca_system_score_codex":0.000010709114,"about_ca_system_score_gemma":0.000030629228,"threshold_uncertainty_score":0.3661021},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0100031085,0.00017015584,0.8851843,0.0048505156,0.00014736775,0.00012243121,0.000006903409,0.0004517697,0.09906343],"genre_scores_gemma":[0.111248046,0.00002130891,0.8775625,0.0006107306,0.00009276615,0.000040340565,0.000006070582,0.000008015424,0.01041017],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99926424,0.000011960315,0.00013246118,0.0002657345,0.00014136703,0.00018426614],"domain_scores_gemma":[0.9990822,0.00005267522,0.00003522858,0.0007309187,0.00002584631,0.000073128715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009811573,0.00006925323,0.00006451794,0.000041210824,0.00011413076,0.0002123151,0.0010727152,0.000021646109,0.00029445603],"category_scores_gemma":[0.000030649917,0.000060886632,0.000023431225,0.00024993395,0.000012466913,0.0004986564,0.00042095874,0.000049950395,0.0003058654],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.7618203e-7,0.00014672978,0.00088359916,0.000010382369,0.000016780348,0.000010303357,0.0026739752,0.00003124523,0.000612312,0.081558645,0.41350374,0.5005521],"study_design_scores_gemma":[0.00010133605,0.000017726867,0.00068770756,0.000011041021,0.0000016792941,0.000011198569,0.000030080695,0.7158704,0.0003616792,0.0006138028,0.28216186,0.00013151788],"about_ca_topic_score_codex":0.000043919517,"about_ca_topic_score_gemma":0.0000027680328,"teacher_disagreement_score":0.7158391,"about_ca_system_score_codex":0.000012693606,"about_ca_system_score_gemma":0.000005786358,"threshold_uncertainty_score":0.3931383},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005599386,0.000037734982,0.99550045,0.0005922342,0.00045760418,0.0004113474,0.000031212643,0.00027380147,0.0021356575],"genre_scores_gemma":[0.0673417,0.000008601211,0.9294298,0.00053735176,0.0005867802,0.00015981834,0.0002427057,0.000015393574,0.0016778397],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987229,0.00001466904,0.0002861797,0.0004515072,0.00021920376,0.00030554738],"domain_scores_gemma":[0.99916077,0.000086643086,0.000067079345,0.0004609398,0.00010747718,0.00011708825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005858813,0.00013317703,0.00011271531,0.00008330122,0.00022816694,0.00016317406,0.00041652034,0.00006932652,0.000032656353],"category_scores_gemma":[0.0000122189595,0.0001221135,0.00007132282,0.00029314085,0.00001997671,0.00048633807,0.000035124274,0.00006991195,0.000031202486],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000067849232,0.00011093043,0.000017598588,0.000007718743,0.000019934547,6.2380457e-7,0.0003286865,0.00012558974,0.0028773427,0.05648828,0.005072024,0.9349445],"study_design_scores_gemma":[0.00041473142,0.00015315023,0.0009801143,0.000005285128,0.000020172327,0.0000049721866,0.00005029597,0.9512817,0.0040717283,0.0023553048,0.040451556,0.00021093358],"about_ca_topic_score_codex":0.000048374695,"about_ca_topic_score_gemma":0.00012472861,"teacher_disagreement_score":0.95115614,"about_ca_system_score_codex":0.00004254995,"about_ca_system_score_gemma":0.000036732963,"threshold_uncertainty_score":0.49796444},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10436482,0.0035906478,0.8863515,0.00035428198,0.0007756107,0.0005025151,0.00026472748,0.00014575999,0.0036500834],"genre_scores_gemma":[0.50539064,0.0035299768,0.48878798,0.00059196487,0.00055226794,0.000037392067,0.00045462715,0.00008670633,0.0005684163],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9971031,0.00012241176,0.0008475357,0.00077382853,0.00067981525,0.00047329595],"domain_scores_gemma":[0.9962493,0.0004794506,0.00079014496,0.001871688,0.00029480646,0.00031461724],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.002933923,0.00026414858,0.0004649972,0.00059369433,0.00046860075,0.0023773757,0.010879196,0.00010039508,0.0005837692],"category_scores_gemma":[0.00036342654,0.00025515442,0.00006755294,0.0017695737,0.000104818224,0.0053931847,0.0039736643,0.00030498143,0.000019892075],"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":[0.0000957036,0.001161163,0.20932053,0.00012603817,0.00038420287,0.00034410425,0.0013319998,0.0051308246,0.020983782,0.0025838502,0.19749622,0.5610416],"study_design_scores_gemma":[0.0013822776,0.00004908361,0.5396767,0.0006829529,0.00016304108,0.00029755617,0.0005114366,0.36221486,0.015820518,0.0018426595,0.07569043,0.001668456],"about_ca_topic_score_codex":0.00040765334,"about_ca_topic_score_gemma":0.00006777459,"teacher_disagreement_score":0.55937314,"about_ca_system_score_codex":0.0000776581,"about_ca_system_score_gemma":0.00018898437,"threshold_uncertainty_score":0.99999005},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006667471,0.000015586367,0.99134326,0.0002766801,0.00033301153,0.00035527238,0.00001650346,0.000046218574,0.00094597356],"genre_scores_gemma":[0.5587106,0.0000051529473,0.44071546,0.0003397899,0.00007674473,0.00007619552,0.000047368383,0.0000022971496,0.000026419302],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99920964,0.000010040746,0.00028709267,0.00020411618,0.00016499545,0.00012414124],"domain_scores_gemma":[0.99895257,0.000051048035,0.00014153968,0.0006569276,0.000147001,0.00005093625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007597708,0.000058646903,0.0000890783,0.00016905076,0.000120078446,0.00026236102,0.0011734894,0.00002065809,4.02088e-7],"category_scores_gemma":[0.00002466881,0.00005279696,0.000008377395,0.00047121526,0.00008766671,0.005972818,0.00041717762,0.000034694232,0.000004297367],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001602877,0.000024582027,0.00032290837,0.00016389664,9.743957e-7,1.2893006e-8,0.00046856413,0.00007099247,0.000046620193,0.16390151,0.0010618382,0.8339365],"study_design_scores_gemma":[0.0001850766,0.00003762328,0.018763684,0.00009529696,0.0000012111896,0.000004936911,0.00003229405,0.914147,0.00025547805,0.00022738315,0.06616398,0.00008602902],"about_ca_topic_score_codex":0.000011692111,"about_ca_topic_score_gemma":3.242151e-7,"teacher_disagreement_score":0.91407603,"about_ca_system_score_codex":0.000021370963,"about_ca_system_score_gemma":0.0002075086,"threshold_uncertainty_score":0.43301487},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00038121137,0.00038766945,0.9914629,0.0056054145,0.00085354695,0.00028403246,0.00009248239,0.00014700854,0.00078576506],"genre_scores_gemma":[0.061649013,0.00009972451,0.92472017,0.010758099,0.0022856386,0.000029906161,0.00007441646,0.000052724536,0.00033029047],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965734,0.00003141734,0.0005051002,0.001420367,0.0008526213,0.00061710883],"domain_scores_gemma":[0.99670917,0.0007808671,0.0003227069,0.0019424692,0.00010807613,0.00013673275],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00080631254,0.00042547385,0.0003325776,0.00019730347,0.00041677285,0.0010298437,0.0051365085,0.00019908638,0.00004516138],"category_scores_gemma":[0.000059485435,0.00031736135,0.00011608523,0.00026802902,0.0002975991,0.0005426779,0.0017364322,0.0009000446,0.000082189545],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.555982e-7,0.00001735688,0.00033072048,0.000005198506,0.00001577319,0.000023933113,0.0015670508,0.004101165,0.00005449646,0.0075929845,0.00021342738,0.98607725],"study_design_scores_gemma":[0.000285978,0.000086518055,0.0012889301,0.00065018766,0.000024546713,0.000020437457,0.0000012056393,0.8130358,0.00074895244,0.15475877,0.028050508,0.0010482088],"about_ca_topic_score_codex":0.0002303369,"about_ca_topic_score_gemma":0.00041674936,"teacher_disagreement_score":0.98502904,"about_ca_system_score_codex":0.00022268138,"about_ca_system_score_gemma":0.00025829475,"threshold_uncertainty_score":0.9999278},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06702692,0.0000074982718,0.9316217,0.00026896113,0.00038704043,0.00016781024,0.00015373364,0.00020590858,0.00016044803],"genre_scores_gemma":[0.19505157,0.000004372693,0.80341226,0.00018935774,0.00034738058,0.000015253786,0.00083428354,0.000009723387,0.00013578916],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987674,0.000020717576,0.00022420131,0.00051354937,0.00020738597,0.00026676385],"domain_scores_gemma":[0.99823934,0.0004566858,0.0001635675,0.0009438576,0.00011178914,0.00008478002],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009878945,0.000094274874,0.000099719255,0.000045002784,0.00022453947,0.00027244663,0.0008830848,0.00009000734,0.0000060353746],"category_scores_gemma":[0.000048767855,0.00009152622,0.000022474173,0.00014982681,0.0000062479835,0.0005110528,0.00015862561,0.00007214001,0.000013796259],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011921661,0.0004229432,0.00032104115,0.0000046923824,0.00006222022,0.0000037107882,0.00057980756,0.0027227227,0.006672899,0.15998106,0.005347376,0.8238696],"study_design_scores_gemma":[0.00016224461,0.000023049091,0.0013367148,0.000006146981,0.00001180643,0.0000012335648,0.00017255418,0.99502796,0.001380676,0.00050103414,0.0012495819,0.00012700549],"about_ca_topic_score_codex":0.00018077332,"about_ca_topic_score_gemma":0.00008619299,"teacher_disagreement_score":0.9923052,"about_ca_system_score_codex":0.0000692012,"about_ca_system_score_gemma":0.000021120224,"threshold_uncertainty_score":0.37323308},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3299036,0.00010161721,0.6680778,0.0013067345,0.000431141,0.000038941693,0.00003084096,0.000017423627,0.000091889626],"genre_scores_gemma":[0.97852826,0.00037960592,0.020289637,0.0003960224,0.0003011031,0.000004246187,0.000013643334,0.000007661665,0.00007979725],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987628,0.000032021773,0.00046656805,0.00019894332,0.00037896537,0.00016069504],"domain_scores_gemma":[0.99906564,0.00010560715,0.00021586323,0.00011569061,0.0003952377,0.0001019697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033635728,0.0001043153,0.00011327569,0.00017175687,0.0000884481,0.00033392568,0.000642422,0.00004012469,0.00019936332],"category_scores_gemma":[0.000055613804,0.00009764377,0.000048375103,0.0001373101,0.000054403623,0.00082107924,0.00012019151,0.00018835769,0.000106559535],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031849881,0.000076694945,0.0002448278,0.0000040847976,0.000018459328,0.000012046594,0.0005060133,0.00001604773,0.0018268019,0.000064862346,0.00033508372,0.9968919],"study_design_scores_gemma":[0.00017732283,0.0003360708,0.0003991458,0.00024543487,0.000018376655,0.00052009587,0.0006051901,0.8751477,0.117439926,0.00111158,0.0036058903,0.0003932503],"about_ca_topic_score_codex":0.000024424064,"about_ca_topic_score_gemma":0.0000031840966,"teacher_disagreement_score":0.99649864,"about_ca_system_score_codex":0.000028249919,"about_ca_system_score_gemma":0.000014827741,"threshold_uncertainty_score":0.39817974},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025151211,0.00005826002,0.99245703,0.0026699416,0.00007157205,0.0005755619,0.000035432666,0.00007051886,0.0015465368],"genre_scores_gemma":[0.43329728,0.0000068265367,0.56439406,0.00014042386,0.0000698219,0.00017791292,0.00017654545,0.000008074968,0.0017290618],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993333,0.000011130512,0.00011565419,0.0002695525,0.00013463652,0.00013573191],"domain_scores_gemma":[0.99917775,0.00014559751,0.0001404881,0.00036142935,0.00012679269,0.000047908845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036913564,0.00008280222,0.000095141426,0.00005930966,0.00008308603,0.00005070119,0.0003208068,0.00006471452,9.3694615e-7],"category_scores_gemma":[0.00002616298,0.000069532136,0.000035055797,0.00031192883,0.000020628806,0.00022489735,0.000054429656,0.000058113503,0.000003522597],"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":[0.000009875272,0.00010537188,0.00009032511,0.000014788382,0.00001548316,1.6434298e-7,0.00018522538,0.000005215348,0.13217342,0.47680354,0.15351388,0.2370827],"study_design_scores_gemma":[0.0011546438,0.00061884074,0.06519472,0.000030470419,0.000032928692,0.000014738402,0.00032836042,0.0523399,0.7512325,0.012545931,0.11599139,0.00051554205],"about_ca_topic_score_codex":0.000029305489,"about_ca_topic_score_gemma":0.000011305643,"teacher_disagreement_score":0.6190591,"about_ca_system_score_codex":0.000042456362,"about_ca_system_score_gemma":0.000019640232,"threshold_uncertainty_score":0.28354383},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13667937,0.00011729002,0.85892916,0.0008686396,0.000043999316,0.00015109866,0.000038785707,0.0002846922,0.0028869922],"genre_scores_gemma":[0.78237575,0.000004224372,0.2167672,0.0002935219,0.00003139394,0.000016761083,0.00004029299,0.000009076636,0.00046175378],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988533,0.000015132035,0.00023429243,0.00045944113,0.00015542941,0.000282351],"domain_scores_gemma":[0.9991743,0.00020561613,0.00007814507,0.00041243472,0.00004339388,0.00008613001],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014936304,0.00015050716,0.00016207759,0.00006683329,0.00018346102,0.00029459226,0.00039508214,0.000055767432,0.00001899678],"category_scores_gemma":[0.00001959852,0.00014282655,0.000027471759,0.0002756167,0.000104059654,0.00022197803,0.00011909393,0.00007744852,0.000020229634],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007776345,0.0008402262,0.0052816505,0.000047159956,0.00006189921,0.00015305133,0.0004315914,0.004125258,0.14208387,0.10207101,0.04694513,0.6979514],"study_design_scores_gemma":[0.00045239873,0.000033953107,0.00039355847,0.000016699498,0.000007334919,0.00002305236,0.000049998776,0.9622905,0.019021286,0.00019361752,0.017228484,0.0002891136],"about_ca_topic_score_codex":0.00031964638,"about_ca_topic_score_gemma":0.000011081585,"teacher_disagreement_score":0.9581652,"about_ca_system_score_codex":0.000015977535,"about_ca_system_score_gemma":0.00003925696,"threshold_uncertainty_score":0.58242977},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03409625,0.00019978362,0.964288,0.00019245023,0.00011755768,0.0001054973,0.0008850886,0.00009924736,0.00001610507],"genre_scores_gemma":[0.9857031,0.0004192302,0.01366876,0.000026865091,0.000033989698,0.000020043142,0.000110551635,0.000008794475,0.000008666798],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990932,0.00001323644,0.0001789564,0.000465786,0.00006761655,0.00018121781],"domain_scores_gemma":[0.9992834,0.0000954758,0.000016879583,0.0005093845,0.000010804383,0.00008410362],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013033832,0.00016332288,0.00014235888,0.00017078308,0.00010687142,0.000091707305,0.00031101218,0.00003239031,0.000003842977],"category_scores_gemma":[0.0000014863026,0.0001522026,0.000017730936,0.00021497921,0.000017230182,0.0010835021,0.000005098458,0.00017035849,0.0000027075228],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013704219,0.00047813874,0.000031588846,0.000085124186,0.000029747995,0.000010539873,0.0016846261,0.008581818,0.011482766,0.0016804059,0.000049232534,0.9758723],"study_design_scores_gemma":[0.00042999483,0.00006536283,0.0044833324,0.00016344138,0.000013157374,0.000042028976,0.00010597953,0.98644996,0.006322247,0.000038522714,0.0015759134,0.00031004264],"about_ca_topic_score_codex":0.000057808036,"about_ca_topic_score_gemma":0.00008358562,"teacher_disagreement_score":0.97786814,"about_ca_system_score_codex":0.00001707544,"about_ca_system_score_gemma":0.000019457706,"threshold_uncertainty_score":0.62066424},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17204763,0.00091784203,0.8192444,0.00079845573,0.0007274857,0.003075083,0.0008049081,0.00031473275,0.0020694556],"genre_scores_gemma":[0.9941827,0.00025269875,0.003163965,0.000105719766,0.00004631554,0.000155588,0.00004069854,0.00002168602,0.0020306308],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99642515,0.0003009807,0.000750497,0.0014536686,0.0005864714,0.0004832467],"domain_scores_gemma":[0.9969861,0.00014378241,0.00023239317,0.0021160478,0.00024050551,0.00028119778],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005387423,0.00041876352,0.0005986423,0.0005536201,0.00035583726,0.0005907763,0.0013010037,0.0001320591,0.000023660908],"category_scores_gemma":[0.00001267681,0.00041268993,0.00008753817,0.0022357984,0.00012457809,0.00030265862,0.000052275653,0.00034595205,0.00010172387],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00075324526,0.041682784,0.010267548,0.00019861823,0.0118185375,0.000823195,0.28439227,0.29362848,0.0010906139,0.034530867,0.018086387,0.30272746],"study_design_scores_gemma":[0.0021661094,0.0012979079,0.013217886,0.00014019714,0.0007383007,0.00003305787,0.011503169,0.9612116,0.00046149892,0.00021924987,0.007974406,0.0010366099],"about_ca_topic_score_codex":0.0008993701,"about_ca_topic_score_gemma":0.0021604889,"teacher_disagreement_score":0.8221351,"about_ca_system_score_codex":0.00026452017,"about_ca_system_score_gemma":0.00009251546,"threshold_uncertainty_score":0.9998325},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011532477,0.00001676848,0.99723184,0.000095897245,0.00067563466,0.00017863976,0.000108878674,0.0000640784,0.00047499264],"genre_scores_gemma":[0.24347216,0.00001270267,0.75555,0.00052576425,0.0002831317,0.00000753749,0.000120514764,0.000014989064,0.000013138068],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99751925,0.000021593376,0.0006125033,0.0006620088,0.0007749876,0.0004096382],"domain_scores_gemma":[0.99812824,0.00022727338,0.0002798763,0.001016759,0.00021902357,0.00012883246],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00056969153,0.0003062715,0.0003736692,0.00052141544,0.00017568958,0.00047287837,0.0023157515,0.00018336141,0.000012557505],"category_scores_gemma":[0.00006558043,0.00029632772,0.000080803315,0.0003548167,0.00044734063,0.0011118345,0.0008541852,0.00037337205,0.000021385922],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020990947,0.000016098078,0.00015848596,0.00006601148,0.0000080991085,0.000004984587,0.00090541254,0.0137268305,0.00015197293,0.0149059,0.000021467384,0.97003263],"study_design_scores_gemma":[0.00015682897,0.00008082535,0.00009530047,0.00036584266,0.000008715081,0.00003944223,4.1405866e-7,0.9940398,0.0015042957,0.0021623052,0.0011812649,0.00036499684],"about_ca_topic_score_codex":0.000031021136,"about_ca_topic_score_gemma":0.0000070026995,"teacher_disagreement_score":0.98031294,"about_ca_system_score_codex":0.00012699373,"about_ca_system_score_gemma":0.00039587865,"threshold_uncertainty_score":0.99994886},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0070971474,0.0004607102,0.98786914,0.00023601166,0.0007743254,0.0013349921,0.0000989098,0.0003043543,0.0018244026],"genre_scores_gemma":[0.9465458,0.00014247674,0.040937755,0.000115168055,0.00032835145,0.0010729997,0.000112832204,0.00006164502,0.01068298],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967607,0.0001713754,0.000840732,0.00087930984,0.0007042175,0.0006436364],"domain_scores_gemma":[0.99793214,0.00027992664,0.00045740223,0.00078507274,0.00025340327,0.00029208083],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008394692,0.0004299351,0.0004739681,0.00023161172,0.00057891296,0.00076526,0.0005935812,0.00026170592,0.000005263778],"category_scores_gemma":[0.000017200564,0.00044277,0.00016640422,0.0002713354,0.00006249411,0.00025431364,0.000013533117,0.00032910754,0.00006809149],"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":[0.000014153173,0.00032366082,0.00004275883,0.00015287766,0.00014076063,0.0000012290915,0.0008037022,0.9765544,0.0001477349,0.00426413,0.0018300718,0.015724553],"study_design_scores_gemma":[0.0011315773,0.0002675563,0.000052780128,0.00012434497,0.00009820483,0.000010266021,0.00024991794,0.92925256,0.00068022974,0.000014079807,0.06764118,0.00047727634],"about_ca_topic_score_codex":0.0001678133,"about_ca_topic_score_gemma":0.000017353948,"teacher_disagreement_score":0.94693136,"about_ca_system_score_codex":0.00030546382,"about_ca_system_score_gemma":0.00007454338,"threshold_uncertainty_score":0.9998024},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.112985335,0.000038894537,0.8838545,0.001583408,0.00004836128,0.00030873754,0.0000075299868,0.00011429349,0.0010589132],"genre_scores_gemma":[0.9496756,0.00010940605,0.049237836,0.0007661659,0.000064741376,0.00009782005,0.000005234545,0.000019851079,0.000023320426],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99750406,0.0000207469,0.00034588855,0.00085275824,0.00046528326,0.000811282],"domain_scores_gemma":[0.9985859,0.00019524156,0.000045230372,0.0002994738,0.00040740604,0.00046677026],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00041844233,0.00030018363,0.00029541636,0.0008872489,0.00037946747,0.00055913406,0.0011067839,0.00015448757,0.000004372905],"category_scores_gemma":[0.000050204217,0.00030316596,0.000030838408,0.0011618321,0.000047053694,0.00048208065,0.00020927252,0.00080983824,0.000020547157],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011220055,0.00007629762,0.00010817738,0.00002040637,0.000008990024,0.00001808703,0.001880685,0.07127681,0.00018886001,0.63114107,0.00022522641,0.29504415],"study_design_scores_gemma":[0.00016503884,0.0001667181,0.0009721492,0.00029970478,0.0000017329822,0.000031356823,0.000048210786,0.99164194,0.000104476116,0.0061395494,0.000090774825,0.00033837775],"about_ca_topic_score_codex":0.002027132,"about_ca_topic_score_gemma":0.0009862053,"teacher_disagreement_score":0.9203651,"about_ca_system_score_codex":0.0003007372,"about_ca_system_score_gemma":0.0005930139,"threshold_uncertainty_score":0.99994206},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34553528,0.00001368198,0.6532123,0.00020359593,0.00006376545,0.00015035912,0.00023303476,0.000040744508,0.0005472184],"genre_scores_gemma":[0.7484725,2.6165694e-7,0.25126585,0.000046453035,0.00004177186,0.000019189916,0.00005180979,0.000003850722,0.000098327415],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992834,0.000006424645,0.00018738814,0.00022601841,0.00013994887,0.0001568236],"domain_scores_gemma":[0.99949896,0.000041423853,0.00007306946,0.00031548392,0.000040494542,0.000030540075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006754188,0.000077161705,0.000094369614,0.00004624594,0.00006402696,0.000046526067,0.00042423944,0.000023271494,0.00001812129],"category_scores_gemma":[0.000004438771,0.00006387013,0.000036956764,0.00012638001,0.000017426964,0.00006265343,0.00010763429,0.000025090687,0.0000011386289],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010246745,0.00063263695,0.012784679,0.000107107786,0.00006862767,0.0000062937547,0.001245378,0.0024256797,0.057903886,0.32993776,0.024848303,0.57002944],"study_design_scores_gemma":[0.001142176,0.0001516774,0.032125033,0.000045198743,0.000021310889,0.000014264633,0.00027556397,0.864171,0.09484439,0.0014007866,0.005437534,0.00037104133],"about_ca_topic_score_codex":0.0010218511,"about_ca_topic_score_gemma":0.00058016065,"teacher_disagreement_score":0.86174536,"about_ca_system_score_codex":0.00002389706,"about_ca_system_score_gemma":0.000029050743,"threshold_uncertainty_score":0.26045483},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16534355,0.0012324364,0.8261517,0.00013858697,0.0005319418,0.00022517223,0.0009919428,0.00014235303,0.00524229],"genre_scores_gemma":[0.81126857,0.00016159753,0.18199562,0.0002725592,0.00047616864,0.0001282487,0.003911326,0.000046124045,0.001739785],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974858,0.0001400067,0.00041304884,0.001256015,0.0002358509,0.0004692793],"domain_scores_gemma":[0.9973748,0.0000847287,0.00015701876,0.0021307257,0.000057801342,0.00019497004],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000626223,0.00032355633,0.00031812274,0.00013342535,0.0004049583,0.0010822976,0.0014754876,0.0000896878,0.000009347651],"category_scores_gemma":[0.00008109482,0.00029583636,0.00004480857,0.00032103638,0.00008453459,0.002180757,0.00082253537,0.00014876675,0.000021646318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000059882086,0.00083695515,0.06569037,0.00018777662,0.00025957052,0.00004495326,0.011250967,0.000017457096,0.0011060716,0.0125064645,0.046091493,0.86200196],"study_design_scores_gemma":[0.002526203,0.00021900902,0.0067055775,0.00037231907,0.0001866629,0.00038687096,0.0037552272,0.91316193,0.0016892301,0.00013437215,0.06875874,0.0021038558],"about_ca_topic_score_codex":0.00020518425,"about_ca_topic_score_gemma":0.0004532245,"teacher_disagreement_score":0.91314447,"about_ca_system_score_codex":0.000041156323,"about_ca_system_score_gemma":0.00020537034,"threshold_uncertainty_score":0.9999547},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02052654,0.0000038097844,0.9447018,0.0040759714,0.000035888446,0.00013555928,0.00008334589,0.00013841552,0.030298678],"genre_scores_gemma":[0.5665728,0.0000017118888,0.43136528,0.0018188565,0.000023391294,0.000019635316,0.000019037898,0.0000048297875,0.00017447527],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99937016,0.000029266124,0.00007096758,0.0002847168,0.00012394646,0.00012094251],"domain_scores_gemma":[0.9994546,0.00012898092,0.000039291353,0.0002459851,0.000053470285,0.000077655764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000098169694,0.000077747834,0.00007359567,0.000039351617,0.00014383698,0.00015292622,0.0002427005,0.000031567623,0.00000820429],"category_scores_gemma":[0.0000229324,0.000063594314,0.000015322636,0.00012663366,0.00004488799,0.00028452094,0.000043983568,0.00007182732,0.000042727752],"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":[0.000005988781,0.00042301472,0.00026548246,0.0000016976791,0.000023287286,0.000007724149,0.0025683586,0.00018584683,0.00031699153,0.83690774,0.00059007405,0.15870377],"study_design_scores_gemma":[0.0014921556,0.0008664716,0.17560244,0.0000497144,0.000011826282,0.0000034934703,0.0005278521,0.73271084,0.01043088,0.07701024,0.0008135018,0.00048056326],"about_ca_topic_score_codex":0.00011965869,"about_ca_topic_score_gemma":0.000022751312,"teacher_disagreement_score":0.75989753,"about_ca_system_score_codex":0.000048076916,"about_ca_system_score_gemma":0.00004957837,"threshold_uncertainty_score":0.2593301},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48516262,0.0005469155,0.50879204,0.0010243745,0.00027175323,0.0002528855,0.0015774933,0.00026130676,0.0021106105],"genre_scores_gemma":[0.7526994,0.00012094112,0.23996638,0.00024510015,0.0006603774,0.00006011726,0.0041831215,0.00003889328,0.0020257244],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99807566,0.000062181694,0.00031673428,0.00094446103,0.00021045758,0.00039052364],"domain_scores_gemma":[0.9980248,0.00013501536,0.00013859716,0.0014775291,0.00008695341,0.0001370948],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034065524,0.00026040018,0.00024315524,0.0001230886,0.0003168859,0.0008432153,0.0012951326,0.0000883836,0.000009813011],"category_scores_gemma":[0.000037256617,0.0002239381,0.000027243661,0.00035700397,0.0000983629,0.003001302,0.0011886776,0.00014902983,0.000029726332],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055070243,0.0005616664,0.0048788753,0.00009738216,0.00016134944,0.00003221812,0.006641196,0.000041375155,0.0015966162,0.0024123061,0.021433176,0.96208876],"study_design_scores_gemma":[0.0021905869,0.00032877832,0.009117535,0.00057817774,0.00014886155,0.00020166078,0.0011287931,0.94326544,0.00075570727,0.00004555566,0.0411676,0.0010713243],"about_ca_topic_score_codex":0.000049758717,"about_ca_topic_score_gemma":0.00076722156,"teacher_disagreement_score":0.96101743,"about_ca_system_score_codex":0.000034025416,"about_ca_system_score_gemma":0.00022037365,"threshold_uncertainty_score":0.91319305},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22663376,0.00018941531,0.74560666,0.005199494,0.0009576742,0.00047455446,0.011158626,0.00046577537,0.009314049],"genre_scores_gemma":[0.79145855,0.00004378315,0.2065696,0.000034673598,0.00008130471,0.0000035766582,0.0017895567,0.000006549237,0.000012388691],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998585,0.0000021921246,0.0003484276,0.0005380947,0.00038447566,0.00014183635],"domain_scores_gemma":[0.99851274,0.000059291266,0.00020540995,0.0009251884,0.00023768489,0.000059654252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021835105,0.00013559197,0.0001736374,0.00013260554,0.000023622053,0.00013649657,0.0053352294,0.00004037316,0.000026320375],"category_scores_gemma":[0.00026700858,0.00013698384,0.000015088962,0.0002320955,0.000020392321,0.0012901856,0.0009767872,0.00011191596,0.000004402943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013447665,0.00033644793,0.0009901737,0.00004731476,0.00018026562,0.000005034928,0.00075092673,0.00039924655,0.06095259,0.5792189,0.0054360777,0.35166952],"study_design_scores_gemma":[0.00017290835,0.000046021432,0.0015241649,0.00024421632,0.00000877063,0.0000031783823,0.000076406504,0.99060076,0.0048277494,0.00062351726,0.0017266215,0.0001457091],"about_ca_topic_score_codex":0.00011839109,"about_ca_topic_score_gemma":0.0000014079203,"teacher_disagreement_score":0.9902015,"about_ca_system_score_codex":0.000024017958,"about_ca_system_score_gemma":0.000050868035,"threshold_uncertainty_score":0.99142724},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00055507367,0.00001725486,0.99195546,0.00072299986,0.00006514004,0.00019821538,0.000020922682,0.00013289721,0.0063320543],"genre_scores_gemma":[0.18070407,0.0000025505058,0.81864625,0.0001938531,0.00008463405,0.00013453535,0.000017499044,0.0000020874124,0.0002145248],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995834,0.000004490923,0.00014459147,0.00007784917,0.00008241505,0.00010720821],"domain_scores_gemma":[0.99962,0.000022554212,0.000033708035,0.0002211708,0.00006839842,0.00003414306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016159972,0.000045905406,0.000049732378,0.000041023824,0.000092021604,0.00018091887,0.00030104665,0.000020596892,0.0000014676364],"category_scores_gemma":[0.0000050816666,0.000039190403,0.00001834981,0.00010060014,0.000004457461,0.0013970181,0.000054887965,0.000024698165,0.00009106928],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.919389e-7,0.000010269371,4.5454595e-7,0.0000035627907,0.000003911297,1.6541426e-8,0.00040392336,0.027806008,0.000021787628,0.8581987,0.004277559,0.10927294],"study_design_scores_gemma":[0.0001193399,0.000013510038,6.750078e-7,0.000004159682,8.7106594e-7,0.0000018656884,0.00019978236,0.90950155,0.000017438708,0.00079366437,0.08929314,0.00005401821],"about_ca_topic_score_codex":0.000021574839,"about_ca_topic_score_gemma":0.0000034988109,"teacher_disagreement_score":0.8816955,"about_ca_system_score_codex":0.00002317814,"about_ca_system_score_gemma":0.00003157374,"threshold_uncertainty_score":0.17446049},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31995946,0.0003643795,0.6730567,0.004255369,0.0005061866,0.00029415736,0.000025704612,0.000056153207,0.0014818913],"genre_scores_gemma":[0.19676721,0.00007790763,0.80216503,0.0004119741,0.0001308358,0.000004050305,0.000017796794,0.000009758948,0.0004154562],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987356,0.0000349483,0.0004285125,0.0002591381,0.00033117866,0.00021060767],"domain_scores_gemma":[0.99894977,0.000046099987,0.0002282998,0.0006361988,0.00004397081,0.00009566035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007177784,0.0001018318,0.00015527557,0.00029496494,0.00006811864,0.00011203547,0.0016585559,0.000023705057,0.000010874103],"category_scores_gemma":[0.000019278461,0.00008700399,0.00003744094,0.000433626,0.000045612276,0.00034124064,0.0008263903,0.00011049721,0.000013057463],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000270161,0.0010407491,0.009039509,0.000026073978,0.00017254429,0.0012987967,0.0008816856,0.0024644246,0.0001413972,0.004444913,0.021525646,0.9589372],"study_design_scores_gemma":[0.002075064,0.000113579736,0.0389124,0.00020142012,0.000032667736,0.0003053459,0.00050604704,0.81797206,0.000025900943,0.0001472939,0.13946356,0.00024463877],"about_ca_topic_score_codex":0.000010210579,"about_ca_topic_score_gemma":0.000008740874,"teacher_disagreement_score":0.9586926,"about_ca_system_score_codex":0.00003482962,"about_ca_system_score_gemma":0.000019226423,"threshold_uncertainty_score":0.35479197},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06379017,0.000025465277,0.9230141,0.0020147937,0.00007123857,0.00004533978,0.0000034960744,0.00014954762,0.010885814],"genre_scores_gemma":[0.81930095,0.000014665111,0.17796457,0.00092533446,0.000119523495,0.000013961248,0.0000047408375,0.0000036984857,0.0016525327],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993894,0.0000052835267,0.00011442588,0.00021482719,0.000115085764,0.00016097898],"domain_scores_gemma":[0.9994573,0.000016037426,0.000028166392,0.0004403181,0.000015733856,0.000042468524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009479243,0.00006249475,0.000052081577,0.000028071294,0.00010101756,0.00022279944,0.0005743137,0.000015120132,0.00002129452],"category_scores_gemma":[0.0000030342508,0.00005127711,0.000020160369,0.00013043979,0.000014435616,0.0012551179,0.00018850162,0.000055336724,0.00035630597],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.357583e-8,0.000026550848,0.00082676,0.0000018740254,0.0000023436776,3.7308817e-7,0.0000852074,0.00003866387,0.00014218983,0.014045547,0.0014109538,0.9834195],"study_design_scores_gemma":[0.0001808709,0.000033009936,0.016231908,0.000022064512,0.0000026072992,0.00001668351,0.000024925073,0.8738934,0.0056402134,0.00014339137,0.10355721,0.00025371488],"about_ca_topic_score_codex":0.00003408191,"about_ca_topic_score_gemma":0.0000066099974,"teacher_disagreement_score":0.98316574,"about_ca_system_score_codex":0.00001912665,"about_ca_system_score_gemma":0.000018786695,"threshold_uncertainty_score":0.45797113},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00091395486,0.000019546998,0.9739731,0.0010317614,0.00012171665,0.00007570568,0.0000036915196,0.000118429525,0.023742123],"genre_scores_gemma":[0.59511894,0.00006771811,0.34471977,0.0013564192,0.00007062284,0.00012956696,0.00015255991,0.00001602137,0.058368377],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994141,0.000022689177,0.000105038875,0.00018373763,0.00015023544,0.00012423264],"domain_scores_gemma":[0.99958605,0.000029280576,0.00005825962,0.00024783635,0.000038678423,0.000039876046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001915998,0.000051334962,0.000045231056,0.000021563787,0.000087816574,0.00019104373,0.00023210616,0.000029338704,0.000060462302],"category_scores_gemma":[0.000031644842,0.00004650152,0.000013833488,0.00021692557,0.0000036155884,0.00038153864,0.0000312744,0.00003466696,0.000202703],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.1904e-7,0.00007681376,0.0017555964,0.0000019437896,0.00001159404,2.812368e-7,0.00017987784,0.0000069166404,0.0019014523,0.7541828,0.14973468,0.092147894],"study_design_scores_gemma":[0.0005734193,0.00006589701,0.0037004657,0.0000057956395,0.000011938192,0.000005494903,0.000056373166,0.02319917,0.036209635,0.019853044,0.9158555,0.0004632351],"about_ca_topic_score_codex":0.000023781879,"about_ca_topic_score_gemma":0.0000020104396,"teacher_disagreement_score":0.76612085,"about_ca_system_score_codex":0.00008327157,"about_ca_system_score_gemma":0.000023145165,"threshold_uncertainty_score":0.26054046},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27581683,0.00072185014,0.7158249,0.0044695106,0.00224384,0.00017902991,0.00013299406,0.000095057316,0.00051599887],"genre_scores_gemma":[0.13522233,0.0002405767,0.8486757,0.0032540243,0.0014912938,0.000014184444,0.00004556586,0.000061005376,0.010995322],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977955,0.00008278885,0.0004272007,0.00068694784,0.00037259984,0.0006349575],"domain_scores_gemma":[0.99834317,0.00013672646,0.0001500011,0.0008293076,0.00015272382,0.00038804938],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00023100505,0.00029600592,0.00029439435,0.0001374437,0.00087503553,0.00027304873,0.00088340347,0.0001827775,0.000058735488],"category_scores_gemma":[0.00010084728,0.0003440734,0.00010385477,0.0006370403,0.000357591,0.000359459,0.00028580916,0.00034431703,0.00027352397],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000795838,0.0003572385,0.005959457,0.00010120716,0.00013286169,0.0011135258,0.051456816,0.0015623035,0.0014142833,0.06896596,0.06442509,0.8045033],"study_design_scores_gemma":[0.0008223968,0.00021637775,0.007014373,0.00029597184,0.00009537673,0.0016494445,0.0008950274,0.6332771,0.0011415249,0.0016055149,0.3516411,0.0013457724],"about_ca_topic_score_codex":0.0014176102,"about_ca_topic_score_gemma":0.000027380655,"teacher_disagreement_score":0.8031575,"about_ca_system_score_codex":0.00026065233,"about_ca_system_score_gemma":0.00016917504,"threshold_uncertainty_score":0.9999011},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013058997,0.00028200838,0.99282587,0.00058126077,0.0007434834,0.001044719,0.0007859779,0.00013869279,0.0022921048],"genre_scores_gemma":[0.12731214,0.00025259977,0.8235545,0.000014992892,0.00036086846,0.000033881624,0.024311742,0.00007572469,0.024083558],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99795747,0.00015092334,0.00022102933,0.0007121461,0.0005197962,0.0004386425],"domain_scores_gemma":[0.9966352,0.0002873627,0.00023529804,0.0017572115,0.00091209967,0.00017284435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017873776,0.00016336655,0.00027016242,0.0004774997,0.0005854502,0.0001237551,0.004033246,0.00020219383,0.000027187016],"category_scores_gemma":[0.00010295573,0.00020269216,0.0000627365,0.00069022493,0.00006755836,0.0009047248,0.0007841182,0.0002930222,0.00006367974],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018633873,0.0006356083,0.00047343067,0.004054311,0.0002828027,0.0000124356875,0.010012627,0.000012255639,0.00043334198,0.026844477,0.13805622,0.81916386],"study_design_scores_gemma":[0.0009656468,0.0001936338,0.007606614,0.0012531677,0.00010097745,0.0000065747213,0.06470795,0.53528833,0.0006048442,0.00007017544,0.38847864,0.00072344294],"about_ca_topic_score_codex":0.0003083718,"about_ca_topic_score_gemma":0.00093124266,"teacher_disagreement_score":0.81844044,"about_ca_system_score_codex":0.00018490558,"about_ca_system_score_gemma":0.00030558408,"threshold_uncertainty_score":0.82655466},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23786534,0.0000027143874,0.760826,0.00084432226,0.000033779208,0.000046183617,0.0000046764235,0.000032954988,0.00034403222],"genre_scores_gemma":[0.6834826,0.0000023106809,0.31579718,0.0003423106,0.000020515234,0.000027140122,0.00002912219,0.000004369984,0.00029449604],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931794,0.0000059129306,0.00012164361,0.00023059368,0.00014213785,0.0001817858],"domain_scores_gemma":[0.99967855,0.000017966755,0.000025409481,0.00023315253,0.0000037683537,0.000041151583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009788611,0.00006122357,0.000052067422,0.0000728141,0.000054770186,0.00006350983,0.00038172596,0.000022546976,0.000017883878],"category_scores_gemma":[0.00000408053,0.000059458427,0.000015341338,0.0001995131,0.00001153401,0.000308579,0.00018590211,0.000052540712,0.000065234264],"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":[0.0000019672684,0.00065117783,0.0438124,0.000013882608,0.000026700958,0.0000626946,0.005050847,0.007600816,0.0039554434,0.63661844,0.0001324694,0.30207315],"study_design_scores_gemma":[0.0022497997,0.00009383879,0.37102333,0.00023231127,0.000006189103,0.000054694774,0.000666618,0.6031703,0.003774503,0.009794891,0.008023678,0.0009099019],"about_ca_topic_score_codex":0.00004345592,"about_ca_topic_score_gemma":0.000020990768,"teacher_disagreement_score":0.62682354,"about_ca_system_score_codex":0.0000562698,"about_ca_system_score_gemma":0.000016792814,"threshold_uncertainty_score":0.24246442},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000025104735,0.0033124343,0.9865974,0.0014770306,0.00048380558,0.0002918934,0.00037684813,0.00011077134,0.0073246704],"genre_scores_gemma":[0.0033165026,0.0037716392,0.9610492,0.0006674587,0.00023894304,0.00002460276,0.000524078,0.000028826738,0.030378735],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979065,0.000026358708,0.00051643886,0.0009095709,0.0004220258,0.00021909433],"domain_scores_gemma":[0.99782115,0.0008850341,0.0003364471,0.0006818815,0.00022416061,0.0000513114],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005937559,0.00026752558,0.0003480388,0.00017215626,0.00016132103,0.00013394002,0.0013379373,0.00012808411,0.0000056616905],"category_scores_gemma":[0.00022285344,0.0002817466,0.000032899155,0.000097821736,0.00009176301,0.0003653919,0.00146497,0.00029224678,0.00003695787],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016490989,0.000056314584,0.000304265,0.00006132838,0.00018705304,0.00003301546,0.0017043732,0.005330214,2.861956e-7,0.24139427,0.0033814716,0.7475458],"study_design_scores_gemma":[0.00010979924,0.00005414134,0.0014235716,0.0005869021,0.000028685561,0.000019942874,0.00016864095,0.89350945,0.000002368378,0.0872151,0.016366553,0.0005148171],"about_ca_topic_score_codex":0.000021672065,"about_ca_topic_score_gemma":0.000064615095,"teacher_disagreement_score":0.88817924,"about_ca_system_score_codex":0.00020685485,"about_ca_system_score_gemma":0.00007873998,"threshold_uncertainty_score":0.99996346},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027108835,0.000014062223,0.9670255,0.0015168845,0.000047796002,0.00013067792,0.0000054285265,0.0003703572,0.0037804514],"genre_scores_gemma":[0.3899067,0.0000033163547,0.6090104,0.00032406516,0.000047240876,0.000043016877,0.0000064024816,0.000006555418,0.0006523354],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991673,0.000007810901,0.00015132723,0.00033960099,0.00014819435,0.00018575435],"domain_scores_gemma":[0.9993846,0.000049270973,0.000047424044,0.00032394327,0.00012675433,0.00006803001],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010830631,0.000093725124,0.00007612133,0.00005655559,0.0003912623,0.00056852784,0.00022250233,0.000034196462,0.00004386082],"category_scores_gemma":[0.00001640516,0.0000765361,0.000019957213,0.00038186178,0.000044952954,0.0006932921,0.00005128963,0.00009282263,0.00014233244],"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":[0.0000018930106,0.000062201514,0.0028192224,0.000007062161,0.00002098237,0.0000074685818,0.00039268093,0.0063575576,0.00090611057,0.9815683,0.00062042446,0.0072361277],"study_design_scores_gemma":[0.0035815095,0.00072461466,0.041784372,0.00012982116,0.0000410526,0.0012463602,0.00025144996,0.67173684,0.096999794,0.160287,0.021450792,0.001766398],"about_ca_topic_score_codex":0.00011853649,"about_ca_topic_score_gemma":0.00006368131,"teacher_disagreement_score":0.82128125,"about_ca_system_score_codex":0.00003934808,"about_ca_system_score_gemma":0.00012574146,"threshold_uncertainty_score":0.54823273},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00092334446,0.000038939732,0.9916537,0.0008222638,0.000037809827,0.00022367014,0.000018836747,0.00019645297,0.006085009],"genre_scores_gemma":[0.02799266,0.0000037400712,0.970879,0.00048751876,0.00005453874,0.00008760227,0.000090136855,0.0000065065,0.00039829142],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925613,0.00000542579,0.0001439151,0.0003176123,0.00010154891,0.00017534904],"domain_scores_gemma":[0.9993165,0.000034132485,0.00004285103,0.00047596244,0.00006295942,0.00006760556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015836555,0.00007712223,0.00009127442,0.0000421751,0.00013189661,0.00015823504,0.0005836379,0.000029733013,0.00000416306],"category_scores_gemma":[0.00002734847,0.00006632988,0.00003344191,0.00030574162,0.000016306401,0.00024140549,0.00010555619,0.000034879395,0.00001988969],"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":[9.967545e-7,0.00019969567,0.00010349627,0.000031849653,0.0000232157,0.0000017652598,0.0005791584,0.0004416304,0.00076765084,0.86659086,0.019313373,0.1119463],"study_design_scores_gemma":[0.0034450453,0.0003293346,0.0021626092,0.00011070029,0.000038958235,0.000116900694,0.00042964966,0.78302306,0.010586293,0.016190678,0.182245,0.0013217828],"about_ca_topic_score_codex":0.0000258755,"about_ca_topic_score_gemma":5.5726997e-7,"teacher_disagreement_score":0.8504002,"about_ca_system_score_codex":0.000026864485,"about_ca_system_score_gemma":0.000037419155,"threshold_uncertainty_score":0.27048537},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006469436,0.000004900994,0.9505239,0.0002843821,0.000054153446,0.00029664594,0.00010518988,0.0002056263,0.04787822],"genre_scores_gemma":[0.16780064,0.000008467318,0.83038664,0.00017085344,0.000023069737,0.00012469734,0.0005813697,0.000008029828,0.00089624926],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894863,0.000012882802,0.00018956784,0.00053614995,0.00013427698,0.00017850411],"domain_scores_gemma":[0.9977788,0.000017594868,0.00006548175,0.0019957216,0.00006088471,0.00008157101],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032489243,0.00009204241,0.00007472081,0.00006807692,0.0001644531,0.000107561435,0.0018548798,0.00003893797,0.000007226726],"category_scores_gemma":[0.000012181869,0.00008430477,0.000019934661,0.00020909568,0.00002484274,0.001255295,0.00039641713,0.000053284402,0.000056947658],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004299968,0.00013215636,0.000049095324,0.000007336743,0.000011346988,3.227731e-7,0.00024486997,0.0003858855,0.00004237617,0.79386425,0.00610993,0.19914813],"study_design_scores_gemma":[0.0001731706,0.0000158477,0.0060661617,0.0000033502918,0.0000093786,5.8224305e-7,0.00008152539,0.9862123,0.000049118342,0.0030559846,0.004205894,0.00012668526],"about_ca_topic_score_codex":0.000007873703,"about_ca_topic_score_gemma":0.000003385916,"teacher_disagreement_score":0.98582643,"about_ca_system_score_codex":0.000021310692,"about_ca_system_score_gemma":0.000047124584,"threshold_uncertainty_score":0.3446859},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000043977216,0.000085134765,0.9931407,0.0018522395,0.00084327924,0.0002459179,0.00004708641,0.00022698008,0.0035146808],"genre_scores_gemma":[0.016541325,0.000016924758,0.976223,0.0035255083,0.0007938036,0.00003146108,0.00006159783,0.000045371922,0.0027610227],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99620706,0.00003567248,0.00046811486,0.0015747313,0.0011046776,0.00060974015],"domain_scores_gemma":[0.9966024,0.00047194946,0.00036738155,0.0020187388,0.00030969706,0.00022979637],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010390498,0.00042237103,0.00040567157,0.00045608275,0.00031436072,0.0008293489,0.0035477711,0.00032855547,0.00006362748],"category_scores_gemma":[0.000121787125,0.00040341532,0.00010106451,0.00065341755,0.00026688402,0.00071345904,0.0005827069,0.00063996605,0.0001274462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010904096,0.00012100727,0.00030635652,0.000019933885,0.000013175763,0.000035788966,0.00040212867,0.011842114,0.00004852576,0.018331828,0.00049884676,0.9683792],"study_design_scores_gemma":[0.00018898201,0.000093611365,0.00040186645,0.00008567616,0.00000874244,0.000008558856,5.443886e-8,0.9603374,0.0002494542,0.02446074,0.013580775,0.00058416114],"about_ca_topic_score_codex":0.00006876425,"about_ca_topic_score_gemma":0.00007548465,"teacher_disagreement_score":0.967795,"about_ca_system_score_codex":0.00053675455,"about_ca_system_score_gemma":0.0004034381,"threshold_uncertainty_score":0.99984175},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016167125,0.0004128234,0.9727748,0.0007705698,0.000060154416,0.00024775334,0.008802668,0.0002628821,0.0005011994],"genre_scores_gemma":[0.41845062,0.00016816828,0.5576675,0.0006024899,0.0002136932,0.00022271948,0.022382865,0.000038149057,0.00025381256],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99777645,0.000054615626,0.00038161257,0.00082669564,0.0003120087,0.0006486381],"domain_scores_gemma":[0.998469,0.00015403541,0.00017089653,0.000911841,0.00008353042,0.00021070546],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021245153,0.0003399021,0.00032975007,0.000081271224,0.0004574084,0.00032101726,0.0006744595,0.000063382584,0.000052267926],"category_scores_gemma":[0.000016738088,0.00028327806,0.000055622495,0.00040358622,0.00023002242,0.0007102828,0.00035810712,0.00016622206,0.00004780817],"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":[0.00018160525,0.0034945956,0.2849434,0.00031163607,0.00044811104,0.00089076365,0.0014233383,0.0044536744,0.00033350463,0.21215062,0.29470742,0.19666134],"study_design_scores_gemma":[0.009351198,0.0004542967,0.2149667,0.00051517,0.00019808614,0.00073865126,0.0019329237,0.31213197,0.00019536844,0.0016086568,0.45469555,0.0032114105],"about_ca_topic_score_codex":0.00037765794,"about_ca_topic_score_gemma":0.00038315303,"teacher_disagreement_score":0.41510734,"about_ca_system_score_codex":0.000017944498,"about_ca_system_score_gemma":0.00007455934,"threshold_uncertainty_score":0.9999619},"labels":[],"label_agreement":null},{"id":"W2121566986","doi":"10.1007/s10115-008-0179-6","title":"PADS: a simple yet effective pattern-aware dynamic search method for fast maximal frequent pattern mining","year":2008,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Executable; Data mining; Benchmark (surveying); Pattern search; Simple (philosophy); Linear subspace; Tree (set theory); Algorithm; Mathematics; Programming language","score_opus":0.019725056746500533,"score_gpt":0.2976702125706421,"score_spread":0.27794515582414153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121566986","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010135972,0.00014533423,0.98750556,0.00008023189,0.00025970876,0.00081980415,0.00025122846,0.000114556446,0.0006876058],"genre_scores_gemma":[0.9800624,0.000032088043,0.018277166,0.00013811361,0.00009954888,0.0008512819,0.00038041925,0.00001267233,0.00014630778],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988135,0.00008124654,0.0004150139,0.00023783593,0.00017728999,0.00027509322],"domain_scores_gemma":[0.998871,0.00025479036,0.00014132449,0.0003564502,0.00026573654,0.00011066137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005285197,0.00015937691,0.00022385968,0.00016833318,0.00037019188,0.00026570857,0.00036821878,0.00007347024,0.0000025258614],"category_scores_gemma":[0.000023406961,0.0001414897,0.000052962798,0.00025408078,0.00002939418,0.0019755187,0.00018201448,0.00009278842,0.00009786879],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002387997,0.00003171597,0.0007883478,0.0002445879,0.00002873267,0.0000011076849,0.012315801,0.00006544156,0.000026388756,0.0006548791,0.0036834623,0.9821572],"study_design_scores_gemma":[0.0005303204,0.00012102892,0.0036821282,0.000074353906,0.0000061684004,0.00008793639,0.00095571287,0.9571458,0.00009206307,0.000014957635,0.037096012,0.00019349571],"about_ca_topic_score_codex":0.00015486077,"about_ca_topic_score_gemma":0.000013276731,"teacher_disagreement_score":0.98196363,"about_ca_system_score_codex":0.00007016634,"about_ca_system_score_gemma":0.00006464611,"threshold_uncertainty_score":0.5769782},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019039422,0.000027940036,0.9779118,0.00026790076,0.00004681084,0.00010224641,0.00001955768,0.00006264198,0.0025217321],"genre_scores_gemma":[0.11699691,0.0000036607187,0.8811806,0.000119233744,0.000021827595,0.000050173112,0.000009587172,0.0000045233824,0.001613527],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99958456,0.000005271293,0.0000729029,0.00018193228,0.00004596491,0.00010937867],"domain_scores_gemma":[0.9996916,0.000044135875,0.000016606538,0.00020332489,0.000012182525,0.00003211596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010443105,0.00005027417,0.00005252924,0.000017209004,0.00008597676,0.00015870089,0.00014762094,0.000014074245,0.0000064352043],"category_scores_gemma":[0.000020163521,0.000041264437,0.000013452478,0.00005626468,0.000015100821,0.0002831241,0.00005842386,0.000020503554,0.000012017942],"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":[4.9573714e-7,0.000022819771,0.0005104768,0.0000057371262,0.000005818764,5.974156e-7,0.00012234204,0.0000024990838,0.00019817721,0.9370975,0.0028022518,0.059231315],"study_design_scores_gemma":[0.0011275349,0.00018020389,0.0056203296,0.000026322765,0.000015409138,0.000066078566,0.00013262949,0.40036184,0.005464046,0.037459765,0.5488397,0.00070615724],"about_ca_topic_score_codex":0.000023479544,"about_ca_topic_score_gemma":0.0000037431892,"teacher_disagreement_score":0.8996377,"about_ca_system_score_codex":0.0000048948095,"about_ca_system_score_gemma":0.000021919157,"threshold_uncertainty_score":0.1682715},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6821444,0.005528986,0.2363827,0.010062274,0.0040844954,0.0045154216,0.008955959,0.0015088547,0.046816915],"genre_scores_gemma":[0.9341832,0.000082161394,0.06240033,0.00032259824,0.00036399392,0.000047992253,0.0006879975,0.00003257855,0.0018791896],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99727106,0.00040672635,0.00046224197,0.0005670485,0.00059466524,0.0006982731],"domain_scores_gemma":[0.99577916,0.0006265505,0.0002867275,0.0023727443,0.00064739434,0.00028740644],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0013414539,0.00024831563,0.000282617,0.0002912349,0.0010355253,0.0012566852,0.0040521994,0.00024512337,0.00004385443],"category_scores_gemma":[0.00047080606,0.00021571957,0.00006683372,0.0011810646,0.00035950108,0.0021912837,0.0027209434,0.0006495453,0.00017581784],"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":[0.00019477014,0.00024941942,0.0010076046,0.00036249947,0.00026289755,0.00017274807,0.08004556,0.000096494485,0.010799822,0.7797243,0.11992546,0.0071584256],"study_design_scores_gemma":[0.0011326561,0.0002976887,0.0044466876,0.00040104435,0.000079947444,0.00021081965,0.0044470215,0.2804888,0.0014408998,0.0012689449,0.7050312,0.00075427204],"about_ca_topic_score_codex":0.00021107515,"about_ca_topic_score_gemma":0.000012590733,"teacher_disagreement_score":0.7784554,"about_ca_system_score_codex":0.00043425141,"about_ca_system_score_gemma":0.00039415655,"threshold_uncertainty_score":0.9997801},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0058727385,0.000030171284,0.9892631,0.0022699991,0.00015723339,0.00005444482,0.000012933797,0.00006802818,0.0022713493],"genre_scores_gemma":[0.35088736,0.00006507713,0.64075315,0.0040332587,0.00036983672,0.00003085494,0.000026773063,0.000013939743,0.0038197704],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995138,0.000012759525,0.000071970135,0.00016789007,0.00010080117,0.00013280302],"domain_scores_gemma":[0.9992196,0.00019621533,0.00003843288,0.00048710976,0.000030483501,0.00002815561],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001289524,0.000051801904,0.000044092743,0.000012812589,0.0001866428,0.00009420246,0.00059902534,0.000011826515,0.000015749092],"category_scores_gemma":[0.000047753703,0.000036787587,0.00000959629,0.00020914283,0.000027788981,0.000058558373,0.0001127272,0.000076266064,0.00040449057],"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":[3.972664e-7,0.000027942604,0.000027573487,0.0000015694202,0.0000024927172,0.0000021830158,0.00033460994,0.000050885457,0.000062703715,0.67523926,0.05365121,0.2705992],"study_design_scores_gemma":[0.00014420826,0.000039564045,0.0029440278,0.0000445608,0.00000258833,0.00002212055,0.000029160989,0.50512666,0.00033169362,0.042333264,0.44874302,0.00023916],"about_ca_topic_score_codex":0.0000068713593,"about_ca_topic_score_gemma":0.0000041552094,"teacher_disagreement_score":0.632906,"about_ca_system_score_codex":0.000009853996,"about_ca_system_score_gemma":0.000012537666,"threshold_uncertainty_score":0.51990426},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007718044,0.000015521911,0.98240656,0.0007113904,0.00015019087,0.00007876838,0.00013014807,0.00017153047,0.008617835],"genre_scores_gemma":[0.38934833,0.000010505012,0.6065979,0.00082617917,0.0002748198,0.0000103132,0.00049536594,0.000012054326,0.002424559],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989165,0.000008428429,0.00018010553,0.00044993957,0.0001933359,0.00025169554],"domain_scores_gemma":[0.9979818,0.000040316216,0.000041282652,0.0017992291,0.000030589767,0.00010678553],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035662254,0.00008797565,0.0000724877,0.000049707396,0.000072724906,0.00016150415,0.0019611875,0.000031249394,0.00009311901],"category_scores_gemma":[0.000010697234,0.00007330636,0.000019611733,0.0001865661,0.000019194518,0.00053102226,0.0009427762,0.00007150162,0.00014438212],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012288075,0.00023185872,0.0015482322,0.0000074321674,0.00003146112,0.000047799505,0.00024061228,0.0000037655475,0.001445497,0.10313012,0.038316447,0.85499555],"study_design_scores_gemma":[0.0011325665,0.00015775845,0.028201822,0.00005213582,0.000041114563,0.00015998149,0.00039111808,0.3293478,0.01116587,0.0028399671,0.6253388,0.0011711048],"about_ca_topic_score_codex":0.000511903,"about_ca_topic_score_gemma":0.00028204895,"teacher_disagreement_score":0.85382444,"about_ca_system_score_codex":0.000017656039,"about_ca_system_score_gemma":0.00003641813,"threshold_uncertainty_score":0.36444068},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038501252,0.000027856076,0.9751623,0.00024358979,0.00006395018,0.0001134444,0.000010015146,0.00018730646,0.020341396],"genre_scores_gemma":[0.2327326,0.0000030892647,0.7665185,0.00021925426,0.000033952845,0.00002446713,0.000058418125,0.00000657063,0.00040317097],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99914575,0.000019785606,0.00017503297,0.00030111815,0.00016094864,0.00019734997],"domain_scores_gemma":[0.9993226,0.00010506125,0.00006065033,0.0003536576,0.00007093722,0.0000871108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004643864,0.00008634745,0.00008747281,0.000094562725,0.00011667867,0.00012623768,0.00044300332,0.000032503827,0.000008570862],"category_scores_gemma":[0.000034661123,0.00007386215,0.000022666087,0.00052685384,0.000046407422,0.0005510529,0.00010579145,0.00005247886,0.000055050292],"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":[0.0000027093984,0.00008334651,0.00022804944,0.0000041415105,0.000011052817,0.000002302505,0.0039974228,0.000020459289,0.0003637631,0.95981866,0.0046723257,0.030795775],"study_design_scores_gemma":[0.00065734825,0.00016389554,0.004458453,0.000019310568,0.000011704523,0.000019775272,0.010978111,0.9534018,0.002972558,0.0024881917,0.024274403,0.0005544394],"about_ca_topic_score_codex":0.000008513065,"about_ca_topic_score_gemma":0.0000058455057,"teacher_disagreement_score":0.95733047,"about_ca_system_score_codex":0.000016466242,"about_ca_system_score_gemma":0.000031323474,"threshold_uncertainty_score":0.3012011},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046698518,0.00004575472,0.9486695,0.0021049457,0.00013351449,0.00018185146,0.000031312473,0.00031356703,0.0018210491],"genre_scores_gemma":[0.7520467,0.0000028557254,0.24722108,0.00022808458,0.00013859029,0.00005131639,0.00018126523,0.000012166956,0.0001179438],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987616,0.0000064846968,0.00019677645,0.0005768224,0.0002322063,0.00022613483],"domain_scores_gemma":[0.999276,0.000033589262,0.00012413994,0.00039935744,0.00011343145,0.00005349807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029250834,0.00013115646,0.00010616211,0.00009915854,0.00020568936,0.00050803635,0.0014442995,0.000039965886,0.000004026637],"category_scores_gemma":[0.00005565202,0.00012248114,0.000022379058,0.00036613326,0.000038126618,0.001769249,0.0005065119,0.00012197331,0.000023593882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022998242,0.00059287733,0.019375892,0.00034666737,0.000041812254,0.000012648396,0.008145237,0.000077446595,0.028568849,0.07885507,0.08260479,0.78135574],"study_design_scores_gemma":[0.00051334,0.00008853944,0.009954595,0.00019208355,0.000026482738,0.000012903098,0.0006695294,0.9580372,0.005645262,0.006709683,0.01767498,0.00047537882],"about_ca_topic_score_codex":0.00038316997,"about_ca_topic_score_gemma":0.000024723582,"teacher_disagreement_score":0.9579598,"about_ca_system_score_codex":0.00006597695,"about_ca_system_score_gemma":0.000029853369,"threshold_uncertainty_score":0.4994636},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046006847,0.00016232164,0.95142895,0.00042150338,0.00059499836,0.00064880884,0.00025367035,0.000093420334,0.00038945585],"genre_scores_gemma":[0.9900346,0.00022593926,0.00878002,0.0001975972,0.00007979344,0.00010369531,0.00005142452,0.000016663951,0.00051031064],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982259,0.000105732186,0.00048246142,0.00059277733,0.00027151837,0.00032158958],"domain_scores_gemma":[0.9985809,0.0006468724,0.0002075671,0.00034253867,0.0000910557,0.00013106878],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004086254,0.00022998577,0.00026879038,0.0001760978,0.00021243226,0.0003256111,0.00017132873,0.00011397419,0.0000055506],"category_scores_gemma":[0.00003568771,0.00024316182,0.000037357007,0.0002051394,0.000040190935,0.0002889973,0.0000052391865,0.0002615127,0.000014523957],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023101667,0.0018834146,0.00034095783,0.00044422256,0.00021350945,0.000025055992,0.0077731493,0.010953526,0.008157097,0.35556537,0.009123594,0.6052891],"study_design_scores_gemma":[0.0042386656,0.001974012,0.0040127668,0.0018621663,0.00017805111,0.00009812485,0.001821661,0.9249831,0.018684173,0.0041238484,0.036464445,0.0015589936],"about_ca_topic_score_codex":0.0001289153,"about_ca_topic_score_gemma":0.00029961512,"teacher_disagreement_score":0.9440277,"about_ca_system_score_codex":0.0001473551,"about_ca_system_score_gemma":0.000032475877,"threshold_uncertainty_score":0.99158514},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00031471826,0.0000046280547,0.98060143,0.0002619339,0.000053538934,0.000104457984,0.000098330085,0.0001572064,0.01840376],"genre_scores_gemma":[0.39776117,0.0000039765205,0.6017835,0.00014863742,0.000024824749,0.00006166375,0.000020592606,0.000009966874,0.00018563305],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918556,0.000017237948,0.0001281878,0.00028272741,0.00016356984,0.00022269036],"domain_scores_gemma":[0.99924785,0.000067246336,0.000047794667,0.00047851622,0.000024187884,0.00013440504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007081187,0.00010068489,0.00009262857,0.00006385289,0.00016750947,0.000078427,0.00039174166,0.0000225229,0.00012461086],"category_scores_gemma":[0.00001772525,0.00007919384,0.000014166557,0.00021223704,0.00006169795,0.00013593862,0.000069446425,0.00009325605,0.00017200953],"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":[0.000030162211,0.00035891944,0.0007346728,0.000023893228,0.000060759307,0.00013970735,0.0040037567,0.000050436214,0.00004533268,0.788863,0.015782615,0.18990676],"study_design_scores_gemma":[0.0028554983,0.004030856,0.10829723,0.0003906465,0.00013449849,0.00029464904,0.0005700413,0.7011518,0.0012259523,0.07328172,0.105557226,0.0022099158],"about_ca_topic_score_codex":0.00004858878,"about_ca_topic_score_gemma":0.000032494154,"teacher_disagreement_score":0.71558124,"about_ca_system_score_codex":0.000014410445,"about_ca_system_score_gemma":0.00004079954,"threshold_uncertainty_score":0.3229431},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032823794,0.0001874399,0.99494165,0.0003346124,0.00046676092,0.00028506646,0.00001209959,0.000076526674,0.0004134755],"genre_scores_gemma":[0.043912742,0.00007112008,0.9552894,0.00030566962,0.0001058842,0.000012194192,0.000048096445,0.000033605236,0.0002212795],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99713093,0.000063767184,0.0005663706,0.0009779079,0.00087005127,0.0003909783],"domain_scores_gemma":[0.9978092,0.00053239684,0.00051834114,0.0005594265,0.0004724737,0.00010817078],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012144637,0.00032835014,0.00043447077,0.0007316306,0.000325857,0.0002948447,0.00089218206,0.00025591187,0.000007295265],"category_scores_gemma":[0.0002466047,0.00034885237,0.000062604515,0.00081923226,0.00019659259,0.00071864075,0.0004348624,0.00044348446,0.0000022799154],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036499728,0.0000906402,0.0014840979,0.00007725296,0.00004198861,0.000012350086,0.0036018535,0.012310986,0.0010091501,0.019942775,0.000023338145,0.96140194],"study_design_scores_gemma":[0.00045559017,0.000101701626,0.0002608635,0.00023559673,0.000015539441,0.0000175332,0.0000027992166,0.991035,0.00077811215,0.0062160394,0.0005183995,0.00036285052],"about_ca_topic_score_codex":0.00004014938,"about_ca_topic_score_gemma":0.00001102915,"teacher_disagreement_score":0.978724,"about_ca_system_score_codex":0.0003550381,"about_ca_system_score_gemma":0.0002498723,"threshold_uncertainty_score":0.99989635},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056709018,0.000013027944,0.94104654,0.0010672858,0.000028911865,0.000035877656,0.000019938616,0.00006588678,0.0010135294],"genre_scores_gemma":[0.9009894,0.000007779323,0.09847775,0.0003537835,0.000036691727,0.000004684466,0.0000100371235,0.0000023153034,0.00011756231],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9996058,0.000003894109,0.00007568214,0.00015821624,0.00005399869,0.00010243477],"domain_scores_gemma":[0.99969995,0.00005573249,0.000011660431,0.00016200426,0.000016116826,0.00005455665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014749994,0.0000476281,0.000041056726,0.000027558519,0.00006487505,0.000051223567,0.00018325553,0.000014656991,0.000016237309],"category_scores_gemma":[0.0000013907592,0.00003450429,0.000012366403,0.00007569786,0.0000213599,0.00013084576,0.000035601413,0.0000306709,0.000010847985],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012003552,0.00008359079,0.0012840399,0.0000054890006,0.000008793369,0.00000626897,0.00101646,0.000002159102,0.0037527666,0.24857433,0.0009574878,0.7443074],"study_design_scores_gemma":[0.00096462056,0.00018635103,0.6852357,0.000049056074,0.000010028739,0.00023473553,0.0017372394,0.17090927,0.050405033,0.023095272,0.06614838,0.0010243232],"about_ca_topic_score_codex":0.000042807318,"about_ca_topic_score_gemma":0.000016381491,"teacher_disagreement_score":0.84428036,"about_ca_system_score_codex":0.0000033999436,"about_ca_system_score_gemma":0.000008554788,"threshold_uncertainty_score":0.14070441},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7221877,0.00018135674,0.21121493,0.017568858,0.0029736252,0.0010363136,0.0008386122,0.00088812044,0.04311048],"genre_scores_gemma":[0.787156,0.0000029072762,0.2113175,0.00018728181,0.00008465022,0.000030532967,0.00013336418,0.000008851807,0.0010789103],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889207,0.00002107277,0.000193272,0.0005071072,0.00014991318,0.00023655682],"domain_scores_gemma":[0.99790674,0.0003649742,0.00006717978,0.0015588499,0.000024082881,0.000078195575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030590632,0.00010674241,0.000116353884,0.00014758098,0.00009718798,0.00016401974,0.0019924561,0.000025629484,0.000020239959],"category_scores_gemma":[0.00019383561,0.000099039666,0.000016304917,0.00061449595,0.000061512015,0.00073979207,0.00090123375,0.00023098664,0.000065253764],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028627753,0.0002817482,0.047810897,0.000009904034,0.000013918137,0.000028837436,0.0017509371,0.000019452851,0.004072876,0.0353619,0.04370196,0.86694473],"study_design_scores_gemma":[0.00037981255,0.000012442609,0.025542699,0.000034927456,0.0000042025626,0.000004561027,0.00016928678,0.7583588,0.00060025434,0.0007087748,0.21393773,0.00024652868],"about_ca_topic_score_codex":0.00026130394,"about_ca_topic_score_gemma":0.0113237025,"teacher_disagreement_score":0.86669815,"about_ca_system_score_codex":0.000012557677,"about_ca_system_score_gemma":0.000059692582,"threshold_uncertainty_score":0.6318892},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09662678,0.00047233404,0.8714099,0.018650813,0.0002279282,0.00020037896,0.000004058285,0.00012008423,0.012287746],"genre_scores_gemma":[0.799513,0.00011947403,0.18957403,0.0004894206,0.00078910746,0.000010798018,0.000009761105,0.000054794644,0.009439611],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973193,0.00073221355,0.0004276059,0.00028515566,0.0008231597,0.00041258085],"domain_scores_gemma":[0.9977609,0.0009889345,0.00028560197,0.0005058801,0.00021174285,0.000246937],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.005018271,0.00011459298,0.0002462483,0.00039199536,0.000451391,0.0013781327,0.0037381058,0.0000542594,0.00010446294],"category_scores_gemma":[0.00079925545,0.00009259699,0.00007156381,0.0007593492,0.000067893605,0.0013610139,0.002111179,0.0013944047,0.00010071363],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010617446,0.00009738193,0.0127011305,0.000013945912,0.000021477019,0.00003078669,0.00086781225,0.00039873898,0.00024456772,0.001093274,0.014796326,0.96972394],"study_design_scores_gemma":[0.00060019916,0.0006044717,0.005083202,0.00013870826,0.000003883837,0.0002117979,0.00013030581,0.42267525,0.0002204645,0.00062298885,0.56956464,0.0001440724],"about_ca_topic_score_codex":0.0000921299,"about_ca_topic_score_gemma":0.000002911434,"teacher_disagreement_score":0.9695799,"about_ca_system_score_codex":0.000025971634,"about_ca_system_score_gemma":0.00015350823,"threshold_uncertainty_score":0.9996585},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04277987,0.000011576591,0.9548551,0.00049021776,0.00008792598,0.00008792118,0.0000011168071,0.00020435847,0.0014819409],"genre_scores_gemma":[0.3371569,0.0000018164083,0.6619414,0.00025834912,0.00003937358,0.000012874903,0.000023727376,0.000006043649,0.0005594938],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904984,0.000018761582,0.00019202134,0.00024706087,0.00026577563,0.00022651434],"domain_scores_gemma":[0.9994213,0.000058569014,0.00013578286,0.00025757367,0.00006471604,0.00006208351],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003078251,0.0000901934,0.00008507365,0.00006797996,0.0002699606,0.0002089778,0.00032461452,0.000040581657,0.000018801864],"category_scores_gemma":[0.00006816933,0.00008747746,0.00003943495,0.00020850023,0.000008103718,0.00033027914,0.00011284096,0.00008672843,0.00007445784],"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":[0.0000017330982,0.00011382673,0.0018873491,0.000011672011,0.000035763514,0.0000055468613,0.0013238495,0.900967,0.0029063036,0.024892278,0.00042892084,0.06742575],"study_design_scores_gemma":[0.0004406777,0.000030683546,0.00054768694,0.000024442887,0.0000062039426,0.000001213076,0.00006800331,0.9901101,0.003432793,0.00010936622,0.0050908113,0.00013799482],"about_ca_topic_score_codex":0.00023018576,"about_ca_topic_score_gemma":0.00000660847,"teacher_disagreement_score":0.29437703,"about_ca_system_score_codex":0.00029198563,"about_ca_system_score_gemma":0.00009569802,"threshold_uncertainty_score":0.35672274},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015759029,0.00023222792,0.99512017,0.00023181533,0.0007528903,0.00023884162,0.000043370568,0.000072837625,0.001731975],"genre_scores_gemma":[0.033700544,0.00000836507,0.9655724,0.00039127743,0.00014441751,0.0000062196555,0.000012425164,0.000025501093,0.00013881919],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99703676,0.000030145178,0.000585861,0.0010541838,0.0008149831,0.00047805294],"domain_scores_gemma":[0.99746335,0.00043646555,0.00053685304,0.0011744169,0.00027101513,0.00011792617],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009422233,0.00034442943,0.00050478993,0.000737371,0.00027974733,0.0002387253,0.0021244301,0.00021138796,0.000009480644],"category_scores_gemma":[0.00014469324,0.00033989997,0.000110811976,0.0010552992,0.00038955818,0.00017354693,0.00076034176,0.00038839944,0.000008064231],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013552875,0.00014065497,0.00025689727,0.000041141626,0.000040597428,0.000026472891,0.002139923,0.2818695,0.00070623506,0.020347252,0.00007321577,0.69435674],"study_design_scores_gemma":[0.00014761915,0.000055544868,0.00019212152,0.00023605012,0.000014884812,0.00002775256,3.2257543e-7,0.9902566,0.0012193939,0.006854836,0.00058231014,0.00041254776],"about_ca_topic_score_codex":0.000030475228,"about_ca_topic_score_gemma":0.000017803077,"teacher_disagreement_score":0.70838714,"about_ca_system_score_codex":0.00030416317,"about_ca_system_score_gemma":0.00049316866,"threshold_uncertainty_score":0.9999053},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15278098,0.000026327942,0.8454089,0.00020766558,0.000091583795,0.000048045113,0.00017884468,0.000053654403,0.001204011],"genre_scores_gemma":[0.509283,0.000001582983,0.49038717,0.00011469888,0.000038528626,0.0000016849378,0.000116857445,0.0000031470945,0.000053332686],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906015,0.000009035889,0.0002204947,0.00035407842,0.00019323238,0.00016299885],"domain_scores_gemma":[0.9981938,0.00015318107,0.00007135122,0.0014872589,0.000031582447,0.000062812025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004175731,0.00006535716,0.000086964195,0.000043363238,0.000042735493,0.000042407068,0.0016749046,0.000022902348,0.000038498354],"category_scores_gemma":[0.000021886628,0.000055327662,0.000015481382,0.00016290291,0.00002024275,0.00008792292,0.00071129296,0.00004095121,0.0000204118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026672767,0.0003619596,0.0069062393,0.000011378151,0.000043860196,0.000020875357,0.001619178,0.0005619185,0.0032552069,0.0463388,0.00543003,0.9354479],"study_design_scores_gemma":[0.00018501742,0.000023097364,0.021051932,0.000030829153,0.0000066351936,0.0000025341187,0.00028241597,0.9692992,0.0039915713,0.00028602043,0.004686868,0.00015386657],"about_ca_topic_score_codex":0.0013161732,"about_ca_topic_score_gemma":0.00008432116,"teacher_disagreement_score":0.9687373,"about_ca_system_score_codex":0.000012921627,"about_ca_system_score_gemma":0.000027396734,"threshold_uncertainty_score":0.31124175},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009152455,0.00012505213,0.96180195,0.00040043762,0.00009911193,0.0003290759,8.534621e-7,0.000042688665,0.028048402],"genre_scores_gemma":[0.95822614,0.0000030823544,0.04114954,0.000065740176,0.000036462137,0.00026534405,0.0000026257137,0.00000391251,0.0002471555],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991367,0.00014384715,0.00017607561,0.00023011869,0.00019106777,0.00012217497],"domain_scores_gemma":[0.99945366,0.00009761686,0.000035085224,0.00029654437,0.000058039503,0.000059054557],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007193695,0.00005776084,0.0000975676,0.000056048797,0.00005756597,0.000042482094,0.0004963943,0.000038738646,0.000005993691],"category_scores_gemma":[0.00015151844,0.00003705543,0.000014708898,0.00058318966,0.00003171691,0.0001072011,0.000110915615,0.000112556656,0.000020752903],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.191107e-7,0.0003419356,0.00007363888,0.000017661443,0.000006417478,6.27084e-7,0.007080354,0.0013222184,0.00006281036,0.9620269,0.001293943,0.02777257],"study_design_scores_gemma":[0.0002488921,0.00008201591,0.00089988875,0.000079089456,0.0000021860496,0.000031348864,0.002624832,0.97191614,0.00016952681,0.00063319167,0.023150314,0.0001625526],"about_ca_topic_score_codex":0.00012905122,"about_ca_topic_score_gemma":0.00000854494,"teacher_disagreement_score":0.9705939,"about_ca_system_score_codex":0.000030000247,"about_ca_system_score_gemma":0.00008539175,"threshold_uncertainty_score":0.15110765},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71277064,0.000004321246,0.28472823,0.00015914797,0.00010726098,0.000068777954,0.000030247606,0.000052520845,0.0020788787],"genre_scores_gemma":[0.78224885,0.0000023091245,0.21746677,0.00016695732,0.000049071008,0.0000056416434,0.000009065592,0.000005434013,0.00004589963],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990575,0.000009861985,0.00022852905,0.00029279632,0.00022986051,0.00018145805],"domain_scores_gemma":[0.9993878,0.000015761198,0.00008887601,0.00042005122,0.000029313092,0.00005822493],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011088702,0.00010033745,0.000119427066,0.00006836,0.00007872658,0.000057112156,0.00051196426,0.000029512079,0.000031952033],"category_scores_gemma":[0.000004424775,0.000094086514,0.000043764994,0.00018874781,0.000028775043,0.00033836017,0.00016266726,0.00005314515,0.00001622274],"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":[0.00003523009,0.0021651203,0.020861503,0.00012031976,0.00017246522,0.00014046273,0.005003552,0.00700483,0.3255614,0.14420673,0.0019599402,0.49276844],"study_design_scores_gemma":[0.0043035853,0.0007572738,0.020547083,0.00048927567,0.0000460385,0.00015893701,0.0007701311,0.5649272,0.402709,0.0007329712,0.0033867357,0.0011717399],"about_ca_topic_score_codex":0.00025646377,"about_ca_topic_score_gemma":0.000053685595,"teacher_disagreement_score":0.5579224,"about_ca_system_score_codex":0.000048431735,"about_ca_system_score_gemma":0.000097776545,"threshold_uncertainty_score":0.38367367},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036604907,0.000057333873,0.95255834,0.002355238,0.00017694781,0.00014544255,0.000021366088,0.00040387164,0.040620957],"genre_scores_gemma":[0.2366847,0.00006419679,0.7307353,0.0014129037,0.000103242586,0.00015839093,0.00009458763,0.000020190148,0.030726483],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931395,0.000011463266,0.00012848499,0.00026483732,0.0001295002,0.00015174464],"domain_scores_gemma":[0.9994599,0.000039562954,0.00004216734,0.0003583379,0.000025932115,0.000074059506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000081620376,0.00007026163,0.00005993569,0.000037599908,0.000121296456,0.00014986849,0.00036101174,0.00002582681,0.0001189594],"category_scores_gemma":[0.000017943794,0.00006278575,0.000018344856,0.00021986142,0.000015518563,0.00028995532,0.00008189142,0.000045658457,0.00016093353],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.3886537e-7,0.00010105423,0.000087539585,0.000004197835,0.0000069490056,0.0000045728816,0.00032321192,0.0000010073527,0.00076714216,0.021532336,0.40091875,0.57625306],"study_design_scores_gemma":[0.00010206148,0.000035644684,0.00012248724,0.000007523898,0.0000032276344,0.000027277398,0.000052396284,0.85649717,0.00035655065,0.00019006517,0.14246231,0.00014327973],"about_ca_topic_score_codex":0.000042407875,"about_ca_topic_score_gemma":0.0000025331508,"teacher_disagreement_score":0.85649616,"about_ca_system_score_codex":0.000022186941,"about_ca_system_score_gemma":0.000010089293,"threshold_uncertainty_score":0.25603288},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020798147,0.00021023849,0.9953512,0.00013354354,0.00018881865,0.00017145654,0.0017138355,0.00014019184,0.00001088752],"genre_scores_gemma":[0.9283933,0.00030451486,0.07050336,0.00008659467,0.00009904372,0.00004571191,0.00043478076,0.000024410429,0.000108303226],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986657,0.000011471756,0.00021942046,0.00077847816,0.000091374844,0.00023353862],"domain_scores_gemma":[0.99757725,0.00035158463,0.000033320066,0.0018794677,0.000035221397,0.00012313416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018134233,0.00017931913,0.00021265313,0.00020712042,0.0002621051,0.00013441547,0.0011308993,0.00005526418,0.0000035248922],"category_scores_gemma":[0.0000103523425,0.00017971887,0.000031471467,0.00036461806,0.000027709164,0.0007536913,0.00010607194,0.00013422537,0.000008439316],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036529127,0.00011536796,0.000046014407,0.000084700616,0.0002774402,0.0000098750625,0.00056669256,0.023443501,0.00010466826,0.000006353896,0.0006013871,0.9747403],"study_design_scores_gemma":[0.00029606148,0.000032708955,0.00012208981,0.000022819833,0.00013061448,0.000043003176,0.0000101362275,0.99127257,0.00010186599,0.0000014679041,0.0077554216,0.00021121552],"about_ca_topic_score_codex":0.0000531368,"about_ca_topic_score_gemma":0.00017374902,"teacher_disagreement_score":0.97452915,"about_ca_system_score_codex":0.000013373277,"about_ca_system_score_gemma":0.000018373763,"threshold_uncertainty_score":0.7328723},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22949407,0.0008966639,0.7688706,0.00023656181,0.00030724434,0.00006651028,0.000078115925,0.00002094098,0.00002931627],"genre_scores_gemma":[0.77285707,0.0003690127,0.22627637,0.000015651047,0.00044107903,0.00000280265,0.000021180978,0.000007887298,0.000008921551],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99831754,0.00019449023,0.0006121076,0.0003037985,0.00039650264,0.00017555837],"domain_scores_gemma":[0.99815226,0.00039726382,0.0006685027,0.00050945295,0.000118094664,0.00015441714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011489647,0.00011800485,0.00033804783,0.00015083779,0.00011890609,0.00022297239,0.0009221233,0.00006997551,9.606568e-7],"category_scores_gemma":[0.00006875833,0.000095086674,0.000061941035,0.00030899703,0.00007481106,0.00080765656,0.00054947275,0.000280046,0.0000013105064],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004004682,0.00040574084,0.01575846,0.000023196617,0.00026240922,0.00008815107,0.00058760896,0.00015118561,0.0017893191,0.00036393973,0.0010405282,0.9794894],"study_design_scores_gemma":[0.0011490957,0.00028833403,0.07262029,0.00036143788,0.00003327519,0.0003115442,0.00012424822,0.90966696,0.0001310001,0.00021964917,0.014871702,0.00022247882],"about_ca_topic_score_codex":0.00064417726,"about_ca_topic_score_gemma":0.0000033910937,"teacher_disagreement_score":0.97926694,"about_ca_system_score_codex":0.000011304911,"about_ca_system_score_gemma":0.00003347546,"threshold_uncertainty_score":0.3877522},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01650557,0.000022687744,0.9817258,0.0012359961,0.00017568145,0.00006234781,0.00023062965,0.00000841111,0.000032847933],"genre_scores_gemma":[0.21179652,0.00001794431,0.78797084,0.00004226667,0.000077157005,0.0000052855517,0.000035673467,0.0000023012508,0.000051986535],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990925,0.0000306235,0.00030418465,0.00012989879,0.00036780807,0.00007499194],"domain_scores_gemma":[0.9976743,0.00016499139,0.00041797294,0.00008080263,0.001580987,0.00008094939],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009890215,0.00005851885,0.00012667535,0.0001105452,0.000048453323,0.00015040355,0.00027961557,0.00003567967,0.0000017048579],"category_scores_gemma":[0.00042441895,0.000047851143,0.000046504607,0.00012767468,0.000013284271,0.0003086616,0.00005341584,0.00007282067,6.8014276e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016237608,0.0006414262,0.07261138,0.00003273772,0.0014878302,0.0000028698403,0.0018214502,0.021800794,0.0005183358,0.3103155,0.017662376,0.572943],"study_design_scores_gemma":[0.00022369342,0.000059814847,0.004775756,0.000005295997,0.000054952565,0.000004970811,0.000004921299,0.7670986,0.000042722313,0.22689043,0.0007949543,0.000043872842],"about_ca_topic_score_codex":0.000030658757,"about_ca_topic_score_gemma":0.00003019553,"teacher_disagreement_score":0.7452978,"about_ca_system_score_codex":0.00017914531,"about_ca_system_score_gemma":0.0001029359,"threshold_uncertainty_score":0.1951313},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037115272,0.000015901505,0.96565723,0.00042148092,0.00007317526,0.0001286333,0.000006392239,0.00013494104,0.029850714],"genre_scores_gemma":[0.63029796,0.0000013912012,0.36863476,0.0007453286,0.000111022484,0.000015529788,0.0000101742835,0.000004803984,0.00017905721],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99919325,0.000022407408,0.0001456636,0.00025879624,0.00015271014,0.00022714368],"domain_scores_gemma":[0.999182,0.00017309283,0.00005301019,0.00045892145,0.00005443839,0.000078577556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007644325,0.000075698,0.00006884709,0.000024939987,0.00022039379,0.00020912672,0.0009695452,0.000019970987,0.0000060490515],"category_scores_gemma":[0.0000250399,0.00004660171,0.000019683772,0.00020653139,0.000055212462,0.00039662162,0.0001162833,0.00009837266,0.000020605206],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013527111,0.00009968022,0.0001249543,0.0000011651883,0.000015001795,0.000002795237,0.0011869766,0.000041739946,0.00024658398,0.5084941,0.00075827923,0.4890274],"study_design_scores_gemma":[0.00024775637,0.00003982955,0.004614798,0.0000033899012,0.0000041176463,0.00003355195,0.0007874193,0.984817,0.0010822462,0.0027186063,0.0055053374,0.0001459405],"about_ca_topic_score_codex":0.000107594475,"about_ca_topic_score_gemma":0.000015329364,"teacher_disagreement_score":0.98477525,"about_ca_system_score_codex":0.00001307927,"about_ca_system_score_gemma":0.000017907067,"threshold_uncertainty_score":0.20166138},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025207885,0.000024026145,0.9908293,0.00067798386,0.00014174893,0.00015393907,0.00004331375,0.000060428465,0.0055484795],"genre_scores_gemma":[0.42237735,7.872972e-7,0.5770526,0.00019603143,0.00006229729,0.000017995513,0.000008769397,0.0000034115185,0.00028076823],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993268,0.000008024852,0.00019123379,0.00015229298,0.0000948419,0.00022680682],"domain_scores_gemma":[0.99931115,0.0001272406,0.00007754829,0.00030576615,0.00004288509,0.00013540388],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001853706,0.00007281006,0.00011072992,0.0000362153,0.000039541315,0.000033509994,0.00038328124,0.000030458243,0.00007622603],"category_scores_gemma":[0.000024135301,0.00006404299,0.00004335788,0.00010455978,0.00005981832,0.00024563048,0.00007832586,0.000028643377,0.000013901625],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.2199395e-7,0.000040510015,0.00088113046,0.0000077268505,0.000014464343,1.6014792e-7,0.000513012,7.3633356e-7,0.00088474684,0.117523246,0.009046031,0.8710878],"study_design_scores_gemma":[0.010117122,0.0010174214,0.023110665,0.00040076405,0.00017428464,0.00033140535,0.0042171218,0.51267684,0.09031213,0.012349728,0.3424422,0.0028502776],"about_ca_topic_score_codex":0.000052023668,"about_ca_topic_score_gemma":0.000003996604,"teacher_disagreement_score":0.86823756,"about_ca_system_score_codex":0.00000950197,"about_ca_system_score_gemma":0.0000806601,"threshold_uncertainty_score":0.26115975},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.080012955,0.00009872755,0.9170102,0.0010818201,0.000091642,0.00007956991,0.00000420187,0.00006328395,0.0015576377],"genre_scores_gemma":[0.29659286,0.00008148015,0.70288277,0.00010107034,0.000051730185,0.000014215218,0.000054655276,0.0000045258207,0.00021670251],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991951,0.000014079099,0.0001669093,0.00039753184,0.00013093246,0.0000954487],"domain_scores_gemma":[0.9990836,0.000044759887,0.000042060314,0.0007682816,0.00002331762,0.000037976162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020629735,0.000057134883,0.000056088753,0.000103941326,0.00008246272,0.00014229947,0.0005089474,0.00003246203,0.000017468943],"category_scores_gemma":[0.000031936324,0.000051926807,0.000004817027,0.00049091806,0.000018079274,0.00043009745,0.00027904718,0.00003911784,0.000021820699],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.6722077e-7,0.00004641241,0.00026654513,9.92869e-7,8.461159e-7,4.5196109e-7,0.00020392596,0.00016786215,0.00017012797,0.00936118,0.004710427,0.98507094],"study_design_scores_gemma":[0.00014251871,0.0000069786934,0.011185696,0.000008274734,0.0000012449634,0.000007580329,0.00004875894,0.98359007,0.000028116221,0.00016342112,0.004751231,0.000066108914],"about_ca_topic_score_codex":0.000020963646,"about_ca_topic_score_gemma":0.000044402135,"teacher_disagreement_score":0.98500484,"about_ca_system_score_codex":0.000017077666,"about_ca_system_score_gemma":0.0000063569337,"threshold_uncertainty_score":0.21175137},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01869728,0.000043986125,0.9792265,0.00019451244,0.00010931459,0.00011454683,0.0000027190672,0.00011789014,0.0014932384],"genre_scores_gemma":[0.1543396,0.000008692938,0.8453139,0.00015924488,0.00003178978,0.000034920777,0.0000028003942,0.000005713866,0.00010331176],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99899554,0.000014281132,0.0003415037,0.00038186306,0.00008327186,0.00018356301],"domain_scores_gemma":[0.9989047,0.00018455287,0.00022293307,0.00051749503,0.00009259475,0.00007771043],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006326418,0.000081549864,0.00010293235,0.00003861195,0.00019048185,0.00028969877,0.0003400778,0.00004278647,0.000007984937],"category_scores_gemma":[0.00078436005,0.0000728125,0.000015227278,0.00037938962,0.000028997913,0.00044390422,0.000062970714,0.000046436766,0.000002536222],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.157193e-7,0.000037526246,0.0010425721,0.000010781579,0.0000037047703,0.0000026574353,0.0003661802,0.000021958795,0.0003661604,0.5768382,0.00019146815,0.4211184],"study_design_scores_gemma":[0.00014534354,0.00012470612,0.0048668,0.00011749798,0.000014235594,0.0001507962,0.0009838851,0.84111285,0.0062201414,0.10640532,0.039214067,0.0006443462],"about_ca_topic_score_codex":0.000008722626,"about_ca_topic_score_gemma":0.0000048575243,"teacher_disagreement_score":0.8410909,"about_ca_system_score_codex":0.0000063445427,"about_ca_system_score_gemma":0.00005364243,"threshold_uncertainty_score":0.29692075},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053170994,0.0001355642,0.91844946,0.0046865,0.00029265153,0.00047655782,0.000043348,0.00003857891,0.022706358],"genre_scores_gemma":[0.48587933,0.00003499595,0.51237184,0.00008628021,0.0003871197,0.000030047277,0.00003974849,0.000019915084,0.0011507284],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978155,0.0005005791,0.0004957074,0.00018627022,0.0007686168,0.00023333597],"domain_scores_gemma":[0.9974481,0.00040174733,0.00027969695,0.0002417746,0.0015194617,0.00010924972],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008198095,0.00007372581,0.00010907319,0.00024068121,0.00035817613,0.00036399518,0.0009479919,0.000021491433,0.000023453811],"category_scores_gemma":[0.00092301663,0.00006278212,0.00005726728,0.00032068382,0.000035684818,0.0008035657,0.00011641718,0.0002061876,0.00011726689],"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":[0.00007084605,0.00088668027,0.0027796673,0.000117084724,0.00028997712,0.000049700953,0.023045992,0.00021976384,0.023170466,0.49013102,0.15421407,0.3050247],"study_design_scores_gemma":[0.004435307,0.0036430564,0.2654566,0.00067728496,0.000063488966,0.00035372959,0.0031267342,0.49008456,0.0044852104,0.031596012,0.19504546,0.001032596],"about_ca_topic_score_codex":0.000003085543,"about_ca_topic_score_gemma":9.965192e-7,"teacher_disagreement_score":0.4898648,"about_ca_system_score_codex":0.00012037149,"about_ca_system_score_gemma":0.00022512898,"threshold_uncertainty_score":0.35100138},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028418483,0.000023849685,0.9690292,0.0011426982,0.000025489127,0.00008409981,0.00006612103,0.00008156764,0.0011285029],"genre_scores_gemma":[0.5362356,0.0000069351236,0.46226966,0.00024015685,0.00005807684,0.000089474706,0.00023826658,0.000008962099,0.00085290265],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999014,0.00001514708,0.00019811119,0.00034130376,0.00014498497,0.00028645294],"domain_scores_gemma":[0.9994684,0.000024580115,0.00003930162,0.0004180371,0.0000055420655,0.00004416714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013073425,0.00009502377,0.00009759932,0.000040343286,0.000066700944,0.0000940292,0.00046969994,0.000033747554,0.00005753025],"category_scores_gemma":[0.0000018416306,0.00008829502,0.000027393595,0.00015662576,0.00001849765,0.00020257542,0.0002586174,0.000065616856,0.00013512214],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000934957,0.0034061559,0.19175106,0.000029468045,0.000030871422,0.00017376826,0.0019413339,0.0078052646,0.0009240217,0.055948634,0.06523065,0.6727494],"study_design_scores_gemma":[0.00072277733,0.000035198595,0.17102234,0.000011328039,0.0000029272203,0.00001073537,0.00013701849,0.7634359,0.00018166518,0.00095680146,0.06319954,0.00028376235],"about_ca_topic_score_codex":0.00024658843,"about_ca_topic_score_gemma":0.00014332752,"teacher_disagreement_score":0.7556306,"about_ca_system_score_codex":0.000034676148,"about_ca_system_score_gemma":0.000010950871,"threshold_uncertainty_score":0.36005664},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07534174,0.0001230432,0.9143455,0.0052652066,0.00066313264,0.0009693048,0.0007675221,0.00052368274,0.0020008828],"genre_scores_gemma":[0.046826277,0.00003208549,0.94943976,0.00023897861,0.00011829728,0.0005517847,0.0015562241,0.00005669145,0.0011799161],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946879,0.0016144721,0.00074299035,0.0016778884,0.00061394274,0.00066276843],"domain_scores_gemma":[0.99219745,0.0010599918,0.0005474617,0.003911176,0.0017894749,0.00049444183],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0052457885,0.000512077,0.00053362246,0.00031345454,0.0008570799,0.0018554166,0.005008162,0.00040850005,0.000026815565],"category_scores_gemma":[0.00043189147,0.00054978614,0.00025161583,0.0004611138,0.00024314442,0.00034857387,0.0032369753,0.0007459801,0.000049958653],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004848741,0.0007789121,0.000058254493,0.000088455316,0.000073213356,0.000006025478,0.014007195,0.0013330575,0.0015760568,0.10356701,0.0011711814,0.8773358],"study_design_scores_gemma":[0.00036162225,0.0000022083718,0.0003656742,0.0005985343,0.000036484103,0.000020262209,0.00013822375,0.96705234,0.011390075,0.004351379,0.014959783,0.00072343927],"about_ca_topic_score_codex":0.0014233027,"about_ca_topic_score_gemma":0.0010520539,"teacher_disagreement_score":0.9657193,"about_ca_system_score_codex":0.00013407496,"about_ca_system_score_gemma":0.00053172646,"threshold_uncertainty_score":0.99969536},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002247114,0.0000052089686,0.9934226,0.00067111704,0.00008383749,0.00016363936,0.000017437686,0.00015220011,0.003236797],"genre_scores_gemma":[0.10806942,0.000026381349,0.88035023,0.0012787833,0.00014105973,0.0002419509,0.00009650477,0.000013041862,0.009782655],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994077,0.000012125482,0.00011511684,0.00021181877,0.000115708426,0.00013754943],"domain_scores_gemma":[0.9994987,0.00010280038,0.000054185508,0.00022312737,0.00008731496,0.000033834498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011472433,0.000057368918,0.00006912297,0.00003396119,0.00022123274,0.000054914322,0.0003148911,0.000031588927,0.000009229822],"category_scores_gemma":[0.000063192594,0.000051748964,0.000033723554,0.0002302085,0.00002337297,0.00033825164,0.000060723363,0.00002813441,0.0000393053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014741292,0.00009652077,0.0009096482,0.0000038658122,0.000021401345,9.936265e-7,0.0011612854,0.00001090427,0.00026743,0.8200763,0.10568506,0.07176512],"study_design_scores_gemma":[0.00057920686,0.00011078108,0.012254192,0.0000067982205,0.0000070271103,0.00000869231,0.00010355005,0.8457924,0.0028504855,0.007699895,0.1302705,0.00031645127],"about_ca_topic_score_codex":0.000010078052,"about_ca_topic_score_gemma":0.0000019053363,"teacher_disagreement_score":0.8457815,"about_ca_system_score_codex":0.000033138043,"about_ca_system_score_gemma":0.000051323917,"threshold_uncertainty_score":0.21102615},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7241221,0.00003093305,0.1396523,0.01511596,0.0051006037,0.0022814581,0.004908138,0.0014726494,0.10731583],"genre_scores_gemma":[0.9876193,0.0007694578,0.006659396,0.0012522717,0.0006281493,0.0005679739,0.001742826,0.00010777265,0.0006528893],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9926582,0.000035692916,0.0018036439,0.002050415,0.0025599464,0.00089210767],"domain_scores_gemma":[0.9907635,0.00017564745,0.0022389386,0.0003546129,0.006082529,0.0003847652],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009030943,0.0009629703,0.0008087324,0.0012812329,0.00049544766,0.000994227,0.0028762151,0.0005658778,0.0021592919],"category_scores_gemma":[0.0004983221,0.00102981,0.00041221455,0.0007093536,0.0001984934,0.002745086,0.0005330104,0.0012156817,0.001601972],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038513038,0.0044417786,0.14576416,0.00034983552,0.002059635,0.000067893205,0.0037035164,0.000015704498,0.011011595,0.07105615,0.0059854696,0.75515914],"study_design_scores_gemma":[0.012592922,0.0026802407,0.16119449,0.0064909067,0.00043002827,0.0007514993,0.002569102,0.6990268,0.05235294,0.054096233,0.0019502888,0.0058645275],"about_ca_topic_score_codex":0.00037584302,"about_ca_topic_score_gemma":0.00007304308,"teacher_disagreement_score":0.7492946,"about_ca_system_score_codex":0.0007265135,"about_ca_system_score_gemma":0.00021177394,"threshold_uncertainty_score":0.99921525},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0089080185,0.000019381185,0.9870651,0.0027054262,0.000096551725,0.0001736687,0.000075929915,0.00014838186,0.0008075776],"genre_scores_gemma":[0.52622014,0.000002720613,0.4727045,0.0005426303,0.0001105757,0.000038681483,0.00006550168,0.000006912692,0.00030834132],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992658,0.000008466052,0.00014797099,0.00027650432,0.00012060312,0.00018067268],"domain_scores_gemma":[0.99937046,0.00006559854,0.000037465088,0.00042090836,0.00003141342,0.00007415379],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017020329,0.00007882219,0.00007461776,0.00004522885,0.00012518905,0.000104701285,0.0003940122,0.000018051409,0.00003621834],"category_scores_gemma":[0.0000049694027,0.00006863199,0.000040042676,0.000117617325,0.000012201424,0.00024620513,0.00002332718,0.000039053702,0.00005141416],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001324835,0.00016911668,0.00003239974,0.000007938088,0.00000932657,5.104787e-7,0.00043105552,0.0022142741,0.0013204305,0.0037589928,0.01102498,0.9810296],"study_design_scores_gemma":[0.00025689745,0.000026654712,0.0002367495,0.000009214621,0.0000045807133,0.0000054668126,0.00003393239,0.94141304,0.0041811024,0.000014415283,0.053713534,0.000104392224],"about_ca_topic_score_codex":0.00007228232,"about_ca_topic_score_gemma":0.000026888381,"teacher_disagreement_score":0.98092526,"about_ca_system_score_codex":0.00003186603,"about_ca_system_score_gemma":0.000020720323,"threshold_uncertainty_score":0.27987313},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021450454,0.0000462632,0.96711904,0.00015097832,0.000062899635,0.00006232653,0.000016440907,0.00047306993,0.010618529],"genre_scores_gemma":[0.0657962,0.0000032346086,0.93386,0.000094527786,0.000004327263,0.000007340739,0.0000141056225,0.0000032256687,0.00021703308],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994456,0.000015759259,0.00013366598,0.00018354823,0.000108376546,0.00011304951],"domain_scores_gemma":[0.9992707,0.000032648877,0.000041320807,0.00057154096,0.000038194317,0.000045642933],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001829979,0.000052598538,0.000072064795,0.000041923307,0.000046565103,0.00003293115,0.0004009759,0.000016186426,0.00003324216],"category_scores_gemma":[0.000043460033,0.0000465027,0.00001787782,0.00034254225,0.00002209046,0.00025615827,0.00008260402,0.000027520897,0.000033776123],"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":[4.6441886e-7,0.00015986033,0.00089274655,0.00001692392,0.000013792158,0.0000061353103,0.00024257913,0.000011931752,0.01721794,0.93568015,0.026324654,0.019432837],"study_design_scores_gemma":[0.00031667124,0.000029908355,0.00070968334,0.000019063673,0.000004650561,0.000018655754,0.00007791359,0.9112733,0.044054195,0.00049770036,0.04281135,0.00018691088],"about_ca_topic_score_codex":0.000020130497,"about_ca_topic_score_gemma":0.0000012072486,"teacher_disagreement_score":0.93518245,"about_ca_system_score_codex":0.0000039840734,"about_ca_system_score_gemma":0.000034410987,"threshold_uncertainty_score":0.1896325},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020930257,0.000019282777,0.98001397,0.0035022607,0.000034853074,0.000053406144,0.000015591098,0.00016711552,0.014100471],"genre_scores_gemma":[0.60222214,0.00001136056,0.38692874,0.003376697,0.00017878963,0.00003463947,0.000024476065,0.00001061956,0.00721257],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99941784,0.000010233893,0.00008284809,0.00023421686,0.00010466332,0.00015018602],"domain_scores_gemma":[0.9995759,0.000035392164,0.000021845663,0.00027985565,0.000027845206,0.00005914804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000070594346,0.000061695406,0.0000526497,0.000021088084,0.00007306376,0.000095937445,0.00047274816,0.00002263201,0.000050590257],"category_scores_gemma":[0.000004181425,0.000054946384,0.000018407645,0.00017990038,0.000013843993,0.0003635938,0.000080519254,0.00006519951,0.00050172524],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.2539642e-7,0.00006867963,0.00008782689,7.991138e-7,0.000008183548,5.1550467e-7,0.00037737205,0.000005008029,0.0002788985,0.007807543,0.14884093,0.842524],"study_design_scores_gemma":[0.00032451696,0.0000567223,0.0019205661,0.0000037468324,0.000006650477,0.0000144873875,0.000055748664,0.51455796,0.009658796,0.0004348295,0.47269765,0.00026831898],"about_ca_topic_score_codex":0.000092323186,"about_ca_topic_score_gemma":0.000020236997,"teacher_disagreement_score":0.8422557,"about_ca_system_score_codex":0.000020575328,"about_ca_system_score_gemma":0.000017763621,"threshold_uncertainty_score":0.64488304},"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":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12581748,0.00037734292,0.8064063,0.008276653,0.0014482513,0.00041684706,0.00019450365,0.0010368844,0.056025755],"genre_scores_gemma":[0.02542416,0.00010801186,0.9722846,0.00044181422,0.00037773195,0.000021402731,0.00014146308,0.0000128495585,0.0011879791],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99869657,0.000024990297,0.00020154372,0.0006202683,0.00018631175,0.00027032607],"domain_scores_gemma":[0.99633056,0.00011081171,0.000050524417,0.003395619,0.000023200999,0.00008928599],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002983463,0.0001156648,0.0001246802,0.00004763048,0.00017945927,0.00022622042,0.004721919,0.00004527917,0.0003829614],"category_scores_gemma":[0.00007526581,0.00010989355,0.000026938056,0.00037813734,0.000027578484,0.0008260771,0.00126645,0.00010460275,0.00020959118],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.7045013e-7,0.000020914445,0.00013698003,0.0000018373041,0.0000069688267,0.000004271962,0.00013061162,0.000003140197,0.00002846158,0.0004282969,0.01703158,0.98220617],"study_design_scores_gemma":[0.0001946442,0.00006460295,0.0023621083,0.000034499546,0.000010050672,0.000027285672,0.000025004632,0.36935508,0.00011190287,0.0022323502,0.6252734,0.0003090695],"about_ca_topic_score_codex":0.00017282034,"about_ca_topic_score_gemma":0.000021494448,"teacher_disagreement_score":0.9818971,"about_ca_system_score_codex":0.000015657452,"about_ca_system_score_gemma":0.000062531704,"threshold_uncertainty_score":0.8774579},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06974934,0.0000011484269,0.91401994,0.0016875392,0.00022891708,0.00066514814,0.00005505911,0.00031706408,0.013275834],"genre_scores_gemma":[0.9766022,8.218081e-8,0.022287218,0.00095020555,0.00007738835,0.000051358704,0.000015102415,0.0000048712905,0.000011581884],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977192,0.00003341188,0.00019217536,0.000941624,0.0008032754,0.00031026485],"domain_scores_gemma":[0.9967312,0.00008860703,0.000093898714,0.0029712827,0.00003576604,0.00007923911],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016501693,0.0001376765,0.00011256902,0.000108551285,0.0007960886,0.0007859575,0.004465287,0.000022575112,0.0000025088152],"category_scores_gemma":[0.000023721952,0.00009449967,0.000012392332,0.0007355636,0.00010107601,0.00036609883,0.00040645234,0.00009927611,0.000072501316],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000068149646,0.0016286621,0.000029882303,0.000010709197,0.000009639269,0.000028426442,0.0046248557,0.0025686908,0.13520798,0.44536746,0.0031271456,0.4073284],"study_design_scores_gemma":[0.00017239302,0.00017088323,0.0014323195,0.000020936679,0.0000035549222,0.0000018856655,0.00030705202,0.9951116,0.002099917,0.00045544223,0.00009018973,0.00013381634],"about_ca_topic_score_codex":0.000005027603,"about_ca_topic_score_gemma":6.669664e-7,"teacher_disagreement_score":0.9925429,"about_ca_system_score_codex":0.000085448606,"about_ca_system_score_gemma":0.00010249656,"threshold_uncertainty_score":0.82976884},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09653583,0.0011173643,0.84489536,0.007708817,0.00018506109,0.0007346518,0.00017439887,0.000507702,0.048140798],"genre_scores_gemma":[0.66534775,0.004384269,0.32384238,0.00010418766,0.000076171076,0.00056187797,0.00093372975,0.00005801613,0.0046916027],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9866935,0.009351715,0.0009913153,0.0016186399,0.0006519069,0.00069290656],"domain_scores_gemma":[0.9905218,0.0025962612,0.0010873426,0.002880024,0.0025524036,0.00036219132],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.008141495,0.00064260716,0.0005904245,0.0002676889,0.0013328284,0.0014650392,0.0028770352,0.00070332165,0.00004864957],"category_scores_gemma":[0.0016433629,0.00073163054,0.00032024877,0.0009052588,0.001975705,0.0010245063,0.0013252036,0.0009719045,0.000090983616],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008661031,0.00094782846,0.0036391732,0.00016662797,0.00009906942,0.000012952634,0.059180938,0.00040165795,0.005545958,0.6131518,0.0015755608,0.3152698],"study_design_scores_gemma":[0.0007154529,0.0000035804067,0.040833205,0.0019205805,0.00011205985,0.0003193446,0.0010362545,0.82723635,0.02447778,0.023972703,0.07829693,0.0010757763],"about_ca_topic_score_codex":0.005503082,"about_ca_topic_score_gemma":0.004978561,"teacher_disagreement_score":0.8268347,"about_ca_system_score_codex":0.0005327819,"about_ca_system_score_gemma":0.0010889084,"threshold_uncertainty_score":0.9999673},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031439764,0.000018099929,0.98630404,0.004961458,0.00007561022,0.00006519692,0.000007559195,0.00018172857,0.0052423356],"genre_scores_gemma":[0.7389284,0.000003483793,0.2542166,0.0049027167,0.00007307034,0.000014435981,0.000019334617,0.0000044803237,0.0018375133],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992852,0.000008900382,0.000114196126,0.00026962807,0.0001451625,0.00017691827],"domain_scores_gemma":[0.9992468,0.000022814664,0.00002841915,0.00061790395,0.000021670983,0.000062413914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000876816,0.00007537072,0.000070922026,0.00003589186,0.00008122164,0.00031247677,0.0006376858,0.0000218438,0.00002254256],"category_scores_gemma":[0.0000051488746,0.000061334336,0.00003293274,0.00020605998,0.000012729699,0.0005587086,0.000054498752,0.000052880907,0.00016707915],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.1616116e-7,0.00016931587,0.00047390602,0.0000022901165,0.0000032401103,0.000005693367,0.00003645506,0.00007843385,0.0008908752,0.058346607,0.0121382205,0.92785454],"study_design_scores_gemma":[0.0006760969,0.00023725476,0.03207563,0.00003722837,0.000008289076,0.000009352135,0.000019031477,0.88403475,0.016527671,0.010888685,0.05489748,0.0005885022],"about_ca_topic_score_codex":0.00008764921,"about_ca_topic_score_gemma":0.0000049956,"teacher_disagreement_score":0.92726606,"about_ca_system_score_codex":0.000019951802,"about_ca_system_score_gemma":0.000041932937,"threshold_uncertainty_score":0.30132207},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000011698091,0.00024440212,0.9961363,0.0010909919,0.0005878098,0.00040441964,0.00025095098,0.000480289,0.00079310185],"genre_scores_gemma":[0.011120887,0.00003271556,0.98729116,0.00063299196,0.0003954714,0.000018004375,0.00043171973,0.00003599103,0.000041077154],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9951793,0.000018677963,0.0007424841,0.0024193136,0.00091364444,0.00072660146],"domain_scores_gemma":[0.99433815,0.0004202928,0.00042148813,0.004415036,0.00019416565,0.000210852],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0010536538,0.0005563009,0.0006458064,0.00056756515,0.00043403226,0.0010915034,0.010333749,0.00031537315,0.000013275904],"category_scores_gemma":[0.00013820024,0.0005412145,0.00007601844,0.0009307874,0.0006043331,0.0010258777,0.005605091,0.000868472,0.000035098124],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018954963,0.000044742388,0.000030163988,0.000025940606,0.000009822097,0.000023328783,0.0003297586,0.0036639364,0.000033616794,0.012941562,0.00015042379,0.9827448],"study_design_scores_gemma":[0.00022521129,0.0001430594,0.00008699696,0.0009909882,0.000017440072,0.00007230489,5.414494e-7,0.9211622,0.00067642704,0.054935433,0.0206984,0.0009909902],"about_ca_topic_score_codex":0.00006253086,"about_ca_topic_score_gemma":0.00005546903,"teacher_disagreement_score":0.9817538,"about_ca_system_score_codex":0.00038441684,"about_ca_system_score_gemma":0.0008590824,"threshold_uncertainty_score":0.99994546},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008099199,0.000029830535,0.99507874,0.0031207309,0.000047268953,0.00033291866,0.00008207857,0.00018299262,0.00031551617],"genre_scores_gemma":[0.025786266,0.00005233803,0.97301185,0.000107005646,0.00014340022,0.00024861758,0.00060577417,0.000009326191,0.00003539332],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882627,0.000016500415,0.00029479322,0.00043709757,0.00027022365,0.00015514331],"domain_scores_gemma":[0.99688685,0.0004255992,0.00015429824,0.0023241655,0.0001219695,0.000087098924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006179645,0.00008350919,0.000121296005,0.00006739781,0.00006879555,0.000040536524,0.0033314298,0.000081658916,0.000008535179],"category_scores_gemma":[0.00079431,0.000079323596,0.000023455095,0.00029262956,0.000079250516,0.0006247504,0.00067502947,0.00006375937,0.000018954539],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018470863,0.00006590452,0.00034118455,0.0000076199917,0.000005093859,3.9297e-7,0.00009950347,4.600481e-8,0.0041654813,0.0013508288,0.005244042,0.98871803],"study_design_scores_gemma":[0.00019180332,0.000026663374,0.0026298107,0.000016784656,0.000008000493,0.000007924844,0.00003684969,0.9328204,0.0028338516,0.00070624286,0.060616437,0.00010522767],"about_ca_topic_score_codex":0.000036938523,"about_ca_topic_score_gemma":0.0000090663425,"teacher_disagreement_score":0.98861283,"about_ca_system_score_codex":0.000013204063,"about_ca_system_score_gemma":0.00007116309,"threshold_uncertainty_score":0.6190681},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00312195,0.000014444417,0.9824697,0.00020978089,0.00051742845,0.00034504035,0.000014387588,0.00021218306,0.013095091],"genre_scores_gemma":[0.5897348,0.000003985199,0.409807,0.00017073346,0.00010209721,0.00012126634,0.000007560869,0.000012495731,0.000040084913],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983505,0.000024425648,0.0004137531,0.00059380545,0.0001831645,0.00043433893],"domain_scores_gemma":[0.9989048,0.00024013799,0.00014083141,0.00051631604,0.00008102364,0.00011685525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000516892,0.00016702221,0.00017016023,0.00008419116,0.0004155777,0.0003322782,0.0007283098,0.000078896344,0.000032138825],"category_scores_gemma":[0.000118590935,0.00017611115,0.0000695943,0.0004566047,0.00016146209,0.00022466802,0.00010493818,0.00016108456,0.00015183049],"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":[0.0000021946814,0.000020167401,0.0000041270146,0.0000036329952,0.000006616749,6.501213e-7,0.00016714865,0.000084940395,0.010657632,0.7338817,0.0001596809,0.2550115],"study_design_scores_gemma":[0.00009471117,0.00006407184,0.000003985664,0.000019308198,0.000020628806,0.000028861265,0.0024238778,0.16468044,0.40478238,0.3830532,0.04421577,0.0006127645],"about_ca_topic_score_codex":0.000007571967,"about_ca_topic_score_gemma":0.000010292956,"teacher_disagreement_score":0.5866128,"about_ca_system_score_codex":0.0000391863,"about_ca_system_score_gemma":0.00013613698,"threshold_uncertainty_score":0.7181604},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028751593,0.00002647376,0.96819985,0.00015002863,0.000045089302,0.0001034822,0.00013402164,0.00005003945,0.0025394212],"genre_scores_gemma":[0.27435547,0.000003931806,0.7253546,0.000107904125,0.00001895478,0.000005403034,0.0000450068,0.000005168714,0.000103540464],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991059,0.000022942526,0.00020982132,0.00032906936,0.00016893807,0.00016336593],"domain_scores_gemma":[0.9977232,0.00005739986,0.0001038115,0.0020243195,0.000045834047,0.00004542983],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033654942,0.00008612195,0.000100146426,0.000032778793,0.00011193988,0.000057854682,0.002518382,0.000025863636,0.000015949365],"category_scores_gemma":[0.000020749376,0.000056591896,0.000020112057,0.00023816015,0.000062103674,0.0004925997,0.0008915774,0.000057183763,0.000004126364],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010604871,0.0007429337,0.0029961383,0.000043695614,0.0002023767,0.000012287808,0.019478401,0.012536889,0.012502035,0.3793402,0.0151369665,0.5569975],"study_design_scores_gemma":[0.00007603152,0.000011438479,0.00009677564,0.000011349119,0.000008573745,0.0000045555794,0.00028404934,0.9968952,0.0010667568,0.0012333007,0.00023374056,0.00007822659],"about_ca_topic_score_codex":0.0010753826,"about_ca_topic_score_gemma":0.000042921743,"teacher_disagreement_score":0.9843583,"about_ca_system_score_codex":0.000010826689,"about_ca_system_score_gemma":0.00009441804,"threshold_uncertainty_score":0.4679822},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.738945,0.00012161648,0.2531948,0.006471694,0.00034000585,0.0008333751,0.000057314257,0.000017811795,0.000018377603],"genre_scores_gemma":[0.9292586,0.00019033422,0.07020073,0.00005976613,0.000119348995,0.000053512278,0.000007634835,0.000024020259,0.00008604381],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9940725,0.0004643345,0.0012392044,0.00044475577,0.0032197938,0.00055943994],"domain_scores_gemma":[0.9931788,0.0013809486,0.00056196045,0.0010903075,0.0035189516,0.00026906433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045921686,0.00017570857,0.00029124913,0.0006854249,0.0007725491,0.00031884364,0.0031433047,0.00012683605,0.000025042536],"category_scores_gemma":[0.0004883563,0.00011316615,0.00026490504,0.003640197,0.00034444494,0.0011462846,0.000029784716,0.0013684802,0.000015251188],"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":[0.0012829475,0.0012336229,0.02137566,0.00026952004,0.0003035219,0.000085208645,0.018164173,0.05755984,0.44846368,0.091860555,0.006733266,0.35266802],"study_design_scores_gemma":[0.0020034465,0.0007841603,0.8943653,0.0007770873,0.00005815535,0.0000017165237,0.0020370758,0.00545242,0.050042197,0.03491168,0.009256483,0.0003102809],"about_ca_topic_score_codex":0.005844124,"about_ca_topic_score_gemma":0.009229651,"teacher_disagreement_score":0.87298965,"about_ca_system_score_codex":0.00020477196,"about_ca_system_score_gemma":0.00078938744,"threshold_uncertainty_score":0.88346064},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017741697,0.000153687,0.980753,0.00007641144,0.00037223156,0.00008412961,0.00045488245,0.0002235896,0.00014034957],"genre_scores_gemma":[0.9338047,0.000048795893,0.06574257,0.000013678674,0.00015303153,0.000031232736,0.00012639558,0.000017349366,0.0000622417],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901813,0.000007836794,0.00018360539,0.0004833777,0.00009854178,0.00020852646],"domain_scores_gemma":[0.9989446,0.00008500744,0.000025273775,0.00085375406,0.000015968068,0.00007543514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008104604,0.00014927115,0.00012272604,0.000085922795,0.00014200454,0.0001899458,0.0006378362,0.000044134737,0.000008920797],"category_scores_gemma":[0.000002348714,0.00015277008,0.00002621944,0.00023401238,0.000018329114,0.00075769064,0.00002214874,0.00015324057,0.000033062373],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016345017,0.0009825596,0.00007444298,0.00009596853,0.00020832183,0.000028960529,0.0008142356,0.081900135,0.028141517,0.01764404,0.003848367,0.8662451],"study_design_scores_gemma":[0.00034118982,0.000023228968,0.00033394966,0.000045815377,0.000021774817,0.0000038865983,0.000010910364,0.96266085,0.011925659,0.00008028219,0.024301598,0.00025083145],"about_ca_topic_score_codex":0.00048478117,"about_ca_topic_score_gemma":0.00008797783,"teacher_disagreement_score":0.916063,"about_ca_system_score_codex":0.00002516229,"about_ca_system_score_gemma":0.000025703483,"threshold_uncertainty_score":0.6229783},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026691861,0.000034068362,0.9568461,0.007535289,0.00003192045,0.00010889437,0.0000040022856,0.00024656128,0.00850126],"genre_scores_gemma":[0.2564508,0.000013453878,0.74169695,0.0004215588,0.00001979208,0.00006196508,0.000027149636,0.000006919269,0.0013013792],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992147,0.000017712497,0.00015968652,0.00023812038,0.00018387135,0.00018591182],"domain_scores_gemma":[0.9990307,0.00007062113,0.00013351234,0.0006038248,0.00010823993,0.000053115986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024015053,0.000087793414,0.000092076516,0.000045982062,0.00017167121,0.00022335724,0.0006563236,0.000043049775,0.000009112709],"category_scores_gemma":[0.00003132904,0.00007240437,0.000019772648,0.0003143432,0.000020198302,0.00062330376,0.00017240577,0.00008553734,0.0000902399],"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":[0.00003367193,0.0014471317,0.011442169,0.000067221656,0.00028994083,0.000016749766,0.018754315,0.0027529716,0.0013076795,0.5491295,0.028684925,0.38607374],"study_design_scores_gemma":[0.019408543,0.0019398297,0.07843525,0.0012882997,0.00023267734,0.00030142133,0.008523947,0.566717,0.020295292,0.12761341,0.1698208,0.0054235235],"about_ca_topic_score_codex":0.000092204566,"about_ca_topic_score_gemma":0.000073198265,"teacher_disagreement_score":0.563964,"about_ca_system_score_codex":0.00010610442,"about_ca_system_score_gemma":0.00006771466,"threshold_uncertainty_score":0.29525647},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014361788,0.000065506036,0.98034513,0.002953641,0.00012046023,0.00017717785,0.00012618507,0.00018544086,0.0016646965],"genre_scores_gemma":[0.14970228,0.000001050645,0.84777343,0.0004461805,0.00028745746,0.000027135968,0.00028725632,0.000008992025,0.0014661924],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999159,0.0000065505087,0.0001630583,0.00032185792,0.00015073062,0.00019885095],"domain_scores_gemma":[0.9994251,0.00006236865,0.00005272157,0.00032896918,0.0000561995,0.00007465651],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005026247,0.000102464226,0.000087038585,0.00008559745,0.00016411992,0.0002154494,0.00049648486,0.000045457644,0.00003254126],"category_scores_gemma":[0.0000066367825,0.00009030347,0.000053098844,0.0003632101,0.00002113187,0.00028095482,0.00007087382,0.00004569237,0.000006980833],"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":[0.0000017337019,0.00007335758,0.00064964045,0.0000069064026,0.000019398129,0.0000022018717,0.00009683162,0.00010397182,0.0036751456,0.68963945,0.18302515,0.12270621],"study_design_scores_gemma":[0.003205496,0.0003788952,0.11072934,0.000089374895,0.000062253275,0.00022886481,0.00009384546,0.31451362,0.011029521,0.30581883,0.2523105,0.0015394504],"about_ca_topic_score_codex":0.0002306813,"about_ca_topic_score_gemma":0.000107322885,"teacher_disagreement_score":0.38382065,"about_ca_system_score_codex":0.000014754024,"about_ca_system_score_gemma":0.000071152426,"threshold_uncertainty_score":0.36824685},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5962031,0.0021967886,0.39462125,0.0004706296,0.0007462732,0.0009140683,0.000066707966,0.00024892009,0.004532278],"genre_scores_gemma":[0.9891848,0.0006029189,0.0063049314,0.000044398348,0.00010963895,0.00014358379,0.000017415305,0.000027751394,0.0035645869],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977947,0.00011420021,0.0005151285,0.00070981,0.00049137755,0.00037478126],"domain_scores_gemma":[0.9988234,0.00010621627,0.00016732572,0.000568145,0.00014691078,0.00018801673],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000527283,0.00029675517,0.00033995335,0.00015706137,0.00045876132,0.0006167522,0.00028016497,0.00014521944,0.000010773748],"category_scores_gemma":[0.000003096529,0.0002952386,0.000036726535,0.00028261,0.000194484,0.00031032925,0.000017391074,0.0002613071,0.000047885846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005886028,0.0015363889,0.005969079,0.000496038,0.00023333426,0.000010523563,0.0024498678,0.18688749,0.0015676351,0.03067632,0.013637192,0.7564773],"study_design_scores_gemma":[0.0009118065,0.00023755283,0.006838828,0.00014344654,0.0000992391,0.00006525498,0.0001341946,0.97131646,0.0013675174,0.00019336537,0.018239053,0.00045329373],"about_ca_topic_score_codex":0.0005234644,"about_ca_topic_score_gemma":0.000108403474,"teacher_disagreement_score":0.78442895,"about_ca_system_score_codex":0.000049111237,"about_ca_system_score_gemma":0.000041645337,"threshold_uncertainty_score":0.99995},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6764367,0.00064701,0.31194773,0.0031275053,0.00044346676,0.00055366475,0.00014264572,0.0005036882,0.006197583],"genre_scores_gemma":[0.77753115,0.00040228138,0.21868367,0.0005272128,0.0004311447,0.000063764186,0.00007792207,0.00007281059,0.0022100178],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99549043,0.0003653145,0.00062281307,0.0013512099,0.00057911815,0.0015910974],"domain_scores_gemma":[0.9960016,0.0005801549,0.00048185705,0.0017929358,0.00036064416,0.000782828],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00076524005,0.00063552934,0.0006552436,0.00062408263,0.00091517164,0.0012560152,0.0026219839,0.00045730447,0.0004011715],"category_scores_gemma":[0.00023862111,0.0007321946,0.00029749976,0.0016662063,0.00038425575,0.0020576087,0.0011476557,0.0007734632,0.0011685326],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039683797,0.001093628,0.015850773,0.0002337333,0.00053593976,0.00065584795,0.0058333073,0.00050657446,0.014158514,0.27877262,0.013845472,0.6684739],"study_design_scores_gemma":[0.0019292654,0.00068309746,0.33775833,0.000727854,0.0004676312,0.0004624662,0.0053758696,0.6028169,0.0068676844,0.012952936,0.02774251,0.002215482],"about_ca_topic_score_codex":0.0022972024,"about_ca_topic_score_gemma":0.000032469386,"teacher_disagreement_score":0.6662584,"about_ca_system_score_codex":0.00067515706,"about_ca_system_score_gemma":0.00073602685,"threshold_uncertainty_score":0.9997808},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25737748,0.000017019496,0.73571426,0.0038321442,0.000077315744,0.00017591333,0.000022046148,0.00020437752,0.0025794646],"genre_scores_gemma":[0.85337967,0.0000063032667,0.14611338,0.00015516063,0.000036158315,0.00001857038,0.00002441589,0.000002383412,0.0002639736],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99936366,0.000014725712,0.00011540829,0.00022659203,0.00012249671,0.0001571371],"domain_scores_gemma":[0.9995659,0.000024665302,0.000049831957,0.00029593604,0.00001829859,0.000045368066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013843138,0.000063313804,0.00007696341,0.00006526418,0.000077910736,0.00012905287,0.000377363,0.000027849579,0.000006386278],"category_scores_gemma":[0.000017540855,0.00005417862,0.00001375718,0.00035645918,0.000009337957,0.00039650922,0.00008364053,0.000061031795,0.0000098450755],"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":[0.0000039434467,0.0012884669,0.1750285,0.0000099693425,0.000019322424,0.00005256822,0.005940533,0.0011784751,0.27486488,0.10093256,0.016171388,0.42450938],"study_design_scores_gemma":[0.00036379852,0.00009026981,0.7384616,0.000044576955,0.0000029914845,0.0000015988065,0.0001603419,0.1407888,0.11493348,0.0030717643,0.0016811909,0.00039957053],"about_ca_topic_score_codex":0.00020606346,"about_ca_topic_score_gemma":0.00009776616,"teacher_disagreement_score":0.59600216,"about_ca_system_score_codex":0.000031459906,"about_ca_system_score_gemma":0.000018879884,"threshold_uncertainty_score":0.220934},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2888933,0.000007567612,0.69944125,0.001672116,0.000075767915,0.000118684686,0.000018724155,0.00035303124,0.009419543],"genre_scores_gemma":[0.48149335,0.000013693708,0.5038632,0.002890063,0.00036112015,0.000060682007,0.00002447626,0.000017282931,0.011276111],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992464,0.000012106355,0.00015454734,0.000270562,0.000121347446,0.00019502403],"domain_scores_gemma":[0.99927825,0.000060684615,0.000020849215,0.0005026941,0.000031283053,0.00010626316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012603428,0.00007746065,0.00007335717,0.000035550984,0.00015607009,0.00018553888,0.00066943286,0.000022473909,0.00018265391],"category_scores_gemma":[0.000013929027,0.000067798595,0.000018716797,0.0002776563,0.0000072255675,0.00028940514,0.00017666821,0.00007050836,0.00026951253],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.721964e-7,0.000042976295,0.010798384,0.000005989328,0.000006056134,0.0000032788098,0.0007586335,0.00039091508,0.0000501894,0.0033555047,0.0058924244,0.978695],"study_design_scores_gemma":[0.00030169616,0.000076837874,0.028771127,0.00009140566,0.0000082834595,0.000022945767,0.00023394899,0.67233396,0.0007346661,0.00015460489,0.2969047,0.00036579676],"about_ca_topic_score_codex":0.00032720494,"about_ca_topic_score_gemma":0.00006487687,"teacher_disagreement_score":0.9783292,"about_ca_system_score_codex":0.000010007214,"about_ca_system_score_gemma":0.000013985842,"threshold_uncertainty_score":0.34641284},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025703307,0.000023152708,0.9703268,0.00024409157,0.000035050867,0.00024728675,0.00002797396,0.000094913754,0.0032974218],"genre_scores_gemma":[0.16142023,0.0000022045035,0.83794,0.00011842851,0.000058078567,0.00006291697,0.000041075455,0.0000071224385,0.00034996928],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891984,0.000006017761,0.00020791052,0.00036547278,0.00015750923,0.00034326123],"domain_scores_gemma":[0.9992927,0.00012328911,0.00002619149,0.00041983635,0.000042151398,0.00009587195],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082415657,0.000094088515,0.00010515103,0.00014744274,0.00006215917,0.00009058385,0.00055996474,0.00004244695,0.000004688248],"category_scores_gemma":[0.000024165745,0.000084551284,0.000032702166,0.00046039588,0.000021164482,0.000233409,0.000143187,0.00008542674,0.000005570413],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006661128,0.0007903019,0.00050008105,0.000030562198,0.00001562622,0.0000060773436,0.0011760845,0.0007978242,0.010628817,0.074228704,0.001574206,0.91024506],"study_design_scores_gemma":[0.00052809756,0.00003775519,0.0006000501,0.000009604204,0.0000017086352,0.000009968875,0.00037794537,0.9939983,0.0022882526,0.0000540496,0.0019523421,0.00014192003],"about_ca_topic_score_codex":0.0001594635,"about_ca_topic_score_gemma":0.000084910476,"teacher_disagreement_score":0.9932005,"about_ca_system_score_codex":0.00004458495,"about_ca_system_score_gemma":0.000075272066,"threshold_uncertainty_score":0.34479013},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000057286616,0.3728141,0.6255513,0.000015589001,0.0008115123,0.00037990327,0.000107308406,0.00015871131,0.00015587521],"genre_scores_gemma":[0.000033147324,0.4229795,0.57572323,0.000026851392,0.0006203607,0.00009251416,0.0003684454,0.000067014655,0.00008893301],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962771,0.000736769,0.0011000142,0.0010015105,0.0003713996,0.0005132255],"domain_scores_gemma":[0.99437636,0.0013325501,0.0010883808,0.002891943,0.00016385315,0.00014690177],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003191373,0.0005059811,0.0015155792,0.00027693008,0.0001974817,0.0002758596,0.005267059,0.00034682464,0.000012338198],"category_scores_gemma":[0.00028869923,0.0004682482,0.00042836726,0.00087072205,0.00010995759,0.00020517358,0.0028764633,0.0007144632,0.000082934],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.112144e-8,0.00004207279,0.000018565941,0.0007663678,0.000055767705,0.0000074718296,0.000055023756,0.0000012947797,2.936022e-7,0.00009756508,0.00041924033,0.9985363],"study_design_scores_gemma":[0.00011821621,0.000034377237,0.000050777224,0.0027634536,0.00009592209,0.00007796565,0.0000049664777,0.0136466315,0.0000033249132,0.00003346361,0.9826189,0.00055197056],"about_ca_topic_score_codex":0.00022720381,"about_ca_topic_score_gemma":0.000015669417,"teacher_disagreement_score":0.99798435,"about_ca_system_score_codex":0.0000433679,"about_ca_system_score_gemma":0.00041487382,"threshold_uncertainty_score":0.9997769},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46234706,0.0000017357355,0.53182405,0.0004822936,0.000063669075,0.000080112135,0.0000029746138,0.000016142323,0.0051819338],"genre_scores_gemma":[0.784769,9.2202106e-7,0.21515456,0.000020580474,0.0000027598346,0.0000064506307,5.2958956e-7,7.1964297e-7,0.000044446057],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997182,0.0000097962065,0.00011156562,0.00006270415,0.000062138985,0.00003560438],"domain_scores_gemma":[0.9995805,0.000048163678,0.00004721547,0.00029579693,0.0000205957,0.000007729706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015619506,0.000022011352,0.000048489223,0.000016804977,0.000012009867,0.000009147612,0.00033910392,0.000014798685,0.000010912261],"category_scores_gemma":[0.000027681222,0.000013545547,0.000019277688,0.00021793942,0.00003260485,0.00010715966,0.00006671339,0.000043835582,0.0000027318206],"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":[0.0000024135393,0.00011377905,0.009087228,0.000008993856,0.000003778749,8.653736e-8,0.00054936577,0.00008075745,0.003899836,0.74371696,0.00056786917,0.24196891],"study_design_scores_gemma":[0.0009881776,0.0000132656905,0.1038329,0.00003223993,0.0000044401318,0.0000073283104,0.000027937891,0.75760615,0.067023575,0.069576934,0.0007801818,0.00010687888],"about_ca_topic_score_codex":0.00019107162,"about_ca_topic_score_gemma":0.00005149506,"teacher_disagreement_score":0.7575254,"about_ca_system_score_codex":9.236408e-7,"about_ca_system_score_gemma":0.000019164356,"threshold_uncertainty_score":0.06301451},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0057215444,0.0053464784,0.98201245,0.00039345253,0.0012616318,0.0006378395,0.000018137747,0.00053961494,0.0040688473],"genre_scores_gemma":[0.4526298,0.00029578508,0.54478663,0.00043946411,0.0008037572,0.000026654523,0.000024171526,0.00011933164,0.00087440974],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976394,0.000024798574,0.0006020505,0.0009452434,0.0003165696,0.0004718979],"domain_scores_gemma":[0.99862355,0.00024806018,0.0003384709,0.0005691259,0.00013500125,0.00008579593],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003685013,0.00051442895,0.0006789834,0.00026789884,0.00056575687,0.00023416986,0.00066300645,0.00013720404,0.000003529755],"category_scores_gemma":[0.000035417273,0.00049590616,0.00008577981,0.00015260135,0.00015561529,0.00010443219,0.0015642003,0.0004381567,0.000005433166],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029576357,0.00022864837,0.00015899606,0.0047766706,0.0010928414,0.0004011921,0.032081492,0.13834749,0.0006507735,0.14109431,0.00019692385,0.6809411],"study_design_scores_gemma":[0.004295698,0.00029913688,0.00030210207,0.01690727,0.00029330936,0.000118215736,0.0013230251,0.87452936,0.00078262115,0.08930733,0.0070547666,0.004787146],"about_ca_topic_score_codex":0.000037221278,"about_ca_topic_score_gemma":0.00003327158,"teacher_disagreement_score":0.7361819,"about_ca_system_score_codex":0.00027325933,"about_ca_system_score_gemma":0.00014144782,"threshold_uncertainty_score":0.99974924},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00043802476,0.000053814376,0.9918854,0.004731921,0.000080062,0.00013111686,0.000006101865,0.00017959854,0.002493958],"genre_scores_gemma":[0.10130007,0.0000134414895,0.8946334,0.0006693348,0.00017655714,0.000052576383,0.000010402881,0.0000052857713,0.0031389056],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992766,0.0000083187615,0.00011191723,0.00027952148,0.0001523862,0.0001712821],"domain_scores_gemma":[0.99935895,0.00006399182,0.000026539608,0.00036877097,0.0000628527,0.00011891109],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011646827,0.000070757495,0.00008675151,0.000025946507,0.00021395364,0.000068028006,0.0006646871,0.000036735342,0.000013064369],"category_scores_gemma":[0.000041576637,0.000056335684,0.00004156153,0.00023918897,0.00003454778,0.00030951557,0.00008606724,0.00005511863,0.00004389781],"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":[0.0000026535595,0.0001150516,0.0003868287,0.0000062361405,0.000018585639,0.000010137308,0.0007268786,0.00002598037,0.0002830171,0.46573088,0.31511557,0.21757819],"study_design_scores_gemma":[0.000993089,0.00025569243,0.0037956203,0.000010280738,0.00001649421,0.00029468432,0.0000690674,0.36361906,0.003717922,0.09546191,0.5310517,0.00071449496],"about_ca_topic_score_codex":0.00026511733,"about_ca_topic_score_gemma":0.000026693939,"teacher_disagreement_score":0.37026897,"about_ca_system_score_codex":0.00001672595,"about_ca_system_score_gemma":0.00020578178,"threshold_uncertainty_score":0.22973025},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.057925515,0.0000032766145,0.92044467,0.0033261809,0.00009775946,0.00006094814,0.000011541799,0.00018747798,0.017942648],"genre_scores_gemma":[0.4766617,9.1572934e-7,0.51074886,0.000670619,0.00010058843,0.00004673691,0.000012562766,0.0000060339075,0.011751967],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99941504,0.000008881511,0.00008177304,0.0002317566,0.00011232555,0.0001502191],"domain_scores_gemma":[0.99940276,0.00004651513,0.000019246603,0.0004521427,0.00001986417,0.000059482456],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000083745894,0.000056601904,0.00004815296,0.00007420441,0.0001229997,0.00018119196,0.00046053436,0.00001857843,0.000044232434],"category_scores_gemma":[0.000005680951,0.00005104038,0.000019449146,0.00026620275,0.0000058694295,0.00026129116,0.00015894411,0.000035106717,0.00019953738],"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":[0.00000206211,0.00016589528,0.007734013,0.0000044264543,0.000010084471,0.0000117441305,0.0006500101,0.00019006318,0.0030925611,0.2763494,0.19486922,0.5169205],"study_design_scores_gemma":[0.00021549147,0.00006438355,0.13152917,0.000021766822,0.000005206486,0.00002977937,0.0003071327,0.041259497,0.011587574,0.0013826479,0.8131937,0.00040368596],"about_ca_topic_score_codex":0.00030202387,"about_ca_topic_score_gemma":0.00012103845,"teacher_disagreement_score":0.61832446,"about_ca_system_score_codex":0.000014830326,"about_ca_system_score_gemma":0.000015258168,"threshold_uncertainty_score":0.25647157},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01539448,0.00010066815,0.98171115,0.0001643064,0.0005305423,0.0003058216,0.0011047663,0.00012402049,0.0005642615],"genre_scores_gemma":[0.7912593,0.000010543888,0.2084568,0.000025509764,0.000005340512,0.000087211636,0.00005373254,0.000010640742,0.00009091013],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851036,0.00010243975,0.00040005497,0.00043867884,0.0003018392,0.00024664417],"domain_scores_gemma":[0.9976213,0.00022503351,0.00013662426,0.0018293519,0.00007089886,0.000116813],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043222588,0.00015841583,0.00020866506,0.00017140503,0.00018475046,0.000068802925,0.00079398433,0.0000469855,0.000022887167],"category_scores_gemma":[0.00005486202,0.0001510834,0.00006799591,0.00051644625,0.00007300417,0.00012208584,0.000015603966,0.00012565145,0.00004884077],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041832005,0.0057409666,0.00012103153,0.0011016758,0.000890603,0.0001555559,0.0052094436,0.23856023,0.06855043,0.30965224,0.003375816,0.3666002],"study_design_scores_gemma":[0.0009237067,0.00014609184,0.000053018826,0.00033853122,0.00004754161,0.00018886467,0.00095314044,0.9841938,0.0050246506,0.0000798514,0.0076071597,0.0004436333],"about_ca_topic_score_codex":0.00010340165,"about_ca_topic_score_gemma":0.000010891232,"teacher_disagreement_score":0.77586484,"about_ca_system_score_codex":0.000052921856,"about_ca_system_score_gemma":0.00011409091,"threshold_uncertainty_score":0.61610025},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17063576,0.0000147971505,0.8286519,0.0000997132,0.00009706009,0.0001982623,0.000012274164,0.00005112838,0.00023909583],"genre_scores_gemma":[0.5375561,0.0000024091237,0.46229404,0.0000285858,0.000047811827,0.000025227591,0.00002890321,0.0000029048908,0.000013997327],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991319,0.000012670229,0.00021744039,0.00020338024,0.00024024879,0.00019432578],"domain_scores_gemma":[0.99891466,0.00028558786,0.00010580207,0.00037422922,0.00027436184,0.000045343986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001428519,0.00006686594,0.00009369146,0.000037109236,0.00009531111,0.000036381392,0.00034905743,0.000056765773,0.0000058669702],"category_scores_gemma":[0.000071020695,0.000060464306,0.000029809404,0.000374951,0.000023477427,0.00017743149,0.00006547938,0.000051474723,0.0000019710742],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005264073,0.000048326885,0.0009712893,0.000007937479,0.000011824953,1.1338089e-7,0.00018363018,0.0035426724,0.00007771915,0.035673797,0.00045542794,0.959022],"study_design_scores_gemma":[0.0001758398,0.000036358077,0.008163177,0.0000276973,0.000011855383,0.000001593535,0.00007586287,0.98953307,0.0011608267,0.0003764184,0.00035863664,0.000078638506],"about_ca_topic_score_codex":0.000004962156,"about_ca_topic_score_gemma":0.0000027008084,"teacher_disagreement_score":0.9859904,"about_ca_system_score_codex":0.000024921557,"about_ca_system_score_gemma":0.0000375977,"threshold_uncertainty_score":0.24656628},"labels":[],"label_agreement":null},{"id":"W2151207331","doi":"10.1007/s10115-008-0127-5","title":"Multirelational classification: a multiple view approach","year":2008,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Shanghai Jiao Tong University","keywords":"Computer science; Relational database; Construct (python library); Table (database); Set (abstract data type); Feature (linguistics); Data mining; Relevance (law); Artificial intelligence; Information retrieval","score_opus":0.04522474571286368,"score_gpt":0.24907032545918464,"score_spread":0.20384557974632095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151207331","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013565423,0.0008014348,0.93666154,0.000112495836,0.00023203956,0.00031867807,0.000021331822,0.00018194297,0.060314003],"genre_scores_gemma":[0.9511789,0.0001946861,0.047235306,0.00008643423,0.0001323371,0.00026021423,0.00021580585,0.000004674702,0.0006916388],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992182,0.000028755334,0.00034620802,0.00014236815,0.00014863712,0.00011582297],"domain_scores_gemma":[0.99924815,0.00006123335,0.00012228802,0.00031012014,0.00017836827,0.00007983527],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020756439,0.000090719186,0.00011247254,0.00010443522,0.00033860776,0.00015764973,0.0002717509,0.000054660923,0.0000017727058],"category_scores_gemma":[0.000027595803,0.00007946236,0.00002379653,0.00032720403,0.00004205008,0.003237837,0.00008389833,0.000069860274,0.00040314248],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003118379,0.00018516881,0.0038756111,0.00022030421,0.00003416803,5.3602366e-7,0.013790975,0.0001797678,0.000038428883,0.7252459,0.031792577,0.22463346],"study_design_scores_gemma":[0.00019377035,0.0000073939,0.009855788,0.000010306859,0.0000012207142,0.00006260054,0.00010032299,0.607186,0.0000037165005,0.0000084923295,0.38249245,0.00007789089],"about_ca_topic_score_codex":0.000012466775,"about_ca_topic_score_gemma":3.1741348e-7,"teacher_disagreement_score":0.94982237,"about_ca_system_score_codex":0.000023688915,"about_ca_system_score_gemma":0.00006290674,"threshold_uncertainty_score":0.51817155},"labels":[],"label_agreement":null},{"id":"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21705072,0.000073128555,0.77890146,0.0007109182,0.00011352749,0.00024954247,0.0015313651,0.00020579498,0.001163519],"genre_scores_gemma":[0.829856,0.000026592335,0.16891429,0.000021612668,0.00024584515,0.00027171473,0.00060866185,0.000013766486,0.000041535433],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99881667,0.0000020043453,0.00033742847,0.00043137002,0.00024488958,0.0001676576],"domain_scores_gemma":[0.9993156,0.00007622457,0.00014295134,0.0002412748,0.00014993087,0.000073969306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011559076,0.00015605058,0.0001360122,0.0001472976,0.00007674573,0.00014547177,0.0005988026,0.000038135746,0.0000087788285],"category_scores_gemma":[0.000013756249,0.00016326834,0.000035886358,0.00019615714,0.00003879002,0.00019597754,0.00023896163,0.00008873544,0.000005507684],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004289617,0.00044123316,0.003540302,0.000104209954,0.00010283946,0.0000022099441,0.00030609136,0.0072085345,0.24848635,0.72680557,0.001008135,0.011990259],"study_design_scores_gemma":[0.00033114257,0.000015192703,0.001652851,0.000115002156,0.000021113656,0.000016914235,0.00007281366,0.9742987,0.013400925,0.00028193794,0.009540021,0.00025335542],"about_ca_topic_score_codex":0.00026855385,"about_ca_topic_score_gemma":0.0000015364286,"teacher_disagreement_score":0.9670902,"about_ca_system_score_codex":0.00003459993,"about_ca_system_score_gemma":0.000019819781,"threshold_uncertainty_score":0.665789},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001680434,0.00037454136,0.9963653,0.000120376586,0.00036585686,0.00017036188,0.00068258034,0.0001945859,0.000045965302],"genre_scores_gemma":[0.113305464,0.000077640856,0.8859453,0.000038752416,0.0002993993,0.00007474193,0.00008503442,0.00002955934,0.00014406312],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99887556,0.000007874056,0.00023049324,0.0005226892,0.000092846494,0.00027051504],"domain_scores_gemma":[0.99880457,0.00013908636,0.000035479443,0.00085615873,0.0000432712,0.00012141129],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019418773,0.00017738853,0.00015783079,0.0001621162,0.00023775583,0.00017684295,0.0007163907,0.000057334855,0.0000045271636],"category_scores_gemma":[0.0000057078573,0.00018363188,0.000037947695,0.00026580834,0.000019417168,0.00093230326,0.000021108925,0.000119306635,0.00001428661],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000229816,0.00015324554,0.0000022708077,0.000037940168,0.00005037117,0.0000012349291,0.0005487343,0.032777097,0.0026304203,0.00047592132,0.0008216894,0.9624988],"study_design_scores_gemma":[0.0002649273,0.00003324448,0.00001543196,0.000058726837,0.000023687266,0.000020602605,0.000029523873,0.9620176,0.003079309,0.0000067978613,0.03423934,0.00021078663],"about_ca_topic_score_codex":0.000015379796,"about_ca_topic_score_gemma":0.000033065317,"teacher_disagreement_score":0.96228796,"about_ca_system_score_codex":0.000041748186,"about_ca_system_score_gemma":0.000038670823,"threshold_uncertainty_score":0.7488291},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55213493,0.000015422247,0.44280213,0.0019264476,0.000101386955,0.00024144798,0.000032020325,0.000067716464,0.0026784989],"genre_scores_gemma":[0.93406767,0.0000086779055,0.06533173,0.00012481234,0.000011282824,0.000015678503,0.000010750588,0.000005366682,0.0004240225],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9992057,0.000015758522,0.00031895723,0.0002211945,0.00011359249,0.00012480664],"domain_scores_gemma":[0.99917734,0.000114536815,0.00014174292,0.0003912101,0.00009994316,0.00007524825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010711544,0.00008000352,0.00016717637,0.000058840003,0.000038059738,0.00006131354,0.00036604187,0.000033728058,0.000021070418],"category_scores_gemma":[0.000040375468,0.000067096356,0.000020907532,0.00021895645,0.000048250047,0.00032703142,0.00029390657,0.000053134605,0.000017463439],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027010785,0.00015864741,0.016613133,0.00016106514,0.000050726234,0.0000028710876,0.0014118019,0.0000031937573,0.007152614,0.012577214,0.011462598,0.95040345],"study_design_scores_gemma":[0.00036113037,0.000264654,0.89606035,0.00025622846,0.000022343358,0.000027060198,0.00030801664,0.096361786,0.0022172132,0.002321559,0.0014205223,0.00037915545],"about_ca_topic_score_codex":0.00030366328,"about_ca_topic_score_gemma":0.0000090472895,"teacher_disagreement_score":0.9500243,"about_ca_system_score_codex":0.000007860822,"about_ca_system_score_gemma":0.000017092685,"threshold_uncertainty_score":0.273611},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033452865,0.000024028115,0.95770997,0.0018406896,0.000046065295,0.00015301464,0.0000124654525,0.00020806231,0.00655285],"genre_scores_gemma":[0.503684,0.0000021897108,0.49507755,0.00021080306,0.00029733707,0.00016032523,0.000016263948,0.000010485233,0.00054106105],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99945205,6.527491e-7,0.00008439794,0.00020672848,0.00009061487,0.00016552796],"domain_scores_gemma":[0.9997737,0.000021764887,0.000032146385,0.00008093445,0.00006352107,0.000027968339],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013072173,0.000052567906,0.000050047198,0.00003655882,0.00013145033,0.00026481337,0.00043767632,0.000016053988,0.0000014250418],"category_scores_gemma":[0.000011544433,0.00004858036,0.000022935932,0.000099773235,0.000012703869,0.0003377482,0.000103321,0.00004039324,0.000030629773],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.146737e-7,0.000033992823,0.0007339985,0.00002541252,0.000002718122,2.1141965e-7,0.00021433135,0.0000011246296,0.002317792,0.38041073,0.012672537,0.60358673],"study_design_scores_gemma":[0.0005209909,0.00008837879,0.011523018,0.000053089687,0.000008780034,0.000022227632,0.00007604734,0.44972432,0.014228837,0.15793182,0.36537865,0.00044386744],"about_ca_topic_score_codex":0.00006329995,"about_ca_topic_score_gemma":0.0000011687453,"teacher_disagreement_score":0.60314286,"about_ca_system_score_codex":0.000009810788,"about_ca_system_score_gemma":0.00000965492,"threshold_uncertainty_score":0.25536016},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00032812243,0.00051067927,0.9973763,0.00020803389,0.00084005523,0.0004284422,0.000121501,0.00007961895,0.0001072253],"genre_scores_gemma":[0.01732436,0.000015938242,0.98189145,0.00023189986,0.00035955763,0.000009878456,0.00011285928,0.000024143037,0.00002990615],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963956,0.0000381655,0.00058476423,0.0015980698,0.0008288447,0.0005545488],"domain_scores_gemma":[0.99432003,0.0004146443,0.00048213216,0.0044184737,0.00022264887,0.00014205514],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0011312319,0.00039351522,0.000395754,0.00027117014,0.00039710934,0.0005814163,0.00940549,0.00016281521,0.000013735787],"category_scores_gemma":[0.0001080123,0.00028795243,0.000058666737,0.0009566916,0.0007021741,0.0010402813,0.0044841436,0.0004680099,0.000010168086],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.074712e-7,0.000045841083,0.000009077717,0.000018755902,0.000007151658,0.0000040714876,0.00044854436,0.029554754,0.00010830114,0.0008834482,0.000037059384,0.9688821],"study_design_scores_gemma":[0.00009871529,0.000067893154,0.00006821056,0.00022466946,0.000015187696,0.000020516905,0.0000010264906,0.99664104,0.00023553355,0.0019475089,0.00034411307,0.00033561446],"about_ca_topic_score_codex":0.00011547983,"about_ca_topic_score_gemma":0.000018823923,"teacher_disagreement_score":0.96854645,"about_ca_system_score_codex":0.00014113063,"about_ca_system_score_gemma":0.00051987753,"threshold_uncertainty_score":0.99995726},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010920343,0.0001620767,0.9967847,0.00027914468,0.00015846433,0.0008853627,0.00001675513,0.000076603836,0.0005448836],"genre_scores_gemma":[0.20611666,0.0000074329705,0.79352474,0.00014662003,0.00011420344,0.000047551213,0.000015119838,0.000016281258,0.0000113687765],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99752223,0.00001598287,0.00055031024,0.0010035913,0.000592875,0.00031498555],"domain_scores_gemma":[0.99839526,0.00024448018,0.0002993655,0.000736859,0.00018963682,0.00013440997],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009859793,0.0002821317,0.0003126203,0.0006565006,0.00017268045,0.00021806442,0.0010729725,0.0001756223,0.0000019810739],"category_scores_gemma":[0.00005100776,0.00028283973,0.000042369906,0.0007609495,0.0001959402,0.00048383305,0.00026426863,0.00024211148,0.000003671127],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026674506,0.000014294685,0.0000123044665,0.00003588416,0.000003896808,0.0000027186288,0.0023271588,0.0029950994,0.0065142266,0.03178366,9.3372745e-7,0.9563072],"study_design_scores_gemma":[0.00026325803,0.00022846238,0.00028848997,0.0006471448,0.000011042951,0.000021789938,0.0000030187803,0.9394461,0.016759308,0.041091036,0.0006414617,0.0005988777],"about_ca_topic_score_codex":0.00006632753,"about_ca_topic_score_gemma":0.00009633382,"teacher_disagreement_score":0.95570827,"about_ca_system_score_codex":0.00013469624,"about_ca_system_score_gemma":0.000231389,"threshold_uncertainty_score":0.9999624},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.103288084,0.000038812068,0.89434016,0.0002690692,0.000019694446,0.00031015996,0.00003459996,0.00013325432,0.0015661693],"genre_scores_gemma":[0.7195113,0.0000013239242,0.27974027,0.00012413479,0.000059994072,0.00017957285,0.00007994542,0.0000055949213,0.0002978585],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906296,0.000017530738,0.00013081155,0.0005240351,0.00011282579,0.0001518193],"domain_scores_gemma":[0.9991691,0.000042592925,0.000036689486,0.0006278474,0.00006327389,0.000060475977],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001854799,0.000085021136,0.000083471175,0.000055794662,0.00017478083,0.00024368207,0.00063015404,0.000030487814,0.000001177091],"category_scores_gemma":[0.000017046685,0.00007820428,0.00000599354,0.0004770606,0.0000141693545,0.00061228056,0.00046493785,0.000044630364,0.000029052557],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028655559,0.00023540655,0.0014462167,0.000021152495,0.00002294614,4.8128516e-7,0.00066606875,0.00035809362,0.043519787,0.047697604,0.0046638525,0.9013655],"study_design_scores_gemma":[0.0001040692,0.00004270183,0.0064289244,0.0000038667863,0.000004626571,0.000002042503,0.00003792761,0.9803272,0.007171483,0.0000772488,0.0056605046,0.0001393938],"about_ca_topic_score_codex":0.00011013545,"about_ca_topic_score_gemma":0.000037292943,"teacher_disagreement_score":0.97996914,"about_ca_system_score_codex":0.000011777558,"about_ca_system_score_gemma":0.000014857183,"threshold_uncertainty_score":0.31890777},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8694665,0.00039073982,0.123744875,0.00020672158,0.00016480667,0.00014422633,0.0017407855,0.00010070209,0.004040689],"genre_scores_gemma":[0.935253,0.000042784424,0.06318785,0.00006154334,0.0001292234,0.000007350239,0.0009886516,0.000010698565,0.00031888654],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861914,0.000036182606,0.0002735557,0.0006248115,0.00018429542,0.00026203273],"domain_scores_gemma":[0.9985238,0.00007343256,0.0001332224,0.0011404972,0.00003878451,0.00009030318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027387575,0.00018387428,0.0002298507,0.0001093448,0.00014858629,0.00031577892,0.0012297815,0.000043772718,0.000004199612],"category_scores_gemma":[0.000020349586,0.00015435244,0.000024707802,0.00027689352,0.000081597434,0.0017388839,0.00077287946,0.00007971603,0.0000046102377],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000291901,0.00043236584,0.0089327255,0.000056393015,0.00008113572,0.000022908755,0.0040574404,0.0000029017367,0.0034282077,0.0028663203,0.0073604225,0.97273],"study_design_scores_gemma":[0.009974956,0.003847947,0.12626189,0.003212299,0.00052259397,0.0005780154,0.019054487,0.79071313,0.013947664,0.00026262293,0.027688382,0.0039359764],"about_ca_topic_score_codex":0.00004097932,"about_ca_topic_score_gemma":0.00018500937,"teacher_disagreement_score":0.968794,"about_ca_system_score_codex":0.000014884667,"about_ca_system_score_gemma":0.00014111797,"threshold_uncertainty_score":0.629431},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00045439843,0.000014917346,0.94254464,0.0004310992,0.000050948125,0.000025597548,6.9613367e-7,0.0001308172,0.056346882],"genre_scores_gemma":[0.06166402,0.0000036925605,0.9314751,0.00048116365,0.000009260409,0.0000106474145,0.0000018030676,0.000002482702,0.0063518467],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.999701,0.000007906298,0.000049076643,0.00011423628,0.000051962477,0.000075789416],"domain_scores_gemma":[0.999625,0.000012816732,0.000009475416,0.00030480162,0.0000134113625,0.000034469023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000065054264,0.000028504526,0.00002760857,0.000018039764,0.00004191108,0.000059894603,0.00027494103,0.000010709556,0.000059736307],"category_scores_gemma":[0.000012178286,0.000023568791,0.000010091965,0.00019875965,0.0000068578042,0.00014751202,0.000034858316,0.000022161168,0.0004066125],"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":[1.7157355e-8,0.000011066157,0.000040471536,3.269954e-7,0.0000011128782,4.3848036e-7,0.000020462967,9.583989e-7,0.00010423181,0.9607033,0.013904072,0.025213543],"study_design_scores_gemma":[0.0001813549,0.000018348997,0.0005947713,0.0000021304459,0.0000017174694,0.000022259266,0.000024567586,0.17221712,0.004694067,0.023768982,0.79831207,0.00016261944],"about_ca_topic_score_codex":0.000010892217,"about_ca_topic_score_gemma":0.0000012338754,"teacher_disagreement_score":0.9369343,"about_ca_system_score_codex":0.0000040007008,"about_ca_system_score_gemma":0.00001704219,"threshold_uncertainty_score":0.52263165},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007922745,0.000008413136,0.9899111,0.0003571112,0.00046028954,0.00014665395,0.000016817186,0.00025043136,0.000926486],"genre_scores_gemma":[0.42288473,0.0000014954726,0.5766341,0.00009594485,0.00008450899,0.00008431534,0.000014999868,0.0000049481814,0.0001949147],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99949104,0.0000040870505,0.000105593535,0.00022053771,0.000063262094,0.000115462484],"domain_scores_gemma":[0.9991377,0.000050628092,0.000029065746,0.00060212624,0.00011494396,0.00006555197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012703706,0.000057539204,0.00006294176,0.000029932124,0.00009928135,0.00019276177,0.0006274159,0.000027061864,0.000013031562],"category_scores_gemma":[0.000014183279,0.000045198274,0.000017397171,0.00013706948,0.000023069293,0.00027993537,0.00005966094,0.00004262933,0.000077033015],"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":[6.2441603e-7,0.000059722897,0.00008383882,0.000018514682,0.000005169998,4.7892973e-7,0.00006902166,0.000003724884,0.0059438697,0.7378806,0.0030765266,0.25285795],"study_design_scores_gemma":[0.00023194733,0.00006613683,0.00093011593,0.000015925543,0.000011297417,0.000048406968,0.00020731815,0.55289805,0.06134511,0.0016110588,0.3822959,0.00033874105],"about_ca_topic_score_codex":0.000049974646,"about_ca_topic_score_gemma":0.000026874266,"teacher_disagreement_score":0.73626953,"about_ca_system_score_codex":0.0000048641305,"about_ca_system_score_gemma":0.00003448116,"threshold_uncertainty_score":0.18588063},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008944063,0.00005692943,0.98871535,0.000018240386,0.00012772532,0.00033379992,0.000074016665,0.00007558311,0.0016542756],"genre_scores_gemma":[0.9935064,0.000058899033,0.005806738,0.000055649023,0.000010438721,0.00009602905,0.00031543625,0.0000065895256,0.0001438273],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990084,0.00006289549,0.0004963425,0.00013664401,0.00017841086,0.000117297226],"domain_scores_gemma":[0.998993,0.00005850309,0.0003339893,0.00019331658,0.00037481374,0.000046396817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027281724,0.00010414576,0.00011777475,0.00025349626,0.0001429519,0.00043276694,0.00016645298,0.000043190314,0.0000028710278],"category_scores_gemma":[0.00011766539,0.00010562061,0.000021296222,0.0005651437,0.000016756785,0.010258492,0.00006666258,0.000035002668,0.000013338946],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012755684,0.000042113643,0.000056737113,0.000052314306,0.000009900734,1.557865e-8,0.0038783664,0.0036196962,0.00034661253,0.98998505,0.00022010812,0.0017878264],"study_design_scores_gemma":[0.00028720286,0.00003228602,0.00012434463,0.0000334682,0.000009324148,0.0000036594029,0.00064725877,0.9925098,0.003249236,0.0008158786,0.0021706694,0.0001169035],"about_ca_topic_score_codex":0.000011900926,"about_ca_topic_score_gemma":0.000002309398,"teacher_disagreement_score":0.9891692,"about_ca_system_score_codex":0.00004658428,"about_ca_system_score_gemma":0.00010114224,"threshold_uncertainty_score":0.74371594},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020672448,0.00009545448,0.82259226,0.13858964,0.00034010463,0.00038630702,0.000038343984,0.0009320123,0.016353447],"genre_scores_gemma":[0.081570975,0.00012345429,0.87214375,0.03206619,0.00096174935,0.00068886107,0.0002196891,0.000049272843,0.0121760545],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987972,0.00005004189,0.00024171188,0.00042970644,0.0002060006,0.0002753455],"domain_scores_gemma":[0.9978099,0.00012120652,0.000040682175,0.0018821927,0.000046974525,0.00009907814],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00015130418,0.00014320103,0.00011395154,0.00008192117,0.00030136656,0.00035898862,0.0015989078,0.000051002928,0.00079273776],"category_scores_gemma":[0.000050093615,0.00013657629,0.000056505734,0.00055890385,0.000047917056,0.0014652649,0.0001981412,0.00013854212,0.0062517216],"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":[0.0000021323817,0.00011403855,0.000061026483,0.0000024848491,0.000017508575,0.0000101396045,0.00095877325,0.00013592902,0.0012393966,0.017907085,0.55157423,0.42797726],"study_design_scores_gemma":[0.0002414497,0.000035628676,0.00067815115,0.000008945807,0.000008039963,0.000016906213,0.000029657886,0.0136871245,0.0012336615,0.0068723806,0.9768925,0.0002955806],"about_ca_topic_score_codex":0.000023702003,"about_ca_topic_score_gemma":0.000008108878,"teacher_disagreement_score":0.42768168,"about_ca_system_score_codex":0.000022167522,"about_ca_system_score_gemma":0.00003870443,"threshold_uncertainty_score":0.99452204},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0803107,0.0000026436576,0.90214705,0.0014457476,0.00001897755,0.0003160257,0.000004810856,0.0004494165,0.015304633],"genre_scores_gemma":[0.51108605,7.0906276e-7,0.48403177,0.00025191167,0.00004738399,0.00018958455,0.000010041197,0.000013410772,0.004369129],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986514,0.0000047795443,0.00019254899,0.00060698565,0.00024636058,0.00029795984],"domain_scores_gemma":[0.9993822,0.0000171147,0.00007158132,0.00022654593,0.00016030933,0.00014228009],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028161527,0.00012923454,0.0001145774,0.00015490924,0.00021226244,0.000733272,0.00068404805,0.00003750128,0.0000010715928],"category_scores_gemma":[0.00008028927,0.00013104695,0.000030270161,0.0008716015,0.000013844114,0.0008112461,0.00026907073,0.0001499425,0.00011825259],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011154505,0.00029634175,0.0016315765,0.000033893888,0.000009103836,5.582519e-7,0.005778578,0.024433656,0.047298424,0.827825,0.014303473,0.078378215],"study_design_scores_gemma":[0.000119251155,0.000037920476,0.0017127873,0.000009721851,0.0000033147094,0.0000031364382,0.0001438112,0.9638943,0.000724057,0.00074786664,0.032414295,0.00018956108],"about_ca_topic_score_codex":0.00014918778,"about_ca_topic_score_gemma":0.0000019941392,"teacher_disagreement_score":0.93946064,"about_ca_system_score_codex":0.000053199805,"about_ca_system_score_gemma":0.00003182276,"threshold_uncertainty_score":0.70709586},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2405016,0.000046344532,0.7553432,0.00017525862,0.0002135303,0.00007398323,0.000045417986,0.000059110513,0.0035415776],"genre_scores_gemma":[0.9264166,0.000006570171,0.07272169,0.000059859984,0.0000961614,0.000013082208,0.00003883131,0.0000027429023,0.00064446445],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994182,0.000023054043,0.0001374225,0.0001605999,0.00011924532,0.0001414806],"domain_scores_gemma":[0.999355,0.000022212844,0.000056118206,0.00048851396,0.000028712484,0.00004941153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022251652,0.000059915208,0.000092878465,0.000025721087,0.00005675435,0.000068458074,0.00027229995,0.000020457817,0.000012968136],"category_scores_gemma":[0.000012653557,0.000046860405,0.000020479578,0.00015047724,0.000023567098,0.0010770331,0.00011846404,0.000028236756,0.000018193079],"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":[0.0000072916414,0.00088600226,0.074458145,0.000039703133,0.00007601248,8.2866455e-7,0.0016209248,0.00004264743,0.04370318,0.45246127,0.038804904,0.38789907],"study_design_scores_gemma":[0.0005814257,0.000083883766,0.21812521,0.000023066876,0.000032968317,0.000013156614,0.000044076198,0.3321343,0.4119141,0.00085041986,0.035583712,0.00061365095],"about_ca_topic_score_codex":0.00069633825,"about_ca_topic_score_gemma":0.000042135987,"teacher_disagreement_score":0.685915,"about_ca_system_score_codex":0.000009568947,"about_ca_system_score_gemma":0.000023226085,"threshold_uncertainty_score":0.1910912},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015030835,0.00005741342,0.9589558,0.0008936446,0.00046281156,0.000091907415,0.00000400441,0.0006080079,0.02389555],"genre_scores_gemma":[0.27539867,0.000027715967,0.72069514,0.00033232415,0.00016219163,0.00002688359,0.000008571409,0.000008096,0.0033404145],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99900746,0.000015300298,0.00016600556,0.00038001093,0.0002161499,0.00021507184],"domain_scores_gemma":[0.9990497,0.00009425867,0.00006435571,0.00065013015,0.000061053135,0.00008045172],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000789477,0.00010960369,0.000109371984,0.000048595204,0.00042221686,0.00017049427,0.0007004581,0.000039182534,0.000017211023],"category_scores_gemma":[0.000039771814,0.00009589556,0.00002923341,0.0003016726,0.000058230202,0.00027569119,0.00019130303,0.000092687565,0.00008323437],"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":[0.000009419912,0.00032332542,0.014576311,0.000014316746,0.000052487263,0.00024581334,0.009625724,0.00010871415,0.0006306809,0.30162802,0.11818033,0.5546049],"study_design_scores_gemma":[0.0019514883,0.0009894691,0.05950352,0.00069733214,0.00003633735,0.0016114688,0.0012158885,0.31385028,0.029141394,0.006664913,0.58083135,0.0035065424],"about_ca_topic_score_codex":0.00004469909,"about_ca_topic_score_gemma":0.000005520117,"teacher_disagreement_score":0.55109835,"about_ca_system_score_codex":0.000017922359,"about_ca_system_score_gemma":0.00007844753,"threshold_uncertainty_score":0.39105073},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08638476,0.0027134712,0.9014692,0.00018331174,0.00088869745,0.00009018718,0.0039507737,0.00018485848,0.0041347444],"genre_scores_gemma":[0.32741687,0.00018709573,0.6388255,0.0003062172,0.0015283417,0.0000133722615,0.028706696,0.00004114154,0.0029747752],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997919,0.000029937935,0.00031227138,0.0011611762,0.00023029897,0.00034728632],"domain_scores_gemma":[0.9957344,0.0006457626,0.00010110425,0.003335474,0.000045761888,0.00013751],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010922808,0.00018811261,0.00018670494,0.00010553064,0.00033713522,0.0007192429,0.0031476056,0.0000716495,0.000013558882],"category_scores_gemma":[0.00021683672,0.00017580572,0.000018030085,0.00032895504,0.000103035134,0.0041519473,0.005595378,0.00011956152,0.000050103572],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000132828645,0.0001774762,0.0047960714,0.000019154479,0.00008363476,0.00002519579,0.0021708133,8.6204795e-7,0.0004233313,0.0038182882,0.100722484,0.88774943],"study_design_scores_gemma":[0.0016303154,0.00011699633,0.0856199,0.00044169906,0.00017099419,0.00013902612,0.008828195,0.49909666,0.00075736636,0.0009093064,0.40062734,0.0016621877],"about_ca_topic_score_codex":0.00017798092,"about_ca_topic_score_gemma":0.0005836725,"teacher_disagreement_score":0.88608724,"about_ca_system_score_codex":0.000017993263,"about_ca_system_score_gemma":0.00016548792,"threshold_uncertainty_score":0.7169149},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5021359,0.00008841791,0.49363306,0.00093347207,0.00006699188,0.00007976829,0.0005301519,0.00006143738,0.0024708416],"genre_scores_gemma":[0.7481051,0.0000049141418,0.25143677,0.00004949371,0.000108630375,0.0000124006365,0.0001966153,0.0000032771497,0.00008276712],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903303,0.00002381702,0.00032835235,0.0002508137,0.0002453288,0.00011865949],"domain_scores_gemma":[0.9990563,0.00026480042,0.00015756424,0.00031469966,0.00015348234,0.000053185682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014885508,0.00008866078,0.00013114183,0.00004580286,0.000059457758,0.00003422249,0.0006019509,0.00003238662,0.0002063926],"category_scores_gemma":[0.00001905607,0.00007930648,0.00004749688,0.0001769108,0.0000817934,0.00038488978,0.00014246063,0.000062903484,0.000027013404],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027831777,0.00032402293,0.014629015,0.000014292721,0.00005109664,0.0000010070886,0.0011739149,0.0010127564,0.0030624338,0.38709456,0.0008519632,0.59178215],"study_design_scores_gemma":[0.0010537301,0.00020284487,0.063967004,0.00051125954,0.00003336004,0.000015572701,0.00092926313,0.7465166,0.14513505,0.0323598,0.008652379,0.0006231331],"about_ca_topic_score_codex":0.00048070794,"about_ca_topic_score_gemma":0.000054834458,"teacher_disagreement_score":0.74550384,"about_ca_system_score_codex":0.000023207875,"about_ca_system_score_gemma":0.00013622231,"threshold_uncertainty_score":0.32340243},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06960252,0.000019873982,0.9175984,0.0046709967,0.00027205312,0.00023598419,0.000056100544,0.0003577916,0.0071862806],"genre_scores_gemma":[0.053401615,0.0000022661923,0.9426189,0.00017219932,0.00003137978,0.000060619608,0.00004418085,0.0000058363275,0.0036630265],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907184,0.000045364664,0.00016538677,0.0002747569,0.00026564553,0.00017700013],"domain_scores_gemma":[0.999127,0.00020803786,0.00011673618,0.00036204178,0.0001244466,0.00006175455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059669424,0.000078654724,0.00009512254,0.00002692819,0.00020666457,0.00023860934,0.00052221055,0.000046538888,0.00004559205],"category_scores_gemma":[0.00026976157,0.000052806852,0.000026839152,0.00017982839,0.000020079793,0.00042463242,0.0001347209,0.00017931455,0.00032437782],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001911888,0.0003552638,0.008118501,0.0000067265205,0.000042110893,4.886751e-7,0.00077408436,0.000017051374,0.06294938,0.19875282,0.4024843,0.32649735],"study_design_scores_gemma":[0.00018515633,0.00006891216,0.0038799911,0.00000475656,0.0000068316763,0.0000011695109,0.000113658454,0.94197965,0.0021517067,0.00095990393,0.050482154,0.00016612062],"about_ca_topic_score_codex":0.00023835749,"about_ca_topic_score_gemma":0.000076935554,"teacher_disagreement_score":0.9419626,"about_ca_system_score_codex":0.00002816727,"about_ca_system_score_gemma":0.000046318586,"threshold_uncertainty_score":0.41693288},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010198369,0.000049929844,0.9873239,0.009519892,0.0012550158,0.00060081884,0.000101796584,0.000057686313,0.00007112719],"genre_scores_gemma":[0.1822085,0.0008525148,0.7825402,0.028870447,0.0030630091,0.001002113,0.0011741128,0.0000719059,0.00021723608],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858695,0.00005692085,0.0004711446,0.00018019046,0.0004502391,0.0002545594],"domain_scores_gemma":[0.9980957,0.00024935213,0.00032458268,0.00029083484,0.00092623354,0.00011333334],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0014126836,0.00016359767,0.0001260325,0.0004715975,0.0012411618,0.0016299706,0.0011243549,0.00007392369,0.000001922633],"category_scores_gemma":[0.0002010461,0.00010569494,0.0001637228,0.0005613743,0.00008326765,0.0011317456,0.0001875676,0.00016757961,0.0000013942298],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039691753,0.000035671717,0.00029181273,0.000024516226,0.00018059812,2.0626155e-7,0.0030860566,0.0050268853,0.000114492206,0.29693416,0.009075792,0.6851901],"study_design_scores_gemma":[0.0004716142,0.000083617575,0.00085981574,0.000031598083,0.000025952751,0.000104567174,0.00039933424,0.67184806,0.000038260514,0.00850587,0.31748793,0.00014340051],"about_ca_topic_score_codex":0.00003846507,"about_ca_topic_score_gemma":0.000038198377,"teacher_disagreement_score":0.68504673,"about_ca_system_score_codex":0.000025863965,"about_ca_system_score_gemma":0.000044019012,"threshold_uncertainty_score":0.99940646},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06248432,0.000024480634,0.9180388,0.0037982406,0.0006392688,0.00016803571,0.0017029166,0.00044403627,0.012699907],"genre_scores_gemma":[0.15246908,0.000002749567,0.8455957,0.00038269348,0.00015359366,0.000012734166,0.0010756669,0.000006310913,0.00030147852],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889463,0.000013631061,0.00018338818,0.0005478573,0.00016433772,0.00019616041],"domain_scores_gemma":[0.99739033,0.0001778476,0.00005839783,0.002221779,0.00003396019,0.00011769007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021500075,0.00010426762,0.0001035267,0.00003309768,0.000109873436,0.00028126372,0.0024616474,0.000050029612,0.00021618544],"category_scores_gemma":[0.00006469494,0.000088698136,0.000016834878,0.00018474861,0.0000697098,0.000539641,0.0007230722,0.00014230967,0.000119371085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.1584115e-7,0.00009109684,0.00075537333,0.0000017667388,0.000026876192,0.000012545514,0.0003057049,0.0000041884755,0.007979202,0.088351384,0.040072583,0.8623987],"study_design_scores_gemma":[0.00033469504,0.00002282672,0.0010731908,0.0000116643205,0.000009357452,0.000015204504,0.00021761647,0.869318,0.0012240071,0.0032213111,0.1242536,0.00029851188],"about_ca_topic_score_codex":0.0012972363,"about_ca_topic_score_gemma":0.00042543391,"teacher_disagreement_score":0.86931384,"about_ca_system_score_codex":0.0000060838065,"about_ca_system_score_gemma":0.000092742084,"threshold_uncertainty_score":0.45743942},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013219107,0.000009691377,0.9822807,0.0014475756,0.00009647289,0.000055479737,0.0000056292665,0.00014029408,0.002745087],"genre_scores_gemma":[0.51789284,0.0000046290816,0.48069003,0.0010535412,0.000035517307,0.00003592459,0.000029692726,0.0000071387785,0.00025064807],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991986,0.000030596668,0.00015727113,0.0002933028,0.000113709146,0.00020651527],"domain_scores_gemma":[0.9993096,0.00007712002,0.000027954027,0.00049975695,0.00002313178,0.00006244135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027395104,0.00007831738,0.00010174638,0.000090959446,0.00005922094,0.00010602434,0.00060794613,0.000030918574,0.000028259794],"category_scores_gemma":[0.000018875859,0.00006831177,0.00002441474,0.00045715694,0.00001517001,0.00024183963,0.00016429572,0.00006303962,0.00009509624],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.1922666e-7,0.000045908713,0.0044854255,0.000002439411,0.000002892155,0.0000018471358,0.00017807983,0.00003253994,0.000049620758,0.01651393,0.005288664,0.97339845],"study_design_scores_gemma":[0.00023371201,0.000025196845,0.016323745,0.000012673644,0.0000011047293,0.000004572549,0.000015077046,0.9581433,0.00032685374,0.0016415789,0.023135127,0.00013706667],"about_ca_topic_score_codex":0.00010327125,"about_ca_topic_score_gemma":0.00008683415,"teacher_disagreement_score":0.97326136,"about_ca_system_score_codex":0.00001016754,"about_ca_system_score_gemma":0.00001186187,"threshold_uncertainty_score":0.2785673},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15227932,0.000112628855,0.84314233,0.0002496205,0.000839133,0.00066841656,0.0017358551,0.00016468707,0.0008079943],"genre_scores_gemma":[0.9521373,0.00006128356,0.045877825,0.00043205958,0.00018215338,0.00033956085,0.000101496706,0.000045455694,0.0008228754],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973266,0.000103870385,0.00050061895,0.0010852208,0.00046969453,0.0005139804],"domain_scores_gemma":[0.99771506,0.00022108157,0.00014686037,0.0013047355,0.000113482965,0.00049876625],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00031484655,0.00041657858,0.0004165967,0.00020092298,0.00035301608,0.00053880387,0.0006177637,0.0001471891,0.000023733008],"category_scores_gemma":[0.0000076288443,0.00040816877,0.0000783429,0.00026390085,0.0001351073,0.00022940004,0.00003204959,0.00045772927,0.00006617379],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007877651,0.0272544,0.0046714945,0.001829722,0.0034670215,0.00038358662,0.04074042,0.032894373,0.033769596,0.40292522,0.052416258,0.39886013],"study_design_scores_gemma":[0.0042062365,0.00084841624,0.0039121415,0.00053218333,0.00034683745,0.00012400685,0.0013888429,0.8727629,0.011422656,0.0004807663,0.10166053,0.0023144719],"about_ca_topic_score_codex":0.002048946,"about_ca_topic_score_gemma":0.00093313813,"teacher_disagreement_score":0.83986855,"about_ca_system_score_codex":0.000036741687,"about_ca_system_score_gemma":0.000074553805,"threshold_uncertainty_score":0.99983704},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06468951,0.000015640084,0.93348396,0.00061515433,0.000039957387,0.0003879528,0.00037393506,0.00013395496,0.00025995774],"genre_scores_gemma":[0.42708254,0.0000033909491,0.56991273,0.00012787904,0.000030614647,0.00022638003,0.0024515737,0.000005635593,0.0001592295],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988774,0.000021118556,0.00018318607,0.0005903976,0.0001345505,0.00019335233],"domain_scores_gemma":[0.9980242,0.000048520607,0.000059099973,0.0017504474,0.00003144693,0.00008625779],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001570974,0.00009130381,0.00008581956,0.000017158667,0.00014406779,0.0006422574,0.0017718388,0.000031304655,0.00001583509],"category_scores_gemma":[0.000010089091,0.000077290824,0.000018606519,0.00012134532,0.00003245756,0.0034666045,0.00035654847,0.000044890137,0.00008317446],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016710874,0.0025638668,0.0026628044,0.000022152271,0.000104235405,4.5549353e-7,0.0007346344,0.0002703267,0.10707403,0.1513829,0.03056187,0.704606],"study_design_scores_gemma":[0.00021929832,0.00002534955,0.014579169,0.000001364291,0.000005965299,5.3445433e-7,0.00023742886,0.98173285,0.00051755406,0.0020242617,0.0005350906,0.000121119614],"about_ca_topic_score_codex":0.0006100633,"about_ca_topic_score_gemma":0.000028204873,"teacher_disagreement_score":0.98146254,"about_ca_system_score_codex":0.00002391209,"about_ca_system_score_gemma":0.000029001189,"threshold_uncertainty_score":0.6193303},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000030563395,0.0001643286,0.9911858,0.00037522934,0.000041112347,0.00026196006,0.00015776345,0.00007081874,0.0077124545],"genre_scores_gemma":[0.07221986,0.00000926124,0.9251188,0.000058219048,0.00002743511,0.00024210225,0.00005767772,0.0000053355525,0.0022612992],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99938756,0.0000047999524,0.00016173886,0.00026287438,0.000084301086,0.000098737226],"domain_scores_gemma":[0.9983365,0.00010312616,0.00006244812,0.001406582,0.00005648975,0.00003488827],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014473054,0.000045330173,0.000075744196,0.000036385383,0.00006471613,0.00006552174,0.0015013219,0.000018877348,0.000017780003],"category_scores_gemma":[0.000011169641,0.000040106737,0.00001397117,0.00022512842,0.000017706625,0.00036932837,0.00027596936,0.00001751343,0.000029719939],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.5678733e-7,0.0001498857,0.000038743656,0.00002786268,0.000020188523,1.3532834e-7,0.00027226924,0.000012016987,0.00015504923,0.41249907,0.13855836,0.44826615],"study_design_scores_gemma":[0.000070369046,0.000013883842,0.000015325417,0.0000046798195,0.000003028519,0.000002652833,0.00006494049,0.6398263,0.000038577316,0.00010780167,0.35979936,0.000053118452],"about_ca_topic_score_codex":0.000015123543,"about_ca_topic_score_gemma":0.0000010013462,"teacher_disagreement_score":0.63981426,"about_ca_system_score_codex":0.0000039515708,"about_ca_system_score_gemma":0.000007841064,"threshold_uncertainty_score":0.27898544},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032958232,0.000029223895,0.93735206,0.010994594,0.00017020942,0.00028136445,0.000042013122,0.0003874757,0.01778485],"genre_scores_gemma":[0.944839,0.0000123588425,0.05356289,0.00057087105,0.00003203391,0.00004475317,0.000021742026,0.000005653618,0.00091070484],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99911916,0.00003352003,0.00015017718,0.00032052794,0.00021506891,0.00016155139],"domain_scores_gemma":[0.99899936,0.00036591003,0.0000998251,0.00041446462,0.000056020304,0.00006443246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002049448,0.000086833395,0.00007488606,0.00006919408,0.00017448263,0.00022456012,0.00027645327,0.000050670682,0.00002971441],"category_scores_gemma":[0.00013083822,0.00007567226,0.000022337008,0.00020802736,0.000015099065,0.00015726898,0.000055659857,0.00007610675,0.00020767303],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000067725746,0.0012075561,0.007528423,0.00002288976,0.000028259548,0.000002629496,0.00073531497,0.004739561,0.0022152192,0.16835856,0.04701778,0.76813704],"study_design_scores_gemma":[0.0002498302,0.000027259654,0.018052168,0.0000059486533,0.0000027067285,4.515992e-7,0.000014708305,0.9702441,0.00020664165,0.00006400865,0.011036785,0.000095400916],"about_ca_topic_score_codex":0.000016519693,"about_ca_topic_score_gemma":0.000005096859,"teacher_disagreement_score":0.9655045,"about_ca_system_score_codex":0.00007474749,"about_ca_system_score_gemma":0.000009226555,"threshold_uncertainty_score":0.30858248},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032430604,0.000016359389,0.96298957,0.00010314274,0.000053966385,0.00011814469,0.0000041065623,0.00009171137,0.004192367],"genre_scores_gemma":[0.9061168,0.000015596757,0.0934168,0.000104532206,0.000021274805,0.000026432728,0.000016073913,0.0000041048356,0.00027839854],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995373,0.000016547443,0.00010834475,0.00015309973,0.000112531896,0.00007220602],"domain_scores_gemma":[0.99951404,0.000044549415,0.00004715522,0.00028492312,0.00007854322,0.00003078819],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006947473,0.00004541328,0.000066910965,0.000042006945,0.0000676285,0.00001334067,0.00027990498,0.000018594717,0.000011987784],"category_scores_gemma":[0.00002075771,0.00003903178,0.00001736649,0.00034099113,0.000030894636,0.00021624313,0.00007577079,0.000020458861,0.000037606398],"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":[0.0000012098636,0.0003407147,0.0071301623,0.000018975601,0.000030199713,0.00000734501,0.0019317294,0.00006798114,0.00801244,0.802161,0.013822441,0.16647583],"study_design_scores_gemma":[0.0011564647,0.00042543036,0.30830407,0.00006609282,0.0000166304,0.00016587078,0.00007581807,0.38325346,0.26416752,0.005922382,0.035715967,0.0007302832],"about_ca_topic_score_codex":0.00007769788,"about_ca_topic_score_gemma":0.0000014437654,"teacher_disagreement_score":0.8736862,"about_ca_system_score_codex":0.00001079455,"about_ca_system_score_gemma":0.000019963009,"threshold_uncertainty_score":0.15916698},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040947692,0.0000138312325,0.96851784,0.0009780072,0.00012678315,0.00005399124,0.00004601253,0.00018069302,0.025988057],"genre_scores_gemma":[0.13760324,0.0000018380083,0.85770553,0.00025233737,0.000106288266,0.000009040903,0.00022243636,0.000005555436,0.004093723],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992994,0.000010409362,0.00011902527,0.000347977,0.00009236938,0.00013083249],"domain_scores_gemma":[0.9986627,0.00005468839,0.000040430936,0.0011879319,0.000025064275,0.00002920364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000089151006,0.00006081165,0.00005889132,0.00003447116,0.00006794667,0.00020967884,0.0016378612,0.000014804149,0.000026298196],"category_scores_gemma":[0.000011382168,0.00005318972,0.000011529214,0.00017280302,0.0000142965755,0.00094410277,0.0009241203,0.00004230874,0.00011828454],"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":[0.0000018606,0.0002465468,0.0013333302,0.0000032755054,0.000018487559,0.000010344796,0.00021699385,0.000009059154,0.00050549506,0.087308854,0.49804336,0.41230237],"study_design_scores_gemma":[0.00027348188,0.000020878613,0.0056454707,0.000015215224,0.000004540361,0.0000182732,0.00010164925,0.57185996,0.00064541196,0.0007005505,0.42051718,0.00019742655],"about_ca_topic_score_codex":0.00028558844,"about_ca_topic_score_gemma":0.000057415513,"teacher_disagreement_score":0.5718509,"about_ca_system_score_codex":0.000010456373,"about_ca_system_score_gemma":0.000018612938,"threshold_uncertainty_score":0.3043581},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23850334,0.0000033413887,0.7574009,0.00011421576,0.00010015236,0.00011050546,0.00004418679,0.000043179858,0.0036802187],"genre_scores_gemma":[0.7430863,0.000004087848,0.25643831,0.00017715606,0.000017185539,0.000016788632,0.000029535826,0.0000033977954,0.0002272302],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992406,0.000025195655,0.00022430412,0.00022246651,0.00015001131,0.00013743488],"domain_scores_gemma":[0.99948156,0.000015847925,0.00008015084,0.00032198042,0.00004031074,0.00006015196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021841314,0.00007683773,0.00009743316,0.000040741936,0.00006412523,0.00006526377,0.00024718585,0.000021914038,0.0002933582],"category_scores_gemma":[0.000014861517,0.00005976217,0.000020366146,0.00011179661,0.000030331421,0.00020771123,0.00005673254,0.00003374216,0.000012106239],"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":[0.00000790893,0.0006512692,0.08537741,0.00005876334,0.00016346395,0.000048301266,0.0041339104,0.00008860336,0.09885857,0.4277788,0.01674204,0.36609092],"study_design_scores_gemma":[0.002752633,0.0008325762,0.010313776,0.000090136855,0.000057908863,0.00044334118,0.002185033,0.2765062,0.67869395,0.00042630988,0.026477622,0.0012205354],"about_ca_topic_score_codex":0.00018321077,"about_ca_topic_score_gemma":0.0001728693,"teacher_disagreement_score":0.57983536,"about_ca_system_score_codex":0.000022646986,"about_ca_system_score_gemma":0.000120655706,"threshold_uncertainty_score":0.32120666},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13708843,0.000015345031,0.860701,0.00022105336,0.00011962102,0.00006588034,0.000047991107,0.00013127383,0.001609408],"genre_scores_gemma":[0.9094631,0.000001422577,0.089650996,0.00005428523,0.000078953795,0.0000031508025,0.00006105504,0.000004965244,0.00068206934],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99924284,0.000024650428,0.0001400981,0.00022315244,0.00021072157,0.00015854351],"domain_scores_gemma":[0.9995177,0.00007691987,0.00008192787,0.0002714652,0.000027581042,0.00002443214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019655307,0.000071542214,0.000082503655,0.00006114492,0.0001510307,0.00023186332,0.0002047109,0.000019567877,0.000009873503],"category_scores_gemma":[0.00000842517,0.00006372803,0.000034092816,0.0003185937,0.000008328742,0.00045224788,0.000023409513,0.00005391006,0.0000217331],"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":[0.000018332941,0.0037102376,0.039582312,0.00006857368,0.0002129518,0.000020889569,0.0008594569,0.40320787,0.100696646,0.23593938,0.056724068,0.15895925],"study_design_scores_gemma":[0.00013044506,0.000007928582,0.021253739,0.0000089142195,0.000009902516,0.0000042782126,0.000012742878,0.9701676,0.004915327,0.00009807864,0.0032651126,0.0001259565],"about_ca_topic_score_codex":0.0012821694,"about_ca_topic_score_gemma":0.00004875757,"teacher_disagreement_score":0.7723747,"about_ca_system_score_codex":0.00013663703,"about_ca_system_score_gemma":0.000033856035,"threshold_uncertainty_score":0.25987536},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000065595227,0.00003648587,0.7832938,0.001281158,0.00005557354,0.00029978747,0.0069991425,0.00007037963,0.20795712],"genre_scores_gemma":[0.0012773715,0.00007529188,0.88129085,0.0021448175,0.00016285422,0.00002074025,0.041111875,0.000025796835,0.07389042],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99803364,0.0000082394245,0.00040924177,0.0009839368,0.0003947847,0.00017012993],"domain_scores_gemma":[0.9914495,0.00008463315,0.00026350457,0.0080892425,0.00004661577,0.00006651172],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00062866334,0.00018492866,0.00033008176,0.0002910629,0.00012290968,0.00018089887,0.008026466,0.00007590537,0.00009019622],"category_scores_gemma":[0.00001590889,0.00013787928,0.000042616466,0.000472343,0.000023811677,0.0003725992,0.004301748,0.0001180271,0.00006481569],"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":[0.0000010694849,0.000023624445,0.0000022169747,0.000003212763,0.00038647285,5.7845773e-7,0.00016837001,0.000024614032,0.0000057154825,0.29715672,0.035346422,0.66688097],"study_design_scores_gemma":[0.000097164826,0.000018712715,0.00019938519,0.000018992136,0.0006209667,9.570788e-7,0.00005168538,0.28296405,0.0000066719517,0.00061118853,0.71518636,0.00022383337],"about_ca_topic_score_codex":0.00003557857,"about_ca_topic_score_gemma":0.0004102846,"teacher_disagreement_score":0.67983997,"about_ca_system_score_codex":0.000016018514,"about_ca_system_score_gemma":0.00007419362,"threshold_uncertainty_score":0.99734056},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02002226,0.000034688714,0.9745314,0.0030981163,0.00031445513,0.00023758167,0.00028165116,0.0003224209,0.0011574423],"genre_scores_gemma":[0.9195196,0.000020652988,0.07995949,0.00008602838,0.00016973683,0.000047721052,0.00014427156,0.0000105777035,0.000041936117],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988492,0.0000011611038,0.00020772727,0.0005210758,0.00020805285,0.00021275549],"domain_scores_gemma":[0.99943733,0.000043068085,0.00007695958,0.0002637806,0.0001039327,0.000074936004],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019103345,0.00015673778,0.00013518316,0.00013361832,0.00007706338,0.00059797044,0.0014613926,0.000036427704,0.0000018393606],"category_scores_gemma":[0.000100780104,0.00015669722,0.000019886771,0.00011551854,0.000015423646,0.0012806252,0.0002962007,0.00009384803,0.0000034660377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000148558065,0.000071962124,0.00022402394,0.00017126166,0.000083321844,0.000004381774,0.0011917049,0.00013094733,0.011087928,0.5751743,0.0019743356,0.409871],"study_design_scores_gemma":[0.0002760118,0.000065493834,0.00042589512,0.00026766895,0.0000069829543,0.000022514025,0.00044760876,0.9944843,0.00083383656,0.00008456377,0.0028893077,0.0001957957],"about_ca_topic_score_codex":0.0000077223085,"about_ca_topic_score_gemma":5.5769283e-7,"teacher_disagreement_score":0.99435335,"about_ca_system_score_codex":0.000043825654,"about_ca_system_score_gemma":0.000021319502,"threshold_uncertainty_score":0.6389927},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032609917,0.000069634836,0.9661078,0.00014377577,0.00016597177,0.00005675784,0.000021833339,0.000116208226,0.0007081419],"genre_scores_gemma":[0.36780018,0.0000029282417,0.63186955,0.00017529172,0.000094505995,0.0000046809528,0.000034178003,0.000005252532,0.000013413472],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988011,0.00003743857,0.00028634822,0.00041731566,0.00029484733,0.00016291493],"domain_scores_gemma":[0.9982516,0.0010572255,0.00010525641,0.00036701548,0.00013594069,0.00008294561],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020869506,0.00011818325,0.0001228632,0.000077584955,0.00026467376,0.00028442766,0.00085599313,0.000037320737,0.000032668828],"category_scores_gemma":[0.00015589736,0.00011447216,0.00004501264,0.0002690642,0.00005412655,0.00040518265,0.0002553877,0.000086717206,0.0002445998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001243502,0.00003431505,0.00013205614,0.0000013075221,0.0000070290002,9.715851e-7,0.000248527,0.20462686,0.00009477978,0.18235146,0.00014638843,0.61235505],"study_design_scores_gemma":[0.000029531786,0.0000144818405,0.0021124056,0.00003786887,0.000002973199,0.0000049538367,0.000017550969,0.81309795,0.0003789921,0.18287426,0.001315718,0.0001133122],"about_ca_topic_score_codex":0.0001540063,"about_ca_topic_score_gemma":0.0000065822956,"teacher_disagreement_score":0.61224174,"about_ca_system_score_codex":0.000031613698,"about_ca_system_score_gemma":0.000047690144,"threshold_uncertainty_score":0.4668039},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000044703218,0.00004960537,0.9938209,0.0047357827,0.000012567042,0.00036593652,0.000002186466,0.00020488455,0.00076344487],"genre_scores_gemma":[0.0030434725,0.000044431563,0.9961016,0.00016049124,0.00006115867,0.00014270986,0.000015369176,0.000003815662,0.0004269283],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994272,0.000035638586,0.0001151568,0.00024051857,0.000079275575,0.00010221681],"domain_scores_gemma":[0.999534,0.00007753001,0.000055638673,0.0002512878,0.000054659897,0.000026873608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024016094,0.00006312804,0.000054488075,0.000030909796,0.00024780433,0.00019889737,0.00028963963,0.000028905059,0.0000010381282],"category_scores_gemma":[0.000017573924,0.00004177345,0.000016178208,0.00018655056,0.000018884532,0.00019138723,0.000041788575,0.00005703615,0.0000015309508],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.782236e-7,0.00000908874,0.000005827898,8.5240913e-7,0.0000012949736,7.953445e-8,0.00008228708,0.00000382184,0.00045282737,0.048998658,0.0002015101,0.9502436],"study_design_scores_gemma":[0.000058330737,0.00008037931,0.0024215956,0.0000039322185,0.000005015964,0.000015540818,0.000039296894,0.9579203,0.0019396615,0.009330526,0.028112192,0.000073190895],"about_ca_topic_score_codex":0.000004496226,"about_ca_topic_score_gemma":3.6989871e-7,"teacher_disagreement_score":0.9579165,"about_ca_system_score_codex":0.000008508236,"about_ca_system_score_gemma":0.000013858044,"threshold_uncertainty_score":0.19179718},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10839725,0.00034136878,0.8890387,0.00042916,0.0010202472,0.0000746967,0.000083914354,0.000018270715,0.0005964108],"genre_scores_gemma":[0.8689594,0.0008229512,0.12950602,0.00047494756,0.00013123975,0.0000014016299,0.000040708026,0.0000040780756,0.000059237253],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986227,0.000020951467,0.00065054005,0.00012007767,0.00045361303,0.00013210233],"domain_scores_gemma":[0.9975235,0.0004820991,0.00057627633,0.00020983149,0.0011194894,0.00008880655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028353592,0.000119833734,0.00016040797,0.00021892606,0.00009518251,0.00021290395,0.0019563772,0.00003228378,0.00001043408],"category_scores_gemma":[0.0004571774,0.00009673987,0.00004657171,0.00016497349,0.000116017836,0.0032021657,0.00080196164,0.000276064,0.000015360289],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000076269294,0.00013218843,0.0009574032,0.000007547964,0.0003017343,0.00011868568,0.007929397,0.000016137468,0.000041136725,0.0033325902,0.0017411632,0.9853457],"study_design_scores_gemma":[0.0012776792,0.00047577603,0.009596678,0.0012829271,0.000060574792,0.009535117,0.007884781,0.9429741,0.005837827,0.0017927483,0.018575294,0.0007064983],"about_ca_topic_score_codex":0.000007294511,"about_ca_topic_score_gemma":0.0000018937733,"teacher_disagreement_score":0.9846392,"about_ca_system_score_codex":0.000028004974,"about_ca_system_score_gemma":0.00009028397,"threshold_uncertainty_score":0.39449373},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029171219,0.00008794206,0.99405634,0.0006621887,0.0011360053,0.00027977064,0.0006056078,0.0001900616,0.00006494976],"genre_scores_gemma":[0.023650581,0.0000012338237,0.97377694,0.00032651887,0.0011369521,0.0000067830815,0.0010480804,0.000022454373,0.000030457823],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979699,0.00005252266,0.00044892603,0.0007716049,0.00028145924,0.00047556285],"domain_scores_gemma":[0.9973832,0.0002633619,0.00023982475,0.0016505901,0.00022538874,0.0002376395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010367322,0.00020333925,0.00026131512,0.00010628857,0.0002982788,0.00051877263,0.002141742,0.000067805464,3.4385852e-7],"category_scores_gemma":[0.00017723761,0.0002048026,0.000051278417,0.0006081271,0.00004886507,0.00043975128,0.0022394864,0.00012212517,0.00000877726],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000052442438,0.00017257068,0.00058136386,0.000046553116,0.00011420644,0.000018477178,0.0016422985,0.018470677,0.000078137666,0.00065215264,0.058625218,0.9195931],"study_design_scores_gemma":[0.00056119426,0.000035697372,0.000049884988,0.000060240873,0.00002810855,0.0000443178,0.00017868205,0.9652516,0.000034031542,0.0002981326,0.03320465,0.0002534656],"about_ca_topic_score_codex":0.00007003674,"about_ca_topic_score_gemma":0.0000067570927,"teacher_disagreement_score":0.9467809,"about_ca_system_score_codex":0.00011069667,"about_ca_system_score_gemma":0.00020187453,"threshold_uncertainty_score":0.8351608},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017888328,0.00027229244,0.9780203,0.0010996638,0.00006889043,0.00012837864,0.00001637081,0.000100442645,0.0024053238],"genre_scores_gemma":[0.00757721,0.00004758056,0.99049276,0.0005417094,0.000022914124,0.000022716706,0.0000042826973,0.000003754536,0.0012870707],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990654,0.000051005438,0.00016395378,0.00042312208,0.00006893078,0.00022759297],"domain_scores_gemma":[0.999155,0.00013410536,0.00004049308,0.00047789325,0.00008073164,0.00011176326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003951771,0.000121361474,0.000120679346,0.00007813243,0.00015327687,0.00073484244,0.00038487985,0.00003050234,0.000018651814],"category_scores_gemma":[0.00006647631,0.00010885883,0.000010666119,0.00068451907,0.000016626731,0.001319808,0.00025270862,0.000056586065,0.000009125988],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.539011e-7,0.00002065582,0.000029795388,0.0000044820854,0.0000023956318,0.00007137554,0.00088856235,6.217093e-7,0.00027549153,0.011146182,0.02185944,0.96570015],"study_design_scores_gemma":[0.000809004,0.00047073682,0.03337911,0.00017935422,0.000031269206,0.005233274,0.0027536815,0.14758684,0.0039812783,0.004720147,0.7989802,0.001875154],"about_ca_topic_score_codex":0.00016201715,"about_ca_topic_score_gemma":0.00004493488,"teacher_disagreement_score":0.963825,"about_ca_system_score_codex":0.00001403815,"about_ca_system_score_gemma":0.000080181555,"threshold_uncertainty_score":0.70861024},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000027526119,0.00011438007,0.019033555,0.0004984336,0.00022329662,0.00013203654,0.00023642414,0.0002893796,0.9794697],"genre_scores_gemma":[0.0006419291,0.000014371631,0.09971328,0.0015304841,0.00059329096,0.000021062222,0.00004127773,0.000025518659,0.8974188],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986877,0.0000073803153,0.00023800603,0.00045360715,0.0003774639,0.00023585852],"domain_scores_gemma":[0.99881774,0.00002837866,0.00025395426,0.0007064822,0.000096372794,0.00009706516],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00012278612,0.00022576428,0.00022596527,0.000036084482,0.00011040883,0.00027627253,0.0009261896,0.00027090387,0.000010084564],"category_scores_gemma":[0.000013001479,0.00023391322,0.00011391728,0.000017197843,0.000016128557,0.00009460035,0.00019890192,0.0001830512,0.0008837527],"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":[2.646461e-7,0.0000036379918,0.0000012203359,0.0000015787687,0.000020682288,0.0000047584235,0.0000090265485,2.5000756e-7,9.837435e-7,0.75860536,0.020603029,0.22074923],"study_design_scores_gemma":[0.000070469774,0.000024172406,0.000057213576,0.000036101977,0.000019909108,0.000007935499,3.8917332e-7,0.00036511244,0.0000062707713,0.5789066,0.4202926,0.0002132371],"about_ca_topic_score_codex":0.000024739913,"about_ca_topic_score_gemma":0.000013252389,"teacher_disagreement_score":0.39968956,"about_ca_system_score_codex":0.00032547553,"about_ca_system_score_gemma":0.00011499136,"threshold_uncertainty_score":0.9998942},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000025110254,0.00012665043,0.99533325,0.002547612,0.0007597301,0.00054119935,0.00006213735,0.000094514486,0.0005097906],"genre_scores_gemma":[0.0028318074,0.0000176174,0.99354666,0.002799057,0.00040742217,0.0000330991,0.00002742265,0.000026118807,0.00031078453],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99677813,0.000007281202,0.0003447999,0.0019481109,0.00042460376,0.0004971005],"domain_scores_gemma":[0.99640566,0.00040787744,0.00014239957,0.002693548,0.0001536014,0.00019692892],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.000970579,0.00033409678,0.00036738158,0.00042612237,0.00031112196,0.0018199612,0.0076404028,0.0001434162,0.0000040655314],"category_scores_gemma":[0.00010104547,0.00030328808,0.000034193865,0.00038387583,0.00023621698,0.000999124,0.0068843463,0.0002807282,0.000014426176],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016201215,0.0000074473587,0.00002342822,0.00003263549,0.0000049664336,0.000002212176,0.00009689686,0.0015143853,0.00004373809,0.019769292,0.0012160862,0.9772873],"study_design_scores_gemma":[0.00012497877,0.00007956168,0.00006539178,0.00024500367,0.0000069384078,0.000018835013,4.504566e-8,0.8474656,0.00027838108,0.046696298,0.10461681,0.0004021678],"about_ca_topic_score_codex":0.000033059605,"about_ca_topic_score_gemma":0.00005085105,"teacher_disagreement_score":0.97688514,"about_ca_system_score_codex":0.000059230075,"about_ca_system_score_gemma":0.00018432138,"threshold_uncertainty_score":0.99994195},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014550047,0.0011440802,0.9960335,0.0009811725,0.00031708763,0.00040079336,0.00075434375,0.00008357051,0.00013994443],"genre_scores_gemma":[0.0027148544,0.00016349109,0.99385035,0.00033392722,0.0005246511,0.00009708247,0.0018081083,0.000035281562,0.00047222842],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973418,0.00004788833,0.00038749044,0.001373825,0.00037199352,0.00047697057],"domain_scores_gemma":[0.99646896,0.00009646802,0.0001576177,0.0030079603,0.00003272749,0.00023624166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014306607,0.00023490694,0.00028332436,0.00017469122,0.00015671295,0.00040972498,0.003730504,0.00007542466,9.649351e-7],"category_scores_gemma":[0.00009692773,0.0002304224,0.000017133789,0.0005402162,0.000105209365,0.0014835544,0.0031661468,0.00016812832,0.00001555033],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013100173,0.000085576976,0.00013332642,0.000013744197,0.000016348391,0.000017856255,0.00026066325,0.000018481065,0.000004206371,0.00020101875,0.003051891,0.99619555],"study_design_scores_gemma":[0.00074850844,0.000047555677,0.00019379114,0.000044142016,0.000023148752,0.000037371112,0.00020291307,0.8984322,0.0000093513945,0.002479207,0.09751047,0.00027132305],"about_ca_topic_score_codex":0.00047821488,"about_ca_topic_score_gemma":0.00008578177,"teacher_disagreement_score":0.99592423,"about_ca_system_score_codex":0.00007366919,"about_ca_system_score_gemma":0.0001797041,"threshold_uncertainty_score":0.93963534},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0065716924,0.00007030313,0.9800923,0.0024998854,0.00007400446,0.00007017843,0.000017960247,0.0002818621,0.010321805],"genre_scores_gemma":[0.024628822,0.000002028801,0.97310823,0.00021162219,0.00005260946,0.000008253131,0.00007815645,0.000005849525,0.0019044381],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992648,0.000009775181,0.00008425481,0.00033666115,0.00016751024,0.00013700307],"domain_scores_gemma":[0.99825466,0.000028131542,0.000029856372,0.0015316928,0.000039520095,0.00011614238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002149942,0.000063987456,0.000063025196,0.00003439324,0.000054011154,0.00016426103,0.0017547733,0.000016133648,0.000009235615],"category_scores_gemma":[0.00001408542,0.000045908288,0.000005174663,0.0003033612,0.00002342773,0.0008281865,0.00090974575,0.000039335864,0.00016329552],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000054932702,0.00016655696,0.000891557,0.0000067918577,0.000032039825,0.000052671905,0.0009072125,0.00007495263,0.000099275916,0.16644369,0.55579656,0.27552322],"study_design_scores_gemma":[0.0003794401,0.00013871759,0.00041628748,0.000013175115,0.0000073060605,0.00007552765,0.000338066,0.79155415,0.00013810006,0.0006562267,0.20605262,0.00023038914],"about_ca_topic_score_codex":0.000053797445,"about_ca_topic_score_gemma":0.000008069479,"teacher_disagreement_score":0.79147923,"about_ca_system_score_codex":0.00000791227,"about_ca_system_score_gemma":0.000096429125,"threshold_uncertainty_score":0.32608348},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005554741,0.00002366089,0.9937655,0.0021613038,0.00013381854,0.0012074417,0.00059269957,0.00023715134,0.0013229979],"genre_scores_gemma":[0.8748137,0.000034468092,0.12092228,0.00048976816,0.0003654862,0.0024304085,0.0008240836,0.000022708238,0.00009712214],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975683,0.000048079248,0.0005695107,0.0010577126,0.00045513274,0.0003012487],"domain_scores_gemma":[0.99710166,0.00022851415,0.00025515514,0.0014313242,0.00076946046,0.00021389412],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00054219726,0.00026085696,0.0002189479,0.00020809773,0.0009752728,0.00040240146,0.002029604,0.0001399787,0.000028342844],"category_scores_gemma":[0.000108309585,0.00026774756,0.00006465875,0.0004061137,0.00022959567,0.0009209612,0.00023563091,0.00024164158,0.00007055707],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025761497,0.0003784214,0.00003989834,0.000007502785,0.000028997381,6.496903e-7,0.00020469837,0.000182474,0.0017665516,0.32239687,0.000086859414,0.67488134],"study_design_scores_gemma":[0.00013437321,0.00011496882,0.00022639935,0.000027685443,0.000024064077,0.00001397081,0.0002765715,0.94010293,0.006995641,0.022577502,0.029101143,0.0004047622],"about_ca_topic_score_codex":0.00010470007,"about_ca_topic_score_gemma":0.00022617537,"teacher_disagreement_score":0.9399204,"about_ca_system_score_codex":0.000056115707,"about_ca_system_score_gemma":0.0002512662,"threshold_uncertainty_score":0.99997747},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73181605,0.0006357042,0.00595455,0.031317372,0.0013084679,0.0017989166,0.00003634868,0.00037186008,0.22676072],"genre_scores_gemma":[0.9404029,0.000012981444,0.05876947,0.00016203888,0.000046769965,0.00008403352,6.187489e-7,0.000006055796,0.0005151261],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99921733,0.0000027015933,0.00017473257,0.00020242033,0.00024443778,0.00015840525],"domain_scores_gemma":[0.9995451,0.0000103544035,0.00009902136,0.00019245844,0.00008959329,0.0000634533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030273836,0.00007274306,0.00009338848,0.000054650736,0.000034168173,0.00006393428,0.0011323905,0.000020384114,9.230242e-7],"category_scores_gemma":[0.000050858882,0.000051220482,0.0000308689,0.00041460973,0.00003200295,0.00027873903,0.0005297822,0.00007756847,0.000015612213],"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":[0.0000103203465,0.000652384,0.007344702,0.000060583072,0.000029550421,0.0000010503861,0.0066056554,0.00006161057,0.026388656,0.78813714,0.08174744,0.08896091],"study_design_scores_gemma":[0.0041826414,0.00048296878,0.040900562,0.0005033286,0.00004381186,0.0001068697,0.0028360647,0.037390493,0.41059938,0.35446092,0.1473643,0.0011286619],"about_ca_topic_score_codex":0.00007825258,"about_ca_topic_score_gemma":0.0000024608607,"teacher_disagreement_score":0.4336762,"about_ca_system_score_codex":0.0000565259,"about_ca_system_score_gemma":0.000042343767,"threshold_uncertainty_score":0.21042821},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011983963,0.00011765834,0.9838828,0.00042787273,0.0002481344,0.00019464835,0.0021292283,0.00023487116,0.0007808366],"genre_scores_gemma":[0.6339324,0.000022045539,0.3589927,0.00008992276,0.0001823147,0.00010920639,0.00618889,0.000038523114,0.00044398368],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99785596,0.00008783719,0.0002636352,0.0011767807,0.0003220275,0.00029376222],"domain_scores_gemma":[0.9941777,0.00014583333,0.000114205424,0.0052391486,0.00009999767,0.00022311948],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028233425,0.00025839993,0.00020490504,0.00015062651,0.000305398,0.0006896158,0.00408963,0.00008465454,0.000006092324],"category_scores_gemma":[0.000031022624,0.00022290775,0.00003379272,0.00060235313,0.000074977426,0.004448361,0.00014923529,0.00026243474,0.00005466597],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025305688,0.0013972207,0.000352817,0.000013827687,0.000115001385,0.0000044938697,0.0048229913,0.00044518302,0.00013743309,0.0006365609,0.0035387059,0.98851043],"study_design_scores_gemma":[0.0023003768,0.0005671641,0.012483664,0.00023387396,0.00025116093,0.000054799337,0.011667481,0.9490593,0.00084679504,0.00097578025,0.020088654,0.0014709743],"about_ca_topic_score_codex":0.00044661193,"about_ca_topic_score_gemma":0.00054693787,"teacher_disagreement_score":0.9870395,"about_ca_system_score_codex":0.00007163878,"about_ca_system_score_gemma":0.00022629791,"threshold_uncertainty_score":0.90899146},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016534269,0.0001603619,0.9895169,0.0017924311,0.0035417646,0.000094417686,0.0031700234,0.000022186328,0.000048466132],"genre_scores_gemma":[0.18135205,0.000094279356,0.8161466,0.00039151846,0.0012635937,0.0000034556188,0.00065278966,0.000013020313,0.00008268427],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99810505,0.000032670756,0.00062940916,0.0004406165,0.0006176372,0.00017460395],"domain_scores_gemma":[0.995622,0.00039840525,0.00050962064,0.0020411164,0.0012143734,0.00021448429],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0011046955,0.00013103671,0.0001714068,0.00018260459,0.000060301067,0.0006901196,0.010751676,0.00004837808,0.0000060670545],"category_scores_gemma":[0.0017374614,0.00011306182,0.000037763137,0.0002136895,0.000075581665,0.0032841226,0.0024047932,0.00014952032,0.000012515488],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028521275,0.000080046615,0.000089214285,0.0000029250793,0.00011399281,0.0006580077,0.00029626122,0.00011918269,0.000033734894,0.004723037,0.06281628,0.9310388],"study_design_scores_gemma":[0.00041652867,0.00015210887,0.000050473092,0.00007661673,0.000039788276,0.015737182,0.00042558776,0.52764416,0.00075207854,0.003952853,0.45049047,0.00026219094],"about_ca_topic_score_codex":0.00009281583,"about_ca_topic_score_gemma":0.000056130855,"teacher_disagreement_score":0.9307766,"about_ca_system_score_codex":0.000057504167,"about_ca_system_score_gemma":0.0004064577,"threshold_uncertainty_score":0.99460065},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019952403,0.000043264146,0.9339134,0.0020144098,0.0000639724,0.000028278011,0.0000020273667,0.00018088274,0.06355422],"genre_scores_gemma":[0.24895836,0.000071577786,0.7385193,0.00088574964,0.000055674725,0.000019577337,0.0000016472524,0.000003973276,0.011484146],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995846,0.000004420775,0.00007179589,0.00016368327,0.000075030206,0.00010044002],"domain_scores_gemma":[0.9994971,0.000023202156,0.000013117158,0.00040647277,0.000016533693,0.000043539363],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000047853693,0.000038579834,0.000034073983,0.000023400375,0.000054024404,0.000092155315,0.00063122576,0.000012574529,0.0003405318],"category_scores_gemma":[0.0000078866615,0.000032237826,0.000014089094,0.00023486801,0.00001529353,0.00021733507,0.000126609,0.000036220088,0.0019943728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.7074848e-8,0.000025131516,0.000013180096,4.9536874e-7,0.0000011439159,0.0000010210138,0.000075664764,0.0000034664133,0.000047983867,0.25439718,0.02861996,0.71681476],"study_design_scores_gemma":[0.000015667316,0.000010318828,0.000046725585,0.0000016217296,4.7195218e-7,0.0000067587016,0.000009729964,0.8225888,0.0006271601,0.0019219558,0.1747093,0.00006150439],"about_ca_topic_score_codex":0.000006343564,"about_ca_topic_score_gemma":0.0000018412583,"teacher_disagreement_score":0.8225853,"about_ca_system_score_codex":0.000004933716,"about_ca_system_score_gemma":0.0000040976443,"threshold_uncertainty_score":0.9987827},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019979976,0.00007830094,0.9785636,0.00054796424,0.0006930091,0.000061661165,0.000026176393,0.000025392754,0.000023908513],"genre_scores_gemma":[0.50269747,0.0000097088405,0.4967559,0.00021066931,0.00031184676,0.0000014177158,0.000005193234,0.0000041057338,0.0000037097434],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99716204,0.000031480744,0.0004081738,0.00039159693,0.0018244759,0.00018222889],"domain_scores_gemma":[0.99510336,0.00024188691,0.00034409066,0.00032129753,0.0037863574,0.0002030158],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017119223,0.00011955941,0.00015156085,0.00033655093,0.00015176144,0.00063743774,0.0041882996,0.000022749142,0.0000016085143],"category_scores_gemma":[0.00111702,0.00010181528,0.000029466359,0.0008996104,0.00037505542,0.0027522526,0.00072722905,0.00015388381,0.000019616999],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020840213,0.00020678932,0.00048570527,0.0000041112885,0.00004875651,0.000045979494,0.0013535373,0.19648346,0.00010649862,0.009388399,0.000475833,0.7913801],"study_design_scores_gemma":[0.00010801994,0.000083891464,0.00033504583,0.000042866963,0.0000092174005,0.000486472,0.00019755335,0.9280371,0.0005126822,0.06957845,0.00047545705,0.00013323515],"about_ca_topic_score_codex":0.000011557949,"about_ca_topic_score_gemma":4.638137e-7,"teacher_disagreement_score":0.79124683,"about_ca_system_score_codex":0.0001120169,"about_ca_system_score_gemma":0.00188646,"threshold_uncertainty_score":0.7782973},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011694153,0.00009458219,0.9923082,0.0019111121,0.0004787562,0.00024669085,0.00012814606,0.000056166136,0.004659399],"genre_scores_gemma":[0.21106938,0.000049595597,0.7757631,0.0023707268,0.0011389478,0.00005445002,0.00015369401,0.00007605192,0.009324072],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975912,0.000032478787,0.00037595144,0.0007346778,0.0009572063,0.00030847927],"domain_scores_gemma":[0.9970525,0.0010418387,0.00047570345,0.0011287007,0.00023574957,0.000065501394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012436925,0.00026774162,0.00033108453,0.00018893606,0.00015827052,0.00041981516,0.0025477961,0.00014870295,0.000010753607],"category_scores_gemma":[0.00024954427,0.00018862705,0.00007870524,0.00034751842,0.00050618465,0.00047678323,0.00057224144,0.00040582358,0.000061594714],"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":[0.0000060835687,0.00007489124,0.00006205506,0.00001897356,0.000027598717,0.000011962164,0.0005605731,0.0040497053,0.00012668222,0.6779073,0.0022845224,0.31486967],"study_design_scores_gemma":[0.00022341659,0.00017498134,0.00009170502,0.00038415275,0.0000101332525,0.0000094346815,3.297062e-7,0.52844054,0.0004540781,0.4649193,0.0047987313,0.00049319584],"about_ca_topic_score_codex":0.000019837802,"about_ca_topic_score_gemma":0.000016155896,"teacher_disagreement_score":0.5243908,"about_ca_system_score_codex":0.00029136962,"about_ca_system_score_gemma":0.0004974025,"threshold_uncertainty_score":0.7691988},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000073583906,0.000082713355,0.4310423,0.00030016038,0.00022485192,0.00006129336,0.000037132682,0.000177488,0.56806666],"genre_scores_gemma":[0.00017238593,0.00005175064,0.6623978,0.00073849974,0.00046002964,0.000010266044,0.00016087022,0.000024428884,0.33598396],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986913,0.0000037267355,0.00025502554,0.0005669522,0.00027496443,0.00020801643],"domain_scores_gemma":[0.9988828,0.000118689684,0.0001266985,0.0007224348,0.000047644724,0.000101743004],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013436121,0.00020324843,0.00019059656,0.00008310991,0.000107223685,0.0002004071,0.001065195,0.00016930855,0.00054391194],"category_scores_gemma":[0.0000071548834,0.00018378439,0.00006687512,0.00004598255,0.00007610974,0.00021057014,0.00027495244,0.00016581886,0.00054061465],"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":[4.3612505e-7,0.000004886469,0.0000022061977,0.0000014366739,0.000026137197,0.000016362339,0.0000942929,0.0000020634996,0.000006130204,0.68902785,0.010155935,0.30066225],"study_design_scores_gemma":[0.00007201975,0.000023129627,0.0000073130955,0.000045443627,0.000014203166,0.000004478542,0.000012532409,0.012177926,0.000096895164,0.0198699,0.9673388,0.00033733633],"about_ca_topic_score_codex":0.00025153393,"about_ca_topic_score_gemma":0.00008032353,"teacher_disagreement_score":0.9571829,"about_ca_system_score_codex":0.000023863791,"about_ca_system_score_gemma":0.00009184821,"threshold_uncertainty_score":0.749451},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007833853,0.00007380381,0.99428093,0.00013100918,0.00021407586,0.0005404729,0.0020976432,0.0003497997,0.0022338938],"genre_scores_gemma":[0.00011160864,0.00010507013,0.9696764,0.00013134192,0.00014562054,0.00046514015,0.023594623,0.000024598101,0.0057456023],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986953,0.000008068983,0.00029006964,0.0005895623,0.00020489145,0.00021208846],"domain_scores_gemma":[0.9987652,0.00017434232,0.0001554821,0.00063369086,0.00020085198,0.00007048793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010033905,0.00021160209,0.00020366984,0.000116746596,0.00021182734,0.00013670883,0.00071178394,0.00012246218,0.000018308896],"category_scores_gemma":[0.000073855874,0.00019906444,0.000054325486,0.00019494443,0.000025067266,0.00035600056,0.000063800384,0.0001437154,0.000023242164],"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":[0.000009892894,0.00021236773,0.000004515764,0.00016285488,0.000032459055,0.000002731797,0.00033911804,3.739073e-7,0.0070856027,0.34423342,0.17450163,0.47341505],"study_design_scores_gemma":[0.0006376378,0.00023319207,0.0008786431,0.00040658953,0.00008387051,0.00010210586,0.00031026485,0.04654396,0.1332364,0.0043733334,0.8115904,0.0016036285],"about_ca_topic_score_codex":0.00013508182,"about_ca_topic_score_gemma":0.000112276786,"teacher_disagreement_score":0.6370888,"about_ca_system_score_codex":0.000030915402,"about_ca_system_score_gemma":0.00019075624,"threshold_uncertainty_score":0.81176126},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47576872,0.016813362,0.37441608,0.0339736,0.03442473,0.010158813,0.002344686,0.0038334639,0.04826654],"genre_scores_gemma":[0.9058105,0.0010651894,0.068158686,0.007819779,0.002268657,0.0013047088,0.0005631868,0.00033136358,0.012677926],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9899421,0.00047281833,0.0022403512,0.0022058699,0.0017803984,0.00335846],"domain_scores_gemma":[0.98755634,0.0013577007,0.0010881884,0.0045686867,0.0020105965,0.003418463],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0027894184,0.0016696838,0.001585893,0.0008960887,0.0012307842,0.0045175054,0.006118107,0.0010020555,0.0004969874],"category_scores_gemma":[0.0030327807,0.0017498676,0.0005675584,0.0032898795,0.00084950624,0.0046717166,0.0027110528,0.0020751327,0.004250083],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021481159,0.0020587244,0.021894664,0.00022270947,0.00065116584,0.00030359326,0.03045327,0.00043682463,0.00011771461,0.009759568,0.5907156,0.34317136],"study_design_scores_gemma":[0.012020933,0.0027047626,0.034669038,0.005171902,0.0011853967,0.002248018,0.05211254,0.45715556,0.0011263448,0.003036756,0.41785476,0.010714011],"about_ca_topic_score_codex":0.0010704244,"about_ca_topic_score_gemma":0.00015923247,"teacher_disagreement_score":0.4567187,"about_ca_system_score_codex":0.0010922586,"about_ca_system_score_gemma":0.00637956,"threshold_uncertainty_score":0.999605},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30613428,0.0106827,0.64172673,0.017857673,0.008339044,0.0027038432,0.0043342453,0.0017078421,0.0065136394],"genre_scores_gemma":[0.773609,0.0009825629,0.20944114,0.0065453993,0.0024285694,0.00041705617,0.0015226442,0.0002664691,0.004787197],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99080676,0.0003794444,0.0017996458,0.002154026,0.0016235788,0.0032365455],"domain_scores_gemma":[0.9862338,0.0017821726,0.0008635584,0.0070329644,0.00086296943,0.0032245382],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0036310204,0.0012385679,0.0011273059,0.0006376483,0.0009954283,0.00369955,0.010410609,0.00085517333,0.00046050685],"category_scores_gemma":[0.0029831086,0.0013183589,0.00032167198,0.0026326922,0.0006244349,0.0042002583,0.0041622208,0.0018368488,0.001118375],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012590326,0.0012282279,0.032330036,0.000121981095,0.00048783125,0.0002695005,0.012583106,0.00046548506,0.000018058206,0.0091456575,0.54521346,0.39801073],"study_design_scores_gemma":[0.004391688,0.00056294695,0.08777342,0.001804501,0.0007424566,0.0022838358,0.0126644885,0.5435152,0.00033332375,0.0033714,0.33811605,0.004440668],"about_ca_topic_score_codex":0.00096603535,"about_ca_topic_score_gemma":0.00031335244,"teacher_disagreement_score":0.54304975,"about_ca_system_score_codex":0.0011025616,"about_ca_system_score_gemma":0.009425069,"threshold_uncertainty_score":0.99965936},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00404793,0.000093374285,0.18320398,0.8086362,0.0021062202,0.0005561556,0.00018911541,0.00021504326,0.0009520116],"genre_scores_gemma":[0.24620187,0.00003325048,0.75088584,0.00022536078,0.00049526175,0.00027926423,0.00025542738,0.000011957645,0.0016117863],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998715,0.000013830078,0.00019556296,0.00061596115,0.00018341892,0.00027621572],"domain_scores_gemma":[0.9973231,0.0013369928,0.00007570183,0.0009090493,0.00022976048,0.000125393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029712444,0.00013039653,0.00016003032,0.000436612,0.0002391619,0.00014546684,0.0015146805,0.00009607177,0.00009142542],"category_scores_gemma":[0.0010662654,0.00012405409,0.000013478393,0.00096215593,0.00018031367,0.00028579932,0.00039360276,0.00041600986,0.000041925814],"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":[0.0000024560063,0.000052650492,0.0003669867,0.000004459326,0.000009272304,3.6937246e-7,0.00028346106,7.489931e-8,0.0008110907,0.9226851,0.013121801,0.062662296],"study_design_scores_gemma":[0.00035673432,0.000088639485,0.0016129867,0.00002981229,0.000008836969,0.000016401897,0.00006818817,0.021328649,0.0011409352,0.9683578,0.006767521,0.00022352241],"about_ca_topic_score_codex":0.00003115034,"about_ca_topic_score_gemma":0.00041085723,"teacher_disagreement_score":0.8084108,"about_ca_system_score_codex":0.000013947304,"about_ca_system_score_gemma":0.0011463574,"threshold_uncertainty_score":0.5058779},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002539664,0.00036226813,0.9950578,0.0004923051,0.00035140626,0.00024372371,0.000030718056,0.000047517173,0.0008745943],"genre_scores_gemma":[0.33588362,0.000058594404,0.66335064,0.00037172117,0.00017966458,0.000015801515,0.0000104442015,0.000024321052,0.000105170046],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99724597,0.000026210593,0.00054379104,0.0011098173,0.0006349423,0.00043929298],"domain_scores_gemma":[0.99739885,0.0009544895,0.000319891,0.00102043,0.00015685718,0.00014948072],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00092450087,0.00034248235,0.00047744118,0.0004376375,0.000086816464,0.00026464488,0.0021034365,0.00016594246,0.0000064346227],"category_scores_gemma":[0.00024785672,0.00031700308,0.000046978843,0.0004924745,0.00032789994,0.00052182155,0.0012680221,0.00041763094,0.0000033423762],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016127404,0.000022932394,0.0008365227,0.00003859092,0.000004704119,0.000037025864,0.0018109527,0.003145984,0.00015320373,0.0033637811,0.00001654339,0.99056816],"study_design_scores_gemma":[0.0006506902,0.00021335318,0.0045496523,0.0014858092,0.00000957405,0.000089477646,0.0000054599727,0.94752276,0.0005676712,0.043123122,0.0009312459,0.0008511785],"about_ca_topic_score_codex":0.00021112709,"about_ca_topic_score_gemma":0.00040978342,"teacher_disagreement_score":0.98971695,"about_ca_system_score_codex":0.00018992845,"about_ca_system_score_gemma":0.00042511534,"threshold_uncertainty_score":0.9999282},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012004329,0.000025031311,0.8822278,0.0092993695,0.0016065695,0.00032127777,0.004894011,0.00029808455,0.089323536],"genre_scores_gemma":[0.17871651,0.000023162129,0.81278217,0.0021760226,0.00023627527,0.000046461533,0.004189854,0.000024832074,0.0018047133],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99734664,0.00006208004,0.0003583764,0.0013019854,0.0005773561,0.00035355787],"domain_scores_gemma":[0.9955377,0.00014274457,0.00013625491,0.0038496365,0.00013124518,0.00020244026],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00070184725,0.00022267607,0.00018336294,0.00023532847,0.00015107448,0.00069711776,0.009135109,0.00005593496,0.00038541536],"category_scores_gemma":[0.00050688395,0.00021906578,0.000022419796,0.00039334118,0.00004175567,0.001070845,0.0031466126,0.00018817386,0.00033502403],"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":[0.000012132052,0.00016407996,0.0005104989,0.0000072047983,0.00009144955,0.000065643304,0.0008114833,0.00007214529,0.0014434413,0.09272522,0.18242477,0.72167194],"study_design_scores_gemma":[0.00031912126,0.00011521025,0.00023553692,0.000077986006,0.000010401491,0.00010307981,0.0002456774,0.31724554,0.00013874468,0.0003584495,0.6807603,0.0003899242],"about_ca_topic_score_codex":0.000021234708,"about_ca_topic_score_gemma":0.000062604,"teacher_disagreement_score":0.721282,"about_ca_system_score_codex":0.000037268284,"about_ca_system_score_gemma":0.00037818114,"threshold_uncertainty_score":0.99622595},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003920889,0.0000612089,0.9853263,0.000061014263,0.00012846365,0.0002559934,0.000006079984,0.00034519285,0.009894877],"genre_scores_gemma":[0.018703757,0.000029083758,0.9775316,0.000035558267,0.0001010298,0.00037995641,0.000018317145,0.0000133674075,0.0031873083],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99899334,0.000024127221,0.00022330707,0.0003392593,0.00011703396,0.00030292827],"domain_scores_gemma":[0.99918187,0.0001527877,0.00014871338,0.00027989884,0.00017440817,0.000062334104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007511117,0.000119164084,0.00012743023,0.0000943621,0.00036137525,0.00012103945,0.00058559777,0.000088832574,0.000016557768],"category_scores_gemma":[0.00010210671,0.00011539953,0.00005084668,0.00024926488,0.000014678392,0.0006012524,0.00017481603,0.00013900694,0.00007613797],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011207622,0.00008440929,0.0015270108,0.000023246994,0.000027035698,3.1441874e-7,0.0020676285,0.000015636591,0.0006997404,0.011022427,0.0007285879,0.98380286],"study_design_scores_gemma":[0.00021645192,0.00011117278,0.002827125,0.000059798695,0.000012670009,0.000005476308,0.00016073047,0.9576726,0.018134825,0.0005638729,0.01995226,0.00028300288],"about_ca_topic_score_codex":0.000016547261,"about_ca_topic_score_gemma":0.0000020461111,"teacher_disagreement_score":0.98351985,"about_ca_system_score_codex":0.00007032843,"about_ca_system_score_gemma":0.000057240686,"threshold_uncertainty_score":0.47058564},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82420325,0.000039091552,0.17372946,0.00035188938,0.00034823405,0.00033197712,0.00002565273,0.00004228971,0.0009281742],"genre_scores_gemma":[0.9661448,0.000015895232,0.03372811,0.000035117995,0.000028060582,0.000017218674,0.0000032767562,0.000009681109,0.000017820683],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982653,0.000010422678,0.00064784713,0.00047023536,0.0003988695,0.00020729861],"domain_scores_gemma":[0.999143,0.00011879317,0.00034991058,0.00014730377,0.00018686017,0.00005412748],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064566213,0.00020947601,0.00029911852,0.0003880002,0.0001141107,0.00016582444,0.00030370426,0.000050161878,0.0000013044768],"category_scores_gemma":[0.000041296567,0.00018205258,0.000031402047,0.0002851023,0.00004059972,0.000174092,0.00031944807,0.00017170703,4.6588845e-8],"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":[0.00021500087,0.0011342382,0.024666496,0.0013303164,0.00018724133,0.00021855115,0.001727484,0.18224199,0.0015568848,0.22911343,0.0048011052,0.5528073],"study_design_scores_gemma":[0.0008887813,0.00006754796,0.0070663253,0.000841558,0.000015164865,0.00014674905,0.0006162881,0.9885963,0.00017149889,0.0012847326,0.00011595295,0.00018908868],"about_ca_topic_score_codex":0.024467967,"about_ca_topic_score_gemma":0.021614285,"teacher_disagreement_score":0.80635434,"about_ca_system_score_codex":0.00019051466,"about_ca_system_score_gemma":0.00007229592,"threshold_uncertainty_score":0.9962387},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18199946,0.000024362713,0.8171392,0.00055040134,0.000026326043,0.00012480876,0.000015385653,0.000029453458,0.00009058584],"genre_scores_gemma":[0.011757851,0.000012825076,0.9880244,0.000023792207,0.000008509088,6.15831e-7,0.00008520367,0.000004200901,0.000082593135],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991908,0.000014336324,0.00010963855,0.00029304193,0.00025371602,0.00013844225],"domain_scores_gemma":[0.99909174,0.000053065105,0.00009715302,0.00057143276,0.00006823333,0.00011838375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024431758,0.00006574561,0.00014581275,0.00008429318,0.0001398093,0.000013459493,0.0016851079,0.000052958974,0.000011680666],"category_scores_gemma":[0.00007804072,0.0000786104,0.0000344524,0.00014801725,0.000101296915,0.00038276296,0.0008928003,0.00008202562,0.000007134238],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010159117,0.00021229248,0.0003608263,0.000044731863,0.000025482797,0.000028991752,0.0011533512,0.000035174744,0.0046786857,0.034367505,0.0003383687,0.9587444],"study_design_scores_gemma":[0.00093921396,0.00016845057,0.0053744735,0.00016223022,0.00007373821,0.00002333526,0.00011833195,0.9762995,0.0008122887,0.001292307,0.014467795,0.00026833097],"about_ca_topic_score_codex":0.0013051342,"about_ca_topic_score_gemma":0.000010863098,"teacher_disagreement_score":0.97626436,"about_ca_system_score_codex":0.000027088969,"about_ca_system_score_gemma":0.00017006852,"threshold_uncertainty_score":0.32056388},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.074576974,0.00022674704,0.92269146,0.0019316024,0.00025970154,0.000114377486,0.0000060374477,0.00006246186,0.00013063548],"genre_scores_gemma":[0.8651753,0.000052503292,0.1341514,0.00036079998,0.00012607279,0.00009847501,0.0000053094186,0.0000045865563,0.000025568868],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99911803,0.000039067283,0.00019529274,0.0003561612,0.00009536089,0.00019608586],"domain_scores_gemma":[0.998857,0.0007715048,0.00014291109,0.00009857662,0.0000673223,0.000062644576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022936273,0.00009951494,0.00010704502,0.000023214072,0.00045239477,0.00022830864,0.00018966566,0.00003294626,0.0000013991602],"category_scores_gemma":[0.00020971935,0.00007933738,0.000025920548,0.00011064822,0.000052858533,0.0013593496,0.00014388961,0.000042647283,0.0000020689115],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000065916297,0.000021400225,0.0008367224,0.000009475156,0.000011324913,0.0000025069473,0.008457304,0.000006302376,0.000060433456,0.02405465,0.0005750544,0.96595824],"study_design_scores_gemma":[0.0073851794,0.0012381267,0.024388423,0.001139737,0.00017658542,0.00036781593,0.027774526,0.71218526,0.00030488044,0.034328964,0.18797737,0.0027331396],"about_ca_topic_score_codex":0.000007277884,"about_ca_topic_score_gemma":9.927331e-7,"teacher_disagreement_score":0.96322507,"about_ca_system_score_codex":0.000007487795,"about_ca_system_score_gemma":0.000025628899,"threshold_uncertainty_score":0.34795004},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08527348,0.00008043012,0.89586955,0.0025525822,0.00007442925,0.00027860966,0.00031751566,0.00015126698,0.015402161],"genre_scores_gemma":[0.36241114,0.00017396268,0.63235414,0.000019226902,0.00006398063,7.329181e-7,0.0006783479,0.000007598726,0.004290859],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99845064,0.0001535859,0.00009832264,0.00047368312,0.0005846672,0.00023909418],"domain_scores_gemma":[0.99808455,0.00052709127,0.00006723399,0.0010551488,0.00017762888,0.00008837133],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005348069,0.000066177905,0.00012108904,0.000107968364,0.0008631767,0.000030454124,0.0026979183,0.000053028027,0.00011039287],"category_scores_gemma":[0.00020117137,0.000078387675,0.000033749082,0.00056971423,0.0002833642,0.0012968894,0.0017117775,0.00035042502,0.00029955604],"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":[0.000011555002,0.0012117019,0.2556514,0.000046458386,0.0002587948,0.0003479045,0.02555728,0.0014967489,0.0039437152,0.17542787,0.22658162,0.30946496],"study_design_scores_gemma":[0.00043068978,0.00004475319,0.08377941,0.0000124339085,0.0000026816217,0.0000044272383,0.0005852463,0.44581133,0.000062524494,0.000586765,0.46857607,0.00010365993],"about_ca_topic_score_codex":0.0011326249,"about_ca_topic_score_gemma":0.00025130084,"teacher_disagreement_score":0.4443146,"about_ca_system_score_codex":0.000033985067,"about_ca_system_score_gemma":0.00012875353,"threshold_uncertainty_score":0.6638945},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002602857,0.0005357237,0.9633302,0.00057387736,0.0014169195,0.0011173072,0.0035546666,0.00009960547,0.029111426],"genre_scores_gemma":[0.01633317,0.0003342521,0.47459003,0.0017259031,0.0042491416,0.0011488366,0.0035656975,0.0004536463,0.49759933],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970186,0.000029909013,0.00065200875,0.0013163784,0.0004468101,0.0005363097],"domain_scores_gemma":[0.9976611,0.00032885073,0.00030720074,0.0014628237,0.00008719158,0.00015279242],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004274112,0.00045403445,0.00041654496,0.00022886833,0.00018347212,0.0006023614,0.0023550405,0.00022594655,0.000039303344],"category_scores_gemma":[0.00014290996,0.0004675863,0.00005670326,0.00008548951,0.00008139727,0.00032417805,0.0011564804,0.0005055939,0.0000127071735],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020422623,0.000092820155,0.00016724369,0.000255384,0.00020937814,0.000093040646,0.0013042896,0.00029037354,0.00013002173,0.009508191,0.05694697,0.9309819],"study_design_scores_gemma":[0.0003751251,0.00006104894,0.00024470812,0.0016961426,0.000086849024,0.000039435454,0.00012197131,0.23057763,0.00084105605,0.005465772,0.7586119,0.0018783282],"about_ca_topic_score_codex":0.005071629,"about_ca_topic_score_gemma":0.20313585,"teacher_disagreement_score":0.92910355,"about_ca_system_score_codex":0.0002765553,"about_ca_system_score_gemma":0.0014281682,"threshold_uncertainty_score":0.99977756},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027677137,0.000016223745,0.9697234,0.0006492899,0.000009107772,0.000026972803,0.0000031866048,0.000104323386,0.0017903562],"genre_scores_gemma":[0.22634919,0.000003933328,0.77316755,0.00007638965,0.00001738506,0.000009187391,0.000015166409,0.000003974747,0.00035720845],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994982,0.000019285082,0.000065456676,0.00020875453,0.0000836532,0.00012464594],"domain_scores_gemma":[0.99953073,0.00021297735,0.000020417914,0.00015801571,0.000020806918,0.000057051693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012159347,0.000057669407,0.000066905246,0.000020085863,0.00014073985,0.00016374428,0.00016599397,0.000013523593,0.000011781567],"category_scores_gemma":[0.000043963944,0.00004113753,0.000004204217,0.000077743716,0.0000447914,0.00016352591,0.00011492246,0.000052922613,0.00002169234],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.7766666e-7,0.000017538936,0.010794859,0.000004197601,0.0000052195082,8.760962e-7,0.00016269159,0.0000321547,0.000015065376,0.43858856,0.0007011751,0.54967695],"study_design_scores_gemma":[0.0002612538,0.0001752841,0.038204588,0.00001382777,0.0000056767144,0.000021172038,0.00012391782,0.88141334,0.000044262782,0.0019067063,0.07764014,0.0001898343],"about_ca_topic_score_codex":0.000030333662,"about_ca_topic_score_gemma":0.000009499923,"teacher_disagreement_score":0.8813812,"about_ca_system_score_codex":0.0000023253176,"about_ca_system_score_gemma":0.000008601513,"threshold_uncertainty_score":0.16775398},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008073502,0.00044991195,0.9962385,0.0009783569,0.0001526098,0.00057913706,0.000662729,0.00008538738,0.000046002013],"genre_scores_gemma":[0.04049643,0.000053909247,0.9583514,0.000426606,0.00010156928,0.000047979673,0.0004225675,0.000029460785,0.00007008115],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965596,0.000014859996,0.00042194338,0.0019284987,0.0006730652,0.00040198924],"domain_scores_gemma":[0.9976721,0.000232425,0.00020451032,0.0014669653,0.00015639196,0.00026761435],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007665659,0.0003809045,0.00034888106,0.00040569116,0.00023981972,0.00045594745,0.0022211238,0.000099103025,0.0000025236943],"category_scores_gemma":[0.00005254182,0.00037114436,0.000018224002,0.00038796704,0.00016334679,0.0011469506,0.0017011272,0.0002821389,0.0000048904158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002470275,0.000032162883,0.000041967938,0.00006508477,0.000010956161,0.0000069700022,0.0007983337,0.0028372481,0.00018442591,0.0039473483,0.000022616148,0.9920504],"study_design_scores_gemma":[0.00022007436,0.00008304308,0.000101148325,0.0004122037,0.000016677126,0.00010505882,0.00000326156,0.99341327,0.000027956054,0.0030281818,0.0021408794,0.00044825836],"about_ca_topic_score_codex":0.00007002366,"about_ca_topic_score_gemma":0.00026337392,"teacher_disagreement_score":0.9916022,"about_ca_system_score_codex":0.00010677199,"about_ca_system_score_gemma":0.000290361,"threshold_uncertainty_score":0.99987406},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5755648,0.000014451373,0.4207076,0.0015109634,0.00013621016,0.000059020997,0.00040074228,0.00005360494,0.0015525849],"genre_scores_gemma":[0.76010466,0.000013974368,0.23945956,0.000028613378,0.00008664422,9.2414275e-8,0.00015932968,0.000004533997,0.00014259398],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99938864,0.00003369837,0.000059402235,0.0002448982,0.00017158965,0.000101805235],"domain_scores_gemma":[0.9990537,0.0000762031,0.00013229878,0.00064962025,0.000055133223,0.000033005952],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014348085,0.00005977233,0.00013590806,0.000058637517,0.00018427595,0.000024475476,0.0017066925,0.000040426057,0.0000075000116],"category_scores_gemma":[0.000016051128,0.00007822552,0.00003327372,0.00015122518,0.0001188381,0.00040338113,0.0012718919,0.00005174391,0.000018174564],"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":[0.000057115103,0.0007747048,0.08507552,0.00017898454,0.00050978106,0.00003319483,0.020259837,0.00007781193,0.0078276675,0.15361887,0.21328875,0.51829773],"study_design_scores_gemma":[0.0015571268,0.0001361933,0.47456747,0.00009112149,0.00014690042,0.0000016864706,0.04152541,0.32830638,0.00041315472,0.001857889,0.15088496,0.00051172933],"about_ca_topic_score_codex":0.0032170415,"about_ca_topic_score_gemma":0.015661487,"teacher_disagreement_score":0.517786,"about_ca_system_score_codex":0.000012182169,"about_ca_system_score_gemma":0.000024044753,"threshold_uncertainty_score":0.87394774},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.51068324,0.0046548685,0.04501784,0.19514908,0.004081323,0.00888078,0.0034063917,0.04351965,0.18460682],"genre_scores_gemma":[0.8107949,0.0009418597,0.18537322,0.0019665128,0.00016542255,0.00032846074,0.00025539147,0.00006352161,0.00011072214],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9937767,0.00010913428,0.0011640898,0.0025477856,0.0012882708,0.0011140662],"domain_scores_gemma":[0.9917956,0.00049397146,0.00029721842,0.0068729077,0.00013146571,0.00040880864],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0008915825,0.0007370764,0.0010179888,0.00067573605,0.00075426203,0.0005142507,0.0067537096,0.00040982163,0.0001461098],"category_scores_gemma":[0.00070363114,0.0006384296,0.00045766635,0.008436138,0.00089426123,0.004195169,0.0037907192,0.0011000428,0.00032315808],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010432375,0.0029680314,0.00020953832,0.00007516707,0.0008114779,0.00017879962,0.00028005446,0.00059788616,0.588925,0.29698274,0.010634272,0.0982327],"study_design_scores_gemma":[0.000845121,0.0007963841,0.8778646,0.0001110813,0.00035385354,0.0000864067,0.000111805195,0.000005517217,0.00010751388,0.0057238187,0.11292302,0.0010708607],"about_ca_topic_score_codex":0.00028176754,"about_ca_topic_score_gemma":0.029470421,"teacher_disagreement_score":0.8776551,"about_ca_system_score_codex":0.00031854672,"about_ca_system_score_gemma":0.00015565063,"threshold_uncertainty_score":0.9996067},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009815131,0.00013092191,0.9877447,0.0006597238,0.00016200055,0.000295253,0.0007282076,0.00021398222,0.0002500879],"genre_scores_gemma":[0.027088197,0.000028259125,0.9708805,0.00040600245,0.00011138455,0.00007086964,0.0013056064,0.000014062167,0.000095089876],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980697,0.000060599523,0.0003912594,0.0008818918,0.00020570554,0.0003908116],"domain_scores_gemma":[0.99760675,0.00023355382,0.00011018693,0.0018007347,0.000106562286,0.000142207],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005779234,0.00018409213,0.00020459022,0.00014956121,0.00024252309,0.00017034527,0.0026625465,0.000060650313,0.00003416485],"category_scores_gemma":[0.00006685081,0.00016670141,0.000031638378,0.0005392133,0.00007511386,0.0018760217,0.00023136294,0.000107998756,0.0000074028057],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.898358e-7,0.00038500477,0.0012083525,0.000007991974,0.000009631834,0.000036239657,0.00028687294,0.00012034619,0.0006828497,0.00170708,0.0019478608,0.993607],"study_design_scores_gemma":[0.0003868671,0.00010380546,0.0026255373,0.000022872258,0.000004073702,0.00001334559,0.0001247506,0.99474007,0.00037941875,0.0006058487,0.0007554368,0.0002379674],"about_ca_topic_score_codex":0.0011537076,"about_ca_topic_score_gemma":0.0005176026,"teacher_disagreement_score":0.9946197,"about_ca_system_score_codex":0.000054588378,"about_ca_system_score_gemma":0.00033094452,"threshold_uncertainty_score":0.67978865},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0055171335,0.00010178772,0.9933375,0.000012990047,0.000052600422,0.00004904926,0.00015143266,0.000018618595,0.0007588501],"genre_scores_gemma":[0.67390096,0.000012363467,0.3259216,0.000007796111,0.0000050722288,0.0000037118984,0.0000025573065,0.0000028365275,0.00014310131],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996439,0.000007080557,0.000088332985,0.00013127476,0.000059244117,0.00007015937],"domain_scores_gemma":[0.9996802,0.000019904328,0.000053762542,0.00014473304,0.00006873547,0.000032658445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000045458502,0.00004952153,0.000061866514,0.000023172737,0.00003800453,0.000022591012,0.00016057542,0.000013626835,0.000012474112],"category_scores_gemma":[0.000011216639,0.00003931869,0.0000040804402,0.00007938015,0.000024795909,0.00010873962,0.00006514362,0.00004002726,0.000006306045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039784638,0.00022321501,0.0003705851,0.00012499574,0.000083221865,0.00001149924,0.009421668,0.00004258683,0.013371791,0.50354695,0.0025980033,0.47016567],"study_design_scores_gemma":[0.0005386065,0.0013050139,0.0049564773,0.00009228911,0.000022558217,0.000050278282,0.0004085444,0.68666285,0.27808028,0.014187604,0.013288576,0.0004069367],"about_ca_topic_score_codex":0.000033936347,"about_ca_topic_score_gemma":0.0000080127365,"teacher_disagreement_score":0.68662024,"about_ca_system_score_codex":0.0000033069,"about_ca_system_score_gemma":0.000010681554,"threshold_uncertainty_score":0.16033697},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012925352,0.0004833183,0.98209184,0.001251708,0.014317609,0.0006442067,0.000022807933,0.00027942043,0.0008961305],"genre_scores_gemma":[0.0029330363,0.00002126282,0.99226165,0.0012783479,0.0018634278,0.000178714,0.00010961355,0.00004634984,0.0013076208],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950192,0.00007285987,0.000524374,0.002065757,0.0011435961,0.0011742348],"domain_scores_gemma":[0.99657273,0.0005932478,0.0002772451,0.0015565525,0.00056579895,0.0004343945],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.002410319,0.0004979222,0.00061712967,0.0015800248,0.0006368515,0.0017767664,0.005739487,0.0003499015,0.0000036884494],"category_scores_gemma":[0.0012250843,0.00047131084,0.000115361865,0.0070773545,0.00022708837,0.0008542234,0.001636235,0.0013013243,0.00007753668],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022001286,0.000052199983,0.000023674032,0.000045654222,0.00000797835,0.000007968845,0.00067431864,0.07127923,0.000046512225,0.00017914736,0.29030043,0.63738066],"study_design_scores_gemma":[0.00017206755,0.00020064965,0.000039514493,0.0001732171,0.000006248761,0.000019331723,0.00000101954,0.8228055,0.0003194292,0.0040007727,0.17175,0.00051220454],"about_ca_topic_score_codex":0.00007688664,"about_ca_topic_score_gemma":0.000025065365,"teacher_disagreement_score":0.7515263,"about_ca_system_score_codex":0.0004468164,"about_ca_system_score_gemma":0.0014944527,"threshold_uncertainty_score":0.99977386},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000033992478,0.00019500326,0.9179089,0.001674556,0.0004975987,0.00028247345,0.000088100984,0.000567717,0.07878225],"genre_scores_gemma":[0.0010214098,0.000070320675,0.845912,0.005624068,0.0063364273,0.00016638551,0.00029717325,0.00030549458,0.14026673],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963511,0.0001786798,0.0005477634,0.0015958479,0.00066252175,0.00066408573],"domain_scores_gemma":[0.9948284,0.0015564985,0.00039312453,0.0028391837,0.00010601724,0.0002767655],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036448205,0.0008596439,0.0009186754,0.00075899385,0.00036760952,0.0006390092,0.0037360669,0.00050490204,0.0000494092],"category_scores_gemma":[0.000077869816,0.00071787497,0.0004976707,0.0003877359,0.00012495153,0.00008510739,0.000757301,0.0013367536,0.00033805796],"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":[0.0000044261565,0.000042892585,0.0000011447622,0.00006562961,0.00020885245,0.000022498325,0.00012141578,0.0065847333,0.0000063711477,0.018496519,0.16998644,0.8044591],"study_design_scores_gemma":[0.00012731754,0.00016351462,0.000048863225,0.00048227122,0.00011463461,0.000062848674,3.0778494e-7,0.113266975,0.00022384868,0.030393332,0.85406077,0.00105531],"about_ca_topic_score_codex":0.0000051690695,"about_ca_topic_score_gemma":0.000016733877,"teacher_disagreement_score":0.80340374,"about_ca_system_score_codex":0.00017489937,"about_ca_system_score_gemma":0.00030010397,"threshold_uncertainty_score":0.9995272},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9661162,0.000093666866,0.008952887,0.019932773,0.000079380225,0.00032588068,0.000437286,0.00007199875,0.00398994],"genre_scores_gemma":[0.93066484,0.000008265668,0.06903344,0.00017540224,0.00004518042,0.000010426156,5.699464e-7,0.0000021488925,0.000059728085],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99837035,0.0000061082305,0.00031524542,0.00027865506,0.0008296573,0.00019997987],"domain_scores_gemma":[0.9989746,0.0003522057,0.00049901044,0.000015938142,0.00013258401,0.000025648758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027278294,0.00006620826,0.00010439034,0.00014638921,0.00019610107,0.000052389805,0.0012440822,0.00005182555,0.000003492007],"category_scores_gemma":[0.0010793029,0.000041360723,0.000030371108,0.00091936375,0.00010216293,0.0012522606,0.00041799014,0.000080949845,0.000002757348],"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":[0.000004851933,0.0002196126,0.16544278,0.000063708634,0.000023643332,2.3051978e-8,0.0010722307,0.000056972505,0.47782627,0.2740455,0.004797349,0.076447085],"study_design_scores_gemma":[0.0008760278,0.00005414042,0.6179377,0.0007277145,0.0000126985115,0.000015383124,0.00023766403,0.07291115,0.1508969,0.15138143,0.004544479,0.00040470177],"about_ca_topic_score_codex":0.000006138262,"about_ca_topic_score_gemma":1.7304133e-7,"teacher_disagreement_score":0.45249492,"about_ca_system_score_codex":0.00007219699,"about_ca_system_score_gemma":0.000030928946,"threshold_uncertainty_score":0.23118351},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013966666,0.00004485347,0.98198897,0.0030585025,0.00018530001,0.00018426879,0.00004714885,0.00020628952,0.00031802643],"genre_scores_gemma":[0.4839947,0.000019455392,0.5149883,0.00018762259,0.000052897936,0.00005777961,0.0000013604631,0.0000138294145,0.000684074],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986737,0.000080775964,0.00018377187,0.00041338676,0.00028587217,0.00036250157],"domain_scores_gemma":[0.99893236,0.0002863435,0.000039033544,0.00049459527,0.00006912697,0.00017853276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018735904,0.00012009653,0.00013939587,0.00018094051,0.0003844265,0.00013683428,0.00041120144,0.000038042243,0.00006114543],"category_scores_gemma":[0.00001807892,0.000089514295,0.000037804213,0.0009150831,0.00017182268,0.00032360476,0.000027939157,0.00018698997,0.00008860177],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.696227e-7,0.000025313006,0.000003554504,0.0000031443515,0.000011867506,0.000003356308,0.0007660853,0.00002347156,0.02247698,0.0000519301,0.00015959292,0.9764741],"study_design_scores_gemma":[0.00037836935,0.00011463113,0.0018088474,0.00011289933,0.000019249563,0.000049047816,0.0005554651,0.97994065,0.004006818,0.0001346352,0.0125007415,0.00037866159],"about_ca_topic_score_codex":0.00024599372,"about_ca_topic_score_gemma":0.000018423054,"teacher_disagreement_score":0.97991717,"about_ca_system_score_codex":0.000069483795,"about_ca_system_score_gemma":0.000065928565,"threshold_uncertainty_score":0.36502868},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035053873,0.00012680369,0.99312264,0.00031456546,0.0000128360925,0.00048048608,0.00007145441,0.000099060795,0.0022667653],"genre_scores_gemma":[0.027129563,0.000015214534,0.9722688,0.00011335822,0.00013610585,0.00013163296,0.000100179015,0.000014814272,0.00009028523],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99766463,0.000054456108,0.00050556473,0.00094823394,0.00037337307,0.00045376946],"domain_scores_gemma":[0.9970082,0.0005162858,0.00012576208,0.0020799665,0.00016819926,0.00010156231],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002687035,0.0001370439,0.00018081434,0.00055673823,0.00022291722,0.00015759552,0.0035868273,0.0000777096,0.0000038796156],"category_scores_gemma":[0.0000030636093,0.00014315393,0.000026855949,0.0022714045,0.00011947819,0.00055809435,0.0014925,0.00030060235,0.00006221061],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011535097,0.0002572718,0.000093121875,0.000014780839,0.000005599474,0.0000024956075,0.00035233793,0.000023898185,0.0020942632,0.0050611575,0.0014284954,0.99066544],"study_design_scores_gemma":[0.00075227855,0.00009103993,0.005689679,0.00021166547,0.0000071187637,0.00003509345,0.00041141195,0.4488587,0.009557792,0.0024236685,0.5314825,0.00047899393],"about_ca_topic_score_codex":0.00003840037,"about_ca_topic_score_gemma":0.00003686271,"teacher_disagreement_score":0.99018645,"about_ca_system_score_codex":0.00005991514,"about_ca_system_score_gemma":0.0001456247,"threshold_uncertainty_score":0.6665277},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011268624,0.00012024719,0.9863174,0.0006368688,0.0000061144915,0.001337187,0.00006465474,0.00009011772,0.00015879972],"genre_scores_gemma":[0.14876547,0.000019816216,0.85058326,0.000051550407,0.00007423936,0.0004170737,0.000057423156,0.000007313558,0.000023871105],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983578,0.0000501337,0.00041175037,0.0006304206,0.00029121237,0.00025872886],"domain_scores_gemma":[0.99878794,0.000094341965,0.00010154869,0.0007369541,0.00019224598,0.00008695838],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004235262,0.00013392202,0.00017356388,0.00038929918,0.00017644149,0.000113146096,0.0008467013,0.0001050411,0.0000015562147],"category_scores_gemma":[0.0000022158406,0.00013435645,0.000028511413,0.0014459478,0.00008117699,0.00034300215,0.00022458499,0.00025621892,0.000009960542],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014542575,0.00012387402,0.000055259305,0.0000066746825,0.0000024246422,3.4745017e-7,0.00018018155,0.000024423487,0.03084478,0.021389235,0.00034139203,0.94702995],"study_design_scores_gemma":[0.0012822138,0.0002916895,0.056578252,0.00013917248,0.000009487541,0.00007051778,0.00006139911,0.56101966,0.027428038,0.21110111,0.14154495,0.00047351958],"about_ca_topic_score_codex":0.00003702027,"about_ca_topic_score_gemma":0.0000115833955,"teacher_disagreement_score":0.94655645,"about_ca_system_score_codex":0.00005524033,"about_ca_system_score_gemma":0.000052576383,"threshold_uncertainty_score":0.5478897},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045150653,0.000008814704,0.98510337,0.00028118628,0.000015499332,0.0004562646,0.000094949195,0.00013158427,0.009393297],"genre_scores_gemma":[0.27282867,0.000012013224,0.72605205,0.00021781924,0.00007695228,0.0005468543,0.00011187843,0.000013266277,0.00014051948],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979975,0.00010307892,0.00036972642,0.00064142444,0.0005244845,0.00036376985],"domain_scores_gemma":[0.9978933,0.00026758818,0.00021177078,0.001029066,0.00049198075,0.000106321786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008581838,0.00016316546,0.00023095019,0.0007670509,0.0003131157,0.00011211516,0.0014522909,0.00010074208,0.000026329011],"category_scores_gemma":[0.0000014002843,0.00015931105,0.00012500689,0.0035808992,0.000058710844,0.00017893511,0.00016352448,0.00030269873,0.00029362144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000140697,0.0032043955,0.0032890604,0.00006373944,0.00048647108,0.0000022591018,0.0009020044,0.00206578,0.00081454567,0.18432122,0.00454586,0.8002906],"study_design_scores_gemma":[0.0003920783,0.00034515912,0.025916971,0.000028675602,0.0000805846,0.0000011380719,0.00004543848,0.9467732,0.012088224,0.0031861302,0.010805565,0.00033688755],"about_ca_topic_score_codex":0.0000797461,"about_ca_topic_score_gemma":0.0000037122386,"teacher_disagreement_score":0.9447074,"about_ca_system_score_codex":0.00014378378,"about_ca_system_score_gemma":0.00010209983,"threshold_uncertainty_score":0.64965165},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025023373,0.00010186332,0.99546355,0.00066359807,0.000010476052,0.0006393248,0.00012853909,0.00016051058,0.00032982338],"genre_scores_gemma":[0.14044306,0.000049726186,0.85827726,0.00024189279,0.00009977812,0.00047361947,0.00036707325,0.000015113387,0.000032495802],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983893,0.000030839255,0.00047572967,0.0006936334,0.0001749143,0.00023560147],"domain_scores_gemma":[0.99732095,0.00009941494,0.00016004547,0.0022569983,0.00008618253,0.00007639071],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002100519,0.00014832306,0.00021748434,0.0001852777,0.00017045853,0.00003609743,0.0034393903,0.000070963084,0.0000031565287],"category_scores_gemma":[9.919331e-7,0.00016069047,0.00003804594,0.0010100189,0.00011071713,0.00061213813,0.001111391,0.00015968976,0.000101472266],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011878332,0.00037167832,0.0021544679,0.000013033861,0.0000085894835,0.0000012945587,0.00035626563,0.00007179845,0.001119049,0.015385589,0.0041050785,0.97641194],"study_design_scores_gemma":[0.0006652445,0.00002776606,0.071266964,0.000016225697,0.00000922831,0.0000765345,0.0000093291565,0.20231615,0.0016209447,0.0012788408,0.7223183,0.00039448432],"about_ca_topic_score_codex":0.00020331053,"about_ca_topic_score_gemma":0.00004063447,"teacher_disagreement_score":0.9760175,"about_ca_system_score_codex":0.000033325778,"about_ca_system_score_gemma":0.0000911588,"threshold_uncertainty_score":0.6552767},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002161329,0.000021196482,0.99318427,0.0028641198,0.000024793568,0.00047567266,0.00006906828,0.0001872707,0.0010122954],"genre_scores_gemma":[0.054624204,0.0000043792897,0.94335175,0.0013578625,0.00015188151,0.00026643183,0.00008994951,0.000009597692,0.00014395316],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998653,0.000017912716,0.00035210385,0.00045953595,0.00026809506,0.00024935976],"domain_scores_gemma":[0.9986918,0.00013734262,0.00025695594,0.0006876177,0.00014722237,0.00007906611],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002294946,0.00015517944,0.0001787844,0.00014644975,0.00016712534,0.00012522956,0.00087955926,0.000068599205,0.000006200254],"category_scores_gemma":[0.0000021929789,0.00015859683,0.00008406037,0.00046779084,0.000016033686,0.00016782919,0.00008473224,0.00010277382,0.000069723326],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012829959,0.00041320024,0.00006676798,0.000007884161,0.0000130826475,3.0767978e-7,0.00011850998,0.00019284169,0.01112367,0.017987533,0.0047984747,0.9652764],"study_design_scores_gemma":[0.0012630357,0.0006299041,0.019654706,0.00008269788,0.00003891271,0.000004136308,0.000025562014,0.5074135,0.051592547,0.004534726,0.41403177,0.00072849076],"about_ca_topic_score_codex":0.000008556485,"about_ca_topic_score_gemma":7.416608e-7,"teacher_disagreement_score":0.96454793,"about_ca_system_score_codex":0.00012416724,"about_ca_system_score_gemma":0.00006516182,"threshold_uncertainty_score":0.6467391},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14017335,0.00002111299,0.8533427,0.0010173818,0.00036743784,0.0001526743,0.000036417223,0.0005309064,0.0043580006],"genre_scores_gemma":[0.33094802,0.0000044736025,0.6683395,0.000033149645,0.00009998702,3.2159318e-7,0.000020156018,0.000012774279,0.0005416448],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987649,0.000025372818,0.00012925857,0.0005896971,0.00012621855,0.0003645807],"domain_scores_gemma":[0.99781394,0.00008284243,0.00013946665,0.0017438028,0.00010403188,0.00011592954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001953532,0.00015905453,0.00016525133,0.00056436384,0.00054760993,0.00020108414,0.0030423724,0.000121498124,0.000011790814],"category_scores_gemma":[0.00007365449,0.00018143895,0.000030391802,0.0019190906,0.00017671223,0.0012381314,0.0027262052,0.00036593532,0.00004568692],"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":[0.000007872587,0.0002267633,0.0014151525,0.000030379524,0.00007294651,0.00011687617,0.001238918,0.00020823488,0.09131919,0.7953299,0.0027031114,0.107330605],"study_design_scores_gemma":[0.00032735546,0.000020273932,0.00028717692,0.000030699557,0.000023553044,0.000051951836,0.00039500234,0.42402887,0.0018777145,0.0005399895,0.5720885,0.00032892512],"about_ca_topic_score_codex":0.000092532915,"about_ca_topic_score_gemma":0.00030367193,"teacher_disagreement_score":0.79478997,"about_ca_system_score_codex":0.00006672134,"about_ca_system_score_gemma":0.00019324652,"threshold_uncertainty_score":0.7398866},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00031745867,0.0000038083276,0.99414724,0.0011580285,0.00009743477,0.000115704366,0.0001064782,0.00023584337,0.0038180104],"genre_scores_gemma":[0.0049009463,0.0000024515375,0.9923918,0.0012744613,0.00006670062,0.000023031202,0.00028614083,0.00000965102,0.0010448144],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985779,0.000021520009,0.00021644252,0.000629732,0.00027472497,0.00027970277],"domain_scores_gemma":[0.9978519,0.00009701698,0.00006207398,0.0018378528,0.000034522818,0.000116631934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003891397,0.00012512098,0.00010918499,0.00007173533,0.00017543482,0.00019730593,0.001528928,0.00003323837,0.00008803927],"category_scores_gemma":[0.000033151697,0.00010976387,0.000025087485,0.0003540885,0.000019092708,0.00040320816,0.00057751714,0.000080634774,0.00014047974],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.8019643e-7,0.00013513015,0.00022003215,0.000001532051,0.000005127237,0.000024037825,0.00006563382,0.00019699964,0.00003958655,0.00042369342,0.006319822,0.9925679],"study_design_scores_gemma":[0.00028614813,0.000042171603,0.00056918664,0.000012293281,0.0000035140226,0.000010801848,0.000040111227,0.9548634,0.00008331215,0.000010641241,0.04393292,0.00014549776],"about_ca_topic_score_codex":0.00007156395,"about_ca_topic_score_gemma":0.000012584983,"teacher_disagreement_score":0.9924224,"about_ca_system_score_codex":0.000026930662,"about_ca_system_score_gemma":0.000072616815,"threshold_uncertainty_score":0.44760406},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018735062,0.00008284233,0.97869205,0.00076578505,0.000018267872,0.0004822776,0.00014934235,0.00013842531,0.0009359619],"genre_scores_gemma":[0.0507868,0.000040598363,0.9480262,0.00014197738,0.00005671532,0.00040212332,0.000086179316,0.0000097710235,0.00044968506],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988076,0.000031459833,0.00035991755,0.00039361423,0.00019995584,0.00020746415],"domain_scores_gemma":[0.99878865,0.00018649662,0.00027770293,0.0005019053,0.00019728232,0.000047967078],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016610502,0.00012918487,0.00019225528,0.00010242113,0.00022923946,0.000083848594,0.00080545014,0.000060162813,0.000002891606],"category_scores_gemma":[0.0000029186872,0.0001291585,0.00008171166,0.0004400735,0.00010396768,0.0005278728,0.00022621446,0.0001100095,0.00013445623],"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":[0.000002317825,0.00035555416,0.0035975846,0.000036201935,0.00011029263,0.0000023760067,0.0017062064,0.00004027991,0.023100223,0.8288676,0.01102172,0.13115965],"study_design_scores_gemma":[0.0025028014,0.00036965692,0.11743608,0.00015506774,0.0001077908,0.00031259633,0.0003827241,0.080718525,0.1140544,0.038991053,0.6428132,0.0021560832],"about_ca_topic_score_codex":0.000030778207,"about_ca_topic_score_gemma":0.0000020652533,"teacher_disagreement_score":0.7898765,"about_ca_system_score_codex":0.00007307852,"about_ca_system_score_gemma":0.00011559061,"threshold_uncertainty_score":0.5266931},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9008703,0.000009239662,0.09770349,0.000439042,0.00009558225,0.00007027439,0.00000483938,0.000012997714,0.00079422374],"genre_scores_gemma":[0.89570475,0.000008140708,0.104153164,0.000006966519,0.00002803974,6.3021254e-8,0.0000036879635,0.000002482284,0.00009273751],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990567,0.00014993112,0.00018229522,0.00013752597,0.00036514676,0.00010838605],"domain_scores_gemma":[0.99853164,0.00013906958,0.0006724789,0.00021470482,0.0003802453,0.00006188083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022842323,0.00006189454,0.00013428382,0.0003251235,0.00009012377,0.000024605335,0.0006972483,0.000097629,0.000006536164],"category_scores_gemma":[0.00025152558,0.00007319468,0.0000600257,0.00051425025,0.000027297581,0.001052776,0.00009001122,0.00038482633,0.0000023827308],"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":[0.0000427553,0.0004281441,0.5254579,0.000012563008,0.00009935974,0.000020336694,0.007872449,0.00056748965,0.026354652,0.01686141,0.0008391066,0.42144385],"study_design_scores_gemma":[0.0021700463,0.00011001282,0.8784701,0.000060766986,0.00011242701,0.000019519392,0.002695076,0.09503764,0.0011179879,0.0010424583,0.01891836,0.0002455935],"about_ca_topic_score_codex":0.00007652835,"about_ca_topic_score_gemma":0.000057909263,"teacher_disagreement_score":0.42119825,"about_ca_system_score_codex":0.0003704557,"about_ca_system_score_gemma":0.0002016334,"threshold_uncertainty_score":0.29847923},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017839354,0.00018849422,0.9689141,0.011181195,0.000008870826,0.00067313784,0.000026452553,0.00020815872,0.0009602323],"genre_scores_gemma":[0.10065253,0.000023273491,0.8982692,0.0002563821,0.00010767234,0.0005371494,0.00001578371,0.000012827718,0.00012521059],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986929,0.000018867913,0.00027147308,0.00054733234,0.00018814046,0.00028128573],"domain_scores_gemma":[0.99871296,0.000101046535,0.00007565832,0.0007946533,0.00023986542,0.00007583446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027129415,0.00011642831,0.00014703909,0.00041313676,0.00026914707,0.00012019367,0.0010200064,0.00007966109,0.000004012711],"category_scores_gemma":[0.0000014641472,0.00011480178,0.0000212771,0.0012870681,0.00018900537,0.00017257624,0.00051231333,0.00022564025,0.0000890428],"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":[5.7777214e-7,0.00022735875,0.00027376652,0.000010569369,0.000010082664,4.9354867e-7,0.00019704053,0.000016956961,0.0046365676,0.1804747,0.0035502105,0.8106017],"study_design_scores_gemma":[0.00039950025,0.00020324548,0.0019624452,0.000058286845,0.00000521065,0.000067238325,0.00006191937,0.009364329,0.036054272,0.019869147,0.93167126,0.0002831319],"about_ca_topic_score_codex":0.000009904499,"about_ca_topic_score_gemma":0.0000035610656,"teacher_disagreement_score":0.9281211,"about_ca_system_score_codex":0.000045449728,"about_ca_system_score_gemma":0.00004794403,"threshold_uncertainty_score":0.46814805},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81330603,0.000022496488,0.18515375,0.0009963686,0.00018500643,0.000044761393,0.000069877584,0.000050613533,0.0001710575],"genre_scores_gemma":[0.8877237,0.000023188575,0.11216822,0.000024966908,0.00002608227,4.451705e-8,0.0000024627273,0.0000018790794,0.000029455128],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.999048,0.00001384764,0.00015450794,0.0002549549,0.00029173077,0.0002369648],"domain_scores_gemma":[0.9988999,0.000023181496,0.00038952887,0.00034106598,0.00024273958,0.00010362192],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044536378,0.000068508845,0.00011730008,0.00032365936,0.00022048458,0.0000735226,0.002073114,0.00007360984,0.000006264148],"category_scores_gemma":[0.00014497446,0.000063242085,0.000015767704,0.00072538434,0.00013230352,0.0015915057,0.00071995775,0.00016497573,0.0000024842818],"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":[0.000026819203,0.00028355338,0.6318448,0.0000071349523,0.0001423468,0.0002448261,0.01336922,0.0000031106506,0.0035205632,0.025784062,0.0009617119,0.32381183],"study_design_scores_gemma":[0.002680307,0.00046604572,0.8636218,0.00018011198,0.00018209417,0.000074801166,0.011611235,0.08796755,0.007924344,0.0044776103,0.020080216,0.000733936],"about_ca_topic_score_codex":0.00013165407,"about_ca_topic_score_gemma":0.000009104872,"teacher_disagreement_score":0.3230779,"about_ca_system_score_codex":0.00010146256,"about_ca_system_score_gemma":0.00019954238,"threshold_uncertainty_score":0.3852396},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029950803,0.00006917083,0.9862082,0.001412593,0.00003971891,0.00060477003,0.00017658592,0.00084913184,0.00764476],"genre_scores_gemma":[0.16623694,0.0000018031479,0.83067304,0.00085944036,0.00043288217,0.0009975288,0.00024437942,0.00003067523,0.00052330416],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980534,0.000043086948,0.0003819599,0.0008484611,0.00027259564,0.00040053678],"domain_scores_gemma":[0.99835753,0.0001551593,0.00015525382,0.0010998673,0.000112244226,0.000119945944],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00020284292,0.00026298343,0.00022010237,0.0002176585,0.00046138672,0.00040332627,0.0012795606,0.00009004152,0.000011106139],"category_scores_gemma":[4.682537e-7,0.00026684525,0.00012100522,0.00083156134,0.00006033033,0.00020235835,0.00022190278,0.00015329725,0.00073881703],"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":[0.000008997554,0.0014444357,0.0015814997,0.00021559604,0.000058782014,0.000027080463,0.0004556715,0.005753461,0.029165989,0.3728866,0.21291979,0.3754821],"study_design_scores_gemma":[0.00031114058,0.000020452162,0.0005538763,0.00003495024,0.000009052625,0.000020144713,0.000013338817,0.5459864,0.00035026966,0.00007822182,0.45239004,0.00023211505],"about_ca_topic_score_codex":0.000042801195,"about_ca_topic_score_gemma":0.0000122989095,"teacher_disagreement_score":0.54023296,"about_ca_system_score_codex":0.0001244453,"about_ca_system_score_gemma":0.00014115476,"threshold_uncertainty_score":0.99997836},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002984844,0.000106784726,0.99229485,0.0029854148,0.000017810797,0.0005331957,0.000047578746,0.00070392364,0.00032560778],"genre_scores_gemma":[0.12934068,0.0000047638323,0.8699152,0.00019029276,0.00010662247,0.00024875975,0.00014299834,0.000009115426,0.000041580264],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984069,0.00002264123,0.0003422176,0.00079644547,0.00012422957,0.0003076013],"domain_scores_gemma":[0.9982646,0.000040480136,0.00011216525,0.0014487166,0.00006683603,0.00006719675],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023527138,0.0001531321,0.000180075,0.0002867924,0.00020098969,0.00018547948,0.0026217701,0.00010133192,0.0000013537311],"category_scores_gemma":[7.3897536e-7,0.00016701243,0.00002274807,0.0018661558,0.00003314867,0.00046671004,0.00043629046,0.00017203012,0.000098535886],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.071078e-7,0.00023299034,0.0006075762,0.000008791076,0.000008782763,0.0000024548326,0.000118141776,0.000060130384,0.0028625939,0.063399695,0.0039290837,0.92876923],"study_design_scores_gemma":[0.0006063545,0.000063764666,0.0072749862,0.0000722532,0.000018474868,0.00022290423,0.00015299,0.63062423,0.0012883303,0.0015041266,0.35768974,0.00048184258],"about_ca_topic_score_codex":0.000012720161,"about_ca_topic_score_gemma":0.000022066917,"teacher_disagreement_score":0.9282874,"about_ca_system_score_codex":0.00007994457,"about_ca_system_score_gemma":0.00008830166,"threshold_uncertainty_score":0.681057},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013488828,0.000028197395,0.99349964,0.0034265886,0.000030734765,0.0011629628,0.00010647916,0.0007905402,0.00081998797],"genre_scores_gemma":[0.0012770115,0.000004312057,0.99489635,0.0020690728,0.0002733415,0.0010519017,0.0002391339,0.000018714121,0.00017018364],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99820995,0.000033226566,0.00036271784,0.00071488414,0.00025573297,0.00042350442],"domain_scores_gemma":[0.99837524,0.00032548246,0.00024813888,0.00070872816,0.00021723454,0.00012516449],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00035655344,0.0002328287,0.00022055965,0.00019891906,0.0005403203,0.00042830023,0.0010832291,0.00011740546,0.0000026087398],"category_scores_gemma":[0.0000032785783,0.00025101835,0.0001188422,0.00057711167,0.000011877979,0.0002852667,0.00008701897,0.00014322433,0.00008283205],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.135309e-7,0.00032537317,0.000012110601,0.0000067877804,0.000018744424,3.7629624e-7,0.00016506677,0.00013787455,0.00037095038,0.011098788,0.0069192434,0.9809438],"study_design_scores_gemma":[0.00041839748,0.00007862025,0.00042070463,0.000016946715,0.000014356615,0.0000024061885,0.0000063143666,0.6278926,0.0007063893,0.0009724586,0.36926103,0.00020976935],"about_ca_topic_score_codex":0.000003232405,"about_ca_topic_score_gemma":7.958351e-7,"teacher_disagreement_score":0.980734,"about_ca_system_score_codex":0.00020507028,"about_ca_system_score_gemma":0.00010433444,"threshold_uncertainty_score":0.9999942},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00047611343,0.00006736819,0.9960797,0.00063047855,0.000011651896,0.0011759897,0.0011116037,0.00028433892,0.00016278887],"genre_scores_gemma":[0.12760004,0.0000034744069,0.8694968,0.000049663173,0.000057133486,0.00048844836,0.0022794763,0.000012115971,0.000012819437],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976795,0.00001259024,0.00071866583,0.0010286997,0.0002559522,0.00030462065],"domain_scores_gemma":[0.9959832,0.00018560067,0.0002828367,0.0033618654,0.00012182924,0.00006469844],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00123292,0.00016497693,0.0003273997,0.00084684795,0.0001449379,0.00008049829,0.005885798,0.00009154487,0.0000017121714],"category_scores_gemma":[0.000003055444,0.00016844324,0.00004426343,0.0031730456,0.00006737527,0.00036283903,0.0021979555,0.000111367575,0.000016684955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025086217,0.0005411494,0.0005179778,0.0001299294,0.00029558194,8.014546e-7,0.00021313455,0.0007467801,0.0012113142,0.19689366,0.0025402457,0.7969069],"study_design_scores_gemma":[0.0005192593,0.000013633286,0.006507015,0.000023663759,0.000106517604,0.00001187284,0.0000749392,0.89915067,0.00071388483,0.0017211002,0.090886995,0.0002704306],"about_ca_topic_score_codex":0.00003884611,"about_ca_topic_score_gemma":0.00008460101,"teacher_disagreement_score":0.8984039,"about_ca_system_score_codex":0.0001023245,"about_ca_system_score_gemma":0.00011924656,"threshold_uncertainty_score":0.9994928},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042278685,0.000566713,0.95458806,0.000078749916,0.0022039665,0.000110516456,0.00004717641,0.00011783179,0.000008295142],"genre_scores_gemma":[0.90408087,0.000071039714,0.094842896,0.000005068226,0.00075571524,0.00007652608,0.0000043595182,0.000028635472,0.00013487633],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989468,0.00000789288,0.00041457842,0.0002243454,0.00019053114,0.00021583724],"domain_scores_gemma":[0.9988682,0.00031884192,0.00013355073,0.00018829439,0.0003641048,0.00012695817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024730546,0.0001852791,0.00021649046,0.00024621547,0.000040893116,0.00018280669,0.00073045946,0.00005709751,0.0000018001844],"category_scores_gemma":[0.00015330322,0.00014465806,0.000111863235,0.000104141705,0.00001298083,0.0007626418,0.00020811077,0.00011878192,0.0000068843747],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028292265,0.0007213697,0.0042554224,0.00066164875,0.000903586,0.00010898008,0.0027116642,0.0022381342,0.029268472,0.03341133,0.0022413183,0.92344975],"study_design_scores_gemma":[0.0054343776,0.00060986396,0.010567385,0.006543816,0.00020636413,0.0011889676,0.00012932082,0.7975836,0.03575962,0.00008299169,0.14008747,0.001806223],"about_ca_topic_score_codex":0.0000019254992,"about_ca_topic_score_gemma":8.867085e-7,"teacher_disagreement_score":0.92164356,"about_ca_system_score_codex":0.00018936524,"about_ca_system_score_gemma":0.000058664074,"threshold_uncertainty_score":0.58989847},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043080607,0.00014772407,0.9796398,0.008714233,0.00012807803,0.0000654314,0.000025608262,0.000093980714,0.0068770363],"genre_scores_gemma":[0.5980799,0.00036936734,0.3986762,0.0014925849,0.00022566106,0.00014779906,0.00017561339,0.000012187623,0.0008207153],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99924266,0.000009747723,0.0001251823,0.0003327214,0.00015518969,0.00013452492],"domain_scores_gemma":[0.9987481,0.00007940692,0.000013502669,0.0010772748,0.000008542706,0.00007314815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002530572,0.000051500556,0.000065748376,0.000044014512,0.000033706532,0.00012842202,0.0022565066,0.000030819854,0.00002869705],"category_scores_gemma":[0.00008291556,0.00004153232,0.000009612589,0.00036874154,0.00002876957,0.001041187,0.0013104771,0.00007923283,0.00018936749],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.6007987e-7,0.0004821574,0.001461303,0.000004261455,0.000004167461,0.000023515497,0.00022540744,0.000009953808,0.000003560547,0.43538904,0.013112954,0.54928344],"study_design_scores_gemma":[0.0029428734,0.000118158045,0.053504918,0.0003280362,0.000010466003,0.00008732847,0.00017200473,0.42411852,0.0012696423,0.04267886,0.47375348,0.0010157088],"about_ca_topic_score_codex":0.0002991781,"about_ca_topic_score_gemma":0.00059982366,"teacher_disagreement_score":0.5937718,"about_ca_system_score_codex":0.000020695901,"about_ca_system_score_gemma":0.00015628422,"threshold_uncertainty_score":0.41931883},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002259142,0.00019048693,0.99632454,0.00034505883,0.000006917489,0.00064950564,0.00006097968,0.00010113386,0.0000622569],"genre_scores_gemma":[0.03261041,0.000008914831,0.96679515,0.000046152887,0.000062993335,0.00026370806,0.00017932321,0.000008806379,0.000024514673],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99881643,0.000034547546,0.0003502872,0.00051437994,0.00011732958,0.00016700049],"domain_scores_gemma":[0.9986689,0.00011502298,0.00015842456,0.0009448214,0.00007029116,0.000042554162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029236198,0.000111476795,0.0001396078,0.00010501767,0.0001422431,0.00014586649,0.0011740612,0.00003159583,0.0000023950142],"category_scores_gemma":[1.8467232e-7,0.0001153444,0.000016483964,0.00042399787,0.000043435983,0.00044578462,0.00058602233,0.000044219472,0.0000108271],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.600502e-7,0.00008198024,0.00031895697,0.00003302686,0.000016497293,5.2657754e-7,0.00023186236,0.00004758834,0.007076567,0.024409717,0.00408791,0.96369493],"study_design_scores_gemma":[0.0014833247,0.00010884437,0.017810414,0.000067279216,0.00009365378,0.00018226329,0.00030901906,0.6726671,0.022836786,0.00640651,0.27719587,0.00083891617],"about_ca_topic_score_codex":0.00016355272,"about_ca_topic_score_gemma":0.000013842274,"teacher_disagreement_score":0.962856,"about_ca_system_score_codex":0.000014856002,"about_ca_system_score_gemma":0.000051665822,"threshold_uncertainty_score":0.47036082},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0071705948,0.00010163921,0.99159276,0.0002405616,0.000016220552,0.0005653149,0.00011660059,0.00006692388,0.00012938192],"genre_scores_gemma":[0.012167332,0.0000068175664,0.98725045,0.000054798908,0.00006996256,0.00027509237,0.00010370961,0.000010926786,0.000060895334],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985517,0.00002050793,0.00056346523,0.00041348807,0.00017034603,0.0002804913],"domain_scores_gemma":[0.9974296,0.00052145304,0.0003278799,0.0013377771,0.00029597667,0.000087297565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080946315,0.00012443459,0.00024400918,0.00024962708,0.0003429484,0.00009316014,0.0020589929,0.000051213694,0.0000016375201],"category_scores_gemma":[0.0000038645776,0.0001050571,0.00016139487,0.0016852975,0.00009220802,0.00023533979,0.0004995372,0.000062442494,0.0000019323363],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017060363,0.00015008736,0.00012958237,0.000011355426,0.0002019489,8.4183306e-8,0.0007413484,0.00015011345,0.004824905,0.009930854,0.0006752815,0.9831827],"study_design_scores_gemma":[0.0002844509,0.00006299378,0.011949072,0.000012340022,0.00023510423,0.0000040670075,0.00022049676,0.77495,0.012890111,0.002569843,0.1965813,0.00024016912],"about_ca_topic_score_codex":0.00005145897,"about_ca_topic_score_gemma":0.000035246667,"teacher_disagreement_score":0.9829426,"about_ca_system_score_codex":0.000020386457,"about_ca_system_score_gemma":0.000047091038,"threshold_uncertainty_score":0.42841044},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00064062653,0.000014095243,0.94382656,0.053743683,0.000015209287,0.00041318798,0.000029013814,0.00005227555,0.0012653597],"genre_scores_gemma":[0.55125153,0.000030151474,0.4372292,0.009012526,0.00014311877,0.00014825516,0.000022004291,0.000014066654,0.0021491596],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992455,0.000068172034,0.00014009091,0.0002231605,0.00016154778,0.00016149768],"domain_scores_gemma":[0.9983913,0.00035579538,0.00017374159,0.00094293826,0.00010888325,0.000027395841],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029178517,0.00008257765,0.00007419771,0.00001985757,0.0008078178,0.000071314316,0.0019656245,0.000045988378,0.0000010998474],"category_scores_gemma":[0.000002460218,0.00004673753,0.00007462976,0.000418601,0.00006705021,0.000067477864,0.00013099134,0.00014895182,0.000021530283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002323347,0.00027329507,0.00013413429,0.0000016904113,0.000020259293,9.1535036e-8,0.00024374755,0.007480788,0.001196077,0.703529,0.049370315,0.23774828],"study_design_scores_gemma":[0.00011455482,0.000014583081,0.004278113,0.0000047029575,0.0000119284805,7.1962154e-7,0.000013804271,0.76764137,0.00055663567,0.005325123,0.2219711,0.000067396766],"about_ca_topic_score_codex":0.000009368183,"about_ca_topic_score_gemma":0.00001286108,"teacher_disagreement_score":0.76016057,"about_ca_system_score_codex":0.00007809998,"about_ca_system_score_gemma":0.00010784732,"threshold_uncertainty_score":0.6213163},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045412578,0.000017891813,0.9508852,0.0013690081,0.000020279662,0.0019728434,0.00003486989,0.000065905246,0.00022144892],"genre_scores_gemma":[0.32108244,2.423972e-7,0.6778329,0.00013376087,0.000068844216,0.00076730625,0.00008454736,0.000007862186,0.0000220829],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984645,0.00004462473,0.00040904104,0.0005732117,0.0003450398,0.00016356296],"domain_scores_gemma":[0.99789065,0.00027752967,0.00012483807,0.001398513,0.00021977306,0.00008868665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016993597,0.000118448836,0.000109558365,0.00013414356,0.00035289332,0.00009141877,0.00150764,0.000024159302,0.0000022246797],"category_scores_gemma":[0.0000042496868,0.00009297978,0.0000126986,0.00068600586,0.000026610574,0.0001673788,0.0008247363,0.00007679812,0.000062313935],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038113074,0.001019021,0.0005989851,0.000018327095,0.00006338207,2.360636e-7,0.009990419,0.000031720116,0.0010410182,0.078669816,0.003241227,0.905322],"study_design_scores_gemma":[0.002131021,0.0003620438,0.34383503,0.0002525687,0.00016100839,0.000067936504,0.009389916,0.088153124,0.008496276,0.0012703409,0.54455006,0.001330695],"about_ca_topic_score_codex":0.0000107595815,"about_ca_topic_score_gemma":0.000028286451,"teacher_disagreement_score":0.90399134,"about_ca_system_score_codex":0.00007740085,"about_ca_system_score_gemma":0.00017811861,"threshold_uncertainty_score":0.37916055},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029701218,0.00019434956,0.9950811,0.0008177168,0.000011364453,0.00048474013,0.000033636898,0.00004928662,0.00035766896],"genre_scores_gemma":[0.21048945,0.000049142353,0.78906316,0.000088955516,0.000052170744,0.00013617279,0.0000959201,0.0000059368163,0.000019093295],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99860823,0.000028492637,0.00054188014,0.0004619692,0.00017032336,0.00018910215],"domain_scores_gemma":[0.9975764,0.00020328724,0.00031047748,0.0017614601,0.00010811468,0.000040267627],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042664158,0.00010558075,0.0001587819,0.0001132914,0.00018388111,0.000071269846,0.0027426775,0.000046346697,6.1909816e-7],"category_scores_gemma":[0.0000025105023,0.00009320697,0.000033788026,0.0009422073,0.00006387728,0.00046653894,0.00042424552,0.000106871616,0.000010802887],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010512565,0.00014256178,0.00032832957,0.000005423505,0.000005753181,7.127359e-8,0.00014428186,0.000049004204,0.0038231742,0.025098922,0.00047917943,0.96992224],"study_design_scores_gemma":[0.0006162042,0.000083539555,0.029789492,0.000057624497,0.0000192521,0.000015537853,0.00013774334,0.4491604,0.0056275385,0.008066119,0.50608844,0.00033809623],"about_ca_topic_score_codex":0.00004040517,"about_ca_topic_score_gemma":0.000016824188,"teacher_disagreement_score":0.96958417,"about_ca_system_score_codex":0.00002423338,"about_ca_system_score_gemma":0.00005477712,"threshold_uncertainty_score":0.5096623},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028701639,0.00011860292,0.9948622,0.0012250191,0.0000040503382,0.0006045569,0.00007442859,0.00013268122,0.000108272696],"genre_scores_gemma":[0.10666327,0.00002113204,0.8918283,0.00025042557,0.000062163104,0.00019000054,0.0009583832,0.000008929022,0.000017395894],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852306,0.000024399984,0.00039175054,0.0006778463,0.00016710116,0.0002158454],"domain_scores_gemma":[0.99800575,0.00005082428,0.00019341015,0.0015807437,0.00010825441,0.000061028728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021490423,0.00014859479,0.00018989318,0.00018679451,0.00009950505,0.00008867325,0.0020537137,0.00005420079,9.039061e-7],"category_scores_gemma":[6.7211005e-7,0.0001430276,0.000020638849,0.0012638882,0.00004310867,0.0006886825,0.00029212266,0.0000812048,0.000018802362],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020026598,0.00026536555,0.0016100574,0.000012263068,0.0000094040315,6.518173e-7,0.00023881196,0.0005529803,0.0050181793,0.028353594,0.0011022515,0.9628344],"study_design_scores_gemma":[0.0010167729,0.00012630566,0.0546832,0.00006878194,0.000026771833,0.000049541206,0.000049556566,0.7260497,0.0035265004,0.0024442074,0.21135037,0.00060829805],"about_ca_topic_score_codex":0.00003362686,"about_ca_topic_score_gemma":0.000029300078,"teacher_disagreement_score":0.96222615,"about_ca_system_score_codex":0.00003170514,"about_ca_system_score_gemma":0.00006370809,"threshold_uncertainty_score":0.5832496},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051161207,0.000041190357,0.9471413,0.00043080843,0.000011837497,0.00048436556,0.000041597,0.000048589365,0.00063912204],"genre_scores_gemma":[0.19207507,0.0000062951735,0.80753744,0.000095636504,0.000041877673,0.00011723388,0.000038421076,0.0000069268513,0.00008109436],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99888635,0.000015693578,0.00040734158,0.00029730354,0.0001933674,0.00019992107],"domain_scores_gemma":[0.998919,0.00016927454,0.00026128034,0.00041266435,0.00018004273,0.000057715308],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049113896,0.00009759952,0.00017380595,0.0003167593,0.00005974415,0.000024351511,0.00071869005,0.000052392137,0.000001827796],"category_scores_gemma":[0.0000011844556,0.000113325754,0.00004229624,0.0008265795,0.000026051246,0.00016899218,0.00019963298,0.000056505276,0.000019138644],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000060833163,0.00048105215,0.009007465,0.00006152874,0.000040812236,5.0321665e-7,0.0037904137,0.0005436366,0.03337263,0.10489434,0.0015068543,0.8462947],"study_design_scores_gemma":[0.0015918227,0.00020292957,0.23357481,0.00019493984,0.00006217616,0.000007994691,0.003273198,0.042900976,0.10973562,0.0038209371,0.6036804,0.00095421146],"about_ca_topic_score_codex":0.00012962655,"about_ca_topic_score_gemma":0.00005075455,"teacher_disagreement_score":0.8453405,"about_ca_system_score_codex":0.00017116911,"about_ca_system_score_gemma":0.000057032452,"threshold_uncertainty_score":0.46212903},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003801463,0.000020398043,0.9851912,0.00021906364,0.00021521978,0.00009845618,0.00002988391,0.0003704402,0.010053856],"genre_scores_gemma":[0.05463211,0.000010097979,0.94405794,0.000503385,0.00005486792,0.00005469445,0.000023461565,0.00001078207,0.00065267866],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998764,0.000021287418,0.00022475998,0.00047929428,0.00020264977,0.00030802103],"domain_scores_gemma":[0.9988639,0.000029751689,0.00007424799,0.00081289234,0.0000755247,0.00014370511],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015027083,0.00014202412,0.00011568151,0.000078142715,0.00012780279,0.000079847785,0.0009616263,0.000043849122,0.00013715973],"category_scores_gemma":[0.000010919318,0.00012358885,0.000042781,0.00040732152,0.00005048132,0.00052701513,0.00030118437,0.00008536128,0.0002650274],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.6693737e-7,0.0000720281,0.00065896905,0.0000018313735,0.00000998881,0.000019012426,0.0009876823,3.2063875e-7,0.00014338388,0.012525417,0.0011568845,0.9844243],"study_design_scores_gemma":[0.00077731453,0.00032470666,0.01146236,0.00008554655,0.000025407402,0.0001978684,0.00079848064,0.9260107,0.021045797,0.0036171582,0.03446792,0.001186728],"about_ca_topic_score_codex":0.0007610112,"about_ca_topic_score_gemma":0.000016475324,"teacher_disagreement_score":0.98323756,"about_ca_system_score_codex":0.000027350783,"about_ca_system_score_gemma":0.000046983838,"threshold_uncertainty_score":0.5039807},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003734237,0.00021040402,0.4392549,0.00048837607,0.00042777785,0.00059038744,0.0015473766,0.0001942549,0.5572492],"genre_scores_gemma":[0.002194393,0.0000066328544,0.96305263,0.0010407842,0.0005309943,0.00008377616,0.00023773756,0.000038548114,0.03281449],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980268,0.000011226541,0.0003863927,0.0008416702,0.00037247207,0.00036145537],"domain_scores_gemma":[0.9977059,0.00019276199,0.0003415431,0.0015883988,0.00008101881,0.00009043017],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004283296,0.00025639473,0.000321073,0.00006994919,0.00010969523,0.00028102432,0.0016896672,0.00037990144,0.0000024961453],"category_scores_gemma":[0.0001319499,0.00027879735,0.00007802715,0.000051958003,0.00001813804,0.00008790117,0.00062469114,0.00024076195,0.00005527893],"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":[0.0000017777027,0.000014689237,0.0000036752115,0.0000058409587,0.000015010291,0.000004914089,0.00004099205,0.000015101488,5.646743e-7,0.82127887,0.0028408468,0.17577773],"study_design_scores_gemma":[0.0003212576,0.00006068018,0.00009361406,0.00038216327,0.000037307087,0.000008695414,0.0000074077766,0.055507492,0.0000050589965,0.79862577,0.1444598,0.0004907594],"about_ca_topic_score_codex":0.0000283212,"about_ca_topic_score_gemma":0.00003187354,"teacher_disagreement_score":0.5244347,"about_ca_system_score_codex":0.0004055542,"about_ca_system_score_gemma":0.00019624224,"threshold_uncertainty_score":0.99996644},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000007738292,0.00021223811,0.9959905,0.00094742136,0.000671277,0.00054978667,0.000019570663,0.00037780314,0.0012236759],"genre_scores_gemma":[0.007445466,0.0000045176857,0.99092627,0.0009221793,0.0004323288,0.00004238385,0.000029923138,0.000044763954,0.00015218822],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960867,0.000041383315,0.00052616437,0.0018563939,0.0008195875,0.00066974724],"domain_scores_gemma":[0.99633265,0.00027934372,0.00031800172,0.0023264028,0.000378059,0.00036556926],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0016842356,0.000536388,0.00048532285,0.0006886822,0.00041815848,0.0011164997,0.004469361,0.000359659,0.000008268803],"category_scores_gemma":[0.00010902829,0.00050407497,0.00009883158,0.0007007198,0.00054725993,0.00084788835,0.00096420664,0.00083179993,0.000020740621],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024729256,0.000045549958,0.000003446213,0.000022588794,0.0000045819606,0.000026293152,0.00022378303,0.0109241465,0.0015641855,0.008956777,0.000037820126,0.97818834],"study_design_scores_gemma":[0.00019200264,0.00017647668,0.000006565429,0.00031358126,0.000007280742,0.000040350085,1.17685246e-7,0.91047585,0.004021845,0.08046393,0.0037003064,0.0006016732],"about_ca_topic_score_codex":0.00006951794,"about_ca_topic_score_gemma":0.000028727527,"teacher_disagreement_score":0.9775867,"about_ca_system_score_codex":0.00033535378,"about_ca_system_score_gemma":0.0015117518,"threshold_uncertainty_score":0.9999204},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043871827,0.000004408836,0.95161676,0.0018062195,0.00015101678,0.0002465924,0.0000023099533,0.00011469069,0.002186193],"genre_scores_gemma":[0.7875687,0.0000047680296,0.2110323,0.0001851364,0.00006440853,0.00018390019,0.0000370538,0.000007778864,0.00091595156],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99924415,0.000015723212,0.00013658109,0.00029682022,0.00015425563,0.0001524912],"domain_scores_gemma":[0.99928296,0.000048135516,0.000057314184,0.0004303856,0.00006960122,0.00011160663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007169798,0.00008784561,0.00006361921,0.00007481746,0.00010737159,0.00040932558,0.00041662817,0.000025031324,0.000370578],"category_scores_gemma":[0.0000050485182,0.00006931794,0.000016758615,0.00020750826,0.000032541597,0.0014503312,0.0000816288,0.0000876644,0.00029821927],"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":[0.0000050560297,0.0010359831,0.008091041,0.0000054009433,0.000030867322,0.0000015417913,0.0015938947,0.00006019856,0.0007866877,0.79417336,0.0066807675,0.1875352],"study_design_scores_gemma":[0.0009865708,0.0014885832,0.17980476,0.0001432163,0.00008499562,0.00033183416,0.008674707,0.7375781,0.011590599,0.034238055,0.023251783,0.0018268222],"about_ca_topic_score_codex":0.00021856463,"about_ca_topic_score_gemma":0.000039578565,"teacher_disagreement_score":0.7599353,"about_ca_system_score_codex":0.00009699876,"about_ca_system_score_gemma":0.00007057704,"threshold_uncertainty_score":0.40575692},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009520904,0.00037647775,0.98806053,0.0044247955,0.000562754,0.00037790558,0.000019582429,0.00016086355,0.0059219026],"genre_scores_gemma":[0.022837011,0.000032534426,0.9745087,0.0015109115,0.000433258,0.000031541513,0.000029020703,0.000040873285,0.0005761391],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99671215,0.000031051783,0.00037313838,0.0013113166,0.0010175128,0.0005548138],"domain_scores_gemma":[0.99681085,0.00040162576,0.00030164284,0.0018352788,0.00044406435,0.00020650691],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009769414,0.00044298466,0.00036968218,0.00031818968,0.00039394514,0.0007422114,0.004183245,0.00017762822,0.000018145465],"category_scores_gemma":[0.000047628735,0.0002817979,0.000053238833,0.00083373615,0.0011820967,0.00044406776,0.0010315385,0.0006647907,0.00004532661],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014138818,0.000020525124,0.000018644334,0.000008313284,0.000013723078,0.000055502176,0.0012200836,0.0011473945,0.000021171425,0.034378827,0.00061925803,0.96249515],"study_design_scores_gemma":[0.00079070416,0.000561416,0.00015251448,0.001046541,0.00003950135,0.0007756368,0.000005415185,0.79273397,0.00060101517,0.09666852,0.104658455,0.001966303],"about_ca_topic_score_codex":0.000030627,"about_ca_topic_score_gemma":0.000063229854,"teacher_disagreement_score":0.96052885,"about_ca_system_score_codex":0.00021868544,"about_ca_system_score_gemma":0.0009748189,"threshold_uncertainty_score":0.9999634},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.095981285,0.0000156343,0.7910767,0.0029798525,0.0015216165,0.00051339134,0.00020705389,0.0003720313,0.107332416],"genre_scores_gemma":[0.9282389,0.000022465998,0.07059541,0.00043459926,0.000098903605,0.00007079401,0.000066082415,0.000012703019,0.0004600872],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99813324,0.000047679674,0.00047708311,0.00060058036,0.00042606535,0.00031535167],"domain_scores_gemma":[0.9988716,0.000102513615,0.00014557721,0.0006025055,0.0001499395,0.00012782583],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00038156964,0.00018256066,0.00015417111,0.00037608386,0.00009478515,0.00026904655,0.0022585297,0.00005660959,0.0013190565],"category_scores_gemma":[0.00012975393,0.00019160964,0.000046870766,0.00046475744,0.00010686,0.0006845264,0.00032099718,0.0002280032,0.0019684315],"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":[0.000018674255,0.00026289863,0.00034034412,0.0000020878688,0.000011854006,0.00006338299,0.002731279,0.000013887018,0.0004934725,0.74440706,0.00020631797,0.25144878],"study_design_scores_gemma":[0.00021240478,0.00036450167,0.0048960387,0.0005040477,0.000010738203,0.0000672591,0.0023138756,0.7395582,0.089723185,0.15381306,0.006993743,0.0015429407],"about_ca_topic_score_codex":0.0004539915,"about_ca_topic_score_gemma":0.00029006304,"teacher_disagreement_score":0.8322577,"about_ca_system_score_codex":0.000073857256,"about_ca_system_score_gemma":0.0001290688,"threshold_uncertainty_score":0.99959385},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020776328,0.00089773413,0.9763868,0.00015811087,0.00032863024,0.0011565606,0.000070985916,0.00006506,0.00015982876],"genre_scores_gemma":[0.98824,0.00001434842,0.011227597,0.000100584926,0.00010124595,0.00027455355,0.000022434828,0.000008846076,0.000010371799],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981704,0.00028144437,0.00050203566,0.00046999383,0.00026908214,0.00030705854],"domain_scores_gemma":[0.9984439,0.00044268483,0.00020244459,0.0005420447,0.00019795656,0.00017094203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001489527,0.00018620274,0.00045636078,0.00014275762,0.00007345684,0.000100719466,0.00039979882,0.00007194561,7.2870426e-7],"category_scores_gemma":[0.00008976586,0.00015698613,0.00007510912,0.00055938156,0.000099385295,0.00013593085,0.00007181735,0.00011812731,0.000006598351],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002958323,0.0015536173,0.057853438,0.00041461724,0.0002771138,0.000045366334,0.002619102,0.109178975,0.0005297091,0.027542349,0.013252215,0.7864377],"study_design_scores_gemma":[0.0010593495,0.00042309824,0.010724904,0.00019552758,0.0000127787725,0.0000059946724,0.00009480325,0.9846834,0.00011702949,0.000980107,0.0015101911,0.00019281097],"about_ca_topic_score_codex":0.0002635271,"about_ca_topic_score_gemma":0.000023913824,"teacher_disagreement_score":0.9674637,"about_ca_system_score_codex":0.0000510102,"about_ca_system_score_gemma":0.00005407988,"threshold_uncertainty_score":0.6401709},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32789722,0.0000065153936,0.6683537,0.0003415678,0.000026263451,0.000032656808,8.6116705e-7,0.00003267068,0.0033085542],"genre_scores_gemma":[0.7933101,6.872796e-7,0.20658194,0.000045782384,0.0000060890607,0.000004655501,7.1293726e-7,0.0000011588453,0.000048853068],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99951065,0.000014289261,0.00012897482,0.00015018787,0.000098637836,0.00009725694],"domain_scores_gemma":[0.99960935,0.000070708484,0.000037519025,0.00024398007,0.000015568128,0.000022882137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030719538,0.000038823528,0.00006609751,0.000052710388,0.00002332391,0.000029414134,0.00044936093,0.000013087897,0.000004644775],"category_scores_gemma":[0.000013617279,0.000031744647,0.000012645343,0.00027458175,0.000020277073,0.00005259453,0.00009223975,0.000026665626,0.000012094186],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.915631e-7,0.00007288051,0.0010606875,0.000012391991,0.0000022269128,9.954848e-7,0.0011762368,0.0161449,0.0029086927,0.8215358,0.00009723273,0.15698744],"study_design_scores_gemma":[0.00009574077,0.000017521996,0.0042097904,0.000020853066,5.7488603e-7,0.000002087782,0.000078422054,0.98570704,0.0029334442,0.006298338,0.00056362315,0.00007253591],"about_ca_topic_score_codex":0.0005903715,"about_ca_topic_score_gemma":0.000020578957,"teacher_disagreement_score":0.9695622,"about_ca_system_score_codex":0.000009249778,"about_ca_system_score_gemma":0.00001543063,"threshold_uncertainty_score":0.12945092},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17834422,0.000008295224,0.8203574,0.00078189134,0.00008431629,0.0001492817,0.000002722256,0.000027221984,0.00024463455],"genre_scores_gemma":[0.9721581,0.000013808205,0.027605347,0.00003485856,0.00013086418,0.00001569492,0.0000043824552,0.000006821762,0.000030130339],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998162,0.00021646259,0.000196525,0.00027373704,0.00082710705,0.00032419906],"domain_scores_gemma":[0.9985732,0.0006634493,0.000084865285,0.00044611204,0.00017463409,0.000057731522],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005050682,0.00006649453,0.00010362863,0.00006735682,0.00040827537,0.00022519536,0.00075545785,0.000074430725,0.0000039636925],"category_scores_gemma":[0.00018881755,0.000052621774,0.000050234357,0.00093927095,0.00007766953,0.0008638334,0.0001900053,0.00044719482,0.0000036566526],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007350345,0.0008473444,0.022249404,0.00021404677,0.00012997448,0.0000042007587,0.033249944,0.02529038,0.017360155,0.67312384,0.009408881,0.21804833],"study_design_scores_gemma":[0.00018620481,0.00004449035,0.0035610315,0.000037794525,0.000002837189,9.183166e-7,0.0018472115,0.9669376,0.00049669953,0.026616085,0.00020338633,0.00006571552],"about_ca_topic_score_codex":0.0001147765,"about_ca_topic_score_gemma":0.000029237026,"teacher_disagreement_score":0.94164723,"about_ca_system_score_codex":0.0005259648,"about_ca_system_score_gemma":0.00008717281,"threshold_uncertainty_score":0.31401652},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014172028,0.00018919828,0.95945317,0.0039264727,0.00092239614,0.00091998064,0.013051086,0.00076813373,0.006597541],"genre_scores_gemma":[0.43432236,0.00013577753,0.52605504,0.00058073783,0.00093614723,0.000008320022,0.01609615,0.00009441161,0.021771071],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972086,0.00006543341,0.00029043003,0.001399056,0.0005319959,0.00050451077],"domain_scores_gemma":[0.99158263,0.0001597655,0.0003199734,0.0074104927,0.00021820507,0.00030895308],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.00041593742,0.0002868461,0.00038486737,0.00022397359,0.00047127838,0.00024807628,0.012816636,0.00015454151,0.003538109],"category_scores_gemma":[0.00010316282,0.00028184828,0.00007324725,0.0009087297,0.00023403559,0.0028892942,0.008657069,0.0002885397,0.0020230059],"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":[0.000026847538,0.0004482232,0.0013826989,0.000094865936,0.0002607183,0.000070507944,0.0074712285,0.000007968718,0.00030317946,0.0019322714,0.40176782,0.5862337],"study_design_scores_gemma":[0.0023264652,0.0001979763,0.009065073,0.0002665429,0.00013923192,0.000072870425,0.011117565,0.2246103,0.00014564315,0.001695846,0.74872094,0.0016415566],"about_ca_topic_score_codex":0.0026189643,"about_ca_topic_score_gemma":0.00039872344,"teacher_disagreement_score":0.5845921,"about_ca_system_score_codex":0.00003195582,"about_ca_system_score_gemma":0.00026848586,"threshold_uncertainty_score":0.99996334},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44081756,0.000012654131,0.5573917,0.0010448848,0.00006914754,0.00003765287,0.000025443316,0.00006641273,0.0005345325],"genre_scores_gemma":[0.8492067,0.000014891951,0.15053879,0.00009275373,0.00004609155,2.9647438e-7,0.000026919894,0.000006012207,0.00006753814],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99927354,0.00003859539,0.00005911331,0.0002988285,0.00017478966,0.00015513427],"domain_scores_gemma":[0.99911714,0.00007893122,0.000098005294,0.00057541876,0.000048216854,0.000082295075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010643715,0.00008754798,0.00012585554,0.00007618933,0.00016982244,0.000043276013,0.00087642495,0.000043180156,0.000005716857],"category_scores_gemma":[0.000008316519,0.00010885126,0.00005569563,0.00018826759,0.0000618891,0.00029497096,0.00030654273,0.000068179594,0.00007393076],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000057368197,0.00020720255,0.113997094,0.000019755562,0.0000963905,0.000040578914,0.001864046,0.00009848514,0.0013473235,0.008811712,0.016614802,0.8568969],"study_design_scores_gemma":[0.0013206705,0.00022188749,0.6605845,0.00012789428,0.0000771691,0.000008808329,0.008814833,0.28580275,0.0009067893,0.0035066546,0.037958376,0.000669655],"about_ca_topic_score_codex":0.0057432023,"about_ca_topic_score_gemma":0.034825284,"teacher_disagreement_score":0.8562272,"about_ca_system_score_codex":0.000023412178,"about_ca_system_score_gemma":0.000016001773,"threshold_uncertainty_score":0.98278666},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00084390544,0.00001957832,0.99519867,0.0009868359,0.00013941871,0.0007423146,0.00040063626,0.00028330428,0.0013853639],"genre_scores_gemma":[0.0012268996,0.0000026868001,0.99615574,0.000085952925,0.00020833053,0.00046184415,0.0002833414,0.000018906609,0.001556321],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837756,0.000013848598,0.00021626505,0.0007922025,0.0002220199,0.0003781015],"domain_scores_gemma":[0.9979105,0.00024346975,0.00012430249,0.0013017971,0.00026878348,0.00015117216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007922866,0.00017075756,0.00021528761,0.000076524004,0.0002432421,0.00037260348,0.0015185867,0.000047746926,0.0000010723134],"category_scores_gemma":[0.000098831006,0.00013657154,0.000029558176,0.00034958674,0.00006386031,0.0009988729,0.00054863037,0.00005073974,0.0000023144867],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014856516,0.00015307865,0.0004433153,0.000032613774,0.00007229885,0.0000024221813,0.0020591074,0.00016998642,0.000016562271,0.013876679,0.08259806,0.90056103],"study_design_scores_gemma":[0.0007758336,0.00023387723,0.00015114516,0.000027349164,0.00001390796,0.000015020923,0.0015691927,0.95583326,0.00006394558,0.00056469743,0.04050616,0.0002456313],"about_ca_topic_score_codex":0.00011840307,"about_ca_topic_score_gemma":0.0001580299,"teacher_disagreement_score":0.95566326,"about_ca_system_score_codex":0.000051980234,"about_ca_system_score_gemma":0.00027687676,"threshold_uncertainty_score":0.5569226},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9803373,0.00016544595,0.009940337,0.0071689403,0.00084311434,0.0008102565,0.00013715315,0.000071242146,0.00052616507],"genre_scores_gemma":[0.64558536,0.0000082581655,0.3501698,0.00037824782,0.00042290927,0.0008433531,0.001231917,0.000026327556,0.0013338056],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9973363,0.00010003632,0.0006542977,0.0010752972,0.00041514135,0.000418916],"domain_scores_gemma":[0.9966159,0.00069475285,0.0002120825,0.0020825956,0.00017527527,0.00021940359],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00066634396,0.00024309939,0.00021368919,0.000343856,0.0002825692,0.0005820217,0.002448211,0.000059716836,0.00049361837],"category_scores_gemma":[0.0003126081,0.0002565311,0.000032739707,0.000856695,0.00006315013,0.0022698045,0.0012079932,0.00021268777,0.00036644624],"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":[0.0000041641388,0.0074977223,0.30470622,0.000030911127,0.00011123209,0.0001489344,0.043741733,0.00006540758,0.00015530089,0.0070982734,0.19438653,0.4420536],"study_design_scores_gemma":[0.0017144426,0.0004551699,0.6927103,0.0004391566,0.00012760334,0.0047735753,0.10639908,0.13747989,0.00012541747,0.001557633,0.051592954,0.0026248184],"about_ca_topic_score_codex":0.0024823395,"about_ca_topic_score_gemma":0.0004136569,"teacher_disagreement_score":0.43942878,"about_ca_system_score_codex":0.00013972422,"about_ca_system_score_gemma":0.0009253034,"threshold_uncertainty_score":0.9999887},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031448096,0.00010096577,0.86676365,0.019509707,0.00047296105,0.00022810418,0.00065990916,0.00011928701,0.08069731],"genre_scores_gemma":[0.96830136,0.000016987018,0.030354615,0.00016422934,0.0000893187,0.000007200419,0.00055589963,0.000004748581,0.00050567155],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990058,0.00008359161,0.00018755221,0.00034543732,0.0002858287,0.00009181012],"domain_scores_gemma":[0.99863225,0.0001876271,0.00017017676,0.0007873936,0.00016613501,0.000056418896],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0005871278,0.00008151814,0.00010744891,0.000035473637,0.00008907314,0.000432956,0.006340155,0.00002111688,0.000094952964],"category_scores_gemma":[0.00034291856,0.00005892809,0.000017608923,0.0001342773,0.00003545637,0.0005901197,0.0027986488,0.00024131396,0.000048077993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050800973,0.00021914003,0.090433635,0.000001697194,0.00018743637,0.000010088263,0.0017196678,0.0012219715,0.0003605481,0.33684886,0.006027878,0.5629183],"study_design_scores_gemma":[0.0002868879,0.000036678754,0.016875403,0.000028076183,0.000005296465,0.000001887597,0.000099320765,0.9624803,0.000046148176,0.0072619794,0.012794989,0.00008302078],"about_ca_topic_score_codex":0.010485795,"about_ca_topic_score_gemma":0.00050524424,"teacher_disagreement_score":0.96125835,"about_ca_system_score_codex":0.000019421137,"about_ca_system_score_gemma":0.00010113031,"threshold_uncertainty_score":0.999036},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7719203,0.00012562753,0.22553964,0.0009424981,0.00017589414,0.00011667702,0.00062623795,0.00008490873,0.0004682069],"genre_scores_gemma":[0.63276815,0.000026182057,0.36684582,0.000017292252,0.000033517153,1.4892838e-7,0.0002772879,0.0000060654434,0.000025557812],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9990264,0.000039655766,0.000101557926,0.00039157836,0.0002919906,0.00014879966],"domain_scores_gemma":[0.9980471,0.000056091816,0.00020121863,0.0014441395,0.00012647863,0.00012495727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017397408,0.00010171897,0.00019424473,0.00012540037,0.000088403096,0.000027969716,0.002396829,0.00006272776,0.0000028041395],"category_scores_gemma":[0.000021781654,0.000121513694,0.00004495253,0.00043106268,0.00012704046,0.00060224585,0.00096547295,0.00008465666,0.000008061056],"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":[0.00015577354,0.0011285419,0.30799848,0.00013864395,0.0010954527,0.00019483289,0.01469715,0.00073638913,0.013268621,0.049223274,0.15844867,0.45291418],"study_design_scores_gemma":[0.00471495,0.0004913323,0.62736493,0.00024095885,0.0002995459,0.000014661713,0.056124467,0.26144636,0.002283361,0.014253655,0.03158444,0.0011813067],"about_ca_topic_score_codex":0.008156258,"about_ca_topic_score_gemma":0.04028738,"teacher_disagreement_score":0.45173287,"about_ca_system_score_codex":0.00002292604,"about_ca_system_score_gemma":0.00008221856,"threshold_uncertainty_score":0.9984485},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000011024448,0.00006928934,0.99232125,0.0011925214,0.0006088549,0.0002673974,0.000061450766,0.00020904506,0.005259142],"genre_scores_gemma":[0.030792234,0.000049304876,0.9669386,0.0007902007,0.0003508934,0.000022224176,0.00001999425,0.00004043068,0.0009960879],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964975,0.000032479275,0.00047716833,0.0015182458,0.0008039242,0.00067066756],"domain_scores_gemma":[0.9971911,0.0009070013,0.00025431707,0.0011713265,0.00023496462,0.00024134158],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00076322607,0.00042121435,0.000425494,0.00039021755,0.00033505165,0.00065988733,0.0030759904,0.00019847954,0.000044757042],"category_scores_gemma":[0.00016980065,0.0003349801,0.000074418225,0.0003348427,0.00073943275,0.00045680246,0.0010660497,0.00070625107,0.00019208988],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012311816,0.000013019685,0.000011098795,0.000008451499,0.000006009322,0.000047453865,0.00015869326,0.0008281442,0.00011972491,0.078947894,0.000047536752,0.9198107],"study_design_scores_gemma":[0.00033450016,0.00027817098,0.00017793041,0.00046666866,0.000009867741,0.00006126616,1.9580759e-7,0.7651883,0.00037230816,0.22136515,0.0108415205,0.0009041513],"about_ca_topic_score_codex":0.000012069067,"about_ca_topic_score_gemma":0.000013172617,"teacher_disagreement_score":0.91890657,"about_ca_system_score_codex":0.00018321861,"about_ca_system_score_gemma":0.00053595874,"threshold_uncertainty_score":0.99991024},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4150415,0.0004601598,0.5825975,0.0013405734,0.0002641447,0.000061976505,0.00007542872,0.00013405277,0.000024657827],"genre_scores_gemma":[0.80152434,0.0028179209,0.19450945,0.00071272097,0.00028632546,0.000019185372,0.0001005399,0.000019448984,0.000010067949],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99780697,0.00011839936,0.00052452396,0.0008097538,0.00042880955,0.0003115211],"domain_scores_gemma":[0.99757934,0.0011751415,0.00016251113,0.00051215716,0.00009236911,0.00047851197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062038144,0.00022693715,0.0003323817,0.00010121033,0.0002654302,0.00037019188,0.00060885074,0.00011123421,0.000007849843],"category_scores_gemma":[0.00028870572,0.00016303238,0.000049911043,0.00020403201,0.0005210328,0.00055005675,0.00057326735,0.00025053113,0.0000048984098],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008860015,0.000077154975,0.002913071,0.0000044124567,0.000017494016,0.00001606241,0.000058736234,8.529178e-8,0.00041626545,0.0020350718,0.0020965587,0.99235624],"study_design_scores_gemma":[0.009146277,0.0005479592,0.08959182,0.0018358311,0.000087512424,0.00030479953,0.00020654812,0.70724815,0.00044628416,0.1654769,0.023455529,0.0016523966],"about_ca_topic_score_codex":0.000079270416,"about_ca_topic_score_gemma":0.0000048942634,"teacher_disagreement_score":0.9907038,"about_ca_system_score_codex":0.000009121234,"about_ca_system_score_gemma":0.00012718352,"threshold_uncertainty_score":0.6648268},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16331753,0.00007139219,0.83512163,0.0006965846,0.00010641757,0.00009142276,0.0000327876,0.00006408902,0.00049813365],"genre_scores_gemma":[0.7749436,0.000014350176,0.22477949,0.00006925055,0.00009408876,0.000010915518,0.000043237917,0.0000052456626,0.000039823783],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906844,0.000021900389,0.00013910879,0.0004349918,0.0002008749,0.000134675],"domain_scores_gemma":[0.9987276,0.000028001798,0.00007124581,0.0010076746,0.00006813418,0.000097349985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036413132,0.000071957766,0.00008152087,0.00004398234,0.00010716785,0.0004548524,0.0012797385,0.000021207557,9.908188e-7],"category_scores_gemma":[0.00004734699,0.000064973734,0.0000063818543,0.0003082961,0.00007262389,0.001921078,0.00073594524,0.000067830246,0.000006323258],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010392097,0.0006622081,0.04540448,0.00011397375,0.00013203025,0.000041524323,0.019974163,0.00069527066,0.04661654,0.21932763,0.012880008,0.6541418],"study_design_scores_gemma":[0.00017694339,0.000018535255,0.004441684,0.000030376246,0.00001409161,0.000025418305,0.0009967797,0.98634833,0.00018918629,0.0060570873,0.0015183026,0.0001832827],"about_ca_topic_score_codex":0.000012721113,"about_ca_topic_score_gemma":0.0000021216947,"teacher_disagreement_score":0.98565304,"about_ca_system_score_codex":0.000030660918,"about_ca_system_score_gemma":0.00014347165,"threshold_uncertainty_score":0.4386152},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013445346,0.000055630288,0.98215073,0.0023548545,0.000053888372,0.00006199903,0.0010980378,0.00010656087,0.0006729384],"genre_scores_gemma":[0.47000977,0.000092087685,0.52522576,0.00022187571,0.0002776412,0.00004463414,0.0027768074,0.000023142551,0.0013282789],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998336,0.000064577434,0.0003171651,0.0007406918,0.00025908934,0.00028247468],"domain_scores_gemma":[0.99659497,0.0002757166,0.000102933576,0.0028991185,0.000033432258,0.0000938534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007968612,0.00011751906,0.00024529395,0.00030667076,0.00008113672,0.00017259983,0.002969833,0.000040737108,0.000072809176],"category_scores_gemma":[0.00017503109,0.00008382694,0.00006516528,0.0015973044,0.000040109106,0.00096384354,0.0013735136,0.000060991282,0.0003746509],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000041820936,0.00021904735,0.20478186,0.000009280315,0.0006605296,0.00003065617,0.00017071413,0.000066491084,0.00036712564,0.045964215,0.007960404,0.7397655],"study_design_scores_gemma":[0.00046279232,0.000018280398,0.30203962,0.000042308406,0.00027683598,0.0000030135427,0.000037774924,0.6582153,0.00010675228,0.0026313278,0.03569644,0.0004695484],"about_ca_topic_score_codex":0.00047902597,"about_ca_topic_score_gemma":0.00078615,"teacher_disagreement_score":0.73929596,"about_ca_system_score_codex":0.000026505835,"about_ca_system_score_gemma":0.0000361274,"threshold_uncertainty_score":0.5518738},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000025303181,0.00016700682,0.98929673,0.00083330483,0.0018164649,0.00026491482,0.0000200599,0.00021877448,0.0073574544],"genre_scores_gemma":[0.0029957837,0.00015250691,0.99482983,0.0009109017,0.00056812336,0.000016064125,0.000018243198,0.000029871562,0.00047869515],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965397,0.000017590974,0.00042294114,0.0016376919,0.0008716893,0.0005103615],"domain_scores_gemma":[0.99737453,0.00029616436,0.000245251,0.0017377265,0.00017520344,0.00017112227],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003644483,0.00044153564,0.00038710053,0.00068720535,0.0004114106,0.00039151666,0.002888209,0.0002490411,0.000024744837],"category_scores_gemma":[0.000057990288,0.0004124183,0.0001027387,0.0006435431,0.00097368995,0.00049505796,0.0007631057,0.0007569623,0.00015862132],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011830228,0.000021221782,0.0000014577774,0.000004946114,0.0000051599213,0.000032735283,0.00019919562,0.0027072595,0.000018160126,0.048067134,0.00025699666,0.9486846],"study_design_scores_gemma":[0.00035086393,0.00032891575,0.000058361526,0.00038583612,0.000008149005,0.0007730131,2.0224995e-7,0.71138275,0.0011955529,0.26274997,0.02164489,0.001121522],"about_ca_topic_score_codex":0.00001796728,"about_ca_topic_score_gemma":0.0000051295565,"teacher_disagreement_score":0.94756305,"about_ca_system_score_codex":0.00024289037,"about_ca_system_score_gemma":0.00048329393,"threshold_uncertainty_score":0.99983275},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000004169511,0.000047447942,0.038047098,0.0011853592,0.000132717,0.00024330812,0.0008400644,0.00020108664,0.95929873],"genre_scores_gemma":[0.11656731,0.00016030652,0.27108812,0.006199091,0.0014925575,0.00021327863,0.000701065,0.00013742852,0.6034408],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980982,0.000030909985,0.00042072212,0.00081354525,0.00039956733,0.00023704555],"domain_scores_gemma":[0.99818796,0.00014039346,0.00047872486,0.0008817856,0.00015784163,0.00015332234],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001961652,0.00031650809,0.00031688358,0.000110424706,0.00026607225,0.0003390586,0.00063240953,0.0003094063,0.0000018829156],"category_scores_gemma":[0.0000699708,0.00030893294,0.000104878854,0.000069362606,0.00007672132,0.0001301187,0.00013680747,0.00028184557,0.000118812415],"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":[0.0000046924088,0.0000130896005,7.7576755e-7,0.0000016447649,0.000055937868,0.0000034462034,0.00007132708,0.0000018009107,0.00000972532,0.8638517,0.0068232273,0.12916261],"study_design_scores_gemma":[0.00064697536,0.00027836335,0.0032762005,0.00016992979,0.00015436279,0.000012687754,0.00002121952,0.0170992,0.000022683364,0.8670091,0.11053559,0.0007736712],"about_ca_topic_score_codex":0.000029958605,"about_ca_topic_score_gemma":0.000025583106,"teacher_disagreement_score":0.3558579,"about_ca_system_score_codex":0.00029802864,"about_ca_system_score_gemma":0.0001800179,"threshold_uncertainty_score":0.9999363},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017583474,0.00021395208,0.072314605,0.00023198864,0.0005370732,0.00023484428,0.00030986808,0.00024598205,0.92573583],"genre_scores_gemma":[0.37270924,0.00017301682,0.50978875,0.007527629,0.0030841103,0.0005413538,0.00026724717,0.0003107701,0.10559786],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99802774,0.00001300049,0.00045905213,0.00074225693,0.00040859924,0.00034933808],"domain_scores_gemma":[0.99885947,0.000059521102,0.00021002251,0.0006561671,0.000069660986,0.00014514262],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00014153575,0.00033760237,0.00033274633,0.0001207785,0.00014553375,0.00018836149,0.00090988184,0.0002370622,0.000018139748],"category_scores_gemma":[0.00001201914,0.00036474445,0.00012830473,0.00004366601,0.0001265616,0.0001257906,0.0003632881,0.00033070042,0.00012380112],"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":[0.0000010153362,0.0000166703,0.0000663533,0.000008848788,0.00003482932,0.00020306538,0.00019804036,0.000012261421,0.000010800608,0.6754066,0.0044627506,0.3195788],"study_design_scores_gemma":[0.0023117594,0.0003167635,0.0024757637,0.0025723553,0.000085912914,0.0037164895,0.00010668989,0.02218361,0.00018760418,0.30049223,0.6611042,0.0044466215],"about_ca_topic_score_codex":0.0003573277,"about_ca_topic_score_gemma":0.00023311954,"teacher_disagreement_score":0.820138,"about_ca_system_score_codex":0.00029718102,"about_ca_system_score_gemma":0.0002987047,"threshold_uncertainty_score":0.99988043},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003156261,0.0001668066,0.43558052,0.00007928662,0.00044252092,0.00037297272,0.00053746457,0.0001799937,0.5626089],"genre_scores_gemma":[0.008902886,0.000010900498,0.8850296,0.0005816911,0.0021758585,0.00011098406,0.0002334015,0.00008184509,0.102872804],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988035,0.000007358507,0.00028635698,0.00034858932,0.00027638013,0.00027779338],"domain_scores_gemma":[0.99879557,0.000049223756,0.00039920877,0.00051173056,0.00015804765,0.000086205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023818787,0.0002100181,0.00021885878,0.000046052068,0.00017858183,0.0001830066,0.0004612279,0.000302404,0.0000032238152],"category_scores_gemma":[0.00001949398,0.00021312505,0.00012825633,0.0000161349,0.000013748537,0.0002419569,0.00017199974,0.0001089907,0.00008169562],"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":[0.0000011378605,0.0000043404693,0.000008395522,0.000009462037,0.00002769582,2.861098e-7,0.000020731359,0.0000035993583,0.000014189959,0.9252072,0.0009597827,0.0737432],"study_design_scores_gemma":[0.00024003067,0.000031046256,0.00009636454,0.00011073746,0.00009170103,0.000011971328,0.000002250301,0.023714425,0.000052569856,0.7521524,0.22300123,0.0004953042],"about_ca_topic_score_codex":0.000053729418,"about_ca_topic_score_gemma":0.000012658545,"teacher_disagreement_score":0.45973608,"about_ca_system_score_codex":0.0007052392,"about_ca_system_score_gemma":0.00012349593,"threshold_uncertainty_score":0.8690987},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017612124,0.0044279923,0.9677124,0.004779201,0.0015527278,0.00041525476,0.000080455895,0.0002408691,0.0031789623],"genre_scores_gemma":[0.21529922,0.0015727861,0.7694806,0.0034941563,0.008157976,0.00003072065,0.00015012131,0.000101649246,0.0017127708],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966873,0.00021108043,0.00070033694,0.0010561774,0.00058072375,0.00076437136],"domain_scores_gemma":[0.99606293,0.00023108134,0.0004189098,0.002758599,0.00013236186,0.0003961172],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0014678772,0.0004834327,0.00049981946,0.00016035198,0.0009793082,0.0027660443,0.0055284314,0.000128459,0.000017271877],"category_scores_gemma":[0.000037346214,0.00035418247,0.0001363587,0.0005490521,0.00018695217,0.0026513878,0.0024785814,0.0008731418,0.000085353786],"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":[0.00002251791,0.00086000026,0.0005012712,0.00002876167,0.00019808381,0.000109878674,0.0029658524,0.00014182301,0.0002009576,0.016525455,0.5215384,0.45690703],"study_design_scores_gemma":[0.0018032021,0.00038327405,0.025287844,0.00021964968,0.00016770413,0.0043378077,0.0001824663,0.65447676,0.00008569286,0.002503131,0.30932727,0.0012251864],"about_ca_topic_score_codex":0.000016562308,"about_ca_topic_score_gemma":0.0000040304544,"teacher_disagreement_score":0.65433496,"about_ca_system_score_codex":0.00006778699,"about_ca_system_score_gemma":0.00025379684,"threshold_uncertainty_score":0.99989104},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000042256575,0.00006725871,0.9598421,0.0019078953,0.00038918667,0.000831595,0.00036014014,0.00012157881,0.03643803],"genre_scores_gemma":[0.038141686,0.0004218443,0.9536676,0.0041635437,0.00031214135,0.00022507916,0.0012585414,0.0000428431,0.0017667166],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99725676,0.000025535428,0.0009953988,0.0007262147,0.0005392802,0.00045682036],"domain_scores_gemma":[0.99315333,0.00060764083,0.00041036814,0.0051243757,0.00048635885,0.000217918],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0018761448,0.0003218265,0.00033743042,0.0008123234,0.0008029698,0.0014188539,0.008325228,0.00013250065,0.000012235813],"category_scores_gemma":[0.00011598138,0.00028291857,0.000049778355,0.00048461836,0.00078349997,0.0042300187,0.007615951,0.00026048027,0.000050547216],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.849284e-7,0.000016514556,0.000047491394,0.000020061083,0.000008109185,1.4243679e-7,0.0018726102,0.000028890081,0.0000031803745,0.33828208,0.00086425483,0.6588557],"study_design_scores_gemma":[0.0004911913,0.000120322846,0.0007233899,0.0004926239,0.000012002074,0.000021246029,0.000040736137,0.6530701,0.0000046807704,0.01790167,0.32649794,0.0006240948],"about_ca_topic_score_codex":0.000016657554,"about_ca_topic_score_gemma":0.000018573324,"teacher_disagreement_score":0.6582316,"about_ca_system_score_codex":0.00018097974,"about_ca_system_score_gemma":0.00043223845,"threshold_uncertainty_score":0.9999623},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027402833,0.00032010797,0.9685919,0.0027666076,0.0007689027,0.000029805096,0.000078424564,0.000018527175,0.000022875904],"genre_scores_gemma":[0.6329951,0.0007625376,0.36597013,0.00003343167,0.00018336042,5.467889e-7,0.000008326563,0.000004787208,0.00004173511],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992012,0.000023311148,0.00027470494,0.00012821863,0.00029759435,0.00007499242],"domain_scores_gemma":[0.9985437,0.00026034663,0.0005828041,0.00022419637,0.00037006027,0.000018940127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054959225,0.000060538023,0.00010317693,0.00019527685,0.00003241074,0.000076495984,0.0010940538,0.00012404089,9.136247e-7],"category_scores_gemma":[0.00033683336,0.00004192306,0.000026340758,0.00010124126,0.000023018802,0.000898197,0.00022207251,0.00016759317,9.4975223e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017736653,0.00007687928,0.0011448992,0.000003700251,0.00016949073,0.000012204331,0.000046980844,0.000087671135,0.022738846,0.009799045,0.0009729469,0.9649296],"study_design_scores_gemma":[0.0018471883,0.00027897817,0.010478953,0.00062426296,0.00013146963,0.0011492934,0.00019374596,0.8590331,0.013177452,0.08785995,0.024723185,0.0005024206],"about_ca_topic_score_codex":0.0000040529726,"about_ca_topic_score_gemma":0.0000021722833,"teacher_disagreement_score":0.9644272,"about_ca_system_score_codex":0.000095538126,"about_ca_system_score_gemma":0.00007237337,"threshold_uncertainty_score":0.20330425},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003877118,0.0049430258,0.51635593,0.0003993431,0.00028451247,0.0020129574,0.0029231184,0.00047279295,0.46873122],"genre_scores_gemma":[0.541754,0.00015931884,0.44360366,0.0010090708,0.0012460188,0.00046806003,0.0005658761,0.00019508215,0.010998884],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985002,0.0000085432375,0.00023886017,0.00077559863,0.00019040088,0.00028639295],"domain_scores_gemma":[0.99849546,0.000044356075,0.00013511984,0.0011074359,0.00005398438,0.00016364799],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00008949297,0.00029123024,0.00030380097,0.00006764294,0.00014350408,0.00021335947,0.0008636428,0.00016592264,0.00000225986],"category_scores_gemma":[0.0000077835,0.00025909342,0.000015785607,0.00008880811,0.00012655374,0.00019908241,0.00097351073,0.00015006152,0.000009047633],"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":[0.000007470104,0.000032990676,0.0006047662,0.000042788644,0.000025440464,0.000024000208,0.00016306365,0.0000044662406,0.0000045776746,0.689157,0.00034695579,0.30958644],"study_design_scores_gemma":[0.0036838336,0.000602496,0.03886378,0.0016846358,0.00055001676,0.003681052,0.00010501322,0.024191722,0.00007656903,0.11090428,0.808953,0.006703603],"about_ca_topic_score_codex":0.0001528558,"about_ca_topic_score_gemma":0.00014506104,"teacher_disagreement_score":0.808606,"about_ca_system_score_codex":0.000044491022,"about_ca_system_score_gemma":0.00017115695,"threshold_uncertainty_score":0.9999861},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000053156564,0.0001737789,0.91760796,0.0001392173,0.00016579572,0.00053523824,0.000101970836,0.00022635222,0.08099653],"genre_scores_gemma":[0.000028417366,0.00021622347,0.9497977,0.00006984605,0.00017770645,0.000034774395,0.000032850625,0.00009546329,0.049547005],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970551,0.00000526699,0.0010247071,0.0007872528,0.00058882096,0.00053881644],"domain_scores_gemma":[0.9976008,0.0005255896,0.0008144683,0.00060933223,0.00027321032,0.0001765981],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00094906916,0.0005525588,0.0008144205,0.000323438,0.00017070762,0.0006792468,0.0013981641,0.00029439476,0.000010295828],"category_scores_gemma":[0.00024010029,0.00056508614,0.000052950756,0.00018167224,0.0001696375,0.0002390914,0.0011207259,0.00070357707,0.00013792541],"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":[2.8635102e-7,0.00009734457,0.000008389799,0.0018733419,0.000028439854,0.000008675849,0.0028265708,0.0000032101066,0.0000108796185,0.93486243,0.036304574,0.023975829],"study_design_scores_gemma":[0.00022323572,0.000047599267,0.000026962762,0.0011375342,0.00005277458,0.000052139952,0.00008624739,0.459094,0.000013467491,0.47605082,0.06252813,0.0006870847],"about_ca_topic_score_codex":0.0000073856622,"about_ca_topic_score_gemma":0.00000911717,"teacher_disagreement_score":0.45909077,"about_ca_system_score_codex":0.00014819043,"about_ca_system_score_gemma":0.00014475208,"threshold_uncertainty_score":0.99968004},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.8743135e-7,0.000076754775,0.53325707,0.000087081215,0.00009114785,0.00028514687,0.0006871139,0.00031470376,0.46520078],"genre_scores_gemma":[0.00014771827,0.0000102494905,0.9386133,0.0006444318,0.00070033333,0.00009067564,0.0004313012,0.000040749055,0.05932124],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984246,0.0000054470806,0.00032262932,0.00078545697,0.00023464787,0.00022720384],"domain_scores_gemma":[0.99767053,0.00004203762,0.00022469598,0.001865426,0.00011225104,0.00008506161],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018830317,0.00025701176,0.00024057139,0.000056406338,0.00014268115,0.00027676084,0.0023294385,0.00022147594,0.0000048019047],"category_scores_gemma":[0.000019877329,0.0002694886,0.00006339175,0.00002584877,0.00004301247,0.00023643812,0.00095789495,0.00008118637,0.000036692094],"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":[7.2151096e-7,0.000003830272,2.4300408e-7,0.0000069730922,0.0000118955095,9.533237e-7,0.00001158115,9.8644826e-8,0.0000024518042,0.63748115,0.019514661,0.34296542],"study_design_scores_gemma":[0.00009462469,0.000049445385,9.27274e-7,0.00012431401,0.000033481232,0.000018370545,0.0000019371846,0.02714665,0.00006717928,0.10175832,0.8703528,0.00035196228],"about_ca_topic_score_codex":0.000015432135,"about_ca_topic_score_gemma":0.00002398582,"teacher_disagreement_score":0.8508381,"about_ca_system_score_codex":0.000088190376,"about_ca_system_score_gemma":0.00015782687,"threshold_uncertainty_score":0.99997574},"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000018000787,0.0002461683,0.04243082,0.00014126013,0.00026911355,0.00015056673,0.00019039793,0.00029884066,0.95627105],"genre_scores_gemma":[0.002471278,0.0000736076,0.19825114,0.0021985923,0.00091949326,0.00006939733,0.000036558093,0.00007580046,0.79590416],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985894,0.0000050866834,0.00025180614,0.000582063,0.00031861477,0.0002530398],"domain_scores_gemma":[0.99842757,0.000018460736,0.00013979015,0.0011953958,0.000070181886,0.00014859461],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000050381677,0.00027834193,0.0002585175,0.00003956505,0.00014682255,0.00013081168,0.0013694509,0.00020718182,0.000013426469],"category_scores_gemma":[0.0000044994563,0.00027819892,0.00013375185,0.000021861193,0.00007972072,0.000077846096,0.00049119774,0.00019438185,0.0010766736],"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":[4.0483422e-7,0.0000039450492,4.119179e-7,0.000003239458,0.000017130937,0.000041098338,0.000021094871,3.5687813e-7,9.04876e-7,0.8674296,0.049429454,0.08305237],"study_design_scores_gemma":[0.00010260938,0.000031630454,0.00001262274,0.000052997322,0.000011637117,0.00015571385,6.487383e-7,0.00051492866,0.000010463134,0.200325,0.79843974,0.00034198977],"about_ca_topic_score_codex":0.000034063472,"about_ca_topic_score_gemma":0.000008918673,"teacher_disagreement_score":0.7490103,"about_ca_system_score_codex":0.000093588045,"about_ca_system_score_gemma":0.00018193093,"threshold_uncertainty_score":0.99996704},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012881773,0.00013741404,0.9832921,0.006348676,0.0013275682,0.00034367325,0.00003361753,0.00018725214,0.008200894],"genre_scores_gemma":[0.028675111,0.000021449483,0.9651836,0.0040564924,0.0011350838,0.00004705649,0.0000069606863,0.000058551443,0.0008156937],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99596214,0.000042063544,0.00050421583,0.0016963729,0.001054069,0.000741153],"domain_scores_gemma":[0.99537927,0.0015363069,0.000350509,0.0023947824,0.00016784719,0.00017125836],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0010772323,0.00053998025,0.0004034797,0.00049504556,0.0005612782,0.0010282126,0.005666009,0.00022664196,0.000022376124],"category_scores_gemma":[0.00016262349,0.00034831025,0.00013056066,0.00057268766,0.00067590235,0.00050126616,0.0016548678,0.0006259987,0.00010896032],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010281564,0.000020540918,0.0000047096178,0.0000058170276,0.000008351701,0.000021099704,0.00023074169,0.0004913494,0.00055866316,0.17397492,0.00019850704,0.8244843],"study_design_scores_gemma":[0.000426634,0.0004914956,0.00014089233,0.0024159804,0.000020903446,0.00013799637,8.698574e-7,0.5662587,0.006545712,0.36021978,0.061515685,0.0018253091],"about_ca_topic_score_codex":0.000012002951,"about_ca_topic_score_gemma":0.000028648465,"teacher_disagreement_score":0.82265896,"about_ca_system_score_codex":0.00034247863,"about_ca_system_score_gemma":0.0002990889,"threshold_uncertainty_score":0.9998969},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000069262715,0.026593227,0.06696779,0.002771796,0.0010006983,0.0013134177,0.014998795,0.00038056227,0.88590443],"genre_scores_gemma":[0.00002647027,0.08484386,0.5632989,0.00036902868,0.00017744846,0.00018098473,0.0046235844,0.000063989886,0.3464158],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99747837,0.000034273537,0.00053490093,0.0012223831,0.0003476963,0.00038238923],"domain_scores_gemma":[0.9973999,0.00026481855,0.00040235257,0.0018227358,0.00004215495,0.00006804106],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00070354715,0.00036310786,0.00040315994,0.00036754698,0.0001489014,0.0002772098,0.0012960101,0.00010086481,0.00003744057],"category_scores_gemma":[0.00007850646,0.000356795,0.000018271186,0.00017335656,0.00009084649,0.007901314,0.0037863005,0.00016342507,0.00002199671],"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":[0.000031669715,0.000045745564,0.00033948297,0.00035121338,0.00012456425,0.00033393083,0.0007195538,0.000008942529,0.000010832212,0.27293438,0.024685666,0.700414],"study_design_scores_gemma":[0.00043867494,0.000029285036,0.00006230217,0.001520628,0.000027572329,0.000005757752,0.00026765384,0.0010522649,0.000010610376,0.001714935,0.99439263,0.00047768326],"about_ca_topic_score_codex":0.0000067227124,"about_ca_topic_score_gemma":0.00035323584,"teacher_disagreement_score":0.96970695,"about_ca_system_score_codex":0.00013474996,"about_ca_system_score_gemma":0.00004363329,"threshold_uncertainty_score":0.9998884},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000082979226,0.0038054772,0.99375296,0.0002840704,0.00045793838,0.00015923938,0.000027342894,0.0000696639,0.0013603534],"genre_scores_gemma":[0.009964846,0.00065744016,0.9843667,0.00047432745,0.00045828705,0.00003514254,0.00019831494,0.00003546554,0.0038094902],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973432,0.00006916841,0.00033654054,0.001443878,0.00035081225,0.00045644364],"domain_scores_gemma":[0.9981598,0.00065213855,0.00012630624,0.0008845591,0.00007398357,0.000103207625],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007208863,0.00031425632,0.00038476594,0.0005436605,0.00020282602,0.00086875836,0.0016843686,0.00010255741,0.000004036266],"category_scores_gemma":[0.00016084818,0.00029426249,0.000040429888,0.001362267,0.00037421394,0.0010657903,0.0030307935,0.00084632996,0.000009531654],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.4082825e-7,0.000062973886,0.00053818244,0.000054987784,0.000003818497,0.00007503403,0.0006352823,0.0015673075,0.000042908785,0.005790507,0.000077693534,0.99115044],"study_design_scores_gemma":[0.00022104719,0.000048599864,0.000416905,0.00062386796,0.0000039825327,0.00007538898,5.288969e-7,0.96533996,0.00022015332,0.0061775004,0.026387194,0.0004848892],"about_ca_topic_score_codex":0.000094733405,"about_ca_topic_score_gemma":0.0004144711,"teacher_disagreement_score":0.99066556,"about_ca_system_score_codex":0.00018039886,"about_ca_system_score_gemma":0.0010715568,"threshold_uncertainty_score":0.99995095},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009074926,0.00044725568,0.08088699,0.0004765199,0.003645964,0.0013560647,0.00039240814,0.00047059153,0.9114167],"genre_scores_gemma":[0.0044126855,0.0000022930135,0.065388285,0.00011755576,0.00016188493,0.00008810602,0.00013891397,0.000043461107,0.9296468],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967715,0.000019498697,0.0005853896,0.0013664925,0.0007000064,0.0005570956],"domain_scores_gemma":[0.99774665,0.00008965452,0.00036199566,0.0015072237,0.00013706142,0.00015739477],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007539053,0.00039769307,0.00041393423,0.0009920334,0.00033732565,0.001245634,0.0019758192,0.00013628858,0.00011161874],"category_scores_gemma":[0.000008254316,0.00036552778,0.000110321205,0.00026763295,0.0004257085,0.00028825953,0.00074682577,0.00047831118,0.00017862668],"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":[0.0000048680026,0.000046308276,0.00003976829,0.000054199732,0.000039391496,0.00026850795,0.0008037668,0.000014825676,0.0001670837,0.7773022,0.0022822774,0.21897683],"study_design_scores_gemma":[0.0009579902,0.000053616855,0.00029938307,0.0018147527,0.00004178946,0.000035378827,0.00004897184,0.0050255903,0.0015738086,0.05834048,0.9300278,0.0017804805],"about_ca_topic_score_codex":0.00006651546,"about_ca_topic_score_gemma":0.0032530022,"teacher_disagreement_score":0.92774546,"about_ca_system_score_codex":0.000121312245,"about_ca_system_score_gemma":0.00021974031,"threshold_uncertainty_score":0.99987966},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12786429,0.000008171036,0.86423385,0.002937849,0.00015064832,0.00006763511,0.000024454888,0.000235207,0.004477901],"genre_scores_gemma":[0.7714181,0.0000010776782,0.22690263,0.00016619476,0.00003999489,0.000015842117,0.0000026617035,0.0000033736696,0.0014501516],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991451,0.00001961533,0.00014556249,0.0003426245,0.00015173238,0.00019536981],"domain_scores_gemma":[0.99898237,0.00013807487,0.000038533002,0.0007184691,0.000041942018,0.00008063934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023754421,0.00007436776,0.00007922086,0.000035582158,0.00009470117,0.00006933422,0.00063849165,0.000026107416,0.0000856272],"category_scores_gemma":[0.000038947543,0.000044593067,0.000026266065,0.00020615457,0.0000368402,0.0000950704,0.00023678073,0.000025520267,0.00031414555],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012722307,0.00010117732,0.00040998711,0.0000024958176,0.000006341449,0.0000025254853,0.00016088599,0.00000760531,0.0022123426,0.12230581,0.021224104,0.85356545],"study_design_scores_gemma":[0.0016751678,0.0001402607,0.06951735,0.00008076658,0.00001166446,0.000022343493,0.00008714782,0.67438513,0.014279322,0.0050607026,0.23392232,0.0008178325],"about_ca_topic_score_codex":0.00003794691,"about_ca_topic_score_gemma":0.000004045763,"teacher_disagreement_score":0.8527476,"about_ca_system_score_codex":0.000016198443,"about_ca_system_score_gemma":0.00002863888,"threshold_uncertainty_score":0.40378106},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007328841,0.000057695554,0.05904832,0.0052067824,0.0019952531,0.00028063715,0.0009850545,0.000054423756,0.93229854],"genre_scores_gemma":[0.009056454,0.00028480438,0.41280118,0.00129552,0.0009178858,0.000096823605,0.0013381523,0.00004719369,0.574162],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99849594,0.0000042078805,0.00027729213,0.0006345861,0.00042777028,0.00016018102],"domain_scores_gemma":[0.99831164,0.000029273184,0.00029356751,0.0011164871,0.000206,0.000043034604],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00016041064,0.00017422668,0.00017771959,0.00007513912,0.00008619999,0.00028980194,0.008103539,0.000104784165,0.00041753324],"category_scores_gemma":[0.000032228465,0.0001186838,0.00004098489,0.00028048386,0.000081743674,0.00039174396,0.0021319634,0.00023229996,0.00060044654],"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":[9.268548e-7,0.00006804158,0.0000030072622,0.00002133856,0.000027952048,1.8937595e-7,0.00014384407,0.000015840467,0.00007717126,0.103188545,0.8791119,0.017341252],"study_design_scores_gemma":[0.00042873013,0.000077497156,0.000115760304,0.0010397283,0.000020275123,0.000021533473,0.00019123299,0.091163814,0.0014170028,0.0013395544,0.9036609,0.0005240029],"about_ca_topic_score_codex":0.00007335306,"about_ca_topic_score_gemma":0.000005113706,"teacher_disagreement_score":0.35813656,"about_ca_system_score_codex":0.000047621772,"about_ca_system_score_gemma":0.0003426857,"threshold_uncertainty_score":0.9972631},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000024534756,0.00013694,0.9760935,0.000059678165,0.00040403684,0.0003442139,0.00072388456,0.00015739295,0.022055853],"genre_scores_gemma":[0.00022054129,0.00015477145,0.97975236,0.00019045749,0.00018947432,0.000045366924,0.0016253339,0.000022508118,0.017799163],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988005,0.0000012135989,0.00042272705,0.0003418399,0.00009718054,0.00033651572],"domain_scores_gemma":[0.9985598,0.00005655965,0.00017910817,0.0010021025,0.000107536755,0.000094917836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049614365,0.00024185261,0.00024132595,0.00030471245,0.00019824116,0.00027150955,0.0022892375,0.0001791806,0.0000025188963],"category_scores_gemma":[0.00003807659,0.00019949164,0.000029596726,0.00013831121,0.00031321577,0.0006358901,0.001004961,0.000196162,0.000011754622],"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":[0.0000017865439,0.000016600796,0.0000064945443,0.00015812715,0.000048231457,8.690371e-7,0.00041669756,0.00052637095,0.00081507396,0.8309577,0.021000197,0.14605184],"study_design_scores_gemma":[0.0000680026,0.000031135867,0.0000040746045,0.00003392582,0.0000060797624,0.000015250095,0.000005306752,0.45070645,0.000022698683,0.000488709,0.5484475,0.00017084181],"about_ca_topic_score_codex":0.0000066113735,"about_ca_topic_score_gemma":0.000003909306,"teacher_disagreement_score":0.830469,"about_ca_system_score_codex":0.000033377943,"about_ca_system_score_gemma":0.00016091236,"threshold_uncertainty_score":0.8135033},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000025607053,0.00022809133,0.39292854,0.00013749243,0.00010554124,0.0002586376,0.0017877654,0.0006561221,0.60389525],"genre_scores_gemma":[0.0012684048,0.000030916854,0.98907447,0.00040077217,0.00038980134,0.000017329497,0.000688334,0.000061511295,0.008068436],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968709,0.000015862819,0.00046979092,0.0016967746,0.00054582936,0.0004008484],"domain_scores_gemma":[0.99255574,0.00006469623,0.0003821722,0.006714126,0.000127183,0.0001560829],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00027219157,0.0004998894,0.0004639873,0.00008213359,0.00030023596,0.00050922413,0.008335904,0.0002399012,0.0000038694993],"category_scores_gemma":[0.00003649701,0.00043078765,0.000042750642,0.00006639191,0.00017591941,0.0006728246,0.0065298597,0.00041332093,0.00003472336],"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":[0.0000032274668,0.000010636941,0.0000035223945,0.000021049,0.00006933762,0.00016411846,0.00017943475,4.46674e-7,0.0000040788595,0.3452737,0.027709056,0.6265614],"study_design_scores_gemma":[0.00039910036,0.00027396844,0.000008807167,0.0025988114,0.00018999804,0.0021208436,0.00010532878,0.051910903,0.000113014554,0.024667442,0.91524976,0.0023620308],"about_ca_topic_score_codex":0.00018964277,"about_ca_topic_score_gemma":0.00011477047,"teacher_disagreement_score":0.8875407,"about_ca_system_score_codex":0.0001188694,"about_ca_system_score_gemma":0.0005383831,"threshold_uncertainty_score":0.9998144},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00035997896,0.00004267013,0.99096096,0.00023519695,0.0027702919,0.0009452716,0.0005235268,0.0003951721,0.0037669477],"genre_scores_gemma":[0.006038932,0.000050229824,0.9832474,0.0002250076,0.00078706606,0.00015756462,0.00094075635,0.000051687915,0.008501337],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971043,0.0000022405127,0.0006042265,0.0009541062,0.0007477655,0.00058739557],"domain_scores_gemma":[0.9981048,0.000051871153,0.00029455454,0.0009040907,0.00036850123,0.00027618167],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0020486393,0.0003581223,0.00030221106,0.001521489,0.0005635463,0.0037794146,0.0027839467,0.00009158473,0.0000052697205],"category_scores_gemma":[0.000044005556,0.0003602622,0.000035656667,0.00074720895,0.0002832607,0.020185143,0.0012833081,0.0003132914,0.00002016276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026575115,0.000025549196,0.00000776365,0.00017054069,0.0000073683277,5.447508e-7,0.0012545446,0.0004535081,0.00003906622,0.5137938,0.00085327297,0.48339137],"study_design_scores_gemma":[0.00014058319,0.000063551444,0.00008649946,0.00022883384,0.0000064692563,0.00001867236,0.000013856226,0.7538476,0.000053120835,0.00039673978,0.24476612,0.00037797831],"about_ca_topic_score_codex":0.0000037686675,"about_ca_topic_score_gemma":0.000005445195,"teacher_disagreement_score":0.75339407,"about_ca_system_score_codex":0.00016073363,"about_ca_system_score_gemma":0.0001872007,"threshold_uncertainty_score":0.99988496},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000057939556,0.00042884,0.97863436,0.0060376753,0.0011098868,0.000329872,0.000078956065,0.00017322005,0.013201424],"genre_scores_gemma":[0.001029099,0.0002651015,0.98587304,0.002106094,0.0008548244,0.000015344518,0.000074865755,0.000058526017,0.009723125],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99643314,0.00003343374,0.00040756934,0.0018520831,0.0007004574,0.000573324],"domain_scores_gemma":[0.99321306,0.0011716168,0.00028549778,0.0050922967,0.000071965325,0.00016556574],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0010617243,0.0003673833,0.00030138087,0.0002339911,0.0009438265,0.0030610862,0.025115302,0.0001691482,0.000026768896],"category_scores_gemma":[0.00009131594,0.00023600223,0.00004769032,0.00050160993,0.0007176307,0.0028142517,0.0230522,0.00044617482,0.00016368444],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020573539,0.0000087644885,0.000008861952,0.0000037466723,0.0000054474776,0.00001147648,0.000109295834,0.00009073387,0.000010390841,0.014838578,0.0026964087,0.9822142],"study_design_scores_gemma":[0.0002095589,0.00006442932,0.000031405605,0.00039500912,0.000005736054,0.000041935873,3.5700816e-7,0.41443262,0.00015218955,0.036656506,0.54752845,0.0004817954],"about_ca_topic_score_codex":0.000010742778,"about_ca_topic_score_gemma":0.000015454558,"teacher_disagreement_score":0.9817324,"about_ca_system_score_codex":0.00007547386,"about_ca_system_score_gemma":0.0006228227,"threshold_uncertainty_score":0.99797386},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008610537,0.06606994,0.57493854,0.004140581,0.00085919234,0.0014200571,0.05228002,0.0001912256,0.30001435],"genre_scores_gemma":[0.000048683953,0.026171833,0.9016826,0.0001543722,0.00004460115,0.000034544915,0.014664901,0.00003612954,0.05716234],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99722105,0.000019641428,0.00056078995,0.0015676748,0.0003615076,0.00026931777],"domain_scores_gemma":[0.99429613,0.00057111325,0.00035041937,0.0046488475,0.000038255752,0.0000952325],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00059514405,0.00034951494,0.0003997457,0.000354246,0.00016304829,0.0001690368,0.002956936,0.00007199389,0.00006541776],"category_scores_gemma":[0.00008780988,0.00031665782,0.000016375612,0.000107821266,0.0003298981,0.00680711,0.007743735,0.0001051918,0.0000073509855],"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":[0.000029462946,0.000040616855,0.000087489505,0.00028280853,0.00004329711,0.000017393293,0.000039923627,0.0000034567697,0.0000027950493,0.13595095,0.011297851,0.85220397],"study_design_scores_gemma":[0.0005948433,0.000053614316,0.00009930451,0.002484087,0.00007726022,0.000013612877,0.00008088177,0.04275427,0.0000029506878,0.004431658,0.9489166,0.00049087673],"about_ca_topic_score_codex":0.000007203202,"about_ca_topic_score_gemma":0.00029669635,"teacher_disagreement_score":0.9376188,"about_ca_system_score_codex":0.000025725913,"about_ca_system_score_gemma":0.000087823224,"threshold_uncertainty_score":0.99992853},"labels":[],"label_agreement":null},{"id":"W2513061279","doi":"10.1007/s10115-016-0986-0","title":"EFIM: a fast and memory efficient algorithm for high-utility itemset mining","year":2016,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":239,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Computer science; Key (lock); Data mining; Projection (relational algebra); Database transaction; Task (project management); Tree (set theory); Algorithm; High memory; Database; Mathematics; Parallel computing","score_opus":0.012865336366108314,"score_gpt":0.2381222319819108,"score_spread":0.22525689561580248,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2513061279","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006712245,0.0003578088,0.98954517,0.0001816323,0.00042065998,0.00041288193,0.00021850383,0.000104664476,0.0020464307],"genre_scores_gemma":[0.92334944,0.00008428992,0.07429645,0.000121844234,0.0003272239,0.00057721615,0.0001028264,0.0000128011525,0.0011278844],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991227,0.000025956433,0.0003644195,0.00019366558,0.00011010527,0.00018315374],"domain_scores_gemma":[0.99909204,0.00017271,0.00013784718,0.0003033266,0.00019065592,0.000103422135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054885296,0.000114391754,0.00016024747,0.000109299894,0.0002194931,0.00027700205,0.00021412801,0.00005614005,0.0000014843866],"category_scores_gemma":[0.00003823084,0.00007865322,0.00002025423,0.00016304702,0.00004770574,0.0014592917,0.00015270719,0.000029572158,0.000048237376],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010815351,0.000013942492,0.000022192164,0.000057253685,0.0000065971567,6.2817215e-8,0.0016184502,0.0000015816044,0.000019661271,0.00993299,0.0035381885,0.984788],"study_design_scores_gemma":[0.00097233587,0.00007488783,0.0013195783,0.00014375744,0.000008045311,0.000027875449,0.000555233,0.78966224,0.00026756898,0.000056502366,0.20669213,0.00021983216],"about_ca_topic_score_codex":0.000017628274,"about_ca_topic_score_gemma":0.000001267471,"teacher_disagreement_score":0.9845682,"about_ca_system_score_codex":0.000022524438,"about_ca_system_score_gemma":0.000039567763,"threshold_uncertainty_score":0.32073852},"labels":[],"label_agreement":null},{"id":"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063108252,0.000076077595,0.9897357,0.0030192423,0.00005449392,0.00041019983,0.00024629897,0.000039441537,0.000107695065],"genre_scores_gemma":[0.019033348,0.000020987683,0.979619,0.00013668311,0.0000375383,0.00006899884,0.00064913346,0.000005297006,0.00042901],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99912924,0.000028268852,0.00022027112,0.00035228042,0.00011094222,0.00015897537],"domain_scores_gemma":[0.995498,0.00085815083,0.000077756464,0.0034850203,0.00005321463,0.000027859827],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003148081,0.000057958605,0.00007727151,0.00003351595,0.00012577613,0.0003923128,0.0048137954,0.000017562232,0.000009534208],"category_scores_gemma":[0.0002536785,0.00003999558,0.000008110911,0.00019551118,0.000057653517,0.0030781897,0.0042566587,0.000039287235,0.0000031931113],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015768985,0.000046342084,0.00035423943,0.000010578846,0.0000105154795,1.5707049e-7,0.00075227837,0.000041110317,0.00018926492,0.014501664,0.17894907,0.8051432],"study_design_scores_gemma":[0.000114753544,0.000013184247,0.0017300673,0.000017725491,0.0000018949684,7.113258e-7,0.00008039954,0.9199384,0.00012435159,0.00080664,0.07711723,0.00005465645],"about_ca_topic_score_codex":0.00059112284,"about_ca_topic_score_gemma":0.000055877023,"teacher_disagreement_score":0.91989726,"about_ca_system_score_codex":0.000004788633,"about_ca_system_score_gemma":0.000036034984,"threshold_uncertainty_score":0.894531},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004130433,0.00050195045,0.99585664,0.0014188921,0.00065104687,0.00039947662,0.000073434785,0.000105122905,0.000580407],"genre_scores_gemma":[0.6155182,0.00012124506,0.37506738,0.0032133143,0.0047586914,0.00021266786,0.00008991004,0.000103840226,0.0009146981],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970808,0.000020657617,0.00039330576,0.0016127418,0.00040890183,0.00048358267],"domain_scores_gemma":[0.9982453,0.00037707863,0.0002063751,0.00085552793,0.00013746369,0.00017827578],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036893567,0.00039868066,0.0003739487,0.00030468157,0.00034131887,0.00063311734,0.0022503627,0.00023038794,0.0000049119503],"category_scores_gemma":[0.000024973473,0.00034054017,0.00006181457,0.0003735748,0.00021036473,0.0006792024,0.0018027966,0.00028604863,0.000042637465],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010120169,0.00001516957,0.00003368626,0.0000065158924,0.0000065592753,0.000004224763,0.0006600094,0.00042126095,0.00015222213,0.0064694006,0.000060354396,0.99216956],"study_design_scores_gemma":[0.00027321567,0.00008461138,0.0009751001,0.00042676643,0.000014271264,0.000012820475,4.649105e-7,0.968761,0.0003174165,0.023283346,0.004962242,0.0008887143],"about_ca_topic_score_codex":0.00003069977,"about_ca_topic_score_gemma":0.00012769975,"teacher_disagreement_score":0.99128085,"about_ca_system_score_codex":0.00017847997,"about_ca_system_score_gemma":0.0001757033,"threshold_uncertainty_score":0.99990463},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036696523,0.000003942701,0.9587591,0.0004547333,0.000056398527,0.00012830526,0.000039183542,0.00057212764,0.0032896663],"genre_scores_gemma":[0.2710006,0.000009354286,0.7277533,0.00006888086,0.00013944243,0.000035712084,0.000007966342,0.000011000401,0.00097378856],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908686,0.000018502986,0.00015705131,0.00037053204,0.00015091989,0.00021611337],"domain_scores_gemma":[0.9992369,0.000036668393,0.000071653194,0.0005189843,0.000059525933,0.000076268756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014107394,0.000113823626,0.000091193724,0.000082573424,0.00014109847,0.000115757706,0.0004080401,0.000045644327,0.000023094095],"category_scores_gemma":[0.000007936722,0.0000684495,0.000024339259,0.00024461575,0.00005669588,0.0006463984,0.0001564001,0.000039441107,0.00000818362],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000040387954,0.00007055305,0.0025437186,0.0000036741521,0.000020967875,0.0000041403887,0.00013545554,0.000002639269,0.010466684,0.009324036,0.0012714361,0.97615266],"study_design_scores_gemma":[0.0025857582,0.0017372785,0.009179864,0.0010221737,0.00012472906,0.00074294704,0.00061669387,0.56683344,0.35213658,0.0015076684,0.061449386,0.0020635047],"about_ca_topic_score_codex":0.000093402545,"about_ca_topic_score_gemma":0.000017277278,"teacher_disagreement_score":0.97408915,"about_ca_system_score_codex":0.000051697152,"about_ca_system_score_gemma":0.00006654862,"threshold_uncertainty_score":0.27912897},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9818921,0.00022857061,0.01045038,0.005374939,0.000018741905,0.00015742323,0.0002464608,0.000037776754,0.0015935918],"genre_scores_gemma":[0.98421395,0.00036577313,0.015050547,0.000035938683,0.00000812765,0.00001688774,0.0002565601,0.0000033197573,0.00004892544],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9981808,0.00018592754,0.00042232175,0.00029106752,0.0007495793,0.00017032],"domain_scores_gemma":[0.9953298,0.0009588023,0.0001754736,0.003007325,0.00047738364,0.000051236635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003019206,0.00007114588,0.00020605579,0.0002472422,0.00015332196,0.00013384948,0.0050451024,0.00007743416,0.0000326656],"category_scores_gemma":[0.0009732518,0.000045952085,0.000035828758,0.0014030857,0.0006666378,0.0009769407,0.00171808,0.00014050586,0.000010154837],"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":[0.00006637293,0.00046716363,0.060821604,0.00004737833,0.00029935778,0.0000022285149,0.004216517,0.00003616689,0.0019412899,0.49583575,0.0048773037,0.43138888],"study_design_scores_gemma":[0.0023801604,0.00032360104,0.5623119,0.001170314,0.000119702825,0.000007246576,0.0020248957,0.38196743,0.010612743,0.006452966,0.032027476,0.000601589],"about_ca_topic_score_codex":0.00031450533,"about_ca_topic_score_gemma":0.000214919,"teacher_disagreement_score":0.5014903,"about_ca_system_score_codex":0.000045230267,"about_ca_system_score_gemma":0.000076522665,"threshold_uncertainty_score":0.93751395},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.064897634,0.000023168459,0.9330827,0.0013566306,0.0005223806,0.000056527977,0.000015810047,0.000018610059,0.000026544443],"genre_scores_gemma":[0.451342,0.000017850785,0.54819024,0.00027511918,0.00017013664,4.1158293e-7,0.0000024589224,0.0000014336104,3.6491426e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987187,0.000027678076,0.00058034994,0.00014808885,0.00037837957,0.00014682295],"domain_scores_gemma":[0.99844724,0.00046897927,0.00058098877,0.00015605953,0.00030236878,0.00004437507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015641679,0.000080327765,0.0001267948,0.0003932093,0.0001361318,0.00058528985,0.0014917228,0.00003819461,0.000001068873],"category_scores_gemma":[0.00022673192,0.000056199307,0.000026783233,0.0002041336,0.00007207514,0.0053553735,0.00044608343,0.000069967355,4.9272046e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004024988,0.000015840202,0.0029946337,0.0000066809607,0.000013174361,0.0000013476338,0.0014111086,0.0003768565,0.00014092807,0.01598446,0.00009781308,0.9789531],"study_design_scores_gemma":[0.00031522903,0.00007942608,0.0024357792,0.00085474487,0.0000033781337,0.0001610874,0.00025019972,0.98985595,0.00061150815,0.0034906506,0.001811919,0.00013012503],"about_ca_topic_score_codex":0.000020738611,"about_ca_topic_score_gemma":0.0000014512826,"teacher_disagreement_score":0.9894791,"about_ca_system_score_codex":0.000040691582,"about_ca_system_score_gemma":0.00009702002,"threshold_uncertainty_score":0.5643963},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05728413,0.00016617782,0.9381247,0.0022592444,0.00083532365,0.0001336105,0.0000467136,0.000043479868,0.0011066067],"genre_scores_gemma":[0.761401,0.000016441027,0.23797885,0.00020544964,0.00019395657,0.000010723408,0.00006011142,0.000013514591,0.00011995434],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979456,0.00009142096,0.0006934705,0.0004291952,0.0005919692,0.00024833993],"domain_scores_gemma":[0.9974548,0.0003037047,0.00087237416,0.0005281025,0.0007762618,0.00006473957],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001493452,0.00015781615,0.00021538103,0.00066349085,0.00007167437,0.00027497346,0.003162733,0.00006312381,0.0000138432515],"category_scores_gemma":[0.00015004053,0.00013209113,0.000037945618,0.00056121155,0.000024188257,0.0024845512,0.0005310513,0.00009625499,0.000016923344],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008076838,0.0011607223,0.05786917,0.00039283058,0.00044285686,0.00019073093,0.0016527874,0.0014337215,0.0005322396,0.002367778,0.0013516326,0.93252474],"study_design_scores_gemma":[0.0026411174,0.000064871034,0.010649207,0.0021747842,0.00008078733,0.0000318376,0.0005767932,0.9765937,0.0004869371,0.00038353138,0.005991073,0.00032537853],"about_ca_topic_score_codex":0.000013002654,"about_ca_topic_score_gemma":0.00007792674,"teacher_disagreement_score":0.97515994,"about_ca_system_score_codex":0.00034056592,"about_ca_system_score_gemma":0.00021956116,"threshold_uncertainty_score":0.58771974},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005397895,0.0000062375134,0.9923015,0.0014879955,0.00009821065,0.00010501414,0.005231277,0.000037831513,0.00019212505],"genre_scores_gemma":[0.23936224,0.000028403741,0.7598459,0.00013852582,0.00007102769,0.000010497541,0.00015261663,0.0000049765285,0.00038581705],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987375,0.0000036747656,0.00018815856,0.00064209476,0.00023740226,0.00019115952],"domain_scores_gemma":[0.99434817,0.00008419239,0.000075792654,0.005309203,0.00010914763,0.00007347709],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0006583964,0.00006252126,0.00008703989,0.000071714116,0.00008198984,0.000086390195,0.008435399,0.000014472498,0.0000023633759],"category_scores_gemma":[0.00011396315,0.000038753893,0.000010847445,0.00029973206,0.00011886971,0.0014271796,0.0037304992,0.00001885289,0.000006569328],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.6125436e-7,0.00010803163,0.00023753871,0.00001254339,0.000012124918,2.9545924e-7,0.00005554881,0.000045354453,0.0036560844,0.099190734,0.011759026,0.88492185],"study_design_scores_gemma":[0.00011693022,0.000011225128,0.0001423512,0.0000146509365,0.000005749663,9.842013e-7,0.000005790855,0.99180174,0.0008442416,0.0016277442,0.0053567505,0.00007186501],"about_ca_topic_score_codex":0.00005199408,"about_ca_topic_score_gemma":0.000059780603,"teacher_disagreement_score":0.9917564,"about_ca_system_score_codex":0.0000138272635,"about_ca_system_score_gemma":0.00025891955,"threshold_uncertainty_score":0.99692947},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030039712,0.000010732543,0.99492544,0.0013898682,0.00011214755,0.00012324707,0.00026786886,0.000089322646,0.00007742699],"genre_scores_gemma":[0.77439713,0.00016534694,0.22234344,0.0008230215,0.00041822606,0.00006398132,0.00046062976,0.000022461429,0.0013057758],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992355,0.000008498615,0.00013804823,0.0003799561,0.00010191081,0.0001360651],"domain_scores_gemma":[0.9990509,0.000095831,0.00004599668,0.0006921636,0.000051671483,0.00006342748],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017899617,0.00006978609,0.000071280745,0.000046139903,0.00007866945,0.00014942946,0.00063255435,0.000025985526,0.0000059626136],"category_scores_gemma":[0.00004048782,0.000045421,0.0000108976,0.00011822078,0.000025176518,0.00042512963,0.00045825588,0.0000138021405,0.000008245208],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.1400186e-7,0.000043513664,0.00096116087,0.0000070354313,0.0000105556755,3.1617662e-7,0.000030554624,3.924292e-7,0.00040160894,0.08284014,0.0031987643,0.9125053],"study_design_scores_gemma":[0.0005561079,0.000104848696,0.0043200757,0.000032976128,0.000017539565,0.00000529961,0.000028992752,0.9075359,0.0019649433,0.00378802,0.08139326,0.0002520383],"about_ca_topic_score_codex":0.00003500279,"about_ca_topic_score_gemma":0.000031671567,"teacher_disagreement_score":0.9122533,"about_ca_system_score_codex":0.000011520925,"about_ca_system_score_gemma":0.000026521282,"threshold_uncertainty_score":0.18522146},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09724024,0.00014222934,0.778702,0.11819545,0.000049914222,0.0002604868,0.000002531974,0.0002018986,0.0052052545],"genre_scores_gemma":[0.77716666,0.000004663444,0.22081137,0.0019021166,0.000049494407,0.000015723424,0.000004235821,0.000004607721,0.000041126565],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992383,0.000023844597,0.00019862692,0.0002047948,0.00015395161,0.00018045117],"domain_scores_gemma":[0.99948853,0.00004854626,0.00010435585,0.00030988935,0.000019433572,0.000029225832],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025968632,0.00007537448,0.00010076479,0.000056734232,0.00008501208,0.00008665206,0.0007635433,0.000020045776,0.0000014045828],"category_scores_gemma":[0.000020229667,0.000055594035,0.000020449485,0.0004218026,0.00005436297,0.00025765356,0.000048273196,0.00009349352,0.000014516861],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025010606,0.00006226432,0.00021887619,0.000015363734,0.000002910932,0.0000054476172,0.003361938,0.00064953824,0.016368857,0.0012563289,0.0018571251,0.97619885],"study_design_scores_gemma":[0.0004701589,0.00005108803,0.026341368,0.00013434232,0.000007335421,0.000015437648,0.00009953773,0.9681873,0.0007548064,0.0030518589,0.00061452657,0.00027226206],"about_ca_topic_score_codex":0.00005388849,"about_ca_topic_score_gemma":0.000006506019,"teacher_disagreement_score":0.9759266,"about_ca_system_score_codex":0.000015894395,"about_ca_system_score_gemma":0.000040537205,"threshold_uncertainty_score":0.22670591},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005828365,0.0004724697,0.987887,0.0021998151,0.000054895747,0.0010249872,0.00024901118,0.0003496443,0.0019337969],"genre_scores_gemma":[0.8287853,0.00009045512,0.16448773,0.0002688569,0.00021729774,0.004856902,0.0000961534,0.000048118356,0.0011491913],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982366,0.000041103696,0.0002956171,0.00074617466,0.00029434866,0.00038618338],"domain_scores_gemma":[0.9981084,0.0002193491,0.0001446015,0.001123198,0.00014940926,0.00025505543],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021202496,0.0002422467,0.00025348694,0.00010830375,0.00037645927,0.00030644273,0.0006341613,0.00006901706,0.000013932876],"category_scores_gemma":[0.000009541085,0.00014437374,0.00001998979,0.0004766192,0.00027070942,0.00059846975,0.000111114896,0.00006904459,0.00008419393],"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":[0.00005198691,0.00085856614,0.018956557,0.00018468148,0.000478623,0.000058252714,0.007860366,0.000054433593,0.016386693,0.564913,0.100669906,0.28952694],"study_design_scores_gemma":[0.0029346645,0.00040590754,0.0026135426,0.00071079336,0.00003467896,0.0014654866,0.002874064,0.0112875085,0.0014785352,0.00022892265,0.9744717,0.0014942357],"about_ca_topic_score_codex":0.000114163886,"about_ca_topic_score_gemma":0.000027665816,"teacher_disagreement_score":0.87380177,"about_ca_system_score_codex":0.00004659308,"about_ca_system_score_gemma":0.00011337272,"threshold_uncertainty_score":0.58873904},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17146263,0.000024196626,0.82135105,0.0012949873,0.00031722226,0.00010354495,0.000014161094,0.00022345228,0.0052087847],"genre_scores_gemma":[0.67847395,0.0000016085662,0.32026896,0.00026711245,0.00012734755,0.000019159721,0.00005413434,0.000004036303,0.00078369403],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991234,0.000029977316,0.00015822955,0.0003281187,0.00019466391,0.00016561987],"domain_scores_gemma":[0.9990972,0.000016414377,0.00005055432,0.00059927825,0.000091380134,0.00014512645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003360159,0.000084885956,0.00009160593,0.000036631107,0.00010045949,0.00021202506,0.00045789967,0.00003341701,0.000015290312],"category_scores_gemma":[0.000029939081,0.000072631505,0.000015973026,0.00021048648,0.0000224638,0.00048786198,0.00016662183,0.00004870034,0.00010018444],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000046076893,0.00017317166,0.006956337,0.0000066087487,0.000025695428,0.000008529052,0.002005498,0.00010156806,0.001932394,0.108971454,0.20675631,0.6730578],"study_design_scores_gemma":[0.00036112047,0.000045039815,0.0030392366,0.00000437146,0.00000495847,0.000011437829,0.000057976544,0.9362668,0.0040681767,0.0009829586,0.0549584,0.0001995142],"about_ca_topic_score_codex":0.00051197706,"about_ca_topic_score_gemma":0.000116928524,"teacher_disagreement_score":0.9361652,"about_ca_system_score_codex":0.000024173183,"about_ca_system_score_gemma":0.00009492965,"threshold_uncertainty_score":0.2961827},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018224333,0.0003815277,0.99344563,0.0032922635,0.00026613878,0.00021608015,0.000024258405,0.000110020956,0.00044166853],"genre_scores_gemma":[0.45284346,0.0002135128,0.5435501,0.001215551,0.00079224835,0.0010212432,0.000006467759,0.000010543345,0.000346939],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99938107,0.000022756032,0.00023479854,0.00018058499,0.000093845956,0.00008692638],"domain_scores_gemma":[0.99877214,0.0005120347,0.000073166084,0.0005153144,0.00009486979,0.000032456996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047280855,0.000048449936,0.000086127555,0.000016664633,0.0000946746,0.00004231742,0.00049455,0.00003068758,0.0000053049253],"category_scores_gemma":[0.00004101191,0.000029672992,0.000052244806,0.00016675747,0.000031172836,0.00018740377,0.0000787513,0.00003797406,0.000024255894],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032347398,0.00014193039,0.00062004937,0.000010101157,0.000026654014,1.14180416e-7,0.00018990459,0.000028896633,0.000109027234,0.09052888,0.11510902,0.7932322],"study_design_scores_gemma":[0.00045406382,0.00013662929,0.0020986965,0.000021096506,0.000012961717,0.000001815739,0.00031719182,0.34347144,0.004499775,0.00004471771,0.6488277,0.000113976595],"about_ca_topic_score_codex":0.000023049788,"about_ca_topic_score_gemma":0.0000081814205,"teacher_disagreement_score":0.79311824,"about_ca_system_score_codex":0.000014598238,"about_ca_system_score_gemma":0.000035009387,"threshold_uncertainty_score":0.12100295},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00056131673,0.0000044219405,0.9961982,0.0021208103,0.00022164364,0.00011267706,0.0000037195964,0.00011482648,0.00066242425],"genre_scores_gemma":[0.66402084,0.0000040058553,0.33371428,0.0013253054,0.0005493562,0.00014059248,0.00003340157,0.000010231702,0.00020197855],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992849,0.000014953937,0.00013471466,0.0002744847,0.00009576946,0.00019515982],"domain_scores_gemma":[0.9994745,0.00010635472,0.00005429103,0.0002498937,0.000079820515,0.000035110086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022639638,0.00007839519,0.00007947697,0.00003279789,0.00022568037,0.00013081035,0.00047304426,0.000039635346,0.0000051436773],"category_scores_gemma":[0.000025736255,0.000069666785,0.000029611465,0.00020674527,0.00002117159,0.00015270051,0.000098874625,0.000043970176,0.00002140138],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.6635897e-7,0.000026258635,0.000017592623,0.000002910855,0.000002454631,8.1414676e-8,0.00008981465,0.00032260464,0.000016758551,0.037211474,0.0036275587,0.9586818],"study_design_scores_gemma":[0.00006130907,0.00003246538,0.0014154913,0.000011327408,0.0000023432683,0.0000010063427,0.000011124039,0.9905548,0.00009256534,0.0010015101,0.006713904,0.000102135535],"about_ca_topic_score_codex":0.000055802833,"about_ca_topic_score_gemma":0.000016611135,"teacher_disagreement_score":0.9902322,"about_ca_system_score_codex":0.000019767718,"about_ca_system_score_gemma":0.000014025897,"threshold_uncertainty_score":0.2840929},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060611006,0.000009469652,0.9310395,0.001998674,0.00008243814,0.00008633677,0.0000047352805,0.00017019655,0.00599766],"genre_scores_gemma":[0.72182995,9.894958e-7,0.27646524,0.00074369565,0.000065210144,0.00004872293,0.000016959328,0.00001047146,0.0008187742],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99887323,0.000027155977,0.00015343165,0.0004247801,0.0002485564,0.00027283153],"domain_scores_gemma":[0.99898636,0.000066242996,0.000054239947,0.0007359594,0.000046208657,0.00011096948],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020892147,0.00012895282,0.00011621,0.000053771204,0.00018430973,0.00027719676,0.00069961534,0.000027419135,0.000034841232],"category_scores_gemma":[0.000008677225,0.000085199885,0.00002920828,0.00025121344,0.000048639886,0.00014480828,0.00017501562,0.00006143977,0.00009758183],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028906911,0.00026916905,0.005707532,0.000015409945,0.000038070277,0.000008667902,0.0016904614,0.0013987774,0.0005152692,0.11328397,0.0050492873,0.8720205],"study_design_scores_gemma":[0.0003469688,0.00013596193,0.00644465,0.00003273306,0.0000073457954,0.000016936865,0.00008311868,0.96883255,0.00087017467,0.00030572084,0.022639968,0.0002838877],"about_ca_topic_score_codex":0.00017245291,"about_ca_topic_score_gemma":0.0000322757,"teacher_disagreement_score":0.96743375,"about_ca_system_score_codex":0.000026976537,"about_ca_system_score_gemma":0.00003563193,"threshold_uncertainty_score":0.34743503},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1838554,0.0000058138467,0.81055135,0.00062796386,0.000042381656,0.000046625188,0.004407068,0.000088999455,0.00037442043],"genre_scores_gemma":[0.7228026,0.0000013288867,0.27455622,0.00003480662,0.000045301727,0.0000031239388,0.002488217,0.0000034389416,0.000064972155],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915457,0.000014447666,0.00021870942,0.00034521057,0.0001327614,0.0001343233],"domain_scores_gemma":[0.9985133,0.00012913709,0.000085698644,0.0011963473,0.000039497674,0.00003601505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000087496024,0.000076234675,0.00011963468,0.000023334274,0.00004622624,0.00007554208,0.0012202114,0.00002791318,0.00003112381],"category_scores_gemma":[0.000010544705,0.000068068424,0.000017045024,0.00014399442,0.00004264844,0.00026200307,0.0004735753,0.000037420024,0.000010767574],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008814464,0.0011383694,0.056368805,0.00005265689,0.00018552016,0.00007338475,0.0005690731,0.00015545751,0.04968214,0.28838825,0.110205986,0.49317154],"study_design_scores_gemma":[0.00043246947,0.000018405866,0.028256552,0.00003293713,0.000013959625,0.0000068462546,0.00016863833,0.9586077,0.0075320923,0.0008771734,0.0038219786,0.00023126636],"about_ca_topic_score_codex":0.0017861942,"about_ca_topic_score_gemma":0.00005690536,"teacher_disagreement_score":0.9584522,"about_ca_system_score_codex":0.000005842435,"about_ca_system_score_gemma":0.000030595056,"threshold_uncertainty_score":0.277575},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005225329,0.000010265382,0.9205368,0.0018030776,0.000059192014,0.000015663969,6.2796215e-7,0.00013067857,0.07692114],"genre_scores_gemma":[0.035938006,6.939452e-7,0.95957994,0.0004998148,0.000034512694,0.0000074566183,0.0000020063605,0.0000013907459,0.0039361697],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9997717,0.000002722838,0.000032025666,0.00008254145,0.000058583024,0.000052425425],"domain_scores_gemma":[0.99965703,0.000006589607,0.000006319875,0.00025078325,0.000021386804,0.000057902686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000066162575,0.000018897425,0.000019383033,0.00001042992,0.000016121692,0.000055807475,0.00032941462,0.0000063354646,0.0000070624906],"category_scores_gemma":[0.000008598365,0.000014922983,0.0000055780347,0.00010259718,0.000005513643,0.00016712699,0.000097054035,0.000014532779,0.0005189662],"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":[5.946828e-8,0.000013728963,0.000043566095,1.82924e-7,8.884878e-7,8.254886e-7,0.000114225455,0.000001254002,0.0000149841835,0.5563515,0.13358852,0.3098703],"study_design_scores_gemma":[0.00015227262,0.000029014776,0.00060450606,0.000001222002,7.2601586e-7,0.000012091196,0.000046260775,0.19549347,0.0006617548,0.024243966,0.7786552,0.000099520934],"about_ca_topic_score_codex":0.000021386973,"about_ca_topic_score_gemma":0.000001152698,"teacher_disagreement_score":0.6450667,"about_ca_system_score_codex":0.0000044702615,"about_ca_system_score_gemma":0.000021298254,"threshold_uncertainty_score":0.6670434},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022813054,0.00012529336,0.95217943,0.0019112006,0.00014316471,0.00004045784,0.000013059847,0.00022724977,0.043078814],"genre_scores_gemma":[0.071677946,0.000098312026,0.9246962,0.0010134988,0.000263626,0.000013284082,0.00017687658,0.0000067376222,0.0020535062],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990826,0.000018123037,0.00013916673,0.00037620554,0.00023276405,0.00015114185],"domain_scores_gemma":[0.9985304,0.00008201222,0.000025372197,0.0012470867,0.00003242933,0.0000827303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002065668,0.00006427376,0.000074709526,0.000021231808,0.00019664105,0.000046003526,0.002069677,0.000043069016,0.0001616688],"category_scores_gemma":[0.00003282179,0.000054326214,0.000013344605,0.00027578964,0.000058187998,0.00089351286,0.0011404998,0.000062161096,0.0004035484],"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":[6.3739117e-7,0.00021811924,0.00026385213,0.0000050875387,0.000013608976,0.00003779245,0.0020826075,6.956648e-7,0.00003382193,0.08828514,0.5515082,0.35755047],"study_design_scores_gemma":[0.0002857574,0.000028319058,0.0017204299,0.000021341762,0.000003431705,0.00028218722,0.00005982222,0.6189115,0.00019114873,0.0006881409,0.37760642,0.00020149915],"about_ca_topic_score_codex":0.000038979695,"about_ca_topic_score_gemma":0.000008354704,"teacher_disagreement_score":0.6189108,"about_ca_system_score_codex":0.000008499374,"about_ca_system_score_gemma":0.000120065335,"threshold_uncertainty_score":0.51869327},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12672973,0.0015503445,0.8704819,0.00036103927,0.00034612883,0.00006488989,0.000021354634,0.0000750814,0.00036950415],"genre_scores_gemma":[0.975091,0.0009927264,0.02207855,0.00022786862,0.0014032848,0.000045663328,0.00005174749,0.000017702212,0.00009150669],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978727,0.00010150317,0.00048012298,0.00075586006,0.00024478536,0.00054499396],"domain_scores_gemma":[0.9988796,0.0004114144,0.00027364955,0.000299543,0.000038472688,0.00009732487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043240236,0.00024590644,0.0005451339,0.00018293744,0.0006091101,0.00023003765,0.0006043643,0.00015436353,0.000013392754],"category_scores_gemma":[0.000024087944,0.00020348441,0.00024893656,0.0013370505,0.00009346026,0.0007081816,0.00034511488,0.0001468447,0.0000015851255],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003856007,0.000029229022,0.055801094,0.0000013373937,0.00020733658,0.000012258514,0.0011124637,0.0011396052,0.000006323668,0.0011250614,0.0002040374,0.9403574],"study_design_scores_gemma":[0.0016945989,0.00006292551,0.1489605,0.00020428363,0.00078259996,0.0000016546411,0.0017908118,0.818296,0.000010874869,0.0016933674,0.025219621,0.0012827534],"about_ca_topic_score_codex":0.00014269492,"about_ca_topic_score_gemma":0.0008373075,"teacher_disagreement_score":0.93907464,"about_ca_system_score_codex":0.000046855646,"about_ca_system_score_gemma":0.00002081475,"threshold_uncertainty_score":0.8297853},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016853389,0.000037948004,0.9923975,0.0029427367,0.00015647935,0.000094315474,0.0018650922,0.000093386625,0.0007272435],"genre_scores_gemma":[0.5664449,0.0022975681,0.4100223,0.004548784,0.00076698395,0.000031751326,0.015248376,0.000029813951,0.00060956844],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991002,0.000011808052,0.00026004136,0.0002700678,0.00020322303,0.00015467877],"domain_scores_gemma":[0.99748844,0.0001109314,0.000141669,0.0020815595,0.00009887246,0.00007852175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035599858,0.00010644185,0.00010953259,0.00012267614,0.00014415907,0.00041432324,0.0020137634,0.000039266655,0.0000046507303],"category_scores_gemma":[0.00024556453,0.000073412804,0.000008457057,0.00037780395,0.0000423599,0.0100513045,0.002170306,0.000038827224,0.00008436767],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001582208,0.000015312471,0.00039111177,0.000025116282,0.000019131538,8.9992244e-7,0.00013331865,9.314632e-7,0.000029659697,0.010089088,0.028595733,0.9606981],"study_design_scores_gemma":[0.00040047,0.000022012153,0.012538263,0.00006931057,0.000026569525,0.0000274784,0.00012928761,0.49528298,0.000066530476,0.000116847645,0.49109757,0.00022267253],"about_ca_topic_score_codex":0.000030148713,"about_ca_topic_score_gemma":0.000009031492,"teacher_disagreement_score":0.96047544,"about_ca_system_score_codex":0.000011803791,"about_ca_system_score_gemma":0.0000676648,"threshold_uncertainty_score":0.7286953},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33771867,0.000014042683,0.660657,0.0004462218,0.00020291931,0.000052526033,0.0006398792,0.00004788713,0.00022085686],"genre_scores_gemma":[0.82778907,0.000017612943,0.17183414,0.00015217173,0.000030288282,0.0000074041964,0.0001034792,0.000004652844,0.00006116648],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99908084,0.000023387624,0.00020896437,0.00037851822,0.00017909895,0.00012917646],"domain_scores_gemma":[0.99846375,0.000121847974,0.00008843447,0.001246113,0.000023820592,0.00005606223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018239171,0.00007770869,0.00009634529,0.000045685763,0.000038836213,0.0000495343,0.0011956483,0.000024026227,0.0001566614],"category_scores_gemma":[0.0000182067,0.000052630643,0.000019342866,0.000057964222,0.0000380253,0.00046557645,0.00078868715,0.00002414363,0.00007582353],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029670925,0.00012585724,0.060146194,0.0000054246334,0.00007916222,0.0000033174165,0.00031773752,1.5070363e-7,0.05837722,0.004123803,0.00815334,0.8686648],"study_design_scores_gemma":[0.004449665,0.0004129443,0.69992805,0.0007344604,0.00012575924,0.000029115057,0.0006759952,0.039758127,0.19703759,0.0022060054,0.052897416,0.0017448869],"about_ca_topic_score_codex":0.0006454332,"about_ca_topic_score_gemma":0.00007228232,"teacher_disagreement_score":0.86691993,"about_ca_system_score_codex":0.000019198362,"about_ca_system_score_gemma":0.000021780872,"threshold_uncertainty_score":0.2221832},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009354086,0.000031333322,0.98373485,0.0018291887,0.000096388794,0.00006131148,0.000026489633,0.00007598975,0.0047903834],"genre_scores_gemma":[0.26910514,0.00006400871,0.71507925,0.005035883,0.00035473364,0.000035621735,0.000034851033,0.000016048209,0.010274455],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995255,0.000013488054,0.00007140784,0.00016857394,0.00009629404,0.00012475559],"domain_scores_gemma":[0.99928415,0.00016256442,0.000024423103,0.000483341,0.000018890341,0.000026650958],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000109400986,0.000051225703,0.000043385156,0.000008873894,0.00018617472,0.00009300067,0.0005881981,0.000011621492,0.00009988712],"category_scores_gemma":[0.000020286943,0.000036414753,0.00000967102,0.00016246644,0.00002943406,0.00005610169,0.00005279139,0.0000749851,0.0010194136],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.247922e-7,0.000020011288,0.0000032317428,0.0000013564953,0.0000017883773,6.7103065e-7,0.00031857044,0.00007957235,0.000022643942,0.2856639,0.047395907,0.666492],"study_design_scores_gemma":[0.00012896793,0.00003650394,0.0016522299,0.000042299525,0.000002367154,0.000008520909,0.000013072453,0.47134182,0.00039107003,0.031015282,0.4951451,0.00022274077],"about_ca_topic_score_codex":0.000006767553,"about_ca_topic_score_gemma":0.0000022029399,"teacher_disagreement_score":0.66626924,"about_ca_system_score_codex":0.000008019763,"about_ca_system_score_gemma":0.000012066862,"threshold_uncertainty_score":0.9997584},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00040501147,0.00037675703,0.9952852,0.0007094811,0.0013982849,0.00029018347,0.00033975518,0.00020127052,0.0009940461],"genre_scores_gemma":[0.030614233,0.000021597634,0.9667251,0.0011593129,0.0008602632,0.000012950955,0.00036406625,0.00004278823,0.00019968407],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99482894,0.000037331687,0.0006179751,0.002754465,0.0010885984,0.00067271985],"domain_scores_gemma":[0.99277085,0.0008401047,0.00037309088,0.0055946843,0.0001620365,0.0002592077],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0010366329,0.00055236474,0.0005401566,0.0004563331,0.00033987773,0.00097422214,0.009774517,0.00026257941,0.000026818143],"category_scores_gemma":[0.00013532744,0.0005065439,0.00007786277,0.0005113101,0.00054527493,0.0002715421,0.0052355845,0.00061319594,0.00014000018],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011586045,0.000028983128,0.00002162065,0.000009050017,0.000012750818,0.000037925478,0.00040423597,0.017578593,0.000050190494,0.0059187245,0.0003070749,0.9756297],"study_design_scores_gemma":[0.00017799855,0.000057187295,0.000065336535,0.00031872332,0.000013360033,0.000026607837,2.958937e-7,0.976601,0.00014297962,0.011892448,0.010118197,0.00058586424],"about_ca_topic_score_codex":0.00020084373,"about_ca_topic_score_gemma":0.00013861204,"teacher_disagreement_score":0.97504383,"about_ca_system_score_codex":0.00019204515,"about_ca_system_score_gemma":0.00045285095,"threshold_uncertainty_score":0.99973863},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009354086,0.000031333322,0.98373485,0.0018291887,0.000096388794,0.00006131148,0.000026489633,0.00007598975,0.0047903834],"genre_scores_gemma":[0.26910514,0.00006400871,0.71507925,0.005035883,0.00035473364,0.000035621735,0.000034851033,0.000016048209,0.010274455],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995255,0.000013488054,0.00007140784,0.00016857394,0.00009629404,0.00012475559],"domain_scores_gemma":[0.99928415,0.00016256442,0.000024423103,0.000483341,0.000018890341,0.000026650958],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000109400986,0.000051225703,0.000043385156,0.000008873894,0.00018617472,0.00009300067,0.0005881981,0.000011621492,0.00009988712],"category_scores_gemma":[0.000020286943,0.000036414753,0.00000967102,0.00016246644,0.00002943406,0.00005610169,0.00005279139,0.0000749851,0.0010194136],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.247922e-7,0.000020011288,0.0000032317428,0.0000013564953,0.0000017883773,6.7103065e-7,0.00031857044,0.00007957235,0.000022643942,0.2856639,0.047395907,0.666492],"study_design_scores_gemma":[0.00012896793,0.00003650394,0.0016522299,0.000042299525,0.000002367154,0.000008520909,0.000013072453,0.47134182,0.00039107003,0.031015282,0.4951451,0.00022274077],"about_ca_topic_score_codex":0.000006767553,"about_ca_topic_score_gemma":0.0000022029399,"teacher_disagreement_score":0.66626924,"about_ca_system_score_codex":0.000008019763,"about_ca_system_score_gemma":0.000012066862,"threshold_uncertainty_score":0.9997584},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009354086,0.000031333322,0.98373485,0.0018291887,0.000096388794,0.00006131148,0.000026489633,0.00007598975,0.0047903834],"genre_scores_gemma":[0.26910514,0.00006400871,0.71507925,0.005035883,0.00035473364,0.000035621735,0.000034851033,0.000016048209,0.010274455],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995255,0.000013488054,0.00007140784,0.00016857394,0.00009629404,0.00012475559],"domain_scores_gemma":[0.99928415,0.00016256442,0.000024423103,0.000483341,0.000018890341,0.000026650958],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000109400986,0.000051225703,0.000043385156,0.000008873894,0.00018617472,0.00009300067,0.0005881981,0.000011621492,0.00009988712],"category_scores_gemma":[0.000020286943,0.000036414753,0.00000967102,0.00016246644,0.00002943406,0.00005610169,0.00005279139,0.0000749851,0.0010194136],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.247922e-7,0.000020011288,0.0000032317428,0.0000013564953,0.0000017883773,6.7103065e-7,0.00031857044,0.00007957235,0.000022643942,0.2856639,0.047395907,0.666492],"study_design_scores_gemma":[0.00012896793,0.00003650394,0.0016522299,0.000042299525,0.000002367154,0.000008520909,0.000013072453,0.47134182,0.00039107003,0.031015282,0.4951451,0.00022274077],"about_ca_topic_score_codex":0.000006767553,"about_ca_topic_score_gemma":0.0000022029399,"teacher_disagreement_score":0.66626924,"about_ca_system_score_codex":0.000008019763,"about_ca_system_score_gemma":0.000012066862,"threshold_uncertainty_score":0.9997584},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018349139,0.0001034043,0.95025754,0.009714901,0.00019990321,0.00010304683,0.00002411731,0.00012448733,0.021123469],"genre_scores_gemma":[0.7941075,0.00012359863,0.2001882,0.00029579335,0.00014161972,0.000051841304,0.0000020938571,0.0000064062883,0.0050829654],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994755,0.000007319831,0.00008788002,0.00023265608,0.00007219296,0.00012449893],"domain_scores_gemma":[0.9995481,0.00004309109,0.000017310747,0.00033047237,0.000012826713,0.000048240378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000903074,0.00004927851,0.00005704807,0.00003077999,0.00003207767,0.00006207176,0.00030635015,0.000017652155,0.000008112083],"category_scores_gemma":[0.000013026939,0.000031281303,0.000008792856,0.00014267264,0.000030161324,0.00033309468,0.00015286061,0.000026686766,0.000052747357],"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":[6.1543653e-7,0.000033754714,0.0016142699,0.0000027015733,0.0000021583521,0.000002926052,0.00011456815,2.61413e-7,0.001139741,0.34287494,0.021912232,0.63230187],"study_design_scores_gemma":[0.0017013426,0.000120718294,0.2020797,0.00017224893,0.000005617611,0.00004327769,0.00010619904,0.013374484,0.004862248,0.107153,0.6695339,0.0008472373],"about_ca_topic_score_codex":0.000025269994,"about_ca_topic_score_gemma":0.000028310293,"teacher_disagreement_score":0.7757583,"about_ca_system_score_codex":0.000012741672,"about_ca_system_score_gemma":0.000016729782,"threshold_uncertainty_score":0.12756145},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009354086,0.000031333322,0.98373485,0.0018291887,0.000096388794,0.00006131148,0.000026489633,0.00007598975,0.0047903834],"genre_scores_gemma":[0.26910514,0.00006400871,0.71507925,0.005035883,0.00035473364,0.000035621735,0.000034851033,0.000016048209,0.010274455],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995255,0.000013488054,0.00007140784,0.00016857394,0.00009629404,0.00012475559],"domain_scores_gemma":[0.99928415,0.00016256442,0.000024423103,0.000483341,0.000018890341,0.000026650958],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000109400986,0.000051225703,0.000043385156,0.000008873894,0.00018617472,0.00009300067,0.0005881981,0.000011621492,0.00009988712],"category_scores_gemma":[0.000020286943,0.000036414753,0.00000967102,0.00016246644,0.00002943406,0.00005610169,0.00005279139,0.0000749851,0.0010194136],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.247922e-7,0.000020011288,0.0000032317428,0.0000013564953,0.0000017883773,6.7103065e-7,0.00031857044,0.00007957235,0.000022643942,0.2856639,0.047395907,0.666492],"study_design_scores_gemma":[0.00012896793,0.00003650394,0.0016522299,0.000042299525,0.000002367154,0.000008520909,0.000013072453,0.47134182,0.00039107003,0.031015282,0.4951451,0.00022274077],"about_ca_topic_score_codex":0.000006767553,"about_ca_topic_score_gemma":0.0000022029399,"teacher_disagreement_score":0.66626924,"about_ca_system_score_codex":0.000008019763,"about_ca_system_score_gemma":0.000012066862,"threshold_uncertainty_score":0.9997584},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21778634,0.000007620149,0.7801319,0.0014965163,0.00025606254,0.00014447387,0.000025666806,0.000020456855,0.0001309987],"genre_scores_gemma":[0.9978881,0.000024115721,0.0016755214,0.00035137887,0.00003844363,0.0000151962395,0.0000015360379,0.0000026494863,0.0000030941653],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986785,0.000039212835,0.00038634456,0.00018049058,0.00046748904,0.00024797488],"domain_scores_gemma":[0.9984366,0.00029245298,0.00033893902,0.00058538106,0.0002984765,0.000048123176],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088943174,0.00012773444,0.000110630936,0.00010488283,0.0006304542,0.00038690612,0.0018931057,0.000022865099,0.0000042180786],"category_scores_gemma":[0.00004851856,0.00004978458,0.000069888854,0.00062285905,0.0005512786,0.002551533,0.0005303354,0.000078525474,0.000007954968],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012403506,0.0000139676795,0.0067084534,0.000011160333,0.0000073821006,5.8377623e-8,0.0011335462,0.0001357,0.00021314863,0.0008515966,0.00028724087,0.9906365],"study_design_scores_gemma":[0.00031543127,0.00015928458,0.12262713,0.00014534824,0.0000032391802,0.0000072396274,0.000062574196,0.86650413,0.0096654445,0.00008604299,0.00029301774,0.00013112446],"about_ca_topic_score_codex":0.000104944374,"about_ca_topic_score_gemma":0.0000016085761,"teacher_disagreement_score":0.9905054,"about_ca_system_score_codex":0.000031243904,"about_ca_system_score_gemma":0.00015258124,"threshold_uncertainty_score":0.4849008},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13289414,0.000010405101,0.8594515,0.0065604215,0.00019080908,0.00006651799,0.000031477026,0.000060864673,0.0007339161],"genre_scores_gemma":[0.83088243,0.00000950418,0.16742879,0.0011941841,0.00025213804,0.00004296741,0.000008297518,0.0000052495407,0.00017645494],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990936,0.000054728767,0.0001536768,0.00031599175,0.00017960918,0.00020243101],"domain_scores_gemma":[0.99871397,0.00045506595,0.000040551535,0.0007385777,0.000014081133,0.000037769023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023647065,0.00008476647,0.000077824414,0.000037788333,0.000072779636,0.00017115861,0.0012395893,0.00004636791,0.000072783434],"category_scores_gemma":[0.0000409832,0.000043615564,0.000027711805,0.00020784454,0.00002706723,0.00018405225,0.00019733113,0.00007511653,0.00010372319],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012051374,0.000058675127,0.0053178947,0.0000013109872,0.0000094673405,0.000016181386,0.0017759822,0.000002780962,0.0006544523,0.065638304,0.0033309967,0.92319274],"study_design_scores_gemma":[0.0031267162,0.0003425963,0.2576998,0.0013391466,0.000051589643,0.000061614875,0.0036263026,0.1404879,0.015129631,0.30878833,0.26669773,0.0026486563],"about_ca_topic_score_codex":0.0006894109,"about_ca_topic_score_gemma":0.0001621296,"teacher_disagreement_score":0.9205441,"about_ca_system_score_codex":0.00001856839,"about_ca_system_score_gemma":0.0000310646,"threshold_uncertainty_score":0.2303486},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016992167,0.000007677091,0.98111457,0.00039655602,0.00006970922,0.00021689892,0.0005930453,0.00014207438,0.00046729497],"genre_scores_gemma":[0.2504572,0.000002459152,0.74856615,0.00017142747,0.000094409545,0.00008592263,0.0003066875,0.000009601044,0.00030617585],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99869186,0.000018186105,0.00016688941,0.0006924136,0.00017110904,0.0002595492],"domain_scores_gemma":[0.99759996,0.000101308135,0.0000554626,0.0020959196,0.00003606625,0.000111279114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031933523,0.00010831436,0.00009629113,0.00003947412,0.000110743335,0.00016673004,0.002124053,0.00003213903,0.000021397433],"category_scores_gemma":[0.000019673133,0.00006664999,0.000022893468,0.000113852824,0.000023967277,0.00043264971,0.0004338225,0.000025156347,0.000008834399],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023883424,0.00039726702,0.0012015312,0.000012101508,0.000019737987,0.0000011489863,0.00025510963,0.00029682973,0.00088098156,0.045491643,0.008738242,0.942703],"study_design_scores_gemma":[0.0003108915,0.00005578141,0.00086139474,0.000012592193,0.0000049005694,0.000002709328,0.00008071374,0.99328095,0.00035146336,0.00010743089,0.004775034,0.00015614303],"about_ca_topic_score_codex":0.0001197816,"about_ca_topic_score_gemma":0.00001145803,"teacher_disagreement_score":0.9929841,"about_ca_system_score_codex":0.0000271203,"about_ca_system_score_gemma":0.000042447067,"threshold_uncertainty_score":0.3947054},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012282783,0.0000036764022,0.9833304,0.0030804442,0.00012246893,0.00006570237,0.000030684074,0.00013589919,0.0009479337],"genre_scores_gemma":[0.8915819,0.0000012546689,0.10561718,0.00037621704,0.00009015531,0.000019975561,0.000021540676,0.000004647015,0.0022871038],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992783,0.000020136,0.00012684736,0.00029360593,0.00014328033,0.0001378324],"domain_scores_gemma":[0.99920887,0.000043926455,0.00003851644,0.00063187734,0.00003151993,0.000045278437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012457413,0.000066797635,0.00005785832,0.00003469573,0.00006976938,0.00014943344,0.00041348595,0.000026398493,0.00008754045],"category_scores_gemma":[0.000008415988,0.00004263542,0.00003380175,0.00012250047,0.000028796165,0.00067706004,0.00011507531,0.000021890666,0.00010988324],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013627172,0.00005383521,0.0018799532,0.0000029288847,0.0000054773436,0.0000015246783,0.000024481104,0.000004636872,0.016017579,0.0152757885,0.0038220568,0.96291035],"study_design_scores_gemma":[0.0012619348,0.00009570758,0.055769753,0.00005093998,0.000013414743,0.000011645295,0.000008510427,0.61511177,0.24905373,0.010742376,0.06727657,0.0006036735],"about_ca_topic_score_codex":0.00006940348,"about_ca_topic_score_gemma":0.000010227996,"teacher_disagreement_score":0.9623067,"about_ca_system_score_codex":0.00001916036,"about_ca_system_score_gemma":0.000046690435,"threshold_uncertainty_score":0.1738622},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048093433,0.0000011536961,0.97031325,0.0165356,0.0001430038,0.00007593697,0.00003238929,0.00019753567,0.007891784],"genre_scores_gemma":[0.8125164,0.000005896526,0.18289801,0.0032820632,0.000079287915,0.00006541521,0.000029432435,0.000010340662,0.0011131905],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992475,0.000027158438,0.00013979511,0.0003114983,0.00011694867,0.00015710022],"domain_scores_gemma":[0.9991996,0.00014878337,0.000051851697,0.000504048,0.000027623992,0.00006806063],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019085569,0.00008280088,0.00006327232,0.000073513685,0.000078580226,0.0000882279,0.00041422722,0.000025518899,0.0002904618],"category_scores_gemma":[0.000020454485,0.0000527945,0.000026725991,0.00015313194,0.000013301446,0.00026925158,0.000080497004,0.000031534608,0.0003588057],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.693374e-7,0.000046509012,0.0003971984,0.0000011483299,0.0000019152917,0.0000010726953,0.000026023761,0.0000014571758,0.001950199,0.0014289591,0.01435895,0.9817861],"study_design_scores_gemma":[0.0007985885,0.000141266,0.0019128257,0.00007296652,0.000003545965,0.0000023588104,0.000017582124,0.86259216,0.004089582,0.00031226513,0.12977365,0.00028322273],"about_ca_topic_score_codex":0.000022584109,"about_ca_topic_score_gemma":0.000010768099,"teacher_disagreement_score":0.9815029,"about_ca_system_score_codex":0.000034309658,"about_ca_system_score_gemma":0.000032980242,"threshold_uncertainty_score":0.4611841},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00076060166,0.000009637299,0.993442,0.0007979385,0.0013154213,0.00050894584,0.0004174582,0.00037013786,0.0023778533],"genre_scores_gemma":[0.96824527,0.0000103630555,0.030108172,0.0004450902,0.00014117881,0.00051973294,0.00013348158,0.00002314696,0.00037357621],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976924,0.000071858805,0.0007667353,0.0003779139,0.0006595093,0.00043160608],"domain_scores_gemma":[0.9971196,0.00009096143,0.00055449316,0.0016529611,0.0003669802,0.00021497975],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005426296,0.00028386395,0.0003007961,0.00030999968,0.0014763256,0.0029877897,0.0016153972,0.00016356216,0.000033174303],"category_scores_gemma":[0.000021641776,0.00027740817,0.0001347354,0.00025349073,0.000082799525,0.004339675,0.000035606212,0.0002691946,0.0006175641],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005209109,0.00015400886,0.0001805842,0.000104694875,0.00006754906,0.000005088073,0.0010117877,0.0046752137,0.000017485356,0.00042029616,0.0011814104,0.99217665],"study_design_scores_gemma":[0.0010459226,0.00008655842,0.0005370124,0.00015788645,0.000020308617,0.00002762849,0.00018843228,0.981295,0.00059496093,0.0000148094405,0.01567096,0.0003605191],"about_ca_topic_score_codex":0.0014648044,"about_ca_topic_score_gemma":0.00003718167,"teacher_disagreement_score":0.99181616,"about_ca_system_score_codex":0.0001347962,"about_ca_system_score_gemma":0.00016259345,"threshold_uncertainty_score":0.9999678},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1966282,0.000048559683,0.79839224,0.003437583,0.00036269389,0.00018684035,0.00005912987,0.00034361638,0.0005411335],"genre_scores_gemma":[0.8987337,0.000069280206,0.10084204,0.000048713275,0.000077725235,0.000064911255,0.0000052303612,0.000009541289,0.00014888296],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998697,0.00001462682,0.0002890361,0.00048082622,0.00024303247,0.00027549794],"domain_scores_gemma":[0.9989245,0.00031609277,0.00015970434,0.00034788766,0.00020241976,0.000049376766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024572303,0.00015441183,0.00015534504,0.0001561641,0.00019251702,0.0002992458,0.00097073975,0.00006767273,0.000014834977],"category_scores_gemma":[0.00026332526,0.00011980967,0.000038192986,0.000119945515,0.00012470338,0.0007637994,0.0005371036,0.000078182245,0.000012695429],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014776737,0.00010161551,0.017649658,0.000052549105,0.0001343479,0.00002601331,0.0007767005,0.000020435578,0.12415086,0.3697863,0.00069456553,0.48659217],"study_design_scores_gemma":[0.0007191084,0.000047901893,0.0010296272,0.00040023035,0.000014121275,0.0001310891,0.0003442003,0.98014754,0.0067477934,0.005837888,0.0042834296,0.0002970578],"about_ca_topic_score_codex":0.000027218988,"about_ca_topic_score_gemma":0.000017241671,"teacher_disagreement_score":0.9801271,"about_ca_system_score_codex":0.000038994738,"about_ca_system_score_gemma":0.000120133096,"threshold_uncertainty_score":0.48856965},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046013676,0.0003185263,0.9514117,0.00062908436,0.0002478249,0.00025970617,0.000021530346,0.000020490972,0.0010774634],"genre_scores_gemma":[0.5281152,0.0010794303,0.46993244,0.0007110705,0.000056493926,0.000014628023,0.000021696605,0.0000137400375,0.00005528954],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995957,0.00008939782,0.0018693128,0.00027441137,0.0013088277,0.00050106086],"domain_scores_gemma":[0.99638295,0.0016380101,0.00048447,0.00032768847,0.0009023711,0.00026451205],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010909451,0.00026912364,0.00039459957,0.0005773543,0.00025983807,0.0002334556,0.0012681774,0.000065320244,0.00008560934],"category_scores_gemma":[0.00016593073,0.00024865728,0.00007839827,0.0012750807,0.00013916711,0.0014613734,0.00015843175,0.00082828884,0.00006751942],"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":[0.000024864958,0.000057379802,0.000024589357,0.000014583857,0.000010814012,0.000006825557,0.00070620084,0.5391682,8.860484e-7,0.022346051,0.000080822996,0.4375588],"study_design_scores_gemma":[0.00015227654,0.0004374793,0.0005936622,0.00037113414,0.000004215938,0.00016424673,0.0037916533,0.90478,0.00039142696,0.08136963,0.007638554,0.0003057468],"about_ca_topic_score_codex":0.0028118247,"about_ca_topic_score_gemma":0.0023795671,"teacher_disagreement_score":0.48210153,"about_ca_system_score_codex":0.0005725428,"about_ca_system_score_gemma":0.0012880268,"threshold_uncertainty_score":0.99999654},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05701343,0.000007619755,0.9395317,0.0028721548,0.00005858649,0.000042192125,0.00008859292,0.00011822103,0.0002675463],"genre_scores_gemma":[0.89187044,0.0000069436924,0.107613064,0.0001235321,0.000032166285,0.000013534193,0.00001682966,0.000002650051,0.0003208215],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9993534,0.000015352034,0.00010960318,0.00028450825,0.000087367276,0.00014976582],"domain_scores_gemma":[0.9994375,0.00005807416,0.000029794153,0.0003775855,0.000024262283,0.00007277793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000106329026,0.00006565139,0.00006870209,0.000015586053,0.00007942198,0.00009388878,0.00032301515,0.000024429322,0.000051350766],"category_scores_gemma":[0.000013139252,0.000041295687,0.000014064715,0.00008176906,0.00004429961,0.00027986706,0.0002657718,0.00002244284,0.000033464166],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.3484866e-7,0.00002760339,0.004464404,0.0000023767184,0.000007336569,0.0000031263492,0.000057640318,2.2641726e-7,0.00039942644,0.01454964,0.005314367,0.975173],"study_design_scores_gemma":[0.0035331494,0.00018708326,0.5687378,0.00010963755,0.00003242329,0.0000952456,0.000116825206,0.26811123,0.0049862764,0.018453903,0.1343243,0.0013121379],"about_ca_topic_score_codex":0.00010368131,"about_ca_topic_score_gemma":0.000011679542,"teacher_disagreement_score":0.97386086,"about_ca_system_score_codex":0.000008048125,"about_ca_system_score_gemma":0.000014733151,"threshold_uncertainty_score":0.16839892},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17181568,0.000068535905,0.8233526,0.0010740163,0.00042391568,0.00014775725,0.00024093932,0.00029119587,0.0025853855],"genre_scores_gemma":[0.9496348,0.0000050690533,0.049225114,0.00009558949,0.00015555818,0.000009547011,0.00026916974,0.00001556256,0.0005895962],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99836445,0.00008489569,0.0002065011,0.00075858907,0.00027686433,0.00030871708],"domain_scores_gemma":[0.9966361,0.00007907169,0.0002699666,0.0028763765,0.000036500358,0.00010197656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005686749,0.00017220703,0.00018741068,0.000044009463,0.0011207137,0.00080897566,0.0034980061,0.000053664233,0.00011613506],"category_scores_gemma":[0.00015905227,0.00016344167,0.00003695088,0.000075317796,0.00008578411,0.0012117344,0.0033052822,0.00032481522,0.00006062937],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024409449,0.000038764323,0.015387149,0.0000049856208,0.000024690602,0.000035097506,0.0002845095,0.00007648231,0.00004786681,0.00040960804,0.0006509818,0.9830374],"study_design_scores_gemma":[0.00035116944,0.000045919987,0.061783914,0.000022980214,0.000013905507,0.000016527281,0.000036643116,0.92782676,0.00010311121,0.00015382808,0.009432988,0.00021223293],"about_ca_topic_score_codex":0.004129658,"about_ca_topic_score_gemma":0.00027129008,"teacher_disagreement_score":0.9828252,"about_ca_system_score_codex":0.000020576581,"about_ca_system_score_gemma":0.00004405221,"threshold_uncertainty_score":0.8619737},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048326295,0.00001476648,0.00051069213,0.03631885,0.006388068,0.0010376015,0.0011075932,0.00014385542,0.90615225],"genre_scores_gemma":[0.9920934,0.000021316439,0.0049231416,0.00014442876,0.0010952381,0.0000967171,0.00000801104,0.000024336206,0.0015934301],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9909797,0.00004529232,0.0017384498,0.002314262,0.0040956805,0.0008266677],"domain_scores_gemma":[0.99042135,0.00018242084,0.0031057273,0.0012492087,0.0047763824,0.00026490897],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0053860075,0.00064968056,0.0008107495,0.0010729866,0.0017247299,0.0030304694,0.031546216,0.00021683866,0.00002674589],"category_scores_gemma":[0.00045489703,0.00044854675,0.0002587015,0.0018810354,0.0018322956,0.005072482,0.0054687574,0.0005578721,0.000061008814],"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":[0.000056417208,0.00016656063,0.004682872,0.000097494725,0.000059584567,9.641973e-7,0.001554205,0.00008671672,0.00072555273,0.9818193,0.005817189,0.0049331863],"study_design_scores_gemma":[0.0014826935,0.0012328649,0.02308116,0.007999377,0.00008667323,0.0002615091,0.92138743,0.029906325,0.002672342,0.0038365193,0.0064032045,0.0016498996],"about_ca_topic_score_codex":0.0005147815,"about_ca_topic_score_gemma":0.000065248736,"teacher_disagreement_score":0.97798276,"about_ca_system_score_codex":0.0004409636,"about_ca_system_score_gemma":0.00065490766,"threshold_uncertainty_score":0.9997966},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0074957004,0.00015469488,0.98970616,0.0020197618,0.000018401135,0.00013285999,0.00009050091,0.000008515075,0.0003733963],"genre_scores_gemma":[0.9409069,0.00023784782,0.05827303,0.00026573858,0.000017868244,0.000016986423,0.000096456344,0.0000031561003,0.00018204577],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99961686,0.00003982708,0.00012491908,0.00009843356,0.00008503685,0.00003491982],"domain_scores_gemma":[0.99910545,0.00029926258,0.00004614354,0.00049793435,0.00004512783,0.00000610074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020114466,0.000023513803,0.000030997322,0.000013123201,0.000045110744,0.000050620198,0.0005222738,0.000009787613,0.000005586333],"category_scores_gemma":[0.000072474155,0.000010077249,0.0000031671345,0.00012673241,0.00006603125,0.00061335333,0.00016359,0.00001157315,6.750128e-7],"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":[4.7893354e-7,0.000013347321,0.0011118698,9.131922e-7,0.000001965521,2.0264347e-8,0.00036069055,0.000009173381,0.0010108362,0.72014236,0.001255434,0.27609292],"study_design_scores_gemma":[0.00040946473,0.00004337826,0.025956644,0.00003298812,0.0000051138986,0.0000048656134,0.0007843301,0.68083817,0.0043636216,0.011463703,0.275993,0.0001047436],"about_ca_topic_score_codex":0.000060640643,"about_ca_topic_score_gemma":0.000070379945,"teacher_disagreement_score":0.9334112,"about_ca_system_score_codex":0.0000018629435,"about_ca_system_score_gemma":0.000029623918,"threshold_uncertainty_score":0.097052336},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93307525,0.00089247315,0.012350877,0.040428534,0.0008985394,0.0015843362,0.0025090873,0.00010455044,0.008156365],"genre_scores_gemma":[0.9508647,0.00027097677,0.03886039,0.00031581364,0.00037827817,0.00012330951,0.00006429022,0.000043401156,0.009078883],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99628735,0.00006203026,0.0011360656,0.0008475632,0.00082464766,0.0008423511],"domain_scores_gemma":[0.94560194,0.0006812925,0.0010906889,0.0006350021,0.051791716,0.00019936619],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0015198858,0.00043773727,0.0006984338,0.00014814275,0.00043090782,0.010743946,0.0036094652,0.00030711218,0.000016048738],"category_scores_gemma":[0.016495368,0.00037344315,0.00032538452,0.0010769641,0.00086661446,0.043420482,0.0012279327,0.0005033163,0.000014459711],"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":[0.001618118,0.0011788394,0.0062413337,0.0024783327,0.00067836815,0.0000033220963,0.12768048,0.000073882125,0.061334074,0.5058214,0.061579518,0.23131235],"study_design_scores_gemma":[0.011061752,0.0028523267,0.053416893,0.0053173415,0.00062514405,0.0001636623,0.008629637,0.18809569,0.24125002,0.028614447,0.45753184,0.0024412281],"about_ca_topic_score_codex":0.0024790834,"about_ca_topic_score_gemma":0.000018536204,"teacher_disagreement_score":0.47720695,"about_ca_system_score_codex":0.000108079286,"about_ca_system_score_gemma":0.0007288068,"threshold_uncertainty_score":0.99987173},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04575059,0.00004899719,0.9326342,0.016821014,0.0020197248,0.000101542224,0.00024686026,0.000027976534,0.0023491527],"genre_scores_gemma":[0.4694486,0.0018181097,0.52295,0.0019998818,0.0013448227,0.00004663847,0.0015921929,0.00002277453,0.000776972],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987933,0.000017255328,0.0005360207,0.000100434416,0.0004296794,0.0001232913],"domain_scores_gemma":[0.99756426,0.00011789179,0.0012945479,0.00037043574,0.00060636376,0.000046512057],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0011845261,0.00007739881,0.000117129865,0.00024543435,0.00018990382,0.0011606459,0.001448622,0.00005815512,0.000004913071],"category_scores_gemma":[0.0009051239,0.000076458324,0.000029229977,0.00005697824,0.000016938944,0.011267726,0.00036388807,0.00009005402,0.000012630154],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026036283,0.000043226657,0.0045371857,0.000017318118,0.000053699405,0.0000020970813,0.0010631577,0.00013381161,0.000044733355,0.00944931,0.0077296915,0.97689974],"study_design_scores_gemma":[0.0021708335,0.000068373905,0.024875144,0.00016358575,0.00002051016,0.00006992379,0.00026189376,0.7449591,0.00023999119,0.0031708458,0.22379643,0.00020333297],"about_ca_topic_score_codex":0.000060012604,"about_ca_topic_score_gemma":0.000017789711,"teacher_disagreement_score":0.9766964,"about_ca_system_score_codex":0.00012979115,"about_ca_system_score_gemma":0.00008847187,"threshold_uncertainty_score":0.99987626},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87151873,0.000027727692,0.12410559,0.0006238535,0.000044838966,0.0002151904,0.0028247514,0.000087668035,0.00055163447],"genre_scores_gemma":[0.9669748,0.0000315574,0.03225604,0.000026640737,0.000027827025,8.7582464e-8,0.0001793073,0.0000148034205,0.00048891816],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99835664,0.00010312568,0.00015024099,0.0007270748,0.00039033606,0.00027255923],"domain_scores_gemma":[0.99804634,0.00027661462,0.00040773966,0.0009807113,0.00014215645,0.00014641117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043837,0.00020628194,0.00036847012,0.00017603833,0.00036220695,0.000034647357,0.0011758299,0.00017102971,0.000058850008],"category_scores_gemma":[0.000051345214,0.00024382089,0.0000913034,0.0002720422,0.00018785578,0.00019847571,0.0009015036,0.00017268218,0.0003685106],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014766899,0.0030758625,0.28459385,0.00031614778,0.0029684843,0.0005144285,0.48667723,0.009088282,0.0021669483,0.014109891,0.0021984223,0.19281375],"study_design_scores_gemma":[0.034967385,0.0011339005,0.33592615,0.0022539059,0.0014249549,0.000039020782,0.40371197,0.170419,0.0007404331,0.03472532,0.010418245,0.004239718],"about_ca_topic_score_codex":0.010154244,"about_ca_topic_score_gemma":0.00061645807,"teacher_disagreement_score":0.18857403,"about_ca_system_score_codex":0.00012804678,"about_ca_system_score_gemma":0.00008262174,"threshold_uncertainty_score":0.99643725},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58656424,0.000018783376,0.41233394,0.00076267304,0.00018442317,0.00005685218,0.000017549508,0.000004487702,0.00005707326],"genre_scores_gemma":[0.9648797,0.000021649974,0.034769148,0.0000065312593,0.00030602215,0.0000030667086,0.0000020555287,0.0000031562115,0.000008650673],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99835074,0.00008082106,0.00050135516,0.0001149154,0.0007175244,0.00023466801],"domain_scores_gemma":[0.99770623,0.00052340154,0.00023174615,0.0003295007,0.0011234428,0.00008569158],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032009261,0.000054557077,0.0001020863,0.00015754331,0.0004994969,0.00015901886,0.0012498914,0.000040820843,0.000035916317],"category_scores_gemma":[0.000512138,0.000037516787,0.00006173891,0.0008058596,0.0004045167,0.0004891415,0.00020543636,0.0008048935,0.000014121187],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023647175,0.00040863737,0.0027877712,0.00002490052,0.000048408154,0.000009856634,0.0013774725,0.0025902512,0.21964768,0.4978826,0.00045743422,0.27474132],"study_design_scores_gemma":[0.000015666545,0.0001669514,0.0013199848,0.00004138833,0.0000055808373,0.00014061248,0.00046705894,0.8216764,0.15758112,0.017772006,0.00075412914,0.000059143993],"about_ca_topic_score_codex":0.00004140543,"about_ca_topic_score_gemma":0.000011372247,"teacher_disagreement_score":0.81908613,"about_ca_system_score_codex":0.000028592836,"about_ca_system_score_gemma":0.00036688085,"threshold_uncertainty_score":0.38417765},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002948343,0.00089364866,0.97620165,0.0006510572,0.001088535,0.00038315027,0.000038066068,0.000109800654,0.020604612],"genre_scores_gemma":[0.9176008,0.001692681,0.052771196,0.0017540094,0.015075933,0.0002670006,0.0005031676,0.00026414817,0.010071074],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981994,0.000026527916,0.00034715602,0.00076437235,0.0002781943,0.00038434408],"domain_scores_gemma":[0.99862045,0.000121096964,0.00036883223,0.0007241313,0.00007024905,0.00009521357],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025441166,0.00038853064,0.00042382732,0.00011783928,0.0006565933,0.0004796479,0.00088512123,0.0008076065,0.000016555952],"category_scores_gemma":[0.000030666914,0.0004001784,0.00012765915,0.000052218576,0.00019690793,0.00021555822,0.00043680792,0.0009801363,0.000014884785],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000049391842,0.000015227577,0.000014443772,0.00001950868,0.00005245031,0.000035344503,0.00042731877,0.00045962902,0.00004678044,0.014846803,0.00048696925,0.9835906],"study_design_scores_gemma":[0.0014955036,0.0002537773,0.0011357369,0.00073231844,0.00018514224,0.00010195756,0.00000388055,0.3486435,0.00029647708,0.42754018,0.21684873,0.0027627852],"about_ca_topic_score_codex":0.00018092807,"about_ca_topic_score_gemma":0.00069247826,"teacher_disagreement_score":0.9808278,"about_ca_system_score_codex":0.00016748231,"about_ca_system_score_gemma":0.00007552071,"threshold_uncertainty_score":0.999845},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8826314,0.001195699,0.07828483,0.025560936,0.00007494242,0.00046447,0.000020427373,0.00016519486,0.011602083],"genre_scores_gemma":[0.8334022,0.00031023344,0.16610315,0.000026610198,0.000010245977,0.000025314115,0.0000036494637,0.000004523974,0.000114061084],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9985085,0.0002918641,0.00022016659,0.00023042405,0.00052514416,0.00022386602],"domain_scores_gemma":[0.9956078,0.00043309308,0.00013008373,0.0029356761,0.000759155,0.00013417326],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0037058587,0.000065908636,0.00010817749,0.0001606334,0.0025584514,0.0054369923,0.003436649,0.00007153966,0.000005684023],"category_scores_gemma":[0.0026720134,0.00005980852,0.000026647023,0.00021617417,0.0004727991,0.010164609,0.0024828892,0.00064922747,0.00003276931],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000055775645,0.00016009313,0.007759904,0.000027530134,0.000023864714,0.0000023167277,0.0019162585,9.906861e-7,0.010006071,0.26140198,0.0005568634,0.7181386],"study_design_scores_gemma":[0.0012176532,0.0003733126,0.7094072,0.00057838403,0.000018755652,0.000026199068,0.0011684429,0.1553072,0.011564318,0.10556804,0.014367321,0.00040315103],"about_ca_topic_score_codex":0.000121269404,"about_ca_topic_score_gemma":0.000022438313,"teacher_disagreement_score":0.7177354,"about_ca_system_score_codex":0.000021379888,"about_ca_system_score_gemma":0.00010528708,"threshold_uncertainty_score":0.9987401},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23123308,0.000054637512,0.7651052,0.00040460465,0.00007497127,0.000082203405,0.0029810984,0.000029838639,0.00003437297],"genre_scores_gemma":[0.9285473,0.00012556318,0.067035235,0.0000369072,0.000035318917,0.0000059959702,0.0041743754,0.000006126378,0.000033169494],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978121,0.00005962116,0.00035645734,0.0012052876,0.00028781686,0.0002787126],"domain_scores_gemma":[0.99068016,0.00014203067,0.00023372949,0.008801166,0.000038481383,0.000104450286],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0009563065,0.00015175213,0.0002825215,0.0002447605,0.0003306363,0.0011576617,0.0069979755,0.0000386228,0.000035233872],"category_scores_gemma":[0.0002361785,0.00014493328,0.00003122188,0.00041901635,0.00009206271,0.0015244951,0.006824338,0.00011777095,0.000014891084],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028142308,0.00021509615,0.1135152,0.000022364653,0.0003922825,0.00004015651,0.00049051445,0.00018857942,0.000017325923,0.000855879,0.00051544677,0.88374436],"study_design_scores_gemma":[0.00008310993,0.0000080567825,0.07420112,0.000022668488,0.00022677807,0.000001315913,0.00017381896,0.9236058,0.00007686607,0.00008707091,0.0013593248,0.00015407272],"about_ca_topic_score_codex":0.0062189493,"about_ca_topic_score_gemma":0.003200823,"teacher_disagreement_score":0.9234172,"about_ca_system_score_codex":0.000021993297,"about_ca_system_score_gemma":0.000045000146,"threshold_uncertainty_score":0.99987924},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003778532,0.00047487067,0.992621,0.00033508555,0.000077143144,0.0019135608,0.00032561453,0.00006266687,0.00041149746],"genre_scores_gemma":[0.964483,0.00000954787,0.030876774,0.00003053304,0.0001239203,0.004350447,0.0000637825,0.000014926886,0.00004703932],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99828845,0.00009501437,0.0003612615,0.00042872468,0.0006358462,0.00019071731],"domain_scores_gemma":[0.9966533,0.00010747664,0.00057060336,0.0017134531,0.00087014236,0.00008499108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001542839,0.0001331605,0.00023136858,0.000042343654,0.0006842215,0.0002984435,0.0010575553,0.00005493772,0.0000014261274],"category_scores_gemma":[0.00007905242,0.00011334408,0.000042453918,0.00009201257,0.000074942975,0.00039441502,0.0000750743,0.00004567635,0.0000032523492],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000370366,0.0013685443,0.0055065337,0.00036120415,0.0007170035,4.6808404e-7,0.0060375817,0.0015960123,0.10385963,0.20389694,0.01070866,0.66591036],"study_design_scores_gemma":[0.0032747528,0.00015192445,0.006145035,0.00030374655,0.00018708769,0.000022362894,0.0014163877,0.92693985,0.015597374,0.0012694107,0.04379351,0.0008985347],"about_ca_topic_score_codex":0.0018414996,"about_ca_topic_score_gemma":0.00008411262,"teacher_disagreement_score":0.96174425,"about_ca_system_score_codex":0.00007941993,"about_ca_system_score_gemma":0.00019796756,"threshold_uncertainty_score":0.5262548},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000057763697,0.00035268362,0.98997575,0.00040107185,0.00016271192,0.0003921458,0.000011380342,0.00015244936,0.008494035],"genre_scores_gemma":[0.013391871,0.0002006548,0.9832171,0.00027231226,0.00039477771,0.00009053556,0.00022137562,0.000040418014,0.0021709565],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985291,0.0000037106142,0.0005608989,0.0003542917,0.00024699673,0.00030504973],"domain_scores_gemma":[0.998192,0.00009712894,0.00083278125,0.00036254193,0.000448411,0.00006714998],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00033709465,0.00032659704,0.00032228013,0.00034460778,0.0007623635,0.0015720275,0.000533886,0.00032710395,0.000009078623],"category_scores_gemma":[0.00027929174,0.00032213557,0.000032420452,0.00017527542,0.00004793501,0.0050097452,0.00017878825,0.00033414518,0.000007000337],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000064318583,0.000003105782,0.000039792478,0.0006995998,0.000007815361,1.6885708e-7,0.0004236896,0.00077288976,0.000027957232,0.0043000695,0.000054694432,0.9936638],"study_design_scores_gemma":[0.0007134307,0.000046162153,0.00034322924,0.0038939228,0.000032828615,0.000053193333,0.0000063949005,0.922664,0.0011537215,0.021578718,0.04873994,0.0007744817],"about_ca_topic_score_codex":0.000043722557,"about_ca_topic_score_gemma":0.00004195647,"teacher_disagreement_score":0.9928893,"about_ca_system_score_codex":0.00009857568,"about_ca_system_score_gemma":0.0005771882,"threshold_uncertainty_score":0.99992305},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49118745,0.00001937829,0.5020413,0.0010635058,0.000531173,0.00094166544,0.00018318169,0.00017803359,0.0038543586],"genre_scores_gemma":[0.907766,0.000025057354,0.091345936,0.00023126893,0.00012377877,0.00013433013,0.0001663278,0.00002408809,0.0001832239],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99779415,0.000021271677,0.0007524267,0.00034365896,0.00041137746,0.00067713513],"domain_scores_gemma":[0.99754936,0.00007716737,0.00039516893,0.0016595676,0.00016532504,0.0001534407],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009297354,0.00026777206,0.00033467246,0.000275337,0.000940721,0.0012482273,0.002307358,0.00014300914,0.000004917678],"category_scores_gemma":[0.00009307522,0.00025260347,0.0001147602,0.0002152426,0.00011173787,0.0028974866,0.00092513405,0.00038713653,0.00009334862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012662551,0.0011508503,0.24599797,0.0009893136,0.00020908707,0.00004774126,0.038566153,0.0024185777,0.0015020306,0.030773766,0.0076989606,0.67051893],"study_design_scores_gemma":[0.0018285639,0.00013130502,0.042289354,0.0003252929,0.000009798334,0.000033001263,0.0005837318,0.94413346,0.0007090726,0.00039294545,0.009134793,0.00042870274],"about_ca_topic_score_codex":0.00016906981,"about_ca_topic_score_gemma":0.00010100996,"teacher_disagreement_score":0.9417149,"about_ca_system_score_codex":0.00012358674,"about_ca_system_score_gemma":0.00008402547,"threshold_uncertainty_score":0.9999926},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.613152,0.00010937595,0.3857238,0.0005307567,0.00008428139,0.000032811364,2.1890133e-7,0.000015880758,0.00035082307],"genre_scores_gemma":[0.8977518,0.00004243117,0.10175731,0.00019147103,0.00022545634,8.525738e-7,3.934065e-8,0.0000030991923,0.00002752259],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991125,0.000012850165,0.00012782394,0.00016206912,0.0004250818,0.00015967192],"domain_scores_gemma":[0.99930954,0.00010263975,0.00013243056,0.00017761697,0.0001627884,0.0001149898],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010381152,0.000059498863,0.00009316783,0.0001233661,0.00019360958,0.00016875785,0.0004986338,0.0000105063555,7.683018e-7],"category_scores_gemma":[0.000024273862,0.000036955666,0.000023175942,0.0007472233,0.00021599769,0.0011668804,0.000047281996,0.00010834556,0.0000011426858],"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":[0.00003133247,0.00010108101,0.00009848837,5.650902e-7,0.0000053615395,0.0000075721387,0.0017439217,0.000012700849,0.2771501,0.0072598015,0.00007501102,0.7135141],"study_design_scores_gemma":[0.0028047585,0.004217215,0.11413755,0.00022851871,0.000010357286,0.001168488,0.0011600999,0.09083785,0.7191408,0.023401722,0.04204261,0.0008499774],"about_ca_topic_score_codex":0.0000067351434,"about_ca_topic_score_gemma":4.1109573e-7,"teacher_disagreement_score":0.7126641,"about_ca_system_score_codex":0.000028517406,"about_ca_system_score_gemma":0.00009073268,"threshold_uncertainty_score":0.16273358},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006870621,0.00014206533,0.98008364,0.0020249907,0.00062790426,0.00003696408,0.0000021280218,0.0000865346,0.016927036],"genre_scores_gemma":[0.007387209,0.000006285865,0.99149036,0.00029810102,0.0001246605,0.000009161463,0.0000010309516,0.0000038879334,0.0006793285],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99947506,0.000039455128,0.000065798726,0.00022180939,0.00008068336,0.000117189215],"domain_scores_gemma":[0.99838585,0.00006956655,0.00006686339,0.0014029503,0.000029886054,0.00004487427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006268613,0.00005599111,0.000071459304,0.000024459376,0.0003963376,0.00042002098,0.0017135164,0.000094467476,0.000005188352],"category_scores_gemma":[0.00024345717,0.000047547688,0.000027744003,0.000051847957,0.000025553529,0.00035472988,0.0005638845,0.00026936427,0.000019853209],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.7713326e-7,0.000005046872,0.00002683432,0.0000016559943,0.0000028150573,0.0000014735876,0.00003858699,0.0000010994927,0.00062494585,0.027019525,0.0011948679,0.971083],"study_design_scores_gemma":[0.00018651111,0.000017619977,0.017616875,0.000017784047,0.0000055615824,0.000024993607,0.000006765312,0.36893967,0.008812699,0.014006093,0.5901399,0.00022546992],"about_ca_topic_score_codex":0.000009365505,"about_ca_topic_score_gemma":0.0000021921237,"teacher_disagreement_score":0.9708575,"about_ca_system_score_codex":0.000008116109,"about_ca_system_score_gemma":0.000014175875,"threshold_uncertainty_score":0.4050272},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022077322,0.000057980214,0.9612945,0.014575472,0.0014335406,0.00042741318,0.000014867394,0.00010423629,0.000014684954],"genre_scores_gemma":[0.72702366,0.00000958919,0.27206197,0.0005188467,0.00027052767,0.000094974406,0.0000010647889,0.000012102866,0.00000725466],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99768966,0.00003691271,0.00053066295,0.00063136034,0.0005401569,0.0005712482],"domain_scores_gemma":[0.99661034,0.00023557375,0.00084289396,0.0014980228,0.0006927226,0.00012045688],"candidate_categories":["sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.0012499319,0.00023453406,0.00029802005,0.0005028411,0.0019262065,0.0009894401,0.007790713,0.00008291226,9.4465497e-7],"category_scores_gemma":[0.00026589978,0.0001466613,0.00013399585,0.0008605009,0.0007730956,0.001057998,0.0011850673,0.00040159345,0.0000040607015],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000069616563,0.000088323664,0.0009834069,0.000010536716,0.000024308745,0.000009222958,0.0002564335,0.0061572744,0.0008730884,0.0004277127,0.0004016056,0.9907611],"study_design_scores_gemma":[0.0008957769,0.00083756604,0.007932778,0.000106687396,0.000037589765,0.000364572,0.000093725466,0.9803827,0.006239343,0.0007062555,0.0021207277,0.00028228448],"about_ca_topic_score_codex":0.00002474639,"about_ca_topic_score_gemma":0.0000045151683,"teacher_disagreement_score":0.9904788,"about_ca_system_score_codex":0.000111154106,"about_ca_system_score_gemma":0.00021315372,"threshold_uncertainty_score":0.99937314},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000262906,0.000022685157,0.9945051,0.00038937994,0.0001456443,0.000112956484,0.000017581733,0.00003191876,0.004511797],"genre_scores_gemma":[0.06095454,0.0000031399727,0.9386553,0.00023767407,0.0001168352,0.0000050010503,0.0000013240743,0.000008600944,0.000017542223],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982954,0.000119876924,0.0006130455,0.00027347816,0.00041864967,0.00027950047],"domain_scores_gemma":[0.99658275,0.002322934,0.00027611371,0.00044949594,0.00012000257,0.00024870172],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004205082,0.00013484308,0.00029558258,0.00010791129,0.000090337046,0.000093853545,0.00073176133,0.00006709425,0.000013652513],"category_scores_gemma":[0.00046998565,0.00010344818,0.000061002906,0.00023826372,0.00008544704,0.00011743905,0.00011007503,0.00038033194,0.0000130826165],"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":[0.000027807391,0.00012256161,0.0000027057765,0.000003963361,0.000008367425,0.000009086559,0.00013250377,0.000048049642,0.0025195095,0.3379533,0.00021457572,0.6589576],"study_design_scores_gemma":[0.00046608894,0.00027921255,0.004248047,0.000016338998,0.000021846443,0.00005404771,0.000011801718,0.11701159,0.0043139462,0.8666396,0.0067533324,0.00018412033],"about_ca_topic_score_codex":0.0000018754833,"about_ca_topic_score_gemma":0.0000016391708,"teacher_disagreement_score":0.6587735,"about_ca_system_score_codex":0.000074739466,"about_ca_system_score_gemma":0.00008715948,"threshold_uncertainty_score":0.42184946},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039968416,0.00073187076,0.89522773,0.051079955,0.00018522168,0.00065901154,0.00060245214,0.0005185589,0.011026754],"genre_scores_gemma":[0.075999804,0.01616815,0.89341736,0.0030988008,0.00047733,0.0012301996,0.00022658317,0.000147786,0.0092339935],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.993113,0.003532915,0.0013149197,0.00071870675,0.00032132887,0.0009991692],"domain_scores_gemma":[0.99067616,0.006423501,0.0006455103,0.001581824,0.00020579969,0.00046720103],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00853984,0.00064384687,0.00071084505,0.00017989952,0.00017117457,0.00080858247,0.0021488718,0.0013432687,0.00014568002],"category_scores_gemma":[0.0017221706,0.00053967815,0.00019499357,0.00049371255,0.00024832017,0.0040989183,0.0007639953,0.0014412446,0.00015816503],"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":[0.000013331629,0.0005010284,0.00038617034,0.00080529985,0.00013045201,0.000047423895,0.0805731,0.000077181496,0.004659887,0.5991748,0.033407345,0.28022397],"study_design_scores_gemma":[0.001222994,0.00052700413,0.0015740573,0.0024817288,0.00009662452,0.0015183674,0.0016817964,0.07789865,0.0121988775,0.116304144,0.7826521,0.0018436603],"about_ca_topic_score_codex":0.0012617937,"about_ca_topic_score_gemma":0.0001917313,"teacher_disagreement_score":0.74924475,"about_ca_system_score_codex":0.0012261667,"about_ca_system_score_gemma":0.0006143382,"threshold_uncertainty_score":0.9999532},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07619032,0.0073815114,0.9023637,0.010914412,0.001114306,0.0007565235,0.0001745716,0.000028197024,0.0010764631],"genre_scores_gemma":[0.04386141,0.045491826,0.90588105,0.0027892855,0.0016341725,0.00003923733,0.000012674012,0.000023084956,0.0002672608],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990863,0.000027700898,0.00047028044,0.00018083457,0.00006956049,0.00016528346],"domain_scores_gemma":[0.9983754,0.000040496347,0.00070905825,0.00063848,0.00008928896,0.00014728773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015359453,0.000100175945,0.00033853546,0.000032253753,0.00021634622,0.00032061737,0.002149622,0.000051775936,0.0000047728013],"category_scores_gemma":[0.000119132375,0.000081728154,0.0001732854,0.000034587603,0.000042437776,0.00088241894,0.00007996248,0.00016955359,0.000025139578],"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":[0.00001539365,0.00003690402,0.00016432117,0.000018410028,0.000017692275,0.0000010569327,0.00006629245,0.00009055901,0.0000141591745,0.10105987,0.0040337616,0.8944816],"study_design_scores_gemma":[0.0007686728,0.0002556941,0.0009914951,0.000119321856,0.000018353681,0.00006866513,0.000008057876,0.05495891,0.00004732963,0.0041546635,0.9384717,0.00013719134],"about_ca_topic_score_codex":0.0000042810316,"about_ca_topic_score_gemma":0.0000012988343,"teacher_disagreement_score":0.9344379,"about_ca_system_score_codex":0.000106335116,"about_ca_system_score_gemma":0.00010082846,"threshold_uncertainty_score":0.39945683},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058078423,0.00023413624,0.8921185,0.023400795,0.011297838,0.00029523778,0.00002309909,0.00010850467,0.0144434245],"genre_scores_gemma":[0.8568859,0.00040640307,0.1076672,0.0008236687,0.032776672,0.000005940323,0.0000075522867,0.000022110742,0.0014045364],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99907166,0.000037516864,0.0003355767,0.00020959978,0.00023835618,0.00010729466],"domain_scores_gemma":[0.99918246,0.00012148395,0.00025558533,0.00015739717,0.0001908728,0.00009219239],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003704086,0.00009742398,0.00012548923,0.00014359131,0.00018180913,0.00043683816,0.00095335435,0.00003597266,0.00014634189],"category_scores_gemma":[0.000063784886,0.000089155976,0.000024161336,0.00017396548,0.00007264861,0.0006166223,0.00039861668,0.00015994345,0.000016043567],"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":[0.000027905555,0.00012847014,0.00050955266,9.95603e-7,0.00009150461,0.000014322758,0.005802767,0.00013146478,0.00009479964,0.063612446,0.022503743,0.907082],"study_design_scores_gemma":[0.00051146874,0.0006688758,0.003989978,0.00012479792,0.000032195887,0.0007124205,0.0017476234,0.0213101,0.0005266437,0.0045470223,0.9655229,0.00030596575],"about_ca_topic_score_codex":0.0000113419355,"about_ca_topic_score_gemma":0.0000055869687,"teacher_disagreement_score":0.94301915,"about_ca_system_score_codex":0.00003471406,"about_ca_system_score_gemma":0.00007027499,"threshold_uncertainty_score":0.42124406},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027972195,0.000018469542,0.96246946,0.00308526,0.00019032102,0.00006067608,0.000031335192,0.00018522069,0.005987056],"genre_scores_gemma":[0.29220322,0.0000015096545,0.70472264,0.0004332643,0.00024895222,0.000033425993,0.00037680488,0.000004058998,0.0019761047],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994799,0.000024027146,0.00010133374,0.00017813503,0.00013823378,0.00007836426],"domain_scores_gemma":[0.9994519,0.000031399108,0.000046023546,0.00027546127,0.000119736986,0.000075529955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000113917005,0.000046430876,0.000051074046,0.000020375113,0.000094585856,0.00016471918,0.00028203713,0.000028285105,0.000021789674],"category_scores_gemma":[0.00005400058,0.000041651576,0.000013247745,0.00019813707,0.000007811779,0.00052634533,0.00006202671,0.000043760152,0.00015390871],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.327331e-7,0.0001913091,0.00052319944,1.6436515e-7,0.000038653918,0.0000022161496,0.020009514,0.000110190085,0.0057896753,0.47182637,0.40825993,0.09324822],"study_design_scores_gemma":[0.0004252503,0.000041917498,0.0126607,0.0000021219582,0.0000071609475,0.0000015654687,0.0008852766,0.90919995,0.0037584358,0.013435013,0.059328724,0.00025387097],"about_ca_topic_score_codex":0.0003716904,"about_ca_topic_score_gemma":0.00009051827,"teacher_disagreement_score":0.9090898,"about_ca_system_score_codex":0.000036926067,"about_ca_system_score_gemma":0.00006825066,"threshold_uncertainty_score":0.19782364},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010828099,0.000094022886,0.9488583,0.0485773,0.00023524847,0.00014772864,0.00008144328,0.00026765498,0.00065545534],"genre_scores_gemma":[0.014243886,0.000018999119,0.97903776,0.004486531,0.00029559105,0.00010158494,0.00044775076,0.000016425442,0.0013514847],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851495,0.00004265557,0.0002995264,0.00062400626,0.0002613833,0.00025749745],"domain_scores_gemma":[0.99608016,0.00021421254,0.00009046302,0.0034526973,0.00006902614,0.00009346687],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00017221608,0.00014829852,0.00011374346,0.00012149544,0.0003725353,0.00030574447,0.002887266,0.00005766753,0.00022333325],"category_scores_gemma":[0.00024093872,0.00014748231,0.00003282268,0.00054237933,0.000052406464,0.0028583193,0.0012553595,0.00014572237,0.0019058794],"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":[4.674853e-7,0.00023078767,0.00050262385,0.0000032471335,0.000034156885,0.000010253828,0.001797058,0.00015607518,0.001179554,0.007773654,0.8761573,0.11215483],"study_design_scores_gemma":[0.00030251066,0.000014318684,0.0009458337,0.000009769948,0.0000099612425,0.000013484307,0.000056322027,0.73513675,0.0000852517,0.0002755928,0.26290494,0.00024523248],"about_ca_topic_score_codex":0.000011405284,"about_ca_topic_score_gemma":0.000013226337,"teacher_disagreement_score":0.7349807,"about_ca_system_score_codex":0.000021849517,"about_ca_system_score_gemma":0.000020918327,"threshold_uncertainty_score":0.99887127},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008697495,0.00024813772,0.13288057,0.00012212094,0.00022213664,0.000092752845,0.0011826317,0.00010454945,0.8651384],"genre_scores_gemma":[0.021166751,0.00008781519,0.53209317,0.0009460331,0.0017666526,0.00003802013,0.0005710539,0.000079252044,0.44325128],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99831915,0.0000064346227,0.00023062418,0.0009765918,0.00025574013,0.00021148717],"domain_scores_gemma":[0.9951636,0.000033003314,0.000271726,0.0043324186,0.000051268224,0.00014796],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00017945748,0.0002519055,0.0003727069,0.000098396966,0.00027456606,0.0007087947,0.0032441937,0.00016400832,0.0000032882315],"category_scores_gemma":[0.000019786417,0.00024620962,0.00008091052,0.000025983967,0.00011526379,0.00015660327,0.0026927209,0.000130232,0.000047393307],"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":[4.054984e-7,0.0000020275263,0.000018444189,0.0000037616492,0.00021638443,0.000015774243,0.00001870481,1.937548e-7,4.8714253e-7,0.5882175,0.002387772,0.40911853],"study_design_scores_gemma":[0.0003168222,0.000054723936,0.00082173926,0.00016446169,0.001385096,0.00007654927,0.000007392945,0.025691153,0.000005368465,0.24216415,0.72818804,0.0011244965],"about_ca_topic_score_codex":0.00018263825,"about_ca_topic_score_gemma":0.00031245739,"teacher_disagreement_score":0.7258003,"about_ca_system_score_codex":0.000029806659,"about_ca_system_score_gemma":0.000120801065,"threshold_uncertainty_score":0.999999},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02893655,0.0011615101,0.96787626,0.000018315312,0.00063318823,0.00021169618,0.000055000906,0.001094474,0.000012994728],"genre_scores_gemma":[0.033059005,0.000033045962,0.96612155,0.000011682562,0.0003372172,0.00020909964,0.000048415197,0.000054296983,0.00012570599],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985888,0.0000074021395,0.00026476147,0.0005388024,0.00013384927,0.00046635992],"domain_scores_gemma":[0.998856,0.00023889304,0.000038258673,0.00050374586,0.00008918213,0.0002738941],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022701942,0.00028572258,0.0002508734,0.0002092901,0.00021157971,0.000097433905,0.00049103395,0.000092701535,0.0000015245382],"category_scores_gemma":[0.000149131,0.00030474234,0.00007016742,0.00037122058,0.000023158696,0.00025491902,0.00016068964,0.00015284632,0.000009532954],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030228684,0.00043352862,0.0003159566,0.00035934252,0.0001469968,0.00005008758,0.0068354486,0.13379994,0.0012369225,0.010192672,0.002241958,0.84438413],"study_design_scores_gemma":[0.00030525608,0.000076371856,0.00068064034,0.00006236158,0.0000083929,0.000095462296,0.000014481252,0.97697836,0.0004414534,0.0000059070667,0.020948794,0.00038254115],"about_ca_topic_score_codex":0.000007777157,"about_ca_topic_score_gemma":5.8942544e-7,"teacher_disagreement_score":0.8440016,"about_ca_system_score_codex":0.000054300566,"about_ca_system_score_gemma":0.00005332834,"threshold_uncertainty_score":0.99994045},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012668422,0.00071273424,0.99630123,0.0005596893,0.00078467914,0.00023626795,0.0004334032,0.000101047226,0.0007442429],"genre_scores_gemma":[0.03315586,0.00002269213,0.9651917,0.00056799187,0.0004434423,0.0000075401585,0.0005139446,0.000031441556,0.000065382235],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962561,0.000031455722,0.0006094989,0.0016484148,0.0008992886,0.0005552044],"domain_scores_gemma":[0.9943032,0.0006708686,0.00046771602,0.004168055,0.00018912404,0.0002010367],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0008166118,0.00043871495,0.00052636664,0.0004684309,0.00017985376,0.00033482458,0.008308007,0.00023275102,0.000036806345],"category_scores_gemma":[0.00008096716,0.00040471426,0.000070102455,0.0006497199,0.000592807,0.00080389495,0.0027250447,0.0004467239,0.000029882312],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012129809,0.00004499658,0.00015827929,0.0000138807645,0.000011908978,0.0000121291005,0.00031960188,0.003182932,0.00019244864,0.0022208756,0.00014124418,0.9937005],"study_design_scores_gemma":[0.00027220973,0.00006476238,0.00048795086,0.00044051427,0.000021239606,0.000008922127,4.622138e-7,0.9835011,0.0015444339,0.0073722475,0.0056660986,0.0006200731],"about_ca_topic_score_codex":0.00027214305,"about_ca_topic_score_gemma":0.00013082872,"teacher_disagreement_score":0.99308044,"about_ca_system_score_codex":0.00013950608,"about_ca_system_score_gemma":0.0006435896,"threshold_uncertainty_score":0.9998405},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040138505,0.000024517556,0.92135346,0.03570633,0.0005976473,0.00047698608,0.0015901268,0.00008451256,0.000027898179],"genre_scores_gemma":[0.24172062,0.0000053849762,0.7544978,0.0019075897,0.000465042,0.00037742086,0.00097012153,0.000018970637,0.00003702473],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984226,0.000035627727,0.00041877344,0.0005906566,0.00026496043,0.00026736798],"domain_scores_gemma":[0.99416286,0.0013996863,0.00019326521,0.0040305755,0.00013949329,0.00007414871],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041543145,0.00017095591,0.00017627727,0.00007159861,0.0003302856,0.00023213797,0.00385701,0.00006809274,0.000047553964],"category_scores_gemma":[0.00036593436,0.00012777658,0.000063149986,0.00025910107,0.00014264535,0.0003631421,0.0008965662,0.00019504988,0.000026571133],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001703593,0.0008670771,0.0013394715,0.0000412675,0.0004615174,0.000014430323,0.011871804,0.0046292692,0.12162717,0.04939465,0.20599014,0.6037462],"study_design_scores_gemma":[0.0005061816,0.000038395006,0.00062401127,0.000021519787,0.000048541926,0.000004921725,0.00047544308,0.9605882,0.0033060992,0.0012754803,0.032858778,0.000252436],"about_ca_topic_score_codex":0.00030003043,"about_ca_topic_score_gemma":0.00013338205,"teacher_disagreement_score":0.9559589,"about_ca_system_score_codex":0.000011905109,"about_ca_system_score_gemma":0.00010244061,"threshold_uncertainty_score":0.7167348},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42821577,0.0002840756,0.49982515,0.0027846857,0.002403103,0.0014571064,0.00026243893,0.00052403135,0.06424364],"genre_scores_gemma":[0.985211,0.000112844195,0.0068734866,0.000037727754,0.00008115464,0.0000022274205,0.0000073544848,0.000010544223,0.007663635],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987608,0.000011760289,0.00014629941,0.00076196453,0.00009649225,0.00022269048],"domain_scores_gemma":[0.9974065,0.00003658263,0.0005348723,0.0017199476,0.00021771502,0.00008437955],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00020499543,0.00019504962,0.0002310392,0.0000793775,0.0003468758,0.00022609824,0.006013301,0.00017597311,0.000008143535],"category_scores_gemma":[0.000055766195,0.00017062583,0.00018275801,0.0002588755,0.00021253605,0.0004390966,0.004568943,0.00044663087,0.00003168556],"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":[0.000010614749,0.0002501353,0.0046131243,0.00017104828,0.00018243332,0.000026583792,0.0007939416,0.0049410965,0.00019693813,0.9360276,0.04339146,0.009395026],"study_design_scores_gemma":[0.0006941234,0.00004207058,0.022215812,0.0007546648,0.00021948873,0.000013526965,0.00023713999,0.7827299,0.0010983094,0.14667483,0.044172447,0.0011476638],"about_ca_topic_score_codex":0.000077298384,"about_ca_topic_score_gemma":0.0000116869405,"teacher_disagreement_score":0.7893528,"about_ca_system_score_codex":0.000050919058,"about_ca_system_score_gemma":0.00014660195,"threshold_uncertainty_score":0.9993646},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000015965454,0.00017841242,0.86080664,0.00094371865,0.00028353525,0.000838839,0.000050713978,0.00009503649,0.13678715],"genre_scores_gemma":[0.0012506021,0.0010010365,0.99374616,0.00039531308,0.00007394796,0.0001422424,0.0002242103,0.000009631354,0.0031568338],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977501,0.000040146333,0.0008535524,0.00028451873,0.0006205508,0.00045111158],"domain_scores_gemma":[0.9929069,0.0007768216,0.0005551079,0.0044692405,0.0011582989,0.00013362012],"candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.004329676,0.00020030262,0.0002792484,0.0012128283,0.0024419972,0.0025043776,0.0095683215,0.00013580016,6.9136274e-7],"category_scores_gemma":[0.00027180702,0.0002057372,0.000045357443,0.00065444555,0.0014189148,0.011505838,0.005969302,0.0006367193,0.000048515874],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.726178e-7,0.000012289333,0.0000032778773,0.000045817782,0.0000023987438,4.582998e-8,0.0021301627,0.00008053991,5.2937276e-7,0.2974243,0.0044724485,0.69582754],"study_design_scores_gemma":[0.00020350386,0.000036193604,0.00013466783,0.00017732091,0.0000014785569,0.000006130693,0.000038071463,0.5625597,0.0000030432932,0.006765557,0.4299156,0.00015870859],"about_ca_topic_score_codex":0.0000077617,"about_ca_topic_score_gemma":0.0000053303884,"teacher_disagreement_score":0.6956688,"about_ca_system_score_codex":0.0002650895,"about_ca_system_score_gemma":0.0012525723,"threshold_uncertainty_score":0.99885666},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017367499,0.00060881994,0.9440228,0.025153738,0.0030323758,0.0010439247,0.005065576,0.00006609948,0.003639186],"genre_scores_gemma":[0.9020532,0.0004348633,0.09496509,0.0011124479,0.00038210186,0.000038370967,0.0009976181,0.0000058608102,0.000010453707],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99673855,0.000028667624,0.0018385096,0.000115421026,0.0010715119,0.00020731932],"domain_scores_gemma":[0.9950972,0.00009362646,0.0027082972,0.00072243216,0.0012008207,0.00017758668],"candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0017525238,0.00014906329,0.0002833873,0.00048149884,0.00045623735,0.0012224679,0.0026943318,0.000052410407,0.0000015370887],"category_scores_gemma":[0.00021562379,0.00013489503,0.000036005753,0.0001428266,0.0000756825,0.0144309085,0.0005501063,0.00025394358,0.000010567999],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003648024,0.00026194187,0.08636113,0.0007803116,0.00019708686,0.000008427565,0.016157202,0.0012087474,0.0000034585737,0.40691447,0.024427086,0.46364364],"study_design_scores_gemma":[0.0024640674,0.00019448649,0.20373645,0.0013945841,0.0000047873646,0.0010132841,0.008638271,0.43553644,0.000008111653,0.0009864696,0.3454946,0.0005284214],"about_ca_topic_score_codex":0.00034321565,"about_ca_topic_score_gemma":0.000051720297,"teacher_disagreement_score":0.8846857,"about_ca_system_score_codex":0.0001822432,"about_ca_system_score_gemma":0.00089488877,"threshold_uncertainty_score":0.99981433},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98105866,0.000011167201,0.00063153554,0.00013907687,0.0005912597,0.0002978018,0.00016918793,0.00022324017,0.016878044],"genre_scores_gemma":[0.77686894,0.0000035833716,0.22260052,0.000095276024,0.000026921665,0.00008163415,0.000021028423,0.00002218974,0.00027989206],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9979122,0.000104037994,0.0005383479,0.0005851957,0.00045546514,0.00040471388],"domain_scores_gemma":[0.99773484,0.00021225591,0.0002441129,0.0012904463,0.00029565414,0.00022268717],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0015188917,0.00021165928,0.00018931169,0.00008187739,0.0015707677,0.00018211422,0.0019112215,0.00011974955,0.000017264794],"category_scores_gemma":[0.00033779137,0.00016582299,0.00006652924,0.0005043955,0.00013501069,0.0009767688,0.0005546026,0.0005626262,0.0001470046],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031083362,0.00007768881,0.0000035241387,0.0000021090164,0.000013164884,0.0000015203169,0.00001535401,0.000001357522,0.03770838,0.38878056,0.0000017605521,0.5733915],"study_design_scores_gemma":[0.00045505544,0.00014164073,0.0042636213,0.00004740243,0.00002244623,0.000038675484,0.00020617888,0.005004335,0.48989218,0.0793916,0.41976735,0.00076952507],"about_ca_topic_score_codex":0.000039279068,"about_ca_topic_score_gemma":0.00088822766,"teacher_disagreement_score":0.57262194,"about_ca_system_score_codex":0.00006180028,"about_ca_system_score_gemma":0.00009651968,"threshold_uncertainty_score":0.99972904},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3562289,0.000027595714,0.21907681,0.17693414,0.006282077,0.0023353372,0.00079863146,0.00045757912,0.23785895],"genre_scores_gemma":[0.9435409,0.000065216176,0.05408689,0.00025102706,0.00012488193,0.00013556541,0.000010684925,0.000009470807,0.0017754042],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866927,0.0000053264666,0.00034569568,0.00038650702,0.00039589193,0.0001973265],"domain_scores_gemma":[0.99769795,0.00013778887,0.0009121227,0.00031992,0.00088355225,0.000048663973],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006707544,0.00013924233,0.00014368561,0.000086080974,0.00041988547,0.0007805153,0.0030770535,0.00007022036,0.000047900325],"category_scores_gemma":[0.0010371668,0.000114928946,0.00009796237,0.00009303146,0.00006107218,0.0008738913,0.00052709796,0.00013887693,0.000026748638],"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":[0.000031440613,0.00016164842,0.00488026,0.000026567577,0.00007473968,1.5586835e-7,0.0004176801,0.000011941944,0.039849665,0.8372466,0.011556703,0.1057426],"study_design_scores_gemma":[0.00032123213,0.00011590741,0.0032445977,0.00027106854,0.000019266323,0.000004779749,0.0002998996,0.8786565,0.04475648,0.05498287,0.01700216,0.00032523222],"about_ca_topic_score_codex":0.000020356345,"about_ca_topic_score_gemma":0.000009015926,"teacher_disagreement_score":0.8786446,"about_ca_system_score_codex":0.0001265008,"about_ca_system_score_gemma":0.00010948347,"threshold_uncertainty_score":0.7526527},"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":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75345397,0.00024038288,0.060729742,0.18272643,0.00018271657,0.000650002,0.00004442307,0.00013727264,0.0018350394],"genre_scores_gemma":[0.06290916,0.00033322524,0.8361568,0.00002131953,0.00008607055,0.000005907465,0.0014016369,0.000048595783,0.09903728],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99911565,0.000039698945,0.000026731526,0.00044525752,0.00020062923,0.00017202938],"domain_scores_gemma":[0.9990877,0.000045907927,0.0002862245,0.00041918366,0.0001144467,0.00004652245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023689917,0.00014259707,0.00024415532,0.00022406987,0.00013608858,0.00005517285,0.0004445388,0.00014649612,4.238005e-7],"category_scores_gemma":[0.000025749045,0.00018696916,0.00004172945,0.00042357706,0.00006423674,0.00041490432,0.00010533119,0.0001443816,0.00000204131],"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":[0.00006734691,0.00038022915,0.011506129,0.002588056,0.000104121274,0.00014612265,0.014823912,0.00017484033,0.0021846718,0.08106432,0.42045328,0.46650696],"study_design_scores_gemma":[0.0020042977,0.0003151257,0.08748736,0.0025391334,0.00019033557,0.000033196076,0.031875692,0.28248268,0.00071820884,0.0010123233,0.58968437,0.0016572848],"about_ca_topic_score_codex":0.00008875899,"about_ca_topic_score_gemma":0.003732867,"teacher_disagreement_score":0.77542704,"about_ca_system_score_codex":0.000061485,"about_ca_system_score_gemma":0.00011637578,"threshold_uncertainty_score":0.7624381},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16810186,0.00003794305,0.7873097,0.0018243078,0.00013718312,0.00022302681,0.000038634516,0.00013866108,0.042188648],"genre_scores_gemma":[0.90284467,0.000039475904,0.096813075,0.00022919745,0.000016090216,0.00002403187,0.000007335458,9.543642e-7,0.000025197716],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99840397,0.000014969403,0.00033012527,0.00019793662,0.00079448574,0.00025853986],"domain_scores_gemma":[0.998437,0.00009063361,0.00062298717,0.00050359865,0.00025221444,0.00009357893],"candidate_categories":["bibliometrics","sts","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.001508145,0.000117839045,0.0001591973,0.011053523,0.0027420514,0.006917721,0.0016629054,0.00003574304,0.000010096716],"category_scores_gemma":[0.0003142521,0.00008343613,0.000032529464,0.030303897,0.00080326403,0.028129708,0.00036234336,0.000058332596,0.000049688162],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023194382,0.000016041306,0.10050035,0.000011396468,0.000053939337,3.2300838e-7,0.0049009356,0.00045503862,0.0000054801244,0.03401365,0.0011632065,0.8588773],"study_design_scores_gemma":[0.00021554928,0.00018180376,0.5771274,0.000021055057,0.000027213762,0.000013175958,0.0012932763,0.4145515,0.000068736415,0.0005370448,0.005747304,0.00021591173],"about_ca_topic_score_codex":0.00036537935,"about_ca_topic_score_gemma":0.000040421397,"teacher_disagreement_score":0.8586614,"about_ca_system_score_codex":0.000026747164,"about_ca_system_score_gemma":0.000176439,"threshold_uncertainty_score":0.99855626},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49801022,0.000018889006,0.016751774,0.05161704,0.002384575,0.00059290364,0.000059707894,0.00020476297,0.43036014],"genre_scores_gemma":[0.9905472,0.000018481913,0.0075744763,0.00009070734,0.00010827364,0.00003357643,0.0000013250955,0.000006908552,0.0016190963],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987685,0.0000019865342,0.00023178487,0.00035973985,0.0004767192,0.00016128714],"domain_scores_gemma":[0.9979756,0.000016356333,0.00055443007,0.0004739544,0.0009388186,0.000040827133],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00022587966,0.00013056268,0.000120941266,0.00006218188,0.000628652,0.00073286763,0.0058817826,0.000036743826,0.000029728588],"category_scores_gemma":[0.00022892076,0.00009815187,0.000050685383,0.00011467288,0.00018159754,0.00084523665,0.0013071626,0.0001307864,0.000015117432],"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":[0.000003400127,0.00010392992,0.0024730717,0.000030409761,0.000016065691,5.892107e-7,0.00017333281,0.000008770876,0.021493688,0.9523582,0.0018793272,0.021459257],"study_design_scores_gemma":[0.0017865947,0.00020934046,0.2886119,0.003728688,0.00004711035,0.00009869868,0.00062876474,0.42600396,0.0891219,0.17392895,0.01427628,0.0015578548],"about_ca_topic_score_codex":0.00009811063,"about_ca_topic_score_gemma":0.000003118502,"teacher_disagreement_score":0.7784292,"about_ca_system_score_codex":0.000031104657,"about_ca_system_score_gemma":0.000047828922,"threshold_uncertainty_score":0.9994969},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041159387,0.000019253495,0.99231684,0.0014690349,0.0011323348,0.00037708986,0.00004355026,0.00019581044,0.00033012778],"genre_scores_gemma":[0.11688306,0.0000027376548,0.88225096,0.00023717078,0.00040703043,0.00012787255,0.0000054486504,0.00000891329,0.000076774384],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976819,0.000010211374,0.00028051774,0.0009568853,0.00045877547,0.0006116854],"domain_scores_gemma":[0.99781,0.000083912506,0.0002610307,0.0012709344,0.0003229433,0.0002511687],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007946822,0.00018603631,0.0001928869,0.00013011855,0.0019253173,0.0019950932,0.003857724,0.00004514634,0.0000034792984],"category_scores_gemma":[0.00010741923,0.00017775033,0.00007710945,0.00030456984,0.00068455504,0.0018983469,0.0015749431,0.00009475897,0.000029172841],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.4443363e-7,0.000057099693,0.000085644504,0.000009389556,0.0000060041784,0.000006833491,0.00047315532,0.000018098519,0.0005327038,0.009068216,0.00058399606,0.9891581],"study_design_scores_gemma":[0.00043857828,0.00009296811,0.0014808641,0.000031203454,0.000005605128,0.00008623303,0.0000105579775,0.98866403,0.00253733,0.0029565329,0.003437379,0.00025871204],"about_ca_topic_score_codex":0.000017466642,"about_ca_topic_score_gemma":0.0000031492218,"teacher_disagreement_score":0.9888994,"about_ca_system_score_codex":0.000057873505,"about_ca_system_score_gemma":0.0005800131,"threshold_uncertainty_score":0.99937403},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12069861,0.000029154142,0.87703973,0.0018513829,0.00012716911,0.000026813806,0.00014458789,0.000005585465,0.000076940916],"genre_scores_gemma":[0.96843326,0.0003188883,0.031094907,0.000042418458,0.00008107307,5.254981e-7,0.0000128045995,0.000002475016,0.0000136678855],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885666,0.0000063057837,0.00019225635,0.00022887813,0.0006142946,0.000101627265],"domain_scores_gemma":[0.99860406,0.000030609273,0.00032897058,0.0005061144,0.00043436326,0.00009590817],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00051243225,0.00006711558,0.000085823245,0.00014861218,0.00040318797,0.001501568,0.0026254102,0.000014892478,0.0000027370695],"category_scores_gemma":[0.00009626222,0.000050444705,0.000009515407,0.00008571192,0.0002807338,0.00578009,0.0002478261,0.00009930476,0.000001088285],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012866932,0.00010133499,0.01484475,0.000008954562,0.00009098656,0.000057155965,0.0005197781,0.00012327552,0.0007316926,0.004160285,0.000044174787,0.97930473],"study_design_scores_gemma":[0.00093920116,0.00017447826,0.13579983,0.00031475077,0.000065554705,0.0009374031,0.00040403398,0.8568245,0.0014361179,0.0009534326,0.0018711091,0.00027958612],"about_ca_topic_score_codex":0.00021596249,"about_ca_topic_score_gemma":0.00012276834,"teacher_disagreement_score":0.9790252,"about_ca_system_score_codex":0.000025438045,"about_ca_system_score_gemma":0.00024070122,"threshold_uncertainty_score":0.99953496},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48071533,0.0000110851815,0.51754194,0.00023758144,0.00043480625,0.000040230923,0.000027921622,0.00004243847,0.0009486672],"genre_scores_gemma":[0.9551956,0.0000019339327,0.044228792,0.000082410144,0.00027597757,0.000009894247,0.00001372627,0.0000062153736,0.00018544271],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991195,0.000013995692,0.00018425395,0.00030438136,0.00018065628,0.00019720299],"domain_scores_gemma":[0.9988375,0.00006722061,0.00016359577,0.00084951805,0.00002828032,0.000053897827],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016078046,0.00009347154,0.000153999,0.000028601151,0.00043652038,0.00026800722,0.0013166373,0.000051498722,0.0000116475585],"category_scores_gemma":[0.000021514179,0.00008541276,0.00008810008,0.000049027334,0.000043173324,0.00010030573,0.0005647063,0.000067373054,0.000015702637],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005138153,0.0003162983,0.017424908,0.000008033474,0.00012162443,0.000029566454,0.001896567,0.0015376236,0.0007797936,0.010137212,0.0049800393,0.9627632],"study_design_scores_gemma":[0.00035503527,0.000021306132,0.09957317,0.000033269593,0.000016536771,7.648158e-7,0.00011622371,0.89811957,0.000571198,0.00013731582,0.0008641316,0.000191465],"about_ca_topic_score_codex":0.00086726143,"about_ca_topic_score_gemma":0.00003177056,"teacher_disagreement_score":0.96257174,"about_ca_system_score_codex":0.00001123952,"about_ca_system_score_gemma":0.000030815507,"threshold_uncertainty_score":0.3483031},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26926267,0.000028553635,0.728929,0.00013331942,0.001081916,0.0001649103,0.00007841948,0.000089836256,0.00023135843],"genre_scores_gemma":[0.96583426,0.0000029812786,0.033438396,0.000014531941,0.00035412423,0.000064256594,0.00008883609,0.0000058103183,0.00019680784],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99880046,0.00011955631,0.00027636433,0.0004858996,0.000085278574,0.00023247361],"domain_scores_gemma":[0.99799937,0.00006577592,0.00029926383,0.0015036471,0.000066223,0.00006574377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000462936,0.00011010823,0.00018322232,0.000042256954,0.00042377904,0.00030123998,0.0011534945,0.000102369835,0.0000098710125],"category_scores_gemma":[0.000056100023,0.00009626151,0.00003914033,0.00004291984,0.000077225246,0.000229776,0.00034009735,0.00005281974,0.000049865495],"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":[0.000020967385,0.00022096222,0.42644814,0.000179385,0.00011282243,0.000018428376,0.00074722036,0.00015431637,0.08090631,0.3264082,0.0034918538,0.1612914],"study_design_scores_gemma":[0.0006534979,0.00011894014,0.5994933,0.000060986476,0.00001831812,0.000054922446,0.000076153694,0.37958932,0.0057759252,0.0013493835,0.012337169,0.0004720742],"about_ca_topic_score_codex":0.0015739523,"about_ca_topic_score_gemma":0.0000508808,"teacher_disagreement_score":0.6965716,"about_ca_system_score_codex":0.000024664127,"about_ca_system_score_gemma":0.00005782165,"threshold_uncertainty_score":0.39254302},"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000049984023,0.00016466818,0.24884576,0.0001379876,0.000271926,0.000089280766,0.00048789242,0.00011878932,0.7498787],"genre_scores_gemma":[0.0116878,0.00005859032,0.6772914,0.0026265823,0.0025755423,0.000021837339,0.0002996605,0.00010524077,0.30533335],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984679,0.0000073015212,0.00025600812,0.0007993462,0.00024978453,0.00021962405],"domain_scores_gemma":[0.99719244,0.00005007556,0.0001682574,0.002382874,0.00005234003,0.00015403716],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00017854373,0.00025282233,0.00028121192,0.00004836636,0.00011813635,0.0003358951,0.0020445557,0.00016848718,0.0000020385987],"category_scores_gemma":[0.000018199227,0.00024915993,0.00003758938,0.000024043882,0.00009194139,0.00006877699,0.0020373866,0.00012377856,0.000057841557],"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":[2.8617148e-7,0.0000012476082,0.0000023990694,0.000005759992,0.000019528776,0.000005881619,0.000010201016,1.5579784e-7,4.3866567e-7,0.6121894,0.00938569,0.378379],"study_design_scores_gemma":[0.00018831523,0.00005034317,0.00002862278,0.00014622534,0.00008209429,0.00008640057,0.000004263854,0.035348974,0.0000025537067,0.11994717,0.8435745,0.00054048176],"about_ca_topic_score_codex":0.000030886717,"about_ca_topic_score_gemma":0.000052910356,"teacher_disagreement_score":0.8341889,"about_ca_system_score_codex":0.000033157037,"about_ca_system_score_gemma":0.00011568347,"threshold_uncertainty_score":0.99999607},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.099144444,0.000057322144,0.0011881643,0.009410054,0.0014125907,0.0008967899,0.0017435607,0.00020158208,0.8859455],"genre_scores_gemma":[0.9902076,0.00005904628,0.008277368,0.00010997217,0.00029153223,0.00007802143,0.000014739783,0.000023729828,0.00093797495],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99302566,0.000065228385,0.0013001638,0.0018130768,0.0031155297,0.0006803368],"domain_scores_gemma":[0.99132997,0.00027001466,0.002191038,0.00083885697,0.0051256414,0.00024447602],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":["sts"],"category_scores_codex":[0.0044939714,0.0006164576,0.00070755254,0.0006961341,0.0013698764,0.001647527,0.021823768,0.00021676079,0.000011522853],"category_scores_gemma":[0.00009801437,0.00041797297,0.00021565515,0.001519176,0.0036503726,0.004872443,0.005451456,0.00047811403,0.000030298981],"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":[0.000037211714,0.00010714391,0.0047553163,0.00009945611,0.00008102067,1.8453792e-7,0.0028341718,0.000020321522,0.00044367925,0.98641026,0.003487421,0.0017237996],"study_design_scores_gemma":[0.0012865247,0.00095704856,0.007245498,0.0070367665,0.00011086843,0.00016371472,0.8823762,0.085880704,0.0019282027,0.009735438,0.0019424262,0.0013366085],"about_ca_topic_score_codex":0.00038091894,"about_ca_topic_score_gemma":0.000033848886,"teacher_disagreement_score":0.97667485,"about_ca_system_score_codex":0.0003251198,"about_ca_system_score_gemma":0.00060208957,"threshold_uncertainty_score":0.9999302},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042663638,0.000058128317,0.95538706,0.00022522191,0.0001415715,0.0002876219,0.00035534956,0.00015700649,0.0007244175],"genre_scores_gemma":[0.15494868,0.0000013747705,0.84424233,0.0001356975,0.00021786953,0.000028185952,0.00020371836,0.000014258051,0.00020789857],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988794,0.000024979045,0.00029759062,0.00036987753,0.0001759337,0.00025226205],"domain_scores_gemma":[0.9990437,0.00013294448,0.00015504575,0.00047942114,0.00011576603,0.00007311775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000280633,0.00011963604,0.00018132276,0.00005932336,0.00013756608,0.00010455756,0.00071363006,0.00005031074,0.000006938394],"category_scores_gemma":[0.000015126286,0.000119407865,0.000060748265,0.00026246917,0.000045026558,0.00029517568,0.00013036912,0.00006825402,0.00001588391],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013645283,0.000118193835,0.00009597187,0.00001673224,0.000013710442,0.0000051395205,0.0004665586,0.00005418991,0.0013035927,0.014553041,0.008801655,0.97456986],"study_design_scores_gemma":[0.0006050775,0.00011515547,0.0026549748,0.000024909386,0.000009985196,0.000013549283,0.000046817862,0.9670234,0.00317384,0.0032795619,0.022845075,0.0002076646],"about_ca_topic_score_codex":0.00016071225,"about_ca_topic_score_gemma":0.000008380232,"teacher_disagreement_score":0.9743622,"about_ca_system_score_codex":0.000021988748,"about_ca_system_score_gemma":0.000058378064,"threshold_uncertainty_score":0.48693115},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7065744,0.0002324295,0.2550943,0.0054961327,0.017429719,0.00047339464,0.00014497814,0.00013668294,0.014417985],"genre_scores_gemma":[0.9479159,0.000008057135,0.014841003,0.000033791348,0.0369918,0.000001946063,0.000004736529,0.000010391121,0.00019235232],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99887556,0.000060100578,0.00026030824,0.000312093,0.0002459501,0.00024596136],"domain_scores_gemma":[0.9987991,0.000056362052,0.00031749933,0.00070823386,0.000041658706,0.00007715687],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007592052,0.00010149941,0.00021132825,0.000061270526,0.0010393659,0.0017951522,0.0020473003,0.00003974663,0.0000015511235],"category_scores_gemma":[0.000035041587,0.00009360583,0.000022369863,0.00006044096,0.00006971487,0.0010196165,0.0005801315,0.00025331983,0.000019236948],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000040587133,0.0001353421,0.0026130918,0.00003415754,0.000043594966,0.00016862788,0.0096040955,0.0001281144,0.00025065435,0.0024312104,0.15498756,0.8295995],"study_design_scores_gemma":[0.0009978422,0.000040384326,0.021138791,0.00018947203,0.000012530321,0.000815593,0.0004905453,0.83898926,0.000018228442,0.00017879953,0.1367847,0.00034387325],"about_ca_topic_score_codex":0.00009997972,"about_ca_topic_score_gemma":0.00001718233,"teacher_disagreement_score":0.8388611,"about_ca_system_score_codex":0.000028179373,"about_ca_system_score_gemma":0.00005801809,"threshold_uncertainty_score":0.99924105},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019780514,0.00020123573,0.98471105,0.009860522,0.000070089605,0.00020163604,0.00060784334,0.000048321268,0.0023212745],"genre_scores_gemma":[0.22028255,0.00085896754,0.77836245,0.00016566413,0.000039879553,0.000020421623,0.000048892554,0.00001857632,0.00020260493],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865824,0.00016170264,0.00033384454,0.00025857397,0.0002936679,0.00029399229],"domain_scores_gemma":[0.99394876,0.0009198689,0.0005760848,0.0041888608,0.000218263,0.0001481651],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0013404243,0.00016530583,0.00017288288,0.00006359065,0.005596771,0.0029721204,0.005000227,0.000025636233,0.0000064414166],"category_scores_gemma":[0.0004306071,0.00010706653,0.000018042088,0.00011254777,0.0004475929,0.00056604337,0.0014004402,0.00049594097,0.000009972704],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009271261,0.00015663389,0.0003255789,0.000013530531,0.00008170773,0.0000143046,0.0025412033,0.000022046015,0.000023099386,0.43896407,0.0059482413,0.5519003],"study_design_scores_gemma":[0.0014148591,0.00084404927,0.013275681,0.0004991471,0.0001186916,0.00078204734,0.0013663943,0.8058097,0.000044009186,0.08010905,0.095012024,0.0007243751],"about_ca_topic_score_codex":0.00009771233,"about_ca_topic_score_gemma":0.00005165714,"teacher_disagreement_score":0.8057876,"about_ca_system_score_codex":0.000023145809,"about_ca_system_score_gemma":0.00013829318,"threshold_uncertainty_score":0.9980629},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010495029,0.0000030549136,0.98805976,0.0007898463,0.00012517288,0.00010534393,0.000011893751,0.000016184926,0.00039369072],"genre_scores_gemma":[0.7848651,0.000018490564,0.2133951,0.0016444984,0.0000472042,0.000013876232,0.0000065105537,0.000001454003,0.0000077745035],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992351,0.0000093693225,0.0001970341,0.00012347395,0.00031624865,0.000118768665],"domain_scores_gemma":[0.9991855,0.00007067182,0.00012756375,0.00039466596,0.0001787533,0.00004283184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006276443,0.000054775046,0.000057146473,0.0001483403,0.00078981963,0.00048640167,0.00065932504,0.000011041961,0.0000017087762],"category_scores_gemma":[0.000010422853,0.000030284475,0.000021283697,0.0015116388,0.0004325663,0.0024041615,0.0002729097,0.00003719025,0.0000032339024],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.731891e-7,0.0000031363359,0.0004313968,0.000001290262,0.000004730266,7.3481328e-9,0.00083876675,0.00004520811,0.000006407112,0.019222215,0.00015665588,0.9792898],"study_design_scores_gemma":[0.000094139294,0.000045318986,0.10041321,0.0000033032643,0.0000067094684,0.0000010414414,0.00007444372,0.893278,0.000828009,0.0001832634,0.0050329287,0.00003965229],"about_ca_topic_score_codex":0.000029110524,"about_ca_topic_score_gemma":0.000008911695,"teacher_disagreement_score":0.97925013,"about_ca_system_score_codex":0.00001220783,"about_ca_system_score_gemma":0.00007153898,"threshold_uncertainty_score":0.60747343},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16982637,0.000026511932,0.8281217,0.0001182131,0.0013858704,0.00032785104,0.00006777439,0.000085566986,0.000040108684],"genre_scores_gemma":[0.9497734,0.000033223863,0.04945574,0.00005565106,0.00053884654,0.00007142331,0.000008025497,0.000031634263,0.000032114865],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99744076,0.0003214228,0.0007080534,0.0006001044,0.0003481695,0.0005815224],"domain_scores_gemma":[0.9985283,0.00024069638,0.00027794996,0.0007073865,0.00012273426,0.00012294995],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011042759,0.00026502158,0.00035982198,0.0004958491,0.00027190265,0.00011424158,0.0007149321,0.00043864636,0.00002722516],"category_scores_gemma":[0.00004070836,0.000288312,0.00012674574,0.001588697,0.00007927415,0.00046001107,0.0000112337075,0.00094445905,0.0000064916117],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007307662,0.00038977654,0.00006222593,0.0000055799683,0.000095394935,0.0000026817465,0.00054272916,0.0026550682,0.045769997,0.0003318959,0.000053262498,0.9500183],"study_design_scores_gemma":[0.0023294794,0.0010741708,0.000030313315,0.00012310616,0.000077075354,0.000032517248,0.00013017122,0.287549,0.7037663,0.00019562274,0.004255847,0.00043641464],"about_ca_topic_score_codex":0.0006840154,"about_ca_topic_score_gemma":0.00041283845,"teacher_disagreement_score":0.9495819,"about_ca_system_score_codex":0.00040912704,"about_ca_system_score_gemma":0.0005080427,"threshold_uncertainty_score":0.9999569},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6674754,0.000012213095,0.33137497,0.0001938535,0.000025240135,0.000040392224,0.0000033476601,0.000058228714,0.0008163124],"genre_scores_gemma":[0.89586943,0.000022615906,0.10379612,0.00015753334,0.000028493136,0.000002645049,0.0000099361405,0.0000025358122,0.00011070272],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99927014,0.000014001389,0.00019215085,0.0002609267,0.000113837465,0.00014892811],"domain_scores_gemma":[0.9992252,0.00001694158,0.00009181879,0.0005173064,0.00005655512,0.00009215771],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008661432,0.00005780759,0.00016788702,0.00021273155,0.00015903231,0.000061907085,0.0003529142,0.000017993592,0.000013217182],"category_scores_gemma":[0.0000042559764,0.00005011417,0.000026019794,0.0009161445,0.000025961554,0.00042585365,0.000097275384,0.00003656794,0.0000059081945],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018056406,0.00025202482,0.38426003,0.000048967046,0.0003308231,0.0000020647049,0.0030295542,0.0006870457,0.00025856827,0.16812252,0.00078863814,0.44220173],"study_design_scores_gemma":[0.0000516686,0.00011704737,0.20468356,0.000007533401,0.00002112367,0.0000029870023,0.000059107737,0.7934815,0.0002565792,0.000022538017,0.0012355997,0.000060725404],"about_ca_topic_score_codex":0.000120833094,"about_ca_topic_score_gemma":0.00003517725,"teacher_disagreement_score":0.79279447,"about_ca_system_score_codex":0.000012652465,"about_ca_system_score_gemma":0.000035615685,"threshold_uncertainty_score":0.20435965},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013433306,0.000024284653,0.9765356,0.02127125,0.000039860195,0.00040282152,0.00009658815,0.00006997984,0.0002162942],"genre_scores_gemma":[0.035347864,0.0000039579945,0.9628729,0.0002853756,0.0001675417,0.00027851344,0.00014746426,0.000009000909,0.0008873796],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985752,0.00018661152,0.00023022894,0.00032580455,0.00039756458,0.00028460874],"domain_scores_gemma":[0.9960635,0.00040694335,0.00002770142,0.00038342839,0.0030341393,0.00008434311],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019321406,0.00007970246,0.00011632177,0.00025563725,0.00071428774,0.0002421458,0.00050073833,0.00008090604,0.000037293223],"category_scores_gemma":[0.0006204255,0.00007282575,0.000047698144,0.0012487418,0.000106834595,0.00037459948,0.00011930318,0.00015579745,0.000034211414],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006484617,0.00079317996,0.000144053,0.0000925668,0.00015352314,0.0000012318006,0.0009814063,0.0698441,0.05621543,0.4514486,0.2894125,0.13084859],"study_design_scores_gemma":[0.00016333374,0.00029532638,0.00076689763,0.000017316745,0.0000021050735,0.0000029404912,0.000008679969,0.96178526,0.023681529,0.0006399522,0.012561365,0.00007528491],"about_ca_topic_score_codex":0.000059460912,"about_ca_topic_score_gemma":0.00017889513,"teacher_disagreement_score":0.8919412,"about_ca_system_score_codex":0.000019820638,"about_ca_system_score_gemma":0.00041463578,"threshold_uncertainty_score":0.5493796},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1321618,0.0000044753674,0.86638004,0.00020068986,0.00017976244,0.00007439905,0.00020876518,0.00006116901,0.00072889845],"genre_scores_gemma":[0.97985,0.0000023428552,0.019686215,0.00005938752,0.000040678602,0.000010622376,0.00033501873,0.0000010413454,0.000014709566],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99941576,0.000009057287,0.00029300054,0.000080315825,0.00013471501,0.000067183246],"domain_scores_gemma":[0.99918616,0.000023664761,0.00019304044,0.00041650565,0.00015645649,0.000024167332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015144014,0.00004297117,0.00005450232,0.000052685904,0.000073307914,0.00011371564,0.0003616191,0.000026360925,0.000020675932],"category_scores_gemma":[0.00003093941,0.000040724357,0.000012541956,0.00020489341,0.000041407282,0.0020797043,0.00007657719,0.000026890932,0.00035489583],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004736349,0.00003635474,0.00078078004,0.000012281483,0.000010222716,5.1652034e-8,0.004127428,0.000008493441,0.0021863114,0.031341974,0.006994259,0.9544971],"study_design_scores_gemma":[0.00032678145,0.000050536186,0.16885765,0.000021700018,0.000009186651,0.0000017472321,0.0001486955,0.68238837,0.10673115,0.011472824,0.029812986,0.00017838509],"about_ca_topic_score_codex":0.00064867106,"about_ca_topic_score_gemma":0.000017897113,"teacher_disagreement_score":0.9543187,"about_ca_system_score_codex":0.0000115209905,"about_ca_system_score_gemma":0.000023865918,"threshold_uncertainty_score":0.45615864},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020267966,0.0010839243,0.9644464,0.00095168734,0.000623437,0.00043048986,0.029705144,0.00020050786,0.00053158327],"genre_scores_gemma":[0.066121496,0.00007788814,0.8095101,0.00021973402,0.0007852207,0.000186227,0.122503266,0.000052377465,0.0005436883],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963353,0.00006383267,0.00053616625,0.0024295412,0.0002682605,0.00036685664],"domain_scores_gemma":[0.99409395,0.000530649,0.0003201588,0.004767869,0.00011239806,0.00017498396],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.00084072707,0.00041070994,0.0004483671,0.00015652325,0.0003751598,0.0011750308,0.005108274,0.00024309279,0.0000028182374],"category_scores_gemma":[0.000400643,0.0004268358,0.00006762198,0.0002465324,0.00011235954,0.0022303092,0.01281509,0.00032298945,0.000014374103],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049184022,0.00040890675,0.0003211457,0.00088063715,0.00023802623,0.000006183033,0.0033079376,0.0023723503,0.00014361214,0.01253683,0.29462478,0.6851104],"study_design_scores_gemma":[0.0004444029,0.000034933444,0.00017594082,0.0003087851,0.00010123519,0.0000029405435,0.000113678165,0.9808395,0.000011853823,0.0012302307,0.016238086,0.0004984478],"about_ca_topic_score_codex":0.000023446599,"about_ca_topic_score_gemma":0.00005927711,"teacher_disagreement_score":0.9784671,"about_ca_system_score_codex":0.000041757565,"about_ca_system_score_gemma":0.0011615411,"threshold_uncertainty_score":0.99986184},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025336083,0.0008638059,0.9931855,0.0026856815,0.0004423829,0.00012726184,0.000010811092,0.000021382726,0.00012956254],"genre_scores_gemma":[0.012403353,0.00062754,0.9835641,0.0024407748,0.0009297352,0.000015272826,0.000005183913,0.000004375899,0.000009707877],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984241,0.000019047919,0.00043937654,0.0003187995,0.0006361029,0.00016254249],"domain_scores_gemma":[0.99692583,0.00007396216,0.0003975695,0.0003492543,0.0021254355,0.00012792667],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073582696,0.00009464556,0.00013788158,0.00021833563,0.00033599988,0.00017724639,0.0016358156,0.000019170606,0.0000065253635],"category_scores_gemma":[0.00007129198,0.00008474262,0.00003437747,0.000656127,0.00037141144,0.0016996734,0.00045918778,0.000120263925,0.00000932053],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023120729,0.00006813384,0.000048881153,0.00001045965,0.000021100599,0.0000052240975,0.00009296654,0.00046245346,0.010258579,0.10655076,0.0007189375,0.8817602],"study_design_scores_gemma":[0.0005694848,0.00018030548,0.000674455,0.00058472087,0.000025841004,0.00175767,0.000022293583,0.8284536,0.0020862005,0.0063641258,0.15895635,0.0003249522],"about_ca_topic_score_codex":0.0000038784674,"about_ca_topic_score_gemma":0.0000013010135,"teacher_disagreement_score":0.8814352,"about_ca_system_score_codex":0.00008039322,"about_ca_system_score_gemma":0.00036559073,"threshold_uncertainty_score":0.34557036},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012317957,0.000044401397,0.9858789,0.00029221294,0.0008445146,0.00045786315,0.00004436854,0.000055330656,0.000064446],"genre_scores_gemma":[0.245833,0.00001517534,0.7534424,0.00014163567,0.00031361452,0.000016055432,0.00019130709,0.000022090204,0.00002473308],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99728143,0.000019124422,0.00045238482,0.0015527311,0.0003545593,0.00033976787],"domain_scores_gemma":[0.9978037,0.00021337574,0.00030710036,0.0014135577,0.00018540889,0.000076888595],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008148743,0.00026174422,0.00024639152,0.00047471884,0.00023090867,0.00045926083,0.0018149763,0.00014614608,0.0000022396464],"category_scores_gemma":[0.00012548857,0.00025687378,0.000022234115,0.00028417126,0.00024435113,0.000921056,0.0017053538,0.00025229395,0.0000034122677],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003211712,0.000028213346,0.0008604233,0.000029096487,0.0000030163849,0.0000011911559,0.0008462414,0.00017496219,0.00012598981,0.0007740846,0.000038355276,0.9971152],"study_design_scores_gemma":[0.00030565218,0.00014236988,0.0041378043,0.0008244523,0.0000066757943,0.000011461491,0.0000016029111,0.9851856,0.00015782163,0.008521277,0.00035305668,0.00035218528],"about_ca_topic_score_codex":0.000026477768,"about_ca_topic_score_gemma":0.000063413594,"teacher_disagreement_score":0.99676305,"about_ca_system_score_codex":0.0001816769,"about_ca_system_score_gemma":0.00012823656,"threshold_uncertainty_score":0.9999884},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023703292,0.013027235,0.96807855,0.000043281125,0.002274811,0.00032134075,0.00020978377,0.000130598,0.015677374],"genre_scores_gemma":[0.60000926,0.008792806,0.34886348,0.0009920552,0.014768785,0.0001027449,0.003103685,0.00045792293,0.02290926],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969154,0.00003904897,0.00095324015,0.001368667,0.00033560098,0.0003880187],"domain_scores_gemma":[0.99706495,0.0004506533,0.0006160118,0.0016505752,0.00008996194,0.00012782731],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005609442,0.00043355042,0.0005906497,0.00018735138,0.00022092098,0.00042498694,0.001935703,0.00018317299,0.000017536033],"category_scores_gemma":[0.000027215272,0.0004274963,0.000051808373,0.000089312365,0.00016738121,0.0004260136,0.001701636,0.0003354691,0.00005219387],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.709643e-7,0.000013095829,0.00016509376,0.00007364421,0.000042752417,0.000029073763,0.0007439256,0.000149319,0.000006266112,0.0069138585,0.00019957531,0.99166244],"study_design_scores_gemma":[0.00020505274,0.000071066555,0.000030759787,0.0036259328,0.000030144503,0.00007550414,0.0003583891,0.7223007,0.000024566314,0.0050003794,0.2674548,0.0008226602],"about_ca_topic_score_codex":0.0005168606,"about_ca_topic_score_gemma":0.00013942273,"teacher_disagreement_score":0.9908398,"about_ca_system_score_codex":0.000073354946,"about_ca_system_score_gemma":0.000057141726,"threshold_uncertainty_score":0.99981767},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024524214,0.000106219966,0.9732014,0.00056685635,0.00054832204,0.0007289282,0.000015620988,0.00008067641,0.00022775683],"genre_scores_gemma":[0.15577376,0.000011037242,0.84232044,0.00004238784,0.00012072208,0.00017409727,0.00004172681,0.000015001434,0.0015008487],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983012,0.000110951856,0.00029427194,0.00042706626,0.00053257414,0.00033391672],"domain_scores_gemma":[0.9982444,0.00045695307,0.00009019737,0.00041677133,0.0006881707,0.0001035163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007308786,0.000092513445,0.00011931387,0.0003293941,0.0003079142,0.00020100691,0.0007211033,0.000074586154,0.0000084778185],"category_scores_gemma":[0.0005508186,0.00008292423,0.000041768366,0.0014996028,0.00014424007,0.0002624728,0.00020929001,0.00018304707,0.000009614747],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002115442,0.00006927667,0.000075827644,0.000019789855,0.000024346698,4.980697e-7,0.003450737,0.021332448,0.001412407,0.00022917996,0.01860516,0.9547592],"study_design_scores_gemma":[0.00018770041,0.00047703958,0.00047932376,0.000047310034,0.000002970086,0.000004320713,0.000094221876,0.9913604,0.00281954,0.00018659588,0.0042456575,0.00009488685],"about_ca_topic_score_codex":0.00014732106,"about_ca_topic_score_gemma":0.00001606964,"teacher_disagreement_score":0.970028,"about_ca_system_score_codex":0.00005729125,"about_ca_system_score_gemma":0.000062483734,"threshold_uncertainty_score":0.33815518},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013449802,0.012148179,0.96293414,0.000040552557,0.001835215,0.00069580355,0.00009105916,0.0001331915,0.020776886],"genre_scores_gemma":[0.4101614,0.008439869,0.56021416,0.00040139467,0.006331041,0.00005937185,0.0014283081,0.00032043242,0.01264405],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965719,0.00006330929,0.0010898623,0.0014837281,0.00032406382,0.0004671421],"domain_scores_gemma":[0.99736077,0.00033764858,0.0005452981,0.0015754944,0.000042556567,0.00013826165],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010654475,0.00043960637,0.0006224869,0.00030640062,0.0001905009,0.00034441534,0.0019171515,0.00018632255,0.000008258718],"category_scores_gemma":[0.000022319917,0.0004538239,0.000037079757,0.000113966074,0.0002173744,0.00056500017,0.0018655659,0.00038378703,0.000032106287],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022802578,0.000044793065,0.00035783465,0.000119624696,0.000016858383,0.000037261685,0.001287811,0.0016226216,0.0000038116061,0.040469646,0.00007555666,0.9559619],"study_design_scores_gemma":[0.0002115115,0.00011634243,0.000052409894,0.0019734753,0.000010015762,0.00006559972,0.0005599687,0.8493965,0.0000048522743,0.0015411401,0.14543605,0.0006320904],"about_ca_topic_score_codex":0.00006244395,"about_ca_topic_score_gemma":0.000076859484,"teacher_disagreement_score":0.95532984,"about_ca_system_score_codex":0.00011178399,"about_ca_system_score_gemma":0.000063879605,"threshold_uncertainty_score":0.9997913},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0073600323,0.000024789102,0.99094236,0.00061599555,0.0003496968,0.00016577276,0.0003600975,0.00008467522,0.00009655973],"genre_scores_gemma":[0.35882595,0.0000064829264,0.6405846,0.00033835426,0.00012922099,0.0000036926644,0.00010186798,0.0000054099073,0.0000043984196],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99704117,0.000022541757,0.0004051226,0.0014077394,0.00060787227,0.00051554956],"domain_scores_gemma":[0.9938845,0.00011496825,0.00019491935,0.0053369063,0.00031599708,0.00015271278],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.002200961,0.00015423135,0.00020751865,0.00029229233,0.00019082727,0.0003229391,0.016094876,0.00004011249,0.000003035937],"category_scores_gemma":[0.00022646744,0.00014714664,0.000013991434,0.0030916177,0.0006851757,0.0026303574,0.0072704875,0.00014380942,0.000032618766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017613755,0.00194307,0.047620233,0.00026073772,0.000034815686,0.000048683723,0.0030451494,0.0021932367,0.005389464,0.09481479,0.012298485,0.83233374],"study_design_scores_gemma":[0.00020313066,0.000055961278,0.0043545044,0.00003879208,0.0000036397907,0.0000076213173,0.000005038491,0.99138093,0.0012494355,0.00049300503,0.0020387834,0.00016913781],"about_ca_topic_score_codex":0.00005570951,"about_ca_topic_score_gemma":0.00006634786,"teacher_disagreement_score":0.9891877,"about_ca_system_score_codex":0.000044552216,"about_ca_system_score_gemma":0.0010519752,"threshold_uncertainty_score":0.98922855},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5273218,0.00002567328,0.4614758,0.008737415,0.0013690097,0.00036794215,0.00031057152,0.000022043248,0.00036976908],"genre_scores_gemma":[0.9594051,0.000016331504,0.0394288,0.00040259882,0.00027511094,0.000020721516,0.00042053452,0.0000040177742,0.000026787146],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99755,0.00005670396,0.00049373053,0.00034020774,0.0012936245,0.00026572356],"domain_scores_gemma":[0.99860513,0.0001536677,0.00030729602,0.00035737557,0.00051096245,0.00006556487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031732023,0.0000714838,0.00009636704,0.00043699512,0.0002942264,0.00047959198,0.0034187275,0.00004159378,0.000014339515],"category_scores_gemma":[0.0004900594,0.00006194484,0.000027620099,0.0008812769,0.00006827954,0.0022140073,0.00048982527,0.00017809286,0.0000042798747],"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":[0.00011406956,0.0010381012,0.20062795,0.00007686047,0.00014538903,0.00004554494,0.013936602,0.0049353302,0.013419151,0.2746689,0.019746996,0.4712451],"study_design_scores_gemma":[0.0010465404,0.00016656613,0.74275523,0.0003896431,0.000014885531,0.00017209168,0.0009869108,0.23292097,0.00020982535,0.016385414,0.0046785497,0.00027338692],"about_ca_topic_score_codex":0.00034943482,"about_ca_topic_score_gemma":0.0011029433,"teacher_disagreement_score":0.54212725,"about_ca_system_score_codex":0.0005759058,"about_ca_system_score_gemma":0.000482676,"threshold_uncertainty_score":0.6352903},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003992436,0.00069202227,0.9957097,0.00007672345,0.00053473364,0.00038089918,0.00049074116,0.000051620693,0.0016643115],"genre_scores_gemma":[0.3879697,0.00077033386,0.57093966,0.000740037,0.021677203,0.00044715736,0.010460176,0.00042512373,0.006570607],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984454,0.000015892994,0.00036297186,0.00066366384,0.00020774732,0.00030434434],"domain_scores_gemma":[0.99842936,0.00039416392,0.00036203017,0.0007025441,0.00006967451,0.000042227246],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001516548,0.0002952866,0.00048216866,0.00009822831,0.00020329567,0.00010130306,0.0016793034,0.00047459782,0.000025112735],"category_scores_gemma":[0.00004953812,0.00026338108,0.000103680104,0.00011353129,0.00012957526,0.0001179855,0.0007665977,0.00034483467,6.0649927e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027700258,0.00008515374,0.0005872313,0.00016739992,0.0003820677,0.0000012987584,0.005531872,0.0035695466,0.000010149785,0.029043814,0.006094929,0.9544988],"study_design_scores_gemma":[0.00070281187,0.00011642433,0.0005837377,0.00049318303,0.00023774111,0.0000012217772,0.000020331176,0.9323881,0.00006210906,0.02210381,0.04219747,0.0010930137],"about_ca_topic_score_codex":0.000050334347,"about_ca_topic_score_gemma":0.00018436814,"teacher_disagreement_score":0.9534058,"about_ca_system_score_codex":0.00006410177,"about_ca_system_score_gemma":0.00007760551,"threshold_uncertainty_score":0.9999818},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000023256747,0.00062144955,0.3064487,0.00008396054,0.0002400235,0.0002901145,0.0002916305,0.00013520902,0.6918657],"genre_scores_gemma":[0.06012412,0.000036005273,0.7701788,0.00077444944,0.000999706,0.00025943306,0.000044014574,0.00008639919,0.1674971],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99884814,0.000007302136,0.0002889332,0.00048249518,0.0001754909,0.00019761582],"domain_scores_gemma":[0.998835,0.00028534763,0.00015504753,0.00051018945,0.00013962289,0.000074767915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001838033,0.00022663576,0.00024329036,0.00006370804,0.00020449275,0.00030102718,0.0005905591,0.00017304772,0.0000045599304],"category_scores_gemma":[0.000037159723,0.00023125418,0.00008089284,0.000018061475,0.000064498636,0.00013393302,0.00035826306,0.00009735781,0.00005173434],"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":[0.0000014130333,0.0000058606533,3.3983625e-7,0.000009510447,0.0000090714375,5.283745e-7,0.00007923035,2.7703024e-7,3.254565e-7,0.6190237,0.0026159112,0.37825382],"study_design_scores_gemma":[0.00018195805,0.000043341035,0.000018631888,0.00027249573,0.00001737191,0.000016683096,0.000009706725,0.0051084533,0.0000033107563,0.8052865,0.18878247,0.00025904967],"about_ca_topic_score_codex":0.0000084409,"about_ca_topic_score_gemma":0.000036228656,"teacher_disagreement_score":0.5243686,"about_ca_system_score_codex":0.00010526028,"about_ca_system_score_gemma":0.00012944732,"threshold_uncertainty_score":0.94302714},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009835181,0.000073189396,0.73854935,0.03437408,0.00059949775,0.0003215261,0.0018913262,0.0014133034,0.21294254],"genre_scores_gemma":[0.1626332,0.00013915455,0.8213306,0.00070287834,0.00022638118,0.0000013195441,0.00012143642,0.000016780265,0.014828264],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99721354,0.000018810739,0.00013663474,0.001518145,0.0006695804,0.00044330937],"domain_scores_gemma":[0.992052,0.00011003919,0.00007359723,0.0074275415,0.00007558791,0.00026123098],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0013012938,0.00010414114,0.00009135616,0.00029075192,0.0008370786,0.0009823248,0.032742895,0.00002313831,0.00009294607],"category_scores_gemma":[0.00016638094,0.00007149599,0.000009273819,0.003179726,0.0017089025,0.02614485,0.025498493,0.00006232581,0.00025203367],"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":[0.00000125234,0.000083505445,0.001026763,0.0000028747943,0.000005223929,0.000013124188,0.00014953176,4.1902967e-7,0.004575257,0.42617318,0.16836761,0.39960125],"study_design_scores_gemma":[0.00019006371,0.000022340362,0.003748515,0.00002477298,0.00000459158,0.000014267911,0.000101405196,0.050783,0.0014602254,0.000653586,0.94277114,0.00022606735],"about_ca_topic_score_codex":0.0000930976,"about_ca_topic_score_gemma":0.0000147470655,"teacher_disagreement_score":0.7744036,"about_ca_system_score_codex":0.00003092402,"about_ca_system_score_gemma":0.00080726674,"threshold_uncertainty_score":0.987476},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054740712,0.0000146968605,0.94080126,0.0010625577,0.00079600833,0.00006975662,0.0011189977,0.00027812744,0.0011178945],"genre_scores_gemma":[0.7109693,0.0000028486588,0.28208697,0.0006673007,0.0031095382,0.000014276996,0.002874895,0.000014882677,0.0002599309],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998527,0.000028918646,0.00021834318,0.0006466123,0.00022373062,0.00035540792],"domain_scores_gemma":[0.9983272,0.00008959386,0.00007923602,0.0013732947,0.000039748564,0.000090937574],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022319179,0.00013321123,0.0001540101,0.0000211229,0.00042982996,0.00038179953,0.00256451,0.000059513655,0.000047512272],"category_scores_gemma":[0.000025263673,0.00012330501,0.00004212576,0.0003179163,0.000048815607,0.00044741336,0.0016541556,0.00008147746,0.00019679106],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033880074,0.00012168258,0.006642252,0.0000025580289,0.0001369355,0.000023462339,0.0008133806,0.0000036594213,0.00018106222,0.009012563,0.31909534,0.66396374],"study_design_scores_gemma":[0.0010120845,0.00011756664,0.0991002,0.00007253445,0.0000860936,0.000008518243,0.00047402486,0.57288957,0.00058447575,0.005234906,0.31931347,0.0011065571],"about_ca_topic_score_codex":0.00073290453,"about_ca_topic_score_gemma":0.0001985885,"teacher_disagreement_score":0.6628572,"about_ca_system_score_codex":0.000016243646,"about_ca_system_score_gemma":0.00005501141,"threshold_uncertainty_score":0.50282323},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9740585,0.000010128799,0.0241333,0.00013436377,0.000060400933,0.00008636732,0.000028103817,0.00009399333,0.0013948026],"genre_scores_gemma":[0.98375875,5.181982e-7,0.015889524,0.00011549907,0.000029368568,0.0000028610634,0.000018722,0.000004093515,0.0001806512],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99912196,0.00003117166,0.00020919317,0.0003045473,0.00018965988,0.00014348136],"domain_scores_gemma":[0.9986345,0.000033263754,0.00008723996,0.0010969202,0.00008112847,0.00006694892],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000115941555,0.00008849374,0.00014987904,0.00012645313,0.00012911584,0.00008797571,0.0010534034,0.00003484571,0.000070799746],"category_scores_gemma":[0.0000081684575,0.00005954525,0.00010733188,0.0017405553,0.00011450305,0.00027034598,0.00017620964,0.00004321938,0.000014113527],"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":[0.000062075924,0.008605545,0.031651907,0.000018194438,0.0060016573,0.000009464851,0.03695188,0.4303229,0.044833068,0.09131872,0.014464686,0.33575994],"study_design_scores_gemma":[0.00010144889,0.000094916475,0.008526331,0.0000019933086,0.00009645919,2.2282762e-7,0.00022760074,0.9790277,0.011344896,0.000015497599,0.00048301052,0.000079964724],"about_ca_topic_score_codex":0.00020629972,"about_ca_topic_score_gemma":0.00017211278,"teacher_disagreement_score":0.5487048,"about_ca_system_score_codex":0.000018293258,"about_ca_system_score_gemma":0.000025914707,"threshold_uncertainty_score":0.24281849},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032533698,0.000010896586,0.965139,0.00086581474,0.00029009162,0.00075530837,0.00004740387,0.00019167377,0.00016614927],"genre_scores_gemma":[0.7026828,0.000014318915,0.29698864,0.00006982849,0.00008066571,0.00007295706,0.000066920824,0.000016137616,0.0000077264],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99810785,0.00006580272,0.0004997382,0.00070006447,0.00033527965,0.00029124878],"domain_scores_gemma":[0.99776906,0.00016128452,0.0002063472,0.0006738774,0.0010353606,0.00015410007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000312696,0.00020440137,0.00026745643,0.00019495253,0.0002795992,0.000087508735,0.00048043602,0.00015050669,0.000004392093],"category_scores_gemma":[0.00022952931,0.00018891119,0.00011231268,0.0011263948,0.00045681137,0.00057671807,0.00020713135,0.0001326692,0.0000047231024],"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":[0.000019737248,0.00025077557,0.000028798451,0.000039334736,0.00003504481,5.0951866e-7,0.00051260646,0.0020456815,0.0006603971,0.95948833,0.00016477256,0.03675404],"study_design_scores_gemma":[0.00029784712,0.00014007154,0.0002452269,0.0000199791,0.00003165626,0.000012270743,0.000015716514,0.61101735,0.0008296469,0.38718945,0.0000675904,0.00013319329],"about_ca_topic_score_codex":0.00003689076,"about_ca_topic_score_gemma":0.000010264977,"teacher_disagreement_score":0.6701491,"about_ca_system_score_codex":0.000049072514,"about_ca_system_score_gemma":0.00007516016,"threshold_uncertainty_score":0.7703575},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0069814306,0.0013299522,0.9573497,0.01944255,0.004455767,0.0010542409,0.000019489862,0.000660545,0.00870629],"genre_scores_gemma":[0.61757684,0.000102441496,0.33159995,0.0007170396,0.016741376,0.00035294998,0.0000312947,0.00012454193,0.03275358],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99756765,0.00013257515,0.00043142017,0.00080045447,0.00041755763,0.0006503149],"domain_scores_gemma":[0.9974385,0.000104114886,0.00018217713,0.0018774694,0.00022684615,0.00017088758],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010008848,0.00031715594,0.00027420034,0.00011130439,0.0009259627,0.00071538624,0.0023165983,0.00014239011,0.000052465133],"category_scores_gemma":[0.0001143422,0.00025788465,0.00012334765,0.00053286005,0.00030573222,0.00032382683,0.00065894413,0.00041620326,0.0008204912],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009429643,0.00011314418,0.00003193919,0.000027189108,0.00005414302,0.000005549377,0.008928343,0.000044023567,0.00008915476,0.13584203,0.0035505665,0.8513045],"study_design_scores_gemma":[0.00019400608,0.00017996028,0.000023611445,0.000060699625,0.00005144772,0.000020855161,0.00009680438,0.23261063,0.000040279545,0.0019229016,0.76451135,0.00028748717],"about_ca_topic_score_codex":0.00017766013,"about_ca_topic_score_gemma":0.000036880512,"teacher_disagreement_score":0.851017,"about_ca_system_score_codex":0.00032770706,"about_ca_system_score_gemma":0.0002249893,"threshold_uncertainty_score":0.99998736},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08843809,0.000016220698,0.90465426,0.0024136545,0.0009767178,0.00089770043,0.00009299288,0.00015284742,0.0023574962],"genre_scores_gemma":[0.930002,0.000014618247,0.069434084,0.0002309735,0.00011399373,0.00010346433,0.000010626774,0.000025410673,0.00006486827],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968884,0.00001936216,0.00071584235,0.0011171291,0.0008279592,0.0004312867],"domain_scores_gemma":[0.99680364,0.00022131849,0.0008676388,0.00095959345,0.0010239929,0.00012379131],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005541931,0.0004416422,0.00048011862,0.00017705496,0.00019543673,0.0008694128,0.004303524,0.00023368718,0.000049240665],"category_scores_gemma":[0.00022881477,0.0003139701,0.00018202845,0.00047906023,0.0004311245,0.0002562104,0.0015698293,0.00072853384,0.00009397972],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050179162,0.00025951816,0.0006269278,0.00015711157,0.000048258436,0.0000017374166,0.000829327,0.0016266926,0.0017425009,0.16489884,0.0004105968,0.8293483],"study_design_scores_gemma":[0.00007978545,0.0003240939,0.00024437634,0.0025947436,0.000052887197,0.000007177709,0.00042487553,0.82047576,0.1257348,0.049204495,0.00016500439,0.0006919697],"about_ca_topic_score_codex":0.000093850795,"about_ca_topic_score_gemma":0.000029274046,"teacher_disagreement_score":0.8415639,"about_ca_system_score_codex":0.00007091615,"about_ca_system_score_gemma":0.00061415916,"threshold_uncertainty_score":0.9999312},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012718322,0.00015729244,0.9970356,0.0016366682,0.00012919701,0.00009572499,0.0004406889,0.0001288173,0.00024883501],"genre_scores_gemma":[0.0068920534,0.000014329942,0.9918872,0.0007881054,0.00012609422,0.00000914242,0.00022930834,0.000012031609,0.00004173413],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99870306,0.000029351075,0.00023689582,0.00039649187,0.00044858526,0.00018559158],"domain_scores_gemma":[0.9986838,0.0006641137,0.000101988684,0.0002017166,0.00015183009,0.00019653533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000099563826,0.0001387122,0.00015028172,0.00004657083,0.0002861972,0.00038203306,0.0006009431,0.000035123183,0.000020492185],"category_scores_gemma":[0.00012463686,0.00013729451,0.000033085442,0.00029983284,0.00006319021,0.00028251702,0.00022636968,0.000103014914,0.00019251322],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015491747,0.00004215592,0.000040948125,0.000006406512,0.0000109166085,0.000015059653,0.0003665379,0.0032156054,0.0000062561044,0.03695214,0.013234205,0.9461082],"study_design_scores_gemma":[0.00022528815,0.0000606777,0.0014499511,0.000020727553,0.000008769133,0.00001203833,0.000026482558,0.8707877,0.00003033506,0.122112796,0.005116251,0.00014898615],"about_ca_topic_score_codex":0.000010624183,"about_ca_topic_score_gemma":0.0000010446822,"teacher_disagreement_score":0.9459592,"about_ca_system_score_codex":0.000026343576,"about_ca_system_score_gemma":0.00010707957,"threshold_uncertainty_score":0.5598708},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024154233,0.00003451003,0.9941031,0.0027082711,0.000050280323,0.00007393256,0.000026602365,0.00016941791,0.00041846087],"genre_scores_gemma":[0.04444621,0.00000474223,0.95421034,0.0008337803,0.00007894389,0.0000064244014,0.00028603076,0.000009056749,0.00012448066],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991044,0.00005616865,0.00012123857,0.00047213654,0.000101424994,0.00014463425],"domain_scores_gemma":[0.9992307,0.00006497931,0.00008196977,0.00045277525,0.000115653456,0.00005392091],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045264474,0.00010497385,0.00011876066,0.0000736261,0.0003720466,0.00025877592,0.0004908647,0.000043423373,0.00004877236],"category_scores_gemma":[0.000016748152,0.00008963704,0.000013520014,0.00051925896,0.000012811173,0.0014608458,0.0004252637,0.00011176986,0.000005978666],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024059658,0.00024170078,0.0010111774,0.000085462816,0.0009632388,0.0000019892914,0.002284305,0.011322512,0.011732879,0.0124796685,0.008557971,0.951295],"study_design_scores_gemma":[0.00011366222,0.00002644196,0.000022921013,0.0000049525543,0.000095437514,0.000011549384,0.000019526056,0.98880774,0.0004986639,0.0001612453,0.010128895,0.000108992346],"about_ca_topic_score_codex":0.0004938625,"about_ca_topic_score_gemma":0.00033956344,"teacher_disagreement_score":0.9774852,"about_ca_system_score_codex":0.0000148090085,"about_ca_system_score_gemma":0.000037222104,"threshold_uncertainty_score":0.36552924},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016301414,0.06792372,0.13253205,0.004322364,0.025493449,0.004612152,0.3083535,0.00077512034,0.4543575],"genre_scores_gemma":[0.15382488,0.028300539,0.38614824,0.0015605207,0.0018716631,0.00016954626,0.07075222,0.00037152995,0.35700086],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99807554,0.000037907157,0.0004886615,0.00091693376,0.00028523398,0.0001957387],"domain_scores_gemma":[0.9945566,0.0005207894,0.00030014498,0.0044110683,0.00018034277,0.000031051975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001217387,0.00022925828,0.000583959,0.00012417255,0.000055346558,0.00003290454,0.0035104873,0.000109802095,0.000007468336],"category_scores_gemma":[0.0002822303,0.00021219155,0.000026172045,0.00014420257,0.00019868217,0.00020240367,0.006992608,0.00020514382,0.000050289276],"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":[0.0000073617407,0.000068543755,0.0010940369,0.00024044071,0.00032943502,0.000016346758,0.00079211936,0.0000015904268,7.6843213e-7,0.04577495,0.40827534,0.5433991],"study_design_scores_gemma":[0.0007671766,0.0001388047,0.027176471,0.0012881292,0.00007111708,0.000009505354,0.00021798404,0.009177882,0.0000073046626,0.009828666,0.95010567,0.0012112871],"about_ca_topic_score_codex":0.0007538117,"about_ca_topic_score_gemma":0.001628279,"teacher_disagreement_score":0.5421878,"about_ca_system_score_codex":0.00002948544,"about_ca_system_score_gemma":0.00014727317,"threshold_uncertainty_score":0.8715786},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3137752,0.001763655,0.5922677,0.022382475,0.00040162713,0.0019361444,0.0007464042,0.0005170637,0.06620971],"genre_scores_gemma":[0.87014425,0.0003420324,0.120747544,0.00014350252,0.00009579619,0.0002508837,0.0006596791,0.000016213093,0.007600076],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990629,0.00002144083,0.00022571889,0.00045981177,0.00010029436,0.00012981708],"domain_scores_gemma":[0.9989758,0.00014722477,0.0000740005,0.0006868879,0.000056032222,0.00006004276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013650327,0.00010012281,0.0001280802,0.00016426228,0.000056416076,0.0002209349,0.0008070435,0.000037358477,0.000039378923],"category_scores_gemma":[0.000031714946,0.00008530936,0.000009883591,0.00061315804,0.000062787396,0.0008852479,0.00055185764,0.000077196564,0.000012192411],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014912418,0.00014871357,0.0063663707,0.00000998029,0.000018657824,2.0119114e-7,0.00032586427,0.000005770258,0.00035714032,0.007155163,0.020147655,0.965463],"study_design_scores_gemma":[0.00057651114,0.000055617653,0.45303404,0.00009490624,0.000011775939,0.000006601088,0.000291835,0.49089777,0.00006352973,0.00021227288,0.054451082,0.00030403904],"about_ca_topic_score_codex":0.00014118207,"about_ca_topic_score_gemma":0.00007987745,"teacher_disagreement_score":0.96515894,"about_ca_system_score_codex":0.000013096009,"about_ca_system_score_gemma":0.000027365422,"threshold_uncertainty_score":0.34788147},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00441232,0.00009625181,0.99141616,0.0005089908,0.00016334643,0.000072755,0.000048943406,0.00015777432,0.0031234575],"genre_scores_gemma":[0.33231154,0.0000021522294,0.6658837,0.0009834974,0.00009628048,0.000017435952,0.00014101597,0.0000060762986,0.0005582754],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992556,0.00002221385,0.000107363616,0.0002670472,0.000116375726,0.00023142985],"domain_scores_gemma":[0.99846673,0.000061345694,0.00002981585,0.00130124,0.000027539,0.00011332235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019984134,0.00007609868,0.00006830431,0.000028284703,0.000120640914,0.0001318803,0.0013319844,0.00002039386,0.00005940359],"category_scores_gemma":[0.00002240085,0.00006320992,0.000012788282,0.00018941307,0.000021888984,0.00067869417,0.0005396077,0.000037875274,0.00024075762],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025143927,0.0005742579,0.0018576737,0.000010114292,0.000057626203,0.000010575842,0.0013223757,0.00033684156,0.001044519,0.030959982,0.12589222,0.8379313],"study_design_scores_gemma":[0.0001600592,0.000025097372,0.00029774042,0.000005272372,0.0000054871007,0.000014403909,0.000039351467,0.8478135,0.0032720524,0.000009567532,0.14817987,0.00017762707],"about_ca_topic_score_codex":0.000022435426,"about_ca_topic_score_gemma":0.0000055303162,"teacher_disagreement_score":0.8474766,"about_ca_system_score_codex":0.000010398079,"about_ca_system_score_gemma":0.000035925605,"threshold_uncertainty_score":0.30945325},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04150332,0.0003346175,0.94289416,0.005503727,0.00030578912,0.0011258922,0.00011635012,0.000052133684,0.008163978],"genre_scores_gemma":[0.84913766,0.0001224044,0.15052319,0.000110620516,0.000013062196,0.00004080183,0.0000018983271,0.000002376159,0.000048005913],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991989,0.0000032919613,0.0002870192,0.00020246195,0.0001725906,0.0001357048],"domain_scores_gemma":[0.9992499,0.00014000066,0.000113543974,0.00011138801,0.00035030072,0.00003487354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001860863,0.000072045936,0.0001301432,0.000055896326,0.00017405803,0.000018547247,0.00060829637,0.000026402018,0.0000023448638],"category_scores_gemma":[0.000056031713,0.000051824933,0.00006094859,0.00048375368,0.000294866,0.00021707802,0.000077397715,0.00006536577,0.0000012881005],"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":[0.0000012393741,0.00004144043,0.00024716128,0.000018005838,0.000007116975,4.5293195e-8,0.0017002994,0.0012892197,0.000023694734,0.95304227,0.00022313495,0.043406352],"study_design_scores_gemma":[0.00006138088,0.00019138007,0.0022827128,0.00015160872,0.0000060504453,0.0000061331484,0.005248921,0.6415322,0.020090513,0.32862607,0.0015721838,0.00023085203],"about_ca_topic_score_codex":0.001049685,"about_ca_topic_score_gemma":0.009024434,"teacher_disagreement_score":0.8076343,"about_ca_system_score_codex":0.00004227432,"about_ca_system_score_gemma":0.0002445277,"threshold_uncertainty_score":0.50358456},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020096581,0.000010565009,0.9916812,0.0022788483,0.00029697866,0.00033415755,0.00012378128,0.00011059288,0.0031541805],"genre_scores_gemma":[0.021239124,4.0598835e-7,0.97549665,0.00092481385,0.0005345204,0.000038020717,0.00010554338,0.000014922544,0.0016459725],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99847007,0.000012966241,0.00019328625,0.0008123518,0.0001863601,0.0003249538],"domain_scores_gemma":[0.99787146,0.000031048025,0.00006051139,0.0017398683,0.000093917624,0.00020322304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025379434,0.00013905617,0.0001424243,0.000075145865,0.00024116892,0.00048052002,0.0023876913,0.00004369607,0.00004404493],"category_scores_gemma":[0.00004562831,0.0001234795,0.000029814293,0.0003120336,0.000043440003,0.00058580533,0.0013785219,0.000049137932,0.00012078282],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037817083,0.00010306354,0.000049287522,0.000015085234,0.000030681524,7.622207e-7,0.0041231154,0.000018771247,0.00069568754,0.0032901561,0.2598211,0.73184854],"study_design_scores_gemma":[0.00024324306,0.00006561331,0.00014914502,0.000021424867,0.000012755303,0.000012100247,0.00042302482,0.8537646,0.00058310677,0.00015294815,0.1443141,0.00025794143],"about_ca_topic_score_codex":0.00035177678,"about_ca_topic_score_gemma":0.000017860213,"teacher_disagreement_score":0.8537458,"about_ca_system_score_codex":0.000029181885,"about_ca_system_score_gemma":0.00024174976,"threshold_uncertainty_score":0.5035348},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.063435785,0.0016234906,0.6476272,0.0029608877,0.00069470337,0.0007622804,0.000022633965,0.00021431368,0.28265873],"genre_scores_gemma":[0.4723249,0.00006246551,0.52361786,0.00009563764,0.000063132415,0.000017868555,0.0000031421055,0.0000048580096,0.003810109],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995478,0.0000023688413,0.000097236385,0.0001625583,0.00007336871,0.000116702824],"domain_scores_gemma":[0.99943,0.000026489479,0.000037360827,0.00044745416,0.000019165753,0.000039558596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026403388,0.000046190347,0.000046372974,0.000022074233,0.000060337643,0.00005907404,0.0011985414,0.000011831071,0.0000036596136],"category_scores_gemma":[0.000009331594,0.000029221677,0.0000079333195,0.00024304708,0.000031507083,0.00041789596,0.0024394921,0.000026405365,0.0000060796337],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.9248984e-7,0.00006600251,0.0014371632,0.000017878765,0.000011393953,2.0523345e-8,0.0011886217,5.9253107e-8,0.000027638078,0.20315184,0.022170799,0.77192837],"study_design_scores_gemma":[0.00031970104,0.000029484992,0.0378013,0.00026002404,0.0000731603,0.000027992191,0.0083105825,0.19973354,0.006032433,0.0009482293,0.74595976,0.0005037874],"about_ca_topic_score_codex":0.0000016955794,"about_ca_topic_score_gemma":0.0000012416484,"teacher_disagreement_score":0.7714246,"about_ca_system_score_codex":0.000004692226,"about_ca_system_score_gemma":0.0000041257954,"threshold_uncertainty_score":0.30406523},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1909874,0.0000040350787,0.8020744,0.0012114552,0.00024219908,0.00006978501,0.000023865325,0.00010228174,0.0052846284],"genre_scores_gemma":[0.9263723,0.0000020048542,0.07217671,0.00049944624,0.00009906455,0.000015090263,0.000011218578,0.0000038551757,0.00082032796],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990949,0.000021440212,0.00016885747,0.00035963117,0.00011007866,0.00024507954],"domain_scores_gemma":[0.99927026,0.00002350987,0.000041160514,0.00055971544,0.000047435504,0.00005792574],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022910257,0.000078207486,0.000088588415,0.000044009616,0.00008642702,0.00013496976,0.00066319935,0.000027645085,0.00012147842],"category_scores_gemma":[0.000015438472,0.000068106645,0.000016820484,0.0002797371,0.00007876965,0.00029054016,0.0002916222,0.00006141841,0.000103171194],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000042825704,0.00013131207,0.019158613,0.0000096050935,0.000009756869,0.000028926062,0.0016535203,0.0000018635251,0.0004668189,0.023497425,0.033010196,0.9220277],"study_design_scores_gemma":[0.0009905967,0.00012944755,0.090604715,0.00007427529,0.000005173914,0.000030584717,0.00016518781,0.8172968,0.0048155156,0.0029856921,0.08234531,0.0005566909],"about_ca_topic_score_codex":0.003476649,"about_ca_topic_score_gemma":0.0030859523,"teacher_disagreement_score":0.921471,"about_ca_system_score_codex":0.000024771789,"about_ca_system_score_gemma":0.000041027404,"threshold_uncertainty_score":0.52556765},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0095587205,0.00020178007,0.9843827,0.0016506374,0.00015180014,0.0005091349,0.000040352843,0.000018364704,0.0034865257],"genre_scores_gemma":[0.7874916,0.00006651545,0.21223131,0.000118734264,0.0000064843653,0.00004193943,0.0000010581887,0.000002506787,0.000039809154],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99920577,0.0000056191107,0.0002822316,0.00021540148,0.00014564511,0.0001453496],"domain_scores_gemma":[0.99925673,0.00017100624,0.000112587346,0.000120562836,0.0003032086,0.00003591622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003027132,0.00007446465,0.00012525784,0.00004692215,0.000089232315,0.000025686824,0.00054052117,0.000023736411,0.000003618557],"category_scores_gemma":[0.00011774945,0.00005373547,0.000055866265,0.00047270008,0.00016702949,0.00020807025,0.000047075137,0.000060831793,0.0000010664293],"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":[7.71665e-7,0.00003242036,0.000119959346,0.000019243209,0.0000056795766,1.9074193e-8,0.00089427794,0.0013957783,0.00003565414,0.9578513,0.00010674553,0.039538164],"study_design_scores_gemma":[0.000044383134,0.00013529274,0.00039538532,0.0001353207,0.0000057512952,0.0000018931415,0.0059681684,0.33371735,0.0333293,0.62446016,0.0016302849,0.00017669547],"about_ca_topic_score_codex":0.000364773,"about_ca_topic_score_gemma":0.0028800797,"teacher_disagreement_score":0.77793294,"about_ca_system_score_codex":0.000038460217,"about_ca_system_score_gemma":0.0002087421,"threshold_uncertainty_score":0.2191269},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028138366,0.00043522168,0.9323171,0.017416026,0.00051650434,0.0002379209,0.00002419313,0.00042231515,0.020492358],"genre_scores_gemma":[0.95632297,0.000033560496,0.042005155,0.0004069174,0.00007771669,0.00003153438,0.0000066738958,0.000005498167,0.0011099711],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992006,0.00006249074,0.000115641094,0.00022703505,0.00022470074,0.00016955247],"domain_scores_gemma":[0.99874836,0.00005166219,0.000055258464,0.00087195303,0.00014897701,0.00012376302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005225276,0.00008326512,0.00007891944,0.00002763483,0.00013322524,0.00031309202,0.0015443362,0.000030290857,0.000017714941],"category_scores_gemma":[0.00007331407,0.000052491305,0.000018912304,0.00025675687,0.00005510971,0.00045273983,0.00041096294,0.00014262157,0.00072657404],"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":[0.0000051629722,0.000115063594,0.0005168808,0.0000061971223,0.000018112132,0.000008713369,0.0021885857,0.000033939454,0.003967389,0.38489488,0.15211377,0.45613134],"study_design_scores_gemma":[0.00044712113,0.00007647831,0.0015261144,0.000042668966,0.000010648795,0.000035949866,0.00029590412,0.44262475,0.0019152771,0.02332913,0.52939093,0.00030500523],"about_ca_topic_score_codex":0.000057578298,"about_ca_topic_score_gemma":0.000012642228,"teacher_disagreement_score":0.9281846,"about_ca_system_score_codex":0.000015286902,"about_ca_system_score_gemma":0.000260624,"threshold_uncertainty_score":0.93388814},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9920804,0.000054544464,0.006087117,0.00075592945,0.00006475589,0.00018260886,0.00003018655,0.000007848701,0.00073661224],"genre_scores_gemma":[0.9978258,0.0000163044,0.0019589516,0.000009584037,0.000005609806,0.000007780252,0.000014262451,0.0000017177116,0.00016000199],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916965,0.00007648799,0.00019178524,0.000105730316,0.00040239005,0.00005397579],"domain_scores_gemma":[0.9991283,0.00006220801,0.0003321092,0.0002560854,0.00021357553,0.000007752775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072416523,0.000048409805,0.00009738114,0.000021619935,0.000044061922,0.000028104238,0.0003253448,0.000037416532,0.000010838439],"category_scores_gemma":[0.000030649237,0.000025119598,0.00002065412,0.00008473248,0.000029958324,0.00017186553,0.0000894311,0.000037501766,0.0000013896334],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027308677,0.0003578612,0.28711146,0.00025630224,0.00015599081,2.054828e-8,0.0036941245,0.005020639,0.14283024,0.2574438,0.00335342,0.29974884],"study_design_scores_gemma":[0.00014366,0.000019734638,0.049078938,0.00004681579,0.000020633182,1.7830307e-7,0.00005557827,0.93289083,0.011690335,0.0059133256,0.00010344547,0.000036513866],"about_ca_topic_score_codex":0.00028153494,"about_ca_topic_score_gemma":0.00001549897,"teacher_disagreement_score":0.9278702,"about_ca_system_score_codex":0.0000109397215,"about_ca_system_score_gemma":0.000089715,"threshold_uncertainty_score":0.10243475},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052383017,0.002979479,0.2794348,0.59651065,0.014085085,0.010733019,0.0013798836,0.00038666005,0.042107444],"genre_scores_gemma":[0.96474606,0.0008426357,0.02662434,0.00024240841,0.0003553102,0.00020328946,0.0000075186545,0.000017771003,0.00696067],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99819386,0.0001860519,0.00024187978,0.00040373224,0.0006088422,0.00036561937],"domain_scores_gemma":[0.99176824,0.0026291835,0.00016880223,0.0007856841,0.004595135,0.000052939864],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00092950294,0.00012824465,0.00016519676,0.00006533888,0.001420045,0.00019938346,0.0022444956,0.000029177349,0.0000031390196],"category_scores_gemma":[0.0026464146,0.0000715681,0.000048532493,0.0010345262,0.00091631245,0.00013758999,0.0008866898,0.00022221015,0.00002397588],"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":[0.00013992722,0.00013176269,0.000023998302,0.000010860705,0.0001423895,4.35523e-7,0.0042043463,0.00015572329,0.00050005934,0.62787056,0.034115825,0.33270413],"study_design_scores_gemma":[0.0017159,0.0010878204,0.000649312,0.001013471,0.000011455741,9.200978e-7,0.028337754,0.07722708,0.047478378,0.044778164,0.7972825,0.0004172086],"about_ca_topic_score_codex":0.000001328672,"about_ca_topic_score_gemma":0.000082645114,"teacher_disagreement_score":0.91236305,"about_ca_system_score_codex":0.00012374364,"about_ca_system_score_gemma":0.00023573237,"threshold_uncertainty_score":0.99987996},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.901731,0.000035993304,0.08976389,0.0026656722,0.0005819563,0.00023498664,0.00034969355,0.00019224183,0.004444531],"genre_scores_gemma":[0.65404606,0.000006105175,0.3436581,0.000345664,0.00026442533,5.107492e-7,0.0000863792,0.000016725564,0.0015760415],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9979526,0.00008433631,0.00019287945,0.0009062317,0.00043593478,0.00042804997],"domain_scores_gemma":[0.9966487,0.00010986063,0.00017511497,0.0025103844,0.00021721063,0.00033872112],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006847511,0.0001909283,0.0002669859,0.00029150138,0.0007050134,0.00013132213,0.0049113003,0.00012203769,0.00012687159],"category_scores_gemma":[0.00013306207,0.000236933,0.000068263136,0.0010928982,0.00033157232,0.0014306554,0.0033480565,0.00020187933,0.00053950434],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010369489,0.00022697452,0.0581429,0.00003997445,0.00019101049,0.00007465267,0.0080776345,0.0000067428095,0.009989385,0.007824581,0.029595675,0.88572675],"study_design_scores_gemma":[0.0038995815,0.0010349678,0.5755475,0.0003931886,0.00020971101,0.00024551325,0.005658823,0.014138451,0.009041803,0.0022495869,0.38532892,0.0022519492],"about_ca_topic_score_codex":0.00011080028,"about_ca_topic_score_gemma":0.0003009752,"teacher_disagreement_score":0.8834748,"about_ca_system_score_codex":0.00006379025,"about_ca_system_score_gemma":0.00016735618,"threshold_uncertainty_score":0.96618474},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19839153,0.00060960534,0.7963625,0.00084925443,0.00040126205,0.00046396093,0.0012256247,0.00014094917,0.0015553061],"genre_scores_gemma":[0.8381269,0.0005515771,0.14436904,0.00013720257,0.00063276856,0.000014990518,0.014519414,0.0000723788,0.0015757631],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864197,0.00003505431,0.000121037374,0.0007549644,0.00027373244,0.00017323883],"domain_scores_gemma":[0.99798757,0.00011754169,0.00030244593,0.0013790547,0.00010974693,0.000103638245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015116112,0.00017808015,0.00024786152,0.00014399298,0.00029120976,0.00007836564,0.0022345704,0.00013698901,0.00000269221],"category_scores_gemma":[0.00001385551,0.000231182,0.000039255785,0.00023027978,0.000036525944,0.00012800365,0.0007060054,0.00015671588,0.00006392245],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000070858773,0.00018949882,0.0011427408,0.00019368967,0.00014008691,0.0000114056775,0.0015511679,0.000055593842,0.00057590136,0.0021301701,0.0061665243,0.9878361],"study_design_scores_gemma":[0.00085090345,0.00007902061,0.11491961,0.0004471408,0.0003130906,0.000004775299,0.014161905,0.74957556,0.00021753585,0.0002674597,0.11816799,0.0009950222],"about_ca_topic_score_codex":0.0019414054,"about_ca_topic_score_gemma":0.053760417,"teacher_disagreement_score":0.98684114,"about_ca_system_score_codex":0.000034087127,"about_ca_system_score_gemma":0.000071640476,"threshold_uncertainty_score":0.963506},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6942971,0.00004292812,0.29964253,0.0016891949,0.00074106647,0.00026914565,0.00007639737,0.000188094,0.0030535283],"genre_scores_gemma":[0.9648704,0.000010526544,0.03359148,0.000359199,0.000034267032,0.000029423381,0.00005673173,0.000008528306,0.0010394703],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999057,0.00002778874,0.0001824291,0.0003663945,0.00015419221,0.00021221634],"domain_scores_gemma":[0.9992357,0.00006708804,0.00004796668,0.00057879713,0.000014524399,0.000055915592],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019240641,0.00009384951,0.00010546289,0.00022010953,0.000045781104,0.00010495722,0.00049721054,0.000020952788,0.00011246206],"category_scores_gemma":[0.0000049588384,0.000096860786,0.000037263202,0.00058706326,0.0000121135345,0.00056930626,0.0000763598,0.00012306227,0.00014130626],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027322281,0.0005666827,0.32895392,0.0001460186,0.00006461881,0.00011139971,0.002941799,0.0007104072,0.027534237,0.079486236,0.015135266,0.5443221],"study_design_scores_gemma":[0.0031110705,0.0001342395,0.09916561,0.0005332067,0.0000315985,0.000043807275,0.00038533358,0.6445836,0.011627381,0.0019373767,0.23704723,0.0013995996],"about_ca_topic_score_codex":0.00019812078,"about_ca_topic_score_gemma":0.0008828432,"teacher_disagreement_score":0.64387316,"about_ca_system_score_codex":0.000026790829,"about_ca_system_score_gemma":0.00004057371,"threshold_uncertainty_score":0.39498684},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005554788,0.021361588,0.9001705,0.000030164148,0.0017358119,0.00059354183,0.000013778756,0.00007275399,0.075466394],"genre_scores_gemma":[0.8839903,0.01914127,0.039360892,0.00015293239,0.00072729634,0.00008369982,0.00019166559,0.00016301232,0.05618893],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982148,0.000020148354,0.0006536115,0.0006458997,0.00021690484,0.00024865672],"domain_scores_gemma":[0.9989326,0.00019351125,0.00032471077,0.00046901594,0.000032984488,0.000047164707],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00033926763,0.00025819617,0.00038708452,0.00028293018,0.00006493653,0.00018862876,0.0004841638,0.00012755707,0.000002548282],"category_scores_gemma":[0.000009835466,0.0002563996,0.00005009763,0.00011752927,0.0000371887,0.0004701911,0.00030823678,0.00034568223,0.000031647876],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011691428,0.000012372677,0.0014817828,0.00013031656,0.0000075013018,0.000010520709,0.00040759853,0.025590518,0.0000016392253,0.80166656,0.00001450286,0.17067555],"study_design_scores_gemma":[0.00017515484,0.00005595592,0.00031150124,0.0032768638,0.000005964915,0.000032712564,0.0001551005,0.87732965,0.0000066727466,0.011504937,0.10658736,0.0005581124],"about_ca_topic_score_codex":0.00018166579,"about_ca_topic_score_gemma":0.000095653115,"teacher_disagreement_score":0.88343483,"about_ca_system_score_codex":0.00011420292,"about_ca_system_score_gemma":0.000039107097,"threshold_uncertainty_score":0.9999888},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05027594,0.000007777936,0.94634235,0.00081134035,0.00011862026,0.00034748172,0.000034567216,0.00015560664,0.0019063099],"genre_scores_gemma":[0.109316744,5.9115126e-7,0.8893572,0.0009204565,0.000013298827,0.000027517863,0.00001859016,0.000012630037,0.0003329499],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989667,0.000029839437,0.00013710352,0.0005042726,0.00014718344,0.00021491297],"domain_scores_gemma":[0.99894494,0.00020738924,0.000051377647,0.0006320644,0.00004996759,0.00011424323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004425895,0.000106707994,0.00012306964,0.00006561083,0.00013290711,0.00023474444,0.00041806328,0.000037415626,0.000044694014],"category_scores_gemma":[0.000020758482,0.00008981869,0.000026760734,0.00015510664,0.0000128787915,0.00016827919,0.00010000728,0.000047585007,0.000039056125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017808617,0.0007146691,0.00058735994,0.00007363489,0.000022691454,0.000004331016,0.0015292338,0.022044305,0.00456984,0.1914627,0.009572548,0.7694009],"study_design_scores_gemma":[0.00033507007,0.00018417707,0.00092020805,0.000017052536,0.0000033930592,0.000003785165,0.00005767005,0.98639745,0.00056916854,0.00015938927,0.011218295,0.00013431853],"about_ca_topic_score_codex":0.000040081497,"about_ca_topic_score_gemma":0.0000011170769,"teacher_disagreement_score":0.96435314,"about_ca_system_score_codex":0.00001924728,"about_ca_system_score_gemma":0.000028191687,"threshold_uncertainty_score":0.36627},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021363216,0.00007870995,0.97628736,0.0010490336,0.00005406671,0.00049029954,0.00006080546,0.00005671394,0.0005598152],"genre_scores_gemma":[0.22717912,0.000090990965,0.7703922,0.00026063842,0.00018844941,0.00021516625,0.00013657077,0.000017111699,0.0015197577],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998575,0.00008061155,0.00018202835,0.00040268808,0.0004268731,0.00033280262],"domain_scores_gemma":[0.9981156,0.00059629057,0.0000577995,0.00089897733,0.00026044127,0.00007087387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024376877,0.00008471968,0.00022375389,0.0001050757,0.00033936475,0.00021318809,0.0010779997,0.000050134182,0.000004810776],"category_scores_gemma":[0.000022861615,0.00005951628,0.00017377638,0.0021664465,0.00016975074,0.00021923648,0.0006086533,0.00022518865,0.0000052519244],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004312009,0.00063908636,0.006092363,0.000587215,0.0043050563,7.6409987e-7,0.021296712,0.0050148456,0.010144364,0.28326485,0.12387174,0.5447399],"study_design_scores_gemma":[0.0001919172,0.00007070397,0.005734335,0.000007810345,0.00004399969,0.0000011269815,0.00023912477,0.9888556,0.00048132712,0.00046677218,0.0038306613,0.000076635224],"about_ca_topic_score_codex":0.000076645796,"about_ca_topic_score_gemma":7.4515793e-7,"teacher_disagreement_score":0.98384076,"about_ca_system_score_codex":0.00003642348,"about_ca_system_score_gemma":0.00007015078,"threshold_uncertainty_score":0.26101536},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8507341,0.000017131062,0.1487732,0.00012758956,0.00006963899,0.00012926516,0.00005724369,0.000022932918,0.00006892088],"genre_scores_gemma":[0.9856288,0.0000033019894,0.014204001,0.00010748677,0.000010390145,0.00001571267,0.000017515587,0.000004325571,0.000008500311],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99914885,0.000024126088,0.00020178904,0.0003161703,0.00015977088,0.00014930237],"domain_scores_gemma":[0.99934334,0.00007859775,0.00010323366,0.0004052419,0.000025481566,0.000044099754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022056377,0.00007862634,0.00013813398,0.00006314685,0.00003589119,0.00016802315,0.0007372928,0.00002685493,0.000019268762],"category_scores_gemma":[0.00000867386,0.00008228332,0.000012240743,0.00024247044,0.000031974534,0.001001515,0.00018842724,0.000071943316,0.0000031524353],"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":[0.000037335732,0.0014999097,0.37533644,0.00024725008,0.000027722259,0.0000105075,0.0012199646,0.0001494264,0.07469439,0.0012779895,0.0009999535,0.54449916],"study_design_scores_gemma":[0.004422493,0.00025224226,0.20482507,0.0003854223,0.000010914212,0.00000375269,0.0002024182,0.56263214,0.22593759,0.00030615224,0.0004965038,0.0005252667],"about_ca_topic_score_codex":0.0012018499,"about_ca_topic_score_gemma":0.000044936085,"teacher_disagreement_score":0.5624827,"about_ca_system_score_codex":0.00001422389,"about_ca_system_score_gemma":0.000034493798,"threshold_uncertainty_score":0.33554164},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12303863,0.00056880066,0.8688662,0.0030038736,0.000055742585,0.0002015119,0.00008097165,0.00014107482,0.0040432005],"genre_scores_gemma":[0.6023225,0.000030930627,0.39654788,0.000085100255,0.00011683242,0.000003932367,0.000061104365,0.000011147635,0.0008205577],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983287,0.000052916195,0.00011718466,0.0008732796,0.00035943088,0.00026848188],"domain_scores_gemma":[0.99780166,0.0002241805,0.000035075536,0.0017390494,0.000111393085,0.00008861397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047913217,0.000103895,0.00013208436,0.00008274684,0.00016960454,0.000456394,0.0016433881,0.000033307137,0.000017926839],"category_scores_gemma":[0.000012471131,0.00008029113,0.0000075469297,0.00032102663,0.000079100144,0.00040974552,0.001971073,0.00016667607,0.000054547232],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004681341,0.00014286416,0.0039864616,0.0000117795835,0.000054353313,0.000008729227,0.01098493,0.000110807414,0.00013502473,0.024358436,0.011932333,0.9482696],"study_design_scores_gemma":[0.0002465042,0.00007306701,0.0030013497,0.000039475617,0.0000028251745,0.000005817851,0.0027212726,0.9869927,0.00004391743,0.00089686125,0.005825378,0.00015081718],"about_ca_topic_score_codex":0.0024646872,"about_ca_topic_score_gemma":0.00010211539,"teacher_disagreement_score":0.9868819,"about_ca_system_score_codex":0.00001537859,"about_ca_system_score_gemma":0.000059739697,"threshold_uncertainty_score":0.44010177},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005856736,0.000016771239,0.9906911,0.00052069733,0.0001483841,0.00060951174,0.0015968095,0.00016239987,0.00039758012],"genre_scores_gemma":[0.010725321,0.000008925451,0.98665345,0.00032273724,0.00028038945,0.00012459671,0.0013968545,0.000026502428,0.0004612194],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99814695,0.000017972588,0.0003427163,0.00077370065,0.0003408736,0.0003777641],"domain_scores_gemma":[0.9982703,0.0001518268,0.0001410939,0.0012542352,0.00006373526,0.0001188424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004714058,0.0001933519,0.00021078957,0.000071145965,0.0001283025,0.000227554,0.0019936522,0.0000460758,0.00017663665],"category_scores_gemma":[0.0000056210706,0.00018356532,0.000056475445,0.0001777706,0.000025093092,0.0006390276,0.0005117864,0.000068842826,0.00015435598],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020855437,0.000270737,0.000086530395,0.00001547135,0.000057090467,0.0000023823645,0.00027011524,0.000019405315,0.011209384,0.00094593264,0.009211378,0.9779095],"study_design_scores_gemma":[0.0011611426,0.0001985941,0.0007217845,0.000042585376,0.000022938248,0.00001192063,0.000060400605,0.9767446,0.0006718081,0.000081789745,0.019990936,0.00029151354],"about_ca_topic_score_codex":0.00016589905,"about_ca_topic_score_gemma":0.0000053949952,"teacher_disagreement_score":0.977618,"about_ca_system_score_codex":0.000042247728,"about_ca_system_score_gemma":0.00008612774,"threshold_uncertainty_score":0.7485576},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11006037,0.0000034734019,0.8868565,0.00039560624,0.000097207674,0.00011064026,0.000006881164,0.00012700468,0.0023423017],"genre_scores_gemma":[0.5953461,3.329317e-7,0.4040786,0.00037953223,0.000017724282,0.000011382562,0.000012345178,0.000004725268,0.00014923036],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991669,0.0000109574885,0.000118716045,0.00032895542,0.00019977681,0.00017465916],"domain_scores_gemma":[0.99917275,0.00011546039,0.000043491935,0.0005577837,0.00004032033,0.000070225025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012103781,0.00008806757,0.000088960216,0.00004258212,0.000056685065,0.00020552304,0.0005200211,0.000027298483,0.00013184358],"category_scores_gemma":[0.0000052656105,0.00006370492,0.000024791007,0.00019316013,0.000033817058,0.00022944024,0.00009764401,0.00005417168,0.0002902015],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019571387,0.000042987154,0.006364161,0.0000035189382,0.0000069095604,0.000007000027,0.00007186,0.00013025131,0.000234818,0.0068973685,0.00074206915,0.9854971],"study_design_scores_gemma":[0.00120956,0.00025494548,0.0055870367,0.00008693057,0.0000074665554,0.000032205277,0.000117309864,0.98109156,0.0026780872,0.00033815554,0.008217002,0.0003797328],"about_ca_topic_score_codex":0.000042818378,"about_ca_topic_score_gemma":0.00002912397,"teacher_disagreement_score":0.9851174,"about_ca_system_score_codex":0.000012328625,"about_ca_system_score_gemma":0.000087421904,"threshold_uncertainty_score":0.373005},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0686093,0.0000059850777,0.9126219,0.0006359263,0.00012966545,0.00003732737,0.0000014736692,0.00019096171,0.01776748],"genre_scores_gemma":[0.6361201,0.000001006472,0.36279598,0.00048353532,0.0000819972,0.0000043241935,0.0000017329436,0.0000021633784,0.0005091777],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994919,0.0000075878684,0.000076900746,0.00020609968,0.00008090897,0.00013663959],"domain_scores_gemma":[0.9994375,0.00003205879,0.000021663249,0.00039989554,0.00006531391,0.000043555436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000112711175,0.000048273912,0.000052960168,0.00003007476,0.00014227114,0.00011122276,0.0004519722,0.000017826147,0.000043128468],"category_scores_gemma":[0.000012912664,0.000041245792,0.000017671646,0.00022815786,0.000059281585,0.00020716737,0.00013217164,0.000026309423,0.00030031352],"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":[0.0000010245562,0.0000539919,0.002162833,0.0000014555001,0.00001273862,0.0000036920756,0.0006072724,1.6321533e-7,0.0019696173,0.59183216,0.048415463,0.35493955],"study_design_scores_gemma":[0.0011331502,0.00043685615,0.09979591,0.000037505266,0.000021284248,0.00014136056,0.00040309533,0.5605502,0.084227964,0.02658098,0.22556226,0.0011094573],"about_ca_topic_score_codex":0.000043709577,"about_ca_topic_score_gemma":0.000039411636,"teacher_disagreement_score":0.5675108,"about_ca_system_score_codex":0.0000046077566,"about_ca_system_score_gemma":0.000017098137,"threshold_uncertainty_score":0.38600227},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9317533,0.00043213626,0.043221254,0.003025964,0.0009804774,0.0010629157,0.00017728159,0.00026773335,0.019078981],"genre_scores_gemma":[0.96115625,0.000047329995,0.038152076,0.00022480263,0.000057560334,0.0000413943,0.000014467912,0.000008224468,0.0002978861],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992383,0.0000051032057,0.00017833931,0.0001783644,0.00022066121,0.0001792019],"domain_scores_gemma":[0.99919885,0.00008066827,0.00016400042,0.0004572907,0.0000630789,0.00003613176],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021762903,0.0001016773,0.00012477707,0.00003345599,0.00013664759,0.00013606207,0.001977144,0.00002496541,0.000029411116],"category_scores_gemma":[0.000010111687,0.0000708892,0.000050430954,0.00022484463,0.00004162768,0.00041139856,0.0012999184,0.0001455137,0.00002572513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023089664,0.00061613723,0.050980475,0.00014233857,0.00027789516,5.8004144e-7,0.012137772,0.000525456,0.052680418,0.76145136,0.035212945,0.08595155],"study_design_scores_gemma":[0.0017119561,0.00018369478,0.014930639,0.0009238634,0.0000799188,0.000016129228,0.005691132,0.82039756,0.09220814,0.018329399,0.04464206,0.00088550925],"about_ca_topic_score_codex":0.0003550345,"about_ca_topic_score_gemma":0.0000038505887,"teacher_disagreement_score":0.8198721,"about_ca_system_score_codex":0.00002584581,"about_ca_system_score_gemma":0.000012884684,"threshold_uncertainty_score":0.36740583},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008887658,0.000067229324,0.9956353,0.0015160553,0.0016213958,0.00043808258,0.00007275308,0.00006576847,0.00049457076],"genre_scores_gemma":[0.0170896,0.00002932984,0.9806028,0.00064923574,0.00048346794,0.000033551252,0.00012239214,0.000037308262,0.00095231016],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975345,0.000018431829,0.00055031315,0.0010823311,0.00042869986,0.0003856928],"domain_scores_gemma":[0.9976027,0.00064075855,0.00042000404,0.0010207115,0.00022421445,0.000091620925],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00062922545,0.00031088584,0.00045322767,0.00048590318,0.0001509945,0.00018784362,0.002208463,0.00019061343,0.000019941057],"category_scores_gemma":[0.00007297076,0.00030575218,0.00013153956,0.00026743364,0.000121671495,0.00045631506,0.00082310673,0.00028930098,0.000008875398],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033502965,0.000034421937,0.000060156366,0.00005582535,0.000008806615,0.0000016597885,0.00032546342,0.00092382036,0.00012245704,0.010867324,0.0001794764,0.9874172],"study_design_scores_gemma":[0.0005896575,0.00047582336,0.0001241837,0.00051364163,0.000024664861,0.00003512249,7.088915e-7,0.921408,0.0021081737,0.018737627,0.055139773,0.00084264827],"about_ca_topic_score_codex":0.00006290915,"about_ca_topic_score_gemma":0.000033566557,"teacher_disagreement_score":0.9865746,"about_ca_system_score_codex":0.0004345153,"about_ca_system_score_gemma":0.0003819465,"threshold_uncertainty_score":0.99993944},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00583601,0.000037379155,0.96613556,0.019759765,0.0002208916,0.0008725249,0.0041233683,0.00052888773,0.0024856217],"genre_scores_gemma":[0.15745077,0.000021690199,0.71936464,0.03580346,0.00055202644,0.00023527237,0.086350925,0.0000759972,0.00014518957],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981723,0.00005105482,0.00027671232,0.001008792,0.00020755165,0.0002835836],"domain_scores_gemma":[0.996857,0.00029354685,0.00017770226,0.0023927933,0.00014723181,0.00013173252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038567776,0.00020112345,0.0001669039,0.000117091775,0.00043988964,0.00027906246,0.0016661413,0.00006762708,0.00001879809],"category_scores_gemma":[0.000013369761,0.00020213236,0.000014852555,0.0013231304,0.000015062073,0.00041659983,0.0009775017,0.0002032167,0.00022764619],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017895896,0.00064326334,0.0009896153,0.00024585793,0.000063038606,0.0000013066764,0.0006843027,0.0032741537,0.00043740665,0.0520151,0.043621097,0.898007],"study_design_scores_gemma":[0.000311041,0.000024115296,0.0010440173,0.000044504537,0.000011150842,0.0000061398987,0.00015223207,0.72751296,0.000031321168,0.00008748054,0.2705849,0.00019011188],"about_ca_topic_score_codex":0.00013714883,"about_ca_topic_score_gemma":0.000056464305,"teacher_disagreement_score":0.89781684,"about_ca_system_score_codex":0.000023095694,"about_ca_system_score_gemma":0.00006851571,"threshold_uncertainty_score":0.8242718},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8442253,0.0002037985,0.14223969,0.0041658515,0.001301415,0.002864289,0.00012969748,0.000196548,0.0046734493],"genre_scores_gemma":[0.89763343,0.000010207881,0.100622945,0.00017065865,0.000067402456,0.0002434801,0.0000027237243,0.000013924841,0.0012352272],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988986,0.0000020641403,0.00021825757,0.00035187957,0.00028725114,0.0002418988],"domain_scores_gemma":[0.9992806,0.000054706565,0.00018057783,0.00030130002,0.0001376661,0.000045186025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025585078,0.00012018037,0.00014648329,0.000057965866,0.000110698245,0.00016386058,0.0012661234,0.000028531555,0.0000024703484],"category_scores_gemma":[0.000027147285,0.000080985934,0.00012650063,0.00034598244,0.00004304125,0.00019577617,0.00043721878,0.00006559136,0.000014707158],"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":[0.00002552519,0.00078304723,0.0048751594,0.0002989809,0.00012693963,2.2793668e-7,0.0015499904,0.000533874,0.0851652,0.8348223,0.010426831,0.06139191],"study_design_scores_gemma":[0.002906623,0.00064082956,0.014247085,0.0003904539,0.000102783524,0.000044341406,0.00077524333,0.5267554,0.3926595,0.01994577,0.040547334,0.0009846651],"about_ca_topic_score_codex":0.000021657046,"about_ca_topic_score_gemma":4.30241e-7,"teacher_disagreement_score":0.81487656,"about_ca_system_score_codex":0.000036720663,"about_ca_system_score_gemma":0.000028802728,"threshold_uncertainty_score":0.33025107},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003467869,0.0001907115,0.98920447,0.0004230952,0.0016227353,0.00032500265,0.00003699413,0.00009732631,0.00775291],"genre_scores_gemma":[0.047975775,0.00010138213,0.94899285,0.001068845,0.000386968,0.000017205659,0.000035065394,0.000048432004,0.0013734576],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99678254,0.000016695783,0.0005574377,0.0013204283,0.0008522209,0.0004706485],"domain_scores_gemma":[0.99697095,0.00032329492,0.0003581845,0.001907857,0.0002899799,0.00014974886],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00059997034,0.0003951971,0.00049251615,0.00061872747,0.00013900308,0.00030910986,0.004099029,0.00021682856,0.00004340525],"category_scores_gemma":[0.00009570565,0.00036304133,0.0001082794,0.0007117238,0.00053053454,0.00063993875,0.0013513137,0.000541523,0.00017722453],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011956154,0.000033012766,0.00006846977,0.000027317345,0.000010440705,0.000014600196,0.00036077554,0.0012820732,0.00016534336,0.0891438,0.0001672439,0.90872574],"study_design_scores_gemma":[0.0009547404,0.001346019,0.0014213399,0.002107929,0.00004455656,0.00035043148,0.000002197464,0.6718776,0.01129023,0.24090202,0.0666158,0.0030871134],"about_ca_topic_score_codex":0.00017740033,"about_ca_topic_score_gemma":0.000039467624,"teacher_disagreement_score":0.90563864,"about_ca_system_score_codex":0.00018689274,"about_ca_system_score_gemma":0.00091560604,"threshold_uncertainty_score":0.99988216},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003649128,0.03379807,0.01172416,0.22903194,0.0068029286,0.00090021687,0.003458824,0.00024664,0.71367234],"genre_scores_gemma":[0.0009396734,0.061790932,0.49885988,0.00046227133,0.0053557497,0.0008623723,0.01332373,0.00010615404,0.41829923],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99750453,0.0000671264,0.00060459576,0.0008899565,0.0005644442,0.0003693583],"domain_scores_gemma":[0.9938512,0.0009522884,0.0006025821,0.004148071,0.00034196314,0.00010391995],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00055289967,0.0003162887,0.0004006363,0.00048013448,0.00021278746,0.000069751004,0.0093852095,0.00039655884,0.00030300196],"category_scores_gemma":[0.0011305881,0.0002523561,0.000057412006,0.0012742315,0.0004154954,0.00037169037,0.0026497128,0.00063036586,0.000229667],"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":[6.7277074e-7,0.00015034301,0.000087146764,0.000026430578,0.000044921275,2.6502366e-7,0.00018783635,6.2220664e-7,2.9280113e-7,0.07467041,0.6716912,0.25313985],"study_design_scores_gemma":[0.00010501534,0.000031448235,0.00042057893,0.00018377145,0.000052081636,0.000049631875,0.00015562329,0.00059767044,0.000002298408,0.12181056,0.87630343,0.00028790566],"about_ca_topic_score_codex":0.00008722661,"about_ca_topic_score_gemma":0.00003142555,"teacher_disagreement_score":0.48713574,"about_ca_system_score_codex":0.0001098118,"about_ca_system_score_gemma":0.004709517,"threshold_uncertainty_score":0.99999285},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011125156,0.000048884733,0.98752064,0.0004334134,0.00019205113,0.00024947018,0.00004443975,0.00030150442,0.000084438056],"genre_scores_gemma":[0.593746,0.000014176993,0.40562737,0.00019293606,0.000015685702,0.00012992535,0.00025162872,0.0000108421345,0.000011440624],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876314,0.0000043751675,0.00036744864,0.00020328622,0.00025591863,0.0004058204],"domain_scores_gemma":[0.9991488,0.0000224123,0.0001867398,0.0005296337,0.00006987427,0.000042544216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016753799,0.00017140004,0.00020616558,0.0006543273,0.000050892784,0.000044903845,0.00077055005,0.00015560986,0.00000931417],"category_scores_gemma":[0.000013466312,0.00018392324,0.000059434395,0.00044693754,0.000022906033,0.0007741772,0.000087711465,0.00030499307,0.00004094183],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008780261,0.00018245107,0.008555057,0.00013158929,0.00020159248,0.00000421738,0.00040075692,0.08166641,0.00061699346,0.070315726,0.005874775,0.8320416],"study_design_scores_gemma":[0.000527331,0.0002169764,0.001242865,0.000042225118,0.000005032047,0.000008196333,0.000070927774,0.9922784,0.0012881284,0.0002761895,0.0038566121,0.00018709687],"about_ca_topic_score_codex":0.000009052409,"about_ca_topic_score_gemma":6.2367866e-7,"teacher_disagreement_score":0.910612,"about_ca_system_score_codex":0.00015082609,"about_ca_system_score_gemma":0.0000806454,"threshold_uncertainty_score":0.7500172},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5998046,0.0008575354,0.005269387,0.20200242,0.00019552096,0.0032594095,0.00037079063,0.00036930662,0.18787105],"genre_scores_gemma":[0.9917306,0.0015691895,0.0024895496,0.00003562789,0.00006118614,0.000003430776,0.000041389565,0.000013230818,0.004055827],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99705267,0.00042401796,0.00012678375,0.00081987603,0.0009789261,0.0005977277],"domain_scores_gemma":[0.996971,0.000752601,0.000040862797,0.0017981342,0.0002791221,0.00015825966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004328219,0.000106559375,0.00014198864,0.0005725677,0.0005320584,0.00025071678,0.0029930098,0.00007974923,0.00002618258],"category_scores_gemma":[0.00015943601,0.00008907685,0.000018329049,0.0015785865,0.00031257668,0.0009141163,0.0032843165,0.0009812029,0.00011032771],"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":[0.00004292294,0.000557734,0.0036855242,0.00017474192,0.000049032402,0.00046522307,0.0028064875,0.000038920378,0.00007129547,0.78000975,0.024265125,0.18783325],"study_design_scores_gemma":[0.0020550576,0.0011564847,0.11180587,0.0011127474,0.000018620804,0.00003794066,0.066977374,0.27258453,0.00029732496,0.008465504,0.53429526,0.0011933056],"about_ca_topic_score_codex":0.0005366845,"about_ca_topic_score_gemma":0.00009743567,"teacher_disagreement_score":0.7715442,"about_ca_system_score_codex":0.00008500299,"about_ca_system_score_gemma":0.00039314834,"threshold_uncertainty_score":0.55618066},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032783756,0.002294985,0.96971154,0.0047218213,0.00011254916,0.0016474467,0.0053087724,0.0007439943,0.012180524],"genre_scores_gemma":[0.03305744,0.0026571488,0.95134056,0.0009855782,0.00048807304,0.0011670392,0.008753576,0.0000459347,0.001504666],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961138,0.000019172474,0.000682989,0.002214001,0.00041432123,0.0005557602],"domain_scores_gemma":[0.9955988,0.00016211982,0.00046798028,0.0031404751,0.00022484711,0.00040581173],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00051860523,0.00042969533,0.0003872874,0.00024195151,0.00091522647,0.0007888224,0.0046819593,0.00013001275,0.00002582012],"category_scores_gemma":[0.00014380996,0.0004541144,0.000029102617,0.00092677993,0.00022842914,0.0037788185,0.0022033292,0.00026103517,0.000018015344],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000803848,0.000174211,0.0002608421,0.000020889991,0.000032462285,0.0000012914602,0.00024218958,0.000015249394,0.00054217305,0.031225754,0.02274797,0.9447289],"study_design_scores_gemma":[0.0010257273,0.000100574674,0.0027319507,0.00014084818,0.00007039968,0.000106657826,0.0010106894,0.12918684,0.000060658214,0.0027246245,0.86204576,0.00079527625],"about_ca_topic_score_codex":0.000021407695,"about_ca_topic_score_gemma":0.000022902506,"teacher_disagreement_score":0.94393367,"about_ca_system_score_codex":0.000038224996,"about_ca_system_score_gemma":0.00015167057,"threshold_uncertainty_score":0.9997911},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1366506,0.0015420985,0.8601842,0.0005205725,0.0006911791,0.00015067196,0.0000060522407,0.000053605323,0.00020104738],"genre_scores_gemma":[0.9905479,0.000050281797,0.009173613,0.000023260813,0.00011298791,0.000004156272,0.000003689958,0.000006213032,0.0000779136],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993091,0.000017417775,0.0002285433,0.000116918854,0.00019805162,0.0001299383],"domain_scores_gemma":[0.99942017,0.00007823178,0.00013980045,0.00022672302,0.00008145094,0.000053605272],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047120432,0.0000732514,0.0001267492,0.00009884372,0.0000332774,0.00012607737,0.00023027351,0.000033116343,9.26857e-7],"category_scores_gemma":[0.000026560572,0.000064554515,0.000030545696,0.00017928838,0.0000036180622,0.00019872801,0.000012223378,0.00016194672,0.000005842689],"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":[0.000023706954,0.00016623289,0.0004505982,0.00023617655,0.00008831814,0.000005520591,0.00025824748,0.8259689,0.0219797,0.13107507,0.0025325143,0.017215017],"study_design_scores_gemma":[0.00021242087,0.0001802193,0.0012129666,0.000063702006,0.0000046573764,0.000052978197,0.000008242159,0.97742325,0.00046192543,0.00002407356,0.020276893,0.000078669145],"about_ca_topic_score_codex":0.0000037601374,"about_ca_topic_score_gemma":9.054039e-8,"teacher_disagreement_score":0.8538973,"about_ca_system_score_codex":0.00007231339,"about_ca_system_score_gemma":0.000106710584,"threshold_uncertainty_score":0.26324567},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59319896,0.00015986663,0.4044153,0.00033313243,0.0009870235,0.00003283124,0.0007950754,0.000028255072,0.00004953701],"genre_scores_gemma":[0.640685,0.00006748219,0.35809425,0.00015906218,0.000314157,6.8587525e-7,0.00063833536,0.000010430333,0.00003057209],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985904,0.000042382446,0.0004393947,0.00035863245,0.00041475837,0.00015442623],"domain_scores_gemma":[0.9983802,0.00033546172,0.00038898652,0.0005741559,0.00023149562,0.00008972843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003973938,0.00012994323,0.00019118663,0.00017698777,0.000071706076,0.00043191403,0.002013834,0.000031564658,0.00003598],"category_scores_gemma":[0.00016013654,0.000115138246,0.000034824392,0.00009652906,0.000028300143,0.0023140186,0.0011363858,0.00016371551,0.000009441925],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037889204,0.000120273464,0.044870757,0.000008865843,0.00031554658,0.00015514823,0.0019090573,0.00012243501,0.0041861576,0.00030685612,0.0035966395,0.9443704],"study_design_scores_gemma":[0.0032679564,0.00017795294,0.010457582,0.0016711995,0.00009626555,0.00089228025,0.0032926323,0.80135024,0.002381547,0.00014113406,0.17557424,0.0006969728],"about_ca_topic_score_codex":0.00045811734,"about_ca_topic_score_gemma":0.000042804535,"teacher_disagreement_score":0.9436734,"about_ca_system_score_codex":0.000034859582,"about_ca_system_score_gemma":0.00012187111,"threshold_uncertainty_score":0.46952015},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050279018,0.000031598312,0.94788146,0.0005769632,0.00007864257,0.00014636443,0.0000084118565,0.00028541326,0.0007121428],"genre_scores_gemma":[0.500522,0.0000022205083,0.4992654,0.00013446638,0.000052629213,0.000005973881,0.000004958867,0.000006173139,0.0000061758165],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987657,0.000031374457,0.00024455128,0.00045649786,0.00020719416,0.00029469756],"domain_scores_gemma":[0.99925673,0.00011330623,0.00009242471,0.00024908685,0.00006236525,0.00022606588],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000187561,0.00013801362,0.00015730502,0.00004537108,0.00023307126,0.00031375,0.00063275796,0.000052251693,0.000053780805],"category_scores_gemma":[0.00018727983,0.00013680426,0.00006085817,0.00036403514,0.00025468422,0.0003285641,0.00027689082,0.00021862032,0.00007981969],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014544884,0.000018944582,0.0002144245,0.0000034922568,0.00000977419,0.0000226125,0.0006515994,0.00068739196,0.001443879,0.00657087,0.00007216202,0.9903034],"study_design_scores_gemma":[0.00047185304,0.00013312203,0.0003933969,0.00006549931,0.000012435408,0.00012616486,0.00079615787,0.9814392,0.0008009139,0.00020920973,0.015229135,0.00032291657],"about_ca_topic_score_codex":0.000005151834,"about_ca_topic_score_gemma":5.431283e-7,"teacher_disagreement_score":0.98998046,"about_ca_system_score_codex":0.00002192807,"about_ca_system_score_gemma":0.00012370062,"threshold_uncertainty_score":0.5578716},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052755643,0.0000059251497,0.9888073,0.0032165283,0.0012282396,0.0002302339,0.000068471854,0.000038823364,0.0011288716],"genre_scores_gemma":[0.9517597,0.000002647658,0.046278194,0.0011363403,0.0007540544,0.000011693938,0.000039093047,0.0000049821697,0.00001330656],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997895,0.000067746034,0.0010118937,0.0001225975,0.00072556135,0.00017720423],"domain_scores_gemma":[0.9908186,0.00058301684,0.0013348634,0.00017338777,0.007046254,0.00004388267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018218552,0.00012591088,0.00014422316,0.00028824076,0.0004410291,0.0006646152,0.0013429368,0.00003788962,0.0000016472778],"category_scores_gemma":[0.0009968898,0.00009049255,0.0000794167,0.00028185186,0.00007676142,0.0011317272,0.00011982181,0.00026800827,0.000014549452],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011104866,0.00015574667,0.00024194867,0.000005065461,0.0004716586,0.0000025647398,0.004590953,0.3869512,0.00009786908,0.10840504,0.0048835203,0.49308392],"study_design_scores_gemma":[0.0026145608,0.00057107117,0.0006797108,0.00007538445,0.0000051350635,0.000009487846,0.00020895337,0.97701174,0.0001461797,0.00062195974,0.017967952,0.000087842556],"about_ca_topic_score_codex":0.0000044141684,"about_ca_topic_score_gemma":6.164025e-7,"teacher_disagreement_score":0.94648415,"about_ca_system_score_codex":0.00014511279,"about_ca_system_score_gemma":0.00022416632,"threshold_uncertainty_score":0.64088994},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45636433,0.000005782751,0.5428472,0.00019017978,0.00003015592,0.00021041415,0.000033972865,0.000055923498,0.00026199405],"genre_scores_gemma":[0.5378581,0.0000025750383,0.46194884,0.000015835169,0.000008741565,0.0000014476518,0.00006224941,0.0000071976838,0.00009494677],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990608,0.000022964656,0.00006310004,0.00043750278,0.00020181444,0.00021382602],"domain_scores_gemma":[0.99900913,0.00003499151,0.000113176684,0.00067022967,0.00008719885,0.00008529784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012328192,0.000114655064,0.00015969368,0.000112066205,0.00017639365,0.0000500763,0.0009339543,0.00004669831,0.000002700096],"category_scores_gemma":[9.873971e-7,0.000116632364,0.000048592305,0.00022621431,0.000045473575,0.00029390186,0.00013644522,0.00006504387,0.000014321342],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00052011845,0.008203853,0.39609742,0.0017001124,0.0011827855,0.0001221712,0.025233787,0.035326913,0.009798303,0.2527233,0.0048386976,0.2642525],"study_design_scores_gemma":[0.00061846734,0.00025101035,0.04032801,0.000028535873,0.000020415273,0.000005583639,0.005045687,0.95240784,0.00008527894,0.00003318229,0.0009880192,0.00018796632],"about_ca_topic_score_codex":0.00028491626,"about_ca_topic_score_gemma":0.0022654086,"teacher_disagreement_score":0.91708094,"about_ca_system_score_codex":0.000058496327,"about_ca_system_score_gemma":0.000040827188,"threshold_uncertainty_score":0.475613},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000027438404,0.00013436652,0.9914684,0.005343865,0.001056305,0.00028232593,0.000043828237,0.00028918678,0.001354269],"genre_scores_gemma":[0.11210496,0.000010350143,0.8838986,0.0034170034,0.000393752,0.000018821169,0.00002819584,0.000024617919,0.000103669074],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99620956,0.000031560012,0.0005198909,0.0018984522,0.000844374,0.00049617596],"domain_scores_gemma":[0.9971694,0.00038943996,0.00026888057,0.0017467875,0.00018243537,0.00024306269],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006556557,0.0004714924,0.00051308144,0.00036525872,0.00026045513,0.0007271526,0.005240754,0.00021612355,0.000040357023],"category_scores_gemma":[0.000100059624,0.00042391717,0.00013179131,0.00074102054,0.0008358332,0.0005550841,0.0014455366,0.00076615444,0.00013482422],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025389893,0.00002761566,0.000020537942,0.00003258213,0.0000070715328,0.000055233755,0.00018825759,0.0037556288,0.00006334602,0.04613771,0.00013004815,0.9495794],"study_design_scores_gemma":[0.00015957044,0.00013803638,0.00009462822,0.00022256112,0.000006945219,0.000014919505,9.536024e-8,0.848032,0.0015237662,0.14379321,0.005471978,0.0005422811],"about_ca_topic_score_codex":0.00006964479,"about_ca_topic_score_gemma":0.000048587757,"teacher_disagreement_score":0.94903713,"about_ca_system_score_codex":0.00016948,"about_ca_system_score_gemma":0.0007716557,"threshold_uncertainty_score":0.99982125},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000027706132,0.002237339,0.9656644,0.0006583775,0.0008224537,0.00034988366,0.00030706142,0.00009701108,0.029835781],"genre_scores_gemma":[0.7068199,0.0075747427,0.13917974,0.007762468,0.03995417,0.0002179067,0.028615905,0.0014133847,0.06846177],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975253,0.00004295942,0.0005419935,0.0010995006,0.0002472642,0.0005430292],"domain_scores_gemma":[0.997392,0.00060659,0.00027467238,0.0016162955,0.000036879323,0.00007356331],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036305786,0.0004534984,0.0006292858,0.00016670799,0.00017653468,0.00031129585,0.0029777116,0.0007247656,0.000010746129],"category_scores_gemma":[0.000042567823,0.00047427538,0.000098880344,0.00038850104,0.000101594655,0.00027819176,0.0021549503,0.0014344933,0.00003403938],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031243565,0.000041535637,0.00018340502,0.000027430555,0.000039573173,0.000008176882,0.00054572173,0.001570555,0.0000023167029,0.010378717,0.006775552,0.98042387],"study_design_scores_gemma":[0.00059937965,0.000038871163,0.00026624108,0.00053305144,0.000059258455,0.000005481187,0.000016376849,0.69839793,0.0000038132162,0.0159005,0.28288883,0.0012902702],"about_ca_topic_score_codex":0.00018018561,"about_ca_topic_score_gemma":0.001285733,"teacher_disagreement_score":0.9791336,"about_ca_system_score_codex":0.00020898011,"about_ca_system_score_gemma":0.00016744004,"threshold_uncertainty_score":0.9997709},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75939155,0.000025190104,0.23599325,0.00302827,0.00013899975,0.00018473966,0.00016945273,0.00016919874,0.0008993584],"genre_scores_gemma":[0.7945042,0.00001021865,0.20380136,0.0001763602,0.000043650325,4.2784498e-7,0.0002784307,0.000018355988,0.0011669935],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990083,0.000036119196,0.00007025811,0.00044990663,0.00023610427,0.00019930625],"domain_scores_gemma":[0.99841636,0.000060072958,0.00011814379,0.0012909864,0.000046622594,0.00006779361],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017559166,0.00011211148,0.00017183882,0.00010741487,0.00021206758,0.00009344869,0.0018664735,0.000050848757,0.000053576252],"category_scores_gemma":[0.0000060351654,0.0001390409,0.000039242335,0.00030173615,0.000050000413,0.0012942479,0.0010033617,0.000086991946,0.00033368464],"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":[0.00008259409,0.0006617392,0.71109444,0.00036211556,0.00037327028,0.00039660104,0.0035805432,0.00027945297,0.01684784,0.0057226024,0.083274364,0.17732443],"study_design_scores_gemma":[0.0008373808,0.00011997627,0.27100903,0.000105802224,0.0000323819,0.000015044953,0.0019209784,0.6931868,0.0002508205,0.00002568526,0.03213319,0.00036288446],"about_ca_topic_score_codex":0.00041197534,"about_ca_topic_score_gemma":0.002175512,"teacher_disagreement_score":0.6929074,"about_ca_system_score_codex":0.000033926353,"about_ca_system_score_gemma":0.000067832225,"threshold_uncertainty_score":0.56699234},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9226967,0.00005978581,0.073350646,0.0010828233,0.00011197475,0.0001564938,0.000024399505,0.00008652982,0.0024306304],"genre_scores_gemma":[0.89824885,0.000029590627,0.101360776,0.00006209259,0.000014809337,5.9366994e-7,0.0000188996,0.000008025848,0.00025636013],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99909246,0.00003648301,0.000082949904,0.00033947243,0.00019621864,0.0002524383],"domain_scores_gemma":[0.99919176,0.000050754687,0.000097854434,0.0005450684,0.000050278475,0.00006431214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017868892,0.000098049764,0.00016409594,0.0002809095,0.00010220337,0.000034587956,0.0008804677,0.000057459667,0.000009880997],"category_scores_gemma":[0.0000048492884,0.00012375633,0.00006562829,0.0007725007,0.000044679084,0.00048891205,0.00031300748,0.00009891564,0.000089745474],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005188865,0.0022136765,0.7973374,0.00019286008,0.00017352197,0.00023191342,0.009731495,0.00013858848,0.013225648,0.11998084,0.019571476,0.037150703],"study_design_scores_gemma":[0.0045636157,0.0005672256,0.75778264,0.000396749,0.000044855125,0.000022042128,0.036786042,0.10478543,0.0015432062,0.003526176,0.088849746,0.0011323],"about_ca_topic_score_codex":0.0009963738,"about_ca_topic_score_gemma":0.040124048,"teacher_disagreement_score":0.11645467,"about_ca_system_score_codex":0.000047759262,"about_ca_system_score_gemma":0.00003143917,"threshold_uncertainty_score":0.9773912},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044874344,0.0000017675783,0.95008713,0.0040190243,0.000073398434,0.00024185076,0.00028855953,0.0001297389,0.00028417114],"genre_scores_gemma":[0.9232316,0.0000018841171,0.075063944,0.00093422417,0.00006071419,0.000049720722,0.0006463121,0.0000036343947,0.000007959861],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991473,0.000018056347,0.00029441385,0.00014603834,0.0001940217,0.00020014451],"domain_scores_gemma":[0.99941653,0.00005084008,0.00008347749,0.00024406509,0.00009557369,0.00010948785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002857733,0.00007699344,0.00008730153,0.00003096785,0.0001646318,0.00043276526,0.00044356947,0.000037086094,0.000017340952],"category_scores_gemma":[0.000054474636,0.00007646688,0.00002553454,0.00016469375,0.000016968397,0.0017798184,0.0001603278,0.00009184938,0.00005768347],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002379822,0.00004069148,0.0003174527,0.00021424382,0.000030665142,0.0000010308306,0.015225409,0.00045766452,0.0011340765,0.076500095,0.02074151,0.8853134],"study_design_scores_gemma":[0.00032488146,0.00006628091,0.00057786924,0.000019811923,0.0000046535024,0.000002538884,0.0001755354,0.9828014,0.0059110248,0.00031435757,0.009666871,0.000134803],"about_ca_topic_score_codex":0.00019757173,"about_ca_topic_score_gemma":0.0000015995665,"teacher_disagreement_score":0.98234373,"about_ca_system_score_codex":0.00003262526,"about_ca_system_score_gemma":0.00006754802,"threshold_uncertainty_score":0.41731653},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39357862,0.000017138815,0.6033906,0.0017406966,0.000038880473,0.00011538842,0.000032344742,0.00013582905,0.0009505629],"genre_scores_gemma":[0.84377444,0.000025421068,0.15550677,0.000038324248,0.000027473532,3.849657e-12,0.000054444794,0.0000041041517,0.0005689873],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99878407,0.000080280995,0.00012666911,0.00052179093,0.00019972905,0.0002874657],"domain_scores_gemma":[0.99861825,0.00009765046,0.00017070399,0.00092230586,0.00007954501,0.00011152759],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034751094,0.00011419579,0.00015792095,0.00021963699,0.00023989128,0.00003549488,0.0025176553,0.000076427285,0.000021817861],"category_scores_gemma":[0.000017123592,0.00016319308,0.000042150576,0.0005547562,0.00007316657,0.0007655557,0.0017556637,0.00018821674,0.000043015378],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048818358,0.0008888743,0.0047873803,0.00005499839,0.0001031966,0.00017709816,0.19321549,0.014061211,0.00071422843,0.062217895,0.008172465,0.71555835],"study_design_scores_gemma":[0.0008385045,0.000015129053,0.013381561,0.00006636029,0.000020605981,0.000011470825,0.03956123,0.93224365,0.00007365588,0.00004548639,0.013503434,0.00023889581],"about_ca_topic_score_codex":0.00074179313,"about_ca_topic_score_gemma":0.00058333686,"teacher_disagreement_score":0.91818243,"about_ca_system_score_codex":0.0002674304,"about_ca_system_score_gemma":0.00012911047,"threshold_uncertainty_score":0.66548204},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005484165,0.0010996824,0.9899189,0.0011496444,0.0015197726,0.0004115593,0.00009086349,0.0000687491,0.0002566764],"genre_scores_gemma":[0.32951695,0.00009622749,0.66645634,0.00075592514,0.0029141002,0.00007951086,0.00003484409,0.000052934585,0.00009314347],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974347,0.000097401564,0.0011175289,0.00039581308,0.000591847,0.0003627635],"domain_scores_gemma":[0.99744415,0.0001911338,0.0007935847,0.0005036084,0.0005591837,0.0005083548],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010476705,0.00022378168,0.00045134587,0.00016654146,0.00016997724,0.0005317805,0.0016747344,0.0000816183,0.0000037875054],"category_scores_gemma":[0.00008850108,0.00018427942,0.00021915403,0.00044614813,0.00003482219,0.00041616216,0.00011335442,0.00021306022,0.000037207003],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004452915,0.00096258934,0.00020759003,0.00025363578,0.0004052984,0.00014193292,0.011423895,0.04503615,0.0033711875,0.030418618,0.044091698,0.8636429],"study_design_scores_gemma":[0.00034550062,0.0009972574,0.00003374196,0.0001646678,0.000033510838,0.00020773412,0.0016464494,0.93905073,0.0013745312,0.0001450862,0.055731226,0.00026956786],"about_ca_topic_score_codex":0.00002611987,"about_ca_topic_score_gemma":7.361987e-7,"teacher_disagreement_score":0.8940146,"about_ca_system_score_codex":0.00010640148,"about_ca_system_score_gemma":0.000164803,"threshold_uncertainty_score":0.7514697},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2987113,0.039037157,0.004405153,0.61178094,0.0012344655,0.018438572,0.0018945481,0.00014278262,0.024355063],"genre_scores_gemma":[0.9874091,0.0066528427,0.0044468935,0.000044082848,0.000041177926,0.00020619984,0.0000069953153,0.00001305917,0.00117964],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9974155,0.00051250675,0.00022799801,0.0006767745,0.0007308511,0.00043641136],"domain_scores_gemma":[0.9920398,0.0036116543,0.000105102794,0.001657761,0.0025382447,0.000047429974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038803585,0.00012310459,0.00024055081,0.00016965588,0.0005352208,0.00015289093,0.0024375003,0.000038184993,0.0000017198364],"category_scores_gemma":[0.0025351862,0.00006941689,0.000016353755,0.0017148694,0.00059295504,0.00031980863,0.0019937311,0.00047393833,0.000007956745],"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":[0.00013207115,0.00030239223,0.00018273646,0.00030069027,0.000081213184,0.0000014558312,0.014112755,0.00028109152,0.0006983804,0.68037695,0.005500242,0.29803002],"study_design_scores_gemma":[0.0028289198,0.002027072,0.0032862287,0.005018038,0.000017001732,0.000001528226,0.42458627,0.32230982,0.018301545,0.10008697,0.12077806,0.0007585456],"about_ca_topic_score_codex":0.0000038575295,"about_ca_topic_score_gemma":0.0002104638,"teacher_disagreement_score":0.6886978,"about_ca_system_score_codex":0.00009970797,"about_ca_system_score_gemma":0.00046333307,"threshold_uncertainty_score":0.45295224},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009333667,0.000032406584,0.98607147,0.000050495717,0.0001723738,0.00036289124,0.00019230349,0.00045953732,0.0033248398],"genre_scores_gemma":[0.5651242,0.0000210911,0.43434194,0.000030362204,0.00008494202,0.0000052650885,0.00013436117,0.00002392247,0.0002339317],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973418,0.00020556417,0.00037598057,0.0015505466,0.00016518813,0.00036090592],"domain_scores_gemma":[0.99714303,0.000086892695,0.00046858305,0.0017878072,0.00021833123,0.00029535996],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004298978,0.00035635175,0.0005558771,0.00020564509,0.00017643682,0.00018088766,0.0031454829,0.00027912596,0.00000642046],"category_scores_gemma":[0.000018424853,0.00041944848,0.000170642,0.000837289,0.00013442656,0.00058773084,0.0018602934,0.00044087993,0.000032524207],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004494172,0.0018132805,0.0010091123,0.0013994146,0.0005182211,0.00042749077,0.0043310975,0.069120675,0.00026865318,0.83402216,0.002733544,0.084311426],"study_design_scores_gemma":[0.00028500168,0.00014222944,0.00015966524,0.00010883088,0.00006310725,0.000009074137,0.000776384,0.99540025,0.00016259374,0.0022156262,0.00026461936,0.00041261746],"about_ca_topic_score_codex":0.00030280516,"about_ca_topic_score_gemma":0.0000036114386,"teacher_disagreement_score":0.9262796,"about_ca_system_score_codex":0.00014937438,"about_ca_system_score_gemma":0.00032307208,"threshold_uncertainty_score":0.9998257},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39967722,0.008906727,0.55614567,0.017383255,0.0005275682,0.013985541,0.0013323228,0.00012100429,0.0019207068],"genre_scores_gemma":[0.9572789,0.0016673524,0.039700475,0.000026394942,0.000013143055,0.0005637818,0.000011550633,0.000009811081,0.00072858785],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988619,0.00020279075,0.0002054725,0.00031751016,0.00024373236,0.00016859616],"domain_scores_gemma":[0.99600846,0.0014632854,0.00015927944,0.00043254893,0.0019004645,0.000035960486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009898971,0.000090677844,0.00021433237,0.000092392555,0.00024396217,0.000040889845,0.00041070016,0.00002641764,9.946015e-7],"category_scores_gemma":[0.00058193196,0.00006389307,0.000019915447,0.0008965334,0.0003904448,0.00034051354,0.00036645407,0.00007469145,8.482435e-7],"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":[0.00006289943,0.00005527221,0.0002123135,0.00010976531,0.000061002218,4.395043e-8,0.004043091,0.000045336245,0.0043511395,0.89694494,0.00027937596,0.09383482],"study_design_scores_gemma":[0.0042574513,0.0017851196,0.0020179008,0.0013286567,0.000052154766,0.0000013800923,0.15457357,0.019457342,0.2130948,0.56260604,0.040145,0.0006805851],"about_ca_topic_score_codex":8.4845647e-7,"about_ca_topic_score_gemma":0.000011531533,"teacher_disagreement_score":0.5576017,"about_ca_system_score_codex":0.00002220171,"about_ca_system_score_gemma":0.00010204401,"threshold_uncertainty_score":0.26054838},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008603337,0.000052690117,0.97511995,0.021423578,0.0002778571,0.00061787735,0.0005388028,0.00019651015,0.00091242464],"genre_scores_gemma":[0.004305086,0.000030989453,0.9899781,0.0014599996,0.00014622179,0.00024416787,0.0037090261,0.000012781992,0.000113674636],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998394,0.00001745088,0.0002911144,0.0009771917,0.00015671737,0.00016350277],"domain_scores_gemma":[0.9972995,0.00006802469,0.00014093694,0.0023606895,0.000061362145,0.0000695181],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003837054,0.0001449817,0.00018330004,0.00007210605,0.000045217355,0.00026322,0.0034208077,0.000109192835,0.00000868438],"category_scores_gemma":[0.00003201859,0.0001448229,0.000025580644,0.00034700445,0.000008690745,0.0003447671,0.004696632,0.00021117176,0.00003775891],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007539421,0.00019318314,0.0002187095,0.00040483515,0.000040906143,0.000017627246,0.001211842,0.00027165512,0.00014628284,0.15083773,0.09147979,0.75516987],"study_design_scores_gemma":[0.00016205879,0.0000065490185,0.00024297957,0.00005498951,0.000004330018,0.0000017306178,0.000020100364,0.8494433,0.000032431115,0.031964004,0.11789547,0.000172041],"about_ca_topic_score_codex":0.00031114806,"about_ca_topic_score_gemma":0.0005061604,"teacher_disagreement_score":0.84917164,"about_ca_system_score_codex":0.000029052744,"about_ca_system_score_gemma":0.00028741735,"threshold_uncertainty_score":0.63567686},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047484998,0.00020582095,0.9480138,0.003375185,0.000746034,0.000064519336,0.000008900515,0.000033383723,0.00006736842],"genre_scores_gemma":[0.21598051,0.000017075607,0.7827387,0.0007001276,0.0005522674,4.6050954e-7,8.8936787e-7,0.000005782704,0.000004171397],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99776584,0.00003602082,0.00070376595,0.00039764092,0.000811817,0.0002849439],"domain_scores_gemma":[0.9978356,0.00010707796,0.00068344735,0.00045693122,0.00043656444,0.0004804107],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006670695,0.0001465581,0.0003050944,0.00017125373,0.0002151101,0.00048938394,0.0035513479,0.00003366238,0.000015325499],"category_scores_gemma":[0.00012558092,0.00012434548,0.00009961585,0.0015202059,0.00018879506,0.0016303858,0.00065428356,0.00023372081,0.000018623141],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036769384,0.00006042763,0.0012988056,0.000008367398,0.000023552939,0.000023760875,0.0030014648,0.00062688225,0.012543199,0.003189789,0.0110646775,0.9681554],"study_design_scores_gemma":[0.0014792146,0.0015520724,0.018968882,0.0005448011,0.000044106793,0.0002837917,0.00030796713,0.9077085,0.03460632,0.0032899731,0.030409439,0.00080492074],"about_ca_topic_score_codex":0.000055012948,"about_ca_topic_score_gemma":0.000001206058,"teacher_disagreement_score":0.9673505,"about_ca_system_score_codex":0.000045288598,"about_ca_system_score_gemma":0.00078599405,"threshold_uncertainty_score":0.6599347},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012708273,0.000093446055,0.98853755,0.0077723055,0.0014747905,0.00039344965,0.000045902947,0.0002866695,0.00012504078],"genre_scores_gemma":[0.31308252,0.000008399307,0.6850271,0.0014867953,0.00032688308,0.00004664645,0.0000089812065,0.000012007288,6.784098e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99583554,0.00011506617,0.00044525557,0.0020774866,0.0008488952,0.0006777542],"domain_scores_gemma":[0.9972184,0.0006136917,0.00034380826,0.0013267824,0.00026818505,0.0002291555],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0008270574,0.00041641956,0.00050855445,0.00037380855,0.0003133141,0.0013381591,0.005508583,0.00023250007,0.0000041665526],"category_scores_gemma":[0.00034989705,0.0004029049,0.00012196908,0.0023263895,0.0004496289,0.00054626924,0.0077626295,0.0014186027,0.000034503464],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001997531,0.00009611292,0.00030732824,0.00003659887,0.000024492305,0.00004928119,0.0035475171,0.015948605,0.0008195106,0.040057167,0.000075955526,0.9390354],"study_design_scores_gemma":[0.00014322474,0.000048108006,0.0021794392,0.0001831209,0.000005309321,0.000007813125,0.0000012428923,0.87936366,0.0023770414,0.114920326,0.00033898995,0.00043171408],"about_ca_topic_score_codex":0.00008362248,"about_ca_topic_score_gemma":0.000029750556,"teacher_disagreement_score":0.9386037,"about_ca_system_score_codex":0.00042830448,"about_ca_system_score_gemma":0.0008754575,"threshold_uncertainty_score":0.9998721},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010754118,0.000029230914,0.9787271,0.008578913,0.00004306902,0.00023794235,0.00008338635,0.00013001087,0.0014162484],"genre_scores_gemma":[0.2780205,0.0000049721234,0.7173087,0.0031062928,0.00018686705,0.00013153537,0.00006113352,0.000013340905,0.0011666748],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999327,0.0000062682284,0.00011187876,0.00032112704,0.00009340518,0.00014033023],"domain_scores_gemma":[0.99950117,0.000057985064,0.000029327904,0.000254925,0.00003290351,0.00012366907],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006914497,0.00007510759,0.00008577387,0.000018970251,0.00007876906,0.00013375594,0.00033554813,0.000021440996,0.000011039031],"category_scores_gemma":[0.000022196245,0.000060657007,0.000024185414,0.00017504646,0.000022609685,0.000087426815,0.00016027896,0.00003462675,0.00002395337],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037899251,0.000085350744,0.00002493197,0.00002069572,0.000014127123,0.0000019024976,0.0012995609,0.00017297661,0.0020226669,0.03341452,0.05305157,0.9098879],"study_design_scores_gemma":[0.0003234052,0.00007185392,0.00013345621,0.0000031293457,0.0000041962535,0.000002718881,0.00013352919,0.9480726,0.0012423373,0.000109219436,0.049797412,0.00010615341],"about_ca_topic_score_codex":0.000019342831,"about_ca_topic_score_gemma":0.0000026007838,"teacher_disagreement_score":0.94789964,"about_ca_system_score_codex":0.000004717222,"about_ca_system_score_gemma":0.000019252617,"threshold_uncertainty_score":0.2473521},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034679559,0.0002433996,0.990116,0.0023937186,0.000023468083,0.0030203531,0.00005313741,0.00036473482,0.0003172209],"genre_scores_gemma":[0.9229126,0.000013536888,0.06847344,0.0007101557,0.00025570535,0.0074306475,0.00015370923,0.00003895945,0.000011223296],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997144,0.00016716949,0.0007544003,0.0011717344,0.0003804767,0.00038221249],"domain_scores_gemma":[0.99760455,0.00022988059,0.00038622695,0.0010402168,0.00032434738,0.0004147503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050836813,0.0002943338,0.00048282786,0.00008727069,0.00028575267,0.0002804285,0.0011090797,0.000119590724,0.0000015153764],"category_scores_gemma":[0.000018730914,0.0002333196,0.00004094361,0.0010908348,0.00011430232,0.0007234594,0.000059504637,0.00027704673,0.000055940494],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015395926,0.006553235,0.031128626,0.00044867187,0.0007689713,0.00012872045,0.029159913,0.020351797,0.009302805,0.3096854,0.0023298906,0.58860236],"study_design_scores_gemma":[0.0024981939,0.0006841796,0.0031712614,0.000113206406,0.000026098274,0.00008515655,0.0011004289,0.984932,0.00039393237,0.00027894668,0.006030367,0.00068622496],"about_ca_topic_score_codex":0.00036360644,"about_ca_topic_score_gemma":0.0000838084,"teacher_disagreement_score":0.9645802,"about_ca_system_score_codex":0.000060405528,"about_ca_system_score_gemma":0.00019581898,"threshold_uncertainty_score":0.9514497},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058273003,0.000017857279,0.939817,0.0007016732,0.000038601742,0.000105307976,0.0000018861091,0.00033239982,0.00071224937],"genre_scores_gemma":[0.4075222,0.0000019082977,0.59229076,0.00011227721,0.000041812807,0.000004710632,0.0000036521226,0.000004901232,0.000017774973],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989652,0.000011089338,0.00021244021,0.0003867373,0.00019777192,0.00022676894],"domain_scores_gemma":[0.9994102,0.0000880689,0.00007152413,0.00022128131,0.000047249065,0.00016168872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015321668,0.000106284446,0.00011466869,0.000034425902,0.00020151056,0.00037311518,0.0005350188,0.00003688342,0.000044091103],"category_scores_gemma":[0.00008005682,0.000094329465,0.000046985428,0.00031062117,0.000045487952,0.00041833712,0.00025274354,0.00016981129,0.00006301629],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015936004,0.000027477216,0.000048770584,0.000002515755,0.0000062629947,0.000010016,0.0005442383,0.0022521971,0.0016515338,0.004908984,0.000101614976,0.9904448],"study_design_scores_gemma":[0.00018519824,0.00008548796,0.0007759872,0.000016730131,0.0000046498444,0.000022651968,0.00033863084,0.98007536,0.0008502729,0.000102715414,0.017377727,0.00016459265],"about_ca_topic_score_codex":0.00002586907,"about_ca_topic_score_gemma":0.0000018233428,"teacher_disagreement_score":0.9902802,"about_ca_system_score_codex":0.000015856484,"about_ca_system_score_gemma":0.000059250906,"threshold_uncertainty_score":0.3846644},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040553813,0.00003986745,0.9940338,0.0003669524,0.0002290378,0.00033195817,0.0008483168,0.00005698616,0.000037679896],"genre_scores_gemma":[0.9859339,0.00015010625,0.013527724,0.00010799869,0.000018870373,0.000050460614,0.00015371623,0.000012788009,0.000044450477],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99813527,0.000048336427,0.0006818703,0.0005568099,0.00039890988,0.00017883383],"domain_scores_gemma":[0.9986979,0.00008488938,0.00016752796,0.0008597089,0.00003551313,0.00015449831],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016663254,0.00015762239,0.00024127928,0.00013457164,0.000059845424,0.00004746541,0.0011867506,0.000067030756,0.00002658801],"category_scores_gemma":[0.000004309068,0.00016308344,0.00005584529,0.00070292706,0.000052969965,0.00045770878,0.0000019561203,0.00017654088,0.000044437547],"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":[0.00002967057,0.00050272245,0.0006938366,0.00018177283,0.00012780509,0.000028769402,0.005215836,0.9452612,0.006571798,0.0034478344,0.00017211032,0.037766684],"study_design_scores_gemma":[0.00024833358,0.000108930544,0.0003053431,0.000093454386,0.000031114258,0.0000022072152,0.00042689044,0.982118,0.012597465,0.000012842393,0.0038384004,0.00021699064],"about_ca_topic_score_codex":0.0002457268,"about_ca_topic_score_gemma":0.000050615035,"teacher_disagreement_score":0.9818785,"about_ca_system_score_codex":0.000050219824,"about_ca_system_score_gemma":0.00007726134,"threshold_uncertainty_score":0.66503495},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000025024778,0.0007122397,0.6850066,0.00016966372,0.00014061177,0.00016032624,0.000043270382,0.00030963056,0.31343263],"genre_scores_gemma":[0.0001915883,0.0009408397,0.4710681,0.00034268017,0.00029502538,0.000014330908,0.00020624704,0.00007036687,0.5268708],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981022,0.00001045764,0.00037934977,0.000879695,0.00030914648,0.00031918465],"domain_scores_gemma":[0.9982973,0.00028802358,0.00012431688,0.000959718,0.00010879449,0.00022187976],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040636153,0.000401983,0.00037254847,0.00023640062,0.0002556135,0.00033509295,0.0010342551,0.00024037708,0.00017744796],"category_scores_gemma":[0.000020042213,0.0003183789,0.00010866909,0.000084149004,0.000099171935,0.00028038028,0.00072923565,0.00048105238,0.00025073715],"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":[0.0000013809519,0.000012970258,0.000003614901,0.000003648301,0.000018573895,0.000010232531,0.00006918156,0.00000179946,0.000008461406,0.105623215,0.0037867143,0.8904602],"study_design_scores_gemma":[0.00027712793,0.0000934842,0.00010807855,0.00007875584,0.000011643186,0.00007268666,0.000018371224,0.07752824,0.00007207209,0.024047194,0.89718217,0.0005101925],"about_ca_topic_score_codex":0.00004019984,"about_ca_topic_score_gemma":0.00001710451,"teacher_disagreement_score":0.8933954,"about_ca_system_score_codex":0.00003781998,"about_ca_system_score_gemma":0.00007047038,"threshold_uncertainty_score":0.9999268},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015214143,0.0001039892,0.9779349,0.0058931294,0.0001777752,0.00035302778,0.000016814865,0.000072430674,0.00023377307],"genre_scores_gemma":[0.03759742,0.0000813423,0.9614515,0.00019412425,0.00033140526,0.00017656136,0.000021042668,0.000010756309,0.00013586518],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99829847,0.00035113457,0.0002537502,0.0003465024,0.00036286627,0.00038725615],"domain_scores_gemma":[0.99736196,0.0010310945,0.00006709563,0.00097396725,0.00045250254,0.000113393384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00409495,0.00008856054,0.00017735192,0.000037232345,0.0006297173,0.00017278818,0.0014691214,0.00007493583,0.000012103089],"category_scores_gemma":[0.00013224936,0.000063499574,0.00012840031,0.0009497704,0.00042751196,0.00036742393,0.00028193768,0.00038876387,0.000009171725],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018414508,0.00023466304,0.0017157987,0.00002671301,0.0000611709,1.9066084e-7,0.006127152,0.000120164084,0.0051760045,0.04536317,0.083880834,0.8572757],"study_design_scores_gemma":[0.00024500824,0.00019483035,0.0011166789,0.000007879945,0.000007202,0.000008316459,0.0014288009,0.8550341,0.004679134,0.010478988,0.12670106,0.00009800707],"about_ca_topic_score_codex":0.00007865617,"about_ca_topic_score_gemma":0.000003939551,"teacher_disagreement_score":0.85717773,"about_ca_system_score_codex":0.000053619686,"about_ca_system_score_gemma":0.00015356613,"threshold_uncertainty_score":0.48433402},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010702247,0.000042873435,0.991749,0.0062154247,0.00023297593,0.0002562695,0.0003289511,0.00007458805,0.000029710714],"genre_scores_gemma":[0.015910357,0.000022949338,0.98239875,0.0012896652,0.00013889658,0.00010978834,0.00010423459,0.000015522171,0.000009842937],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986216,0.000013194981,0.0002511461,0.0006949077,0.000145952,0.00027320464],"domain_scores_gemma":[0.99856806,0.00025821835,0.00010278834,0.00095889036,0.000009116586,0.00010293644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002412788,0.00012549691,0.00015772431,0.00005619383,0.00010713825,0.00033442397,0.0035509525,0.000058230853,0.0000092092405],"category_scores_gemma":[0.00006387784,0.00013207826,0.000024225446,0.0003503874,0.00002010352,0.00069891126,0.0011038351,0.0001524446,0.000016945985],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021794813,0.00009101297,0.00010047808,0.000015508554,0.000013548664,0.0000035170126,0.000516221,0.00028358426,0.0003282149,0.0010749339,0.0020056753,0.9955651],"study_design_scores_gemma":[0.00026251262,0.000026874146,0.00035852252,0.00003664707,0.0000052978185,0.0000028344782,0.000046643498,0.9842289,0.0001876335,0.0009707304,0.0136970505,0.00017632052],"about_ca_topic_score_codex":0.0000327442,"about_ca_topic_score_gemma":0.0000058765113,"teacher_disagreement_score":0.9953888,"about_ca_system_score_codex":0.00004394528,"about_ca_system_score_gemma":0.00003001397,"threshold_uncertainty_score":0.65986127},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016642764,0.00014566771,0.99552435,0.00063266617,0.00077845954,0.00032183397,0.00007898855,0.00016161238,0.0006921416],"genre_scores_gemma":[0.5181662,0.000007713269,0.48118308,0.00035257984,0.00019504358,0.000013677284,0.000023177112,0.000021383843,0.000037198213],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961379,0.00003094182,0.0006792937,0.0016916867,0.0009662711,0.0004939161],"domain_scores_gemma":[0.9969932,0.00035423887,0.00041866966,0.0017832514,0.00023813732,0.00021250884],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00047156907,0.00044865833,0.00060952734,0.0003682131,0.00018325867,0.00025605815,0.003737066,0.00020027951,0.000033482796],"category_scores_gemma":[0.00009371016,0.00041831643,0.00012439679,0.00052607607,0.00047800664,0.00016142787,0.0019118555,0.0005037247,0.000025774834],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000053751596,0.0000901437,0.00028251857,0.000082455634,0.00002207432,0.000056226192,0.0027428607,0.013933898,0.00013429171,0.011609548,0.00006742457,0.9709732],"study_design_scores_gemma":[0.0002068967,0.0001362427,0.0014350116,0.00034324545,0.00001059397,0.00001649017,0.0000012991169,0.98777866,0.0011934962,0.007925538,0.00044205133,0.00051046914],"about_ca_topic_score_codex":0.000090178706,"about_ca_topic_score_gemma":0.00004728687,"teacher_disagreement_score":0.97384477,"about_ca_system_score_codex":0.0001475386,"about_ca_system_score_gemma":0.00044252945,"threshold_uncertainty_score":0.99982685},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002561655,0.015784541,0.97761184,0.00097306154,0.00035858338,0.0005568521,0.002577054,0.000096642085,0.002015815],"genre_scores_gemma":[0.112665616,0.011390194,0.7914592,0.004109799,0.0045736236,0.00011093176,0.07214643,0.00025340775,0.0032907976],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99637055,0.000038804374,0.0007550853,0.0022311285,0.0003784011,0.00022599954],"domain_scores_gemma":[0.9951353,0.000853666,0.00023440567,0.0034047584,0.000046796,0.00032506205],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0007061666,0.00029535888,0.00042314274,0.00010783747,0.00021809104,0.0002838432,0.0044354373,0.00013361812,0.0000040438404],"category_scores_gemma":[0.0003242328,0.00030549194,0.000011563506,0.00013233774,0.000055076252,0.001097502,0.011136928,0.00030588673,0.000042982276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010356236,0.000030081223,0.00030328234,0.00020872084,0.0000704637,0.00002323329,0.0006437337,0.0014418791,0.000007810268,0.439889,0.0031925251,0.5541789],"study_design_scores_gemma":[0.00006157518,0.000014984069,0.000013041159,0.00023895077,0.000014984596,0.000013410812,0.000055013068,0.6112416,8.107849e-7,0.0010252115,0.3871101,0.00021033523],"about_ca_topic_score_codex":0.00013098426,"about_ca_topic_score_gemma":0.00006901152,"teacher_disagreement_score":0.6097997,"about_ca_system_score_codex":0.00005720858,"about_ca_system_score_gemma":0.00013303157,"threshold_uncertainty_score":0.99993974},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017626604,0.00017578196,0.9607204,0.017101254,0.00060708326,0.00017684631,0.0035343333,0.00004822304,0.000009483009],"genre_scores_gemma":[0.7314314,0.00027417194,0.25573847,0.0013081917,0.00075965514,0.000017985216,0.010439081,0.000023595156,0.000007421038],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979829,0.0001016373,0.0007498327,0.00034114317,0.00055598695,0.00026845612],"domain_scores_gemma":[0.9973631,0.00051890645,0.0009422504,0.00029986125,0.0007178944,0.00015796741],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068984914,0.00015790974,0.00026738958,0.000081071244,0.00006621969,0.0004382623,0.0019005673,0.00011531357,0.00001161761],"category_scores_gemma":[0.0009400925,0.00015490295,0.00009865409,0.00036239036,0.000015784755,0.0009316682,0.00027271145,0.00035205574,0.0000050814106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018981881,0.0030097358,0.055463437,0.000108254724,0.0037839992,0.0006030644,0.0018300671,0.2548456,0.0062324763,0.021327898,0.38549894,0.26539832],"study_design_scores_gemma":[0.0016524274,0.00005335098,0.014480015,0.00007670174,0.00002977369,0.00004444871,0.00008964548,0.9449545,0.000105609935,0.00027393515,0.03806315,0.00017642614],"about_ca_topic_score_codex":0.000014337829,"about_ca_topic_score_gemma":0.000015981435,"teacher_disagreement_score":0.71380484,"about_ca_system_score_codex":0.00025239628,"about_ca_system_score_gemma":0.00013077946,"threshold_uncertainty_score":0.6316759},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000013799098,0.0000936534,0.9929908,0.0030346008,0.0007965489,0.00043446512,0.00005234662,0.00020734317,0.00238887],"genre_scores_gemma":[0.0032838613,0.000022809718,0.9927492,0.0026196188,0.000551139,0.000044423527,0.000036792084,0.000034146655,0.0006579724],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969795,0.000007301452,0.0004048687,0.00154083,0.00050417625,0.0005633693],"domain_scores_gemma":[0.9978897,0.00030982762,0.00020900469,0.0012155941,0.00020434053,0.00017153042],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005584272,0.00038617893,0.00041793924,0.0002798414,0.00024034585,0.00048410916,0.0034726032,0.00016813158,0.0000111061445],"category_scores_gemma":[0.00015144864,0.00036283088,0.000119582335,0.00047695104,0.0003014438,0.00045968947,0.0010604966,0.00048201345,0.00005594014],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002131083,0.000011271261,0.0000037235725,0.000026730939,0.0000069263206,0.000025757892,0.00024424877,0.0025191752,0.0000340949,0.089410216,0.00075706444,0.90695864],"study_design_scores_gemma":[0.00021234553,0.00016696149,0.000018194758,0.00019093633,0.0000067028227,0.000049577222,9.8466394e-8,0.8731031,0.00040494793,0.06673489,0.05861846,0.00049378205],"about_ca_topic_score_codex":0.0000063844454,"about_ca_topic_score_gemma":0.000008772577,"teacher_disagreement_score":0.9064649,"about_ca_system_score_codex":0.00014746164,"about_ca_system_score_gemma":0.00048492115,"threshold_uncertainty_score":0.99988234},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04045342,0.00048798253,0.93304586,0.024140306,0.000055519977,0.00028328082,0.000053625987,0.0013767451,0.00010324031],"genre_scores_gemma":[0.7028777,0.0014389051,0.2951406,0.00020740743,0.000005871097,0.0002579288,0.00003290889,0.000015091882,0.000023592795],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982698,0.00008904391,0.00042185324,0.0005660888,0.00020270822,0.00045053827],"domain_scores_gemma":[0.99740577,0.00014697947,0.00011877445,0.0022468362,0.000019899582,0.00006174177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025490433,0.00021892633,0.00024005263,0.0001806669,0.00060205883,0.000090273636,0.002647649,0.00014996232,0.000036183475],"category_scores_gemma":[0.00003047088,0.00023843868,0.000081799284,0.0013274206,0.00010585559,0.00039966975,0.00019806348,0.00063774287,0.00006400398],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010291554,0.0008818396,0.0017132325,0.000022230637,0.000069789174,0.0000055905357,0.003010058,0.016098592,0.00030756893,0.0031267207,0.0006844034,0.97406965],"study_design_scores_gemma":[0.001305365,0.00029809354,0.0152635025,0.00018515968,0.000055584827,0.000009265045,0.007908607,0.817211,0.0048521142,0.0030779485,0.1487232,0.001110199],"about_ca_topic_score_codex":0.00002193733,"about_ca_topic_score_gemma":0.000119325305,"teacher_disagreement_score":0.97295946,"about_ca_system_score_codex":0.00006854763,"about_ca_system_score_gemma":0.000028510418,"threshold_uncertainty_score":0.9723247},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46221194,0.000047630714,0.5307687,0.005596746,0.00018207298,0.0005502893,0.000035451227,0.00008863851,0.00051856023],"genre_scores_gemma":[0.7549926,0.000008101587,0.24469934,0.00008494521,0.000059620557,0.00009777002,0.000004866829,0.0000087360295,0.000044007265],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805194,0.0001275632,0.00035820733,0.000579535,0.0005880891,0.00029467995],"domain_scores_gemma":[0.9984917,0.00010816938,0.000097787604,0.00056907465,0.00045330648,0.00027995618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039335073,0.000104400875,0.00018755322,0.00023500697,0.00013335381,0.00014753708,0.0009021531,0.00010714661,0.000021512771],"category_scores_gemma":[0.00070785615,0.000110338384,0.00003079228,0.0021289873,0.00025845095,0.0005063147,0.0005929742,0.00043607093,0.000013484551],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010399162,0.0003087936,0.02719681,0.00013332054,0.00005622459,0.00004620857,0.012950016,0.1765623,0.11201957,0.08425059,0.016400896,0.56997126],"study_design_scores_gemma":[0.0002141155,0.00004120275,0.0011904148,0.000044947217,0.0000014964106,0.0000053600543,0.0011010182,0.98510194,0.011112958,0.00036693367,0.0007097401,0.00010984711],"about_ca_topic_score_codex":0.00010387235,"about_ca_topic_score_gemma":0.0000097636785,"teacher_disagreement_score":0.8085397,"about_ca_system_score_codex":0.000075177275,"about_ca_system_score_gemma":0.00034343288,"threshold_uncertainty_score":0.44994685},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039744243,0.00012448605,0.9389332,0.003036916,0.000073462004,0.00050135696,0.00026004386,0.0003618132,0.016964475],"genre_scores_gemma":[0.9046445,0.000045643093,0.09303853,0.00091553124,0.000035953468,0.000024822351,0.0012844392,0.000005744071,0.000004827921],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990855,0.00004250298,0.00044811002,0.00015708544,0.00015777934,0.00010904786],"domain_scores_gemma":[0.9989212,0.0001256882,0.00033812784,0.00046783866,0.000057486042,0.00008961822],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002300285,0.00010805639,0.00012197421,0.00018750144,0.0001581632,0.0004064648,0.0004671995,0.00006276879,0.0000025824431],"category_scores_gemma":[0.00019644247,0.000106792366,0.000011937207,0.0005340948,0.00008187822,0.019187845,0.0003096885,0.00007373395,0.000012754191],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017923594,0.000014009015,0.00070667674,0.0002805405,0.0000067083306,9.61295e-8,0.0069219754,0.00008832841,0.0000460057,0.032017313,0.001728938,0.9581715],"study_design_scores_gemma":[0.0002840575,0.0000901824,0.010034328,0.000114159026,0.000006600342,0.0000030370634,0.00060093467,0.9516929,0.00035898705,0.00013429794,0.036565945,0.00011460553],"about_ca_topic_score_codex":0.0000030051133,"about_ca_topic_score_gemma":1.5947029e-7,"teacher_disagreement_score":0.95805687,"about_ca_system_score_codex":0.000013693898,"about_ca_system_score_gemma":0.00008018873,"threshold_uncertainty_score":0.99453026},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.790833e-7,0.0092326,0.9128487,0.0011553628,0.0005005903,0.0006047492,0.00036689348,0.0000559973,0.07523434],"genre_scores_gemma":[0.00061217207,0.12767215,0.7159886,0.0008655899,0.0003714961,0.00014673804,0.00046253722,0.000032457276,0.15384829],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980778,0.0000067360083,0.0003617109,0.0011076701,0.00020850927,0.00023753697],"domain_scores_gemma":[0.9986976,0.00010911685,0.00009853179,0.00092526356,0.00007834655,0.00009116682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004108255,0.00023992026,0.00026700334,0.00022300621,0.0005451987,0.0009978138,0.0014154688,0.000047705544,0.000001147877],"category_scores_gemma":[0.0001377917,0.00023018144,0.000016996451,0.0001518069,0.0011320994,0.005154478,0.0020631927,0.00009784482,0.0000033401038],"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":[0.0000022631284,0.000010267871,0.000006099439,0.0001083803,0.000009169598,0.000003847943,0.00013311312,0.00023081992,0.0000012508584,0.9021584,0.0007677697,0.09656865],"study_design_scores_gemma":[0.000172452,0.00008937164,0.00002515983,0.00014891579,0.00004376045,0.0000045077877,0.00022167659,0.099107005,0.000004572094,0.024907507,0.874912,0.0003630416],"about_ca_topic_score_codex":0.0000039923843,"about_ca_topic_score_gemma":0.00023238795,"teacher_disagreement_score":0.87725085,"about_ca_system_score_codex":0.000039454855,"about_ca_system_score_gemma":0.00011557931,"threshold_uncertainty_score":0.96219414},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003420446,0.00020430713,0.86874527,0.002021539,0.00013163305,0.00035129153,0.00006475504,0.0000914664,0.1283555],"genre_scores_gemma":[0.10350668,0.00094516523,0.893097,0.0015619607,0.00005673586,0.00005813618,0.00014504183,0.000017493148,0.00061180355],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99824256,0.000015643145,0.0007379434,0.000319895,0.0004950445,0.0001889289],"domain_scores_gemma":[0.99695873,0.00008959917,0.0003853607,0.0020664544,0.00036242927,0.00013742459],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057745853,0.00020628565,0.00027804295,0.00062741037,0.00028720315,0.00040826516,0.004271391,0.000092049624,0.000004210089],"category_scores_gemma":[0.000049357393,0.00020411576,0.000051117386,0.0006016084,0.0009492383,0.0024727536,0.0042171343,0.00032824837,0.000033289256],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010384848,0.000019218183,0.0000047033536,0.000029412216,0.000004596202,2.2996565e-7,0.0020828145,0.00048305793,0.000005443648,0.533292,0.00028114382,0.46379638],"study_design_scores_gemma":[0.00016794584,0.000048699254,0.0005037547,0.00014799109,0.0000048071806,0.000013700563,0.00005465217,0.92007077,0.000019281933,0.0008452828,0.07790112,0.0002220008],"about_ca_topic_score_codex":0.0000190049,"about_ca_topic_score_gemma":0.0000031002294,"teacher_disagreement_score":0.91958773,"about_ca_system_score_codex":0.000089761365,"about_ca_system_score_gemma":0.00037295648,"threshold_uncertainty_score":0.8323599},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.071052395,0.0000151827035,0.91943663,0.00869815,0.000059196074,0.00008346638,0.000040165916,0.00007323488,0.0005415842],"genre_scores_gemma":[0.8842576,0.000007212594,0.11416085,0.0015248753,0.000015841128,0.000013084744,0.00001898083,7.079908e-7,8.166571e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99913484,0.000018806344,0.00026565522,0.0001806295,0.00023723465,0.00016286105],"domain_scores_gemma":[0.9995083,0.00010739191,0.000099910656,0.0001631633,0.000033949316,0.00008727519],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003698575,0.000069427035,0.00008846332,0.00005729766,0.0001755219,0.00049929257,0.00061499624,0.00003475464,0.0000061522373],"category_scores_gemma":[0.00017169253,0.000059769576,0.00001121206,0.0008471773,0.00011593058,0.0027354953,0.00022651914,0.000085484404,0.000039690407],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002500766,0.000023838695,0.034120437,0.000025175677,0.0000031772024,0.0000014515738,0.011870479,0.0012745033,0.000007096248,0.054259628,0.0022410208,0.8961707],"study_design_scores_gemma":[0.00018472037,0.000051177758,0.13212727,0.000026281372,0.000001188007,0.000003050437,0.0010117145,0.8533221,0.000023601631,0.0069626602,0.0061272765,0.00015895131],"about_ca_topic_score_codex":0.00009002281,"about_ca_topic_score_gemma":0.000006950153,"teacher_disagreement_score":0.89601177,"about_ca_system_score_codex":0.000008050291,"about_ca_system_score_gemma":0.00004606231,"threshold_uncertainty_score":0.48146895},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0054007103,0.000094975265,0.99141526,0.0017712184,0.000026185324,0.00024305248,0.0009529096,0.00007948169,0.000016216869],"genre_scores_gemma":[0.5026826,0.0000993211,0.49516284,0.00044474492,0.000054676653,0.00004075825,0.001472961,0.000008645154,0.000033416574],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983315,0.000042304593,0.00028878756,0.0009739368,0.00016701913,0.00019644681],"domain_scores_gemma":[0.9978193,0.00016312246,0.0001033877,0.0016865383,0.00007784081,0.00014978377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035727315,0.00013783468,0.00027604226,0.00007161355,0.00014153462,0.00039575598,0.0016121905,0.00003528919,0.000003883268],"category_scores_gemma":[0.00013309384,0.00012133139,0.00009187216,0.0011281252,0.000053226388,0.0014896053,0.0013499908,0.000077634264,0.000009133158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007831689,0.00087532727,0.009525922,0.00020439563,0.0043952996,0.000012996346,0.004327556,0.029727884,0.0008047389,0.23367569,0.005188692,0.7111832],"study_design_scores_gemma":[0.00006119813,0.000022700615,0.0005962127,0.0000025595782,0.00031877434,4.5942136e-7,0.00003867587,0.9890908,0.00024617405,0.0069262255,0.0025477638,0.0001484627],"about_ca_topic_score_codex":0.000524104,"about_ca_topic_score_gemma":0.000081714505,"teacher_disagreement_score":0.9593629,"about_ca_system_score_codex":0.000019358982,"about_ca_system_score_gemma":0.000035584275,"threshold_uncertainty_score":0.49477506},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016276948,0.00073104183,0.99123096,0.005242406,0.0003809141,0.00009521613,0.000014930402,0.00031886093,0.00035799254],"genre_scores_gemma":[0.8977454,0.0009343509,0.09810085,0.000163992,0.000037187325,0.00023910611,0.000007745761,0.000015804171,0.002755573],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991587,0.000017255583,0.00019112356,0.00037277123,0.00009267708,0.00016746299],"domain_scores_gemma":[0.99870586,0.000063416555,0.00003783031,0.001049077,0.000091892936,0.000051905565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000769089,0.000097919394,0.00013384376,0.00018991706,0.00019351758,0.00010737864,0.00053353905,0.00011476399,0.00001721901],"category_scores_gemma":[0.000021459264,0.000092353526,0.000028232345,0.00069998595,0.00005626737,0.000107615284,0.00003468069,0.0001752051,0.00009925313],"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":[6.537561e-7,0.00012737216,0.00003459401,0.000015536434,0.000041706775,0.000020740761,0.00007980587,0.000063135325,0.0005954794,0.2832414,0.00033218958,0.71544737],"study_design_scores_gemma":[0.0005047926,0.00039094652,0.00011118201,0.00021902008,0.000050902414,0.0017910743,0.0021478182,0.060981736,0.11201778,0.04696634,0.7740106,0.000807814],"about_ca_topic_score_codex":0.00003113442,"about_ca_topic_score_gemma":0.00000965194,"teacher_disagreement_score":0.8961177,"about_ca_system_score_codex":0.000019574834,"about_ca_system_score_gemma":0.00003650304,"threshold_uncertainty_score":0.37660676},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011563479,0.0001401863,0.9858717,0.000099361576,0.0002674773,0.00010058065,0.000028400522,0.00012641544,0.0018024304],"genre_scores_gemma":[0.67749506,0.000008833176,0.32194114,0.0003797412,0.00010224491,0.000011915982,0.000023865943,0.000010452433,0.000026779431],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985893,0.000019207275,0.00028377798,0.00057830266,0.00023421481,0.0002952379],"domain_scores_gemma":[0.99869436,0.00011472063,0.00009915972,0.00086086907,0.00012859754,0.00010230904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008391492,0.00016407006,0.00017241665,0.00004825031,0.00018792778,0.00025358069,0.00091494404,0.00005937837,0.000077438424],"category_scores_gemma":[0.000046718837,0.00016847564,0.00003886381,0.0004835577,0.00005260009,0.00009768895,0.00040683872,0.00016523356,0.000048168236],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017262,0.000119691686,0.00021599482,0.00004564752,0.000050079947,0.00009409784,0.0039047936,0.0033389546,0.04968114,0.13862313,0.0002981449,0.8036266],"study_design_scores_gemma":[0.000094582974,0.000017248334,0.0002274183,0.000071115945,0.000020325431,0.00008721854,0.00027386606,0.8040557,0.17444345,0.012441495,0.0077902395,0.00047731944],"about_ca_topic_score_codex":0.000058123052,"about_ca_topic_score_gemma":0.000012822975,"teacher_disagreement_score":0.8031493,"about_ca_system_score_codex":0.000039232615,"about_ca_system_score_gemma":0.00011293823,"threshold_uncertainty_score":0.68702376},"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":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70655274,0.00008919029,0.28947943,0.0028733446,0.0002529095,0.000223737,0.00010528482,0.0003112706,0.000112070746],"genre_scores_gemma":[0.18724431,0.000016435812,0.81172603,0.000614548,0.00003492911,0.00010473571,0.00024182805,0.0000104657065,0.000006687724],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875784,0.00004901202,0.0004908916,0.0003211226,0.00011697589,0.00026418478],"domain_scores_gemma":[0.99873006,0.000111828944,0.00019914041,0.00068830315,0.00018343976,0.00008723886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037800038,0.0001500789,0.00018955591,0.00035431157,0.00020395676,0.00025977037,0.00060287205,0.0006325302,0.000014151659],"category_scores_gemma":[0.00029474823,0.00016120895,0.00002169596,0.0009518807,0.00008593439,0.000853324,0.00032095483,0.0004508804,0.0000115202865],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017041176,0.00010911392,0.0024651657,0.000018924145,0.000026891174,0.000008971292,0.0021525137,0.0005515338,0.0025957716,0.073639825,0.0010060389,0.91742355],"study_design_scores_gemma":[0.0025939024,0.00019319954,0.009324156,0.00019443108,0.000036885365,0.00023951907,0.005957431,0.78259474,0.10912237,0.013413187,0.075239986,0.0010901996],"about_ca_topic_score_codex":0.000046222664,"about_ca_topic_score_gemma":0.0000038036703,"teacher_disagreement_score":0.9163334,"about_ca_system_score_codex":0.00008613094,"about_ca_system_score_gemma":0.0001191944,"threshold_uncertainty_score":0.657391},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.838084,0.0005889855,0.064703874,0.05366145,0.00042061394,0.0014685529,0.000091558024,0.0005106172,0.040470365],"genre_scores_gemma":[0.8645822,0.000017900727,0.13491927,0.0003034072,0.000045169072,0.00002960682,6.562806e-7,0.000006717899,0.000095068805],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991196,0.0000029521643,0.0002468928,0.00022930832,0.00025373464,0.00014750999],"domain_scores_gemma":[0.99943054,0.00002338798,0.00021637754,0.00014672648,0.00012119171,0.00006180488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016608651,0.000085478365,0.00015005335,0.000026013542,0.0000619162,0.000049493097,0.0011860491,0.000022360124,0.0000068860786],"category_scores_gemma":[0.000066035165,0.00006184247,0.000062301115,0.0003678818,0.00005480744,0.00025651252,0.0005986982,0.00006337939,0.00000532019],"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":[0.000029044208,0.000827283,0.012678753,0.0006134823,0.00015975627,8.8659743e-7,0.014803257,0.000031424646,0.2912116,0.40322495,0.046570268,0.22984932],"study_design_scores_gemma":[0.000681178,0.0005609812,0.0041714613,0.00022427073,0.0000421252,0.000010831112,0.0009878761,0.07152831,0.89771265,0.0045671924,0.019189823,0.00032329818],"about_ca_topic_score_codex":0.000026902802,"about_ca_topic_score_gemma":2.2447796e-7,"teacher_disagreement_score":0.60650104,"about_ca_system_score_codex":0.000013760361,"about_ca_system_score_gemma":0.00002550283,"threshold_uncertainty_score":0.25218627},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08661741,0.0010478605,0.9075681,0.0012771979,0.0005214266,0.0009241373,0.0001551359,0.0002880714,0.0016006572],"genre_scores_gemma":[0.19088453,0.00050113694,0.8023647,0.000045865985,0.001110481,0.0007420264,0.00291981,0.00006539409,0.0013660474],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964019,0.0005884846,0.00034842777,0.0008443525,0.0013289622,0.00048788366],"domain_scores_gemma":[0.9962212,0.00037786103,0.00025142365,0.0012925814,0.0017208512,0.00013608603],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0027549537,0.00018428973,0.00023545479,0.0003953575,0.00047401694,0.0017850137,0.0011203059,0.00033035348,0.000028527578],"category_scores_gemma":[0.0009994857,0.00020075867,0.00011473929,0.00089239207,0.000037653048,0.0006241485,0.0023800838,0.0010386998,0.000127269],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000072473817,0.0010932675,0.002779281,0.0021555845,0.00022364718,0.000050995735,0.0068011307,0.0030978194,0.002463376,0.048665997,0.011065683,0.921596],"study_design_scores_gemma":[0.00015645048,0.000023506085,0.0017309309,0.0007824631,0.000011156934,0.0000035676676,0.00023195359,0.985059,0.0019540293,0.006779361,0.0029876074,0.00027994998],"about_ca_topic_score_codex":0.00027991214,"about_ca_topic_score_gemma":0.000030928546,"teacher_disagreement_score":0.9819612,"about_ca_system_score_codex":0.001107377,"about_ca_system_score_gemma":0.0008870675,"threshold_uncertainty_score":0.99925125},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013507342,0.00012731766,0.98385525,0.00076142856,0.00009629062,0.0000769317,0.00011862517,0.00021211163,0.0012446984],"genre_scores_gemma":[0.12422709,0.000023453049,0.8740771,0.0002457336,0.00008562315,0.0000016624886,0.0010051368,0.000007602775,0.00032659093],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987531,0.000013455344,0.0001961552,0.0006642605,0.0001746486,0.00019838104],"domain_scores_gemma":[0.99657166,0.00014464871,0.000063394626,0.0030909295,0.000026606984,0.00010277186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087373384,0.000089516776,0.00008993492,0.00005439902,0.00016852163,0.00026194533,0.0028669373,0.000032716616,0.000015570884],"category_scores_gemma":[0.00007493114,0.00007341234,0.000005114821,0.0002361186,0.000038800255,0.0018201288,0.0041582696,0.00006104617,0.00002402704],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013989861,0.00003946927,0.010497159,0.0000058761034,0.000006722966,0.00000811794,0.00017219316,5.509207e-7,0.000028759854,0.0019025698,0.03377256,0.95356464],"study_design_scores_gemma":[0.0002291692,0.00002781023,0.010124353,0.00002984548,0.000009465919,0.000034460394,0.00027506994,0.66206217,0.00017709156,0.00015013712,0.32663602,0.00024439613],"about_ca_topic_score_codex":0.0002712841,"about_ca_topic_score_gemma":0.00056034984,"teacher_disagreement_score":0.9533202,"about_ca_system_score_codex":0.000006444718,"about_ca_system_score_gemma":0.00004817361,"threshold_uncertainty_score":0.53275305},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038522776,0.00059794047,0.9444974,0.008208185,0.0008830425,0.0002619833,0.0006117329,0.00041899696,0.0059979516],"genre_scores_gemma":[0.33437857,0.0000035780558,0.6645626,0.0005224508,0.0002063888,0.000009058717,0.00007647787,0.0000050279764,0.0002358533],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99842095,0.000025586158,0.00017615329,0.0007127882,0.0003148971,0.0003496086],"domain_scores_gemma":[0.99895895,0.00025172028,0.0000733605,0.000589451,0.00008327557,0.000043269],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008429841,0.00009739652,0.0001240457,0.000072277326,0.0011251319,0.00079769845,0.0024611051,0.000031248117,0.000006477644],"category_scores_gemma":[0.0002182005,0.00008138649,0.000038602717,0.0013378182,0.00021373364,0.0007857072,0.0011512941,0.000072582734,0.000005759429],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022610413,0.00015982334,0.00026098028,0.000043944532,0.000051575575,0.000027981134,0.002173088,0.00008553212,0.0048336745,0.537868,0.02650763,0.42798552],"study_design_scores_gemma":[0.00022659164,0.000040378633,0.00047115918,0.000013138081,0.000014451631,0.000019683377,0.001849439,0.98489803,0.0021226509,0.0031282702,0.006934764,0.00028144405],"about_ca_topic_score_codex":0.000050687555,"about_ca_topic_score_gemma":0.00014831415,"teacher_disagreement_score":0.9848125,"about_ca_system_score_codex":0.000018554392,"about_ca_system_score_gemma":0.00023271897,"threshold_uncertainty_score":0.86537176},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037115272,0.000015901505,0.96565723,0.00042148092,0.00007317526,0.0001286333,0.000006392239,0.00013494104,0.029850714],"genre_scores_gemma":[0.63029796,0.0000013912012,0.36863476,0.0007453286,0.000111022484,0.000015529788,0.0000101742835,0.000004803984,0.00017905721],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99919325,0.000022407408,0.0001456636,0.00025879624,0.00015271014,0.00022714368],"domain_scores_gemma":[0.999182,0.00017309283,0.00005301019,0.00045892145,0.00005443839,0.000078577556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007644325,0.000075698,0.00006884709,0.000024939987,0.00022039379,0.00020912672,0.0009695452,0.000019970987,0.0000060490515],"category_scores_gemma":[0.0000250399,0.00004660171,0.000019683772,0.00020653139,0.000055212462,0.00039662162,0.0001162833,0.00009837266,0.000020605206],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013527111,0.00009968022,0.0001249543,0.0000011651883,0.000015001795,0.000002795237,0.0011869766,0.000041739946,0.00024658398,0.5084941,0.00075827923,0.4890274],"study_design_scores_gemma":[0.00024775637,0.00003982955,0.004614798,0.0000033899012,0.0000041176463,0.00003355195,0.0007874193,0.984817,0.0010822462,0.0027186063,0.0055053374,0.0001459405],"about_ca_topic_score_codex":0.000107594475,"about_ca_topic_score_gemma":0.000015329364,"teacher_disagreement_score":0.98477525,"about_ca_system_score_codex":0.00001307927,"about_ca_system_score_gemma":0.000017907067,"threshold_uncertainty_score":0.20166138},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025151211,0.00005826002,0.99245703,0.0026699416,0.00007157205,0.0005755619,0.000035432666,0.00007051886,0.0015465368],"genre_scores_gemma":[0.43329728,0.0000068265367,0.56439406,0.00014042386,0.0000698219,0.00017791292,0.00017654545,0.000008074968,0.0017290618],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993333,0.000011130512,0.00011565419,0.0002695525,0.00013463652,0.00013573191],"domain_scores_gemma":[0.99917775,0.00014559751,0.0001404881,0.00036142935,0.00012679269,0.000047908845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036913564,0.00008280222,0.000095141426,0.00005930966,0.00008308603,0.00005070119,0.0003208068,0.00006471452,9.3694615e-7],"category_scores_gemma":[0.00002616298,0.000069532136,0.000035055797,0.00031192883,0.000020628806,0.00022489735,0.000054429656,0.000058113503,0.000003522597],"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":[0.000009875272,0.00010537188,0.00009032511,0.000014788382,0.00001548316,1.6434298e-7,0.00018522538,0.000005215348,0.13217342,0.47680354,0.15351388,0.2370827],"study_design_scores_gemma":[0.0011546438,0.00061884074,0.06519472,0.000030470419,0.000032928692,0.000014738402,0.00032836042,0.0523399,0.7512325,0.012545931,0.11599139,0.00051554205],"about_ca_topic_score_codex":0.000029305489,"about_ca_topic_score_gemma":0.000011305643,"teacher_disagreement_score":0.6190591,"about_ca_system_score_codex":0.000042456362,"about_ca_system_score_gemma":0.000019640232,"threshold_uncertainty_score":0.28354383},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12809512,0.0032262448,0.8570812,0.0011542236,0.00049051177,0.00044120662,0.009041163,0.00026307054,0.00020726865],"genre_scores_gemma":[0.084902346,0.0017650794,0.90196794,0.00034788638,0.00016787309,0.000017765184,0.010727926,0.000039368268,0.000063826345],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982657,0.00009870967,0.00020544925,0.001047765,0.00014800536,0.0002344163],"domain_scores_gemma":[0.9963527,0.00014241191,0.000073839845,0.0032587363,0.00006139502,0.00011093668],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0011052592,0.00012945868,0.00019010727,0.00003960752,0.00041991327,0.0018786615,0.0029221142,0.000027927708,0.000002619395],"category_scores_gemma":[0.00018727407,0.00012635115,0.0000052419864,0.00038296878,0.00004907342,0.0055941674,0.015754055,0.00012126655,0.0000039739807],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000560756,0.00020304465,0.009576298,0.00013585557,0.00009597067,0.00009595301,0.0015703801,0.00005487969,0.0009385316,0.0021582285,0.006766818,0.97839844],"study_design_scores_gemma":[0.0005298153,0.00002228359,0.015794454,0.00027704865,0.000031906322,0.00024229103,0.00025669165,0.8687004,0.0001441417,0.00025793596,0.11322395,0.00051910704],"about_ca_topic_score_codex":0.0023972527,"about_ca_topic_score_gemma":0.00049785496,"teacher_disagreement_score":0.97787935,"about_ca_system_score_codex":0.000010864447,"about_ca_system_score_gemma":0.00014691403,"threshold_uncertainty_score":0.9991575},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17913203,0.00009817978,0.8202053,0.00012442691,0.00019319412,0.00009162017,0.0000148093095,0.0000914526,0.000048986483],"genre_scores_gemma":[0.9474416,0.000022019522,0.05198588,0.00003495155,0.000027788814,0.00009456263,0.000028714592,0.000012203166,0.000352326],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991018,0.000004103009,0.00028504204,0.0002702833,0.00011605832,0.00022268179],"domain_scores_gemma":[0.9992143,0.0000693193,0.00010248909,0.00047047817,0.00009328057,0.0000501616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014395818,0.00009544396,0.00015097304,0.000048904498,0.00005212721,0.000045156088,0.00017859819,0.000032523447,0.000011219299],"category_scores_gemma":[0.000011801237,0.000102933715,0.00006983525,0.00019229972,0.0000047007243,0.00018067005,0.000028271208,0.00007433792,0.0000011485457],"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":[0.000004680456,0.00048056894,0.001094457,0.0008346201,0.00037820847,0.00014956447,0.0038076353,0.038784992,0.7992684,0.0068987063,0.0002252912,0.14807284],"study_design_scores_gemma":[0.0004638604,0.000084535015,0.004310612,0.0003035313,0.000064352076,0.0004003533,0.00033697404,0.5130554,0.42630976,0.00006141366,0.054071397,0.0005378077],"about_ca_topic_score_codex":0.000020127432,"about_ca_topic_score_gemma":0.000017596736,"teacher_disagreement_score":0.76830953,"about_ca_system_score_codex":0.000026274947,"about_ca_system_score_gemma":0.00006909131,"threshold_uncertainty_score":0.4197515},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09303618,0.00015893833,0.90610415,0.000312694,0.00009895959,0.000068632944,0.00011186348,0.000035719877,0.00007285023],"genre_scores_gemma":[0.5335761,0.000004241114,0.46590766,0.000017367951,0.000024735264,0.0000031274458,0.00042222312,0.0000048151246,0.000039772025],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99897337,0.000012051051,0.00020985123,0.00048747216,0.00014545239,0.00017179594],"domain_scores_gemma":[0.9988089,0.000048055925,0.000063016705,0.0008001041,0.0002250434,0.000054872373],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040038084,0.00008013686,0.00012560152,0.000042501422,0.00032841097,0.0004990942,0.0009022798,0.00002658809,0.0000017921751],"category_scores_gemma":[0.000014937734,0.00007776329,0.000011773783,0.00064408395,0.00010763074,0.0009855201,0.0006275802,0.000050820974,9.1035326e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014835409,0.00012227196,0.000017210657,0.00008410089,0.00002134668,0.000003862175,0.007024484,0.00015758058,0.0008813286,0.030269433,0.00008175137,0.9613351],"study_design_scores_gemma":[0.00023175484,0.000021540996,0.00501865,0.000055232256,0.000014956099,0.000017945991,0.0019968953,0.9850411,0.00121736,0.002607188,0.0036041427,0.00017323186],"about_ca_topic_score_codex":0.000009930471,"about_ca_topic_score_gemma":0.000033196586,"teacher_disagreement_score":0.98488355,"about_ca_system_score_codex":0.000006107115,"about_ca_system_score_gemma":0.00057202135,"threshold_uncertainty_score":0.48127767},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54946023,0.000048426544,0.40711704,0.0058394545,0.00023142113,0.00026994332,0.0000060277866,0.00034598703,0.03668147],"genre_scores_gemma":[0.5592912,0.000017955432,0.4376344,0.000058744936,0.00006652937,0.000047299513,0.000009343773,0.0000061335263,0.0028683776],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990904,0.000035601766,0.00012164978,0.00034678957,0.00021891901,0.00018665002],"domain_scores_gemma":[0.9990291,0.00016946202,0.000029252986,0.0005548359,0.00011906358,0.0000983152],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007932407,0.000057743022,0.000056211178,0.0001211847,0.0002944387,0.00030537642,0.0004962694,0.000056123903,0.0000560349],"category_scores_gemma":[0.000073153475,0.00004705903,0.000013108322,0.000477511,0.00009152828,0.00046689739,0.0001818366,0.0001741055,0.00009134205],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.8343114e-7,0.000050266728,0.00043824606,0.0000042152897,0.00000237496,8.4938085e-7,0.00034182525,1.6233567e-7,0.049992893,0.09637549,0.016199676,0.8365931],"study_design_scores_gemma":[0.00056658965,0.00016191354,0.10896015,0.00004100943,0.00000739541,0.000058624588,0.0011057005,0.6494615,0.011998936,0.016499436,0.21062317,0.00051557156],"about_ca_topic_score_codex":0.000016838067,"about_ca_topic_score_gemma":0.000037855887,"teacher_disagreement_score":0.8360776,"about_ca_system_score_codex":0.000004736796,"about_ca_system_score_gemma":0.000036232286,"threshold_uncertainty_score":0.2944752},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04840089,0.00013241424,0.95046705,0.0007808587,0.000067573725,0.00003505368,0.000021895421,0.000018537017,0.0000757249],"genre_scores_gemma":[0.8346937,0.00039801473,0.16477777,0.000017766262,0.00007037587,0.0000020100993,0.000018386756,0.000004865334,0.000017145741],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99878824,0.000025594833,0.00021351253,0.00024300825,0.0001667493,0.0005628945],"domain_scores_gemma":[0.9991411,0.00008470031,0.000058201476,0.0005832625,0.0000585128,0.000074249714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011068601,0.000059778853,0.000089724985,0.00007015822,0.00017607835,0.00010161086,0.00087921065,0.000032389868,0.0000028153852],"category_scores_gemma":[0.00013071952,0.000053503016,0.000015051284,0.00016881549,0.000058325964,0.00048405555,0.0002969282,0.0010512337,0.0000016489436],"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":[0.0000010700827,0.000024935911,0.00019788924,0.0000013089375,0.000016933618,7.2970823e-7,0.00004737331,0.000041630385,0.00065469026,0.92412156,0.000030910058,0.074860975],"study_design_scores_gemma":[0.0001219156,0.000025949968,0.00021027485,0.0000034873053,0.000009211992,0.0002917784,0.00011904327,0.7017114,0.000014538754,0.29732087,0.000114670926,0.000056854176],"about_ca_topic_score_codex":0.00013304886,"about_ca_topic_score_gemma":0.00036466942,"teacher_disagreement_score":0.7862928,"about_ca_system_score_codex":0.0000146480415,"about_ca_system_score_gemma":0.0005409131,"threshold_uncertainty_score":0.4567146},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8589288,0.008655574,0.12315047,0.0015469193,0.0019970695,0.0026902852,0.0006360284,0.0006857665,0.0017091046],"genre_scores_gemma":[0.9537417,0.000016219086,0.04565704,0.000030278707,0.00010938932,0.0001511055,0.000054126398,0.000025626732,0.00021447144],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972006,0.00030787726,0.0007549832,0.0009052138,0.0005514009,0.00027989055],"domain_scores_gemma":[0.9955544,0.000068793546,0.00045970813,0.0032485249,0.00054578116,0.00012280283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047361813,0.00023093288,0.0004398924,0.00007761705,0.0003398437,0.00019679162,0.0015416296,0.0000851924,0.000002028722],"category_scores_gemma":[0.00008094885,0.00017496925,0.00015185442,0.00090198446,0.00014218576,0.0005910362,0.0006676408,0.00012023007,0.0000061654846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004807968,0.0035970465,0.014167635,0.011853618,0.00035910547,0.00006784227,0.0062720617,0.002423797,0.3449688,0.5847205,0.0007024847,0.030819029],"study_design_scores_gemma":[0.0011367288,0.00040440453,0.07113334,0.0047807056,0.00028064108,0.0008131153,0.01189003,0.7662175,0.13900793,0.000121458084,0.0030006962,0.0012134147],"about_ca_topic_score_codex":0.00009503065,"about_ca_topic_score_gemma":0.000003099756,"teacher_disagreement_score":0.76379377,"about_ca_system_score_codex":0.00013830257,"about_ca_system_score_gemma":0.0003820116,"threshold_uncertainty_score":0.7135039},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008126411,0.000005493701,0.9829013,0.00171743,0.00008486925,0.000035429162,7.880095e-7,0.00016261225,0.006965716],"genre_scores_gemma":[0.17155994,0.0000044290928,0.8262617,0.00022647696,0.00004938257,0.000005440503,0.000054542175,0.000006632164,0.0018314492],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995183,0.000010144533,0.00007918978,0.00021298461,0.00009915464,0.00008026037],"domain_scores_gemma":[0.99943876,0.00001673759,0.00003425577,0.00033091858,0.0001452479,0.000034065626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000040404804,0.000046886802,0.00004590033,0.000019810523,0.00009962918,0.00017040178,0.0001766878,0.000014665333,0.000055522807],"category_scores_gemma":[0.000029484467,0.000038336857,0.0000069480557,0.0006257173,0.000012923921,0.0002951979,0.000118783704,0.000035305646,0.000048044887],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.3069477e-7,0.0000507632,0.004121257,0.000004486003,0.000013627411,0.000010156448,0.00026072943,0.000015501084,0.0010893918,0.3255348,0.002683109,0.66621584],"study_design_scores_gemma":[0.0028606257,0.00027327804,0.053290233,0.00011488,0.00008878507,0.0022783899,0.004332845,0.41959307,0.34851408,0.00681783,0.16017802,0.0016579524],"about_ca_topic_score_codex":0.00001016238,"about_ca_topic_score_gemma":0.000016607639,"teacher_disagreement_score":0.6645579,"about_ca_system_score_codex":0.000023711393,"about_ca_system_score_gemma":0.00007321827,"threshold_uncertainty_score":0.16431883},"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":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000015582244,0.00008008913,0.11169296,0.0015608426,0.0001273501,0.00029748154,0.8856943,0.00030919854,0.0002361684],"genre_scores_gemma":[0.00031578637,0.0000020465848,0.22686367,0.0003998179,0.00023038645,0.00054966804,0.7714381,0.000020580092,0.00017994514],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99830025,0.00004679621,0.00024620068,0.0008951495,0.00026535883,0.00024625563],"domain_scores_gemma":[0.9980668,0.00011122682,0.00019704622,0.0013866064,0.00006290984,0.00017540925],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000075748954,0.0002382912,0.00020675024,0.00004971283,0.00016992877,0.0011136322,0.0027872631,0.00017104736,0.0119689815],"category_scores_gemma":[0.00044089992,0.00017765888,0.00007233763,0.00020820397,0.000007017759,0.0003149841,0.0055795056,0.00040191406,0.0035631931],"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":[6.6071544e-7,0.000014109558,0.0000014330204,0.0000801995,0.000008130683,0.000018594434,0.00014463293,0.00026470784,0.0000059680197,0.000028976041,0.9514848,0.04794779],"study_design_scores_gemma":[0.00010171133,0.000023858918,0.00041390528,0.0013863078,0.000005867813,0.0000069212488,0.0000072800253,0.28945974,0.00028241053,0.0006186209,0.7072647,0.00042869154],"about_ca_topic_score_codex":0.000004970782,"about_ca_topic_score_gemma":5.012772e-7,"teacher_disagreement_score":0.28919503,"about_ca_system_score_codex":0.00003135869,"about_ca_system_score_gemma":0.00020659827,"threshold_uncertainty_score":0.9999233},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027297281,0.00007046784,0.9945585,0.0007647439,0.00020999988,0.00023558103,0.000039773797,0.00014446491,0.0012467428],"genre_scores_gemma":[0.37033132,0.000013407439,0.62866,0.00017201893,0.00015823844,0.00012002876,0.00008981615,0.000011596273,0.00044358912],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984108,0.000016710015,0.00029194914,0.00074999226,0.00020388802,0.00032661908],"domain_scores_gemma":[0.9985787,0.00012925373,0.00008759562,0.0010125544,0.000055425924,0.00013641774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023929792,0.00016162067,0.00018037486,0.000036088433,0.00017376944,0.00024403668,0.0009946002,0.00007324344,0.000071900344],"category_scores_gemma":[0.000028393039,0.0001688875,0.00007100356,0.00035377414,0.00003750991,0.00019546271,0.00038971537,0.0001020816,0.000049009835],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002132471,0.000034708784,0.000022360051,0.000013849504,0.000012963934,0.0000020757088,0.0002964236,0.000056390425,0.00034656943,0.3942212,0.0011906135,0.6038007],"study_design_scores_gemma":[0.00034510606,0.00007611973,0.0008907995,0.00005912028,0.000049700982,0.000047119025,0.001002387,0.26389286,0.5155833,0.15893823,0.058173183,0.00094211544],"about_ca_topic_score_codex":0.000053633852,"about_ca_topic_score_gemma":0.000015762902,"teacher_disagreement_score":0.6028586,"about_ca_system_score_codex":0.000025052539,"about_ca_system_score_gemma":0.00017834787,"threshold_uncertainty_score":0.68870324},"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":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89844626,0.000032360058,0.09368519,0.0050310506,0.00014764987,0.00024830698,0.00006406537,0.00009565451,0.0022494656],"genre_scores_gemma":[0.47174832,0.000052915624,0.527269,0.00011091457,0.00025735478,0.00017785466,0.000017051696,0.000016826569,0.0003497784],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992537,5.753674e-8,0.00020734202,0.00017208692,0.00020725038,0.0001595508],"domain_scores_gemma":[0.9996732,0.00010113113,0.000046501715,0.00006421996,0.00008556813,0.000029393037],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023238992,0.00007955828,0.00009306974,0.000023919443,0.000055863817,0.00014671382,0.00073202717,0.000034738405,0.0000075174316],"category_scores_gemma":[0.00008965753,0.00006792273,0.00013339458,0.00016982557,0.000025212961,0.0004442244,0.000109476416,0.00011000863,0.0000028879995],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009060573,0.00024350172,0.0010639417,0.000059900467,0.00022308897,3.3929453e-7,0.0011760739,0.009177808,0.06014433,0.817746,0.0030734686,0.107082516],"study_design_scores_gemma":[0.0003017662,0.000024061486,0.009514672,0.0000445497,0.000009404146,0.000002727703,0.000060044233,0.9776643,0.0061444393,0.0016062094,0.0044867736,0.00014108645],"about_ca_topic_score_codex":0.000045515233,"about_ca_topic_score_gemma":8.571149e-7,"teacher_disagreement_score":0.9684865,"about_ca_system_score_codex":0.00007784157,"about_ca_system_score_gemma":0.000014916051,"threshold_uncertainty_score":0.27698085},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10271992,0.0002642496,0.8962837,0.00026665992,0.00021328637,0.00006700229,0.000024089039,0.000039262122,0.000121840254],"genre_scores_gemma":[0.67991024,0.000013432138,0.31978437,0.00007833133,0.000056068155,0.000023607321,0.000017581322,0.000008267595,0.00010810096],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992919,0.000019775354,0.00018331436,0.00025948466,0.00008411766,0.00016143228],"domain_scores_gemma":[0.9993127,0.00020743188,0.00008947687,0.0002641216,0.00009128503,0.000035001554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014731991,0.00006879768,0.00010728121,0.000032025666,0.00010846729,0.00008232548,0.00033980876,0.00002531924,0.0000092219725],"category_scores_gemma":[0.000055472065,0.00007046082,0.00004880235,0.00018282217,0.00000974493,0.00019207329,0.00014543293,0.000032344273,0.0000047438325],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.210373e-7,0.000026958274,0.00030813008,0.00002274624,0.000022896933,0.0000026534767,0.0010420065,0.000046734727,0.019603543,0.00075180683,0.00013851863,0.97803336],"study_design_scores_gemma":[0.0014865751,0.0002574466,0.0605114,0.00041110802,0.000098983546,0.00015801891,0.0042580455,0.7740331,0.12830535,0.0035675096,0.025844617,0.001067832],"about_ca_topic_score_codex":0.000016546092,"about_ca_topic_score_gemma":0.000023176473,"teacher_disagreement_score":0.97696555,"about_ca_system_score_codex":0.000009594316,"about_ca_system_score_gemma":0.00007363696,"threshold_uncertainty_score":0.28733087},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11279121,0.0001542783,0.88278985,0.0034957542,0.00040353343,0.00006553327,0.000033707583,0.00020192425,0.00006418012],"genre_scores_gemma":[0.83587426,0.000021354288,0.16373703,0.00011068318,0.00003460822,0.00001726463,0.000009544284,0.00000912503,0.00018611606],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988446,0.000034014807,0.00032544244,0.00039483022,0.00013950432,0.00026158578],"domain_scores_gemma":[0.9979719,0.00042695637,0.00010994472,0.0013460759,0.00011291717,0.000032232158],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013613084,0.00011947577,0.00016458298,0.0000862906,0.00018453694,0.00006927891,0.0015453334,0.00010341833,0.000028093227],"category_scores_gemma":[0.000051999283,0.00009921222,0.000071781746,0.0005955222,0.00010477753,0.000042839256,0.00014031188,0.00027727775,0.000023959665],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000052664545,0.00021198236,0.0005766424,0.0000048142174,0.00012687416,0.000015190784,0.0005761168,0.0056725927,0.00044657578,0.014252422,0.0007245791,0.97738695],"study_design_scores_gemma":[0.00054955325,0.00019278828,0.0016728606,0.00026333265,0.00004460507,0.00007694845,0.00077968696,0.92228067,0.043072984,0.005419012,0.025327357,0.0003201827],"about_ca_topic_score_codex":0.00009225532,"about_ca_topic_score_gemma":0.00009909438,"teacher_disagreement_score":0.97706676,"about_ca_system_score_codex":0.000027556624,"about_ca_system_score_gemma":0.000038318347,"threshold_uncertainty_score":0.40457568},"labels":[],"label_agreement":null},{"id":"W3197889602","doi":"10.1016/j.datak.2021.101924","title":"Mining high utility patterns in interval-based event sequences","year":2021,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Pruning; Interval (graph theory); Computer science; Event (particle physics); Data mining; Range (aeronautics); Point (geometry); Sequential Pattern Mining; Algorithm; Mathematics; Engineering","score_opus":0.041472155210488644,"score_gpt":0.29062862660563255,"score_spread":0.2491564713951439,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197889602","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05081657,0.00035929863,0.9475017,0.00026706967,0.00044051404,0.000066103545,0.00029644417,0.00015973444,0.00009253375],"genre_scores_gemma":[0.720634,0.000013098093,0.27828124,0.00003865829,0.00010101465,0.000036823505,0.0008389571,0.000013618219,0.000042605483],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987159,0.00003276075,0.00026847524,0.0005980427,0.00012027275,0.00026456267],"domain_scores_gemma":[0.9982424,0.00014506404,0.000036442903,0.0014487869,0.000047986137,0.00007931992],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038947942,0.00013843285,0.00016583833,0.000091889946,0.000043494907,0.00015561766,0.0015786167,0.000040206614,0.000028444638],"category_scores_gemma":[0.00013687511,0.00014846103,0.000026709135,0.0005295536,0.00001208095,0.000548056,0.0010638923,0.00015052823,0.00003431593],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001274374,0.0003327789,0.0047531095,0.00018588753,0.000027831187,0.00012278555,0.00079090445,0.000549154,0.0012564352,0.003913797,0.0016839389,0.9863821],"study_design_scores_gemma":[0.0001476228,0.000007765841,0.0088244025,0.00016941757,0.0000036218773,0.0000063568377,0.00003825904,0.9776545,0.0020390996,0.000019080704,0.010924771,0.00016506726],"about_ca_topic_score_codex":0.00007111082,"about_ca_topic_score_gemma":0.00017670124,"teacher_disagreement_score":0.986217,"about_ca_system_score_codex":0.000047440277,"about_ca_system_score_gemma":0.00012568351,"threshold_uncertainty_score":0.60540646},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7451195,0.001092137,0.2532513,0.00015942285,0.000021232787,0.0001227938,0.000008561902,0.000022040247,0.00020301664],"genre_scores_gemma":[0.8730742,0.00049922033,0.12621753,0.00006907029,0.000004497597,0.000033804634,0.000032385262,0.000006197715,0.0000631166],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991046,0.00007420886,0.00029063746,0.00027901758,0.00008339376,0.00016811173],"domain_scores_gemma":[0.9987089,0.00017707086,0.000120537814,0.00091306557,0.00002979568,0.00005065415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029526712,0.00008994306,0.00017552396,0.00005352969,0.00014220015,0.00009132048,0.0006193901,0.000037648064,0.0000024842025],"category_scores_gemma":[0.000008827083,0.00009754502,0.000018098035,0.0001893129,0.00007636561,0.00025651298,0.0021087849,0.00013201807,9.365938e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015720436,0.0005661035,0.09981241,0.00009474666,0.000029224811,0.000005780443,0.033612117,0.000042818523,0.0036859794,0.01565979,0.00004644514,0.846443],"study_design_scores_gemma":[0.00039995956,0.000032313434,0.012886892,0.00023257639,0.0000060165303,0.000020881149,0.002791197,0.9783147,0.0015266542,0.000087991364,0.003550953,0.00014985132],"about_ca_topic_score_codex":0.000085483436,"about_ca_topic_score_gemma":0.000030187908,"teacher_disagreement_score":0.9782719,"about_ca_system_score_codex":0.000015300291,"about_ca_system_score_gemma":0.000025393841,"threshold_uncertainty_score":0.39777702},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06856588,0.00001822502,0.9293852,0.0002562675,0.000081223436,0.00011761922,0.00001677068,0.000014052088,0.0015447581],"genre_scores_gemma":[0.9809091,0.000022085662,0.018800905,0.00018054477,0.000020992602,0.000015202905,0.000016247765,0.0000033278454,0.000031589687],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99883443,0.000043553948,0.0004208949,0.0002995335,0.00025674954,0.00014483197],"domain_scores_gemma":[0.99867713,0.00025854376,0.00015642321,0.0008040913,0.00007753188,0.000026303784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005062258,0.00009160074,0.00018412073,0.000051981337,0.000021876791,0.00004632934,0.0013538297,0.000061025148,0.000048729235],"category_scores_gemma":[0.00006413118,0.00007300326,0.00004165532,0.0006974958,0.00007657662,0.00012888422,0.00034662845,0.0002257149,0.00000838809],"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":[0.0000072840476,0.00032657533,0.0021220539,0.00002966022,0.000025180112,0.0000093113185,0.005245793,0.00023775379,0.00041721284,0.49353188,0.0004618497,0.49758545],"study_design_scores_gemma":[0.0004913742,0.0001600827,0.014855808,0.00022036035,0.000041228574,0.00003172769,0.0028172347,0.35720032,0.5433881,0.075960785,0.004249191,0.0005837546],"about_ca_topic_score_codex":0.0005326607,"about_ca_topic_score_gemma":0.000024764371,"teacher_disagreement_score":0.9123432,"about_ca_system_score_codex":0.000012896676,"about_ca_system_score_gemma":0.00007702291,"threshold_uncertainty_score":0.29769868},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026376813,0.026021486,0.97035444,0.0002641188,0.00035211816,0.00020754407,0.00004734497,0.00011382234,0.0000014568336],"genre_scores_gemma":[0.004126496,0.0019600736,0.9934103,0.00022128341,0.00013726382,0.0000390753,0.00006850149,0.000020527972,0.000016495404],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99844366,0.000024171266,0.00051957415,0.00048797042,0.0002514654,0.00027312685],"domain_scores_gemma":[0.9980807,0.0003758722,0.0003076516,0.00086248864,0.00032951665,0.00004381446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007288764,0.00018774222,0.0005040729,0.000070313734,0.00011233235,0.00009199052,0.0007293767,0.0000378365,3.7348292e-7],"category_scores_gemma":[0.00037567908,0.00019591827,0.00009685688,0.00035037604,0.000008542896,0.00041724968,0.0009167131,0.000068121684,6.0882024e-7],"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":[7.49953e-7,0.000060724014,0.00004857227,0.009042057,0.00025584118,0.0000044263097,0.00040107802,0.7676163,0.000205341,0.00007540491,0.0021053716,0.22018415],"study_design_scores_gemma":[0.00019950813,0.000012996238,0.000039523125,0.004624746,0.00007803538,0.000005676658,0.000010944526,0.9941716,0.00007239606,0.0000024185501,0.0005938587,0.00018828399],"about_ca_topic_score_codex":0.0000013479935,"about_ca_topic_score_gemma":0.0000025078764,"teacher_disagreement_score":0.22655533,"about_ca_system_score_codex":0.00010826443,"about_ca_system_score_gemma":0.00011972806,"threshold_uncertainty_score":0.7989315},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033242676,0.00014547865,0.8475749,0.02747728,0.00041468797,0.0013205385,0.00043201953,0.0027829134,0.086609505],"genre_scores_gemma":[0.55039716,0.000078053425,0.41671374,0.0085256845,0.0014287448,0.0000027770684,0.007283105,0.0026495643,0.0129211815],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980389,0.00037009854,0.0001834461,0.0006423432,0.0004287768,0.00033643784],"domain_scores_gemma":[0.9976589,0.00003414913,0.000041338884,0.0010200881,0.000803911,0.00044161812],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006576377,0.00010315862,0.00010001188,0.00021544672,0.0016693535,0.0022732478,0.0017585201,0.000045130208,0.00027507186],"category_scores_gemma":[0.00088294933,0.00011488164,0.000028888866,0.0014006894,0.000041433836,0.00059217436,0.0020006874,0.00019572162,0.0032068177],"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":[0.0000165801,0.00021802483,0.0000018587182,0.000018536735,0.000019304878,0.000052215695,0.0064318045,0.00014526267,0.040643066,0.025855398,0.40003532,0.52656263],"study_design_scores_gemma":[0.00016483392,0.00028153302,0.0016694482,0.000025174619,0.00000342373,0.00012987995,0.000582243,0.0014035683,0.0059412317,0.0004138669,0.9891975,0.00018731285],"about_ca_topic_score_codex":0.000040474908,"about_ca_topic_score_gemma":0.0000022468016,"teacher_disagreement_score":0.5891622,"about_ca_system_score_codex":0.000117646145,"about_ca_system_score_gemma":0.000013914912,"threshold_uncertainty_score":0.99963033},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46517646,0.00009621905,0.5064849,0.00028564603,0.0009024464,0.00072489644,0.00083849183,0.0017397162,0.023751182],"genre_scores_gemma":[0.7551793,0.000021048714,0.2440462,0.00039131893,0.00003785645,0.000069197995,0.000056955014,0.000035665966,0.00016246505],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99731886,0.00026146998,0.00047587967,0.00091512094,0.0005212094,0.00050743995],"domain_scores_gemma":[0.9974713,0.0002987997,0.00031893523,0.0014287004,0.00020302767,0.00027925163],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012654446,0.0003060134,0.00027010246,0.00018729648,0.0012920629,0.00023852014,0.0013749277,0.00015960129,0.000020495696],"category_scores_gemma":[0.0002864208,0.00031639967,0.00013723977,0.00072478806,0.00005523821,0.001217974,0.00027455442,0.0005214549,0.00049565994],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000399377,0.000100101104,0.000035143035,0.000012284847,0.0000146156735,0.0000025585475,0.000002285634,0.01423467,0.00078769476,0.34965512,0.000008060661,0.63514346],"study_design_scores_gemma":[0.00052626414,0.00007803407,0.00012090397,0.00005572583,0.0000249891,0.0000072590824,0.0000045658057,0.84132344,0.014846347,0.056752943,0.08581623,0.0004432802],"about_ca_topic_score_codex":0.0002901055,"about_ca_topic_score_gemma":0.000037795944,"teacher_disagreement_score":0.8270888,"about_ca_system_score_codex":0.0001646235,"about_ca_system_score_gemma":0.000025357225,"threshold_uncertainty_score":0.99992883},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000028107488,0.000028751763,0.98756814,0.0003812174,0.00051742455,0.0006472863,0.00004896577,0.00025574837,0.010524334],"genre_scores_gemma":[0.022040224,0.0000547018,0.9715875,0.00038836215,0.000033045948,0.00071061007,0.00040139316,0.000010699712,0.004773473],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987831,0.000027021433,0.00044036517,0.0002543882,0.00028467324,0.00021042895],"domain_scores_gemma":[0.99850595,0.000070848364,0.00014173743,0.0010542071,0.00013148299,0.00009578989],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026552443,0.00013644427,0.00013910755,0.0002522792,0.00029323003,0.000602246,0.0007121301,0.00005819222,0.000015513695],"category_scores_gemma":[0.000010539247,0.00014021981,0.000090056004,0.0008178124,0.000008956195,0.0014774182,0.000025777063,0.0000837294,0.0001317209],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009306423,0.00013892705,0.000008444915,0.00025383965,0.00025046125,0.0000021095937,0.0016680277,0.040397417,0.0000104505825,0.1237553,0.019486912,0.8140188],"study_design_scores_gemma":[0.0012513101,0.000054128854,0.00008477721,0.0000840287,0.000066362954,0.00003287136,0.0030563145,0.6928012,0.0001795781,0.00040886467,0.3016353,0.00034529492],"about_ca_topic_score_codex":0.00003436354,"about_ca_topic_score_gemma":0.0000012132742,"teacher_disagreement_score":0.8136735,"about_ca_system_score_codex":0.0000594725,"about_ca_system_score_gemma":0.00004966125,"threshold_uncertainty_score":0.5807472},"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":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000951833,0.000053978485,0.8845112,0.013082195,0.00016911523,0.00030863582,0.0005524274,0.0019029254,0.098467715],"genre_scores_gemma":[0.82544535,0.00009104335,0.14400853,0.0092714075,0.0020622131,3.2057474e-7,0.012165722,0.0027698486,0.004185557],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987137,0.0001273808,0.00014904697,0.0005715298,0.00023403775,0.00020432525],"domain_scores_gemma":[0.9986779,0.0000117918335,0.000064594766,0.00091400876,0.0001651965,0.00016651947],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002508949,0.000088278764,0.00008183729,0.00005340057,0.0014689105,0.0017295567,0.0033373921,0.000030046735,0.002912862],"category_scores_gemma":[0.00008496603,0.00009347293,0.000018181549,0.00049407594,0.000055978537,0.0008264436,0.0035205693,0.00015768342,0.008910786],"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":[0.0000042594306,0.000038124606,0.000006239599,0.000016772377,0.000013642076,0.0000062015247,0.00053212576,0.000004080396,0.0025239764,0.002938193,0.93876976,0.05514665],"study_design_scores_gemma":[0.00011934962,0.000054852724,0.0004963978,0.0000065900385,0.00000440746,0.00011823104,0.00005074942,0.0330402,0.000473663,0.000056845056,0.965468,0.00011073294],"about_ca_topic_score_codex":0.000007632374,"about_ca_topic_score_gemma":4.4353975e-8,"teacher_disagreement_score":0.8244935,"about_ca_system_score_codex":0.000029977142,"about_ca_system_score_gemma":0.000003548906,"threshold_uncertainty_score":0.999831},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.100224584,0.00009536712,0.88596976,0.00032724222,0.0002481706,0.00011628532,0.012777335,0.00007420725,0.00016707793],"genre_scores_gemma":[0.7326949,0.00002942583,0.2648723,0.000033786502,0.000045942394,0.000033762437,0.0018059406,0.000018826244,0.00046507127],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979524,0.000083059946,0.00033866335,0.0010624115,0.00028063165,0.00028281164],"domain_scores_gemma":[0.99418455,0.00019856551,0.00010232656,0.0052701617,0.00014032342,0.000104068255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002332727,0.00022152533,0.00029202588,0.00007448958,0.00022186466,0.0002669857,0.0028298225,0.00007829855,0.000088574],"category_scores_gemma":[0.000023688748,0.00020415557,0.000064458756,0.00050868595,0.00009732098,0.002242213,0.00033665542,0.00021597004,0.00003197923],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008769757,0.005021908,0.0019225747,0.00017488074,0.00079627277,0.000043540906,0.0020238338,0.009585463,0.0049179774,0.0036118387,0.003961254,0.9678528],"study_design_scores_gemma":[0.0011736405,0.00010129725,0.0057399757,0.00031217356,0.00023368915,0.000017465865,0.00029601637,0.9467992,0.03906717,0.0047532683,0.00088346173,0.00062259944],"about_ca_topic_score_codex":0.0005649258,"about_ca_topic_score_gemma":0.0014609449,"teacher_disagreement_score":0.96723014,"about_ca_system_score_codex":0.000036049558,"about_ca_system_score_gemma":0.0004455495,"threshold_uncertainty_score":0.8325223},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.2083307e-7,0.00003265238,0.48793924,0.00016209252,0.00012765841,0.000051169063,0.0000068755703,0.00015862135,0.51152146],"genre_scores_gemma":[0.00002994213,0.000023595854,0.36640498,0.0005829913,0.00046827554,0.0000067911224,0.00008642916,0.000019697727,0.6323773],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989267,0.0000035064559,0.00021311271,0.0004912915,0.00016737767,0.00019803314],"domain_scores_gemma":[0.99864703,0.000054261865,0.00011716467,0.0010145899,0.0000750951,0.000091859525],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000106800086,0.00019861214,0.00019338136,0.00006375871,0.00013152008,0.00021277388,0.0012531264,0.00014822715,0.0014440352],"category_scores_gemma":[0.0000028854397,0.00018223353,0.000067375135,0.000038731632,0.00007992233,0.00013203656,0.00056785485,0.00013561205,0.0009712479],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.5150822e-7,0.0000033915594,3.481322e-7,0.0000016310469,0.000014267153,0.0000027626425,0.000032719396,0.0000033591716,5.6943657e-7,0.57348996,0.30931187,0.11713895],"study_design_scores_gemma":[0.000039027836,0.000024421763,0.000008474395,0.000027008873,0.000006157821,0.000010443,0.0000019252898,0.19511369,0.0000011125979,0.007296753,0.7972611,0.00020986074],"about_ca_topic_score_codex":0.000005634677,"about_ca_topic_score_gemma":0.000008023726,"teacher_disagreement_score":0.5661932,"about_ca_system_score_codex":0.000019206936,"about_ca_system_score_gemma":0.000034169498,"threshold_uncertainty_score":0.9998066},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018803814,0.00066762883,0.99564296,0.00063488097,0.00043041748,0.00025270824,0.000052246214,0.000088980145,0.00034977493],"genre_scores_gemma":[0.23281857,0.0000056834333,0.7645557,0.0003550176,0.00022432812,0.0014057365,0.00018432963,0.00002075432,0.00042991788],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987356,0.00006976989,0.00031538866,0.00044660494,0.00017232026,0.00026029933],"domain_scores_gemma":[0.9991836,0.00012749764,0.00006892226,0.00047782328,0.000068900525,0.00007325368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042656268,0.00011434888,0.00022244285,0.000059985457,0.00010533884,0.00013271213,0.0003364298,0.00005039998,0.000012374641],"category_scores_gemma":[0.000017872306,0.000113691,0.0000722742,0.00029223794,0.00000906909,0.00023853005,0.00003023214,0.00005470008,0.000012484488],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034308596,0.0029404457,0.017564155,0.00074317853,0.0003816749,0.00075746624,0.031809896,0.008421493,0.0701983,0.07506782,0.062778935,0.72930235],"study_design_scores_gemma":[0.0006374083,0.00005417955,0.0004170364,0.00014944698,0.0000051765287,0.000029232902,0.0004762857,0.9121355,0.0074075297,0.00005075287,0.07839786,0.00023962103],"about_ca_topic_score_codex":0.0011520812,"about_ca_topic_score_gemma":0.00012419844,"teacher_disagreement_score":0.903714,"about_ca_system_score_codex":0.00005328515,"about_ca_system_score_gemma":0.00011854374,"threshold_uncertainty_score":0.46361846},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033930995,0.00008073696,0.9574443,0.007803645,0.00033299738,0.00014101322,0.0000041839694,0.0001400072,0.00012212597],"genre_scores_gemma":[0.365911,0.000005198435,0.6331862,0.0006814078,0.00019136773,0.000013885048,0.0000017471727,0.0000041483117,0.0000049961695],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979434,0.00005236113,0.0002574377,0.0007013393,0.0005609043,0.0004845308],"domain_scores_gemma":[0.99825776,0.0004418388,0.0001572996,0.0008165917,0.00022636238,0.000100137135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010212248,0.00014807943,0.00015825561,0.0002354281,0.00033916434,0.00072052394,0.0021548646,0.00006668767,0.0000073953966],"category_scores_gemma":[0.00045946075,0.00014087821,0.000027173697,0.0029848595,0.00008582936,0.0015579418,0.0012127724,0.00019301623,0.000037777194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.9757544e-7,0.000052177813,0.0023072688,0.0000029176026,0.000003606895,0.0000033120784,0.00341996,0.025884338,0.001080255,0.00042876083,0.00021539586,0.9666013],"study_design_scores_gemma":[0.00017231434,0.00002953436,0.0043249805,0.00002910997,0.0000014518198,0.0000065376,0.0000019792385,0.9804559,0.009487238,0.003401448,0.0019010367,0.00018851452],"about_ca_topic_score_codex":0.00002356766,"about_ca_topic_score_gemma":0.00004538879,"teacher_disagreement_score":0.9664128,"about_ca_system_score_codex":0.0003444571,"about_ca_system_score_gemma":0.0002671275,"threshold_uncertainty_score":0.6948029},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000012756559,0.0003054486,0.9954447,0.00083689427,0.0010746005,0.0005926084,0.00017691505,0.00016693777,0.001400623],"genre_scores_gemma":[0.00016689187,0.00003531675,0.99695694,0.0015075488,0.0004066465,0.000082240425,0.000041734176,0.000040086783,0.0007625717],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963667,0.000013282657,0.00051408075,0.0017470982,0.00064762693,0.0007112599],"domain_scores_gemma":[0.99732774,0.0004627295,0.0002705925,0.0014806284,0.00028183314,0.00017647211],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007157284,0.0005048245,0.0004534235,0.00054214016,0.00046667334,0.0005817367,0.0030215967,0.0002588614,0.000014516876],"category_scores_gemma":[0.00007085749,0.0004982128,0.0001535563,0.0004469181,0.0005223915,0.00065884157,0.000997011,0.00052279036,0.00003725099],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.306704e-7,0.000045779598,0.000002832698,0.000023511075,0.0000113999195,0.000008895599,0.00014399688,0.0028760561,0.0001363676,0.0042578857,0.000455975,0.99203634],"study_design_scores_gemma":[0.00033954476,0.00009386264,0.000047086574,0.00020897118,0.000008410973,0.00010863201,1.947772e-7,0.9406794,0.0005561264,0.025241412,0.03206416,0.00065221917],"about_ca_topic_score_codex":0.000016588023,"about_ca_topic_score_gemma":0.0000076083106,"teacher_disagreement_score":0.99138415,"about_ca_system_score_codex":0.00027582693,"about_ca_system_score_gemma":0.00037504887,"threshold_uncertainty_score":0.999747},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000031370342,0.00019028843,0.9942118,0.00019297127,0.00082161376,0.00032384807,0.000012533712,0.0002539795,0.0039616004],"genre_scores_gemma":[0.07178829,0.00008583587,0.92567927,0.00040708907,0.00044447763,0.00006324691,0.00005026475,0.000056443365,0.0014250606],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99693435,0.000036638892,0.0005086272,0.0013620094,0.00057236955,0.000586027],"domain_scores_gemma":[0.9978188,0.00032300892,0.0002669854,0.0012822839,0.00015854447,0.00015032613],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006557597,0.0003981469,0.00044944082,0.0008631648,0.00033860875,0.0005932325,0.003156594,0.00024193789,0.000025232512],"category_scores_gemma":[0.00008221564,0.00039115341,0.00007734786,0.00079596933,0.00039900737,0.0006305834,0.0012162331,0.0010526747,0.000116960306],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012485835,0.00004001176,0.00016337831,0.000032249693,0.0000071488066,0.00004448235,0.000974031,0.03070766,0.000033277138,0.03470523,0.00007474449,0.9332165],"study_design_scores_gemma":[0.00023681791,0.00015230091,0.00096974586,0.00045848743,0.000006756565,0.00011995954,9.640936e-7,0.93026173,0.000051131457,0.03954106,0.027352605,0.0008484176],"about_ca_topic_score_codex":0.00022170086,"about_ca_topic_score_gemma":0.00011426381,"teacher_disagreement_score":0.9323681,"about_ca_system_score_codex":0.00026287173,"about_ca_system_score_gemma":0.00034303634,"threshold_uncertainty_score":0.999854},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89246124,0.0003244856,0.10589038,0.00014782076,0.00004007947,0.00010552728,0.000001041294,0.00005852076,0.000970879],"genre_scores_gemma":[0.8716641,0.000012096711,0.12818106,0.00006005423,0.000015118111,0.000013186764,0.0000027709605,0.000007642801,0.000043966473],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99867,0.00010039898,0.0002643698,0.0003647149,0.00027438666,0.0003261434],"domain_scores_gemma":[0.99857014,0.0007640961,0.0001822633,0.0003763706,0.00004817975,0.000058969028],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020853798,0.00013277557,0.00015840596,0.00027412755,0.0002587198,0.00011335906,0.00058741844,0.000046188634,0.0000011645415],"category_scores_gemma":[0.00016258965,0.00009180861,0.000030320836,0.0011698323,0.00013532079,0.00022724371,0.00010160542,0.0002720546,4.841225e-7],"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":[0.000017221631,0.00009532826,0.2364764,0.00005342878,0.000025782463,0.00004503778,0.028695513,0.00012634501,0.0009969068,0.017465672,0.000100272126,0.7159021],"study_design_scores_gemma":[0.002897167,0.0023581781,0.7382545,0.0012923861,0.00009162715,0.0004893715,0.06510157,0.17613898,0.0026527431,0.0011115919,0.00801116,0.0016007188],"about_ca_topic_score_codex":0.00034410544,"about_ca_topic_score_gemma":0.00008963524,"teacher_disagreement_score":0.71430135,"about_ca_system_score_codex":0.000006512698,"about_ca_system_score_gemma":0.000028876133,"threshold_uncertainty_score":0.37438464},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47668803,0.00050131144,0.21076639,0.027612392,0.002980761,0.016790757,0.0014611583,0.0005285384,0.26267067],"genre_scores_gemma":[0.5033129,0.00004110417,0.48005787,0.0010606535,0.00022144325,0.0015646429,0.00008099634,0.000038071506,0.013622321],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988573,0.000042652253,0.0002060201,0.00051486446,0.000095357915,0.00028379413],"domain_scores_gemma":[0.99886113,0.00019807079,0.000109236076,0.0007022521,0.000049735198,0.00007957188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027807118,0.00013239664,0.00021869171,0.000045321565,0.00024265835,0.00040533772,0.0010981717,0.00008665387,0.00018331596],"category_scores_gemma":[0.000059869497,0.00011273346,0.000025347801,0.00013149483,0.00006446852,0.00029885836,0.000631811,0.00007538405,0.00003718373],"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":[0.00008105509,0.0003077887,0.0010792074,0.000044374054,0.000081949926,0.0001478599,0.0005799973,0.00025234412,0.0005784337,0.8592745,0.091843285,0.045729194],"study_design_scores_gemma":[0.007736739,0.0027245597,0.08307477,0.00012323882,0.00007019317,0.008687622,0.000098233766,0.49928197,0.0024951205,0.26847717,0.1251629,0.0020674486],"about_ca_topic_score_codex":0.0002467896,"about_ca_topic_score_gemma":0.0000018766161,"teacher_disagreement_score":0.5907973,"about_ca_system_score_codex":0.000016618307,"about_ca_system_score_gemma":0.000023381794,"threshold_uncertainty_score":0.45971373},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056407858,0.0014303921,0.8645071,0.018889297,0.00028023953,0.004020144,0.01441026,0.00068269385,0.039372053],"genre_scores_gemma":[0.15395002,0.0004826672,0.8414566,0.0005631637,0.00027885436,0.0009036704,0.0011486497,0.000028691107,0.0011876737],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99799514,0.000009491925,0.0004012504,0.0011071509,0.0002522584,0.00023473875],"domain_scores_gemma":[0.9969381,0.00017442586,0.0003250919,0.0022906617,0.00015513376,0.000116579635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028222863,0.00019981817,0.0001952399,0.000083911946,0.0004363393,0.00021207324,0.0038587016,0.0000575502,0.000014001505],"category_scores_gemma":[0.000054842818,0.00017398267,0.000017716262,0.0004648357,0.0002208952,0.0016244772,0.0025475514,0.00014045315,0.000006774344],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003358859,0.00009329172,0.00017302652,0.000020318386,0.000020659107,5.995947e-8,0.00021775007,0.000008818382,0.0022887306,0.067835346,0.0021663967,0.92717224],"study_design_scores_gemma":[0.0006323831,0.000039164057,0.0013036005,0.000111604844,0.000032830805,0.000031231786,0.0010064329,0.11406831,0.0010670689,0.0012724572,0.88006306,0.00037184],"about_ca_topic_score_codex":0.0000034723191,"about_ca_topic_score_gemma":0.000034551264,"teacher_disagreement_score":0.92680043,"about_ca_system_score_codex":0.000019093179,"about_ca_system_score_gemma":0.00006437401,"threshold_uncertainty_score":0.7170492},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0059382427,0.000008260469,0.963483,0.0050286124,0.00007108078,0.000030228568,0.0000035546898,0.00017994984,0.025257105],"genre_scores_gemma":[0.10391386,0.0000076126776,0.8922993,0.0008243213,0.00007043651,0.000017489641,0.000010915888,0.0000032846194,0.0028528085],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9996606,0.0000033450467,0.00005241538,0.00011037494,0.00009192391,0.00008130422],"domain_scores_gemma":[0.99971527,0.000017191007,0.00002365064,0.00019779669,0.000021804804,0.000024310328],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009019296,0.000027616392,0.000028714603,0.000016965387,0.00005495372,0.000091777285,0.00027052703,0.000016169399,0.000011483161],"category_scores_gemma":[0.000015713464,0.000024119721,0.000012870276,0.000111115776,0.0000029993955,0.00023540636,0.00005634036,0.000026670594,0.0006220254],"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":[3.8838024e-8,0.00002710334,0.0001263417,4.788562e-7,0.000003072828,4.1817358e-7,0.00007548836,0.000017624474,0.00010664856,0.91951066,0.0027916352,0.07734048],"study_design_scores_gemma":[0.001588201,0.00011870166,0.07269739,0.000028613007,0.000014375154,0.000018446543,0.00008693093,0.07545578,0.016526641,0.46451947,0.3681893,0.0007561294],"about_ca_topic_score_codex":0.000050263476,"about_ca_topic_score_gemma":0.000005751471,"teacher_disagreement_score":0.4549912,"about_ca_system_score_codex":0.000052365664,"about_ca_system_score_gemma":0.00002330414,"threshold_uncertainty_score":0.7995085},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000048814032,0.00023575885,0.9913848,0.0012472614,0.00097628776,0.00021097087,0.000008777631,0.00020026817,0.005687066],"genre_scores_gemma":[0.042974386,0.000034165892,0.9536561,0.0015363862,0.0006962584,0.000017718483,0.000013733605,0.00003607561,0.0010351845],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967936,0.000019606197,0.00041038953,0.0014667335,0.00071344274,0.0005961893],"domain_scores_gemma":[0.99725026,0.0005126747,0.0002629253,0.0016172397,0.00016871306,0.00018821009],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007937732,0.0004253537,0.0004555455,0.00050273014,0.0003041316,0.0008195774,0.00391939,0.00021979275,0.000017385302],"category_scores_gemma":[0.000074000134,0.00039047436,0.000090062924,0.00047635526,0.00059051294,0.00039738306,0.0011457928,0.00048565379,0.000095927746],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.8412515e-7,0.000009689851,0.00002097596,0.000011254577,0.0000057263123,0.000016608534,0.00033927566,0.0014501709,0.00005064178,0.051684305,0.00013786454,0.9462728],"study_design_scores_gemma":[0.00024503915,0.00012706894,0.00012444858,0.0003447519,0.000008908682,0.00007655896,2.498675e-7,0.92288303,0.0007091999,0.04902763,0.025644632,0.00080846593],"about_ca_topic_score_codex":0.000020642152,"about_ca_topic_score_gemma":0.00006440466,"teacher_disagreement_score":0.9454643,"about_ca_system_score_codex":0.0001185617,"about_ca_system_score_gemma":0.00031217374,"threshold_uncertainty_score":0.99985474},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027051829,0.0000284717,0.96742666,0.0033408161,0.000108961365,0.00006809186,0.00007598253,0.00003968001,0.0018595189],"genre_scores_gemma":[0.9141208,0.000037965518,0.08516388,0.00011061945,0.000046685316,0.0000032626735,0.00040690592,0.0000030261845,0.00010686683],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921286,0.000017683129,0.00018863149,0.00031236454,0.00017197966,0.00009645197],"domain_scores_gemma":[0.99956846,0.000042997945,0.000066094646,0.00025928614,0.0000379745,0.00002519923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021483673,0.000064341184,0.00006591775,0.0000981937,0.00007684535,0.00016735165,0.00043848253,0.000021142132,0.000004873675],"category_scores_gemma":[0.000005202444,0.00006577711,0.000007048559,0.0000790648,0.00001262864,0.00042616375,0.00011767062,0.000059988077,0.0000053243084],"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":[0.0000042647116,0.00005585451,0.00032023262,0.0000018558613,0.0000027193978,6.572917e-7,0.00026131407,0.783544,0.000013431303,0.13334978,0.00018145778,0.08226441],"study_design_scores_gemma":[0.00016848007,0.000014712033,0.0003476946,0.000034357654,3.2332653e-7,9.1616675e-7,0.000025709913,0.9916728,0.000003755253,0.005513895,0.0021528979,0.00006442841],"about_ca_topic_score_codex":0.0002591469,"about_ca_topic_score_gemma":0.000052039773,"teacher_disagreement_score":0.887069,"about_ca_system_score_codex":0.000030035051,"about_ca_system_score_gemma":0.000035704918,"threshold_uncertainty_score":0.26823127},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000004618939,0.00009172186,0.073027715,0.00055619,0.0003444545,0.00019949314,0.00015554331,0.00030353593,0.92531675],"genre_scores_gemma":[0.0040161833,0.000013483423,0.030646704,0.00080299634,0.00049800676,0.000036034515,0.00006510794,0.000026395994,0.9638951],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99840736,0.000010685893,0.00035293057,0.0005492414,0.00045069112,0.00022909456],"domain_scores_gemma":[0.9983814,0.000027532638,0.00042862535,0.00090934074,0.00015889632,0.00009422283],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00021129113,0.00022546512,0.00021435575,0.000050243958,0.00014647093,0.000430276,0.0009803518,0.00028575977,0.000009236283],"category_scores_gemma":[0.000020536394,0.00024958045,0.00011461747,0.00003480626,0.0000172637,0.00015758153,0.00016302807,0.00018441303,0.00091435335],"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":[3.6329004e-7,0.000009962255,0.0000016266625,0.0000024943797,0.000022927052,0.0000013214368,0.000014674722,6.304778e-7,0.000013970059,0.84172297,0.014499915,0.14370917],"study_design_scores_gemma":[0.000094978925,0.000037126316,0.00013488681,0.000038597762,0.000036922684,0.000009091607,9.855166e-7,0.0009537128,0.000042160846,0.6362818,0.36207175,0.00029797788],"about_ca_topic_score_codex":0.000023550303,"about_ca_topic_score_gemma":0.000019262496,"teacher_disagreement_score":0.34757182,"about_ca_system_score_codex":0.00047300887,"about_ca_system_score_gemma":0.00011751032,"threshold_uncertainty_score":0.99999565},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008081984,0.0002665011,0.9925238,0.0009580206,0.001159498,0.0005047148,0.0042556296,0.00015236334,0.00017138982],"genre_scores_gemma":[0.0006136235,0.000050748917,0.99332047,0.0011463574,0.0011183172,0.000020634454,0.0034565842,0.000047410187,0.00022588174],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9938982,0.00003125602,0.00071388035,0.0036285303,0.00094267906,0.0007854625],"domain_scores_gemma":[0.98789674,0.0012363266,0.00043739064,0.009949345,0.00023124527,0.0002489713],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0016772508,0.0005795656,0.000667954,0.00043091743,0.00038902476,0.0013070547,0.019953655,0.00028543174,0.000018489485],"category_scores_gemma":[0.00018365399,0.00054622826,0.00007217445,0.00043968958,0.00033258504,0.0010741109,0.010162798,0.00052693876,0.00002933611],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.5789586e-7,0.00002316188,0.000021469335,0.000017083128,0.000025266856,0.000013801893,0.00010284558,0.0018962126,0.0000059496965,0.0015067632,0.0008220288,0.99556464],"study_design_scores_gemma":[0.00026575537,0.000070181675,0.000025241898,0.0003478715,0.00003454831,0.00001464639,3.4921365e-7,0.95019233,0.000050537885,0.023107762,0.025268741,0.00062201207],"about_ca_topic_score_codex":0.00037834028,"about_ca_topic_score_gemma":0.00032596086,"teacher_disagreement_score":0.99494267,"about_ca_system_score_codex":0.00017974623,"about_ca_system_score_gemma":0.0006679474,"threshold_uncertainty_score":0.9997297},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45678708,0.0011065203,0.5389504,0.0011415351,0.00037749895,0.000604018,0.00009665192,0.00017273365,0.0007635816],"genre_scores_gemma":[0.86359024,0.000078680394,0.13558958,0.0001744244,0.000076386925,0.000043684955,0.000051502437,0.000012567542,0.00038290757],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99840605,0.0000588222,0.00030539648,0.0004232639,0.0002426919,0.0005637589],"domain_scores_gemma":[0.9987223,0.00026967714,0.00007781356,0.0006186032,0.00014313437,0.0001684392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085575023,0.00015824096,0.00019853424,0.00014076984,0.00013093498,0.00017657116,0.0008644817,0.000096446005,0.000032615586],"category_scores_gemma":[0.00011633495,0.00015190628,0.00004824858,0.0005081991,0.000063213876,0.0006446952,0.0002926381,0.00018403925,0.00008816061],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009661803,0.0005929152,0.0061218394,0.00014339798,0.000030301682,0.000009866859,0.012123277,0.000016691465,0.0938437,0.09269581,0.006333132,0.7879925],"study_design_scores_gemma":[0.006385418,0.0016610643,0.11110391,0.0013310879,0.00006699095,0.00018755585,0.0039345846,0.42838588,0.16034603,0.0070513687,0.27553114,0.004014991],"about_ca_topic_score_codex":0.00004435785,"about_ca_topic_score_gemma":0.000015891068,"teacher_disagreement_score":0.78397745,"about_ca_system_score_codex":0.000075343065,"about_ca_system_score_gemma":0.00018559324,"threshold_uncertainty_score":0.6194559},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0058222953,0.0002092491,0.9653841,0.020724075,0.00039366688,0.0004169783,0.00007088308,0.00020901387,0.006769692],"genre_scores_gemma":[0.581652,0.00025992203,0.41316596,0.0039208108,0.000116816445,0.00023941536,0.00026784898,0.000047694957,0.0003295116],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99768144,0.00025051154,0.00041719605,0.0008686761,0.00039744575,0.0003847304],"domain_scores_gemma":[0.9944565,0.0005202061,0.00019758804,0.0044093886,0.0001977379,0.00021855065],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025711465,0.0003456533,0.00036233914,0.00018328115,0.00076455233,0.0008157752,0.0026258177,0.00008776183,0.0000146944285],"category_scores_gemma":[0.000008320672,0.00032084988,0.000090187175,0.00068634225,0.00017026394,0.00029329813,0.0009088068,0.0003886734,0.000052951036],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008683974,0.005644227,0.0036198522,0.00017587398,0.0005268726,0.00026758926,0.00501153,0.10086003,0.004913379,0.08441843,0.027185373,0.76729],"study_design_scores_gemma":[0.0011829041,0.0003357917,0.0012102025,0.00032536616,0.00003179166,0.000034316698,0.00010239009,0.9719797,0.0008285714,0.000085209635,0.02336369,0.0005201173],"about_ca_topic_score_codex":0.000111170004,"about_ca_topic_score_gemma":0.0000649422,"teacher_disagreement_score":0.8711196,"about_ca_system_score_codex":0.00006926707,"about_ca_system_score_gemma":0.00019223381,"threshold_uncertainty_score":0.99992436},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003693999,0.0030806407,0.25078973,0.0038687715,0.0014407624,0.000731324,0.0006214263,0.0010741604,0.73802376],"genre_scores_gemma":[0.000092884984,0.000892124,0.08289613,0.00023082524,0.0004232231,0.0000098446535,0.000038542265,0.000021160624,0.91539526],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993432,0.0000046889945,0.00010508744,0.00025769195,0.00019932466,0.00009001571],"domain_scores_gemma":[0.9993086,0.00008004714,0.00014182388,0.00034236474,0.00008636334,0.000040818035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014385213,0.00009733158,0.0001026591,0.000058089525,0.00007876755,0.00033017958,0.00028941742,0.00011717921,0.00002820593],"category_scores_gemma":[0.000028808028,0.00009156754,0.000023857405,0.000023416467,0.000016581396,0.00026588087,0.00016123393,0.00008580758,0.00027618572],"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":[7.313037e-7,0.000012232765,0.00010141174,0.000015889542,0.0001156597,0.0000044309704,0.0003940364,1.6460972e-7,0.000014699645,0.36477682,0.3565423,0.2780216],"study_design_scores_gemma":[0.000036536218,0.000013822073,0.00017859314,0.00002819959,0.00001892225,0.0000027004735,7.769363e-7,0.000886587,0.0000072007433,0.013479768,0.98522335,0.00012356964],"about_ca_topic_score_codex":0.000019041792,"about_ca_topic_score_gemma":0.0000121282355,"teacher_disagreement_score":0.628681,"about_ca_system_score_codex":0.000036117515,"about_ca_system_score_gemma":0.000022844188,"threshold_uncertainty_score":0.3734016},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021211972,0.00003900692,0.9380029,0.0015346362,0.0035013326,0.00024843408,0.05571878,0.000076106924,0.0006667288],"genre_scores_gemma":[0.21629333,0.0005114232,0.5865594,0.0010627215,0.0020635827,0.00028004983,0.19186218,0.000029109073,0.0013381959],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971436,0.00006902122,0.0006013415,0.0010884387,0.0007699579,0.0003276354],"domain_scores_gemma":[0.9935153,0.00031574734,0.00034492006,0.0047686864,0.0008935489,0.00016178726],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0004888961,0.0002455379,0.0003302285,0.0003266646,0.00021341164,0.0022196455,0.0066088405,0.0001418231,0.00007706412],"category_scores_gemma":[0.00078649813,0.00024303913,0.00007452771,0.0010608111,0.000050019527,0.0031519816,0.001975674,0.00027616668,0.00034148025],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021682637,0.00041421386,0.00024291605,0.00005143652,0.001112559,0.000015395959,0.00018909926,0.0004797947,0.00035078806,0.23241054,0.030279826,0.73443174],"study_design_scores_gemma":[0.00033293202,0.000019813362,0.0003816228,0.00008718595,0.00007387741,0.0000070096603,0.00011942045,0.8022205,0.00021686217,0.00037911537,0.19589981,0.00026181186],"about_ca_topic_score_codex":0.0002590388,"about_ca_topic_score_gemma":0.00017367768,"teacher_disagreement_score":0.80174077,"about_ca_system_score_codex":0.000076519944,"about_ca_system_score_gemma":0.00046391657,"threshold_uncertainty_score":0.99881613},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059706517,0.000039965595,0.93835765,0.0001520458,0.000113116,0.00022268144,0.000114242735,0.00010853767,0.0011852632],"genre_scores_gemma":[0.7019633,0.0000017253749,0.29775932,0.00007557604,0.000011002931,0.00010744063,0.00005276924,0.0000055864607,0.000023312157],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984492,0.000036139347,0.00038846364,0.00047502623,0.00043810357,0.00021306759],"domain_scores_gemma":[0.9989743,0.00015594256,0.00018490426,0.00054717495,0.00007813727,0.000059512997],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041689974,0.0001197191,0.00015960881,0.000103860366,0.00033717137,0.00002800693,0.000980115,0.000026856793,0.00003175019],"category_scores_gemma":[0.000015537982,0.00013376524,0.00004352087,0.0006719019,0.00008474396,0.000058771475,0.00070247345,0.00015226172,0.000020813972],"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":[0.0000068501786,0.00018528866,0.000016041276,0.0000087808585,0.0000068047057,5.139289e-7,0.00078899454,0.67903847,0.0011721293,0.21200086,0.00087930466,0.105895974],"study_design_scores_gemma":[0.000057014815,0.000033913264,0.00029183715,0.0000036279494,0.000004479225,0.0000031514242,0.0002574731,0.98213995,0.0018701507,0.014989076,0.00021857611,0.0001307671],"about_ca_topic_score_codex":0.00004206315,"about_ca_topic_score_gemma":6.6201136e-7,"teacher_disagreement_score":0.64225674,"about_ca_system_score_codex":0.00006963898,"about_ca_system_score_gemma":0.00011094108,"threshold_uncertainty_score":0.5454788},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010163329,0.00006089639,0.9635747,0.01989611,0.0014557694,0.0009801891,0.00013190653,0.00034922012,0.0033878456],"genre_scores_gemma":[0.7113921,0.00004412683,0.2813519,0.0013831764,0.001595148,0.00059505284,0.00018437277,0.00003081675,0.0034233013],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99816775,0.000016328047,0.0004808566,0.0005623155,0.00041322637,0.00035954578],"domain_scores_gemma":[0.99860084,0.00010140819,0.00034319208,0.00025843506,0.00062955625,0.000066591296],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004092378,0.00023651353,0.00017791982,0.00008686447,0.00039048123,0.0004610833,0.0012400149,0.00007999549,0.000019911073],"category_scores_gemma":[0.000044337517,0.00018153328,0.000115616895,0.00029744513,0.000104838124,0.0006013109,0.00011456615,0.00024758794,0.00009145278],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019577108,0.0002584319,0.00049100805,0.000010837589,0.0000328013,7.966083e-7,0.000101961785,0.0032623424,0.0038143224,0.910616,0.054250296,0.02714165],"study_design_scores_gemma":[0.00050009304,0.000051434465,0.015220064,0.000060373473,0.000010145083,0.000015239698,0.00001750364,0.9630868,0.00026948002,0.005351336,0.0151950745,0.00022246939],"about_ca_topic_score_codex":0.00004454116,"about_ca_topic_score_gemma":0.00001842252,"teacher_disagreement_score":0.95982444,"about_ca_system_score_codex":0.00007761133,"about_ca_system_score_gemma":0.000055709064,"threshold_uncertainty_score":0.7402712},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09858044,0.0008042508,0.64728034,0.21101731,0.0008985734,0.00054251647,0.000038119368,0.0017680767,0.03907041],"genre_scores_gemma":[0.55039626,0.0001873504,0.42889017,0.005552846,0.00046492703,0.00012248522,0.00003846619,0.000031632204,0.0143158315],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99905163,0.00002327339,0.0001514888,0.0003486132,0.00016995985,0.00025500575],"domain_scores_gemma":[0.9983498,0.00011248059,0.00005053919,0.0013488557,0.000035931836,0.00010243091],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001643895,0.00010408695,0.00009588998,0.00004760577,0.00013438897,0.00014615835,0.001717428,0.000041125684,0.0003508144],"category_scores_gemma":[0.00013561013,0.000097323886,0.000038243586,0.0002859289,0.000033642063,0.00008548848,0.00053790014,0.00009868849,0.003156083],"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":[0.000004684867,0.00019900697,0.000813226,0.000005477675,0.000017952134,0.00012493307,0.00034942347,0.000011450695,0.00093879947,0.03314986,0.30853084,0.65585434],"study_design_scores_gemma":[0.00018057055,0.00002824749,0.0030015826,0.000009199178,0.0000031268949,0.00009535865,0.0000135871605,0.0017600548,0.00038519275,0.0019176089,0.9924314,0.00017406952],"about_ca_topic_score_codex":0.000113138405,"about_ca_topic_score_gemma":0.0000023318887,"teacher_disagreement_score":0.6839006,"about_ca_system_score_codex":0.000014289824,"about_ca_system_score_gemma":0.000023379893,"threshold_uncertainty_score":0.99762005},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020837493,0.000020811496,0.0009732691,0.07838422,0.0116584385,0.0017289362,0.0036766408,0.00024304278,0.88247716],"genre_scores_gemma":[0.993897,0.000013894803,0.0016003565,0.00047757284,0.0015357439,0.00023792546,0.000020207353,0.000026896741,0.0021903527],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.98896533,0.000095115225,0.0016011001,0.0022736439,0.0062677325,0.0007970748],"domain_scores_gemma":[0.99159896,0.000263147,0.002471168,0.0010638224,0.004364565,0.00023834116],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0062001105,0.0006553777,0.000681836,0.0008865875,0.002629264,0.0017006691,0.029786183,0.00013559648,0.00008282912],"category_scores_gemma":[0.00023487573,0.00040504104,0.00032200612,0.003356437,0.0013168589,0.0023568843,0.0064369906,0.00084653246,0.000086328],"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":[0.000091256945,0.00022541104,0.00052057055,0.000054978165,0.000086264794,6.3726935e-7,0.0017588969,0.0006534195,0.00034568066,0.9674945,0.025209239,0.003559155],"study_design_scores_gemma":[0.0009805792,0.0024092367,0.0026578233,0.0019389216,0.000103883525,0.0003279997,0.9167142,0.03524711,0.0014179404,0.003422424,0.03349544,0.0012844789],"about_ca_topic_score_codex":0.00038196333,"about_ca_topic_score_gemma":0.00002839216,"teacher_disagreement_score":0.97305954,"about_ca_system_score_codex":0.0005902211,"about_ca_system_score_gemma":0.00073866517,"threshold_uncertainty_score":0.99984014},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00075657567,0.000025548574,0.97464377,0.0020457923,0.00006974447,0.000049852693,0.000002122579,0.00020884184,0.022197777],"genre_scores_gemma":[0.33377433,0.0000046618034,0.6623369,0.0012750967,0.00005002885,0.000031073996,0.000003502056,0.000005787205,0.0025186278],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994772,0.0000065796607,0.000090794114,0.0001993583,0.00009361067,0.00013246956],"domain_scores_gemma":[0.99940246,0.000022398537,0.000020663572,0.00048499618,0.000014422736,0.000055068045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00004958308,0.00005588442,0.000047738773,0.000033782904,0.00007810449,0.00013725519,0.0005305794,0.000016495298,0.00022708361],"category_scores_gemma":[0.000004521081,0.000047769874,0.000021869215,0.00015214908,0.000013796247,0.00017505263,0.00010658468,0.000039984647,0.00054510165],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.6046533e-7,0.00011293752,0.00018438578,0.0000059745626,0.000004866757,0.000006786729,0.00019652018,0.00015801458,0.00083503517,0.01671469,0.020842116,0.9609385],"study_design_scores_gemma":[0.000102676815,0.000015045129,0.0005585409,0.0000053934245,9.1459776e-7,0.000004058446,0.0000040678706,0.9713961,0.0006347137,0.00010516219,0.027088527,0.00008480862],"about_ca_topic_score_codex":0.000020558158,"about_ca_topic_score_gemma":0.00000439483,"teacher_disagreement_score":0.9712381,"about_ca_system_score_codex":0.000013426457,"about_ca_system_score_gemma":0.000005425134,"threshold_uncertainty_score":0.700636},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033893906,0.00001509956,0.9599735,0.0006335338,0.0003103741,0.00036123578,0.0043000528,0.00023941147,0.0002728588],"genre_scores_gemma":[0.24784623,0.0000029840842,0.7497827,0.0015078182,0.000117761665,0.00015731201,0.00036311665,0.000019376486,0.00020271384],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901134,0.000010059709,0.00041932668,0.00010189867,0.00026702535,0.00019034263],"domain_scores_gemma":[0.99886364,0.00030621112,0.00021742689,0.00041897132,0.000089795336,0.00010393624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040445902,0.000085854845,0.00010106124,0.00008271945,0.0005111407,0.00017322873,0.00057845184,0.00001346476,0.0000018309439],"category_scores_gemma":[0.00037301218,0.00008461687,0.00004035207,0.0004184892,0.00001979692,0.0005609534,0.00046750883,0.000099873345,0.0000047213744],"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":[0.0001275199,0.0032342917,0.1768744,0.0010259871,0.0004878418,0.00005033979,0.048711173,0.30718595,0.0002480218,0.080034554,0.097292185,0.28472775],"study_design_scores_gemma":[0.00029481255,0.000046250898,0.0014561405,0.0000054803063,0.000014188717,0.0000015480149,0.00044513636,0.9753517,0.000014532679,0.00014634393,0.022116182,0.00010766475],"about_ca_topic_score_codex":0.000004182861,"about_ca_topic_score_gemma":4.9307823e-7,"teacher_disagreement_score":0.6681658,"about_ca_system_score_codex":0.000066178254,"about_ca_system_score_gemma":0.00019363074,"threshold_uncertainty_score":0.39313328},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017416138,0.00030995705,0.4696402,0.03559901,0.0016422956,0.002075731,0.00056964316,0.0010363434,0.47171068],"genre_scores_gemma":[0.9542199,0.00037889005,0.035905484,0.0043188995,0.000042726944,0.00066970114,0.0013301814,0.000012362071,0.0031218745],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99799377,0.00017055137,0.0005488129,0.00030181385,0.00075717253,0.00022789191],"domain_scores_gemma":[0.9982147,0.00012280655,0.00038284145,0.0009776468,0.0002099295,0.00009206156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063691253,0.00019948982,0.00017426972,0.00035702795,0.0009874316,0.0006977066,0.0025545312,0.00003971518,0.0005048865],"category_scores_gemma":[0.00003261431,0.00022034107,0.000053810632,0.00035230935,0.00010436324,0.0015841798,0.0023463108,0.0003817965,0.000051671974],"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":[0.000019282994,0.00007898449,0.00021518215,0.000008455189,0.000055905006,0.0000011124507,0.0020727233,0.00018041136,0.0000053826434,0.7834553,0.0099547235,0.20395254],"study_design_scores_gemma":[0.0011317891,0.00016762046,0.002230801,0.000038879316,0.000016709899,0.000017985107,0.005950525,0.5098666,0.000044263048,0.008759734,0.47136834,0.00040677655],"about_ca_topic_score_codex":0.00003837484,"about_ca_topic_score_gemma":0.000008210398,"teacher_disagreement_score":0.93680376,"about_ca_system_score_codex":0.00014680487,"about_ca_system_score_gemma":0.00005384339,"threshold_uncertainty_score":0.8985248},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016177718,0.000056021043,0.98620516,0.0005265629,0.00018181045,0.00018509288,0.000025709414,0.00026578968,0.010936092],"genre_scores_gemma":[0.68417746,0.0000040050677,0.31379983,0.0012922563,0.000033051634,0.0004732675,0.00003711603,0.0000122217,0.0001707799],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984805,0.000028420316,0.0002581139,0.0005678834,0.0003616225,0.00030343258],"domain_scores_gemma":[0.9986641,0.00015629799,0.00009088968,0.00096551416,0.000032037726,0.000091201866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042141444,0.00013827541,0.00012848146,0.000121992736,0.0005279991,0.0001075899,0.0018777208,0.000023327519,0.00025038753],"category_scores_gemma":[0.000014677571,0.00015047731,0.000054329972,0.0010933535,0.0000714427,0.000113342176,0.0006308269,0.00021050204,0.00009602636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005898691,0.00018337555,0.000097061595,0.00000835287,0.000010571242,0.0000071049353,0.0006124726,0.0011660042,0.00052859355,0.34358087,0.0071837613,0.6466159],"study_design_scores_gemma":[0.00017483128,0.00014906614,0.00034133147,0.0000085337,0.000012705744,0.000023418426,0.0009980069,0.6930746,0.018633014,0.037240203,0.2486511,0.0006932268],"about_ca_topic_score_codex":0.00002475329,"about_ca_topic_score_gemma":0.0000018183425,"teacher_disagreement_score":0.69190854,"about_ca_system_score_codex":0.000033173797,"about_ca_system_score_gemma":0.00009041369,"threshold_uncertainty_score":0.6136287},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09710121,0.00033590975,0.89811826,0.002850723,0.00031688667,0.00051947864,0.00029266722,0.0002714243,0.00019346477],"genre_scores_gemma":[0.43629912,0.00013807145,0.5491792,0.0027270769,0.0008061623,0.0017709137,0.0015034131,0.00010650439,0.0074695256],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987822,0.000056093926,0.00018390885,0.00033569508,0.00027215813,0.0003699509],"domain_scores_gemma":[0.9991553,0.00020539788,0.00014581293,0.00031370606,0.000099377154,0.00008040477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049676996,0.000098547745,0.00012217066,0.00011446287,0.00040507474,0.00019403962,0.00071758864,0.00002740749,0.000015993584],"category_scores_gemma":[0.00008461282,0.00011300723,0.00005645174,0.00046188626,0.0000042005436,0.00037390465,0.00027167902,0.00021537277,0.000033789685],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000097155105,0.001835814,0.0009402686,0.000028376278,0.00036290337,0.0000059732247,0.0048780926,0.007708201,0.006576017,0.25585663,0.08616793,0.63554263],"study_design_scores_gemma":[0.00026020833,0.00053360447,0.000264791,0.0000016845601,0.000019546378,0.000005826939,0.00013143022,0.62521744,0.0010365814,0.0045996634,0.36773017,0.00019906428],"about_ca_topic_score_codex":0.000008628489,"about_ca_topic_score_gemma":0.000012515944,"teacher_disagreement_score":0.63534355,"about_ca_system_score_codex":0.0006831455,"about_ca_system_score_gemma":0.00018835108,"threshold_uncertainty_score":0.4608301},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005926109,0.010349607,0.9407019,0.030214552,0.0046320218,0.0013131502,0.00016429425,0.0011263567,0.005571979],"genre_scores_gemma":[0.12494298,0.00032457302,0.39064676,0.005335302,0.003132433,0.0006464633,0.0004665113,0.00030559782,0.47419938],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963616,0.00029533522,0.0006781028,0.0009679904,0.00054544234,0.0011514886],"domain_scores_gemma":[0.9960441,0.00024404892,0.00044003568,0.0023108304,0.00029711175,0.0006638728],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014708572,0.00046818386,0.00046477772,0.00010557108,0.00089169,0.00087643333,0.0021510795,0.00023839847,0.00007615397],"category_scores_gemma":[0.00028163957,0.00044564606,0.00023550996,0.0009836423,0.00032620397,0.00036652878,0.000734877,0.0007415244,0.00017249874],"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":[0.000007789354,0.0002784279,0.0003774023,0.00007120804,0.00013410098,0.00049372,0.023878148,0.000023067418,0.00063252717,0.029943226,0.031397782,0.9127626],"study_design_scores_gemma":[0.00053409574,0.00012038406,0.00038325664,0.0001624869,0.00019919992,0.0004497129,0.0015392029,0.04291317,0.000386918,0.0017858755,0.9508867,0.00063897274],"about_ca_topic_score_codex":0.0002943416,"about_ca_topic_score_gemma":0.00023032282,"teacher_disagreement_score":0.91948897,"about_ca_system_score_codex":0.0008526464,"about_ca_system_score_gemma":0.0022289406,"threshold_uncertainty_score":0.99979955},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9632555,0.00013313147,0.026769124,0.0071495418,0.00017909736,0.0012669694,0.00018904934,0.00018447246,0.00087311916],"genre_scores_gemma":[0.9458161,0.00001119642,0.05325273,0.00062760996,0.0000708322,0.00010158168,0.000067460736,0.000027372487,0.000025093688],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972543,0.000031706575,0.0004831283,0.0012766974,0.0005170105,0.0004371188],"domain_scores_gemma":[0.9971904,0.00010901107,0.00045388416,0.0021303922,0.000046756075,0.00006956317],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0011294024,0.00027556357,0.00038530352,0.00016946591,0.0005375933,0.00034519684,0.009087061,0.000048144866,0.0000010875485],"category_scores_gemma":[0.000033888908,0.0001986365,0.000025820958,0.0008315734,0.00018265887,0.00058576063,0.016668644,0.0004723607,9.1167294e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011037402,0.0031031102,0.04189981,0.0014355548,0.000689591,0.000027122685,0.030534111,0.0066633318,0.3067549,0.36333802,0.012596402,0.23185432],"study_design_scores_gemma":[0.006556501,0.00069292623,0.008267316,0.0005075769,0.00013992295,0.00030657198,0.0040335255,0.9497616,0.006988318,0.013175081,0.007658525,0.0019120777],"about_ca_topic_score_codex":0.00013653866,"about_ca_topic_score_gemma":0.00001639834,"teacher_disagreement_score":0.9430983,"about_ca_system_score_codex":0.000049151553,"about_ca_system_score_gemma":0.00008618745,"threshold_uncertainty_score":0.99627423},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05345312,0.000045106244,0.9435732,0.00085355714,0.00054290565,0.00024182856,0.001111115,0.000095973475,0.000083199484],"genre_scores_gemma":[0.969461,0.0000097091815,0.029665735,0.00016863894,0.000036606914,0.0002822621,0.00021596618,0.0000096587355,0.00015040328],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99860364,0.000066415094,0.00028672456,0.0005217499,0.00028631822,0.00023515841],"domain_scores_gemma":[0.9985892,0.000061912295,0.000045005814,0.0011906686,0.000016727721,0.000096453434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032642332,0.000104313585,0.00012996538,0.00022127992,0.00031886855,0.00014200056,0.00167515,0.000017186536,0.00014355956],"category_scores_gemma":[0.000004593677,0.000118661075,0.000026653299,0.0008632931,0.0000101340165,0.0004026708,0.0002596363,0.00017759796,0.000034798624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030931384,0.0026167617,0.014562035,0.00009706307,0.0002825026,0.00014840424,0.014931456,0.08682054,0.0018417734,0.013740711,0.011508643,0.8534192],"study_design_scores_gemma":[0.00065573136,0.00023078219,0.015414019,0.000078058365,0.000050709223,0.00011422019,0.0076066162,0.8684553,0.0005284515,0.00007735309,0.10602128,0.0007675187],"about_ca_topic_score_codex":0.0034054278,"about_ca_topic_score_gemma":0.00058572495,"teacher_disagreement_score":0.9160079,"about_ca_system_score_codex":0.0001293677,"about_ca_system_score_gemma":0.000056960616,"threshold_uncertainty_score":0.5148011},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.8674233e-7,0.000038039452,0.4052261,0.00035952043,0.00012458429,0.000039843682,0.00013888408,0.0001045509,0.5939683],"genre_scores_gemma":[0.000001360716,0.0000099730705,0.46505508,0.00015203131,0.00024117513,0.0000018184858,0.0006314996,0.0000088849265,0.5338982],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988246,0.0000026746052,0.00019147314,0.0006305271,0.0002376102,0.00011310217],"domain_scores_gemma":[0.9972826,0.00007451614,0.00010556448,0.0024125448,0.000064914,0.000059818853],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00017560417,0.00013645219,0.00011537184,0.000064390784,0.000106828185,0.00012642266,0.0023780847,0.00011491003,0.0012922582],"category_scores_gemma":[0.000014293148,0.00012646295,0.0000246199,0.000029573515,0.000057188263,0.00043160128,0.0017474944,0.000114078575,0.002249983],"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":[8.695253e-8,0.000002280483,4.2725216e-7,0.000001096178,0.000010259082,0.0000012734539,0.000023247878,8.358398e-8,2.4928087e-7,0.61064833,0.32772473,0.06158795],"study_design_scores_gemma":[0.000035074125,0.000010588615,0.000007953928,0.000026184664,0.00000705034,0.000011001486,0.0000013098576,0.049294952,8.093085e-7,0.018250233,0.93219614,0.00015871333],"about_ca_topic_score_codex":0.0000041368585,"about_ca_topic_score_gemma":0.0000062143586,"teacher_disagreement_score":0.6044714,"about_ca_system_score_codex":0.0000143561065,"about_ca_system_score_gemma":0.000100648256,"threshold_uncertainty_score":0.9996207},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.2077173e-7,0.000018968567,0.4459174,0.00017607001,0.00013848531,0.000057943962,0.000012312069,0.00011655373,0.55356187],"genre_scores_gemma":[0.0000038805088,0.000025478921,0.27997857,0.0002991153,0.00016761909,0.000008727238,0.000063460255,0.000009162944,0.719444],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993246,0.0000020868767,0.00013175086,0.00031117088,0.00014474185,0.00008564886],"domain_scores_gemma":[0.999213,0.00002241069,0.000075636606,0.000591402,0.000053697866,0.00004384788],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000065925444,0.00011214063,0.00008819916,0.0000560944,0.00006257137,0.00012495749,0.000549773,0.00008073433,0.0008436196],"category_scores_gemma":[0.0000020840323,0.000101304584,0.000037265494,0.000020412539,0.000032753353,0.00018967806,0.0001953974,0.000071468385,0.00299421],"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":[9.3574656e-8,0.000003177487,1.3276527e-7,0.0000023083514,0.000008105125,0.00000105714,0.00004237906,7.310348e-8,0.000009863472,0.72215897,0.120615385,0.15715843],"study_design_scores_gemma":[0.00004508987,0.000028583334,0.000003766002,0.000024431269,0.0000064947435,0.0000067590363,0.0000030511014,0.0035407504,0.00014007468,0.06584512,0.93016833,0.00018753162],"about_ca_topic_score_codex":0.000007441517,"about_ca_topic_score_gemma":0.0000049406744,"teacher_disagreement_score":0.80955297,"about_ca_system_score_codex":0.000023261742,"about_ca_system_score_gemma":0.000039819814,"threshold_uncertainty_score":0.99778205},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000018046503,0.000030502442,0.45886248,0.00019553916,0.00015534314,0.00004849749,0.000020214828,0.00015536557,0.54053026],"genre_scores_gemma":[0.000036387693,0.000029066716,0.1609177,0.0006343575,0.00029691798,0.000010894448,0.000046536657,0.000022734444,0.8380054],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99894863,0.0000027552637,0.00018930438,0.00049971807,0.00019356777,0.00016600825],"domain_scores_gemma":[0.9986938,0.0000349954,0.00010351761,0.0010221057,0.00006499682,0.00008053883],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00009154187,0.00018736039,0.00015835576,0.00010515024,0.00009384896,0.00018040289,0.0011672929,0.00012362887,0.00091032975],"category_scores_gemma":[0.000002652068,0.0001676362,0.0000766399,0.000036289446,0.000059944246,0.00015309246,0.00043793488,0.000111938694,0.0018151173],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.00330254e-7,0.000006074828,0.0000021642209,0.000005105508,0.000023221806,0.000006795851,0.00015327406,6.9866495e-8,0.000001579777,0.23843266,0.2121622,0.54920673],"study_design_scores_gemma":[0.0000549448,0.00003748727,0.000009857802,0.000055714714,0.000008878694,0.000013969472,0.0000041854573,0.0037327176,0.000014371887,0.026661893,0.9691122,0.00029377776],"about_ca_topic_score_codex":0.000013758337,"about_ca_topic_score_gemma":0.000013467244,"teacher_disagreement_score":0.75695,"about_ca_system_score_codex":0.000012186515,"about_ca_system_score_gemma":0.00003487751,"threshold_uncertainty_score":0.9989621},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.101637e-7,0.000022552658,0.48208973,0.00007300892,0.00073442725,0.000042794756,0.0000037391626,0.00014142947,0.516892],"genre_scores_gemma":[0.0000086036025,0.000053808915,0.12130347,0.00016614955,0.00049024157,0.000002958307,0.000027395352,0.000014012484,0.8779334],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991846,0.0000024169256,0.00015810368,0.0003946547,0.00014678181,0.00011340565],"domain_scores_gemma":[0.9990633,0.000035972193,0.00009251932,0.0006840383,0.00007083985,0.000053294712],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00009694268,0.00013872351,0.000119293356,0.00007731133,0.00008152436,0.00015616413,0.00057864934,0.00012110463,0.0007481502],"category_scores_gemma":[0.000004121067,0.00012914983,0.000054634194,0.000031233834,0.000037348294,0.00017082159,0.00018606099,0.0001446536,0.004887594],"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":[2.5473224e-7,0.000005562066,2.7762027e-7,0.0000028196544,0.000011666013,0.0000022742845,0.000051731276,0.0000014216995,0.000004012403,0.51004624,0.26842102,0.2214527],"study_design_scores_gemma":[0.000023066548,0.000023873696,0.000001525469,0.00003297118,0.000005821272,0.00001592625,0.0000020864504,0.0477224,0.000072600196,0.02447279,0.9274466,0.0001803194],"about_ca_topic_score_codex":0.000018613222,"about_ca_topic_score_gemma":0.00001204621,"teacher_disagreement_score":0.6590256,"about_ca_system_score_codex":0.000028513334,"about_ca_system_score_gemma":0.000044685738,"threshold_uncertainty_score":0.9958872},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000010030852,0.000021042253,0.42630434,0.00020733745,0.00012915146,0.000038611615,0.000014539934,0.00013375377,0.5731502],"genre_scores_gemma":[0.000022045766,0.00001376135,0.15343088,0.0005322963,0.00029439543,0.0000068190957,0.00003129842,0.000016893224,0.8456516],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99910736,0.0000020162286,0.00016042353,0.00042740925,0.00016416221,0.00013864446],"domain_scores_gemma":[0.9988461,0.0000308741,0.000085696025,0.0009156996,0.00005489515,0.000066703535],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00007666694,0.00015585808,0.00013412534,0.0000633995,0.00007343434,0.00016153949,0.0010400628,0.000107237225,0.0012127826],"category_scores_gemma":[0.0000026898242,0.0001393983,0.000052455925,0.00002088782,0.000042337928,0.00013263173,0.00044641132,0.0000931188,0.0030183173],"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":[5.730535e-8,0.0000036757299,9.721823e-7,0.0000033821862,0.000013234944,0.0000049038845,0.00011736925,3.6345263e-8,0.0000010402578,0.18431835,0.20598513,0.60955185],"study_design_scores_gemma":[0.000037520917,0.000026035705,0.000005023355,0.000040420793,0.0000052985947,0.000010658713,0.0000025936122,0.0070204586,0.000011527452,0.009454835,0.98317623,0.00020941599],"about_ca_topic_score_codex":0.000008983346,"about_ca_topic_score_gemma":0.000008671987,"teacher_disagreement_score":0.7771911,"about_ca_system_score_codex":0.000014683496,"about_ca_system_score_gemma":0.000036536097,"threshold_uncertainty_score":0.99970025},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.1521394e-7,0.000016722279,0.5074303,0.00028036884,0.00008724943,0.00003068359,0.000006805083,0.00011556557,0.49203208],"genre_scores_gemma":[0.00008081811,0.0000131034785,0.12474852,0.0007861587,0.0001925165,0.000007975119,0.000034520996,0.000018134057,0.87411827],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99912727,0.000002792729,0.00016639425,0.00040686695,0.00016319688,0.00013348405],"domain_scores_gemma":[0.99884164,0.00004944471,0.000091195485,0.00091354595,0.000035103425,0.000069092115],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00009222471,0.00015807174,0.00015657108,0.00006203585,0.0000635536,0.00015014112,0.0010000978,0.00010495577,0.0002356852],"category_scores_gemma":[0.000003157955,0.00014191172,0.000057750483,0.000016499072,0.000022711565,0.00007038159,0.00036113965,0.00011447721,0.001355256],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.9463867e-8,0.0000011168162,6.4118217e-7,0.0000024763142,0.0000052683695,0.0000015709611,0.000019288509,1.6316439e-7,4.5314505e-7,0.39354363,0.037140083,0.5692853],"study_design_scores_gemma":[0.000040122748,0.000016168824,0.00000591307,0.000036303933,0.000005020709,0.00000861762,8.173727e-7,0.01740842,0.000005213965,0.0051865103,0.9770826,0.00020426135],"about_ca_topic_score_codex":0.000011028794,"about_ca_topic_score_gemma":0.000006384107,"teacher_disagreement_score":0.93994254,"about_ca_system_score_codex":0.000012403679,"about_ca_system_score_gemma":0.00002555935,"threshold_uncertainty_score":0.9994223},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000017040722,0.001297234,0.1036694,0.00009045636,0.0008877151,0.00046123107,0.0025939047,0.0001610118,0.8908374],"genre_scores_gemma":[0.0004030726,0.0035132517,0.07312631,0.0001498437,0.00092033355,0.00006754409,0.002625872,0.00008044744,0.91911334],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978229,0.000022491311,0.000702479,0.00068487035,0.00049693824,0.00027034842],"domain_scores_gemma":[0.9970708,0.0001199723,0.0005112316,0.0019728043,0.0001491308,0.00017605843],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003325817,0.0003435201,0.0005570726,0.00019258945,0.00007578253,0.00008355488,0.0014658438,0.00018557388,0.00010844743],"category_scores_gemma":[0.00003021931,0.0003355847,0.00010952348,0.000084294625,0.00016596628,0.00041179408,0.0003369257,0.00028801648,0.00048165862],"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":[0.0000011846273,0.000034943667,0.0000032802666,0.00013600985,0.00005101633,0.000041269952,0.000069049594,0.0000025968063,0.000023525994,0.79900724,0.072147004,0.12848288],"study_design_scores_gemma":[0.0001995629,0.000056945464,0.0000071400705,0.0005604494,0.00003366259,0.000055704015,0.000010619041,0.0022472823,0.00002074747,0.0011333531,0.9952756,0.00039890083],"about_ca_topic_score_codex":0.00007416547,"about_ca_topic_score_gemma":0.0000038834287,"teacher_disagreement_score":0.9231286,"about_ca_system_score_codex":0.000038205773,"about_ca_system_score_gemma":0.0002726582,"threshold_uncertainty_score":0.99990964},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005210405,0.00020702924,0.9969506,0.0002483844,0.0007842241,0.00028931373,0.000047173027,0.00026369066,0.0006884914],"genre_scores_gemma":[0.03420764,0.000014889115,0.96456546,0.000472507,0.00023716368,0.0000057027814,0.00010497843,0.00004572081,0.00034596265],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952925,0.000031715397,0.00066432275,0.0024251875,0.00088837865,0.00069789676],"domain_scores_gemma":[0.9945025,0.0005193002,0.0004381826,0.004137026,0.00019856311,0.00020443935],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0011785025,0.00052867195,0.0005289564,0.0006325232,0.00053010276,0.00066231494,0.007406285,0.00031667677,0.0000061666756],"category_scores_gemma":[0.00020769534,0.0005051285,0.00007836073,0.00078435463,0.0006048727,0.0008836917,0.005152666,0.0006960083,0.000027931444],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022489903,0.00003081977,0.00008023818,0.000024531631,0.000020421561,0.000021172373,0.0011743857,0.2644558,0.00022353687,0.010995593,0.00007131029,0.7229],"study_design_scores_gemma":[0.00022066849,0.00003740406,0.0000138127225,0.00028340612,0.0000140280845,0.000054521424,3.117447e-7,0.9860438,0.00018661366,0.010691501,0.0018743838,0.0005795255],"about_ca_topic_score_codex":0.000049189257,"about_ca_topic_score_gemma":0.000045966663,"teacher_disagreement_score":0.72232044,"about_ca_system_score_codex":0.00016501576,"about_ca_system_score_gemma":0.00058400095,"threshold_uncertainty_score":0.99974},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000011716238,0.000115609786,0.42288816,0.00006435768,0.000098135366,0.00021023725,0.0013514895,0.0005114787,0.57475936],"genre_scores_gemma":[0.0017344647,0.00001013731,0.9877677,0.00033324197,0.0003219784,0.000019048166,0.00052562455,0.000062589235,0.009225208],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970449,0.00001589241,0.0004535961,0.0016613681,0.00043176772,0.00039246306],"domain_scores_gemma":[0.99221766,0.000049244944,0.00040172282,0.007049541,0.00012560008,0.00015623649],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00037143816,0.0004893869,0.0004394427,0.00007864291,0.00021563677,0.0005415557,0.009078583,0.00024255538,0.000008824189],"category_scores_gemma":[0.000031823463,0.00041388022,0.000039751605,0.000054504962,0.00014971851,0.0006952893,0.0074004326,0.000389392,0.000045760175],"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":[0.000002278144,0.000006511789,0.0000022885176,0.000014833488,0.000044543947,0.000045487388,0.00011250467,5.300855e-8,0.0000025318282,0.5644814,0.0049333214,0.43035427],"study_design_scores_gemma":[0.0004859203,0.00044768953,0.000012694395,0.004137154,0.00040072718,0.001101459,0.00015025157,0.028611206,0.00023398778,0.2531424,0.70792735,0.0033491594],"about_ca_topic_score_codex":0.00030659031,"about_ca_topic_score_gemma":0.0001686578,"teacher_disagreement_score":0.70299405,"about_ca_system_score_codex":0.00009125405,"about_ca_system_score_gemma":0.00042278177,"threshold_uncertainty_score":0.9998313},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000004375534,0.00029964524,0.21913114,0.0015847399,0.0008584802,0.00036300224,0.0000543619,0.0006921093,0.77701217],"genre_scores_gemma":[0.000024191035,0.000014193362,0.35735705,0.0015298929,0.000876683,0.00007059226,0.00013262065,0.00009680487,0.639898],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99576336,0.000070457565,0.0011136908,0.0015209955,0.0007320625,0.0007994172],"domain_scores_gemma":[0.9964152,0.000295832,0.00070095307,0.0018904475,0.00023832644,0.00045922337],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0017014599,0.00068776624,0.00069492235,0.0005611894,0.00027386818,0.0012662616,0.0042568166,0.0013437872,0.00031259438],"category_scores_gemma":[0.00013064951,0.00071565993,0.00028160002,0.00010996614,0.00023874774,0.0016393708,0.0011504603,0.0022266253,0.00028048066],"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":[0.0000016000411,0.0000054305874,0.000001070268,0.000008251467,0.000068172834,0.000009923509,0.00036260576,0.0000014791598,0.00011573502,0.17512396,0.18095347,0.6433483],"study_design_scores_gemma":[0.00017360927,0.000026674456,0.0000067189426,0.00009891587,0.00006644896,0.000050821633,0.000021697453,0.004594728,0.00020422744,0.030440839,0.9635482,0.0007671086],"about_ca_topic_score_codex":0.0000134305765,"about_ca_topic_score_gemma":0.0000055366236,"teacher_disagreement_score":0.78259474,"about_ca_system_score_codex":0.00019105329,"about_ca_system_score_gemma":0.00067094545,"threshold_uncertainty_score":0.9999527},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000082386425,0.000111277324,0.10830769,0.000111208064,0.00052136154,0.00019850867,0.0002430746,0.00019914277,0.89022535],"genre_scores_gemma":[0.4530515,0.000048837337,0.43052104,0.0055287024,0.0022505198,0.00052986597,0.0001798298,0.00028093928,0.10760876],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998155,0.000013025567,0.00044274953,0.0007262924,0.00032110617,0.00034180566],"domain_scores_gemma":[0.9988293,0.000044984758,0.00022115941,0.00069038745,0.00006880242,0.00014533772],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001948476,0.00033030193,0.00031466974,0.00011549191,0.000103569546,0.0002006602,0.0009940959,0.00023976264,0.00004231738],"category_scores_gemma":[0.000010442604,0.0003500105,0.000119057695,0.00003563639,0.00010724022,0.00013012509,0.00041363502,0.00031103144,0.00016448386],"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":[7.2352054e-7,0.000010260041,0.000043433167,0.000006295947,0.000022531343,0.00005533591,0.00012498237,0.0000013967173,0.0000067468495,0.7608064,0.00076396746,0.23815794],"study_design_scores_gemma":[0.00082682644,0.00015330162,0.0010533084,0.0012118735,0.000054042124,0.0005535683,0.000044910907,0.0034927072,0.00011579812,0.8543609,0.13627289,0.0018598709],"about_ca_topic_score_codex":0.0005854586,"about_ca_topic_score_gemma":0.0003462297,"teacher_disagreement_score":0.7826166,"about_ca_system_score_codex":0.00022643096,"about_ca_system_score_gemma":0.00023299578,"threshold_uncertainty_score":0.9998952},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46780038,9.382241e-7,0.5302629,0.0008065289,0.0002598742,0.00076188927,0.00004045051,0.000053837935,0.000013208246],"genre_scores_gemma":[0.96517825,4.323203e-7,0.02382476,0.009783953,0.00015492178,0.0009884095,0.00004199871,0.000019574605,0.000007676522],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995998,0.00053159957,0.0013550805,0.00039449055,0.0011774165,0.0005433719],"domain_scores_gemma":[0.99722266,0.00092463853,0.00024689877,0.0010518556,0.00006873666,0.0004852068],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026473778,0.00024147288,0.000356994,0.0002181124,0.00040365162,0.00037843396,0.0023064835,0.00008371648,0.00012734809],"category_scores_gemma":[0.00034684825,0.00019206585,0.000078352045,0.0009121004,0.0000489469,0.00048562646,0.0016520884,0.0007703539,0.000026278725],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043294116,0.003452926,0.13645382,0.000075868054,0.0001096256,0.0001951516,0.12531145,0.011241585,0.000034348577,0.00024664123,0.0024049527,0.7204303],"study_design_scores_gemma":[0.001014549,0.0007130308,0.02028186,0.000094091665,0.000012690119,0.000018469747,0.006442348,0.9698246,0.0000094157285,0.000011847122,0.0012963323,0.00028075773],"about_ca_topic_score_codex":0.00047060475,"about_ca_topic_score_gemma":0.00033900366,"teacher_disagreement_score":0.958583,"about_ca_system_score_codex":0.00016475376,"about_ca_system_score_gemma":0.00037443213,"threshold_uncertainty_score":0.78322184},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.117247276,0.00040584046,0.87528855,0.0022334608,0.001681363,0.00013085849,0.00015432893,0.0001121984,0.0027461562],"genre_scores_gemma":[0.9840394,0.0016325973,0.011369953,0.0003753964,0.0017705827,0.000078166384,0.00013102223,0.000023753852,0.0005791003],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99711174,0.00013177034,0.0006333863,0.0010209037,0.0005487922,0.000553405],"domain_scores_gemma":[0.9982616,0.00052285346,0.00045568965,0.00046213059,0.00015952544,0.00013825962],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00047782657,0.0003686291,0.00058930845,0.00026742317,0.00046015062,0.00043163195,0.0016124274,0.0002113218,0.00012041058],"category_scores_gemma":[0.00007962351,0.00030226368,0.00029926485,0.00071814616,0.00015281378,0.00078148,0.00043327882,0.00025231572,0.000013296115],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032026488,0.000118948934,0.026160007,0.000002307556,0.0005340946,0.000025017653,0.00096643204,0.0008345952,0.00005063126,0.017109474,0.001324152,0.9528423],"study_design_scores_gemma":[0.00237464,0.00013453326,0.077884324,0.0005982182,0.00038275943,0.0000032083367,0.0012257512,0.89099604,0.000036293568,0.0062696086,0.018575333,0.0015192678],"about_ca_topic_score_codex":0.00013926454,"about_ca_topic_score_gemma":0.00055024924,"teacher_disagreement_score":0.95132303,"about_ca_system_score_codex":0.0001219123,"about_ca_system_score_gemma":0.000070312315,"threshold_uncertainty_score":0.99994296},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050008646,0.000002412096,0.88822895,0.00039057448,0.000088103305,0.00012562996,0.000026283878,0.00015430705,0.1059829],"genre_scores_gemma":[0.3052965,0.0000023517257,0.69365615,0.0004969251,0.000055325614,0.00002306684,0.00010088088,0.000003293953,0.00036551777],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99945855,0.00000963345,0.00012612005,0.00010915192,0.00018347989,0.000113050046],"domain_scores_gemma":[0.99954545,0.000027832148,0.000021548442,0.00027317766,0.0000727655,0.000059192145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017799782,0.000045485896,0.000039661205,0.00005178107,0.00008595781,0.00009305609,0.00043784708,0.00002217215,0.00015348646],"category_scores_gemma":[0.00002015848,0.000039179267,0.000016838896,0.00025578952,0.000032451684,0.0012833568,0.00007822128,0.000060169154,0.00041286013],"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":[0.0000013237509,0.00003938435,0.000023939558,0.0000033348526,0.0000024523288,3.4891812e-7,0.0006716806,0.0000026622283,0.000015555948,0.9638513,0.002439376,0.032948665],"study_design_scores_gemma":[0.0006852538,0.00035282766,0.046348102,0.000014755105,0.000010220469,0.00008695286,0.00023414203,0.64606106,0.0057953685,0.27919018,0.020671261,0.0005498828],"about_ca_topic_score_codex":0.000022794571,"about_ca_topic_score_gemma":6.570829e-7,"teacher_disagreement_score":0.6846611,"about_ca_system_score_codex":0.000016186565,"about_ca_system_score_gemma":0.000059736893,"threshold_uncertainty_score":0.53066194},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000015269476,0.00018040977,0.057140693,0.00014572249,0.00057835423,0.0002436553,0.0017840922,0.00029600417,0.9396158],"genre_scores_gemma":[0.013036983,0.00011713615,0.62135917,0.002699423,0.0015972053,0.00008272289,0.0009559525,0.00018024136,0.35997117],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99773204,0.0000139467065,0.0003917975,0.0011509048,0.00037682505,0.00033448587],"domain_scores_gemma":[0.9961747,0.00006269751,0.00030526746,0.003179548,0.000102242666,0.00017552254],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00009040997,0.00039220724,0.00037447695,0.000066363486,0.00017841089,0.00028602208,0.0041826083,0.00020614681,0.000014309499],"category_scores_gemma":[0.0000213427,0.00040268074,0.00009929335,0.000033046133,0.000097418364,0.00038513975,0.002996382,0.00029001103,0.00039612994],"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":[0.0000051832653,0.000020146912,0.0000043831537,0.000007586432,0.0001076392,0.000114077855,0.00016659909,4.3094616e-7,0.0000023116422,0.69353604,0.12326867,0.18276691],"study_design_scores_gemma":[0.0003597926,0.00007010079,0.00003687162,0.0003044175,0.000044696215,0.00032081053,0.00001593138,0.006318752,0.000012197364,0.014630287,0.97718513,0.0007009855],"about_ca_topic_score_codex":0.000068243666,"about_ca_topic_score_gemma":0.000041076393,"teacher_disagreement_score":0.85391647,"about_ca_system_score_codex":0.00014421901,"about_ca_system_score_gemma":0.0002412846,"threshold_uncertainty_score":0.9998425},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5997924,0.00005872268,0.37546834,0.00028711962,0.00020650159,0.003306929,0.00028947933,0.00029663142,0.020293845],"genre_scores_gemma":[0.89597267,0.00014637297,0.09886558,0.00003150981,0.000077124365,0.00044979196,0.0024203183,0.00003652686,0.002000118],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99806076,0.00004322101,0.00051462546,0.0008231404,0.00039623832,0.00016203702],"domain_scores_gemma":[0.9967302,0.00013883783,0.0004878489,0.0024006804,0.00017417861,0.00006824951],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035282152,0.00022040893,0.0003599409,0.00029610933,0.00014587247,0.00005886379,0.0015476783,0.0000810006,0.0000032770502],"category_scores_gemma":[0.0000073140395,0.00017939678,0.00001708409,0.0006999428,0.00005015346,0.00031492097,0.00031574833,0.00018828311,0.000004803371],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024516828,0.0053547327,0.025372714,0.0014834922,0.0003573225,0.0000023276964,0.0043849675,0.0004841465,0.0007984126,0.012853515,0.0033236279,0.94533956],"study_design_scores_gemma":[0.0006662946,0.0015709276,0.27155355,0.00021141107,0.00010879648,0.0000030045924,0.0011790292,0.71999055,0.0002713794,0.000027759497,0.003983816,0.00043345906],"about_ca_topic_score_codex":0.00019753582,"about_ca_topic_score_gemma":0.000626592,"teacher_disagreement_score":0.9449061,"about_ca_system_score_codex":0.000019891622,"about_ca_system_score_gemma":0.00009477262,"threshold_uncertainty_score":0.73155886},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.286064e-7,0.00004222063,0.3138317,0.00017600918,0.00014773107,0.000045562712,0.000012544138,0.00017412436,0.6855693],"genre_scores_gemma":[0.0000045427537,0.000021158825,0.31003088,0.00025579744,0.00017053094,0.0000056435597,0.000020627775,0.000012122947,0.6894787],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991098,0.000001928063,0.00015748414,0.00042775137,0.00016466659,0.00013834225],"domain_scores_gemma":[0.998832,0.000032105898,0.00008328588,0.00092042313,0.00006142027,0.00007075387],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00008634566,0.00015500629,0.00013551784,0.000097666925,0.00009036748,0.00015020967,0.001052477,0.00011147019,0.0007666822],"category_scores_gemma":[0.0000034071793,0.00013827636,0.00006596149,0.00003816285,0.000061134735,0.00014452399,0.0003652483,0.000092668946,0.0016854431],"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":[7.81137e-8,0.0000026527687,1.9937977e-7,0.0000019082652,0.000010913913,0.0000024109527,0.00006441865,4.1398952e-8,0.000001166998,0.7187646,0.18955962,0.09159198],"study_design_scores_gemma":[0.000034267618,0.000025737463,0.000002417553,0.00003024397,0.0000058904807,0.000009694874,0.0000026262157,0.0019207635,0.000012312558,0.0625749,0.9351852,0.00019593145],"about_ca_topic_score_codex":0.000005155385,"about_ca_topic_score_gemma":0.0000053566914,"teacher_disagreement_score":0.74562556,"about_ca_system_score_codex":0.000010573259,"about_ca_system_score_gemma":0.00003968904,"threshold_uncertainty_score":0.99909186},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000022060965,0.00005765019,0.078037016,0.00020196853,0.0010142722,0.000250313,0.0019481897,0.00028388106,0.91818464],"genre_scores_gemma":[0.008984018,0.000011876038,0.78247416,0.0017111591,0.0013598913,0.00005840606,0.0006113848,0.00012166445,0.20466745],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99781156,0.00001130984,0.00036879865,0.0011390202,0.00034196608,0.00032733975],"domain_scores_gemma":[0.9957107,0.00006743549,0.0003136057,0.003611973,0.000109398614,0.00018690403],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00014302644,0.0003828905,0.00034835556,0.00006244681,0.0001622419,0.0004787192,0.0047264323,0.0003021422,0.000027505577],"category_scores_gemma":[0.00002895661,0.00038537476,0.00009098041,0.00002731572,0.00009946287,0.00037674402,0.0033645576,0.00051058835,0.0004011863],"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":[0.0000033034853,0.0000135028495,0.0000029389798,0.0000061247993,0.000063541585,0.000032649205,0.000072376286,6.971723e-8,0.000022120099,0.85125935,0.011033898,0.13749012],"study_design_scores_gemma":[0.00033275934,0.00005996416,0.000029909457,0.00025773005,0.000059171252,0.0001328797,0.000014720734,0.0037139424,0.000058271835,0.07562034,0.9190103,0.0007100588],"about_ca_topic_score_codex":0.00006865002,"about_ca_topic_score_gemma":0.00013128383,"teacher_disagreement_score":0.9079763,"about_ca_system_score_codex":0.000085738764,"about_ca_system_score_gemma":0.00021512057,"threshold_uncertainty_score":0.9998598},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019780514,0.00020123573,0.98471105,0.009860522,0.000070089605,0.00020163604,0.00060784334,0.000048321268,0.0023212745],"genre_scores_gemma":[0.22028255,0.00085896754,0.77836245,0.00016566413,0.000039879553,0.000020421623,0.000048892554,0.00001857632,0.00020260493],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865824,0.00016170264,0.00033384454,0.00025857397,0.0002936679,0.00029399229],"domain_scores_gemma":[0.99394876,0.0009198689,0.0005760848,0.0041888608,0.000218263,0.0001481651],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0013404243,0.00016530583,0.00017288288,0.00006359065,0.005596771,0.0029721204,0.005000227,0.000025636233,0.0000064414166],"category_scores_gemma":[0.0004306071,0.00010706653,0.000018042088,0.00011254777,0.0004475929,0.00056604337,0.0014004402,0.00049594097,0.000009972704],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009271261,0.00015663389,0.0003255789,0.000013530531,0.00008170773,0.0000143046,0.0025412033,0.000022046015,0.000023099386,0.43896407,0.0059482413,0.5519003],"study_design_scores_gemma":[0.0014148591,0.00084404927,0.013275681,0.0004991471,0.0001186916,0.00078204734,0.0013663943,0.8058097,0.000044009186,0.08010905,0.095012024,0.0007243751],"about_ca_topic_score_codex":0.00009771233,"about_ca_topic_score_gemma":0.00005165714,"teacher_disagreement_score":0.8057876,"about_ca_system_score_codex":0.000023145809,"about_ca_system_score_gemma":0.00013829318,"threshold_uncertainty_score":0.9980629},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004581742,0.0000790558,0.98961073,0.0014021967,0.00045099447,0.00020542978,0.00006264656,0.00033629674,0.0032708964],"genre_scores_gemma":[0.046492912,0.000046438712,0.9475167,0.00035824353,0.00023126182,0.00025225256,0.0009770007,0.000015148915,0.0041100606],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983171,0.000043642918,0.00028726915,0.00083986064,0.0003223774,0.00018970312],"domain_scores_gemma":[0.99840724,0.00006790306,0.0001306807,0.0011238435,0.00020015312,0.00007019704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023523552,0.00018186233,0.00016357018,0.000112050795,0.00014159766,0.00055436563,0.0008580531,0.00016653957,0.00014913699],"category_scores_gemma":[0.000064619926,0.00018748203,0.00008385935,0.00040920448,0.000020685711,0.0005169845,0.0019683857,0.00051118265,0.00009461585],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000048464453,0.0006662008,0.0017606476,0.00016876998,0.00020882921,0.00003072236,0.0009090565,0.005785133,0.0015482722,0.5540395,0.07454917,0.36032885],"study_design_scores_gemma":[0.00016077522,0.000011737737,0.0073141046,0.0001073692,0.000016142121,0.000042016127,0.000034849818,0.9669864,0.00094617717,0.0042526117,0.019644786,0.00048300045],"about_ca_topic_score_codex":0.00023606098,"about_ca_topic_score_gemma":0.00002890499,"teacher_disagreement_score":0.9612013,"about_ca_system_score_codex":0.0000776302,"about_ca_system_score_gemma":0.0004478291,"threshold_uncertainty_score":0.7645295},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014462693,0.0011069695,0.9964091,0.00033576338,0.00022370783,0.00018836193,0.000072462,0.00005814312,0.0014608403],"genre_scores_gemma":[0.009445207,0.00015819073,0.9872443,0.00030925206,0.00079527614,0.00006433081,0.00021123281,0.000029068553,0.0017431165],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99710953,0.00003100174,0.0003308174,0.0018562367,0.00027175358,0.00040064458],"domain_scores_gemma":[0.99692386,0.00057297584,0.00013603408,0.0021911075,0.000057785986,0.000118232914],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00081758294,0.00029667903,0.00032453972,0.0008224104,0.0002430041,0.0009865167,0.003765695,0.00015103644,0.0000014225471],"category_scores_gemma":[0.000053537828,0.0002691655,0.000018114577,0.0015598404,0.0008422177,0.0013628975,0.0049169944,0.00033566388,0.000004626711],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.0561397e-7,0.000030346728,0.00021683867,0.000020784535,0.0000026264534,0.0000028734403,0.000671152,0.000033572844,0.0000059843187,0.0019083259,0.0004289003,0.9966782],"study_design_scores_gemma":[0.00025085974,0.00007789227,0.0037502574,0.0003291721,0.000009639494,0.000047696445,0.0000013106604,0.94935185,0.000036283054,0.017427342,0.0281151,0.0006025894],"about_ca_topic_score_codex":0.00002446834,"about_ca_topic_score_gemma":0.00030589037,"teacher_disagreement_score":0.9960756,"about_ca_system_score_codex":0.000102435726,"about_ca_system_score_gemma":0.00049224735,"threshold_uncertainty_score":0.99997604},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000011634527,0.000032327534,0.22373265,0.000065161505,0.00014200591,0.00014447451,0.0005098507,0.00021371973,0.77515864],"genre_scores_gemma":[0.000030443016,0.00004101425,0.007756975,0.00007292091,0.0001235684,0.0000010151275,0.000020366477,0.000021368623,0.99193233],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.998859,0.000010317292,0.00012485856,0.0005725167,0.00020015563,0.00023315307],"domain_scores_gemma":[0.9983781,0.000056153855,0.00015106899,0.0011625304,0.000099344164,0.00015280135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006251424,0.00024160654,0.00021964192,0.00011621587,0.00017678084,0.00006398805,0.0017108093,0.00019693963,0.0000027242666],"category_scores_gemma":[0.0000033150031,0.00023810515,0.00013106484,0.000007715073,0.00012666492,0.00019623304,0.0009669964,0.00020973566,0.000102281774],"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":[0.0000020899888,0.000002789445,8.649339e-8,0.000007718904,0.000028723263,0.00004928546,0.000008513297,4.656477e-8,0.000007193904,0.8789153,0.0659429,0.05503531],"study_design_scores_gemma":[0.00020000734,0.000020855796,0.0000034740228,0.000090205765,0.000029176279,0.000012420216,0.000001451797,0.00056568126,0.000078584744,0.00013917778,0.9985477,0.00031130284],"about_ca_topic_score_codex":0.000016433718,"about_ca_topic_score_gemma":4.3823803e-7,"teacher_disagreement_score":0.9326048,"about_ca_system_score_codex":0.0000966019,"about_ca_system_score_gemma":0.00009096321,"threshold_uncertainty_score":0.97096455},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.226798e-8,0.000029749268,0.49958903,0.00046518625,0.000083474806,0.00003114894,0.000065731474,0.00008849395,0.49964714],"genre_scores_gemma":[0.000004665104,0.000009503768,0.4495362,0.00021960914,0.00016095475,0.0000021063586,0.00069210446,0.000009487369,0.54936534],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99885094,0.0000036446213,0.00019823918,0.0006017813,0.00023629692,0.00010910941],"domain_scores_gemma":[0.99726,0.000116535164,0.00011198409,0.0024071834,0.000042487092,0.00006185608],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002093471,0.0001382927,0.00013361285,0.00006309166,0.00009311762,0.00011796226,0.0022916908,0.00011259219,0.0002738341],"category_scores_gemma":[0.000016648908,0.00012862634,0.000026973914,0.000023639781,0.000031662956,0.0002368323,0.001429605,0.00013880513,0.001054072],"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":[5.1737363e-8,0.0000012206661,4.779005e-7,0.0000013503844,0.0000070913557,7.1694353e-7,0.00000695077,5.7555786e-7,1.878762e-7,0.7043885,0.12985283,0.16574004],"study_design_scores_gemma":[0.000036582205,0.0000065916443,0.00000909874,0.000023136712,0.0000065563772,0.000008797981,4.291662e-7,0.107203215,3.736822e-7,0.010163906,0.8823896,0.00015172113],"about_ca_topic_score_codex":0.00000502042,"about_ca_topic_score_gemma":0.000004647841,"teacher_disagreement_score":0.7525368,"about_ca_system_score_codex":0.000012224695,"about_ca_system_score_gemma":0.00007170364,"threshold_uncertainty_score":0.99972373},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.771191e-8,0.000019575524,0.5166585,0.00010504344,0.0005451931,0.00003710714,0.0000019578663,0.00013285535,0.48249972],"genre_scores_gemma":[0.000029505218,0.000050762403,0.09735801,0.0002379126,0.00032337947,0.0000033970057,0.000029776213,0.000014825226,0.90195245],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99920106,0.0000033018232,0.00016373087,0.00037656512,0.00014596882,0.00010937948],"domain_scores_gemma":[0.9990614,0.00005645809,0.000098187375,0.0006825243,0.000046278998,0.000055134067],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00011581161,0.00014061117,0.00013827183,0.00007578013,0.000070964066,0.00014569944,0.0005576015,0.00011865312,0.00015777319],"category_scores_gemma":[0.0000048080865,0.00013137488,0.000059901173,0.000024923991,0.000020590422,0.000093548944,0.00015201225,0.0001763139,0.002290691],"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":[8.4533596e-8,0.0000016591107,1.7443075e-7,0.0000019420586,0.0000044954777,7.1416537e-7,0.000008601095,0.0000055359615,0.0000016901068,0.6490585,0.049221426,0.30169514],"study_design_scores_gemma":[0.000023423147,0.000014409638,0.0000017043029,0.000028316425,0.000005266608,0.000012371882,6.625069e-7,0.10262132,0.000032572814,0.013279463,0.8838127,0.0001677686],"about_ca_topic_score_codex":0.000022567285,"about_ca_topic_score_gemma":0.000008996035,"teacher_disagreement_score":0.8345913,"about_ca_system_score_codex":0.000024225143,"about_ca_system_score_gemma":0.00003176073,"threshold_uncertainty_score":0.99848616},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.88027e-7,0.000037904145,0.42637345,0.00023710568,0.00009686143,0.000037531812,0.000006141539,0.00015498528,0.5730556],"genre_scores_gemma":[0.00003647989,0.00002419708,0.22045363,0.0003910388,0.00012718634,0.000007344499,0.000028022132,0.000015552907,0.77891654],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990757,0.0000029807445,0.00017409158,0.00042886968,0.0001737641,0.0001445904],"domain_scores_gemma":[0.9987562,0.000056624245,0.00009401987,0.00097070745,0.000043575426,0.00007889425],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000114712086,0.00016742357,0.00016936702,0.00010130035,0.00008029397,0.0001330158,0.0010615708,0.00011842071,0.00016686364],"category_scores_gemma":[0.0000043876485,0.00015116493,0.00007780521,0.000032804845,0.000035284476,0.00008019259,0.0002940974,0.00012074847,0.00078865804],"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":[4.824955e-8,0.0000012707366,4.3638954e-7,0.0000021985518,0.0000066496914,0.0000012640145,0.000016499282,1.6528949e-7,0.0000010701026,0.75882417,0.03950386,0.20164235],"study_design_scores_gemma":[0.000040505754,0.000017345179,0.0000050606463,0.00002832004,0.000006143433,0.000008487013,8.967477e-7,0.005800652,0.000008884194,0.019013245,0.9748589,0.00021156827],"about_ca_topic_score_codex":0.000007879657,"about_ca_topic_score_gemma":0.000005801879,"teacher_disagreement_score":0.935355,"about_ca_system_score_codex":0.000010040977,"about_ca_system_score_gemma":0.000031485713,"threshold_uncertainty_score":0.99998933},"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.364644e-8,0.000155995,0.39146578,0.0014742108,0.00010929038,0.000051746243,0.0000097738775,0.00012180297,0.6066113],"genre_scores_gemma":[0.000015532014,0.00014738781,0.14992872,0.0002642737,0.00009266464,0.000012420213,0.00015519907,0.0000122616375,0.84937155],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99910337,0.0000035911742,0.00018279068,0.00045596232,0.00015668494,0.00009759175],"domain_scores_gemma":[0.9986036,0.000025359448,0.00008697779,0.0011320804,0.00009741157,0.000054608525],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000077827026,0.00012652318,0.0001272245,0.000050582705,0.00006814482,0.00018174574,0.00069631875,0.00010211789,0.00033839894],"category_scores_gemma":[0.000006175307,0.0001209498,0.00005750378,0.00004182111,0.000020513955,0.00014140164,0.00025258344,0.00012993289,0.001123528],"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":[3.8370697e-8,0.000003562715,5.0113705e-8,0.0000033609858,0.0000062318095,0.0000023555224,0.000009677235,2.5012972e-7,0.000014982756,0.7816376,0.02111005,0.19721185],"study_design_scores_gemma":[0.000022962684,0.000005724353,0.000006917041,0.000034023476,0.0000068466056,0.000009909303,0.0000012538654,0.00442926,0.00012167022,0.027309021,0.96788096,0.0001714637],"about_ca_topic_score_codex":0.000007260304,"about_ca_topic_score_gemma":0.0000035206729,"teacher_disagreement_score":0.9467709,"about_ca_system_score_codex":0.000025057734,"about_ca_system_score_gemma":0.00007649145,"threshold_uncertainty_score":0.99965423},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000017375186,0.00009311218,0.15004677,0.00041403188,0.0002193967,0.00017955538,0.00005715302,0.00025893832,0.8487293],"genre_scores_gemma":[0.0054821884,0.000024013316,0.4754074,0.0038749943,0.0011766555,0.00007080487,0.00003458637,0.000068276386,0.51386106],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998301,0.000008882342,0.00032141924,0.0006652737,0.00037939602,0.0003240191],"domain_scores_gemma":[0.99851733,0.00002163223,0.0001297117,0.0010861193,0.000045232027,0.00019996623],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001027191,0.00031497783,0.00028727527,0.000049294595,0.00013322273,0.0003413825,0.0013798036,0.00020620623,0.000013415687],"category_scores_gemma":[0.0000043162736,0.00031077644,0.00013757816,0.000021984619,0.00005696796,0.000095966614,0.00065730856,0.00029237545,0.00035040133],"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":[9.444233e-7,0.000003521976,9.645756e-8,0.0000033638112,0.000011977995,0.000022470631,0.000014923023,0.000002320665,0.0000013959541,0.66217273,0.0019676215,0.33579865],"study_design_scores_gemma":[0.00013544313,0.000069968715,0.000012906022,0.00009766354,0.000014628589,0.00007369241,6.540853e-7,0.0021855943,0.0000071154477,0.66642225,0.33063158,0.00034852812],"about_ca_topic_score_codex":0.000023129309,"about_ca_topic_score_gemma":0.000017013332,"teacher_disagreement_score":0.3354501,"about_ca_system_score_codex":0.00016426062,"about_ca_system_score_gemma":0.00012762923,"threshold_uncertainty_score":0.99993443},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000024300482,0.00011467704,0.1838161,0.00006832058,0.00042011074,0.00015338397,0.0010366386,0.0002516436,0.8141367],"genre_scores_gemma":[0.004281858,0.000027257025,0.6637907,0.0015517364,0.0010627841,0.000085011874,0.0011657769,0.0001129318,0.32792196],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980657,0.000008959679,0.00035215254,0.000943537,0.0003565688,0.0002730987],"domain_scores_gemma":[0.9964666,0.000034373435,0.00024544532,0.0029900586,0.00010718171,0.00015633779],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001577922,0.00030434068,0.00026392873,0.000065985194,0.00015140547,0.00017354357,0.003249084,0.00020258225,0.00003171868],"category_scores_gemma":[0.000019237166,0.00031150924,0.00005970989,0.00003642015,0.000064822525,0.00026547554,0.0017122977,0.00017089072,0.000416608],"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":[9.746302e-7,0.0000061864707,0.0000019520794,0.0000043068617,0.0000324352,0.000016671733,0.000062768064,8.4873314e-8,6.7669805e-7,0.86336327,0.023372699,0.11313796],"study_design_scores_gemma":[0.00021831386,0.0000465611,0.000025325926,0.00014581383,0.00005141619,0.00006562908,0.000009452257,0.0046799,0.000009057377,0.20366399,0.7904776,0.00060695],"about_ca_topic_score_codex":0.00008569499,"about_ca_topic_score_gemma":0.0000475466,"teacher_disagreement_score":0.76710486,"about_ca_system_score_codex":0.00007012917,"about_ca_system_score_gemma":0.00020187646,"threshold_uncertainty_score":0.9999337},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004087706,0.00036423802,0.014690323,0.00009770366,0.00044088505,0.00025338941,0.002305555,0.0003488186,0.9814582],"genre_scores_gemma":[0.1074452,0.000057983252,0.20010613,0.005193293,0.0014911992,0.00011208333,0.00037983438,0.00024868373,0.6849656],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99815303,0.000010673388,0.00033653277,0.0008129217,0.0003423224,0.0003445025],"domain_scores_gemma":[0.99802816,0.000017197337,0.00022480924,0.0014342305,0.0000831991,0.00021237646],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000064136366,0.00042637676,0.00035587727,0.000048321548,0.00015451676,0.00023066124,0.0019803264,0.0004153626,0.00006025365],"category_scores_gemma":[0.0000058180844,0.00040612603,0.00013048213,0.000033607546,0.00010930268,0.0001290231,0.00058961275,0.000337158,0.0003204845],"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":[0.0000012202854,0.0000057263323,0.0000016948749,0.0000067125484,0.000026121814,0.000013566267,0.00003169722,1.0876686e-7,0.00007011565,0.88112485,0.028354546,0.090363644],"study_design_scores_gemma":[0.00018679295,0.00005566033,0.000011244913,0.000045770248,0.000030355277,0.000047251848,9.5226216e-7,0.00042144317,0.00008645712,0.34848276,0.6501364,0.00049489323],"about_ca_topic_score_codex":0.0000645582,"about_ca_topic_score_gemma":0.0000322053,"teacher_disagreement_score":0.6217819,"about_ca_system_score_codex":0.000096839154,"about_ca_system_score_gemma":0.0002158036,"threshold_uncertainty_score":0.99983907},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.4331323e-8,0.000050942734,0.4758189,0.00026601055,0.0001355417,0.000033967204,0.0000024781705,0.00013170976,0.5235604],"genre_scores_gemma":[0.000007932515,0.000011262443,0.3421289,0.00071823737,0.00042166357,0.000005788912,0.000020677864,0.000012978895,0.6566726],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991013,0.0000033666631,0.00017260393,0.00039593448,0.00014981661,0.00017701731],"domain_scores_gemma":[0.99881935,0.000071497714,0.000098675104,0.00090479886,0.00003457745,0.00007108074],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00013946397,0.00015845719,0.00017168853,0.00003578768,0.00009801885,0.00014772349,0.0009891851,0.00011763464,0.00015653273],"category_scores_gemma":[0.000003598463,0.00014385371,0.00005270229,0.000028268878,0.000025382466,0.00006496812,0.00038569243,0.00012410714,0.00091666717],"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":[4.421648e-8,6.193603e-7,2.3693676e-7,0.0000013070862,0.000004462411,9.376545e-7,0.000007886796,0.0000046873197,8.28195e-8,0.6549177,0.1798136,0.16524842],"study_design_scores_gemma":[0.000029748671,0.000014674856,0.000002626178,0.00003716441,0.000005404164,0.0000063903103,3.4786805e-7,0.017478973,5.453933e-7,0.042313118,0.93992835,0.00018266597],"about_ca_topic_score_codex":0.0000038980897,"about_ca_topic_score_gemma":0.0000035081648,"teacher_disagreement_score":0.7601147,"about_ca_system_score_codex":0.000011843368,"about_ca_system_score_gemma":0.000032058986,"threshold_uncertainty_score":0.99986124},"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.471896e-7,0.000097371834,0.3649797,0.0001150399,0.00019795992,0.00004919708,0.000023855218,0.000120542165,0.63441604],"genre_scores_gemma":[0.0000128945985,0.00003898953,0.0717081,0.00012427589,0.0003685639,0.000007861212,0.000034242265,0.000015277566,0.9276898],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99917567,0.000002325751,0.0001477712,0.00043535608,0.000110047244,0.00012883832],"domain_scores_gemma":[0.9987541,0.00003518077,0.000063574,0.0010296922,0.000058615205,0.000058827092],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00007217828,0.00016063607,0.00014050659,0.00006661354,0.0000758103,0.00028869766,0.0011299856,0.00010732692,0.00043168335],"category_scores_gemma":[0.000003166452,0.00013408944,0.000068221314,0.000029797751,0.00006714393,0.00037059307,0.0006033905,0.0001123484,0.006101493],"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":[7.2848074e-8,0.0000059620215,6.027178e-8,0.0000026518244,0.000007863807,9.474552e-7,0.00003563477,1.243386e-8,0.0000011184004,0.78550404,0.15418763,0.060253993],"study_design_scores_gemma":[0.000030420897,0.000021927224,0.000002586402,0.00003056389,0.000005319189,0.0000054080724,9.729569e-7,0.0018216796,0.00002081631,0.06424026,0.93363464,0.0001854253],"about_ca_topic_score_codex":0.0000038361695,"about_ca_topic_score_gemma":0.000009783091,"teacher_disagreement_score":0.77944696,"about_ca_system_score_codex":0.000022601254,"about_ca_system_score_gemma":0.00008331527,"threshold_uncertainty_score":0.99467236},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013437516,0.00013103896,0.9947237,0.0015898495,0.0015032393,0.00075592153,0.00009043438,0.00018519489,0.00088626647],"genre_scores_gemma":[0.015574199,0.000019580883,0.9798584,0.0030730912,0.00062835345,0.0000959547,0.00012397286,0.000053663658,0.00057277083],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99623305,0.00003257484,0.00057847146,0.0017561442,0.0006901041,0.00070963986],"domain_scores_gemma":[0.9972416,0.00039709726,0.00034766996,0.001449566,0.0003878393,0.00017621116],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00070916134,0.0005212175,0.00047232988,0.00050121924,0.00042721708,0.0008280846,0.0028033238,0.000357191,0.00001650223],"category_scores_gemma":[0.00006979797,0.0005091581,0.00014279256,0.0005500585,0.00040088026,0.0006225271,0.0007861682,0.0004912558,0.00002338603],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000044089434,0.000047835572,0.00002005468,0.000041464715,0.000019246834,0.000019259685,0.0005542451,0.0034277805,0.00065619434,0.0048363823,0.00041071084,0.9899624],"study_design_scores_gemma":[0.0005388414,0.00021686779,0.00008625733,0.0002962631,0.000022319533,0.0000797897,2.7912427e-7,0.96433604,0.0008695157,0.025532207,0.007266605,0.0007550007],"about_ca_topic_score_codex":0.000018754652,"about_ca_topic_score_gemma":0.00009405538,"teacher_disagreement_score":0.9892074,"about_ca_system_score_codex":0.00022212017,"about_ca_system_score_gemma":0.0005184613,"threshold_uncertainty_score":0.999736},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000031281293,0.00015815526,0.068420105,0.0003522417,0.00015773851,0.00021387824,0.00078256446,0.00037589768,0.9295363],"genre_scores_gemma":[0.010240241,0.0000075495464,0.78411025,0.0067860372,0.0013433243,0.000075821656,0.0008276342,0.00012656269,0.19648257],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99785674,0.0000069892203,0.00032954637,0.001052406,0.0004371125,0.0003172139],"domain_scores_gemma":[0.99647295,0.000032067008,0.00023327234,0.0029983993,0.00010001414,0.00016332052],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00015422307,0.00034727092,0.0003089203,0.000056315046,0.00014782172,0.00030394824,0.0041436423,0.00021983362,0.000009579637],"category_scores_gemma":[0.00001716119,0.00034979323,0.00006811953,0.00004200503,0.0000642728,0.00019051941,0.00061521464,0.00020447873,0.00018532391],"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":[0.0000012505066,0.000008863,8.6958505e-7,0.000010551187,0.00001373446,0.000023296723,0.000013994026,0.0000031402258,7.74429e-7,0.6438278,0.008201743,0.34789395],"study_design_scores_gemma":[0.0004907657,0.00015729548,0.000026745245,0.0005021157,0.000089398374,0.00007048337,0.0000064848227,0.055599168,0.000036583402,0.37834728,0.56345016,0.0012235333],"about_ca_topic_score_codex":0.000014420887,"about_ca_topic_score_gemma":0.00001747879,"teacher_disagreement_score":0.73305374,"about_ca_system_score_codex":0.00006932085,"about_ca_system_score_gemma":0.00049052876,"threshold_uncertainty_score":0.9998954},"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.0828316e-7,0.000020241776,0.29715338,0.0004052287,0.00011713506,0.000047520596,0.000023007688,0.00017603449,0.70205694],"genre_scores_gemma":[0.0000075412677,0.0000152548155,0.24676685,0.00025277623,0.0002263966,0.000005183815,0.00003511708,0.0000108756085,0.75268],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990572,0.0000031828702,0.00017966078,0.0004548582,0.00017149163,0.00013361375],"domain_scores_gemma":[0.9985908,0.000038460385,0.000097234755,0.0011290708,0.00007097082,0.0000734395],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00015016971,0.00014671774,0.00014528769,0.000050998802,0.000088501525,0.00013923946,0.0010060514,0.000119861455,0.0007073204],"category_scores_gemma":[0.000006322402,0.00013143224,0.000053972122,0.00002665725,0.000060126575,0.00014019986,0.00043790875,0.000096374715,0.0013828062],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.00046776e-7,0.0000027388146,1.6615739e-7,0.0000023641092,0.0000079255005,0.0000018590325,0.000059016296,3.4394255e-8,7.1780676e-7,0.64954114,0.2507584,0.09962551],"study_design_scores_gemma":[0.00002919838,0.000019736459,0.0000052672353,0.00002610856,0.0000050673475,0.00000732428,0.000002036721,0.003980792,0.000010139433,0.0413897,0.95435196,0.00017266106],"about_ca_topic_score_codex":0.000017277873,"about_ca_topic_score_gemma":0.000012109606,"teacher_disagreement_score":0.70359355,"about_ca_system_score_codex":0.000020229354,"about_ca_system_score_gemma":0.000055041135,"threshold_uncertainty_score":0.9993947},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000024507328,0.0016104514,0.072896324,0.00012222573,0.001313587,0.00051160745,0.0025779726,0.00018693722,0.92077845],"genre_scores_gemma":[0.00014134619,0.0019514505,0.08823866,0.000091202375,0.0013876074,0.00006232933,0.002695636,0.000080475475,0.9053513],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974179,0.000029162018,0.00078588404,0.00084397953,0.00061842107,0.00030460925],"domain_scores_gemma":[0.9963802,0.000103003615,0.0006301028,0.0025531787,0.0001415703,0.00019192215],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027457683,0.00043581854,0.0006438201,0.00024221899,0.000093039096,0.00010647984,0.0018359205,0.0002725062,0.0000651486],"category_scores_gemma":[0.000030019666,0.00039979207,0.00015057283,0.00011410887,0.00008437067,0.00045326466,0.0003946262,0.0003884347,0.00021790374],"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":[0.0000024564558,0.00002922922,0.0000032116873,0.00012408785,0.00006402218,0.000039434686,0.000094545336,0.0000037444968,0.000045324592,0.57198924,0.14390586,0.28369886],"study_design_scores_gemma":[0.0001875696,0.000052579668,0.000027175623,0.00034753978,0.00004366629,0.000038569542,0.000010066684,0.003216267,0.000016027785,0.0017373024,0.99388206,0.0004411739],"about_ca_topic_score_codex":0.00007284664,"about_ca_topic_score_gemma":0.000022931987,"teacher_disagreement_score":0.8499762,"about_ca_system_score_codex":0.00004161792,"about_ca_system_score_gemma":0.00021758875,"threshold_uncertainty_score":0.9998454},"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.9858783e-8,0.000050554663,0.4027026,0.00034720657,0.000086976346,0.00006370672,0.000007459591,0.00014954664,0.5965919],"genre_scores_gemma":[0.000049767623,0.000112936854,0.11938039,0.0001783528,0.00007484236,0.000016309727,0.000054987737,0.000014992477,0.8801174],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991808,0.0000025930822,0.00018458515,0.00040711608,0.00012068468,0.000104237966],"domain_scores_gemma":[0.9986304,0.000015130706,0.000109478424,0.0011202688,0.000065262975,0.000059482845],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00008691483,0.00013598552,0.00011499229,0.00006813835,0.000063572974,0.0000831303,0.0009497049,0.00010990894,0.000386252],"category_scores_gemma":[0.0000032573098,0.0001221499,0.00004912336,0.00002700849,0.000029304949,0.0001740805,0.00020750557,0.00012086494,0.0035154268],"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":[8.913773e-8,0.0000035569947,6.9419876e-8,0.0000022170773,0.0000048407232,6.125541e-7,0.000023298131,3.1356127e-8,0.0000041151843,0.7415549,0.018386137,0.24002013],"study_design_scores_gemma":[0.00001986013,0.000010591357,0.000012049593,0.00001829716,0.0000065455715,0.000004920515,3.468588e-7,0.0011233819,0.00006983311,0.16741838,0.83115065,0.00016515901],"about_ca_topic_score_codex":0.000020474074,"about_ca_topic_score_gemma":0.000003038386,"teacher_disagreement_score":0.8127645,"about_ca_system_score_codex":0.000018236098,"about_ca_system_score_gemma":0.000040000912,"threshold_uncertainty_score":0.99726045},"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.4456009e-8,0.000028449786,0.39693463,0.0028183348,0.00017823128,0.00003542546,0.0000034461725,0.00013841431,0.59986305],"genre_scores_gemma":[0.0000012857258,0.00009492514,0.09603839,0.0001545596,0.0010862766,0.0000051038182,0.00004360165,0.000009042365,0.9025668],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99932134,0.0000013434263,0.00011449321,0.00035773005,0.000119193486,0.000085917985],"domain_scores_gemma":[0.99909574,0.000009176785,0.000053871252,0.00076123275,0.000039938084,0.00004006781],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00005476362,0.00010524665,0.000092007045,0.000060134542,0.000052166783,0.00009679263,0.0005278531,0.00007926612,0.00089426443],"category_scores_gemma":[0.0000025605184,0.00009596627,0.000036854624,0.000029395609,0.000018881381,0.00015312323,0.00015830838,0.00011815633,0.002172243],"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":[3.889247e-8,0.0000018358288,2.36946e-8,6.0415886e-7,0.0000031196462,9.543415e-7,0.000003064931,3.1237883e-7,0.0000010326012,0.61562973,0.18021785,0.20414142],"study_design_scores_gemma":[0.000018936855,0.000009933858,0.0000012262344,0.0000039488823,0.0000033647618,0.000022996495,3.626362e-7,0.001915089,0.000008368295,0.04601097,0.9518926,0.000112197085],"about_ca_topic_score_codex":0.0000054968514,"about_ca_topic_score_gemma":0.0000020629825,"teacher_disagreement_score":0.77167475,"about_ca_system_score_codex":0.000020723233,"about_ca_system_score_gemma":0.000022803217,"threshold_uncertainty_score":0.99860466},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8694665,0.00039073982,0.123744875,0.00020672158,0.00016480667,0.00014422633,0.0017407855,0.00010070209,0.004040689],"genre_scores_gemma":[0.935253,0.000042784424,0.06318785,0.00006154334,0.0001292234,0.000007350239,0.0009886516,0.000010698565,0.00031888654],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861914,0.000036182606,0.0002735557,0.0006248115,0.00018429542,0.00026203273],"domain_scores_gemma":[0.9985238,0.00007343256,0.0001332224,0.0011404972,0.00003878451,0.00009030318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027387575,0.00018387428,0.0002298507,0.0001093448,0.00014858629,0.00031577892,0.0012297815,0.000043772718,0.000004199612],"category_scores_gemma":[0.000020349586,0.00015435244,0.000024707802,0.00027689352,0.000081597434,0.0017388839,0.00077287946,0.00007971603,0.0000046102377],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000291901,0.00043236584,0.0089327255,0.000056393015,0.00008113572,0.000022908755,0.0040574404,0.0000029017367,0.0034282077,0.0028663203,0.0073604225,0.97273],"study_design_scores_gemma":[0.009974956,0.003847947,0.12626189,0.003212299,0.00052259397,0.0005780154,0.019054487,0.79071313,0.013947664,0.00026262293,0.027688382,0.0039359764],"about_ca_topic_score_codex":0.00004097932,"about_ca_topic_score_gemma":0.00018500937,"teacher_disagreement_score":0.968794,"about_ca_system_score_codex":0.000014884667,"about_ca_system_score_gemma":0.00014111797,"threshold_uncertainty_score":0.629431},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000023420023,0.0037423512,0.1282491,0.0001647237,0.0012653377,0.0005603038,0.01150408,0.00011714868,0.8543946],"genre_scores_gemma":[0.000088210865,0.0060705636,0.24388143,0.0001385026,0.0019581567,0.000049159768,0.023592442,0.00011865753,0.72410285],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970534,0.0000298884,0.0007923034,0.0011860502,0.00062214484,0.0003162315],"domain_scores_gemma":[0.99289155,0.00020288366,0.00074480096,0.0058401255,0.00014236705,0.00017827963],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00054252107,0.00040569287,0.0006242467,0.00023251958,0.00010797997,0.00010881661,0.0046805516,0.00019141928,0.000034626442],"category_scores_gemma":[0.0000640701,0.00040186627,0.0000799224,0.0001177752,0.00007913236,0.0009667523,0.001911012,0.00030393022,0.00023055427],"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":[0.0000034803772,0.000069442096,0.0000058471023,0.00026256675,0.00016860901,0.00011242331,0.00034733035,0.000007216022,0.000032646396,0.30665553,0.42774072,0.2645942],"study_design_scores_gemma":[0.00015700361,0.000048052665,0.000006006734,0.00065960636,0.0000647903,0.000041475803,0.00004602781,0.008391462,0.0000057181346,0.00020673059,0.9899256,0.00044748173],"about_ca_topic_score_codex":0.0001408835,"about_ca_topic_score_gemma":0.000010580903,"teacher_disagreement_score":0.56218493,"about_ca_system_score_codex":0.00003907887,"about_ca_system_score_gemma":0.0002857275,"threshold_uncertainty_score":0.9998433},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022160228,0.0010517694,0.97383106,0.00010526374,0.001999658,0.00008750457,0.00002025162,0.000015641657,0.0007285989],"genre_scores_gemma":[0.8596598,0.000012419465,0.14013876,0.000016194097,0.0001397559,0.000005881149,0.000006873857,0.0000053878084,0.000014959524],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99818677,0.00006347864,0.0008322149,0.00018164763,0.0006276952,0.000108209024],"domain_scores_gemma":[0.99789864,0.0002559332,0.00067375344,0.00012570767,0.0009645017,0.00008143873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000252623,0.00012141259,0.00022846281,0.00022714246,0.00006285664,0.00011306724,0.00091081037,0.00004011763,0.000018521096],"category_scores_gemma":[0.000047714915,0.00011346745,0.00007210392,0.00015142516,0.0001030982,0.000840224,0.00021307207,0.00013044673,0.000008098649],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00062980264,0.0017160872,0.0029106273,0.000056748846,0.0010873551,0.00009080906,0.038055852,0.28763852,0.0011353758,0.5755897,0.001950043,0.08913903],"study_design_scores_gemma":[0.00041146524,0.0004995081,0.0018848503,0.00017314976,0.000011570958,0.00033583955,0.0022128168,0.98481935,0.0049215523,0.003960438,0.00059793686,0.00017152891],"about_ca_topic_score_codex":0.00006502239,"about_ca_topic_score_gemma":0.0000010005202,"teacher_disagreement_score":0.83749956,"about_ca_system_score_codex":0.00008440911,"about_ca_system_score_gemma":0.00009620983,"threshold_uncertainty_score":0.46270683},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.061018e-8,0.00007392402,0.47942433,0.00014872265,0.00012765611,0.000037338235,0.000010652468,0.000099494326,0.5200778],"genre_scores_gemma":[0.000046144472,0.000036086443,0.055361934,0.00017853394,0.00023412213,0.000008941693,0.000036736823,0.000015946289,0.94408154],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99919564,0.0000032248327,0.00015328832,0.00041439492,0.000109400884,0.00012403377],"domain_scores_gemma":[0.9987502,0.00005642374,0.00006766564,0.0010272758,0.00003745355,0.000060944636],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0000868989,0.00016292543,0.00016407722,0.000065190834,0.00006557316,0.00026831857,0.0010865774,0.000105040395,0.00008368728],"category_scores_gemma":[0.000003720004,0.00013651385,0.00007512929,0.000023520366,0.0000359561,0.00019652833,0.00048793928,0.00013821576,0.0027431967],"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":[4.405889e-8,0.000003224547,7.099009e-8,0.0000034607601,0.0000055730193,5.404766e-7,0.000010415226,9.995925e-8,8.6825105e-7,0.7696135,0.051191263,0.17917097],"study_design_scores_gemma":[0.00003440926,0.000014379388,0.0000032244855,0.000029016453,0.000005329724,0.0000046206774,3.2372444e-7,0.0048235087,0.000009951142,0.03818558,0.95669836,0.00019128133],"about_ca_topic_score_codex":0.0000047078224,"about_ca_topic_score_gemma":0.0000071976274,"teacher_disagreement_score":0.9055071,"about_ca_system_score_codex":0.000019074401,"about_ca_system_score_gemma":0.00005822989,"threshold_uncertainty_score":0.9980333},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.2316164e-8,0.000024752615,0.5273872,0.0002453055,0.000039624392,0.000026557598,0.0000125286215,0.00010221857,0.47216174],"genre_scores_gemma":[0.00008827521,0.000028976534,0.15149161,0.0004627402,0.00010705239,0.000006980655,0.00009692936,0.000010156341,0.8477073],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990182,0.000004271377,0.00019179577,0.00047747916,0.00018296926,0.00012527629],"domain_scores_gemma":[0.9983901,0.00005356296,0.00010689271,0.0013187717,0.000053913605,0.000076762604],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001279988,0.00015843117,0.00026394293,0.0002296586,0.00006340011,0.00014966146,0.0010582177,0.00012313818,0.00036528124],"category_scores_gemma":[0.0000038219096,0.00013687968,0.0001850304,0.0001157959,0.000031784846,0.00007236238,0.00030822793,0.00013117131,0.00117292],"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":[4.6043596e-8,0.0000022143938,0.0000014028506,0.0000015354826,0.00012654199,0.0000012808559,0.000006172959,0.000004952221,3.7338978e-7,0.8672999,0.016109018,0.11644653],"study_design_scores_gemma":[0.000025250836,0.0000107679425,0.000027663478,0.0000065873837,0.00015342105,0.0000021259902,3.8147348e-7,0.04495976,0.0000039277547,0.021031205,0.9335587,0.00022018442],"about_ca_topic_score_codex":0.00003590119,"about_ca_topic_score_gemma":0.000030324209,"teacher_disagreement_score":0.9174497,"about_ca_system_score_codex":0.000016826258,"about_ca_system_score_gemma":0.00003195152,"threshold_uncertainty_score":0.99960476},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.55202e-9,0.000014613845,0.5170084,0.0005620393,0.000051843148,0.00004630971,0.00012321625,0.00009496748,0.48209858],"genre_scores_gemma":[0.000023938603,0.000074158495,0.2282121,0.0004580336,0.00015330588,0.0000054061857,0.0018445335,0.000014267967,0.7692143],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992312,0.000002385822,0.00017077595,0.000350583,0.00016011808,0.00008492297],"domain_scores_gemma":[0.9977559,0.00002530295,0.00006337126,0.002082434,0.000027797098,0.00004520495],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001568825,0.00011195786,0.00010993717,0.00004896075,0.000057351397,0.00013778909,0.0023092045,0.00008500524,0.00011805107],"category_scores_gemma":[0.0000026810508,0.00009797536,0.000023111588,0.000017269887,0.00001740817,0.0003533726,0.00035729873,0.00010785841,0.001136405],"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":[3.497769e-8,9.104365e-7,5.5542295e-9,0.0000028308687,0.0000032449618,1.4149218e-7,0.000009552557,1.847902e-7,3.3781797e-7,0.63678735,0.028586533,0.33460885],"study_design_scores_gemma":[0.000032965196,0.000007453045,6.99073e-7,0.00001378513,0.000005718628,0.0000045596867,4.1737033e-7,0.099030174,0.0000031277232,0.017381484,0.8834024,0.00011723387],"about_ca_topic_score_codex":0.0000054572406,"about_ca_topic_score_gemma":0.000009141875,"teacher_disagreement_score":0.85481584,"about_ca_system_score_codex":0.000008438206,"about_ca_system_score_gemma":0.000032084758,"threshold_uncertainty_score":0.9996413},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000005088113,0.00006583235,0.07400001,0.0002585413,0.00032188982,0.00018333812,0.00096135755,0.00027457732,0.9239294],"genre_scores_gemma":[0.006473546,0.000022902448,0.5454195,0.007477265,0.0014692456,0.00006725971,0.0019353648,0.00011992169,0.43701497],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979706,0.000009364218,0.00032279376,0.00096396205,0.00047027713,0.00026300806],"domain_scores_gemma":[0.9967445,0.00006354118,0.00021153064,0.0027589523,0.000079273355,0.00014218279],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00014243116,0.0003135938,0.00025995227,0.00007703898,0.00015960139,0.00022624774,0.0026405153,0.00018965495,0.000012335748],"category_scores_gemma":[0.000028442644,0.0003163357,0.00005905228,0.0000406725,0.000039995244,0.0001792253,0.000700773,0.00019688267,0.00032537262],"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":[0.0000014104858,0.000008035156,2.2139383e-7,0.000001925926,0.000016200294,0.00001773346,0.000019083056,0.000001167713,4.8531854e-7,0.7363357,0.03135431,0.2322437],"study_design_scores_gemma":[0.00031774348,0.00014196824,0.000022305097,0.00025423482,0.000037481386,0.00004725121,0.0000061916326,0.014361409,0.0000070815126,0.33993456,0.6442161,0.0006536667],"about_ca_topic_score_codex":0.000020772635,"about_ca_topic_score_gemma":0.00002017747,"teacher_disagreement_score":0.6128618,"about_ca_system_score_codex":0.00010350165,"about_ca_system_score_gemma":0.00016045936,"threshold_uncertainty_score":0.9999289},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000061528544,0.00015376248,0.025321983,0.00026329953,0.00020873296,0.00021010151,0.00010023859,0.000349724,0.973386],"genre_scores_gemma":[0.0022012528,0.000006511294,0.31793767,0.0019098558,0.000634105,0.00004735204,0.000023966522,0.000045813,0.67719346],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984335,0.0000058048445,0.0002857054,0.00065124134,0.00032465765,0.0002991033],"domain_scores_gemma":[0.99849474,0.00001888302,0.00017661968,0.0010866,0.000074114,0.00014906452],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00009211804,0.00030790025,0.00027998077,0.000048278973,0.00012960531,0.0002674251,0.0013728876,0.00022496752,0.000009735825],"category_scores_gemma":[0.0000063021107,0.00030900407,0.000119815355,0.000027703645,0.000047926715,0.00009799801,0.00034690366,0.00018494025,0.00040961325],"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":[4.6568695e-7,0.000001997239,8.0630133e-7,0.000003040797,0.000011371619,0.000018176419,0.000021055193,3.1617884e-7,0.000001489047,0.68933034,0.006796068,0.30381486],"study_design_scores_gemma":[0.00016581078,0.00008975459,0.00004121667,0.00017194099,0.000028688266,0.00008828004,0.0000030840654,0.001316367,0.000023555784,0.5361676,0.461322,0.00058164954],"about_ca_topic_score_codex":0.000013451305,"about_ca_topic_score_gemma":0.000007853017,"teacher_disagreement_score":0.45452595,"about_ca_system_score_codex":0.000100467,"about_ca_system_score_gemma":0.00017190744,"threshold_uncertainty_score":0.9999362},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.992666e-8,0.0000150112055,0.52610254,0.00023705441,0.00009318469,0.000045857323,0.000005740291,0.000100283396,0.4734002],"genre_scores_gemma":[0.000014499852,0.000024756955,0.24336118,0.00045077037,0.00011187014,0.0000104137425,0.00007141102,0.000010036088,0.7559451],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993379,0.0000028897223,0.0001366496,0.0002962196,0.0001438897,0.00008246209],"domain_scores_gemma":[0.9992139,0.000035876317,0.00008048704,0.0005900127,0.00003434535,0.000045415985],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0000792848,0.0001137319,0.00010294994,0.00005488548,0.00005416069,0.00011614139,0.00052863656,0.00007901734,0.0001639781],"category_scores_gemma":[0.0000024462774,0.00010312981,0.000041023482,0.000016126844,0.000017578563,0.00010067775,0.00015808477,0.000087843706,0.0013445668],"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":[3.9213766e-8,0.0000011912666,1.0794663e-7,0.0000020846542,0.000003980906,4.178307e-7,0.000008595613,4.0427128e-7,0.0000052999176,0.6923616,0.026249036,0.28136724],"study_design_scores_gemma":[0.00004619125,0.000017013428,0.000004245282,0.000021025271,0.000005896122,0.000005236534,9.21647e-7,0.008456481,0.00006071226,0.035152234,0.9560548,0.00017523924],"about_ca_topic_score_codex":0.000009136896,"about_ca_topic_score_gemma":0.0000036378312,"teacher_disagreement_score":0.92980576,"about_ca_system_score_codex":0.000019655174,"about_ca_system_score_gemma":0.000027863962,"threshold_uncertainty_score":0.999433},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000038066198,0.00032066356,0.12296476,0.00018564869,0.0001829263,0.00024501164,0.010853843,0.00031266754,0.8649307],"genre_scores_gemma":[0.0008343218,0.000052031108,0.93946725,0.0011082913,0.00074655307,0.000021538068,0.003015987,0.000088954206,0.054665096],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99701697,0.000011695636,0.00036869475,0.0016778635,0.0005565954,0.00036820595],"domain_scores_gemma":[0.9895262,0.000055984212,0.00028423208,0.009858762,0.000082061495,0.00019273564],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00017385244,0.00041921233,0.00040461705,0.00005536186,0.00025355897,0.00031771124,0.010931417,0.00017320941,0.000008247127],"category_scores_gemma":[0.00001427283,0.00037424933,0.000033924232,0.000048871298,0.00017605696,0.00047341632,0.008010593,0.00026445673,0.00022813425],"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":[0.0000035785122,0.000010364616,0.000004341906,0.000010858968,0.00008998504,0.00015433345,0.000035138026,0.0000010748942,6.5609925e-7,0.6832873,0.13945304,0.1769493],"study_design_scores_gemma":[0.00025072714,0.00006385767,0.000023164075,0.00018900353,0.00005178219,0.00047880228,0.000003984865,0.01878664,9.342314e-7,0.008893013,0.9706572,0.0006008428],"about_ca_topic_score_codex":0.00010708214,"about_ca_topic_score_gemma":0.00017856093,"teacher_disagreement_score":0.83120424,"about_ca_system_score_codex":0.00006486427,"about_ca_system_score_gemma":0.00046128916,"threshold_uncertainty_score":0.99987096},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012656891,0.00030676433,0.1101686,0.0010644512,0.0002952825,0.00078560313,0.03683536,0.00017170527,0.85035956],"genre_scores_gemma":[0.07000096,0.000101714715,0.8517202,0.004050357,0.0030614838,0.0010746157,0.022849936,0.00018289368,0.0469578],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969603,0.0000144580545,0.0005845854,0.0013000555,0.0007531246,0.00038747824],"domain_scores_gemma":[0.99588853,0.000073426585,0.00059619255,0.003072384,0.00015694229,0.00021251409],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00043039228,0.00038383956,0.00042834168,0.0001345624,0.00054251304,0.00036190214,0.004324304,0.00013548802,0.000008965626],"category_scores_gemma":[0.000035551435,0.00042288573,0.000070092196,0.0000454227,0.00018383456,0.0006099209,0.0013791157,0.00033329363,0.00010980691],"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":[0.0000013609763,0.000037072972,0.00012362355,0.00002453204,0.00002312542,0.0000065680742,0.000043325817,0.000004074791,8.719983e-7,0.9403002,0.019966582,0.039468642],"study_design_scores_gemma":[0.00088345667,0.00007850156,0.008098448,0.00095971173,0.000015978254,0.00013586905,0.000029540859,0.01206474,0.0000038682083,0.362813,0.6134829,0.0014340093],"about_ca_topic_score_codex":0.00019576923,"about_ca_topic_score_gemma":0.00057825516,"teacher_disagreement_score":0.80340177,"about_ca_system_score_codex":0.00029249597,"about_ca_system_score_gemma":0.0017447951,"threshold_uncertainty_score":0.9998223},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.4762665e-8,0.000041041516,0.47885874,0.00069325295,0.00015668306,0.00006385595,0.0001632643,0.00016614934,0.519857],"genre_scores_gemma":[0.000010527092,0.00005455405,0.24577597,0.0005066388,0.000449886,0.00000402962,0.0010220443,0.000018159019,0.75215816],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984806,0.000004441155,0.00020999939,0.000871593,0.00025835788,0.00017499323],"domain_scores_gemma":[0.9954563,0.00005186394,0.00008729665,0.00421317,0.00007796684,0.00011344848],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00019685976,0.00019283868,0.00018991534,0.00005356683,0.000109593726,0.00021918242,0.0046418263,0.00018283821,0.0007333532],"category_scores_gemma":[0.000014204132,0.00016638475,0.00003691517,0.000039643455,0.000086005355,0.00036050976,0.0032711884,0.00023220011,0.0038368711],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.08742555e-7,0.00000686143,1.3100673e-7,0.0000019802915,0.000009468018,0.0000043070536,0.000008861968,2.1218062e-8,2.5818446e-7,0.58566326,0.38148,0.032824747],"study_design_scores_gemma":[0.000032833595,0.000017208826,0.000003143836,0.0000057856755,0.000010369914,0.000014263739,5.9092383e-7,0.02700828,0.0000027790322,0.09617568,0.8765288,0.00020028473],"about_ca_topic_score_codex":0.00002211073,"about_ca_topic_score_gemma":0.000020573201,"teacher_disagreement_score":0.49504876,"about_ca_system_score_codex":0.000023548098,"about_ca_system_score_gemma":0.00011279516,"threshold_uncertainty_score":0.99693877},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000002621804,0.000103316626,0.14189248,0.00019576369,0.00016313758,0.00008943051,0.000017124023,0.0003390409,0.8571971],"genre_scores_gemma":[0.0000097539605,0.000015292442,0.31507504,0.00021648392,0.00014830526,0.0000069932157,0.000036456753,0.00002181925,0.6844698],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987177,0.0000040926557,0.000230959,0.0005936353,0.00023831766,0.0002152785],"domain_scores_gemma":[0.9984739,0.00006982389,0.00013446162,0.0011090325,0.00011136189,0.00010142785],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00015475668,0.00023143872,0.00021027031,0.00014946568,0.00015765689,0.0002816489,0.001326672,0.00015562639,0.0025128184],"category_scores_gemma":[0.000009841106,0.0002149066,0.00009678127,0.000060484337,0.0000787463,0.00028372084,0.000561237,0.00013829496,0.004746284],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.38253e-7,0.000005074411,5.1046555e-7,0.0000031072784,0.00002327799,0.0000044415274,0.000098633245,1.04892415e-7,0.000013546956,0.64239,0.30123776,0.056223374],"study_design_scores_gemma":[0.00006329985,0.00004718179,0.000005863959,0.00009431303,0.000015369586,0.000019429055,0.0000036751564,0.02517901,0.000041659583,0.05645035,0.9176631,0.0004167362],"about_ca_topic_score_codex":0.000005987689,"about_ca_topic_score_gemma":0.0000028225186,"teacher_disagreement_score":0.61642534,"about_ca_system_score_codex":0.00002171498,"about_ca_system_score_gemma":0.00006030989,"threshold_uncertainty_score":0.998399},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000019171198,0.0012937933,0.10780797,0.00016053578,0.00068738504,0.00044318664,0.0012597472,0.00016720849,0.8881782],"genre_scores_gemma":[0.00027878047,0.0036912337,0.07589154,0.00006528776,0.0011566244,0.000101725585,0.003781122,0.0000703158,0.91496336],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978144,0.000025218977,0.00071207876,0.0007093622,0.00052128313,0.00021763005],"domain_scores_gemma":[0.9965976,0.00010343231,0.00064200436,0.0023728698,0.00014875793,0.00013532469],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034084826,0.00031589012,0.00045587507,0.00022185236,0.00007921213,0.00008750246,0.0015296952,0.00019369168,0.000023327015],"category_scores_gemma":[0.000029640449,0.00030587424,0.000105840205,0.000104039435,0.000059334547,0.00047299222,0.00024973205,0.00026519265,0.00035101917],"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":[0.000001055925,0.00003350025,0.0000030195067,0.00007892969,0.000026036128,0.000008967808,0.00005291842,0.0000017666949,0.00003865053,0.72638357,0.06367194,0.20969962],"study_design_scores_gemma":[0.00012558892,0.00004764313,0.00007460519,0.0003358217,0.000033049644,0.000018000772,0.000009819235,0.0066982363,0.0000067036312,0.0012176521,0.99109983,0.00033304517],"about_ca_topic_score_codex":0.0000571672,"about_ca_topic_score_gemma":0.000009566784,"teacher_disagreement_score":0.9274279,"about_ca_system_score_codex":0.00005246012,"about_ca_system_score_gemma":0.00017874314,"threshold_uncertainty_score":0.9999393},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000017289482,0.0004203181,0.5125508,0.00075195456,0.00026458912,0.00020189221,0.000010298139,0.00032256788,0.48547587],"genre_scores_gemma":[0.000005722359,0.000024625017,0.6141976,0.0007466018,0.00045574276,0.000048054873,0.000020263524,0.000050875915,0.38445047],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99710536,0.000098843564,0.00062233687,0.0012676943,0.00041559586,0.0004901699],"domain_scores_gemma":[0.9979687,0.0003718807,0.00043098364,0.0007722841,0.00014690746,0.0003092667],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019191352,0.0004993932,0.0005150988,0.00045869302,0.00026319548,0.00093650696,0.0016428385,0.0010199471,0.000063954714],"category_scores_gemma":[0.00009437574,0.00051105354,0.00012663184,0.00008989492,0.0001273188,0.0014794436,0.0008292253,0.0017782938,0.000028882549],"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":[0.0000011456284,0.0000021960655,0.0000018360198,0.000010401707,0.00005278581,0.0000012934053,0.0003326582,0.0000015594585,0.00010948932,0.16265662,0.05019683,0.7866332],"study_design_scores_gemma":[0.00018054587,0.000029187775,0.0000103090315,0.00007814046,0.00006441643,0.00012484194,0.000016995004,0.019269632,0.00020109539,0.030258063,0.9492189,0.00054784113],"about_ca_topic_score_codex":0.000017931041,"about_ca_topic_score_gemma":0.0000033360957,"teacher_disagreement_score":0.8990221,"about_ca_system_score_codex":0.00014123645,"about_ca_system_score_gemma":0.00022341755,"threshold_uncertainty_score":0.9997341},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000066428605,0.0004718526,0.21208024,0.0011427002,0.00022376036,0.00026862006,0.0022968596,0.00007107066,0.7833785],"genre_scores_gemma":[0.01587648,0.0000068319505,0.96978986,0.0005143227,0.00009876146,0.000016289569,0.0003683157,0.000029844976,0.013299291],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985068,0.0000069554626,0.0003118569,0.0007275488,0.0003077068,0.00013911938],"domain_scores_gemma":[0.9980867,0.00015317701,0.00020210922,0.0013530913,0.000069454465,0.00013548136],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001062995,0.00020498964,0.00026685384,0.000051737406,0.0000788113,0.00012536274,0.0016088833,0.00011804109,0.000015843347],"category_scores_gemma":[0.00003903863,0.00020750315,0.000043246535,0.000041146584,0.000085828724,0.00012713455,0.0010410382,0.00010664855,0.000033813914],"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":[0.0000037676946,0.000010046547,0.000010027403,0.000014807416,0.000017972587,0.0000023667928,0.000012293226,0.0000026221774,0.0000068856034,0.7952224,0.006071257,0.19862555],"study_design_scores_gemma":[0.00057973724,0.00012791783,0.00040190635,0.00053688756,0.000088169436,0.000034552624,0.0000073398232,0.5010265,0.000011354664,0.42995793,0.06662356,0.0006041616],"about_ca_topic_score_codex":0.00002856622,"about_ca_topic_score_gemma":0.000054838947,"teacher_disagreement_score":0.7700792,"about_ca_system_score_codex":0.00004835769,"about_ca_system_score_gemma":0.0004511374,"threshold_uncertainty_score":0.8461733},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000035317566,0.000028043802,0.38835153,0.000017313947,0.00013920352,0.000100926816,0.000084128005,0.00015428272,0.61112106],"genre_scores_gemma":[0.000089643014,0.00004501627,0.0242294,0.00007156449,0.00010682095,6.8137257e-7,0.000038561928,0.000020441697,0.9753979],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987577,0.000014134648,0.00014778838,0.0006194614,0.00025852304,0.00020237998],"domain_scores_gemma":[0.9981819,0.00011506485,0.00015919592,0.0012836728,0.00010300404,0.00015718411],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000097797536,0.0002522014,0.00026183642,0.00014652891,0.00021032616,0.0001331132,0.0018343759,0.00020927153,0.0000019429121],"category_scores_gemma":[0.0000070236547,0.00028240512,0.00013846709,0.000010777751,0.00010355189,0.000117564,0.0009798742,0.0002579482,0.00008381227],"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":[0.0000028820314,0.0000030097076,1.077763e-7,0.000005220093,0.000018118777,0.000028636703,0.000009469334,0.000001267154,0.0000049149908,0.807861,0.07686334,0.11520208],"study_design_scores_gemma":[0.00021073998,0.000030059704,0.000011121051,0.000087047316,0.000035022353,0.0000119228325,0.0000017978193,0.00444701,0.000049351154,0.000086057415,0.99472135,0.0003084919],"about_ca_topic_score_codex":0.000045255114,"about_ca_topic_score_gemma":0.0000020057803,"teacher_disagreement_score":0.91785806,"about_ca_system_score_codex":0.000074560354,"about_ca_system_score_gemma":0.00006373097,"threshold_uncertainty_score":0.9999628},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.5120825e-7,0.00002027456,0.43318003,0.00027086062,0.00014118433,0.000048134294,0.000006802399,0.00015265998,0.5661796],"genre_scores_gemma":[0.000106885695,0.000008647303,0.19779928,0.0001034966,0.00023110937,0.0000074989593,0.000043350614,0.000011029821,0.8016887],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99925786,0.0000031680509,0.00015819429,0.00033789442,0.0001529119,0.00008996507],"domain_scores_gemma":[0.9989386,0.000075036434,0.00010185054,0.000763844,0.000068999056,0.000051665684],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000105860636,0.00011700455,0.00008585984,0.00008244628,0.0001211883,0.00013443686,0.0005183412,0.00014425626,0.0008466796],"category_scores_gemma":[0.000010963143,0.00011035972,0.000045883982,0.000032219425,0.00003577221,0.00029312557,0.00013157532,0.00016573595,0.005291026],"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":[1.0242635e-7,0.000002985004,0.0000014040667,0.0000015085269,0.0000031636212,8.5156563e-7,0.000019254656,1.1984932e-7,0.0000010358322,0.8959964,0.07178712,0.03218604],"study_design_scores_gemma":[0.000024534074,0.000015226795,0.00008974391,0.000012545277,0.0000059790923,0.000013198654,9.799614e-7,0.0028739762,0.000008708712,0.17741336,0.8194047,0.00013700494],"about_ca_topic_score_codex":0.0000045632414,"about_ca_topic_score_gemma":0.0000052310156,"teacher_disagreement_score":0.7476176,"about_ca_system_score_codex":0.000028497008,"about_ca_system_score_gemma":0.00004383516,"threshold_uncertainty_score":0.99548346},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003156261,0.0001668066,0.43558052,0.00007928662,0.00044252092,0.00037297272,0.00053746457,0.0001799937,0.5626089],"genre_scores_gemma":[0.008902886,0.000010900498,0.8850296,0.0005816911,0.0021758585,0.00011098406,0.0002334015,0.00008184509,0.102872804],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988035,0.000007358507,0.00028635698,0.00034858932,0.00027638013,0.00027779338],"domain_scores_gemma":[0.99879557,0.000049223756,0.00039920877,0.00051173056,0.00015804765,0.000086205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023818787,0.0002100181,0.00021885878,0.000046052068,0.00017858183,0.0001830066,0.0004612279,0.000302404,0.0000032238152],"category_scores_gemma":[0.00001949398,0.00021312505,0.00012825633,0.0000161349,0.000013748537,0.0002419569,0.00017199974,0.0001089907,0.00008169562],"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":[0.0000011378605,0.0000043404693,0.000008395522,0.000009462037,0.00002769582,2.861098e-7,0.000020731359,0.0000035993583,0.000014189959,0.9252072,0.0009597827,0.0737432],"study_design_scores_gemma":[0.00024003067,0.000031046256,0.00009636454,0.00011073746,0.00009170103,0.000011971328,0.000002250301,0.023714425,0.000052569856,0.7521524,0.22300123,0.0004953042],"about_ca_topic_score_codex":0.000053729418,"about_ca_topic_score_gemma":0.000012658545,"teacher_disagreement_score":0.45973608,"about_ca_system_score_codex":0.0007052392,"about_ca_system_score_gemma":0.00012349593,"threshold_uncertainty_score":0.8690987},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.7887344e-7,0.000029193525,0.48163956,0.00017407097,0.000054840584,0.00003139027,0.000024622927,0.00011140548,0.5179345],"genre_scores_gemma":[0.000024850944,0.000030176388,0.18323529,0.0003168058,0.0001599014,0.0000059582853,0.0000873579,0.000009417318,0.8161302],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989973,0.0000031131806,0.00018511775,0.0005005956,0.00018398189,0.00012992595],"domain_scores_gemma":[0.9983868,0.00003392407,0.000100650934,0.0013216771,0.000082787345,0.000074147196],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00010677162,0.00015627338,0.0002273934,0.0002341494,0.00007300281,0.00016043708,0.0010981067,0.00012569792,0.0017436318],"category_scores_gemma":[0.0000032668675,0.00013453433,0.00016855728,0.00014552972,0.00005806742,0.00013255335,0.00037791787,0.00010729995,0.0025100007],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.0386735e-7,0.000005565033,0.0000016515037,0.0000016620194,0.00024600478,0.000003053182,0.000027931539,9.3017167e-7,6.612811e-7,0.876295,0.07057986,0.052837603],"study_design_scores_gemma":[0.00002497634,0.000018044791,0.000024738987,0.000007726001,0.00017053986,0.0000027594422,0.0000012160874,0.019946525,0.0000088229,0.038872153,0.9406847,0.00023783499],"about_ca_topic_score_codex":0.000029658111,"about_ca_topic_score_gemma":0.000040708874,"teacher_disagreement_score":0.8701048,"about_ca_system_score_codex":0.000019880517,"about_ca_system_score_gemma":0.00004513004,"threshold_uncertainty_score":0.99916893},"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":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0080228755,0.000039136787,0.99070257,0.00083941675,0.000024329232,0.000118419026,0.0000016689575,0.00008043488,0.00017116507],"genre_scores_gemma":[0.105991006,0.0000028304473,0.8936506,0.00023842155,0.000021842641,0.000048137732,0.0000027770188,0.0000039650104,0.000040400562],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99939096,0.0000045097763,0.00013708894,0.00022782704,0.00006525458,0.00017435882],"domain_scores_gemma":[0.99949133,0.00028147106,0.000025574858,0.00014829078,0.000010695412,0.000042637974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020050185,0.0000616896,0.0000692631,0.00006001766,0.00013323377,0.00023134747,0.0002104903,0.000031951597,0.0000029560697],"category_scores_gemma":[0.00008265741,0.000059037266,0.00000920058,0.00016097925,0.000011106606,0.0004236022,0.00012414275,0.000045694404,0.0000028282388],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.943816e-7,0.000014089571,0.00054184964,0.0000045956476,0.0000028871566,3.967154e-7,0.001880577,0.000023063774,0.000010163759,0.28403893,0.00016872118,0.7133141],"study_design_scores_gemma":[0.0019726604,0.00012787359,0.00928442,0.0010255611,0.000012408498,0.000042898366,0.0071700322,0.78885216,0.003459821,0.11547789,0.07101509,0.0015592058],"about_ca_topic_score_codex":0.0000027806536,"about_ca_topic_score_gemma":0.000030135296,"teacher_disagreement_score":0.7888291,"about_ca_system_score_codex":0.000085423395,"about_ca_system_score_gemma":0.000047677953,"threshold_uncertainty_score":0.24074699},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009461899,0.00010016125,0.95420617,0.00027282716,0.00036730466,0.0002640162,0.000009771407,0.0002063396,0.035111524],"genre_scores_gemma":[0.0040308773,0.000020259524,0.9890249,0.00022850845,0.00021909684,0.00005250714,0.0008646086,0.000027289025,0.005532],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99814904,0.00007988819,0.00045666183,0.00075881707,0.00027062985,0.00028496078],"domain_scores_gemma":[0.9982846,0.00012297138,0.0003551972,0.0010022029,0.00014475809,0.00009031231],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004279672,0.00029607888,0.00030478367,0.00026656254,0.0003471162,0.00042201,0.0011231961,0.00024578278,0.000027091099],"category_scores_gemma":[0.000034630102,0.00027825293,0.00011203825,0.00062307395,0.000018222061,0.0005944715,0.00007566356,0.00028398167,0.000048875034],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019507308,0.00007453208,0.000026321963,0.000021222699,0.000023572045,0.0000024752705,0.00055062503,0.000022616812,0.037327643,0.004348497,0.0015383759,0.95606214],"study_design_scores_gemma":[0.00013257549,0.000059234466,0.036554873,0.0001472175,0.00005732889,0.000007738432,0.00046997226,0.95252424,0.005127715,0.0011283207,0.0032705632,0.0005202237],"about_ca_topic_score_codex":0.00022758084,"about_ca_topic_score_gemma":0.000053839187,"teacher_disagreement_score":0.95554197,"about_ca_system_score_codex":0.00007121567,"about_ca_system_score_gemma":0.00013978385,"threshold_uncertainty_score":0.999967},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019128728,0.000038926195,0.96607786,0.001525563,0.00012035431,0.000043942196,0.0000014344962,0.00021787055,0.030061187],"genre_scores_gemma":[0.0076166987,0.000011613766,0.98737985,0.0008319996,0.000053703934,0.00002117239,0.0000041403573,0.000005336335,0.004075507],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992558,0.000030750416,0.00012872825,0.0002811829,0.00009987673,0.00020370133],"domain_scores_gemma":[0.99921507,0.000074996795,0.0000317536,0.0005695909,0.000030787327,0.00007781811],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029874776,0.000071788876,0.00007921744,0.000045318367,0.00010582006,0.00016610646,0.0007276261,0.00002592575,0.0001541275],"category_scores_gemma":[0.000017176106,0.00006224127,0.000027140883,0.0003502593,0.000017334058,0.00037255188,0.00021084503,0.0000495988,0.00023053151],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.3297685e-8,0.000021314238,0.0007474732,8.64266e-7,0.0000039575616,0.000003401406,0.00009099784,0.0000043219743,0.00038111274,0.008181672,0.00529521,0.9852696],"study_design_scores_gemma":[0.0002098635,0.00003480185,0.0029881138,0.000012612608,0.0000052620308,0.00007665284,0.00008864031,0.67076135,0.0035738386,0.002890944,0.31908327,0.0002746444],"about_ca_topic_score_codex":0.00015196853,"about_ca_topic_score_gemma":0.00000798159,"teacher_disagreement_score":0.98499495,"about_ca_system_score_codex":0.000012995048,"about_ca_system_score_gemma":0.00001897464,"threshold_uncertainty_score":0.2963093},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004581742,0.0000790558,0.98961073,0.0014021967,0.00045099447,0.00020542978,0.00006264656,0.00033629674,0.0032708964],"genre_scores_gemma":[0.046492912,0.000046438712,0.9475167,0.00035824353,0.00023126182,0.00025225256,0.0009770007,0.000015148915,0.0041100606],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983171,0.000043642918,0.00028726915,0.00083986064,0.0003223774,0.00018970312],"domain_scores_gemma":[0.99840724,0.00006790306,0.0001306807,0.0011238435,0.00020015312,0.00007019704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023523552,0.00018186233,0.00016357018,0.000112050795,0.00014159766,0.00055436563,0.0008580531,0.00016653957,0.00014913699],"category_scores_gemma":[0.000064619926,0.00018748203,0.00008385935,0.00040920448,0.000020685711,0.0005169845,0.0019683857,0.00051118265,0.00009461585],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000048464453,0.0006662008,0.0017606476,0.00016876998,0.00020882921,0.00003072236,0.0009090565,0.005785133,0.0015482722,0.5540395,0.07454917,0.36032885],"study_design_scores_gemma":[0.00016077522,0.000011737737,0.0073141046,0.0001073692,0.000016142121,0.000042016127,0.000034849818,0.9669864,0.00094617717,0.0042526117,0.019644786,0.00048300045],"about_ca_topic_score_codex":0.00023606098,"about_ca_topic_score_gemma":0.00002890499,"teacher_disagreement_score":0.9612013,"about_ca_system_score_codex":0.0000776302,"about_ca_system_score_gemma":0.0004478291,"threshold_uncertainty_score":0.7645295},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71277064,0.000004321246,0.28472823,0.00015914797,0.00010726098,0.000068777954,0.000030247606,0.000052520845,0.0020788787],"genre_scores_gemma":[0.78224885,0.0000023091245,0.21746677,0.00016695732,0.000049071008,0.0000056416434,0.000009065592,0.000005434013,0.00004589963],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990575,0.000009861985,0.00022852905,0.00029279632,0.00022986051,0.00018145805],"domain_scores_gemma":[0.9993878,0.000015761198,0.00008887601,0.00042005122,0.000029313092,0.00005822493],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011088702,0.00010033745,0.000119427066,0.00006836,0.00007872658,0.000057112156,0.00051196426,0.000029512079,0.000031952033],"category_scores_gemma":[0.000004424775,0.000094086514,0.000043764994,0.00018874781,0.000028775043,0.00033836017,0.00016266726,0.00005314515,0.00001622274],"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":[0.00003523009,0.0021651203,0.020861503,0.00012031976,0.00017246522,0.00014046273,0.005003552,0.00700483,0.3255614,0.14420673,0.0019599402,0.49276844],"study_design_scores_gemma":[0.0043035853,0.0007572738,0.020547083,0.00048927567,0.0000460385,0.00015893701,0.0007701311,0.5649272,0.402709,0.0007329712,0.0033867357,0.0011717399],"about_ca_topic_score_codex":0.00025646377,"about_ca_topic_score_gemma":0.000053685595,"teacher_disagreement_score":0.5579224,"about_ca_system_score_codex":0.000048431735,"about_ca_system_score_gemma":0.000097776545,"threshold_uncertainty_score":0.38367367},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016433021,0.00050927117,0.95396864,0.00003445837,0.00014629982,0.00015263943,0.00013856453,0.00008849154,0.044797316],"genre_scores_gemma":[0.30609643,0.00082743407,0.66993296,0.00069328264,0.00029348966,0.00018027423,0.0027710667,0.00013012499,0.019074947],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898773,0.0000037997302,0.00047391257,0.00022085814,0.00016087233,0.0001528392],"domain_scores_gemma":[0.9988899,0.00003435674,0.00042884232,0.00034967193,0.00021250872,0.00008471072],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013079857,0.00020664469,0.0002199825,0.00015257784,0.00017900848,0.00012870875,0.00036472167,0.00011151608,0.000010140856],"category_scores_gemma":[0.000016671731,0.00019788099,0.000029544084,0.00006998641,0.000072811956,0.001003373,0.00038871448,0.00029266923,0.000024051045],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017361093,0.000012973612,6.180982e-7,0.00025905814,0.000004127014,9.942451e-8,0.0007036579,0.00003487857,0.0002727648,0.0073965183,0.000033856253,0.9912797],"study_design_scores_gemma":[0.0005108418,0.00005201556,0.000017756887,0.0010358086,0.0000189027,0.000015729358,0.00014397428,0.7010078,0.0027168335,0.0003940767,0.29355884,0.0005274262],"about_ca_topic_score_codex":0.0000052948444,"about_ca_topic_score_gemma":0.000011340495,"teacher_disagreement_score":0.9907523,"about_ca_system_score_codex":0.000024338617,"about_ca_system_score_gemma":0.00011717851,"threshold_uncertainty_score":0.80693525},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.3308166e-7,0.00018222445,0.44159043,0.000068454035,0.0001876173,0.00006403406,0.000006912535,0.00005951885,0.5578401],"genre_scores_gemma":[0.00013872565,0.000109545195,0.03280348,0.0001348139,0.00039977516,0.000014921746,0.000041116782,0.000017935412,0.9663397],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990803,0.0000043865657,0.00020165916,0.00045547565,0.00008653316,0.00017163123],"domain_scores_gemma":[0.99896413,0.00005174046,0.00006332809,0.00083842874,0.000033560933,0.00004881874],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00012213358,0.00016636014,0.00017232215,0.000102617094,0.000041822037,0.00022056403,0.001007363,0.00015124159,0.00016172354],"category_scores_gemma":[0.0000029594385,0.00014608588,0.00005164109,0.000062623476,0.00005727074,0.0003450748,0.0005660678,0.0001949856,0.0008181836],"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":[2.4060384e-7,0.000012757089,0.0000013463731,0.000002641728,0.0000055156543,0.0000030923982,0.000049465252,0.000003453416,1.7243802e-7,0.85948265,0.054048963,0.08638968],"study_design_scores_gemma":[0.00008029556,0.000026454445,0.00003421649,0.000095290605,0.000003815271,0.000004814549,0.0000018705255,0.09732316,0.000002218619,0.03358709,0.8685558,0.0002850012],"about_ca_topic_score_codex":0.0000131646075,"about_ca_topic_score_gemma":0.00010909811,"teacher_disagreement_score":0.8258956,"about_ca_system_score_codex":0.000036256777,"about_ca_system_score_gemma":0.0000631421,"threshold_uncertainty_score":0.99995977},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007645337,0.017908681,0.44374123,0.0010776413,0.0093893325,0.0029135281,0.08323532,0.0004311818,0.44122663],"genre_scores_gemma":[0.0014607736,0.025429478,0.421731,0.00063041976,0.01211057,0.00033552336,0.12006243,0.00042568045,0.4178141],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99249274,0.0001553488,0.002294639,0.0021485446,0.0021505053,0.00075822667],"domain_scores_gemma":[0.9917521,0.00073129067,0.0017139004,0.0044763233,0.0007186369,0.0006077899],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00145548,0.0010275759,0.001287721,0.00058870885,0.00046225247,0.00020023348,0.0024166396,0.0004812485,0.00057169684],"category_scores_gemma":[0.0002605445,0.0010427186,0.00034662822,0.00036936023,0.0003728143,0.0015339964,0.0014061761,0.0010841404,0.0032035979],"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":[0.000022520946,0.00027649332,0.000036090583,0.0003266287,0.0001959417,0.000198141,0.000117463205,0.0001093703,0.000115400355,0.8759722,0.09020137,0.032428347],"study_design_scores_gemma":[0.00063507434,0.00015015113,0.00022027137,0.0024126347,0.00024569468,0.00017849047,0.00002965019,0.031797938,0.000011511996,0.0009437802,0.9622586,0.0011162478],"about_ca_topic_score_codex":0.00037928415,"about_ca_topic_score_gemma":0.000014534198,"teacher_disagreement_score":0.87502843,"about_ca_system_score_codex":0.00012535224,"about_ca_system_score_gemma":0.0008760675,"threshold_uncertainty_score":0.9992023},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018453889,0.00067672983,0.18412597,0.000067907196,0.0003703436,0.00068675785,0.0010495009,0.00015267108,0.81268555],"genre_scores_gemma":[0.69310784,0.000012917396,0.012627213,0.0010920846,0.0005927167,0.0005135835,0.00007633638,0.00010597325,0.29187134],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99859047,0.0000101387195,0.0003254164,0.0006274037,0.00013067215,0.00031587033],"domain_scores_gemma":[0.99877405,0.00006411336,0.00015159229,0.00086842367,0.000051235816,0.0000906071],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001196152,0.00030567896,0.00036434463,0.0000807154,0.000058110138,0.00020134839,0.0010847395,0.00019021655,0.000006415228],"category_scores_gemma":[0.000010812751,0.00029351676,0.00015638473,0.00002710246,0.00005834247,0.00014871007,0.00042650904,0.00016891221,0.00021329951],"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":[0.0000027373885,0.000020563997,0.0000064307437,0.00003416489,0.000021038983,0.000020916348,0.00045757744,4.6484818e-8,0.0000070845617,0.79144275,0.0020834203,0.20590325],"study_design_scores_gemma":[0.0028323408,0.0004147448,0.00019399832,0.0019853488,0.0001419237,0.00013769243,0.00016327234,0.0107339,0.00013837534,0.60048455,0.38036615,0.0024076947],"about_ca_topic_score_codex":0.00026793912,"about_ca_topic_score_gemma":0.00146172,"teacher_disagreement_score":0.6929233,"about_ca_system_score_codex":0.00010708933,"about_ca_system_score_gemma":0.00022141356,"threshold_uncertainty_score":0.9999517},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01950629,0.00028253195,0.91353834,0.004319462,0.0004088105,0.0002511121,0.000003418615,0.0006319287,0.061058123],"genre_scores_gemma":[0.82877564,0.00001442075,0.16756025,0.000585187,0.00011309408,0.000023044639,0.000018951696,0.000005786631,0.0029036403],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99897313,0.000013623465,0.0002623899,0.00036230896,0.00019746789,0.00019109379],"domain_scores_gemma":[0.99882674,0.000024583385,0.00011515535,0.0009039451,0.000038377253,0.000091195674],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002668114,0.00009285499,0.00012400081,0.00004545896,0.00011793886,0.00016178448,0.00033116605,0.00003379479,0.000017526132],"category_scores_gemma":[0.00004175341,0.00008019301,0.000055362794,0.00024791402,0.000015727754,0.00033145104,0.000060658695,0.00007134512,0.0000448477],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016180877,0.0001338014,0.0004993049,0.0000013856549,0.000008740836,0.00035919884,0.00018498403,0.00003941465,0.0011037568,0.017750386,0.025221156,0.95469624],"study_design_scores_gemma":[0.0010364978,0.00022088081,0.10422094,0.000041330088,0.000025854097,0.0027097133,0.000026398822,0.042038057,0.0064808265,0.050878633,0.7914872,0.0008336382],"about_ca_topic_score_codex":0.000021093361,"about_ca_topic_score_gemma":0.0000031249338,"teacher_disagreement_score":0.9538626,"about_ca_system_score_codex":0.000013437887,"about_ca_system_score_gemma":0.000036291232,"threshold_uncertainty_score":0.3270176},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.876011e-7,0.0020527372,0.36995757,0.00008378416,0.0005206417,0.00041890115,0.016145248,0.00015284067,0.6106674],"genre_scores_gemma":[0.00010159267,0.004074384,0.23728594,0.00012350336,0.0011007045,0.000043618787,0.019214757,0.00008687269,0.7379686],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970596,0.00002377562,0.00079782796,0.0011564853,0.00066650944,0.00029579617],"domain_scores_gemma":[0.9926579,0.0001188471,0.0005851431,0.006314597,0.00013876287,0.0001847684],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00048294943,0.00039975112,0.00061300094,0.0001598606,0.00009038441,0.000095415315,0.004992343,0.0002068865,0.000023827384],"category_scores_gemma":[0.00004609362,0.0003877616,0.00007318288,0.00008031812,0.00014808147,0.0010037225,0.001859493,0.0003615191,0.00022753714],"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":[0.0000011964864,0.000031128326,4.7813387e-7,0.0000473297,0.000037743404,0.00001560755,0.00010183315,0.000093195886,0.000006802528,0.79809856,0.169096,0.032470126],"study_design_scores_gemma":[0.0001479723,0.00002944056,6.505036e-7,0.00028596108,0.000041338386,0.00001778576,0.00001355385,0.19953027,0.000002021368,0.001052151,0.79850656,0.00037230505],"about_ca_topic_score_codex":0.00008853632,"about_ca_topic_score_gemma":0.000009218984,"teacher_disagreement_score":0.7970464,"about_ca_system_score_codex":0.000034785775,"about_ca_system_score_gemma":0.0004049914,"threshold_uncertainty_score":0.9998574},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.827097e-7,0.000028996295,0.36923018,0.00033585032,0.000106674095,0.000036387606,0.000008201829,0.00016422347,0.63008916],"genre_scores_gemma":[0.000030705534,0.00001849428,0.24800953,0.00039165295,0.00014752519,0.0000061116257,0.000020360814,0.000013228208,0.7513624],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991543,0.0000025843303,0.00015977406,0.00039329584,0.00016016308,0.00012986833],"domain_scores_gemma":[0.9988546,0.000053653723,0.000084386105,0.00089857186,0.00003764484,0.00007117852],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00010443016,0.00015118267,0.00015527457,0.000070800495,0.000069512425,0.00014447751,0.0010025424,0.00010954,0.00022765422],"category_scores_gemma":[0.000004837194,0.00013557803,0.000057421115,0.000022003895,0.000027064041,0.00007402756,0.0003427173,0.00011366686,0.0014138287],"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":[3.4371947e-8,0.0000010403703,1.6233601e-7,0.000001921731,0.0000048657935,0.0000011178713,0.000010940646,1.9451107e-7,0.0000017793132,0.7097762,0.07414306,0.21605867],"study_design_scores_gemma":[0.000043896885,0.000014155353,0.0000013794469,0.000027293148,0.0000047564604,0.000007975364,6.7432586e-7,0.027257614,0.000004546886,0.007627781,0.96483076,0.00017915112],"about_ca_topic_score_codex":0.000003206654,"about_ca_topic_score_gemma":0.0000045365405,"teacher_disagreement_score":0.8906877,"about_ca_system_score_codex":0.000012890573,"about_ca_system_score_gemma":0.000053623615,"threshold_uncertainty_score":0.99936366},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000011239776,0.005071984,0.039799407,0.00010645903,0.001611555,0.00050418114,0.003137771,0.0002381459,0.9495193],"genre_scores_gemma":[0.00014172103,0.0009284361,0.03821428,0.000036138852,0.0007417322,0.00003962974,0.0024752237,0.000045365276,0.9573775],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99761957,0.00002600533,0.0006088747,0.0008424227,0.0006286515,0.00027450165],"domain_scores_gemma":[0.99649465,0.0001069393,0.00047675185,0.0025914717,0.0001800527,0.00015016182],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005454463,0.0003225191,0.00047045868,0.00031271754,0.00014776885,0.00027371533,0.0017541955,0.0001589742,0.00003832757],"category_scores_gemma":[0.00004358312,0.00030354314,0.0001139703,0.0001437017,0.00013188004,0.0005761319,0.00045023346,0.00027113812,0.00040876755],"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":[0.0000011125214,0.00005095311,0.0000042029124,0.00019812396,0.00004293036,0.00005982238,0.00018261526,0.0000057219554,0.00006976859,0.7033994,0.17055899,0.12542632],"study_design_scores_gemma":[0.00009438632,0.000030884516,0.000010547442,0.000494762,0.000026448095,0.000027089276,0.00002131125,0.0011270145,0.000021365458,0.00062349444,0.99718076,0.00034192248],"about_ca_topic_score_codex":0.00012269056,"about_ca_topic_score_gemma":0.000016876902,"teacher_disagreement_score":0.8266218,"about_ca_system_score_codex":0.000039246337,"about_ca_system_score_gemma":0.0002508285,"threshold_uncertainty_score":0.99994165},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000020013184,0.01473695,0.9824805,0.00008354593,0.00020384551,0.00008606921,0.000033274406,0.00014050979,0.0022152462],"genre_scores_gemma":[0.00040554165,0.028962221,0.9554258,0.00027784976,0.0010319795,0.000022324179,0.0002098724,0.00005776273,0.013606677],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984701,0.000005580984,0.0002860395,0.0008200997,0.00015302717,0.00026514646],"domain_scores_gemma":[0.99878955,0.00016546625,0.000075799115,0.0008388413,0.000030018526,0.00010033983],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00013138504,0.0002805892,0.00042354586,0.0003859842,0.00007858726,0.00020845584,0.00076595665,0.00011458248,0.000004545368],"category_scores_gemma":[0.000013055182,0.00027867575,0.00003501921,0.00028646455,0.000086136424,0.0011623658,0.0008985384,0.00022542992,0.0000030297304],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035293515,0.000010069665,0.00004305739,0.000049960858,0.00016306277,0.000022888169,0.0001478148,0.0005848658,0.0000024858489,0.053518724,0.00053358305,0.94491994],"study_design_scores_gemma":[0.00008498142,0.00009610392,0.00012930928,0.00006462427,0.00006320932,0.000032512595,4.8732284e-7,0.5174538,0.000005845865,0.0018077428,0.47992158,0.0003397999],"about_ca_topic_score_codex":0.0000042698775,"about_ca_topic_score_gemma":0.000015818016,"teacher_disagreement_score":0.94458014,"about_ca_system_score_codex":0.000021266158,"about_ca_system_score_gemma":0.000026356825,"threshold_uncertainty_score":0.99996656},"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.4824174e-7,0.000048096637,0.33457586,0.00025906204,0.00014408214,0.00004370493,0.00021310704,0.0001477186,0.66456825],"genre_scores_gemma":[7.970306e-7,0.00001887521,0.41596898,0.00020636372,0.00022987627,0.0000018135122,0.00031559574,0.000010478137,0.58324724],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988558,0.0000020656469,0.00016641869,0.0006684123,0.00017665804,0.0001306301],"domain_scores_gemma":[0.99623525,0.000042160067,0.00008827375,0.0035211637,0.000047561087,0.00006560939],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001511196,0.00014561949,0.00013293946,0.000056342968,0.00008164996,0.00019723689,0.0039522513,0.00009913735,0.0008612804],"category_scores_gemma":[0.000008761123,0.00012992854,0.000023319595,0.000026304573,0.000053542888,0.00033403086,0.002541456,0.000095221956,0.0023849262],"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":[6.185544e-8,0.0000024343426,9.008695e-8,0.0000018201129,0.000010362772,0.000002377289,0.00002534424,1.1780389e-8,4.869963e-7,0.30218738,0.51685953,0.18091008],"study_design_scores_gemma":[0.000027842101,0.000013559514,0.0000010218197,0.000027720844,0.0000070800165,0.000009657099,0.0000020113391,0.023009896,0.0000023217242,0.008635778,0.9680932,0.000169891],"about_ca_topic_score_codex":0.000005417818,"about_ca_topic_score_gemma":0.000013325492,"teacher_disagreement_score":0.45123366,"about_ca_system_score_codex":0.000009939579,"about_ca_system_score_gemma":0.000068213114,"threshold_uncertainty_score":0.9983918},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000002126394,0.000056070035,0.21438849,0.00020609958,0.00016857222,0.000055523447,0.000015428845,0.00021087144,0.7848968],"genre_scores_gemma":[0.000009808594,0.000025063764,0.25697336,0.0002610942,0.00019185212,0.000006193355,0.000025055677,0.000014289499,0.7424933],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990545,0.000002151641,0.00016784134,0.0004505262,0.00017479103,0.00015018106],"domain_scores_gemma":[0.998759,0.000035349884,0.00008834775,0.000972993,0.00006815067,0.000076164724],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00009534979,0.00016507786,0.00014508,0.00010352476,0.00009278444,0.00014311503,0.0011039884,0.00012099533,0.00085910544],"category_scores_gemma":[0.00000373688,0.00014848662,0.000070669215,0.000041534877,0.00006579126,0.00015113523,0.00036356683,0.00009821021,0.0017577603],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.0383676e-7,0.000003057241,4.8345214e-7,0.000002194616,0.000012210965,0.0000028841453,0.000073398915,2.6891362e-8,0.000001795431,0.7504612,0.15968089,0.08976171],"study_design_scores_gemma":[0.00003689725,0.000027212465,0.0000041869944,0.000030717216,0.0000063156745,0.000010226427,0.0000027724582,0.002262895,0.00001913489,0.033438258,0.9639501,0.00021128908],"about_ca_topic_score_codex":0.000006418608,"about_ca_topic_score_gemma":0.000007881795,"teacher_disagreement_score":0.8042692,"about_ca_system_score_codex":0.000011888088,"about_ca_system_score_gemma":0.00004501352,"threshold_uncertainty_score":0.9990195},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036604907,0.000057333873,0.95255834,0.002355238,0.00017694781,0.00014544255,0.000021366088,0.00040387164,0.040620957],"genre_scores_gemma":[0.2366847,0.00006419679,0.7307353,0.0014129037,0.000103242586,0.00015839093,0.00009458763,0.000020190148,0.030726483],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931395,0.000011463266,0.00012848499,0.00026483732,0.0001295002,0.00015174464],"domain_scores_gemma":[0.9994599,0.000039562954,0.00004216734,0.0003583379,0.000025932115,0.000074059506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000081620376,0.00007026163,0.00005993569,0.000037599908,0.000121296456,0.00014986849,0.00036101174,0.00002582681,0.0001189594],"category_scores_gemma":[0.000017943794,0.00006278575,0.000018344856,0.00021986142,0.000015518563,0.00028995532,0.00008189142,0.000045658457,0.00016093353],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.3886537e-7,0.00010105423,0.000087539585,0.000004197835,0.0000069490056,0.0000045728816,0.00032321192,0.0000010073527,0.00076714216,0.021532336,0.40091875,0.57625306],"study_design_scores_gemma":[0.00010206148,0.000035644684,0.00012248724,0.000007523898,0.0000032276344,0.000027277398,0.000052396284,0.85649717,0.00035655065,0.00019006517,0.14246231,0.00014327973],"about_ca_topic_score_codex":0.000042407875,"about_ca_topic_score_gemma":0.0000025331508,"teacher_disagreement_score":0.85649616,"about_ca_system_score_codex":0.000022186941,"about_ca_system_score_gemma":0.000010089293,"threshold_uncertainty_score":0.25603288},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.2337801e-7,0.00006925833,0.34015974,0.00021245675,0.00021686788,0.000046188554,0.00000572495,0.00016470074,0.65912485],"genre_scores_gemma":[0.0000021342,0.000011694611,0.37342057,0.00048071076,0.0006376333,0.0000048924144,0.000018528835,0.000011952175,0.62541187],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99908066,0.0000024291062,0.00016639757,0.00041594054,0.00015070016,0.00018386554],"domain_scores_gemma":[0.998833,0.00004460834,0.0000927165,0.0009069393,0.000054096803,0.00006861714],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00011588234,0.00015623386,0.0001470468,0.000036571168,0.00011329334,0.00015894196,0.0010287098,0.00012019373,0.0008065696],"category_scores_gemma":[0.0000030638762,0.00014130196,0.000047862464,0.000035802626,0.00004736362,0.00012248401,0.00047687444,0.000100911195,0.0020430994],"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":[7.408962e-8,0.000001160366,2.0412003e-7,0.0000010154412,0.0000063806788,0.0000016657822,0.000027331966,5.9232644e-7,1.0815169e-7,0.5354918,0.4077084,0.05676126],"study_design_scores_gemma":[0.000026410891,0.000022455199,0.0000021165104,0.00003929896,0.000005415413,0.0000075076246,0.0000010490536,0.0066903112,0.0000011452785,0.071218655,0.9218078,0.0001778065],"about_ca_topic_score_codex":0.000003175827,"about_ca_topic_score_gemma":0.0000047670674,"teacher_disagreement_score":0.5140994,"about_ca_system_score_codex":0.000014027593,"about_ca_system_score_gemma":0.000045851662,"threshold_uncertainty_score":0.99873394},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.9730128e-7,0.00011126613,0.32998192,0.0003697674,0.00018887347,0.00005860849,0.000012926039,0.00018827629,0.66908795],"genre_scores_gemma":[0.000008868058,0.000033163065,0.36901668,0.00024981613,0.0003919123,0.0000059207628,0.000022760993,0.000014638585,0.63025624],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988912,0.00000292991,0.00020871837,0.0005064852,0.0002245193,0.00016617616],"domain_scores_gemma":[0.99857193,0.00007796651,0.00011638096,0.0010508234,0.00009381584,0.00008906295],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00014278632,0.00018211314,0.00018021904,0.00023734002,0.00009722939,0.00019942169,0.0012874191,0.00015589506,0.00086141005],"category_scores_gemma":[0.000013891805,0.00016135552,0.0000723604,0.00011760898,0.000048115424,0.00016605672,0.00051587797,0.00013553775,0.0028903836],"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":[8.614482e-8,0.0000027856859,3.188359e-7,0.000002872067,0.000015645217,0.0000031058273,0.000045886423,1.0770778e-7,5.9543385e-7,0.48878103,0.08400935,0.4271382],"study_design_scores_gemma":[0.00004256889,0.000034440985,0.000006208486,0.000028824672,0.000010387072,0.000010085726,0.0000018784565,0.008215906,0.000018493854,0.01765686,0.9737435,0.00023083876],"about_ca_topic_score_codex":0.0000057727775,"about_ca_topic_score_gemma":0.0000027298586,"teacher_disagreement_score":0.88973415,"about_ca_system_score_codex":0.000017320592,"about_ca_system_score_gemma":0.00006242013,"threshold_uncertainty_score":0.997886},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000037719,0.00016300881,0.18130279,0.00014220361,0.00029959067,0.00023780881,0.00035901336,0.00032725968,0.8171306],"genre_scores_gemma":[0.17413189,0.000077906865,0.5281526,0.009586756,0.002117339,0.0005555919,0.00033919385,0.00030436087,0.28473437],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99794376,0.000012616304,0.00038461914,0.00082103524,0.0004725515,0.00036542604],"domain_scores_gemma":[0.9980409,0.00004157696,0.00025172945,0.0013578206,0.000107659485,0.00020032006],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00007298305,0.00041012745,0.00034938465,0.00006813899,0.00018255042,0.00020203377,0.0016075331,0.00026608072,0.000022744363],"category_scores_gemma":[0.0000066966963,0.00040788928,0.00016304057,0.000029916235,0.00009645089,0.0000862281,0.00036633157,0.00024035668,0.00035953274],"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":[0.0000013219938,0.000015920816,0.000017789422,0.0000150736,0.00003720865,0.00008000986,0.00007952046,0.000006219808,0.0000028447942,0.6172153,0.016418403,0.36611038],"study_design_scores_gemma":[0.0013298619,0.00042227804,0.00037818227,0.0011840385,0.000117361844,0.00027635306,0.000010415535,0.02570235,0.00021323274,0.12835364,0.83914,0.0028722947],"about_ca_topic_score_codex":0.00011731649,"about_ca_topic_score_gemma":0.00003931563,"teacher_disagreement_score":0.8227216,"about_ca_system_score_codex":0.00017185886,"about_ca_system_score_gemma":0.00038862438,"threshold_uncertainty_score":0.9998373},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25697482,0.000011974071,0.7337631,0.00086163334,0.00007266157,0.000066972185,0.000009699472,0.00015626788,0.008082894],"genre_scores_gemma":[0.6749654,0.000025752273,0.317751,0.00086099317,0.00016698803,0.00004065073,0.000057270117,0.0000066607004,0.0061253277],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993872,0.00001221428,0.00011403674,0.00024237134,0.00010843654,0.00013570745],"domain_scores_gemma":[0.99949545,0.000007307201,0.000020571793,0.0004025737,0.000017007795,0.00005712002],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008003981,0.0000644843,0.00005649247,0.00002424951,0.00010947461,0.00018391652,0.00035203708,0.000018913292,0.00039831217],"category_scores_gemma":[0.0000018117703,0.00005516396,0.000016187396,0.000107268934,0.0000082319475,0.0003149366,0.000039599505,0.000033026416,0.00019266698],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.428797e-7,0.000035109704,0.0022273757,0.0000016228691,0.0000075097337,0.0000030103129,0.00043443887,0.00009930125,0.00092047564,0.008916104,0.0084787505,0.97887594],"study_design_scores_gemma":[0.00020624817,0.00003388497,0.004121784,0.000009430719,0.00000433602,0.000019084317,0.000021656268,0.93510014,0.0043554083,0.00014576281,0.055764917,0.00021733825],"about_ca_topic_score_codex":0.0003118098,"about_ca_topic_score_gemma":0.00010149193,"teacher_disagreement_score":0.9786586,"about_ca_system_score_codex":0.000014141814,"about_ca_system_score_gemma":0.000020604002,"threshold_uncertainty_score":0.43612388},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000038307295,0.00062695984,0.046186447,0.0008886999,0.0012268103,0.00036362614,0.0070370478,0.00039496148,0.9432371],"genre_scores_gemma":[0.0719181,0.0012564173,0.20309798,0.012342116,0.01759892,0.001256999,0.005964883,0.0005273696,0.68603724],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983977,0.000017498036,0.00024017245,0.00070671004,0.00041479364,0.00022309816],"domain_scores_gemma":[0.99653715,0.00011748565,0.0002604606,0.0028734568,0.000068549445,0.0001428697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019391227,0.00023595327,0.00018669205,0.00001568588,0.0001943659,0.00032655022,0.0035286618,0.00009827445,0.00001549448],"category_scores_gemma":[0.00005057308,0.00018729757,0.00007134609,0.000021215228,0.000033202785,0.00038540125,0.0017340403,0.00020461949,0.0004800594],"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":[0.0000015133297,0.000005485492,0.000022737873,0.000002075283,0.000050943752,0.000008332456,0.00006469759,1.7827826e-7,5.304169e-7,0.8993326,0.012306164,0.088204734],"study_design_scores_gemma":[0.000103923776,0.000010314407,0.00089658826,0.00011934457,0.00011174313,0.000001649482,0.0000050280933,0.0008506256,0.0000053820386,0.5076622,0.4898657,0.00036756645],"about_ca_topic_score_codex":0.0004946679,"about_ca_topic_score_gemma":0.00008423464,"teacher_disagreement_score":0.4775595,"about_ca_system_score_codex":0.00013088246,"about_ca_system_score_gemma":0.00015428527,"threshold_uncertainty_score":0.7637773},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000012565902,0.00011881938,0.47823545,0.0000778028,0.00009333123,0.00020183869,0.0011367844,0.0004893327,0.5196454],"genre_scores_gemma":[0.00082585623,0.000006959382,0.99057084,0.00046662372,0.000411111,0.000009911513,0.000592459,0.00005648076,0.007059762],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967659,0.00001300824,0.0005096079,0.0016776331,0.00057910243,0.00045471534],"domain_scores_gemma":[0.9926542,0.00008273415,0.00039598002,0.0065575796,0.00013869787,0.00017082698],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00059646415,0.00049665803,0.00044064072,0.00010606144,0.00023365462,0.00065941457,0.008262985,0.0002733119,0.0000050470135],"category_scores_gemma":[0.00003989527,0.00042884555,0.000040506256,0.00007690116,0.00014950459,0.0006310316,0.006496306,0.000448196,0.000033273976],"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":[0.0000025015472,0.0000059856343,0.0000022858387,0.000015238792,0.000039842926,0.00007553293,0.00006462749,1.7180624e-7,0.0000028481413,0.47819734,0.0042265793,0.51736706],"study_design_scores_gemma":[0.00048516263,0.00034365893,0.0000107695005,0.0037464162,0.0002971068,0.0011977623,0.00019505489,0.05718907,0.00019551963,0.07936309,0.85400826,0.0029681178],"about_ca_topic_score_codex":0.00020142266,"about_ca_topic_score_gemma":0.0002470572,"teacher_disagreement_score":0.8497817,"about_ca_system_score_codex":0.00013499823,"about_ca_system_score_gemma":0.000419602,"threshold_uncertainty_score":0.99981636},"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000015406958,0.000042555203,0.14275962,0.0002892167,0.00018451548,0.000053438907,0.000020499365,0.00022169018,0.85642695],"genre_scores_gemma":[0.000008213047,0.00001923558,0.2853204,0.00026227548,0.00022377018,0.000005168404,0.0000182519,0.000012194231,0.7141305],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991349,0.000001861217,0.00015400002,0.000413238,0.00016110722,0.00013491155],"domain_scores_gemma":[0.998859,0.000033389024,0.00007926557,0.0009006847,0.000058975103,0.00006868928],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000086642205,0.00014904875,0.00013290666,0.000072330724,0.00008042443,0.00015546048,0.0010425862,0.00011192895,0.0011764157],"category_scores_gemma":[0.000004113762,0.00013316156,0.00005212071,0.000027902764,0.000050656705,0.000139751,0.00042406353,0.000092305454,0.0031515178],"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":[7.6029224e-8,0.000002574534,1.8366867e-7,0.000001967323,0.000009187381,0.000002621498,0.000050157254,3.2125378e-8,0.0000030626938,0.61400086,0.28521177,0.100717485],"study_design_scores_gemma":[0.000039969193,0.000022281323,0.0000011376034,0.000029635372,0.0000048909515,0.000009625441,0.0000020925302,0.0107185,0.000009806478,0.013518936,0.9754642,0.000178891],"about_ca_topic_score_codex":0.0000026142882,"about_ca_topic_score_gemma":0.0000061711917,"teacher_disagreement_score":0.6902524,"about_ca_system_score_codex":0.000015292939,"about_ca_system_score_gemma":0.000076821794,"threshold_uncertainty_score":0.99973667},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.0418914e-8,0.000016722215,0.48850584,0.00037842378,0.000069700036,0.000052970547,0.00023889903,0.000099947516,0.51063746],"genre_scores_gemma":[0.000006226409,0.00007378668,0.26340175,0.00029402057,0.00022189641,0.0000043833234,0.001586211,0.000012599583,0.73439914],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99921614,0.0000017251613,0.00016467307,0.00036822815,0.00016106408,0.00008819486],"domain_scores_gemma":[0.9977502,0.00001583404,0.000059564343,0.002087321,0.00004341847,0.000043653377],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00013058618,0.00011039797,0.00009422582,0.00005004871,0.0000662118,0.00014824087,0.0024013852,0.0000868491,0.0006061082],"category_scores_gemma":[0.000002285912,0.00009624715,0.000021002077,0.000021840317,0.000032366283,0.0006649821,0.0004413781,0.00008782989,0.0025300363],"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":[7.3974e-8,0.0000021513638,6.0761893e-9,0.000002781603,0.000005854093,3.172836e-7,0.000041678963,2.982241e-8,5.5778725e-7,0.6939346,0.114510596,0.19150133],"study_design_scores_gemma":[0.000031017436,0.00001204416,5.987101e-7,0.000015426862,0.0000060695547,0.0000056664003,0.0000013287254,0.04284337,0.0000069490593,0.03152999,0.9254266,0.00012090792],"about_ca_topic_score_codex":0.000004442509,"about_ca_topic_score_gemma":0.000012406442,"teacher_disagreement_score":0.810916,"about_ca_system_score_codex":0.000009975147,"about_ca_system_score_gemma":0.000045797933,"threshold_uncertainty_score":0.9982466},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.0462411e-8,0.00003315798,0.5466482,0.00092664565,0.000108419816,0.000051566083,0.00007978743,0.00014527925,0.45200694],"genre_scores_gemma":[0.000037425863,0.00005382474,0.21202977,0.0007577987,0.00031078153,0.000004833556,0.0011600379,0.000020078369,0.78562546],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985189,0.0000060543584,0.00021743402,0.0008318574,0.0002569365,0.00016881517],"domain_scores_gemma":[0.99545395,0.00008115646,0.00009261347,0.004203923,0.00005101708,0.00011732237],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002347603,0.0001954431,0.00021996816,0.000052489104,0.00009550829,0.00020451262,0.004473574,0.00017914842,0.00015522733],"category_scores_gemma":[0.000016549322,0.00016923406,0.00004044922,0.000031680964,0.00004758754,0.00019775947,0.0026764383,0.00028259782,0.0017987455],"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":[7.120046e-8,0.0000040410355,1.61429e-7,0.0000026855273,0.0000072013177,0.0000026683836,0.0000029143516,1.611204e-7,2.1419646e-7,0.7130093,0.18270399,0.104266584],"study_design_scores_gemma":[0.000036199748,0.000011317108,0.0000038034057,0.000005402573,0.000010192582,0.000012053639,2.0451782e-7,0.064027384,0.0000013559832,0.058688115,0.8770016,0.00020237743],"about_ca_topic_score_codex":0.000026829219,"about_ca_topic_score_gemma":0.000015383608,"teacher_disagreement_score":0.6942976,"about_ca_system_score_codex":0.000020045056,"about_ca_system_score_gemma":0.00008032912,"threshold_uncertainty_score":0.9989785},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000002238632,0.00025058404,0.13970916,0.00033393668,0.00015211018,0.00023054532,0.0104757175,0.00029411822,0.8485516],"genre_scores_gemma":[0.0006170365,0.000014311583,0.93241656,0.0011430297,0.0010017168,0.000016683853,0.0021736436,0.000068779234,0.06254826],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970386,0.000011015854,0.00037745718,0.0016681642,0.0005281421,0.0003765884],"domain_scores_gemma":[0.9896282,0.000052803174,0.00028402254,0.009767734,0.00007419127,0.00019307515],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0002429695,0.00041840787,0.0003857334,0.000054538286,0.00018960274,0.0004723288,0.011212644,0.00017369035,0.000016751954],"category_scores_gemma":[0.000012640517,0.0003737731,0.00003220782,0.000044002983,0.00012909934,0.00054272433,0.008078685,0.00026489125,0.0002929226],"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":[0.0000021499297,0.000006878163,0.000001979568,0.0000066938505,0.00005563611,0.000034229248,0.000013496847,0.0000011946863,5.276382e-7,0.70342326,0.034768578,0.26168537],"study_design_scores_gemma":[0.00023292915,0.00005042986,0.000015368229,0.00018924355,0.00006502407,0.00016708601,0.0000040957043,0.027822612,8.6419385e-7,0.016186314,0.95470643,0.0005596204],"about_ca_topic_score_codex":0.00007465948,"about_ca_topic_score_gemma":0.0003543566,"teacher_disagreement_score":0.91993785,"about_ca_system_score_codex":0.00007801107,"about_ca_system_score_gemma":0.00038052426,"threshold_uncertainty_score":0.9999438},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.2030164e-7,0.000098209515,0.5435548,0.000047419577,0.000109212844,0.00030123594,0.00070701353,0.00033257224,0.4548492],"genre_scores_gemma":[0.00018878595,0.00003617982,0.94930506,0.0005868889,0.00048689617,0.00011062573,0.00056643493,0.000049811875,0.04866932],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99841946,0.000005791163,0.00031496154,0.0007901161,0.0002475818,0.00022211141],"domain_scores_gemma":[0.99763787,0.000044638477,0.00022487124,0.001883395,0.00012428555,0.00008493524],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00013373182,0.0002575121,0.0002526104,0.00005727551,0.00019206986,0.00018432656,0.0022690466,0.00022084199,0.0000023278255],"category_scores_gemma":[0.000022496855,0.00026983442,0.00006684505,0.00002875848,0.000059061604,0.0002055769,0.000949534,0.00008104877,0.000028423552],"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":[9.338566e-7,0.0000044779454,4.1623946e-7,0.000008788762,0.000014953527,0.0000034196833,0.000023699768,6.814452e-8,0.0000023545244,0.7187068,0.06327483,0.21795927],"study_design_scores_gemma":[0.000107975604,0.000066556284,0.0000014933016,0.0001313537,0.00002805935,0.00005707563,0.0000019932424,0.019244159,0.00007696578,0.06017504,0.9197088,0.00040052627],"about_ca_topic_score_codex":0.000022286145,"about_ca_topic_score_gemma":0.000011905891,"teacher_disagreement_score":0.856434,"about_ca_system_score_codex":0.00007303959,"about_ca_system_score_gemma":0.00019220207,"threshold_uncertainty_score":0.9999754},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000053697427,0.00008160451,0.33869356,0.0011361262,0.00008971067,0.00009855392,0.00022379436,0.00013854486,0.6595327],"genre_scores_gemma":[0.000071543924,0.0000933944,0.27941516,0.00034700884,0.00078771665,0.0000038853914,0.0003700692,0.000023894767,0.7188873],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990179,0.000004239495,0.000115344184,0.0005543698,0.0001781149,0.00013001979],"domain_scores_gemma":[0.99875385,0.00003129824,0.00003123541,0.0010853552,0.00004631842,0.00005192282],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002164658,0.00011300948,0.0001194008,0.000049613656,0.00019837765,0.00027361367,0.0016002092,0.00009772696,0.00018145317],"category_scores_gemma":[0.0000037571092,0.00010315097,0.000014469259,0.000022388725,0.00010333794,0.00028897598,0.0026586193,0.00014460494,0.00031765792],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.6078025e-7,0.0000027657475,4.617869e-7,0.000005967936,0.0000122179035,0.0000018596412,0.00012348851,9.598832e-9,0.0000024442493,0.65634,0.06643429,0.27707633],"study_design_scores_gemma":[0.00005716401,0.000015365438,0.000014589203,0.000021045113,0.000008514298,0.000011878914,0.000008548838,0.029550415,0.0000072324424,0.013414007,0.95667523,0.00021600234],"about_ca_topic_score_codex":0.000036384234,"about_ca_topic_score_gemma":0.000016187456,"teacher_disagreement_score":0.89024097,"about_ca_system_score_codex":0.000009857506,"about_ca_system_score_gemma":0.00006488823,"threshold_uncertainty_score":0.42063743},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019301382,0.0012759154,0.41415334,0.00015894725,0.00015491326,0.0012317698,0.001674608,0.00030388674,0.57911646],"genre_scores_gemma":[0.45590088,0.00015709508,0.5213767,0.0011736036,0.0008607012,0.0005636856,0.00053342356,0.00023302829,0.01920087],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99842924,0.00000801402,0.00024608706,0.00090432673,0.0001683189,0.0002440193],"domain_scores_gemma":[0.99845827,0.000034516386,0.00013944281,0.0011696673,0.000060926657,0.0001371904],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00007485828,0.00029370387,0.0003078001,0.00007212977,0.00013694986,0.00019252476,0.00098121,0.00016598719,0.0000026462087],"category_scores_gemma":[0.000007716943,0.00026148208,0.000016167893,0.0000863456,0.00014205521,0.00015745772,0.0009882455,0.00014719262,0.000008295485],"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":[0.000009149315,0.000027921646,0.00032212294,0.0000351598,0.000024102044,0.00004250393,0.00018223272,0.000002449003,0.0000026026405,0.808742,0.00032763052,0.1902821],"study_design_scores_gemma":[0.0042248946,0.0010360644,0.033010986,0.0021445176,0.0005423523,0.0038781874,0.00009805873,0.021225058,0.000098479664,0.37243855,0.5537846,0.0075182645],"about_ca_topic_score_codex":0.00027743564,"about_ca_topic_score_gemma":0.00023092295,"teacher_disagreement_score":0.5599156,"about_ca_system_score_codex":0.00003606436,"about_ca_system_score_gemma":0.00020094363,"threshold_uncertainty_score":0.9999837},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000039802795,0.00086443045,0.35204235,0.00017323821,0.00041346948,0.00015366553,0.00028423793,0.00008138236,0.6459474],"genre_scores_gemma":[0.0004449324,0.00083659193,0.1858538,0.00017715947,0.0009849877,0.000015231162,0.0007570395,0.000045968787,0.8108843],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988121,0.00000532978,0.00023205693,0.0007488554,0.000041496693,0.00016020368],"domain_scores_gemma":[0.9981496,0.000098184486,0.00008543981,0.0016019021,0.000009768358,0.0000551414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023119425,0.00017142034,0.00020079882,0.000092570765,0.00005335417,0.0003577792,0.0015878588,0.0001223102,0.0000652748],"category_scores_gemma":[0.0000035244927,0.00016232295,0.000016708593,0.00002115232,0.00008133281,0.00079063873,0.0025995146,0.00011463442,0.0001256061],"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":[9.71582e-7,0.0000129205555,0.0000203814,0.00000983701,0.000024901527,0.0000048534534,0.00015207159,0.000006498909,2.0995164e-7,0.411599,0.15984406,0.4283243],"study_design_scores_gemma":[0.000092211885,0.000016792863,0.000043269112,0.00008260278,0.000006424586,0.000008601302,0.0000065880754,0.5033706,3.226724e-7,0.0030506984,0.49307874,0.0002431602],"about_ca_topic_score_codex":0.000026164631,"about_ca_topic_score_gemma":0.00077051244,"teacher_disagreement_score":0.5033641,"about_ca_system_score_codex":0.00003264305,"about_ca_system_score_gemma":0.00010150996,"threshold_uncertainty_score":0.6619338},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000051537204,0.000052117994,0.123273805,0.00007192331,0.00044972688,0.00016610659,0.0010938252,0.00023553132,0.8746518],"genre_scores_gemma":[0.013283271,0.000027324348,0.5205166,0.0043415623,0.0013887411,0.00014370444,0.001775156,0.0001890574,0.45833462],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980824,0.0000094257475,0.0003142883,0.000952514,0.00038572948,0.0002556487],"domain_scores_gemma":[0.99654686,0.000057184676,0.00022537351,0.002941241,0.00008453408,0.00014481782],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00014364842,0.00030734483,0.0002479683,0.000074010895,0.00014842056,0.00015349247,0.0028564495,0.00019188205,0.000031817857],"category_scores_gemma":[0.000026055026,0.00030512136,0.000057211804,0.000033217344,0.000055061028,0.00018351781,0.0011562774,0.00018707888,0.0005677998],"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":[0.0000019813942,0.000009249768,6.5277584e-7,0.000003375114,0.000028290233,0.000016955186,0.000048924212,2.3981502e-7,4.1705073e-7,0.8765259,0.03038867,0.092975385],"study_design_scores_gemma":[0.00029558688,0.00011885423,0.00002040745,0.00024407021,0.000045992845,0.000044293356,0.000007199262,0.005323565,0.000011250401,0.4740906,0.51910657,0.0006915981],"about_ca_topic_score_codex":0.00005634712,"about_ca_topic_score_gemma":0.000030211908,"teacher_disagreement_score":0.4887179,"about_ca_system_score_codex":0.000077858655,"about_ca_system_score_gemma":0.00015749909,"threshold_uncertainty_score":0.9999401},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000005577,0.00006440981,0.75803334,0.00006183964,0.00010904392,0.00031962452,0.0007186419,0.00015787173,0.24052963],"genre_scores_gemma":[0.028931431,0.00004290615,0.7539884,0.002331421,0.0012271215,0.00038618574,0.004796744,0.0002686578,0.20802714],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99844015,0.000025150115,0.00026934745,0.00085644994,0.00019327308,0.00021565385],"domain_scores_gemma":[0.9985222,0.00011006897,0.00024015654,0.0008478896,0.00016532873,0.000114308474],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00028512315,0.00027411227,0.00028155753,0.000051122308,0.00028538232,0.00027478457,0.0009504732,0.00019139342,0.000004234622],"category_scores_gemma":[0.000060744333,0.0002806577,0.000039337632,0.000028565519,0.000098704615,0.00018891599,0.0006582447,0.00013544121,0.000013478101],"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":[0.000006023716,0.000006152019,0.0000020965292,0.00001288164,0.000026623446,0.0000022742913,0.00009198904,0.000007178258,0.000004247082,0.8928998,0.0031067294,0.103833966],"study_design_scores_gemma":[0.00077845284,0.00052543916,0.00001043139,0.00032888044,0.00011507145,0.000020739937,0.00003377396,0.44894683,0.00005698694,0.046851035,0.5014426,0.00088975107],"about_ca_topic_score_codex":0.000057727357,"about_ca_topic_score_gemma":0.000043308748,"teacher_disagreement_score":0.8460488,"about_ca_system_score_codex":0.000047513888,"about_ca_system_score_gemma":0.00023662327,"threshold_uncertainty_score":0.99996454},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032696974,0.0019501211,0.94506705,0.0059745125,0.0028508087,0.0015832889,0.009196018,0.00035540204,0.0003258171],"genre_scores_gemma":[0.7188888,0.0035711813,0.2490804,0.0020079503,0.00066021,0.0009169281,0.02326884,0.00017271117,0.00143293],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99627197,0.00014055351,0.00045440826,0.00149163,0.0008637125,0.000777717],"domain_scores_gemma":[0.99776995,0.000121206576,0.00037342755,0.0013974848,0.00017413528,0.00016376666],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009583732,0.00038599566,0.00031076578,0.00027933097,0.0008568998,0.00046533707,0.0034464863,0.00010122009,0.00010913577],"category_scores_gemma":[0.00005750013,0.00042142384,0.000069577785,0.00050081336,0.000047058544,0.00072380033,0.0021321513,0.0013294084,0.000017480077],"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":[0.00009413601,0.0004283183,0.000031769385,0.000016965098,0.00026889436,0.000009611497,0.00020648299,0.020793358,0.017423332,0.80658495,0.004280067,0.14986213],"study_design_scores_gemma":[0.0004745146,0.00026739924,0.000005706813,0.000015998296,0.000026444892,0.00005395498,0.0001226707,0.75798047,0.0021238623,0.003729716,0.23484321,0.0003560617],"about_ca_topic_score_codex":0.00009710729,"about_ca_topic_score_gemma":0.00009694326,"teacher_disagreement_score":0.80285525,"about_ca_system_score_codex":0.000901856,"about_ca_system_score_gemma":0.001054039,"threshold_uncertainty_score":0.99982375},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007353962,0.00001424754,0.9841916,0.00076871243,0.00011128704,0.00013690797,0.0000040581717,0.00019688079,0.0072223325],"genre_scores_gemma":[0.29346237,0.0000025819709,0.69652385,0.0003107778,0.000056743047,0.0006339305,0.00007994152,0.000008922337,0.008920927],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99940264,0.00002428617,0.00009634876,0.00023803102,0.00012278717,0.00011590402],"domain_scores_gemma":[0.99955326,0.00010952421,0.000044914315,0.00024204378,0.000023476521,0.000026786376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002286563,0.00003990698,0.00004766991,0.000058875365,0.00051580527,0.00008546987,0.00041238443,0.0000069716816,0.00003437682],"category_scores_gemma":[0.000030084462,0.000041828716,0.000032075626,0.00035426897,0.0000076209694,0.00019177454,0.000254295,0.000061044375,0.0000052754563],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004519709,0.00010284077,0.0029818744,0.000005673384,0.000018899482,0.0000013125112,0.002879385,0.004972263,0.0012573785,0.16055523,0.10519486,0.72202575],"study_design_scores_gemma":[0.00018701998,0.00008413967,0.0006383183,9.1413233e-7,0.000002646478,0.000008435144,0.0010038088,0.7562255,0.00040116342,0.0013894569,0.23996317,0.00009538099],"about_ca_topic_score_codex":0.00003329112,"about_ca_topic_score_gemma":0.0000016466662,"teacher_disagreement_score":0.7512533,"about_ca_system_score_codex":0.000014292099,"about_ca_system_score_gemma":0.000019491266,"threshold_uncertainty_score":0.39672092},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013680064,0.000013645752,0.98359543,0.0003051877,0.00014519865,0.000303144,0.00013566857,0.000118256496,0.0017033849],"genre_scores_gemma":[0.8683936,0.000013268274,0.1304892,0.0002578365,0.000041308955,0.00059290434,0.00013136158,0.000011719288,0.000068779824],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984147,0.000037444224,0.0003121651,0.0005947826,0.00032192326,0.00031898436],"domain_scores_gemma":[0.99898463,0.00012513435,0.00006934051,0.00073500647,0.000017364713,0.00006854472],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031846509,0.00013654341,0.00013655519,0.00009941138,0.00021673822,0.00010827909,0.0013791478,0.000015130885,0.0003314702],"category_scores_gemma":[0.000018711036,0.0001408121,0.000028057866,0.00067034486,0.00005016754,0.0002309751,0.0013484644,0.0002603745,0.00006553067],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000070506694,0.00020776184,0.00039180988,0.000015671423,0.00000702525,0.000026820579,0.0006473222,0.003671201,0.00093735446,0.8494528,0.00017171806,0.1444635],"study_design_scores_gemma":[0.00029559497,0.00014599445,0.0015476758,0.00004896401,0.000013712251,0.00006527094,0.0015052919,0.89347225,0.013353903,0.041533824,0.046955563,0.0010619255],"about_ca_topic_score_codex":0.0003389154,"about_ca_topic_score_gemma":0.000053116368,"teacher_disagreement_score":0.8898011,"about_ca_system_score_codex":0.0001165732,"about_ca_system_score_gemma":0.00008925125,"threshold_uncertainty_score":0.5742151},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014555853,0.00019059352,0.99369067,0.0029894442,0.001333766,0.0005035236,0.00014845292,0.00017698236,0.00082101405],"genre_scores_gemma":[0.003271604,0.00004210124,0.9929347,0.003025506,0.00029030436,0.000089983885,0.00004948731,0.000043337466,0.0002529787],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953701,0.0000406808,0.00056037476,0.0020196494,0.0012571026,0.00075208856],"domain_scores_gemma":[0.99697274,0.0004778831,0.00012389812,0.0018575169,0.0001969787,0.00037096828],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00068363664,0.000523563,0.00051477953,0.0008013538,0.00041585494,0.00056717393,0.0044837524,0.00015194643,0.0001390224],"category_scores_gemma":[0.00008516423,0.00050185405,0.00013212716,0.0009624089,0.00034017314,0.0005649889,0.0030843904,0.00083314214,0.00015656804],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024626506,0.00007087556,0.000020509,0.000013872294,0.00001381599,0.00012265665,0.00097244466,0.004501467,0.00007552728,0.04917092,0.00013701212,0.9448984],"study_design_scores_gemma":[0.00028630823,0.00062769995,0.00026153657,0.0002351131,0.000014427552,0.00009452767,0.0000011834578,0.941259,0.00054896995,0.028627302,0.02697274,0.0010711406],"about_ca_topic_score_codex":0.00017710567,"about_ca_topic_score_gemma":0.00008591486,"teacher_disagreement_score":0.9438273,"about_ca_system_score_codex":0.00044434855,"about_ca_system_score_gemma":0.00045028277,"threshold_uncertainty_score":0.9997433},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008506729,0.004604711,0.99157447,0.000334734,0.0006808721,0.00026364397,0.00003047896,0.00006468397,0.0023613484],"genre_scores_gemma":[0.005059923,0.00075856666,0.99234456,0.00037782133,0.00044952775,0.000035347686,0.00007642075,0.000023399165,0.00087444886],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99679077,0.000036370537,0.0003858858,0.0018951333,0.00037781915,0.0005140099],"domain_scores_gemma":[0.9966255,0.0006501769,0.0001634044,0.0023830305,0.000066823355,0.00011107853],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0007860122,0.00032903586,0.00037951066,0.0005417723,0.00016149804,0.0012023171,0.0060868845,0.00014783784,0.000002218932],"category_scores_gemma":[0.00011355641,0.0002920011,0.000022417735,0.0010934259,0.0005481337,0.004357978,0.00555246,0.00046795537,0.000021008422],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.5124538e-7,0.000026380734,0.00008155277,0.000031368538,0.0000012227786,0.0000084644835,0.00050097797,0.00037520047,0.000005782072,0.0013414869,0.0003160623,0.9973112],"study_design_scores_gemma":[0.00016507343,0.000045651657,0.00039562146,0.00050082646,0.0000029279095,0.00003025225,6.926754e-7,0.9596035,0.000029690125,0.020555986,0.018216241,0.00045356498],"about_ca_topic_score_codex":0.000029118019,"about_ca_topic_score_gemma":0.00024841976,"teacher_disagreement_score":0.9968576,"about_ca_system_score_codex":0.00014563161,"about_ca_system_score_gemma":0.000797875,"threshold_uncertainty_score":0.9999532},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033186395,0.0002843466,0.38832366,0.09736188,0.01267495,0.0029109158,0.0026928314,0.0014594574,0.46110556],"genre_scores_gemma":[0.013903431,0.000068343135,0.97619456,0.00043722088,0.0003583329,0.000060838647,0.00013090893,0.000015517982,0.008830834],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982857,0.0000062525446,0.00030525523,0.00076909875,0.0004794781,0.00015421133],"domain_scores_gemma":[0.99665195,0.00017730461,0.00029846418,0.002676491,0.00014714168,0.000048674006],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00029904742,0.00017032452,0.00016537747,0.00008187412,0.00007315618,0.00030672742,0.01515312,0.00012717013,0.000046665074],"category_scores_gemma":[0.0004783275,0.00011764122,0.00005802749,0.00022407935,0.000065452616,0.0002968916,0.019132454,0.00041674305,0.000033203254],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021940152,0.0002447323,0.0005330167,0.000037655263,0.000095277144,7.7945583e-7,0.0016843195,0.00006478677,0.00009525095,0.011641941,0.41019621,0.5754038],"study_design_scores_gemma":[0.00014370639,0.000007683552,0.0019302046,0.00034616163,0.000012509314,0.0000041555613,0.00012948319,0.94872314,0.00034747252,0.0011705903,0.046956677,0.0002282395],"about_ca_topic_score_codex":0.000027875658,"about_ca_topic_score_gemma":0.0000036749448,"teacher_disagreement_score":0.94865835,"about_ca_system_score_codex":0.000027947051,"about_ca_system_score_gemma":0.00004955864,"threshold_uncertainty_score":0.99017537},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.232988,0.000010075233,0.7647056,0.00044877172,0.00010829272,0.000038799328,0.000014797743,0.000057325575,0.0016283586],"genre_scores_gemma":[0.75303113,3.662814e-7,0.24673831,0.000104773455,0.000005895917,0.00001928996,0.0000047888525,0.000002791806,0.00009265429],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993758,0.00003098487,0.0001524624,0.00018166249,0.00014992579,0.00010911749],"domain_scores_gemma":[0.99948174,0.00016346891,0.00003138954,0.0002675434,0.0000240596,0.000031807012],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016891767,0.000044888184,0.00007309899,0.000046312376,0.00012028731,0.000028623639,0.0005712548,0.000006719919,0.00007163525],"category_scores_gemma":[0.000038675273,0.000043079963,0.000023926972,0.0002287198,0.000018249491,0.0001346625,0.0007183682,0.000073270654,0.0000068505947],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000052283654,0.00024283837,0.0065275785,0.000016596614,0.00003317801,0.000013661154,0.005736963,0.0002821855,0.002495929,0.7825875,0.0035138098,0.1985445],"study_design_scores_gemma":[0.00018577396,0.00023220782,0.006749411,0.0000149935795,0.000004840106,0.000017602919,0.002263506,0.98469615,0.0013331424,0.0009284111,0.003427393,0.00014655375],"about_ca_topic_score_codex":0.00006525904,"about_ca_topic_score_gemma":0.0000045027678,"teacher_disagreement_score":0.984414,"about_ca_system_score_codex":0.000013962112,"about_ca_system_score_gemma":0.00002417318,"threshold_uncertainty_score":0.17567499},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37525392,0.00017716839,0.57350343,0.0020867654,0.0018509232,0.0011291443,0.00016972687,0.0004241471,0.045404773],"genre_scores_gemma":[0.97107923,0.00013939303,0.013699052,0.000045408553,0.000100903606,0.000002901257,0.000014852887,0.000013741111,0.014904507],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986647,0.000013706286,0.00015966406,0.0008149983,0.00010626259,0.00024068862],"domain_scores_gemma":[0.9970889,0.000042305852,0.00056968565,0.00196588,0.0002395874,0.00009366003],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00023061631,0.0002121114,0.00024816705,0.00008929207,0.0003722378,0.0002459766,0.0060787583,0.00019305406,0.000013994484],"category_scores_gemma":[0.00007305654,0.0001869653,0.0001955172,0.00028269217,0.00022775981,0.00044300006,0.004712391,0.00048366105,0.00007692912],"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":[0.000016918142,0.00038358156,0.0070332997,0.0002615675,0.000275628,0.00002274709,0.0013575181,0.0077067553,0.0003407382,0.89572644,0.07384796,0.013026843],"study_design_scores_gemma":[0.00114105,0.00004935872,0.029995136,0.0012495627,0.0003718943,0.000025074676,0.00026783376,0.5379635,0.0009825116,0.22841328,0.19750935,0.002031446],"about_ca_topic_score_codex":0.00009404601,"about_ca_topic_score_gemma":0.000028699886,"teacher_disagreement_score":0.66731316,"about_ca_system_score_codex":0.00005602161,"about_ca_system_score_gemma":0.00015099745,"threshold_uncertainty_score":0.9992988},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52898365,0.0029850362,0.23624706,0.0863855,0.0015130093,0.005061087,0.0045431447,0.00036028677,0.13392124],"genre_scores_gemma":[0.968535,0.0007251098,0.025626037,0.000047984602,0.00003325578,0.000085260945,0.0007843989,0.000026341191,0.0041366313],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99701524,0.00056090124,0.0004690743,0.0013202677,0.00037827593,0.0002562253],"domain_scores_gemma":[0.9941589,0.0015518317,0.00048990175,0.0032385024,0.00048737923,0.00007345794],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0030706648,0.0003125733,0.0003271867,0.00021061175,0.00022599277,0.0012555291,0.0054865046,0.00013508854,0.000009565812],"category_scores_gemma":[0.0005064542,0.00022041751,0.000030923686,0.00058295735,0.00049377925,0.0010093505,0.00808835,0.0006971109,0.00000416815],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015892336,0.005570761,0.024458472,0.0006634603,0.00029434214,0.0000066938587,0.076061174,0.0001254291,0.0023625772,0.26521975,0.046936315,0.5781421],"study_design_scores_gemma":[0.00095165457,0.0000029872024,0.056176357,0.0046218717,0.000028975728,0.00001123506,0.0016311257,0.9269123,0.0006437876,0.00040330805,0.00816566,0.0004507482],"about_ca_topic_score_codex":0.0002691344,"about_ca_topic_score_gemma":0.002309991,"teacher_disagreement_score":0.92678684,"about_ca_system_score_codex":0.000081302496,"about_ca_system_score_gemma":0.00019512934,"threshold_uncertainty_score":0.999934},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000013276453,0.0007130206,0.99610794,0.00062264135,0.00029425288,0.00054370525,0.000050278497,0.0001555151,0.0014993869],"genre_scores_gemma":[0.00046459155,0.000086503635,0.99735826,0.0006872165,0.00039730914,0.000111957954,0.0001153517,0.000020085643,0.00075869175],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967076,0.000019930225,0.0003576517,0.001950562,0.00048710415,0.0004771483],"domain_scores_gemma":[0.99539083,0.00045439962,0.00020476033,0.0036426107,0.00013122857,0.00017616068],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0005437922,0.0003222741,0.00032311017,0.00037120207,0.00032849232,0.0008864329,0.0068729855,0.0001566301,0.000005404572],"category_scores_gemma":[0.000061537554,0.0003030749,0.000024254054,0.00095797563,0.00053799985,0.0013348825,0.0049539357,0.00035965213,0.000041441122],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.741545e-7,0.00001484452,0.000007835268,0.000016738164,0.0000030471497,0.0000024768235,0.0001435772,0.00032187277,0.000019084287,0.0017258043,0.0006756678,0.9970689],"study_design_scores_gemma":[0.00014497602,0.000039201037,0.00009251352,0.00014750838,0.000006376551,0.000044432123,3.7544143e-7,0.9155863,0.000052940904,0.02528962,0.058124166,0.00047161887],"about_ca_topic_score_codex":0.000014705982,"about_ca_topic_score_gemma":0.000026244257,"teacher_disagreement_score":0.99659723,"about_ca_system_score_codex":0.00011330349,"about_ca_system_score_gemma":0.00069727475,"threshold_uncertainty_score":0.9999421},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008506729,0.004604711,0.99157447,0.000334734,0.0006808721,0.00026364397,0.00003047896,0.00006468397,0.0023613484],"genre_scores_gemma":[0.005059923,0.00075856666,0.99234456,0.00037782133,0.00044952775,0.000035347686,0.00007642075,0.000023399165,0.00087444886],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99679077,0.000036370537,0.0003858858,0.0018951333,0.00037781915,0.0005140099],"domain_scores_gemma":[0.9966255,0.0006501769,0.0001634044,0.0023830305,0.000066823355,0.00011107853],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0007860122,0.00032903586,0.00037951066,0.0005417723,0.00016149804,0.0012023171,0.0060868845,0.00014783784,0.000002218932],"category_scores_gemma":[0.00011355641,0.0002920011,0.000022417735,0.0010934259,0.0005481337,0.004357978,0.00555246,0.00046795537,0.000021008422],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.5124538e-7,0.000026380734,0.00008155277,0.000031368538,0.0000012227786,0.0000084644835,0.00050097797,0.00037520047,0.000005782072,0.0013414869,0.0003160623,0.9973112],"study_design_scores_gemma":[0.00016507343,0.000045651657,0.00039562146,0.00050082646,0.0000029279095,0.00003025225,6.926754e-7,0.9596035,0.000029690125,0.020555986,0.018216241,0.00045356498],"about_ca_topic_score_codex":0.000029118019,"about_ca_topic_score_gemma":0.00024841976,"teacher_disagreement_score":0.9968576,"about_ca_system_score_codex":0.00014563161,"about_ca_system_score_gemma":0.000797875,"threshold_uncertainty_score":0.9999532},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017972913,0.00007893882,0.929943,0.0006697316,0.00018549552,0.00004182852,0.000040122064,0.0001951699,0.050872765],"genre_scores_gemma":[0.31118223,0.000007181192,0.68305886,0.0007446683,0.0003330867,0.000021095611,0.000046005047,0.0000055265114,0.0046013575],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99952865,0.000009214409,0.000070335416,0.00013503121,0.000091466485,0.00016531938],"domain_scores_gemma":[0.9994453,0.000025924357,0.000018068178,0.00040944532,0.000009104282,0.000092151924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000084387306,0.000049791142,0.00004924167,0.00001542388,0.000063811734,0.00007056198,0.00043654753,0.000019562478,0.00017795962],"category_scores_gemma":[0.0000035205169,0.00004096303,0.00001823833,0.00007783269,0.000013007522,0.0003223906,0.000114962284,0.00003713467,0.0004954325],"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":[4.452579e-7,0.00015257798,0.0038729138,0.0000011841431,0.000017910379,0.0000014963234,0.00084072456,0.0000047444732,0.0022602219,0.5516733,0.19189438,0.24928014],"study_design_scores_gemma":[0.0003107923,0.000020549423,0.04709024,0.000004764118,0.000007571439,0.0000076838605,0.00007500852,0.09868953,0.011181342,0.0045436854,0.83765936,0.00040947582],"about_ca_topic_score_codex":0.00018902162,"about_ca_topic_score_gemma":0.0000029037928,"teacher_disagreement_score":0.645765,"about_ca_system_score_codex":0.000007479845,"about_ca_system_score_gemma":0.000008441495,"threshold_uncertainty_score":0.63679475},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006059787,0.008800124,0.89108723,0.027806707,0.0011247192,0.0020104842,0.0007440588,0.0012016381,0.061165225],"genre_scores_gemma":[0.015798882,0.0031108232,0.9557006,0.000637328,0.00010656503,0.00024414406,0.002918122,0.00011541544,0.021368127],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99151313,0.0030446039,0.0010809964,0.0026913283,0.0007991009,0.0008708569],"domain_scores_gemma":[0.9847517,0.003362005,0.00094106584,0.009138315,0.0012214041,0.000585515],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0063233147,0.0007564732,0.00081073184,0.00031645686,0.0008396885,0.0019446191,0.006868446,0.00050740346,0.000451917],"category_scores_gemma":[0.0027216312,0.0008243485,0.00018837496,0.0010766964,0.000549864,0.0006795834,0.007973567,0.0011912787,0.00014563503],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013308021,0.0009400615,0.00043142994,0.0003083472,0.00023273772,0.000023995191,0.01096554,0.00009596538,0.0005931958,0.01916083,0.12981217,0.83742243],"study_design_scores_gemma":[0.0013282908,0.0000010042249,0.0029610104,0.0038225634,0.00012579934,0.00004825528,0.0005333061,0.6397528,0.0005550715,0.0005543113,0.348712,0.0016056217],"about_ca_topic_score_codex":0.00037375902,"about_ca_topic_score_gemma":0.00064672186,"teacher_disagreement_score":0.8358168,"about_ca_system_score_codex":0.00012450501,"about_ca_system_score_gemma":0.00041781884,"threshold_uncertainty_score":0.99942076},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027723275,0.00049244013,0.905986,0.012943837,0.00034399645,0.00050799176,0.00007635333,0.00070739357,0.051218722],"genre_scores_gemma":[0.21707787,0.0001819826,0.7767637,0.00013985498,0.000058357567,0.00016572047,0.00053818274,0.00004817129,0.0050262003],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9944485,0.0025232865,0.0006437562,0.0013594895,0.0005097697,0.0005152323],"domain_scores_gemma":[0.99180627,0.0010110926,0.00061045535,0.004759356,0.0015468978,0.00026590124],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0040210476,0.0004120659,0.00044275747,0.00022890535,0.0006485692,0.0018085391,0.004226464,0.0002607801,0.00008682697],"category_scores_gemma":[0.00072256394,0.00044842664,0.00022119704,0.0006033043,0.00030491612,0.00048036902,0.004499495,0.00084452913,0.0001851305],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014285761,0.0004737344,0.0001994687,0.00011733856,0.00007031403,0.0000042311426,0.0074316235,0.000066766814,0.0018204285,0.42692405,0.006975826,0.5559148],"study_design_scores_gemma":[0.000596507,7.0265503e-7,0.00783867,0.002617499,0.000054081454,0.000043230386,0.00010900636,0.8689582,0.030475982,0.059488885,0.028462261,0.0013550244],"about_ca_topic_score_codex":0.00462341,"about_ca_topic_score_gemma":0.00064909714,"teacher_disagreement_score":0.86889136,"about_ca_system_score_codex":0.00015263112,"about_ca_system_score_gemma":0.00036653123,"threshold_uncertainty_score":0.99979675},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00051691884,0.00001006895,0.99427485,0.0006694006,0.00006980287,0.00022057738,0.00002145858,0.00014963232,0.00406731],"genre_scores_gemma":[0.16651551,4.9326707e-7,0.8319668,0.00028753342,0.000025043057,0.0007551019,0.00009125255,0.00000576062,0.00035248496],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991776,0.000019165485,0.00013215291,0.00034396048,0.00019430104,0.00013283364],"domain_scores_gemma":[0.9992098,0.00015004408,0.00005105469,0.00051570765,0.000032417665,0.00004095802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038968917,0.000059529517,0.000063961605,0.00007821088,0.00043396535,0.0001146516,0.00076314807,0.000014192164,0.000017153521],"category_scores_gemma":[0.000024333585,0.000055907538,0.00004343955,0.00038862543,0.00000956652,0.00016729672,0.0001979999,0.000059021146,0.000005422957],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004217828,0.00014762179,0.000025934542,0.0000035034911,0.0000028233717,1.4002279e-7,0.000065992295,0.0031538552,0.0008409768,0.09562033,0.010365497,0.88976914],"study_design_scores_gemma":[0.00024739775,0.00004231847,0.0002555775,8.6372387e-7,0.0000023226823,0.0000014815024,0.000084716456,0.9753599,0.00027378518,0.001189366,0.022463242,0.00007902857],"about_ca_topic_score_codex":0.000010384189,"about_ca_topic_score_gemma":0.0000014648348,"teacher_disagreement_score":0.97220606,"about_ca_system_score_codex":0.0000462405,"about_ca_system_score_gemma":0.00005460439,"threshold_uncertainty_score":0.33377546},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008275791,0.00033272067,0.49199575,0.00032597274,0.000622815,0.00066117925,0.0022899734,0.0002155967,0.5034732],"genre_scores_gemma":[0.0029314265,0.000022700471,0.9666027,0.0007284334,0.0005855047,0.00014551132,0.0002753654,0.00005471963,0.028653668],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979946,0.000011276532,0.0003903023,0.0008502324,0.00039395745,0.00035965003],"domain_scores_gemma":[0.99764043,0.00023097543,0.00034443074,0.0016050378,0.00008718361,0.00009191428],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00031613765,0.00025707477,0.0003249509,0.00007035224,0.00014340924,0.00018579743,0.0016670509,0.00037980673,0.0000025718273],"category_scores_gemma":[0.00014029234,0.00028062213,0.00008152696,0.000052428717,0.000028600705,0.00008700568,0.00087016047,0.00024397454,0.000069721624],"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":[0.0000021774567,0.000017285445,0.000009639708,0.000008778485,0.000024664116,0.000010802824,0.00009788971,0.000019107922,5.059614e-7,0.9323875,0.009927753,0.05749393],"study_design_scores_gemma":[0.00068165583,0.00008701222,0.00016465267,0.00063646876,0.000058535337,0.000043702126,0.000016449088,0.11403898,0.00001023552,0.46598223,0.41727644,0.0010036456],"about_ca_topic_score_codex":0.000043336655,"about_ca_topic_score_gemma":0.000031283125,"teacher_disagreement_score":0.47481957,"about_ca_system_score_codex":0.00040762467,"about_ca_system_score_gemma":0.0002463669,"threshold_uncertainty_score":0.9999646},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011078968,0.0001789341,0.98955435,0.003876404,0.00021314963,0.0016822184,0.0008490761,0.00022810862,0.0023098635],"genre_scores_gemma":[0.13909326,0.00005678228,0.8498395,0.00018263335,0.00010848008,0.00048285106,0.009030921,0.00005576153,0.0011497722],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99368244,0.0019510179,0.00073815195,0.0023254005,0.0007713587,0.0005316545],"domain_scores_gemma":[0.9895857,0.00046122447,0.00037350948,0.008571817,0.0003612482,0.0006465025],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.005818766,0.00047352078,0.0004859625,0.00034423056,0.00026085036,0.0010281974,0.009227303,0.00027285906,0.0000164657],"category_scores_gemma":[0.00053898804,0.0005280049,0.000069327034,0.0007610323,0.000078450175,0.00057649513,0.012109954,0.0005851747,0.00023816174],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002350049,0.0016103773,0.000434511,0.000075221695,0.000048829315,0.0000034190314,0.0107877515,0.0054767723,0.0026228225,0.013722683,0.017763257,0.94743085],"study_design_scores_gemma":[0.0007559375,0.0000022330028,0.0046208487,0.00047577915,0.00003758599,0.000011540933,0.0001200494,0.9528849,0.007143602,0.0022110315,0.030762484,0.0009740092],"about_ca_topic_score_codex":0.01690479,"about_ca_topic_score_gemma":0.0027040106,"teacher_disagreement_score":0.94740814,"about_ca_system_score_codex":0.00030333202,"about_ca_system_score_gemma":0.00072248734,"threshold_uncertainty_score":0.9997172},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00732005,0.00016567574,0.98981285,0.001646024,0.00039870053,0.000050274368,0.0005435426,0.000006031073,0.000056863923],"genre_scores_gemma":[0.6129434,0.000010794549,0.38660127,0.00017661207,0.00020676987,0.0000013402812,0.000038741004,0.0000062907798,0.000014801824],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991197,0.00008649743,0.0002866445,0.000120976445,0.00029508295,0.00009112215],"domain_scores_gemma":[0.9985976,0.00018148308,0.0004101214,0.0006779286,0.00009638965,0.000036468435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064956944,0.000048274243,0.000099899094,0.000071305214,0.00031322334,0.00007495211,0.0020001067,0.000008574424,0.00000441755],"category_scores_gemma":[0.00007388121,0.000034630226,0.00003658468,0.00029626235,0.00004032668,0.0004606111,0.0012364844,0.00017085928,5.6294977e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000211902,0.00051398436,0.0007461506,0.000009719886,0.00017547478,0.000037697795,0.0032259533,0.008379313,0.0032431446,0.0021819652,0.030579805,0.9508856],"study_design_scores_gemma":[0.00026384924,0.000065085995,0.00059148617,0.00002147033,0.000022308159,0.00028675422,0.0007602313,0.9752642,0.00015853213,0.0011799613,0.021328598,0.00005755514],"about_ca_topic_score_codex":0.00003449182,"about_ca_topic_score_gemma":0.000002411026,"teacher_disagreement_score":0.96688485,"about_ca_system_score_codex":0.00003008649,"about_ca_system_score_gemma":0.00015456889,"threshold_uncertainty_score":0.3716729},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02590994,0.000060412032,0.8863432,0.0856034,0.0006901848,0.0003528875,0.00009484245,0.00045145964,0.0004936737],"genre_scores_gemma":[0.3049092,0.0000074965137,0.6744365,0.017088741,0.00034553386,0.0013988529,0.0003911996,0.00003600204,0.0013864432],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984572,0.00009051751,0.0002539345,0.0004958439,0.00040411856,0.0002984201],"domain_scores_gemma":[0.9981133,0.00023431043,0.00009561512,0.0014230849,0.000045182976,0.00008851895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024511263,0.0001459361,0.00012362769,0.00015849061,0.0011346235,0.000165658,0.0014549644,0.000026429767,0.00026553226],"category_scores_gemma":[0.00008149783,0.00015391229,0.000067241956,0.0007123972,0.000034677327,0.00089449564,0.0015031989,0.0002694154,0.00042315378],"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":[0.0000054293832,0.00037800323,0.00047023757,0.0000047368026,0.000049363847,0.000055602875,0.0032685648,0.0071844724,0.008874969,0.1003354,0.8149069,0.064466305],"study_design_scores_gemma":[0.000477965,0.00008666827,0.00070568774,0.000005104156,0.000012069259,0.00005239129,0.0003280089,0.13893926,0.0011994814,0.0052950033,0.8524459,0.0004524876],"about_ca_topic_score_codex":0.000020865893,"about_ca_topic_score_gemma":0.0000029988848,"teacher_disagreement_score":0.27899927,"about_ca_system_score_codex":0.000071928094,"about_ca_system_score_gemma":0.00006901292,"threshold_uncertainty_score":0.8726722},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44253817,0.000013811622,0.5549192,0.00018295734,0.00037944532,0.00042659658,0.0013026769,0.00017923658,0.000057923648],"genre_scores_gemma":[0.9627589,0.00001194399,0.03561949,0.0001481829,0.000074436364,0.00005040285,0.0009387827,0.000019054309,0.0003788138],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99752104,0.00014756445,0.00027801696,0.0015646091,0.00013381313,0.0003549638],"domain_scores_gemma":[0.9975464,0.0002870587,0.00032808972,0.0015764646,0.00013649854,0.00012552613],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00031235075,0.00030820063,0.00034055838,0.00018555803,0.000363877,0.00026011612,0.0026230118,0.00014859045,0.00018985428],"category_scores_gemma":[0.000040833092,0.00035253065,0.00024784377,0.00038195768,0.000086298016,0.00028857368,0.0022126164,0.00039622292,0.000010245146],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008748264,0.006517343,0.24148591,0.0022244554,0.0032748505,0.0014348815,0.014175606,0.25813124,0.00061914534,0.29201937,0.018598761,0.16064362],"study_design_scores_gemma":[0.0005483499,0.000096828924,0.008801592,0.00012431406,0.000088933484,8.1277886e-7,0.0002960117,0.9709378,0.0001592734,0.014982632,0.003462691,0.0005007465],"about_ca_topic_score_codex":0.002806397,"about_ca_topic_score_gemma":0.00016548276,"teacher_disagreement_score":0.7128066,"about_ca_system_score_codex":0.0002636059,"about_ca_system_score_gemma":0.00047997283,"threshold_uncertainty_score":0.99989265},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021027006,0.00088869093,0.9431216,0.0054598954,0.00024941383,0.00019273804,0.000027669663,0.00021352178,0.028819434],"genre_scores_gemma":[0.033393115,0.00006735031,0.9634727,0.0014653112,0.000077628014,0.000004648071,0.000007871454,0.0000049933324,0.0015063568],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991683,0.000020161608,0.00013846128,0.0004104323,0.000104638195,0.00015804793],"domain_scores_gemma":[0.9967964,0.0020182927,0.00005886669,0.0010065029,0.000051481526,0.0000684311],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011711977,0.00007627191,0.00008091489,0.000042278156,0.00017316977,0.0001592204,0.00050036644,0.00002252095,0.0000075223475],"category_scores_gemma":[0.0006098909,0.000061656654,0.0000056796066,0.0002090304,0.000041854484,0.0008909989,0.00086661166,0.00007611173,0.000018355182],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000047567983,0.000055867942,0.000009718146,0.000009295235,0.000042691696,0.0008045088,0.0018271273,8.520633e-7,0.000031933585,0.021065647,0.02698273,0.94916487],"study_design_scores_gemma":[0.0010646908,0.00022907658,0.0007110033,0.00014775724,0.00007642008,0.018964725,0.03371202,0.09252556,0.00054443587,0.000986998,0.85010165,0.00093565235],"about_ca_topic_score_codex":0.000007976815,"about_ca_topic_score_gemma":0.00008097855,"teacher_disagreement_score":0.9482292,"about_ca_system_score_codex":0.00000957339,"about_ca_system_score_gemma":0.000015775331,"threshold_uncertainty_score":0.2514285},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004464051,0.00004355548,0.97950804,0.003625437,0.00006279371,0.000048234804,0.000009586595,0.00024894119,0.011989334],"genre_scores_gemma":[0.11949387,0.000009409864,0.8787615,0.00082738145,0.00005968086,0.0000019772608,0.000051245643,0.0000022989777,0.0007926552],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992949,0.000009328828,0.00010927134,0.00033881678,0.00011441998,0.00013330313],"domain_scores_gemma":[0.9984943,0.00003142179,0.00002878127,0.001367104,0.000019942476,0.00005841538],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016855757,0.000056993547,0.00005837542,0.00002760705,0.00009496098,0.00017560287,0.0017094566,0.000021280617,0.00002136436],"category_scores_gemma":[0.000022494665,0.00004553185,0.000010245727,0.00021989239,0.000008430457,0.00089447637,0.0002878787,0.000043456625,0.000102441525],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.5556625e-7,0.000032128777,0.000023032091,4.5249024e-7,0.000001078124,0.0000017221873,0.00007413631,0.00000148026,0.00025236025,0.01416275,0.020800438,0.9646503],"study_design_scores_gemma":[0.00020226793,0.00006302355,0.0068254876,0.000021179654,0.0000052667096,0.00002571121,0.00011745526,0.87768614,0.0010561841,0.0029382932,0.11081969,0.00023928816],"about_ca_topic_score_codex":0.0000073148462,"about_ca_topic_score_gemma":0.000002637516,"teacher_disagreement_score":0.96441096,"about_ca_system_score_codex":0.0000048711977,"about_ca_system_score_gemma":0.000024444424,"threshold_uncertainty_score":0.3176624},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24959062,0.00005960484,0.6022164,0.023684777,0.001492959,0.0011707006,0.00027026847,0.00032809045,0.12118657],"genre_scores_gemma":[0.94715333,0.000026915033,0.04765729,0.0038983054,0.000115901814,0.00013099433,0.000076276156,0.00001566564,0.0009253411],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99870265,0.00005197112,0.00036240066,0.00023335272,0.0004414862,0.00020813954],"domain_scores_gemma":[0.9992005,0.00015453367,0.00019223877,0.00029511415,0.00006318672,0.00009443346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000726531,0.00014646265,0.00013415946,0.00018534472,0.0007432019,0.0004617634,0.0009323563,0.000018446768,0.00006603891],"category_scores_gemma":[0.000030918905,0.00012791119,0.000031561478,0.00026555028,0.000033147713,0.00018268204,0.0012153673,0.0003057208,0.000025580463],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013493054,0.00017869456,0.00009766289,0.000018141323,0.000072098905,0.00000190841,0.011822923,0.005619111,0.000040819126,0.74116755,0.012111026,0.22885656],"study_design_scores_gemma":[0.00016532924,0.00010639331,0.00011363854,0.000035744255,0.0000029479804,0.000025733683,0.0018194697,0.96918404,0.000013480962,0.0008549763,0.027519116,0.00015914568],"about_ca_topic_score_codex":0.000012846274,"about_ca_topic_score_gemma":2.6846087e-7,"teacher_disagreement_score":0.96356493,"about_ca_system_score_codex":0.00006025034,"about_ca_system_score_gemma":0.0000381452,"threshold_uncertainty_score":0.5716183},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000026865959,0.00007435432,0.9316299,0.0005266485,0.00042438827,0.00020225844,0.0021883685,0.000243166,0.06468405],"genre_scores_gemma":[0.0009623644,0.0029362622,0.059467252,0.00030544738,0.0006541579,0.000027146494,0.01124571,0.00009355735,0.9243081],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99896425,0.000007649782,0.00024900254,0.00041449157,0.00027369964,0.00009093316],"domain_scores_gemma":[0.9985773,0.00010024856,0.0002802957,0.0009231818,0.00008350655,0.000035491008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002653189,0.00011395143,0.00016091493,0.00010203696,0.000045416396,0.00010609199,0.00077032804,0.000120274985,0.000015169596],"category_scores_gemma":[0.000031138406,0.00010876009,0.00001939714,0.000041595446,0.000013126297,0.0002004465,0.00086127996,0.0000669043,0.00006721853],"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":[1.2557446e-7,0.0000085353295,0.0001047767,0.00002785031,0.0000383074,8.8912407e-7,0.00004873132,3.44982e-7,0.000005905663,0.7174017,0.0074780704,0.2748848],"study_design_scores_gemma":[0.0005523271,0.00013173027,0.007526387,0.0007190043,0.00019781991,0.000008176338,0.000031051208,0.17520331,0.00019690592,0.13795474,0.6761979,0.0012806589],"about_ca_topic_score_codex":0.00011676794,"about_ca_topic_score_gemma":0.00007327382,"teacher_disagreement_score":0.87216264,"about_ca_system_score_codex":0.000030725972,"about_ca_system_score_gemma":0.000040277537,"threshold_uncertainty_score":0.4435108},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010523383,0.0013091605,0.37592342,0.00012297525,0.0005626623,0.00022080676,0.003084735,0.00008308101,0.6186826],"genre_scores_gemma":[0.004159741,0.00010512187,0.44201282,0.00075466576,0.002544113,0.000079291334,0.0009863466,0.00010364355,0.5492543],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983877,0.0000066384227,0.00027762426,0.0009295482,0.0001580215,0.0002404761],"domain_scores_gemma":[0.99756986,0.00012891756,0.00014525052,0.0019393639,0.00009764582,0.00011897266],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00015004251,0.00026674534,0.00032832648,0.000044706154,0.00014755422,0.00065750594,0.0015364278,0.00016366389,9.2983817e-7],"category_scores_gemma":[0.00003727901,0.00026799965,0.000072169656,0.000034017823,0.00007899543,0.00019560091,0.0021996042,0.00011478955,0.000011101189],"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":[8.4808073e-7,0.0000064083288,0.0000014483873,0.000024649225,0.000048426606,0.000007168569,0.000028260507,2.928524e-7,0.0000014821431,0.77084935,0.0089669125,0.22006479],"study_design_scores_gemma":[0.00035551927,0.00006550056,0.000016794782,0.0003466277,0.0001668002,0.00006932243,0.000030026114,0.02841563,0.000011465859,0.116029,0.85381544,0.00067787495],"about_ca_topic_score_codex":0.0000136817935,"about_ca_topic_score_gemma":0.000101317266,"teacher_disagreement_score":0.8448485,"about_ca_system_score_codex":0.00005264224,"about_ca_system_score_gemma":0.00035489097,"threshold_uncertainty_score":0.99997723},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000840802,0.000020213482,0.99748015,0.00037741833,0.00009066488,0.0001570352,0.000490965,0.00007246298,0.00047027942],"genre_scores_gemma":[0.41880116,0.00006340082,0.56413406,0.0024249735,0.00016172051,0.001194191,0.012191961,0.000017022863,0.0010115221],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996226,0.000010906489,0.00010481878,0.00012827854,0.00006756028,0.000065824766],"domain_scores_gemma":[0.9995112,0.000029624982,0.00003705437,0.00037121595,0.000027244268,0.000023704768],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021656718,0.00003409353,0.000033185213,0.000042866643,0.0002199987,0.00012760308,0.0004997094,0.000006565232,0.000016690225],"category_scores_gemma":[0.000010383224,0.00003323864,0.000005376401,0.00012394944,0.0000045576735,0.0010242627,0.00078950264,0.000022361892,0.0000064333153],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.111942e-7,0.000043022657,0.000153138,0.000014801638,0.0000044258886,5.1639642e-8,0.0006920799,0.000019142484,0.000013461733,0.38178658,0.024757773,0.5925149],"study_design_scores_gemma":[0.00009301011,0.000020921962,0.00033009818,7.865892e-7,0.000001384048,0.0000020702194,0.00008631478,0.5873697,0.00002375896,0.0004751755,0.41155696,0.000039881812],"about_ca_topic_score_codex":0.000030512461,"about_ca_topic_score_gemma":0.0000103285465,"teacher_disagreement_score":0.592475,"about_ca_system_score_codex":0.000014353936,"about_ca_system_score_gemma":0.000031650892,"threshold_uncertainty_score":0.16920744},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010100909,0.00018482331,0.9875466,0.00032233555,0.00020126427,0.00007414867,0.00031275742,0.00010828299,0.0011488268],"genre_scores_gemma":[0.9149493,0.00006559368,0.07518961,0.0008386595,0.0003363825,0.000111599344,0.004113545,0.0000222106,0.0043730955],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99917156,0.000046495796,0.000110692265,0.000438122,0.00013059523,0.0001025381],"domain_scores_gemma":[0.9992233,0.00008704565,0.000034641173,0.0006017228,0.000013036641,0.000040273175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018478639,0.000063500236,0.000066419816,0.000045091045,0.00027911278,0.00027329678,0.0009044215,0.000010992013,0.000033429616],"category_scores_gemma":[0.000014926806,0.000059655235,0.000007762962,0.00035390857,0.00002092949,0.0006600285,0.0030230947,0.00005527794,0.000014346028],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021113954,0.00025306852,0.00039142955,0.0000037417444,0.00001764196,0.0000029149762,0.0007679654,0.0000133544245,0.0004132065,0.15423489,0.024030603,0.8198691],"study_design_scores_gemma":[0.00013495453,0.00003326051,0.0012217193,0.0000021042374,0.0000044820113,0.0000030906474,0.0002323718,0.8922373,0.00008413738,0.0011715824,0.10476179,0.00011318786],"about_ca_topic_score_codex":0.0004017226,"about_ca_topic_score_gemma":0.000047326717,"teacher_disagreement_score":0.91235703,"about_ca_system_score_codex":0.000018576133,"about_ca_system_score_gemma":0.000063155574,"threshold_uncertainty_score":0.37680712},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0085568195,0.00016674104,0.98195153,0.0051908973,0.00020107909,0.00007139796,0.000005267207,0.00028387856,0.003572376],"genre_scores_gemma":[0.84450316,0.0059242635,0.1252208,0.0018775717,0.0018685021,0.00012096849,0.00023209376,0.00007748681,0.020175124],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981781,0.000015282712,0.00020304849,0.00013232825,0.00026822428,0.0012030073],"domain_scores_gemma":[0.9994773,0.000034421744,0.000090727175,0.00025586472,0.00007094966,0.000070725146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011520368,0.000080430436,0.000074143616,0.00014339227,0.0002880441,0.00022115247,0.0008857582,0.000032272957,0.000007789695],"category_scores_gemma":[0.000032790707,0.00007195044,0.00005068618,0.0007053007,0.000017145874,0.0008243419,0.0001387155,0.0006715083,0.000486803],"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":[7.6126616e-7,0.000014147226,0.000034804092,0.000001385462,0.000024586107,0.0000021094013,0.0001355046,0.00034375157,0.000039607734,0.8170218,0.0026824272,0.17969915],"study_design_scores_gemma":[0.00057201745,0.00016222136,0.0032496175,0.00001795539,0.0000095111955,0.0012691498,0.0007531579,0.2540963,0.000079146645,0.6586286,0.08081762,0.00034473743],"about_ca_topic_score_codex":0.000009024709,"about_ca_topic_score_gemma":0.000029843,"teacher_disagreement_score":0.85673076,"about_ca_system_score_codex":0.00019444275,"about_ca_system_score_gemma":0.0011330814,"threshold_uncertainty_score":0.62570304},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008524309,0.0034059756,0.8430781,0.019543756,0.0003034265,0.003682869,0.106784314,0.0104651,0.00421216],"genre_scores_gemma":[0.59700364,0.0042547164,0.38648582,0.00015261016,0.000023198601,0.0003153937,0.010981154,0.00009888851,0.00068458996],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988556,0.000020301779,0.00023538583,0.00049671705,0.00026222365,0.000129803],"domain_scores_gemma":[0.99396574,0.0014801794,0.00021954864,0.0042130155,0.0000931312,0.000028405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002390664,0.00023965318,0.00036349328,0.0007216079,0.00017556205,0.00013668233,0.003194087,0.00029095844,9.774718e-7],"category_scores_gemma":[0.00035688363,0.00022497866,0.000041703435,0.00038634014,0.00010307352,0.00012898695,0.001381512,0.00046361153,0.0000028834343],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017654687,0.0006070713,0.0011424186,0.00008080294,0.0022563846,0.000009459882,0.0005028106,0.010504274,0.00020212817,0.46481302,0.00035684905,0.5195071],"study_design_scores_gemma":[0.0002255247,0.00039937833,0.012547454,0.00029421927,0.0010906771,0.0000011923313,0.000059452625,0.97916526,0.00027043826,0.003257257,0.0021366896,0.00055243785],"about_ca_topic_score_codex":0.000030413212,"about_ca_topic_score_gemma":0.00006417143,"teacher_disagreement_score":0.968661,"about_ca_system_score_codex":0.0000676807,"about_ca_system_score_gemma":0.000022765911,"threshold_uncertainty_score":0.91743636},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000044616745,0.000096198855,0.49572203,0.0011473878,0.00021024242,0.00014520383,0.0004293183,0.00039468444,0.5018505],"genre_scores_gemma":[0.000024639934,0.00014124047,0.3154137,0.00012008055,0.00017267217,0.000004148927,0.00033211746,0.000029376362,0.683762],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99875396,0.0000025086579,0.00015650946,0.0007297019,0.00020836048,0.00014896969],"domain_scores_gemma":[0.9976293,0.00008726852,0.00008974298,0.0020630718,0.00004140695,0.00008922212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014255523,0.00017789268,0.0001805256,0.00011113298,0.00008851,0.00027208807,0.0015355716,0.000080789985,0.000009344296],"category_scores_gemma":[0.000008051064,0.00014160984,0.000012900906,0.00008824875,0.00006854182,0.00019295105,0.0016801172,0.00011291486,0.000080545404],"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":[5.236342e-7,0.000005096774,0.000004660189,0.000014699382,0.0000640481,0.000024496178,0.00005864393,0.0000013473216,0.0000011501153,0.2357454,0.047409646,0.7166703],"study_design_scores_gemma":[0.00019902499,0.00008693139,0.000076504766,0.00023571662,0.00009920933,0.000078400626,0.000042001873,0.17538288,0.000006246589,0.0063923425,0.81669044,0.0007102633],"about_ca_topic_score_codex":0.00001971674,"about_ca_topic_score_gemma":0.00006521781,"teacher_disagreement_score":0.76928085,"about_ca_system_score_codex":0.000007968334,"about_ca_system_score_gemma":0.00009084704,"threshold_uncertainty_score":0.57746816},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000041852945,0.0030070858,0.947288,0.00039946166,0.00052508357,0.00052360125,0.000016877364,0.00006103573,0.048137028],"genre_scores_gemma":[0.542808,0.0012396735,0.44846603,0.00022170073,0.00047831802,0.00034121895,0.00019164862,0.00007351724,0.0061798873],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972848,0.000050774073,0.00080471864,0.0005665816,0.0011202378,0.00017287047],"domain_scores_gemma":[0.99683124,0.00037535603,0.00049415644,0.0004308087,0.001832253,0.00003618579],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015200616,0.0002575092,0.0003576675,0.00030209162,0.00009921178,0.00005188763,0.00082529616,0.000087437205,0.000057172114],"category_scores_gemma":[0.0004192915,0.0002660056,0.0000789548,0.0001796423,0.00034660567,0.00025067717,0.00041439044,0.00022096606,0.000098690834],"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":[0.0000024677363,0.000029852778,0.0000042242677,0.000062320956,0.000056634774,0.0000011668743,0.0006346222,0.019376729,0.0000013031138,0.5827461,0.00010836167,0.39697623],"study_design_scores_gemma":[0.00008100677,0.000047274516,0.000060483682,0.0008743921,0.000032371005,0.000007976499,0.000079013895,0.37756872,0.0000428494,0.6195225,0.0014467876,0.00023657132],"about_ca_topic_score_codex":0.000008572637,"about_ca_topic_score_gemma":0.00003104899,"teacher_disagreement_score":0.54276615,"about_ca_system_score_codex":0.00044350137,"about_ca_system_score_gemma":0.00028060508,"threshold_uncertainty_score":0.9999792},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000018752748,0.0021258127,0.35237578,0.03717149,0.16567823,0.0012957283,0.0087920455,0.0029845112,0.42955765],"genre_scores_gemma":[0.00001837488,0.0007886207,0.09759044,0.001072559,0.003926264,0.00015558655,0.014358498,0.00007471057,0.88201493],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99846673,0.000027455659,0.00021929116,0.00076071714,0.00025519115,0.00027060643],"domain_scores_gemma":[0.99648684,0.000099085,0.00009795063,0.0032251608,0.00003599531,0.00005494917],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004885146,0.00014474493,0.00020921575,0.0001727601,0.00006112398,0.00046001206,0.0052498584,0.0002222545,0.000014173137],"category_scores_gemma":[0.00023312762,0.00014312817,0.000018596354,0.0011271294,0.000019065368,0.00064939394,0.003252662,0.00067177636,0.00093516166],"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":[1.4700728e-7,0.0000145673075,0.000006394891,0.000011600566,0.0000035574396,0.000016978822,0.000033681936,0.0000012465013,2.8781326e-7,0.0006312325,0.79678476,0.20249555],"study_design_scores_gemma":[0.000085882035,0.000006876668,0.00055341295,0.00009613949,0.0000024951435,0.0000036625104,0.000008437392,0.16551627,0.0000010233657,0.0005007815,0.8330836,0.00014138884],"about_ca_topic_score_codex":0.0010957546,"about_ca_topic_score_gemma":0.0004889459,"teacher_disagreement_score":0.4524573,"about_ca_system_score_codex":0.000041557778,"about_ca_system_score_gemma":0.0003332719,"threshold_uncertainty_score":0.9998427},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.575923,0.0000746747,0.42180002,0.00033853552,0.0007771416,0.00024444607,0.000023171453,0.00038480706,0.00043415496],"genre_scores_gemma":[0.7659937,0.000009755431,0.23370512,0.00012631212,0.000015651009,0.00005688833,0.000019265834,0.00001370823,0.000059558126],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998783,0.000051931966,0.00023522439,0.0004242942,0.00022922506,0.00027632134],"domain_scores_gemma":[0.9988406,0.00013446459,0.00011014205,0.000739029,0.00006848474,0.000107318396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014176339,0.00015288977,0.0001733096,0.00008095513,0.00036536693,0.00013118377,0.0007101107,0.00006605397,0.000013946159],"category_scores_gemma":[0.000044402557,0.00015625807,0.00006631607,0.00043193466,0.0000749115,0.00060081895,0.00023405446,0.00013520666,0.000049126127],"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":[0.000021291515,0.0011337536,0.05169876,0.000027124863,0.00029452416,0.0004996369,0.005368998,0.000360701,0.04580347,0.7994613,0.023986263,0.07134417],"study_design_scores_gemma":[0.0020945682,0.0002496857,0.046176977,0.00019869255,0.000063419226,0.00019951543,0.00014419657,0.23961072,0.033139553,0.66291136,0.013684979,0.0015263194],"about_ca_topic_score_codex":0.0002591276,"about_ca_topic_score_gemma":0.000004998229,"teacher_disagreement_score":0.23925002,"about_ca_system_score_codex":0.00006084676,"about_ca_system_score_gemma":0.000057051187,"threshold_uncertainty_score":0.6372019},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000068517445,0.001070734,0.99668515,0.00030202523,0.00059081434,0.0002026216,0.00003804351,0.00016827353,0.0008738255],"genre_scores_gemma":[0.011697286,0.0009515758,0.97092396,0.0005379643,0.00083354424,0.00008700953,0.00027897276,0.00009009258,0.014599595],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99735993,0.000053924407,0.0003399825,0.0013818069,0.00036426578,0.000500117],"domain_scores_gemma":[0.9980144,0.0008814388,0.00012765879,0.0008236824,0.00005174899,0.0001010652],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009247768,0.0003143946,0.0003571639,0.0008108452,0.00021544879,0.00070763077,0.0019422111,0.000101557496,0.0000017225843],"category_scores_gemma":[0.00017778033,0.00028842728,0.000036929207,0.0017345825,0.00039848278,0.0010233358,0.003079719,0.0008117182,0.00003912171],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001072509,0.000041407562,0.0005310568,0.000056560344,0.0000036663682,0.00005269102,0.0006771062,0.0024756668,0.000023207807,0.005756995,0.00014411577,0.99023646],"study_design_scores_gemma":[0.00018190185,0.00005143241,0.00059353583,0.00046542461,0.0000030209437,0.000028841241,3.616452e-7,0.97265404,0.00006762282,0.013422031,0.012118812,0.0004129429],"about_ca_topic_score_codex":0.00011415836,"about_ca_topic_score_gemma":0.0004980564,"teacher_disagreement_score":0.9898235,"about_ca_system_score_codex":0.00017427973,"about_ca_system_score_gemma":0.0007124778,"threshold_uncertainty_score":0.9999568},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000068517445,0.001070734,0.99668515,0.00030202523,0.00059081434,0.0002026216,0.00003804351,0.00016827353,0.0008738255],"genre_scores_gemma":[0.011697286,0.0009515758,0.97092396,0.0005379643,0.00083354424,0.00008700953,0.00027897276,0.00009009258,0.014599595],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99735993,0.000053924407,0.0003399825,0.0013818069,0.00036426578,0.000500117],"domain_scores_gemma":[0.9980144,0.0008814388,0.00012765879,0.0008236824,0.00005174899,0.0001010652],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009247768,0.0003143946,0.0003571639,0.0008108452,0.00021544879,0.00070763077,0.0019422111,0.000101557496,0.0000017225843],"category_scores_gemma":[0.00017778033,0.00028842728,0.000036929207,0.0017345825,0.00039848278,0.0010233358,0.003079719,0.0008117182,0.00003912171],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001072509,0.000041407562,0.0005310568,0.000056560344,0.0000036663682,0.00005269102,0.0006771062,0.0024756668,0.000023207807,0.005756995,0.00014411577,0.99023646],"study_design_scores_gemma":[0.00018190185,0.00005143241,0.00059353583,0.00046542461,0.0000030209437,0.000028841241,3.616452e-7,0.97265404,0.00006762282,0.013422031,0.012118812,0.0004129429],"about_ca_topic_score_codex":0.00011415836,"about_ca_topic_score_gemma":0.0004980564,"teacher_disagreement_score":0.9898235,"about_ca_system_score_codex":0.00017427973,"about_ca_system_score_gemma":0.0007124778,"threshold_uncertainty_score":0.9999568},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000068517445,0.001070734,0.99668515,0.00030202523,0.00059081434,0.0002026216,0.00003804351,0.00016827353,0.0008738255],"genre_scores_gemma":[0.011697286,0.0009515758,0.97092396,0.0005379643,0.00083354424,0.00008700953,0.00027897276,0.00009009258,0.014599595],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99735993,0.000053924407,0.0003399825,0.0013818069,0.00036426578,0.000500117],"domain_scores_gemma":[0.9980144,0.0008814388,0.00012765879,0.0008236824,0.00005174899,0.0001010652],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009247768,0.0003143946,0.0003571639,0.0008108452,0.00021544879,0.00070763077,0.0019422111,0.000101557496,0.0000017225843],"category_scores_gemma":[0.00017778033,0.00028842728,0.000036929207,0.0017345825,0.00039848278,0.0010233358,0.003079719,0.0008117182,0.00003912171],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001072509,0.000041407562,0.0005310568,0.000056560344,0.0000036663682,0.00005269102,0.0006771062,0.0024756668,0.000023207807,0.005756995,0.00014411577,0.99023646],"study_design_scores_gemma":[0.00018190185,0.00005143241,0.00059353583,0.00046542461,0.0000030209437,0.000028841241,3.616452e-7,0.97265404,0.00006762282,0.013422031,0.012118812,0.0004129429],"about_ca_topic_score_codex":0.00011415836,"about_ca_topic_score_gemma":0.0004980564,"teacher_disagreement_score":0.9898235,"about_ca_system_score_codex":0.00017427973,"about_ca_system_score_gemma":0.0007124778,"threshold_uncertainty_score":0.9999568},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000068517445,0.001070734,0.99668515,0.00030202523,0.00059081434,0.0002026216,0.00003804351,0.00016827353,0.0008738255],"genre_scores_gemma":[0.011697286,0.0009515758,0.97092396,0.0005379643,0.00083354424,0.00008700953,0.00027897276,0.00009009258,0.014599595],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99735993,0.000053924407,0.0003399825,0.0013818069,0.00036426578,0.000500117],"domain_scores_gemma":[0.9980144,0.0008814388,0.00012765879,0.0008236824,0.00005174899,0.0001010652],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009247768,0.0003143946,0.0003571639,0.0008108452,0.00021544879,0.00070763077,0.0019422111,0.000101557496,0.0000017225843],"category_scores_gemma":[0.00017778033,0.00028842728,0.000036929207,0.0017345825,0.00039848278,0.0010233358,0.003079719,0.0008117182,0.00003912171],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001072509,0.000041407562,0.0005310568,0.000056560344,0.0000036663682,0.00005269102,0.0006771062,0.0024756668,0.000023207807,0.005756995,0.00014411577,0.99023646],"study_design_scores_gemma":[0.00018190185,0.00005143241,0.00059353583,0.00046542461,0.0000030209437,0.000028841241,3.616452e-7,0.97265404,0.00006762282,0.013422031,0.012118812,0.0004129429],"about_ca_topic_score_codex":0.00011415836,"about_ca_topic_score_gemma":0.0004980564,"teacher_disagreement_score":0.9898235,"about_ca_system_score_codex":0.00017427973,"about_ca_system_score_gemma":0.0007124778,"threshold_uncertainty_score":0.9999568},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42412993,0.0004292605,0.5513966,0.016306506,0.0002807695,0.00033178838,0.000051244046,0.0005356481,0.00653827],"genre_scores_gemma":[0.5602269,0.000023898052,0.4365635,0.00043718284,0.000045640547,0.00006948504,0.000015114324,0.000008183944,0.0026101104],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993129,0.00002447028,0.000077793,0.00025601964,0.00018355844,0.00014527098],"domain_scores_gemma":[0.9995354,0.00003307925,0.000012344635,0.0003485361,0.000013313358,0.000057341716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027235752,0.00004969386,0.00005741272,0.0000474075,0.00054731464,0.00014162587,0.00048507133,0.000008698622,0.000044297154],"category_scores_gemma":[0.00000763297,0.000048288686,0.0000123406635,0.00025990655,0.000019789875,0.00017439178,0.0010058732,0.00008794242,0.000010117762],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001606989,0.00016712565,0.009497584,0.000019552579,0.000021473055,0.00003545735,0.0051975856,0.00016495843,0.0003023594,0.39339668,0.018258287,0.5729373],"study_design_scores_gemma":[0.00046973026,0.00022328123,0.021192843,0.000007766972,0.000007433903,0.00015300541,0.0023185688,0.46106443,0.0003603209,0.0017594589,0.51198506,0.0004581119],"about_ca_topic_score_codex":0.00010803427,"about_ca_topic_score_gemma":0.000011332933,"teacher_disagreement_score":0.5724792,"about_ca_system_score_codex":0.00001549032,"about_ca_system_score_gemma":0.000021539014,"threshold_uncertainty_score":0.42095572},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042719026,0.000019529907,0.9671212,0.0015865773,0.000092008166,0.000050997314,0.000005648007,0.00024915667,0.02660297],"genre_scores_gemma":[0.6718398,0.000003957901,0.3008413,0.0005064387,0.000010613758,0.0001122149,0.000027303837,0.000006839,0.026651531],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994614,0.000040005816,0.00006259889,0.00017360043,0.00014760758,0.00011478942],"domain_scores_gemma":[0.99968684,0.000055194592,0.000037767444,0.00018045625,0.000015304857,0.000024413057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019311925,0.00003701485,0.00004499143,0.000029429279,0.0004317859,0.000060923496,0.00047096796,0.0000065512822,0.00009953521],"category_scores_gemma":[0.000014882162,0.00003777486,0.00001939611,0.00028699057,0.0000057101893,0.00013120135,0.00051235553,0.00014038359,0.000072687966],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.0269573e-7,0.00012809053,0.0005148549,0.0000015091214,0.000025384963,0.000008005837,0.0025614703,0.0016476939,0.0011443304,0.31773478,0.015259602,0.66097355],"study_design_scores_gemma":[0.0000795529,0.000048286034,0.0010919836,4.6641924e-7,0.0000013313687,0.0000059351155,0.00040763232,0.90400463,0.00006611568,0.0028913978,0.09131414,0.000088502435],"about_ca_topic_score_codex":0.000028963032,"about_ca_topic_score_gemma":0.0000033600575,"teacher_disagreement_score":0.902357,"about_ca_system_score_codex":0.000062108105,"about_ca_system_score_gemma":0.00002728282,"threshold_uncertainty_score":0.33209917},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047018792,0.000031045176,0.9510058,0.0008534856,0.0000705851,0.00005972224,0.000022714214,0.000067164605,0.0008706716],"genre_scores_gemma":[0.7191308,6.816989e-7,0.28027913,0.0002932541,0.000038666123,0.00004378819,0.00006449703,0.00000544281,0.00014371386],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989485,0.00007506909,0.00023159418,0.00027347694,0.00028412888,0.00018723772],"domain_scores_gemma":[0.99947816,0.000077503595,0.000054561293,0.00030296214,0.000045114874,0.0000417137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031697992,0.00006888371,0.00020282532,0.00011882029,0.00036325556,0.000039025643,0.0006391754,0.000016881624,0.00009206052],"category_scores_gemma":[0.00001774296,0.00006799472,0.000116325355,0.0022679414,0.00003695841,0.00014234663,0.00052309874,0.0000818739,0.0000054642524],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011808693,0.00026220898,0.0063003777,0.000004232517,0.0010335089,0.000008534463,0.0071094385,0.0124013405,0.00033378098,0.91592175,0.016657388,0.039955657],"study_design_scores_gemma":[0.00009498734,0.00007337174,0.007701173,8.6796376e-7,0.00017923854,0.0000011317993,0.0005409954,0.98649895,0.000027664742,0.0013632306,0.0034023311,0.00011606673],"about_ca_topic_score_codex":0.00011341468,"about_ca_topic_score_gemma":0.000020864694,"teacher_disagreement_score":0.9740976,"about_ca_system_score_codex":0.000026466276,"about_ca_system_score_gemma":0.00002835557,"threshold_uncertainty_score":0.27939048},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000068517445,0.001070734,0.99668515,0.00030202523,0.00059081434,0.0002026216,0.00003804351,0.00016827353,0.0008738255],"genre_scores_gemma":[0.011697286,0.0009515758,0.97092396,0.0005379643,0.00083354424,0.00008700953,0.00027897276,0.00009009258,0.014599595],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99735993,0.000053924407,0.0003399825,0.0013818069,0.00036426578,0.000500117],"domain_scores_gemma":[0.9980144,0.0008814388,0.00012765879,0.0008236824,0.00005174899,0.0001010652],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009247768,0.0003143946,0.0003571639,0.0008108452,0.00021544879,0.00070763077,0.0019422111,0.000101557496,0.0000017225843],"category_scores_gemma":[0.00017778033,0.00028842728,0.000036929207,0.0017345825,0.00039848278,0.0010233358,0.003079719,0.0008117182,0.00003912171],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001072509,0.000041407562,0.0005310568,0.000056560344,0.0000036663682,0.00005269102,0.0006771062,0.0024756668,0.000023207807,0.005756995,0.00014411577,0.99023646],"study_design_scores_gemma":[0.00018190185,0.00005143241,0.00059353583,0.00046542461,0.0000030209437,0.000028841241,3.616452e-7,0.97265404,0.00006762282,0.013422031,0.012118812,0.0004129429],"about_ca_topic_score_codex":0.00011415836,"about_ca_topic_score_gemma":0.0004980564,"teacher_disagreement_score":0.9898235,"about_ca_system_score_codex":0.00017427973,"about_ca_system_score_gemma":0.0007124778,"threshold_uncertainty_score":0.9999568},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000068517445,0.001070734,0.99668515,0.00030202523,0.00059081434,0.0002026216,0.00003804351,0.00016827353,0.0008738255],"genre_scores_gemma":[0.011697286,0.0009515758,0.97092396,0.0005379643,0.00083354424,0.00008700953,0.00027897276,0.00009009258,0.014599595],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99735993,0.000053924407,0.0003399825,0.0013818069,0.00036426578,0.000500117],"domain_scores_gemma":[0.9980144,0.0008814388,0.00012765879,0.0008236824,0.00005174899,0.0001010652],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009247768,0.0003143946,0.0003571639,0.0008108452,0.00021544879,0.00070763077,0.0019422111,0.000101557496,0.0000017225843],"category_scores_gemma":[0.00017778033,0.00028842728,0.000036929207,0.0017345825,0.00039848278,0.0010233358,0.003079719,0.0008117182,0.00003912171],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001072509,0.000041407562,0.0005310568,0.000056560344,0.0000036663682,0.00005269102,0.0006771062,0.0024756668,0.000023207807,0.005756995,0.00014411577,0.99023646],"study_design_scores_gemma":[0.00018190185,0.00005143241,0.00059353583,0.00046542461,0.0000030209437,0.000028841241,3.616452e-7,0.97265404,0.00006762282,0.013422031,0.012118812,0.0004129429],"about_ca_topic_score_codex":0.00011415836,"about_ca_topic_score_gemma":0.0004980564,"teacher_disagreement_score":0.9898235,"about_ca_system_score_codex":0.00017427973,"about_ca_system_score_gemma":0.0007124778,"threshold_uncertainty_score":0.9999568},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055670083,0.000020954889,0.9408087,0.0024955038,0.000118080825,0.0004061883,0.000059604426,0.00038573897,0.000035128607],"genre_scores_gemma":[0.8792473,0.000018477052,0.119946636,0.000003958301,0.000027816359,0.00049046264,0.000005794937,0.0000111839045,0.00024837122],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978863,0.000009993442,0.0002047823,0.0004938364,0.0006864602,0.0007186552],"domain_scores_gemma":[0.9978781,0.0009035244,0.000071519295,0.000900614,0.00020207679,0.000044213328],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003418226,0.00009421234,0.00012869184,0.00087584316,0.0004984982,0.0001632738,0.002328839,0.000091791764,6.3641494e-7],"category_scores_gemma":[0.00081242714,0.00007756141,0.0000321768,0.005139689,0.00022576969,0.00031777227,0.0012114297,0.00032606674,0.000013604691],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000051940606,0.00016992456,0.0029349127,0.00008346915,0.00009632719,0.000004337327,0.0011174119,0.015217877,0.49130532,0.28013194,0.0017508827,0.20718239],"study_design_scores_gemma":[0.00020196871,0.000022847675,0.014337701,0.00002145737,0.0000029150297,0.0000014399465,0.0007183712,0.9575026,0.0260112,0.0007185553,0.00035744236,0.000103477876],"about_ca_topic_score_codex":0.000020897527,"about_ca_topic_score_gemma":0.0000052635155,"teacher_disagreement_score":0.94228476,"about_ca_system_score_codex":0.0002005798,"about_ca_system_score_gemma":0.00016373991,"threshold_uncertainty_score":0.4327601},"labels":[],"label_agreement":null},{"id":"W4362589576","doi":"10.1007/s10115-023-01852-3","title":"Mining frequent generators and closures in data streams with FGC-Stream","year":2023,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Sliding window protocol; Data stream mining; Data mining; Exploit; Association rule learning; Factoring; Data stream; STREAMS; Window (computing); Computer security","score_opus":0.029363750963375318,"score_gpt":0.26678572819741725,"score_spread":0.23742197723404193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362589576","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8919629,0.0027783841,0.081416525,0.0006923502,0.0007899681,0.0010670408,0.0004584197,0.0007273995,0.020107029],"genre_scores_gemma":[0.9914883,0.00031438863,0.007079957,0.000049222162,0.00010757631,0.00009803703,0.0006304067,0.000007404275,0.00022474346],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992988,0.000021608605,0.0002578042,0.00017571659,0.00010693122,0.00013912132],"domain_scores_gemma":[0.9993071,0.000045746587,0.00007871075,0.00045444173,0.00005060718,0.00006339419],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036675463,0.00008717779,0.00011198671,0.00018275119,0.00010404996,0.00038856716,0.0003309895,0.000035576755,4.6124367e-7],"category_scores_gemma":[0.000014673173,0.00006802668,0.000004679357,0.00053168734,0.00002518972,0.002877244,0.00027972492,0.000047133948,0.00004466475],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004708584,0.000053033433,0.02238384,0.00033090124,0.000044312746,0.0000062126596,0.018920101,0.00020928118,0.00004159533,0.059866387,0.047246333,0.8508933],"study_design_scores_gemma":[0.00045894508,0.00004867652,0.0089167245,0.00014162694,0.000004690011,0.000030477206,0.0018512497,0.7736908,0.000044285178,0.00002026305,0.21460149,0.00019078961],"about_ca_topic_score_codex":0.00008655433,"about_ca_topic_score_gemma":0.000059274924,"teacher_disagreement_score":0.8507025,"about_ca_system_score_codex":0.0000118930375,"about_ca_system_score_gemma":0.0000478068,"threshold_uncertainty_score":0.37469622},"labels":[],"label_agreement":null},{"id":"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04443792,0.00090066274,0.93619144,0.014819206,0.0009882854,0.0019218915,0.00005190467,0.00006403614,0.00062463107],"genre_scores_gemma":[0.22730222,0.00002233869,0.771634,0.00058105757,0.00020295432,0.00008091376,0.000085142485,0.000018192419,0.000073166164],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99826527,0.00009290948,0.00041675518,0.000323036,0.00052522536,0.0003768166],"domain_scores_gemma":[0.99712217,0.000049558323,0.0002457025,0.00096384453,0.00079071824,0.0008279824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017593966,0.00012874085,0.0001561263,0.00039535036,0.0002454417,0.00088137825,0.0017779698,0.00005283711,0.000118117205],"category_scores_gemma":[0.00023597969,0.00012027032,0.00004739075,0.0008575527,0.000048253045,0.001579823,0.00009447854,0.00017451923,0.000142299],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.30898e-7,0.000028107446,0.00016294967,0.000003870064,0.000025562293,0.0000025595104,0.00049043173,0.0002895247,0.0001036092,0.0042349314,0.09539804,0.89925987],"study_design_scores_gemma":[0.0009900547,0.00047265922,0.008961978,0.0002009346,0.00014193571,0.00023789296,0.0005332585,0.2712922,0.000110215304,0.044094767,0.67228466,0.00067942357],"about_ca_topic_score_codex":0.005209203,"about_ca_topic_score_gemma":0.014111141,"teacher_disagreement_score":0.89858043,"about_ca_system_score_codex":0.00021063547,"about_ca_system_score_gemma":0.0013048614,"threshold_uncertainty_score":0.8499151},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07307892,0.000010546085,0.9230479,0.00067577325,0.0003391371,0.00018374143,0.00008382305,0.00080148765,0.0017786876],"genre_scores_gemma":[0.868143,0.0001598684,0.10594842,0.00014613509,0.00016922693,0.000009259124,0.00024075931,0.00005324551,0.025130076],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984185,0.000055250643,0.0001407211,0.0009421192,0.00013130983,0.00031211524],"domain_scores_gemma":[0.9982804,0.0001731058,0.00030686476,0.0009961725,0.00013520037,0.00010823523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029644353,0.00021226451,0.00022041015,0.00019271474,0.00021159207,0.00025160058,0.0015029066,0.00019766249,0.000008593148],"category_scores_gemma":[0.00004076776,0.00023067668,0.000083404826,0.0006084457,0.00004111837,0.00036991673,0.0012626206,0.00034979088,0.00025784477],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003417981,0.0004577435,0.07547141,0.0002761543,0.0015200559,0.00093385694,0.0039123595,0.4081759,0.000053327494,0.42971745,0.057906087,0.02154147],"study_design_scores_gemma":[0.00024672473,0.00003347869,0.0068353834,0.00010855649,0.000078361176,0.0000018117729,0.00018405878,0.9787127,0.000017899578,0.010790731,0.0025824122,0.00040789574],"about_ca_topic_score_codex":0.00020833293,"about_ca_topic_score_gemma":0.000072824245,"teacher_disagreement_score":0.81709945,"about_ca_system_score_codex":0.00028607444,"about_ca_system_score_gemma":0.00020316918,"threshold_uncertainty_score":0.9406722},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019480811,6.2518794e-8,0.9794873,0.00023901329,0.000016121545,0.00049068785,0.00019769341,0.000039388353,0.000048921367],"genre_scores_gemma":[0.0771293,0.0000076160677,0.92273915,0.000036986745,0.0000021881483,0.0000056230015,0.000064649954,0.000002185326,0.0000123319915],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907064,0.0000045173497,0.00031784642,0.00021964013,0.00023874357,0.00014860921],"domain_scores_gemma":[0.9990373,0.00014272971,0.00023068333,0.00023022864,0.00030414652,0.000054860626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007543651,0.000077167606,0.00016812129,0.0007919661,0.00014132261,0.00004846724,0.0003370008,0.0000187735,2.522412e-7],"category_scores_gemma":[0.00003682106,0.000077006174,0.000023260714,0.0021296982,0.00012419716,0.0006312869,0.00023987476,0.000030207533,1.7921424e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034420107,0.00006088346,0.000016858148,0.000093126044,0.000024532468,6.746889e-8,0.00020016203,0.019619513,0.00018147702,0.032845896,0.0005149353,0.94640815],"study_design_scores_gemma":[0.0002057054,0.00075588917,0.004925463,0.000026344547,0.000042916305,1.7931244e-7,0.00011657736,0.9921108,0.00086491933,0.0005264729,0.00035201636,0.000072756906],"about_ca_topic_score_codex":0.000002744993,"about_ca_topic_score_gemma":0.0000016511025,"teacher_disagreement_score":0.97249126,"about_ca_system_score_codex":0.000031652897,"about_ca_system_score_gemma":0.000045722554,"threshold_uncertainty_score":0.31402206},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056119077,0.002060855,0.9396035,0.0011330353,0.0003688245,0.0003807579,0.00008651855,0.00021972113,0.000027684304],"genre_scores_gemma":[0.82888854,0.004947767,0.16376528,0.00012255393,0.0013918832,0.00018964784,0.00018816377,0.00011166903,0.00039449387],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962177,0.00008176894,0.0005380431,0.0008578933,0.00031152525,0.001993061],"domain_scores_gemma":[0.99816716,0.00021944176,0.0004667215,0.00084613095,0.000159967,0.00014059027],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019003011,0.00033738697,0.00040412362,0.00017927073,0.0006918832,0.0009629045,0.0015001368,0.00018484416,0.0000010382953],"category_scores_gemma":[0.00011407182,0.00032293863,0.00018265753,0.00031004168,0.0000480568,0.00067587505,0.0010137721,0.0022130886,0.0000066224998],"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":[0.000013891805,0.00020706333,0.00049559167,0.00011516153,0.000637625,0.0000048673596,0.00216409,0.0020377764,0.00015644201,0.8454757,0.00034233165,0.14834946],"study_design_scores_gemma":[0.00049791037,0.0006683528,0.00009113035,0.00012328486,0.00006910274,0.000084780986,0.000755384,0.11689903,0.00014060386,0.8790538,0.0011838491,0.00043281814],"about_ca_topic_score_codex":0.000038492235,"about_ca_topic_score_gemma":0.00028956437,"teacher_disagreement_score":0.77583826,"about_ca_system_score_codex":0.00039083787,"about_ca_system_score_gemma":0.0016014816,"threshold_uncertainty_score":0.9999223},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024868774,0.0000074772133,0.99292344,0.0028965194,0.00023525096,0.00023903526,0.00004085936,0.0002548465,0.00091569335],"genre_scores_gemma":[0.7107652,0.0000036032216,0.28823832,0.00026870525,0.00020280469,0.000084332285,0.0001238543,0.000009693284,0.00030353022],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889064,0.000023663528,0.00016880332,0.00049932156,0.00017377437,0.00024381856],"domain_scores_gemma":[0.9991599,0.000051900242,0.00008200653,0.0003388401,0.00031120965,0.000056179317],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012699311,0.00014627716,0.00012221352,0.00009860767,0.00024536523,0.000324736,0.0005915487,0.000074015115,0.000001884888],"category_scores_gemma":[0.000007985617,0.000142957,0.00005351381,0.0002696576,0.000022091279,0.00046834833,0.00006573586,0.00012418261,0.000023168437],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000118886865,0.00016868228,0.000027342247,0.000009567353,0.000013358229,7.939028e-7,0.0003861279,0.0067083286,0.000940384,0.62883836,0.031692743,0.33120245],"study_design_scores_gemma":[0.00021265008,0.00011567054,0.0005139651,0.000022055712,0.0000040799678,0.0000059439067,0.000094293406,0.99011123,0.0001732641,0.0059198895,0.0026546153,0.0001723254],"about_ca_topic_score_codex":0.000055744043,"about_ca_topic_score_gemma":0.000011075458,"teacher_disagreement_score":0.9834029,"about_ca_system_score_codex":0.0000418016,"about_ca_system_score_gemma":0.00007067729,"threshold_uncertainty_score":0.58296174},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97848547,0.00006288046,0.011521954,0.007847769,0.00029889512,0.00015780717,0.000011072288,0.0010700573,0.00054407195],"genre_scores_gemma":[0.9652232,0.000035945875,0.034613833,0.0000073909896,0.00000858307,0.000051051757,0.0000013643805,0.0000030750307,0.00005554327],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891675,0.0000070106275,0.00017276013,0.00046476975,0.00012400975,0.00031470376],"domain_scores_gemma":[0.999406,0.000077237346,0.000020979875,0.00044088438,0.000017142846,0.000037788057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001057513,0.00007505902,0.0000925281,0.0009475638,0.00007598292,0.000062654835,0.00076495437,0.00005523882,2.545628e-7],"category_scores_gemma":[0.00018554353,0.000065677385,0.0000060999705,0.004868052,0.00026000405,0.00028975637,0.00041353906,0.00012852611,0.000044609875],"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":[8.178849e-7,0.000021773509,0.00032965138,0.0000038300473,5.295628e-7,0.00001305006,0.00025154089,0.00034547545,0.002873486,0.9734382,0.00003193587,0.022689726],"study_design_scores_gemma":[0.0009823049,0.00013753743,0.061052617,0.00012589608,0.0000014980053,0.000051130795,0.00023134433,0.7878406,0.012192604,0.10656158,0.030281559,0.00054131413],"about_ca_topic_score_codex":0.000010845468,"about_ca_topic_score_gemma":0.000009041739,"teacher_disagreement_score":0.8668766,"about_ca_system_score_codex":0.000052005747,"about_ca_system_score_gemma":0.000042014464,"threshold_uncertainty_score":0.2678246},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9073545,0.000009337081,0.074201554,0.0116878245,0.00009712918,0.0002217732,0.00009279428,0.0008076236,0.0055275066],"genre_scores_gemma":[0.9624158,0.0000014924126,0.037139058,0.00029130952,0.000013859687,0.00002033981,0.00004405524,0.0000030900144,0.000070967646],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922013,0.00004578532,0.00015422305,0.00020630214,0.00016810658,0.00020545015],"domain_scores_gemma":[0.9989897,0.00006280054,0.000033891207,0.0007790351,0.000036265916,0.00009830728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043036696,0.00006072473,0.000102935264,0.0003897917,0.00010129007,0.000145359,0.0011328154,0.00012322002,0.00003202275],"category_scores_gemma":[0.000041943218,0.0000439575,0.00002930492,0.0059916866,0.000025471329,0.00016627356,0.00007728227,0.00022736518,0.000026725917],"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":[0.0000015662589,0.0003511225,0.19017681,0.000018173105,0.00051386736,0.00020967728,0.014849594,0.010370422,0.0000376245,0.5072043,0.04275438,0.23351249],"study_design_scores_gemma":[0.000024965337,0.000010887837,0.43085748,0.0000029390528,0.000016160076,0.000001408968,0.00012508304,0.5670714,0.000034830897,0.0010249722,0.0007704817,0.000059382237],"about_ca_topic_score_codex":0.23931998,"about_ca_topic_score_gemma":0.49019688,"teacher_disagreement_score":0.55670094,"about_ca_system_score_codex":0.000030954932,"about_ca_system_score_gemma":0.00022814154,"threshold_uncertainty_score":0.76574546},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011974702,0.000021776645,0.9398597,0.020699978,0.00024534547,0.00013367458,0.0000682996,0.0014332209,0.025563287],"genre_scores_gemma":[0.38101318,0.00035595678,0.5037474,0.0025954964,0.00036387882,0.0005630412,0.0020646632,0.000040062805,0.1092563],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994237,0.0000132896785,0.000095682524,0.00018139192,0.00016234074,0.00012360969],"domain_scores_gemma":[0.9995425,0.000060268943,0.000050254414,0.00027726748,0.00003617215,0.00003355133],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002341097,0.000039983133,0.00003930472,0.0000390395,0.00008891586,0.00013833867,0.00035024414,0.000030308758,0.000015216772],"category_scores_gemma":[0.00003320423,0.00003676019,0.00001600875,0.000374182,0.000004666731,0.0002531043,0.00006833931,0.000036720034,0.0020019873],"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":[6.897514e-8,0.000023959941,0.0006956791,0.0000012808222,0.000006101383,2.2075038e-7,0.00008245143,0.0000018710649,0.0037661982,0.25256526,0.61489236,0.12796451],"study_design_scores_gemma":[0.00011950615,0.000014269918,0.038596995,0.000003527276,0.0000031004845,6.1108165e-7,0.000055168035,0.5694776,0.0016159947,0.009005025,0.38095424,0.00015393834],"about_ca_topic_score_codex":0.00003233617,"about_ca_topic_score_gemma":0.000002023226,"teacher_disagreement_score":0.56947577,"about_ca_system_score_codex":0.000057649362,"about_ca_system_score_gemma":0.000015175256,"threshold_uncertainty_score":0.99877506},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00060168584,0.00006077046,0.98420674,0.0044810832,0.0012743268,0.00096467254,0.007635556,0.0007127576,0.00006243048],"genre_scores_gemma":[0.0062841615,0.00012853112,0.92795813,0.0002810626,0.0011737943,0.00044677686,0.062644415,0.00008087737,0.0010022491],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99508715,0.00007475963,0.0006912972,0.003188877,0.00049842894,0.00045949593],"domain_scores_gemma":[0.9810461,0.00024802663,0.0003897867,0.017879575,0.0002558365,0.000180683],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0022982848,0.00039710134,0.000434046,0.00023284538,0.00023844565,0.00030990576,0.013608789,0.00027494296,0.000031562904],"category_scores_gemma":[0.0006275373,0.00043448465,0.00009335025,0.0004690746,0.000063480744,0.00065382005,0.023934731,0.00055825955,0.00066230935],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000136551935,0.001112595,0.0075245663,0.00071049045,0.00096513255,0.000040803337,0.0004350601,0.049809005,0.0017974119,0.00569634,0.08264455,0.8492504],"study_design_scores_gemma":[0.00025693083,0.000009902973,0.0019665614,0.000058081503,0.000085465625,0.0000018281976,0.000005495969,0.9473891,0.0012723295,0.0017374861,0.04678558,0.0004311899],"about_ca_topic_score_codex":0.00030280589,"about_ca_topic_score_gemma":0.000051356456,"teacher_disagreement_score":0.89758015,"about_ca_system_score_codex":0.00008756751,"about_ca_system_score_gemma":0.000587988,"threshold_uncertainty_score":0.9998107},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15404926,0.00041410513,0.83729976,0.0050055315,0.00022529875,0.00029726484,0.00014295743,0.00034803737,0.0022177557],"genre_scores_gemma":[0.57315296,0.00048471097,0.41394952,0.0043424214,0.00020172082,0.00014180093,0.000077559154,0.000041294774,0.007607993],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965489,0.00025259014,0.00053562986,0.00090006326,0.00034352613,0.0014192993],"domain_scores_gemma":[0.9971651,0.00035048276,0.00020004805,0.0014723268,0.00011433981,0.00069772056],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009251121,0.0004453418,0.0004290675,0.00015494076,0.00076022506,0.0005835107,0.0022865674,0.00029381627,0.00022554083],"category_scores_gemma":[0.00019812875,0.0004193034,0.00018296753,0.00067526905,0.00031556448,0.0005193585,0.00072766613,0.0006297525,0.0002787725],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007870086,0.0029095837,0.0794915,0.00011424033,0.0003179996,0.0015998149,0.031479765,0.00068463036,0.0022409887,0.04771926,0.4310364,0.40232712],"study_design_scores_gemma":[0.001149609,0.00035957168,0.031309236,0.00016369969,0.00008521576,0.0027197856,0.002652785,0.9262943,0.0036876004,0.0024099546,0.028201954,0.0009662719],"about_ca_topic_score_codex":0.008631975,"about_ca_topic_score_gemma":0.0008776826,"teacher_disagreement_score":0.9256097,"about_ca_system_score_codex":0.0006496653,"about_ca_system_score_gemma":0.0011902181,"threshold_uncertainty_score":0.9998259},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2598078,0.0000020703785,0.7391077,0.0001055382,0.00009056234,0.0003373195,0.00009005879,0.00037532707,0.00008361783],"genre_scores_gemma":[0.8260637,0.0000031747643,0.17326695,0.0002977186,0.00005576256,0.00013580995,0.00014709719,0.00002012524,0.000009651046],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846405,0.00003757255,0.0003703293,0.000581378,0.0002523068,0.00029438492],"domain_scores_gemma":[0.9986901,0.00015295608,0.00019064557,0.0007338427,0.00013288709,0.00009952821],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003463855,0.00017497827,0.00019362553,0.00021792362,0.0003709821,0.00012426828,0.0010569462,0.000071370865,0.0000022853894],"category_scores_gemma":[6.8009217e-7,0.00018952503,0.00007487035,0.0011253245,0.000014647823,0.00042979984,0.000014546696,0.00010609128,0.000025752304],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028364102,0.0009539523,0.00043746686,0.0006761718,0.000111830865,0.0000011117377,0.009699719,0.16920564,0.015578507,0.0013670482,0.000026782354,0.8019134],"study_design_scores_gemma":[0.00035359143,0.00011723641,0.0006081796,0.000050948016,0.00001923368,0.000006323805,0.0018125703,0.9868091,0.009894651,0.00006557547,0.0000818892,0.00018073262],"about_ca_topic_score_codex":0.0005552289,"about_ca_topic_score_gemma":0.00007062969,"teacher_disagreement_score":0.8176034,"about_ca_system_score_codex":0.000028090819,"about_ca_system_score_gemma":0.00003396682,"threshold_uncertainty_score":0.77286065},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013544822,0.000037172125,0.9827715,0.00030947017,0.00034651006,0.00080973184,0.0014707299,0.00039672584,0.00031332468],"genre_scores_gemma":[0.56953883,0.000026709446,0.41597772,0.00022815847,0.00010055145,0.00026808566,0.013800567,0.000022941957,0.000036455065],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978398,0.000055511555,0.0007506673,0.0005327431,0.00028972316,0.00053154206],"domain_scores_gemma":[0.9969175,0.00016436834,0.0003154885,0.002379617,0.00014507525,0.000077987264],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0022190004,0.00018831789,0.00024118998,0.00032071196,0.00060327526,0.0014620143,0.0049242084,0.0000948366,0.0000038371777],"category_scores_gemma":[0.00045291186,0.00018620497,0.000025804444,0.0014204915,0.000060835508,0.010858695,0.0046531023,0.00014379488,0.00008825605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017466238,0.00014059212,0.00034595854,0.00025299285,0.000026556887,0.0000048468983,0.009334274,0.002239138,0.00023929159,0.009682846,0.010023858,0.9676922],"study_design_scores_gemma":[0.00046362611,0.000045319277,0.0007095261,0.00015461174,0.000006957509,0.000020089215,0.00056393136,0.98486453,0.0001332395,0.0013770193,0.011434076,0.00022707891],"about_ca_topic_score_codex":0.00051357446,"about_ca_topic_score_gemma":0.00041972895,"teacher_disagreement_score":0.98262537,"about_ca_system_score_codex":0.00016462596,"about_ca_system_score_gemma":0.00018433205,"threshold_uncertainty_score":0.99957454},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.412022,0.0000058920045,0.58537966,0.0016031269,0.00004476648,0.000288256,0.000034187036,0.00025770636,0.00036441287],"genre_scores_gemma":[0.74128467,0.0000916705,0.25818858,0.00025820907,0.000040247483,0.000056869358,0.000021712849,0.000008383547,0.000049673512],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99826604,0.00002034815,0.00048971176,0.0004638348,0.0005267923,0.00023325537],"domain_scores_gemma":[0.9991211,0.00015860186,0.00035976345,0.00017679622,0.0001075462,0.000076185264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009519046,0.00013708626,0.00022103489,0.00020269484,0.00009105551,0.00007499575,0.0014951201,0.00008592918,0.000008693395],"category_scores_gemma":[0.00006437631,0.00014277705,0.00005110882,0.0009293163,0.0000717153,0.0008383198,0.00068757444,0.00017431384,0.00002080998],"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":[0.000004554013,0.00018566225,0.007819911,0.00052309234,0.0000695268,8.7360354e-7,0.0013666283,0.00011342447,0.0010148226,0.75238323,0.0013160618,0.23520224],"study_design_scores_gemma":[0.00038067,0.000111569425,0.7599254,0.0002579452,0.00003178224,0.0000012770824,0.0005770918,0.09760241,0.0050300914,0.13387933,0.0018282373,0.00037412957],"about_ca_topic_score_codex":0.000015431617,"about_ca_topic_score_gemma":1.6708654e-7,"teacher_disagreement_score":0.75210553,"about_ca_system_score_codex":0.000016306994,"about_ca_system_score_gemma":0.000012253127,"threshold_uncertainty_score":0.58222795},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006393295,0.00047405928,0.97376966,0.00028823622,0.00053300796,0.00023561245,0.0006136127,0.00035876612,0.023663128],"genre_scores_gemma":[0.005892499,0.0012892201,0.9227986,0.00039588843,0.00052348536,0.0000045917377,0.00038271103,0.00016872147,0.068544276],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973259,0.000026904736,0.0006873847,0.0010590747,0.00039061377,0.00051012996],"domain_scores_gemma":[0.99756765,0.0009165742,0.00048699664,0.0006238688,0.00014042632,0.00026450993],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003477581,0.0005361688,0.0005982905,0.00021814308,0.00073811173,0.00091122754,0.00062436913,0.00019393225,0.000007506433],"category_scores_gemma":[0.00004230448,0.00056121923,0.00005669983,0.00012703142,0.00021896895,0.00009885351,0.0015154246,0.0005505089,0.000041169653],"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":[6.981859e-7,0.000007871007,0.0000109401035,0.000049442828,0.000046698326,0.000037070276,0.0002833433,0.000027749564,0.0000012948378,0.5985931,0.002836582,0.3981052],"study_design_scores_gemma":[0.00029625033,0.00014634385,0.00058900786,0.0002906395,0.000070178125,0.00008319545,0.000051854768,0.7181413,0.0000016124033,0.2495574,0.030035742,0.00073645817],"about_ca_topic_score_codex":0.000029904497,"about_ca_topic_score_gemma":0.000015078887,"teacher_disagreement_score":0.71811354,"about_ca_system_score_codex":0.000020986447,"about_ca_system_score_gemma":0.000095998126,"threshold_uncertainty_score":0.9996839},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005468886,0.000044264547,0.82703704,0.035877224,0.00084153947,0.00027823081,0.000008313012,0.0005586566,0.12988584],"genre_scores_gemma":[0.52800554,0.0025666868,0.3485138,0.004771266,0.00058968837,0.00020995735,0.00011615838,0.000039472943,0.1151874],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994069,0.000008230914,0.00008912158,0.00020930298,0.0001615197,0.00012493336],"domain_scores_gemma":[0.9995095,0.00013677093,0.000024186596,0.0002850012,0.000013583529,0.000030916293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022283637,0.000050416427,0.00003250872,0.000045110348,0.00023912596,0.00030976656,0.00059264776,0.000009890882,0.000004420421],"category_scores_gemma":[0.000007982651,0.000034005756,0.000013467274,0.00027025366,0.00002312615,0.0000770901,0.0006396992,0.000047293008,0.0001915487],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.5851815e-7,0.000009720583,0.000026903364,0.0000012557649,0.000011583213,0.000002934562,0.000054597986,0.00008539502,0.000002461663,0.3703476,0.024874704,0.6045825],"study_design_scores_gemma":[0.000115903604,0.00000932706,0.008720227,0.000023376286,0.0000016576836,0.0000027203944,0.00022688217,0.66125685,0.000018502942,0.0017265398,0.32781956,0.00007847349],"about_ca_topic_score_codex":0.0000061375576,"about_ca_topic_score_gemma":0.0000039783577,"teacher_disagreement_score":0.66117144,"about_ca_system_score_codex":0.000011340344,"about_ca_system_score_gemma":0.000003360533,"threshold_uncertainty_score":0.29870862},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008686649,0.00006775747,0.99636984,0.00059584045,0.00086223584,0.00019820555,0.00005145594,0.00017433742,0.0008116724],"genre_scores_gemma":[0.124260075,0.000054957723,0.8736715,0.00066938024,0.00055041345,0.00002883804,0.00004014103,0.00007303423,0.00065167696],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967652,0.00001759349,0.00056136533,0.0012745719,0.00084406725,0.0005371796],"domain_scores_gemma":[0.9974356,0.0005899619,0.00016376867,0.0014664144,0.00017602369,0.00016821214],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005311558,0.0003631718,0.00046793057,0.0006355455,0.00014759167,0.00027101667,0.0034139329,0.000221874,0.000015423102],"category_scores_gemma":[0.00010426391,0.00034040105,0.00011939856,0.00072744285,0.000493668,0.00037649416,0.0018860738,0.00043738476,0.00006101578],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003062302,0.00004076515,0.00023671363,0.00006459607,0.000014933659,0.00009898025,0.0009512599,0.0015810821,0.00016935961,0.0203251,0.00010583749,0.9764083],"study_design_scores_gemma":[0.00032669218,0.0002622642,0.0015971799,0.0009674883,0.000017417082,0.0000623101,0.0000011050573,0.9644718,0.0023160207,0.027950812,0.0011953359,0.00083157985],"about_ca_topic_score_codex":0.000025706076,"about_ca_topic_score_gemma":0.000035808283,"teacher_disagreement_score":0.97557676,"about_ca_system_score_codex":0.00008560818,"about_ca_system_score_gemma":0.00036880505,"threshold_uncertainty_score":0.9999048},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02266964,0.00001196038,0.97004116,0.004927655,0.000101800826,0.000076268174,0.0011531479,0.0005773592,0.00044102603],"genre_scores_gemma":[0.32553464,0.00003429455,0.6578261,0.0014247666,0.00055497594,0.000031774103,0.0118442075,0.000033071592,0.0027161217],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999031,0.00000838227,0.00013923406,0.00044971626,0.00017348016,0.00019818825],"domain_scores_gemma":[0.99861455,0.00006232964,0.00004893481,0.0011702538,0.000019650322,0.000084305095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011262548,0.0000773661,0.00009088405,0.000042378597,0.00010548571,0.00045021035,0.0013212615,0.000013870719,0.000021819735],"category_scores_gemma":[0.000009490755,0.00005886022,0.000009667912,0.00034347185,0.000015823338,0.000894338,0.0009443133,0.00004240953,0.0002842951],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015785163,0.000050344246,0.0042505837,0.0000070201468,0.00003541399,0.00001919454,0.0005654404,0.000035567504,0.000021025837,0.0019248282,0.10323633,0.88985264],"study_design_scores_gemma":[0.0002998364,0.00007066802,0.0069739427,0.000047699265,0.0000039414235,0.000010474084,0.00032489566,0.94023645,0.00006756798,0.00027996054,0.051436964,0.00024762593],"about_ca_topic_score_codex":0.0005420545,"about_ca_topic_score_gemma":0.000102731756,"teacher_disagreement_score":0.94020087,"about_ca_system_score_codex":0.0000075647786,"about_ca_system_score_gemma":0.000085039086,"threshold_uncertainty_score":0.43413886},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20905474,0.0010960716,0.77051556,0.009552728,0.0015138733,0.00080522103,0.000049672268,0.00020406058,0.007208055],"genre_scores_gemma":[0.7203514,0.0010392574,0.2671007,0.0025059762,0.005650152,0.0002352073,0.000029980281,0.00009389359,0.002993427],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981756,0.00006764477,0.00039627776,0.0005788654,0.0004871256,0.0002944439],"domain_scores_gemma":[0.9978738,0.000069495385,0.00032850722,0.0010416103,0.00043440494,0.00025221184],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007568976,0.0001822933,0.00030974686,0.00045085303,0.00032461324,0.0020597987,0.0046333876,0.00004128874,0.001692485],"category_scores_gemma":[0.00010053664,0.00014892807,0.000046008106,0.0018259063,0.00011321768,0.0032539263,0.0013425671,0.0001771102,0.0001625135],"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":[0.000055528566,0.00025320495,0.012531467,0.000015823247,0.00009504266,0.000009627632,0.00047483845,0.00008407663,0.032810565,0.0039804163,0.6146661,0.33502328],"study_design_scores_gemma":[0.00049607997,0.0001036978,0.27813846,0.00022603555,0.00004539718,0.000080302074,0.00006703746,0.0032470399,0.06588214,0.0067343395,0.64421886,0.000760638],"about_ca_topic_score_codex":0.000288959,"about_ca_topic_score_gemma":0.00003383481,"teacher_disagreement_score":0.5112967,"about_ca_system_score_codex":0.00005079446,"about_ca_system_score_gemma":0.00010455756,"threshold_uncertainty_score":0.99922013},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04982708,0.0000064811024,0.94587,0.0014244148,0.0011466449,0.00028986606,0.00028286848,0.0008622942,0.0002903661],"genre_scores_gemma":[0.5887806,0.000017958773,0.40766472,0.00008420692,0.00035038852,0.0001617305,0.0011305081,0.00002603757,0.0017838747],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977299,0.000064626314,0.00042901663,0.0010982713,0.00037981552,0.00029838033],"domain_scores_gemma":[0.9976421,0.00008213066,0.00021341543,0.0018431189,0.00010934177,0.00010988477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004851472,0.00023763077,0.00024768742,0.00012493118,0.00014907226,0.0004925431,0.0015393168,0.00019111074,0.00009376025],"category_scores_gemma":[0.000025263105,0.00023359944,0.000100680234,0.00023721777,0.000035228004,0.00019251893,0.002730434,0.00027100614,0.00016000205],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009716089,0.00042910755,0.0038104227,0.00038537075,0.0003100838,0.00008827727,0.0020994453,0.0050857025,0.0043231444,0.0853726,0.04987849,0.84820765],"study_design_scores_gemma":[0.00017262921,0.000022145881,0.059312057,0.00008941302,0.000030787523,0.000004337648,0.000042454532,0.91364634,0.007544535,0.016280176,0.0022656338,0.0005894686],"about_ca_topic_score_codex":0.0013297043,"about_ca_topic_score_gemma":0.00004876882,"teacher_disagreement_score":0.90856063,"about_ca_system_score_codex":0.000059210335,"about_ca_system_score_gemma":0.00015578857,"threshold_uncertainty_score":0.9525908},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04982708,0.0000064811024,0.94587,0.0014244148,0.0011466449,0.00028986606,0.00028286848,0.0008622942,0.0002903661],"genre_scores_gemma":[0.5887806,0.000017958773,0.40766472,0.00008420692,0.00035038852,0.0001617305,0.0011305081,0.00002603757,0.0017838747],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977299,0.000064626314,0.00042901663,0.0010982713,0.00037981552,0.00029838033],"domain_scores_gemma":[0.9976421,0.00008213066,0.00021341543,0.0018431189,0.00010934177,0.00010988477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004851472,0.00023763077,0.00024768742,0.00012493118,0.00014907226,0.0004925431,0.0015393168,0.00019111074,0.00009376025],"category_scores_gemma":[0.000025263105,0.00023359944,0.000100680234,0.00023721777,0.000035228004,0.00019251893,0.002730434,0.00027100614,0.00016000205],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009716089,0.00042910755,0.0038104227,0.00038537075,0.0003100838,0.00008827727,0.0020994453,0.0050857025,0.0043231444,0.0853726,0.04987849,0.84820765],"study_design_scores_gemma":[0.00017262921,0.000022145881,0.059312057,0.00008941302,0.000030787523,0.000004337648,0.000042454532,0.91364634,0.007544535,0.016280176,0.0022656338,0.0005894686],"about_ca_topic_score_codex":0.0013297043,"about_ca_topic_score_gemma":0.00004876882,"teacher_disagreement_score":0.90856063,"about_ca_system_score_codex":0.000059210335,"about_ca_system_score_gemma":0.00015578857,"threshold_uncertainty_score":0.9525908},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12797542,0.000082362894,0.8534598,0.00058018934,0.00096390373,0.00013504873,0.016073024,0.0005542049,0.00017606516],"genre_scores_gemma":[0.94733584,0.00022033186,0.044535972,0.00011166901,0.00025908978,0.00009260102,0.0068550673,0.000048019665,0.00054139877],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99774593,0.00006013424,0.0003523463,0.0012149205,0.00024119235,0.00038549321],"domain_scores_gemma":[0.9936139,0.00078367,0.00008274014,0.00536118,0.000031658816,0.00012685606],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001784589,0.00026761045,0.00023923922,0.00021257365,0.00037948863,0.00076320814,0.0056080706,0.000075535914,0.000053174506],"category_scores_gemma":[0.00007505007,0.000259243,0.000094544455,0.0008407405,0.000052785595,0.003305503,0.0006782473,0.00031658754,0.0009672329],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017081282,0.0006436243,0.0017333233,0.000025358499,0.00031515418,0.00003847947,0.0022259443,0.00047849992,0.0023986404,0.0013669779,0.0063863564,0.9843706],"study_design_scores_gemma":[0.0024278942,0.00022901624,0.07162513,0.0013798096,0.0003279841,0.000014694995,0.002454008,0.8276272,0.012941786,0.027994221,0.050227396,0.0027508975],"about_ca_topic_score_codex":0.0016907239,"about_ca_topic_score_gemma":0.0008285621,"teacher_disagreement_score":0.98161966,"about_ca_system_score_codex":0.000042617085,"about_ca_system_score_gemma":0.00007908837,"threshold_uncertainty_score":0.999986},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020839709,0.0000619287,0.99613047,0.00041645428,0.0009787343,0.00052436674,0.00006499625,0.00038229176,0.0012323462],"genre_scores_gemma":[0.007896792,0.000007782446,0.99008995,0.00040573042,0.00038936347,0.00003369229,0.00012551161,0.000058954738,0.0009922172],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957206,0.000034830708,0.00057759456,0.0016597087,0.0013401521,0.0006670976],"domain_scores_gemma":[0.9971676,0.00041431494,0.0005749284,0.0013549217,0.00033598923,0.00015222961],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012226704,0.00047005407,0.0004524141,0.0009424715,0.0004632677,0.00091459736,0.0025224364,0.00035769015,0.0000064488167],"category_scores_gemma":[0.00008944047,0.000462653,0.00013117766,0.0012964144,0.00023061152,0.00027201814,0.0009773356,0.0005588088,0.000067949775],"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":[0.0000036622218,0.000057208996,0.000023365861,0.000041787684,0.000010866887,0.000010223285,0.00038034515,0.9032569,0.000050229257,0.014442254,0.000027392121,0.081695795],"study_design_scores_gemma":[0.0004000406,0.00003882906,0.00004376985,0.00016581325,0.000013775374,0.000005274559,3.802843e-7,0.9944539,0.00021565908,0.0034226289,0.00073952804,0.0005003711],"about_ca_topic_score_codex":0.00006865806,"about_ca_topic_score_gemma":0.000018794888,"teacher_disagreement_score":0.091197066,"about_ca_system_score_codex":0.00080677815,"about_ca_system_score_gemma":0.0007506327,"threshold_uncertainty_score":0.9997825},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013215684,0.0012962779,0.99579734,0.0004989556,0.00050840585,0.00032901738,0.000042828982,0.00014876953,0.0012462384],"genre_scores_gemma":[0.024747355,0.0018570451,0.94493544,0.00042078245,0.0014695346,0.00020224784,0.00036293833,0.00015253879,0.025852146],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99607337,0.00016875795,0.0004074203,0.0017885948,0.00076717895,0.0007946695],"domain_scores_gemma":[0.9964794,0.0020233241,0.000104694336,0.0011151339,0.00013477622,0.00014267379],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003504139,0.00031435033,0.00038566912,0.0014915583,0.00039802463,0.0010986825,0.0028568064,0.00014184341,0.0000025768961],"category_scores_gemma":[0.00040142552,0.00028965832,0.000039677932,0.0034369035,0.0007971975,0.0011902184,0.0041673733,0.0018175906,0.00007205623],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021678068,0.00007159849,0.00035360028,0.000084044106,0.000004151238,0.000083892104,0.0015632426,0.0019342643,0.00004296436,0.007070813,0.00037407593,0.9884152],"study_design_scores_gemma":[0.00022502428,0.000092970295,0.0005295747,0.0006192347,0.0000021387616,0.000029698864,0.0000013571631,0.95733225,0.000085106665,0.023312883,0.017353902,0.00041586003],"about_ca_topic_score_codex":0.0001870724,"about_ca_topic_score_gemma":0.0008947801,"teacher_disagreement_score":0.9879993,"about_ca_system_score_codex":0.00031067166,"about_ca_system_score_gemma":0.0012932689,"threshold_uncertainty_score":0.99995553},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002017606,0.0010448697,0.9960108,0.00030766384,0.00043504243,0.00039897638,0.00013128863,0.00016365404,0.0013059346],"genre_scores_gemma":[0.039846092,0.0013511326,0.9551281,0.0006645164,0.0006117492,0.00007272279,0.00047006618,0.000090760994,0.001764875],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994984,0.000043849235,0.00045397005,0.0029278498,0.00084463635,0.0007457085],"domain_scores_gemma":[0.99641573,0.00097206264,0.00018938661,0.0021050835,0.00011250997,0.00020522947],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.003556811,0.0004154435,0.00046345405,0.0011637076,0.00056146603,0.0016408485,0.0056306603,0.000113124705,0.000001105076],"category_scores_gemma":[0.0004733512,0.0003819911,0.000017164293,0.0035626988,0.0020157753,0.0029549166,0.011673408,0.0009792083,0.000017149858],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021234637,0.000044895507,0.00022884959,0.00007408799,0.0000035817388,0.000025490413,0.0007117011,0.0006050618,0.0001681507,0.0065018227,0.000117052616,0.9915172],"study_design_scores_gemma":[0.00027654515,0.000042134518,0.00071237516,0.00031045752,0.000006472174,0.000045239285,0.0000016364538,0.9833667,0.000108630666,0.00604542,0.00856636,0.00051797344],"about_ca_topic_score_codex":0.000090533475,"about_ca_topic_score_gemma":0.00041892438,"teacher_disagreement_score":0.9909992,"about_ca_system_score_codex":0.00023978532,"about_ca_system_score_gemma":0.0021695844,"threshold_uncertainty_score":0.9998632},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013215684,0.0012962779,0.99579734,0.0004989556,0.00050840585,0.00032901738,0.000042828982,0.00014876953,0.0012462384],"genre_scores_gemma":[0.024747355,0.0018570451,0.94493544,0.00042078245,0.0014695346,0.00020224784,0.00036293833,0.00015253879,0.025852146],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99607337,0.00016875795,0.0004074203,0.0017885948,0.00076717895,0.0007946695],"domain_scores_gemma":[0.9964794,0.0020233241,0.000104694336,0.0011151339,0.00013477622,0.00014267379],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003504139,0.00031435033,0.00038566912,0.0014915583,0.00039802463,0.0010986825,0.0028568064,0.00014184341,0.0000025768961],"category_scores_gemma":[0.00040142552,0.00028965832,0.000039677932,0.0034369035,0.0007971975,0.0011902184,0.0041673733,0.0018175906,0.00007205623],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021678068,0.00007159849,0.00035360028,0.000084044106,0.000004151238,0.000083892104,0.0015632426,0.0019342643,0.00004296436,0.007070813,0.00037407593,0.9884152],"study_design_scores_gemma":[0.00022502428,0.000092970295,0.0005295747,0.0006192347,0.0000021387616,0.000029698864,0.0000013571631,0.95733225,0.000085106665,0.023312883,0.017353902,0.00041586003],"about_ca_topic_score_codex":0.0001870724,"about_ca_topic_score_gemma":0.0008947801,"teacher_disagreement_score":0.9879993,"about_ca_system_score_codex":0.00031067166,"about_ca_system_score_gemma":0.0012932689,"threshold_uncertainty_score":0.99995553},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013215684,0.0012962779,0.99579734,0.0004989556,0.00050840585,0.00032901738,0.000042828982,0.00014876953,0.0012462384],"genre_scores_gemma":[0.024747355,0.0018570451,0.94493544,0.00042078245,0.0014695346,0.00020224784,0.00036293833,0.00015253879,0.025852146],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99607337,0.00016875795,0.0004074203,0.0017885948,0.00076717895,0.0007946695],"domain_scores_gemma":[0.9964794,0.0020233241,0.000104694336,0.0011151339,0.00013477622,0.00014267379],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003504139,0.00031435033,0.00038566912,0.0014915583,0.00039802463,0.0010986825,0.0028568064,0.00014184341,0.0000025768961],"category_scores_gemma":[0.00040142552,0.00028965832,0.000039677932,0.0034369035,0.0007971975,0.0011902184,0.0041673733,0.0018175906,0.00007205623],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021678068,0.00007159849,0.00035360028,0.000084044106,0.000004151238,0.000083892104,0.0015632426,0.0019342643,0.00004296436,0.007070813,0.00037407593,0.9884152],"study_design_scores_gemma":[0.00022502428,0.000092970295,0.0005295747,0.0006192347,0.0000021387616,0.000029698864,0.0000013571631,0.95733225,0.000085106665,0.023312883,0.017353902,0.00041586003],"about_ca_topic_score_codex":0.0001870724,"about_ca_topic_score_gemma":0.0008947801,"teacher_disagreement_score":0.9879993,"about_ca_system_score_codex":0.00031067166,"about_ca_system_score_gemma":0.0012932689,"threshold_uncertainty_score":0.99995553},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002017606,0.0010448697,0.9960108,0.00030766384,0.00043504243,0.00039897638,0.00013128863,0.00016365404,0.0013059346],"genre_scores_gemma":[0.039846092,0.0013511326,0.9551281,0.0006645164,0.0006117492,0.00007272279,0.00047006618,0.000090760994,0.001764875],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994984,0.000043849235,0.00045397005,0.0029278498,0.00084463635,0.0007457085],"domain_scores_gemma":[0.99641573,0.00097206264,0.00018938661,0.0021050835,0.00011250997,0.00020522947],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.003556811,0.0004154435,0.00046345405,0.0011637076,0.00056146603,0.0016408485,0.0056306603,0.000113124705,0.000001105076],"category_scores_gemma":[0.0004733512,0.0003819911,0.000017164293,0.0035626988,0.0020157753,0.0029549166,0.011673408,0.0009792083,0.000017149858],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021234637,0.000044895507,0.00022884959,0.00007408799,0.0000035817388,0.000025490413,0.0007117011,0.0006050618,0.0001681507,0.0065018227,0.000117052616,0.9915172],"study_design_scores_gemma":[0.00027654515,0.000042134518,0.00071237516,0.00031045752,0.000006472174,0.000045239285,0.0000016364538,0.9833667,0.000108630666,0.00604542,0.00856636,0.00051797344],"about_ca_topic_score_codex":0.000090533475,"about_ca_topic_score_gemma":0.00041892438,"teacher_disagreement_score":0.9909992,"about_ca_system_score_codex":0.00023978532,"about_ca_system_score_gemma":0.0021695844,"threshold_uncertainty_score":0.9998632},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013215684,0.0012962779,0.99579734,0.0004989556,0.00050840585,0.00032901738,0.000042828982,0.00014876953,0.0012462384],"genre_scores_gemma":[0.024747355,0.0018570451,0.94493544,0.00042078245,0.0014695346,0.00020224784,0.00036293833,0.00015253879,0.025852146],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99607337,0.00016875795,0.0004074203,0.0017885948,0.00076717895,0.0007946695],"domain_scores_gemma":[0.9964794,0.0020233241,0.000104694336,0.0011151339,0.00013477622,0.00014267379],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003504139,0.00031435033,0.00038566912,0.0014915583,0.00039802463,0.0010986825,0.0028568064,0.00014184341,0.0000025768961],"category_scores_gemma":[0.00040142552,0.00028965832,0.000039677932,0.0034369035,0.0007971975,0.0011902184,0.0041673733,0.0018175906,0.00007205623],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021678068,0.00007159849,0.00035360028,0.000084044106,0.000004151238,0.000083892104,0.0015632426,0.0019342643,0.00004296436,0.007070813,0.00037407593,0.9884152],"study_design_scores_gemma":[0.00022502428,0.000092970295,0.0005295747,0.0006192347,0.0000021387616,0.000029698864,0.0000013571631,0.95733225,0.000085106665,0.023312883,0.017353902,0.00041586003],"about_ca_topic_score_codex":0.0001870724,"about_ca_topic_score_gemma":0.0008947801,"teacher_disagreement_score":0.9879993,"about_ca_system_score_codex":0.00031067166,"about_ca_system_score_gemma":0.0012932689,"threshold_uncertainty_score":0.99995553},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013215684,0.0012962779,0.99579734,0.0004989556,0.00050840585,0.00032901738,0.000042828982,0.00014876953,0.0012462384],"genre_scores_gemma":[0.024747355,0.0018570451,0.94493544,0.00042078245,0.0014695346,0.00020224784,0.00036293833,0.00015253879,0.025852146],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99607337,0.00016875795,0.0004074203,0.0017885948,0.00076717895,0.0007946695],"domain_scores_gemma":[0.9964794,0.0020233241,0.000104694336,0.0011151339,0.00013477622,0.00014267379],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003504139,0.00031435033,0.00038566912,0.0014915583,0.00039802463,0.0010986825,0.0028568064,0.00014184341,0.0000025768961],"category_scores_gemma":[0.00040142552,0.00028965832,0.000039677932,0.0034369035,0.0007971975,0.0011902184,0.0041673733,0.0018175906,0.00007205623],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021678068,0.00007159849,0.00035360028,0.000084044106,0.000004151238,0.000083892104,0.0015632426,0.0019342643,0.00004296436,0.007070813,0.00037407593,0.9884152],"study_design_scores_gemma":[0.00022502428,0.000092970295,0.0005295747,0.0006192347,0.0000021387616,0.000029698864,0.0000013571631,0.95733225,0.000085106665,0.023312883,0.017353902,0.00041586003],"about_ca_topic_score_codex":0.0001870724,"about_ca_topic_score_gemma":0.0008947801,"teacher_disagreement_score":0.9879993,"about_ca_system_score_codex":0.00031067166,"about_ca_system_score_gemma":0.0012932689,"threshold_uncertainty_score":0.99995553},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004197778,0.0012642249,0.98952913,0.0037707558,0.00052701717,0.00028939013,0.000024729054,0.00034719385,0.000049800834],"genre_scores_gemma":[0.041352626,0.024010958,0.9154147,0.0003838754,0.0014972524,0.00038975565,0.0006449595,0.00017090427,0.016134964],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963821,0.0001402352,0.00048028713,0.0008287346,0.00045226022,0.0017163381],"domain_scores_gemma":[0.9981538,0.0001037466,0.0003506331,0.0010512492,0.00016869411,0.00017189744],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0021652803,0.0002662765,0.00030984473,0.00026949242,0.00040080474,0.00056318135,0.0019659058,0.00009358783,0.0000074139884],"category_scores_gemma":[0.00029250747,0.0002647101,0.00013859906,0.0006106264,0.000021588432,0.00041496166,0.0021688594,0.0038172826,0.0005119405],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010541818,0.00024105438,0.0010666513,0.00009681053,0.00045748355,0.000038610193,0.0014796279,0.009904955,0.0008911736,0.11635862,0.004296291,0.8651582],"study_design_scores_gemma":[0.0020523022,0.0005970676,0.0070007625,0.0020163907,0.00028217185,0.0017772206,0.0060366676,0.6124788,0.0009857727,0.23058668,0.13269386,0.0034923144],"about_ca_topic_score_codex":0.0004476822,"about_ca_topic_score_gemma":0.000397252,"teacher_disagreement_score":0.86166584,"about_ca_system_score_codex":0.0005327686,"about_ca_system_score_gemma":0.0019486895,"threshold_uncertainty_score":0.9999805},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011981599,0.0000350177,0.9849988,0.0022943986,0.00018988342,0.00027240874,0.000058504567,0.00009595725,0.000073384406],"genre_scores_gemma":[0.20088701,0.00015147783,0.79040647,0.002104025,0.0017305729,0.0000929418,0.000105008876,0.00012014615,0.0044023804],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99891555,0.000089490575,0.0003168367,0.00015669661,0.00027514753,0.00024625697],"domain_scores_gemma":[0.99828416,0.00038937465,0.0002917772,0.0007266531,0.0001862554,0.000121753954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017551756,0.0001073966,0.00018714268,0.0000806338,0.00041065007,0.0005183401,0.0042663706,0.00003531431,0.000014498688],"category_scores_gemma":[0.00018743252,0.00007111633,0.00007929381,0.00041532025,0.00004739433,0.00094545755,0.0006651277,0.00017371721,0.00006230351],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043634816,0.00011765504,0.00034295567,0.000014961043,0.00006664769,0.000012444753,0.007602913,0.0012883428,0.00031197228,0.0014275425,0.05499424,0.9337767],"study_design_scores_gemma":[0.003440156,0.0018883632,0.013461973,0.00026451272,0.0001966138,0.0006172596,0.0053077578,0.15192138,0.0019379071,0.03752154,0.7824874,0.00095515826],"about_ca_topic_score_codex":0.00010679079,"about_ca_topic_score_gemma":0.000032278327,"teacher_disagreement_score":0.9328215,"about_ca_system_score_codex":0.0000200144,"about_ca_system_score_gemma":0.00010817211,"threshold_uncertainty_score":0.79280496},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008878924,0.00006170234,0.99110156,0.0018398486,0.00041509382,0.00080559705,0.0006673442,0.000236963,0.0039839754],"genre_scores_gemma":[0.08278038,0.0005128325,0.9117039,0.0013718165,0.000098403885,0.000573951,0.0018674249,0.00002689651,0.0010644282],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979739,0.000031789325,0.0008009506,0.0004895817,0.0004209016,0.00028285015],"domain_scores_gemma":[0.99599344,0.00062876055,0.00041323082,0.0024273775,0.0004343225,0.00010286595],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001095248,0.00024957335,0.00028965966,0.00069561077,0.0006245818,0.0010696161,0.004037803,0.00012410295,0.00000804754],"category_scores_gemma":[0.00007964279,0.00024458632,0.000071745955,0.00043373328,0.0005691176,0.0038132907,0.0019602682,0.00027676058,0.00003401826],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004617075,0.00004527928,0.00023939117,0.00006628283,0.000018061164,4.2059898e-7,0.0028587205,0.00013325346,0.0000045652505,0.2834808,0.00080412265,0.71234447],"study_design_scores_gemma":[0.00031018202,0.000059941412,0.00413002,0.00040883102,0.000009285674,0.0000023168736,0.00004420564,0.942945,0.000020058855,0.012759781,0.03898763,0.0003227439],"about_ca_topic_score_codex":0.00018538679,"about_ca_topic_score_gemma":0.000068432484,"teacher_disagreement_score":0.9428117,"about_ca_system_score_codex":0.00012514245,"about_ca_system_score_gemma":0.0005140306,"threshold_uncertainty_score":0.9999674},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002188404,0.00056162925,0.9962732,0.000020508623,0.00034545865,0.00033565424,0.00021520203,0.00004666129,0.0000132714895],"genre_scores_gemma":[0.30040225,0.00022062866,0.6989523,0.000009991531,0.0001532962,0.000071693314,0.00016686629,0.000012186807,0.000010793807],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874985,0.000049424772,0.0004114652,0.00046953655,0.00014392336,0.0001757879],"domain_scores_gemma":[0.9988997,0.00014843354,0.00016794525,0.00067819864,0.000059946684,0.00004576114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006471297,0.00010802761,0.0002863109,0.00013209599,0.00004806941,0.000065472064,0.00081603974,0.00004178355,2.0782927e-7],"category_scores_gemma":[0.0000027979524,0.00009745466,0.000027413302,0.00037642947,0.000038474136,0.0011907304,0.00010363501,0.00005161491,2.8524727e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000050306544,0.00008988081,0.00005614245,0.00026123418,0.00001919469,6.204056e-7,0.00073325576,0.010832819,0.0019321454,0.0012496462,0.00003944781,0.9847806],"study_design_scores_gemma":[0.00038868518,0.00012695463,0.000115297255,0.000059499398,0.000005808593,0.0000046217347,0.00018794001,0.9974758,0.00026738812,0.00016410612,0.0010979283,0.000105951105],"about_ca_topic_score_codex":0.000045678087,"about_ca_topic_score_gemma":0.0000026509238,"teacher_disagreement_score":0.986643,"about_ca_system_score_codex":0.000006225958,"about_ca_system_score_gemma":0.000020907783,"threshold_uncertainty_score":0.39740855},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62621194,0.0000025060017,0.3730996,0.00010722993,0.00004605934,0.000052762018,0.000170436,0.00007830892,0.00023112651],"genre_scores_gemma":[0.9183349,0.000005383857,0.08131696,0.000010397772,0.0000071861136,0.000015422955,0.000089658715,0.0000034848292,0.00021660543],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992333,0.000013751079,0.00022054282,0.0002632946,0.00014895105,0.000120156976],"domain_scores_gemma":[0.9991043,0.0001031299,0.00009673023,0.00061617186,0.000047967776,0.00003168851],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000110371904,0.00006358894,0.00013622355,0.000047412872,0.00002562978,0.000016398346,0.00057693315,0.000027115455,0.000051222676],"category_scores_gemma":[0.000015391975,0.000056082827,0.000030180694,0.0003271399,0.000027504519,0.00013428676,0.00025845176,0.000033825152,0.000022379732],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022202412,0.000062419254,0.0031140489,0.000027827862,0.00002597325,0.0000011312148,0.0009506651,0.00001356674,0.014492104,0.0066880165,0.0003627229,0.9742593],"study_design_scores_gemma":[0.00029579017,0.000060963095,0.30663088,0.000061944076,0.000008742315,3.0273586e-7,0.00037895972,0.5763061,0.11272318,0.0033303676,0.000047444573,0.00015532522],"about_ca_topic_score_codex":0.0010619794,"about_ca_topic_score_gemma":0.00006954675,"teacher_disagreement_score":0.974104,"about_ca_system_score_codex":0.000006179323,"about_ca_system_score_gemma":0.000027167202,"threshold_uncertainty_score":0.22869913},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002478564,0.00005746838,0.9931663,0.0018580039,0.000090139176,0.0012533799,0.00006691185,0.00087742874,0.002382483],"genre_scores_gemma":[0.16744661,0.000008995008,0.8049412,0.00078244787,0.0010413618,0.018827666,0.0006858991,0.00007748445,0.00618837],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982558,0.000030404188,0.0002803442,0.00071326405,0.000357829,0.00036239013],"domain_scores_gemma":[0.9979807,0.000057820343,0.00008920521,0.001443228,0.00008414542,0.00034487515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016410368,0.00019433953,0.00019849766,0.00022243217,0.0002537975,0.00032277984,0.0012013363,0.00005553048,0.0000046547143],"category_scores_gemma":[0.0000051930533,0.0001638943,0.0000457098,0.0018227106,0.000019369412,0.00019035651,0.00015492804,0.00008223228,0.00060249155],"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":[0.000021195357,0.00082939153,0.001109519,0.00017066946,0.00016972808,0.000014606149,0.0050219037,0.01595316,0.0054513407,0.29950368,0.41728914,0.25446564],"study_design_scores_gemma":[0.000704014,0.000094425326,0.0010441162,0.000069809634,0.0000113626875,0.000028788012,0.00039635113,0.38856083,0.00059522665,0.000076693184,0.60784954,0.0005688729],"about_ca_topic_score_codex":0.0009769326,"about_ca_topic_score_gemma":0.000028951745,"teacher_disagreement_score":0.37260768,"about_ca_system_score_codex":0.00005616855,"about_ca_system_score_gemma":0.00017796691,"threshold_uncertainty_score":0.7744011},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000057872476,0.000039756582,0.8994052,0.0006163386,0.0020960039,0.00042142364,0.00004445634,0.00066101755,0.09665798],"genre_scores_gemma":[0.002237341,0.00020085028,0.91061604,0.0022361968,0.0012923969,0.000106677464,0.000054330005,0.00017187145,0.08308428],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956413,0.000013722983,0.0005146496,0.0019748595,0.00116342,0.0006920402],"domain_scores_gemma":[0.996387,0.00021147865,0.00024076873,0.002792882,0.00012750992,0.00024035823],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013394024,0.00043197637,0.00038334812,0.0010244364,0.00032781443,0.00070682575,0.0050922753,0.00014946333,0.000017559787],"category_scores_gemma":[0.000049033184,0.00044448694,0.00009153043,0.00088964385,0.00047650342,0.0008601229,0.0037311327,0.0007582252,0.0010085299],"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":[0.0000010446794,0.000026676875,0.000008524413,0.000015684021,0.000006339329,0.00008945417,0.00012886328,0.00021752888,0.00003451685,0.7330013,0.00060335617,0.26586673],"study_design_scores_gemma":[0.0006367178,0.00028657741,0.0013753753,0.002056615,0.000014613733,0.000062832514,0.0000024035824,0.7847603,0.0007403132,0.057472065,0.15036622,0.0022259702],"about_ca_topic_score_codex":0.000049109884,"about_ca_topic_score_gemma":0.000015808362,"teacher_disagreement_score":0.7845428,"about_ca_system_score_codex":0.00022323098,"about_ca_system_score_gemma":0.00051282934,"threshold_uncertainty_score":0.9998007},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019077734,0.000062422136,0.9946793,0.00025033913,0.00007410118,0.00046635396,0.000031351676,0.0022820388,0.0002463337],"genre_scores_gemma":[0.22039168,0.000032706008,0.77849954,0.00000621798,0.00010494738,0.0006622343,0.00018366055,0.000051062474,0.00006796512],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99809736,0.00001218808,0.00050037197,0.000726219,0.0002365771,0.00042730788],"domain_scores_gemma":[0.99825716,0.00030298627,0.00009630911,0.0011343297,0.000072142524,0.00013708952],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010673192,0.00024800535,0.0002982771,0.00021882089,0.00021109503,0.0003933205,0.00094241416,0.00012966662,2.582684e-7],"category_scores_gemma":[0.000077395736,0.00024214294,0.000044837456,0.00060792296,0.000022630213,0.0004449592,0.00031927394,0.00017173395,0.000010433382],"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":[0.0000021905116,0.00008464604,0.0000049242626,0.0035227614,0.0000649912,0.0000012318195,0.0014075639,0.5224283,0.0025713856,0.44718814,0.00039561588,0.022328315],"study_design_scores_gemma":[0.00011338042,0.0000179326,0.000007364503,0.00038475182,0.00002206473,0.000018588287,0.00017192622,0.99699163,0.00013545307,0.0008265486,0.0010279097,0.00028243658],"about_ca_topic_score_codex":0.000005571218,"about_ca_topic_score_gemma":1.3410548e-7,"teacher_disagreement_score":0.4745634,"about_ca_system_score_codex":0.000045369827,"about_ca_system_score_gemma":0.000028837327,"threshold_uncertainty_score":0.9874302},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03964771,0.0000064710794,0.95839995,0.0008936059,0.000103680606,0.00023410782,0.000020400217,0.00040929738,0.00028480485],"genre_scores_gemma":[0.77456653,0.0000011811944,0.22510402,0.00016871371,0.000031485924,0.000016942582,0.00008944475,0.000011506418,0.000010184812],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898404,0.000023959694,0.00027566377,0.00029678748,0.00023011997,0.00018942298],"domain_scores_gemma":[0.9987583,0.00030001745,0.00016739167,0.0005168702,0.0002184783,0.00003890665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030927724,0.00010740123,0.000121106445,0.000100243844,0.0005159473,0.00013137079,0.00054204033,0.000049696304,0.0000012056973],"category_scores_gemma":[0.000035329726,0.00009428674,0.000024723266,0.0024913459,0.0000918526,0.00011330505,0.00018763864,0.0000975819,0.00003757189],"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":[0.0000012600174,0.000031340598,0.00023755743,0.000010730228,0.000008274225,2.52283e-7,0.00063024083,0.7337452,0.004621037,0.24069317,0.0005824302,0.019438487],"study_design_scores_gemma":[0.00025486664,0.0000050712483,0.0007124969,0.000008006574,0.00000814785,0.0000013766951,0.0004107651,0.9859274,0.00180027,0.010653943,0.000114673414,0.00010295211],"about_ca_topic_score_codex":0.000015122643,"about_ca_topic_score_gemma":0.0000088793895,"teacher_disagreement_score":0.73491883,"about_ca_system_score_codex":0.000025901003,"about_ca_system_score_gemma":0.00017178967,"threshold_uncertainty_score":0.39683017},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37476718,0.000004538804,0.62365234,0.00054093363,0.00009470274,0.000041391297,0.000010994015,0.00012238312,0.00076552975],"genre_scores_gemma":[0.83554393,0.000002386048,0.16421364,0.00006442512,0.000009084993,0.000016456874,0.000008165141,0.0000037300326,0.00013819274],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993596,0.000013304498,0.00014195623,0.00018811728,0.0001569701,0.0001400738],"domain_scores_gemma":[0.9994547,0.00013905962,0.000018902734,0.00030402993,0.00003797226,0.00004536699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015437245,0.000048417252,0.00007464759,0.00006611344,0.000042010375,0.000028796016,0.00037361577,0.00001533309,0.000015625426],"category_scores_gemma":[0.000034458197,0.000040230563,0.000026749898,0.00043977867,0.000024876821,0.000040493,0.00019627437,0.000030135196,0.00015210961],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018608156,0.00018740792,0.0018438126,0.000024211751,0.000030395624,0.00001387129,0.0033827976,0.0023318338,0.0032524418,0.90309936,0.0057813386,0.08005067],"study_design_scores_gemma":[0.000080613725,0.0000418221,0.013314425,0.00001545659,0.000002164238,0.0000011318607,0.0002953452,0.98306525,0.0024086311,0.00025874688,0.00045047,0.00006593217],"about_ca_topic_score_codex":0.000043589374,"about_ca_topic_score_gemma":0.0000035148462,"teacher_disagreement_score":0.98073345,"about_ca_system_score_codex":0.0000079832835,"about_ca_system_score_gemma":0.00002054484,"threshold_uncertainty_score":0.1955112},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001597245,3.153571e-7,0.9948342,0.00081782095,0.000008276631,0.0000569505,0.0006062682,0.00021362075,0.0018653409],"genre_scores_gemma":[0.26703176,0.0000012833586,0.73202026,0.00023258242,0.0000052522346,0.000015096446,0.0004759932,0.0000040323803,0.00021377947],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989516,0.00002374312,0.00021360413,0.00038945858,0.00026441773,0.00015717646],"domain_scores_gemma":[0.9976732,0.0006278886,0.000035537476,0.0015588333,0.000027784472,0.000076729644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000398682,0.00006886198,0.00019027745,0.00019307114,0.000046237572,0.000049124006,0.0013511155,0.00003360084,0.00012697023],"category_scores_gemma":[0.00017164974,0.000050364157,0.000035579073,0.0013698573,0.00004656243,0.0001091688,0.00053694594,0.000058386464,0.00018693855],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025595061,0.0005256348,0.00013716758,0.0000102035,0.00010790164,0.000009845803,0.00005223129,0.113378584,0.000018492405,0.82402223,0.030590033,0.031145105],"study_design_scores_gemma":[0.0000653841,0.00002968806,0.003482881,0.0000019296328,0.00006210953,1.634701e-7,0.0000062368654,0.990961,0.000013900698,0.005203843,0.000110635774,0.00006223712],"about_ca_topic_score_codex":0.00000549263,"about_ca_topic_score_gemma":0.0000039607344,"teacher_disagreement_score":0.87758243,"about_ca_system_score_codex":0.00000819069,"about_ca_system_score_gemma":0.000044774257,"threshold_uncertainty_score":0.25107312},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047122715,0.000003244903,0.99362725,0.00078360614,0.00005627457,0.00028773604,0.000046737332,0.0003150562,0.00016782802],"genre_scores_gemma":[0.80115473,0.000014327004,0.19806287,0.00008852438,0.00009491617,0.00011784548,0.0003497661,0.000022354614,0.0000946856],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866915,0.000034795023,0.00019581795,0.00042755116,0.00046486256,0.00020783572],"domain_scores_gemma":[0.9989514,0.00022394107,0.000049571798,0.0005806285,0.00012610659,0.000068368805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047073426,0.00010288617,0.000106544176,0.00043144962,0.00013958754,0.0000793257,0.00040427188,0.000093696464,0.0000037938025],"category_scores_gemma":[0.00005028237,0.00009519026,0.000019215773,0.0019618901,0.00003741973,0.0001539735,0.00012535113,0.00018680443,0.000024588206],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006814244,0.00012111278,0.00004639838,0.000053096937,0.000008777771,0.0000019137783,0.000091101705,0.13554311,0.006629837,0.30251193,0.00120575,0.55378014],"study_design_scores_gemma":[0.00017501901,0.00010859935,0.0026538225,0.000018966864,0.0000020257173,8.9925845e-7,0.000012773978,0.9846155,0.009464348,0.0015678052,0.0012870562,0.00009318677],"about_ca_topic_score_codex":0.000034523324,"about_ca_topic_score_gemma":0.0000011543552,"teacher_disagreement_score":0.8490724,"about_ca_system_score_codex":0.000032364554,"about_ca_system_score_gemma":0.000029661185,"threshold_uncertainty_score":0.38817462},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18632995,0.000031805328,0.7211845,0.028611582,0.0005523579,0.00033408173,0.000009800383,0.0011881911,0.061757743],"genre_scores_gemma":[0.88784736,0.00002835566,0.10888226,0.0010722539,0.00013522373,0.00010064357,0.000013196173,0.000006779853,0.0019139423],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995897,0.00001163103,0.00006325332,0.00012910359,0.000096332216,0.00010997776],"domain_scores_gemma":[0.99950373,0.00006915655,0.000008761616,0.0003988321,0.000005569823,0.000013967171],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002580715,0.000031288448,0.000029589079,0.00003895417,0.00005579007,0.000099920115,0.00072093814,0.000011075132,0.0000050893073],"category_scores_gemma":[0.0000123034115,0.000019567098,0.00001065793,0.00069418456,0.000004883871,0.00016204554,0.00013006541,0.00005570748,0.0003080231],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.9314953e-7,0.00003285213,0.00082580437,0.0000029104701,0.0000028499987,0.000013239046,0.0026150034,0.000113369206,0.00025769052,0.25163862,0.03394703,0.7105504],"study_design_scores_gemma":[0.00011624493,0.000015944946,0.032900162,0.00000955435,9.109408e-7,0.0000055554815,0.00034991314,0.697019,0.00018005223,0.0069680917,0.26230404,0.00013057035],"about_ca_topic_score_codex":0.00008129574,"about_ca_topic_score_gemma":0.000033650766,"teacher_disagreement_score":0.71041983,"about_ca_system_score_codex":0.0000054242664,"about_ca_system_score_gemma":0.000009285448,"threshold_uncertainty_score":0.39591166},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05269663,0.000054275562,0.9464713,0.00021361458,0.00021308812,0.00011588933,0.0000035314438,0.000034611498,0.00019708206],"genre_scores_gemma":[0.9488488,0.000017888513,0.0510675,0.00003436801,0.000018294018,0.000010405792,0.0000010218339,8.149891e-7,9.050618e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991365,0.0000110824,0.00028579158,0.00016397616,0.00028808854,0.000114537776],"domain_scores_gemma":[0.99935824,0.00017357312,0.00004977198,0.00029607612,0.00008676165,0.000035603323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010142958,0.00005673255,0.00007130558,0.00020794965,0.00013711158,0.00089510833,0.0006287645,0.0000131381385,6.537706e-7],"category_scores_gemma":[0.00001913935,0.000032678203,0.000010117407,0.0014108213,0.00025006197,0.005025601,0.00021393289,0.000063996114,0.000007500736],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011538523,0.000006154809,0.00008138036,0.000013762891,7.1809615e-7,2.2229038e-7,0.0023236955,0.002530074,0.000031596373,0.17566554,0.000020004225,0.8193257],"study_design_scores_gemma":[0.000016164207,0.000038885028,0.006576167,0.00009654013,7.3766506e-7,0.000017116392,0.00019450934,0.99057484,0.00029695264,0.0016830065,0.000455345,0.00004971438],"about_ca_topic_score_codex":0.000038176746,"about_ca_topic_score_gemma":0.000004361331,"teacher_disagreement_score":0.9880448,"about_ca_system_score_codex":0.000021441429,"about_ca_system_score_gemma":0.00011513929,"threshold_uncertainty_score":0.863155},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04458065,0.0033999218,0.83661085,0.024079382,0.017936932,0.0035409904,0.0012317578,0.004206683,0.064412855],"genre_scores_gemma":[0.47264892,0.0002533066,0.48125124,0.00039294735,0.002861856,0.021983664,0.0003894853,0.00012290744,0.020095674],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99830157,0.000029084122,0.00022579127,0.00079634454,0.00027136767,0.00037581997],"domain_scores_gemma":[0.9984335,0.00005217021,0.00007478421,0.0012408952,0.000045818684,0.0001528848],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041997962,0.00020460808,0.00021627857,0.00011595232,0.00005790053,0.00080316595,0.0018429265,0.00012999181,0.000005524541],"category_scores_gemma":[0.000034779856,0.00019069381,0.000114063194,0.00024245476,0.000042074946,0.00009678372,0.0047370624,0.00050454156,0.00020474636],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.081e-7,0.000050950268,0.00002973895,0.00003946748,0.00005733777,0.000023355526,0.00012392731,0.00048708828,0.0000011316861,0.034844737,0.015897993,0.9484435],"study_design_scores_gemma":[0.00043442321,0.00002530754,0.10054129,0.00013344995,0.00017071725,0.000045183002,0.00006135384,0.5013902,0.0004332855,0.061961528,0.33279395,0.0020092542],"about_ca_topic_score_codex":0.00010159329,"about_ca_topic_score_gemma":0.000016835513,"teacher_disagreement_score":0.9464342,"about_ca_system_score_codex":0.000059042122,"about_ca_system_score_gemma":0.000096460804,"threshold_uncertainty_score":0.77762675},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033776166,0.00007435846,0.99516225,0.000331386,0.00013000936,0.0001499453,0.00030856917,0.00005383514,0.00041205037],"genre_scores_gemma":[0.12906373,0.0000038332855,0.8690174,0.00016608862,0.000055818593,0.000014135685,0.0012865755,0.000005609514,0.00038680417],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991715,0.0000069158336,0.00016103635,0.0003906864,0.00013972033,0.00013014642],"domain_scores_gemma":[0.99899334,0.00013167212,0.000060208455,0.0006468487,0.000111504654,0.00005643813],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002431153,0.00007633519,0.00012318828,0.00012595548,0.00011550698,0.00013099756,0.0006796748,0.00002265622,0.000011180964],"category_scores_gemma":[0.00005766594,0.000073006675,0.000017310404,0.00048126047,0.000017072,0.00010435245,0.000467695,0.000042849046,0.000034392084],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018065262,0.0006530062,0.06531213,0.00023363615,0.0013430809,0.000005940561,0.0014156194,0.006850286,0.00010948863,0.31960684,0.024320785,0.5801311],"study_design_scores_gemma":[0.00020725028,0.000015053298,0.01292238,0.000004628113,0.000034618795,0.0000013064293,0.000005081826,0.82457453,0.00002297394,0.0011250493,0.16097718,0.000109915476],"about_ca_topic_score_codex":0.000022225646,"about_ca_topic_score_gemma":0.000021100996,"teacher_disagreement_score":0.8177243,"about_ca_system_score_codex":0.000011790342,"about_ca_system_score_gemma":0.00007769969,"threshold_uncertainty_score":0.29771256},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013008038,0.000008239606,0.9854843,0.0006331803,0.000092335365,0.00014079729,0.00008235474,0.00015584494,0.0003948833],"genre_scores_gemma":[0.018429618,0.000006529042,0.9808826,0.00009116294,0.000021404887,0.00011701636,0.00003683996,0.0000072792554,0.0004075856],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992179,0.000010980017,0.00018306935,0.0002481916,0.00013660021,0.0002032537],"domain_scores_gemma":[0.99926215,0.00026555848,0.000026797086,0.0003092023,0.00007954887,0.000056727873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021741533,0.00006568299,0.00011522068,0.00007480424,0.00006767495,0.00004904132,0.00042860227,0.000025304127,0.000011469567],"category_scores_gemma":[0.000042243642,0.000057259425,0.000045149063,0.00041901064,0.000027132714,0.0001891042,0.0001596242,0.000029364164,0.000052193736],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013726305,0.00009990102,0.00026399412,0.000025091489,0.000034762084,0.0000030784247,0.00083960954,0.000029894509,0.0010281109,0.23986918,0.010901058,0.74690396],"study_design_scores_gemma":[0.00018875016,0.00010139695,0.0011320637,0.00001885045,0.000004501433,0.0000012603634,0.0002414999,0.9887514,0.005233703,0.0017759078,0.0024647645,0.00008588766],"about_ca_topic_score_codex":0.00006156749,"about_ca_topic_score_gemma":0.0000057018037,"teacher_disagreement_score":0.9887215,"about_ca_system_score_codex":0.000010287348,"about_ca_system_score_gemma":0.00003477313,"threshold_uncertainty_score":0.23349716},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17002898,0.005268183,0.72252166,0.09364734,0.0023493252,0.0025282975,0.0004717625,0.00040526176,0.0027791928],"genre_scores_gemma":[0.93390816,0.0004997638,0.065429814,0.000010149771,0.00007479563,0.00005242513,0.000010513073,0.0000058063547,0.000008580846],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981339,0.000014105556,0.00022313668,0.00053808535,0.0007662927,0.0003244527],"domain_scores_gemma":[0.99862546,0.000507736,0.000018092633,0.00056331727,0.00023219187,0.000053212352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007627521,0.000058785383,0.00008379793,0.0026585471,0.00015169644,0.00066572084,0.0038116632,0.00006281337,0.0000010726669],"category_scores_gemma":[0.00075793796,0.000052839037,0.000004753956,0.0026787838,0.00038061937,0.000897917,0.0021676302,0.00076422043,0.0000018697586],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007704205,0.000023124043,0.0000055497258,0.000006675713,0.0000036053145,0.0000069468497,0.00007826132,0.00009288663,0.014886054,0.4332391,0.00023037639,0.5514197],"study_design_scores_gemma":[0.000060773502,0.00008521671,0.00023068182,0.00015041982,5.5921254e-7,0.00010548338,0.00045981232,0.8318526,0.004468789,0.14976043,0.012754827,0.00007041563],"about_ca_topic_score_codex":0.000036809703,"about_ca_topic_score_gemma":0.000027185488,"teacher_disagreement_score":0.8317597,"about_ca_system_score_codex":0.000121521436,"about_ca_system_score_gemma":0.00027151636,"threshold_uncertainty_score":0.7083082},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002717636,0.0002689171,0.99255884,0.0005651747,0.0002236976,0.00016554669,0.00001615044,0.00048367202,0.0030003432],"genre_scores_gemma":[0.8211388,0.000016408188,0.17799048,0.00048461187,0.00011141661,0.00012151521,0.000027965403,0.00002270909,0.00008605981],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99850243,0.000009814742,0.00021207701,0.0006890957,0.00027182285,0.00031475778],"domain_scores_gemma":[0.9989015,0.00013579271,0.00004460383,0.00076866645,0.000042338444,0.00010709522],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001353856,0.000206857,0.00014067432,0.00014075855,0.00014117638,0.0004270132,0.0011178543,0.00006311802,0.000056629542],"category_scores_gemma":[0.000003797745,0.00015897858,0.000044175467,0.0010139369,0.000105584855,0.00021883787,0.000119881675,0.00020910423,0.00023431913],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002156222,0.000023372744,0.00007378921,0.00003493518,0.000024058125,0.000027249791,0.00057766493,0.00030088756,0.00038680548,0.1036371,0.0018317676,0.89308023],"study_design_scores_gemma":[0.00019723087,0.00020957031,0.00089634786,0.0003823776,0.00006387247,0.00010775005,0.00033702696,0.75013405,0.12313724,0.023366416,0.0997394,0.001428728],"about_ca_topic_score_codex":0.000018413137,"about_ca_topic_score_gemma":0.000010342615,"teacher_disagreement_score":0.8916515,"about_ca_system_score_codex":0.000024572926,"about_ca_system_score_gemma":0.00009496122,"threshold_uncertainty_score":0.6482959},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024777923,0.000003565985,0.9770192,0.0028323503,0.00013067326,0.000046444624,0.000004558146,0.0007490368,0.01673637],"genre_scores_gemma":[0.16702989,0.0000055774835,0.8119395,0.0021319774,0.00014336334,0.00010557862,0.00005202711,0.000016282907,0.018575842],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993733,0.000009145058,0.00009579223,0.00022732757,0.0001217426,0.00017267992],"domain_scores_gemma":[0.9993668,0.00006817297,0.00001883903,0.00046753668,0.000023495766,0.00005511292],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00018178433,0.000052315492,0.000052389572,0.00006814662,0.00010573255,0.00012532138,0.0004919275,0.000021726486,0.00006074938],"category_scores_gemma":[0.000017470984,0.000045242326,0.00002451023,0.00063971506,0.000012333344,0.00019384152,0.00014403678,0.000046317844,0.0018200625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.3633865e-7,0.00008069029,0.00023163465,0.000012719505,0.000010809794,0.000015523505,0.0002475938,0.00014524838,0.011499504,0.21696597,0.15513714,0.61565256],"study_design_scores_gemma":[0.00010547257,0.000011925401,0.002902109,0.0000068342133,0.0000013809065,0.0000012347558,0.000030528896,0.89062244,0.010815125,0.0019688027,0.09341343,0.00012073433],"about_ca_topic_score_codex":0.000021470887,"about_ca_topic_score_gemma":0.0000072535872,"teacher_disagreement_score":0.8904772,"about_ca_system_score_codex":0.000009896161,"about_ca_system_score_gemma":0.00004238258,"threshold_uncertainty_score":0.99895716},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011531021,0.000006280335,0.98578966,0.0020617642,0.00007261224,0.00007281895,0.00002080206,0.00014393599,0.00030111318],"genre_scores_gemma":[0.08575978,0.000015066866,0.9119675,0.00037640298,0.00021222449,0.00006885926,0.00005257427,0.000009058648,0.0015385034],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99954516,0.0000062620084,0.000076989694,0.00016840879,0.00005438854,0.00014882113],"domain_scores_gemma":[0.9996461,0.00017079375,0.000025898034,0.00010337217,0.000027093296,0.000026709069],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016203136,0.00004325795,0.000062450315,0.00002827641,0.00019328941,0.00010670765,0.00018367618,0.000017173488,0.0000013833127],"category_scores_gemma":[0.000013777965,0.000039542214,0.000017710512,0.00030855899,0.000014785213,0.000113291244,0.00013016995,0.000017380762,0.0000084664935],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012169661,0.000012340217,0.001550732,0.000012160723,0.000027525304,0.0000015158565,0.0018289336,0.00009773322,0.000010909561,0.5994919,0.1551528,0.24181224],"study_design_scores_gemma":[0.00011177028,0.0000330366,0.0071070273,0.0000049393784,0.0000049565165,6.2670574e-7,0.00034359732,0.9702019,0.000009615756,0.006507974,0.015587555,0.000086970285],"about_ca_topic_score_codex":0.0000075010093,"about_ca_topic_score_gemma":0.000016603724,"teacher_disagreement_score":0.9701042,"about_ca_system_score_codex":0.0000036104168,"about_ca_system_score_gemma":0.000010941221,"threshold_uncertainty_score":0.16124848},"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":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004590766,0.00009652649,0.031037742,0.00019006548,0.00018799602,0.00046615725,0.9660698,0.00044203247,0.0014637841],"genre_scores_gemma":[0.00016035308,0.00027316203,0.006351327,0.0001256716,0.000077543154,1.4461459e-7,0.99225324,0.00059222296,0.00016633376],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970335,0.00039878543,0.000501685,0.00090690743,0.0007286051,0.00043051448],"domain_scores_gemma":[0.9964614,0.000059186863,0.0003361794,0.0025166394,0.00041291033,0.00021368747],"candidate_categories":["metaepi_narrow","sts","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007394349,0.00025706447,0.00029267237,0.0004266483,0.0019083901,0.00083180715,0.0061694616,0.000103615304,0.056190405],"category_scores_gemma":[0.00044821796,0.0002901112,0.0000741145,0.0013483282,0.00014128028,0.000357614,0.007884379,0.00056678295,0.0026952806],"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":[0.000007678279,0.00022927507,5.762608e-8,0.00009265468,0.000049299917,0.000035544723,0.00010929586,0.00026845196,0.00012639622,0.0005530652,0.96813154,0.030396761],"study_design_scores_gemma":[0.0003164664,0.00018094666,0.00003514101,0.000035319947,0.000032094307,0.000104885665,0.000029232024,0.01272471,0.000022646926,0.00006749592,0.98617,0.00028104684],"about_ca_topic_score_codex":0.00013884704,"about_ca_topic_score_gemma":3.8792646e-7,"teacher_disagreement_score":0.053495124,"about_ca_system_score_codex":0.0001209528,"about_ca_system_score_gemma":0.000019370902,"threshold_uncertainty_score":0.9999551},"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":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004590766,0.00009652649,0.031037742,0.00019006548,0.00018799602,0.00046615725,0.9660698,0.00044203247,0.0014637841],"genre_scores_gemma":[0.00016035308,0.00027316203,0.006351327,0.0001256716,0.000077543154,1.4461459e-7,0.99225324,0.00059222296,0.00016633376],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970335,0.00039878543,0.000501685,0.00090690743,0.0007286051,0.00043051448],"domain_scores_gemma":[0.9964614,0.000059186863,0.0003361794,0.0025166394,0.00041291033,0.00021368747],"candidate_categories":["metaepi_narrow","sts","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007394349,0.00025706447,0.00029267237,0.0004266483,0.0019083901,0.00083180715,0.0061694616,0.000103615304,0.056190405],"category_scores_gemma":[0.00044821796,0.0002901112,0.0000741145,0.0013483282,0.00014128028,0.000357614,0.007884379,0.00056678295,0.0026952806],"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":[0.000007678279,0.00022927507,5.762608e-8,0.00009265468,0.000049299917,0.000035544723,0.00010929586,0.00026845196,0.00012639622,0.0005530652,0.96813154,0.030396761],"study_design_scores_gemma":[0.0003164664,0.00018094666,0.00003514101,0.000035319947,0.000032094307,0.000104885665,0.000029232024,0.01272471,0.000022646926,0.00006749592,0.98617,0.00028104684],"about_ca_topic_score_codex":0.00013884704,"about_ca_topic_score_gemma":3.8792646e-7,"teacher_disagreement_score":0.053495124,"about_ca_system_score_codex":0.0001209528,"about_ca_system_score_gemma":0.000019370902,"threshold_uncertainty_score":0.9999551},"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":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.7429504e-7,0.00005546958,0.012181388,0.0006397577,0.0002008096,0.00029253014,0.98368615,0.0005642995,0.0023787126],"genre_scores_gemma":[0.0000030617166,0.00016585566,0.0016926721,0.00039151477,0.00013373251,1.8127959e-7,0.99687636,0.0005160178,0.0002205926],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975504,0.0002963219,0.00029608174,0.0008610618,0.00058716926,0.00040890768],"domain_scores_gemma":[0.9969816,0.000035138033,0.00019396335,0.002407486,0.00018394203,0.0001978354],"candidate_categories":["sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.00074627757,0.00021697355,0.00019769813,0.00030934537,0.0033815664,0.0020186272,0.0075859735,0.00008768411,0.10642205],"category_scores_gemma":[0.00027184625,0.00024253533,0.000051567346,0.0008698059,0.00011186748,0.0004197909,0.010304171,0.00064966496,0.0143354405],"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":[0.0000024517697,0.000115617426,8.581847e-9,0.00003019686,0.000023194021,0.000023249388,0.0000432715,0.0000055031487,0.000008394402,0.0011893313,0.9440612,0.054497577],"study_design_scores_gemma":[0.00016096584,0.000121409685,0.000004542992,0.000009803152,0.000014641751,0.00015994889,0.000023395134,0.00036900848,0.0000035577027,0.00009978258,0.9987693,0.00026366033],"about_ca_topic_score_codex":0.00008944778,"about_ca_topic_score_gemma":5.287241e-7,"teacher_disagreement_score":0.092086606,"about_ca_system_score_codex":0.00014976144,"about_ca_system_score_gemma":0.000009729545,"threshold_uncertainty_score":0.99901736},"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":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.1671477e-9,0.000054228545,0.021664592,0.00014368688,0.00009583515,0.00015795582,0.97771454,0.00012132746,0.000047841648],"genre_scores_gemma":[9.4771264e-7,0.0000018059413,0.009881961,0.00039285037,0.00028736962,0.00015551671,0.98923266,0.000009993372,0.000036913454],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984997,0.00003173651,0.00020605524,0.0007607808,0.0002970334,0.00020471735],"domain_scores_gemma":[0.99444264,0.00019020635,0.0002243908,0.004982883,0.00007410135,0.00008580019],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00008170947,0.0001966744,0.00017727498,0.00007177285,0.00012641853,0.00046098005,0.00578877,0.00015287817,0.014800911],"category_scores_gemma":[0.0005172384,0.00019116043,0.000034976983,0.0002703106,0.000004780862,0.00043112086,0.0014278193,0.00022186477,0.0077809077],"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":[2.3921632e-7,0.000018646839,8.157823e-8,0.0000836164,0.000003880247,0.0000022981226,6.8092965e-7,0.000015979134,4.2482778e-8,0.000012236286,0.99030495,0.009557343],"study_design_scores_gemma":[0.00007024923,0.000008353637,0.000021587719,0.00049572065,0.0000056969757,8.823066e-7,1.4543039e-7,0.13881588,0.0000017124189,0.000017784472,0.86035925,0.00020272343],"about_ca_topic_score_codex":0.000028691078,"about_ca_topic_score_gemma":0.000040009323,"teacher_disagreement_score":0.13879989,"about_ca_system_score_codex":0.000027112523,"about_ca_system_score_gemma":0.00016715957,"threshold_uncertainty_score":0.9995904},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003479774,0.012039073,0.9831848,0.00047221844,0.0011648894,0.0001922685,0.000056350447,0.000094883384,0.002760698],"genre_scores_gemma":[0.0060940003,0.0011821509,0.99005216,0.0003918601,0.00072711986,0.000029499934,0.00009868113,0.00003544338,0.0013890817],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99667436,0.000028657254,0.0003669127,0.002087807,0.00037692316,0.00046532715],"domain_scores_gemma":[0.9970783,0.0005894914,0.00010096422,0.0020949293,0.000043193446,0.00009314406],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000932392,0.00032279172,0.00035073547,0.0006618408,0.00012784259,0.0014265502,0.005293091,0.00013839063,0.0000010452503],"category_scores_gemma":[0.00009069871,0.00028434087,0.000026082755,0.0014717354,0.00049227604,0.002913974,0.006366173,0.00056592777,0.000021784857],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.5085716e-7,0.00002044133,0.000030535946,0.00006994496,0.0000017549153,0.000030237337,0.00071100646,0.00039301676,0.000004572183,0.002610395,0.0003529917,0.9957746],"study_design_scores_gemma":[0.00010286882,0.00004045232,0.00009167772,0.0009153926,0.0000048792117,0.000043953412,6.702474e-7,0.9269667,0.00002515526,0.038729046,0.032674834,0.00040433643],"about_ca_topic_score_codex":0.000013189129,"about_ca_topic_score_gemma":0.00030981225,"teacher_disagreement_score":0.9953703,"about_ca_system_score_codex":0.00016679196,"about_ca_system_score_gemma":0.000985849,"threshold_uncertainty_score":0.9999609},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003479774,0.012039073,0.9831848,0.00047221844,0.0011648894,0.0001922685,0.000056350447,0.000094883384,0.002760698],"genre_scores_gemma":[0.0060940003,0.0011821509,0.99005216,0.0003918601,0.00072711986,0.000029499934,0.00009868113,0.00003544338,0.0013890817],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99667436,0.000028657254,0.0003669127,0.002087807,0.00037692316,0.00046532715],"domain_scores_gemma":[0.9970783,0.0005894914,0.00010096422,0.0020949293,0.000043193446,0.00009314406],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000932392,0.00032279172,0.00035073547,0.0006618408,0.00012784259,0.0014265502,0.005293091,0.00013839063,0.0000010452503],"category_scores_gemma":[0.00009069871,0.00028434087,0.000026082755,0.0014717354,0.00049227604,0.002913974,0.006366173,0.00056592777,0.000021784857],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.5085716e-7,0.00002044133,0.000030535946,0.00006994496,0.0000017549153,0.000030237337,0.00071100646,0.00039301676,0.000004572183,0.002610395,0.0003529917,0.9957746],"study_design_scores_gemma":[0.00010286882,0.00004045232,0.00009167772,0.0009153926,0.0000048792117,0.000043953412,6.702474e-7,0.9269667,0.00002515526,0.038729046,0.032674834,0.00040433643],"about_ca_topic_score_codex":0.000013189129,"about_ca_topic_score_gemma":0.00030981225,"teacher_disagreement_score":0.9953703,"about_ca_system_score_codex":0.00016679196,"about_ca_system_score_gemma":0.000985849,"threshold_uncertainty_score":0.9999609},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003479774,0.012039073,0.9831848,0.00047221844,0.0011648894,0.0001922685,0.000056350447,0.000094883384,0.002760698],"genre_scores_gemma":[0.0060940003,0.0011821509,0.99005216,0.0003918601,0.00072711986,0.000029499934,0.00009868113,0.00003544338,0.0013890817],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99667436,0.000028657254,0.0003669127,0.002087807,0.00037692316,0.00046532715],"domain_scores_gemma":[0.9970783,0.0005894914,0.00010096422,0.0020949293,0.000043193446,0.00009314406],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000932392,0.00032279172,0.00035073547,0.0006618408,0.00012784259,0.0014265502,0.005293091,0.00013839063,0.0000010452503],"category_scores_gemma":[0.00009069871,0.00028434087,0.000026082755,0.0014717354,0.00049227604,0.002913974,0.006366173,0.00056592777,0.000021784857],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.5085716e-7,0.00002044133,0.000030535946,0.00006994496,0.0000017549153,0.000030237337,0.00071100646,0.00039301676,0.000004572183,0.002610395,0.0003529917,0.9957746],"study_design_scores_gemma":[0.00010286882,0.00004045232,0.00009167772,0.0009153926,0.0000048792117,0.000043953412,6.702474e-7,0.9269667,0.00002515526,0.038729046,0.032674834,0.00040433643],"about_ca_topic_score_codex":0.000013189129,"about_ca_topic_score_gemma":0.00030981225,"teacher_disagreement_score":0.9953703,"about_ca_system_score_codex":0.00016679196,"about_ca_system_score_gemma":0.000985849,"threshold_uncertainty_score":0.9999609},"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007152531,0.0012044164,0.11305195,0.0008106838,0.00080236286,0.0010187951,0.00045812197,0.000521291,0.8820608],"genre_scores_gemma":[0.0006858036,0.00017240591,0.5286711,0.0002212835,0.00039091083,0.000041049472,0.0003387908,0.00013743773,0.46934125],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99691063,0.000018482475,0.0007472308,0.0011198669,0.0006986213,0.0005051828],"domain_scores_gemma":[0.99480754,0.00032412237,0.00020709133,0.004462023,0.00006240198,0.00013682053],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016708209,0.00037080576,0.00055169075,0.00084158586,0.00009918768,0.0005798381,0.008604236,0.00016855256,0.000021606753],"category_scores_gemma":[0.00016978772,0.00034486488,0.0000524492,0.000789106,0.00035679468,0.0007598708,0.0030204228,0.0008745639,0.0010072936],"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":[5.815752e-7,0.00023092954,0.00000641129,0.00056377496,0.000019861161,0.00012094126,0.0023691715,0.000045238405,0.00002486728,0.8814591,0.0919614,0.023197684],"study_design_scores_gemma":[0.00012097351,0.00001639495,0.000020823092,0.0014846614,0.000013762329,0.000035941175,0.00002895278,0.623589,0.000019320696,0.2690943,0.10514614,0.00042977757],"about_ca_topic_score_codex":0.000013739567,"about_ca_topic_score_gemma":0.00003912503,"teacher_disagreement_score":0.62354374,"about_ca_system_score_codex":0.00035597404,"about_ca_system_score_gemma":0.0015560149,"threshold_uncertainty_score":0.99990034},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26155666,0.00051127025,0.7208192,0.001077231,0.0007406721,0.00046548998,0.00038301837,0.00064918766,0.013797341],"genre_scores_gemma":[0.9596822,0.00025588926,0.021544566,0.00009175566,0.000058644375,0.0000031936174,0.00002639155,0.000021345673,0.018316012],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985624,0.000033999666,0.00017393022,0.0009117632,0.00008651274,0.00023141678],"domain_scores_gemma":[0.9982305,0.00005873258,0.0001623748,0.0013484602,0.00010015863,0.000099786244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016104894,0.00020688077,0.00026220735,0.0001958874,0.00009141352,0.00015090934,0.0016439881,0.00015021661,0.000045357916],"category_scores_gemma":[0.000014005349,0.00023125371,0.00015092635,0.0007441688,0.00011375784,0.00020813695,0.0036111893,0.00046679852,0.00018367123],"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":[0.000016263763,0.00018437348,0.000622638,0.0004489539,0.00025187232,0.00022879058,0.0021223235,0.030366365,0.000058544072,0.9405657,0.017334295,0.0077998573],"study_design_scores_gemma":[0.00021841997,0.00005940537,0.0002222225,0.0002936292,0.00010096042,0.0000071302593,0.00027044865,0.88812065,0.0004903366,0.07983765,0.029876156,0.000502975],"about_ca_topic_score_codex":0.0004018568,"about_ca_topic_score_gemma":0.000028750906,"teacher_disagreement_score":0.8607281,"about_ca_system_score_codex":0.000072073024,"about_ca_system_score_gemma":0.00029843644,"threshold_uncertainty_score":0.9430253},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007854935,0.0005356776,0.98850703,0.010066927,0.00012539962,0.000085306754,0.00035584025,0.000024777311,0.0002204644],"genre_scores_gemma":[0.17766838,0.00081709836,0.8184043,0.00021802375,0.0017265105,0.00006009279,0.0003478651,0.000012924936,0.00074477145],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902064,0.000006212543,0.0003576165,0.00027008064,0.00026044942,0.00008501324],"domain_scores_gemma":[0.9986365,0.0003629218,0.00014438861,0.0004609915,0.00026490111,0.00013032196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003430398,0.000075044576,0.00014182871,0.00039071214,0.00006224775,0.00058871444,0.0018369738,0.00002676905,0.000018457173],"category_scores_gemma":[0.00005888825,0.00006184692,0.00011799435,0.0006931644,0.000020929845,0.00062959443,0.00025101833,0.00008488965,0.000008358298],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014212541,0.000055888755,0.00017041157,0.0000039047554,0.0008006936,0.0000023399543,0.00009314378,0.000033265194,0.00038452033,0.046145156,0.012256098,0.94005316],"study_design_scores_gemma":[0.00024368081,0.000042070216,0.0014298175,0.000028969658,0.00061698834,0.000075652395,0.000043062424,0.49697793,0.00024308157,0.021035418,0.47912005,0.00014328906],"about_ca_topic_score_codex":0.0000364927,"about_ca_topic_score_gemma":0.00003669368,"teacher_disagreement_score":0.9399099,"about_ca_system_score_codex":0.000021913449,"about_ca_system_score_gemma":0.0001525939,"threshold_uncertainty_score":0.5676987},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27945656,0.000040379833,0.71900815,0.00039427096,0.00020959762,0.000046369198,0.000041320975,0.00009925406,0.0007040883],"genre_scores_gemma":[0.83626765,0.000023004239,0.16356033,0.00004328948,0.00007743758,2.0883456e-7,0.0000045905244,0.000005604673,0.000017899949],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916637,0.000003888047,0.000107469685,0.00023426676,0.0003206557,0.00016736383],"domain_scores_gemma":[0.9994746,0.000119190234,0.000045243396,0.00018330432,0.000055546832,0.00012211279],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036285326,0.00009159944,0.00011066159,0.00036547115,0.00019394758,0.00027204663,0.0005907226,0.000017100989,0.0000074283735],"category_scores_gemma":[0.000013568549,0.000086540436,0.000024104844,0.0006121502,0.000046376834,0.0011621157,0.00014845873,0.00013314305,0.0000059643285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010322923,0.00018700217,0.0004709539,0.00017177779,0.00017751353,0.0012200071,0.007101445,0.022507617,0.41551805,0.220915,0.0028640707,0.32876334],"study_design_scores_gemma":[0.00017444887,0.000047698853,0.0008613454,0.00021895515,0.00001598726,0.00002064641,0.0003128698,0.9821145,0.007092706,0.00004585641,0.00893551,0.00015945673],"about_ca_topic_score_codex":0.000007412224,"about_ca_topic_score_gemma":3.6051466e-7,"teacher_disagreement_score":0.9596069,"about_ca_system_score_codex":0.000065862674,"about_ca_system_score_gemma":0.00012728809,"threshold_uncertainty_score":0.35290164},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09568321,0.0017763777,0.8576155,0.024575606,0.000107450745,0.000275203,0.00008911987,0.00028322556,0.019594347],"genre_scores_gemma":[0.33690596,0.0016387963,0.6366792,0.0001958834,0.00003904206,0.00010696813,0.00017342674,0.00006345804,0.024197305],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9884083,0.009060407,0.0005403643,0.0008993208,0.000367767,0.00072378555],"domain_scores_gemma":[0.99259007,0.0047877408,0.00020100978,0.0012219223,0.00082369713,0.0003755439],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.01717077,0.0003606989,0.0003040083,0.00022487521,0.000573082,0.002012688,0.0016094717,0.0004106934,0.000052968324],"category_scores_gemma":[0.0017419534,0.00041765635,0.00019158471,0.0016268233,0.00033315687,0.0010245031,0.00075874466,0.0008763489,0.00007180772],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009094104,0.00094912446,0.0007813049,0.00036856928,0.00012836192,0.00004172068,0.09352762,0.00065562426,0.024479283,0.052998938,0.0023432618,0.8237171],"study_design_scores_gemma":[0.0006211854,0.0000019133336,0.0071908534,0.0019659447,0.00009013682,0.00022983174,0.0009861268,0.89401734,0.027129786,0.007860787,0.05943163,0.0004744792],"about_ca_topic_score_codex":0.013142361,"about_ca_topic_score_gemma":0.0066239736,"teacher_disagreement_score":0.8933617,"about_ca_system_score_codex":0.0005633262,"about_ca_system_score_gemma":0.0018196502,"threshold_uncertainty_score":0.9998275},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00089045195,0.00022003424,0.9879133,0.000061272665,0.00018525614,0.0003987719,0.010015681,0.0002711488,0.00004410155],"genre_scores_gemma":[0.014777164,0.0000032203632,0.96468246,0.0000887582,0.00006223482,0.00013466616,0.020220306,0.000014999089,0.000016166943],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855596,0.00003232523,0.00026533016,0.0007343965,0.00013695877,0.00027502104],"domain_scores_gemma":[0.99862397,0.00019133868,0.000045294164,0.0010594951,0.00002503616,0.000054850385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007871435,0.00011856347,0.00014027719,0.0002121605,0.00012392929,0.0005711666,0.0010154691,0.0000543499,0.0000030811714],"category_scores_gemma":[0.000042385378,0.00010834235,0.000024753142,0.0006820645,0.000016206262,0.0009815975,0.00035465654,0.0000842375,0.000010224697],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002330834,0.0010751187,0.00083751546,0.0026157263,0.00017364653,0.00011377002,0.00080583803,0.005248375,0.0005900469,0.011501055,0.15054946,0.82646614],"study_design_scores_gemma":[0.00021327163,0.000014815151,0.000019722356,0.00014478489,0.000012672188,0.000018260387,0.00007275364,0.99141574,0.000026255422,0.0001599177,0.0077429274,0.00015885185],"about_ca_topic_score_codex":0.00017511703,"about_ca_topic_score_gemma":0.000024428451,"teacher_disagreement_score":0.9861674,"about_ca_system_score_codex":0.000025930416,"about_ca_system_score_gemma":0.000098029515,"threshold_uncertainty_score":0.55077726},"labels":[],"label_agreement":null},{"id":"W4401314125","doi":"10.1007/s10115-024-02185-5","title":"An efficient approach for incremental erasable utility pattern mining from non-binary data","year":2024,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Research Foundation of Korea","keywords":"Computer science; Data mining; Binary number; Task (project management); Database; Mathematics","score_opus":0.04000251640079476,"score_gpt":0.2932303513575283,"score_spread":0.2532278349567335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401314125","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012903292,0.0005620196,0.981371,0.000025020605,0.00047252668,0.00042163074,0.00094181625,0.00014857393,0.003154115],"genre_scores_gemma":[0.96179014,0.000009941516,0.033789653,0.000035407807,0.00019461692,0.00014899675,0.0039813207,0.000005803885,0.00004408957],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990606,0.000023762186,0.00033621103,0.00030353502,0.00012400988,0.00015188803],"domain_scores_gemma":[0.9989662,0.00006838563,0.00006055477,0.0007577364,0.00006678774,0.00008029424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063383416,0.00010581624,0.00012384838,0.00008727199,0.00019357624,0.0009998335,0.0006926324,0.00004757532,0.0000024845067],"category_scores_gemma":[0.000008231741,0.000091734364,0.000017757402,0.00019816759,0.000016985747,0.0037009066,0.0003378471,0.000057409216,0.000052456326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000069700022,0.000261807,0.0006352159,0.001006762,0.00008180913,7.69647e-7,0.01899321,0.0006595673,0.00017417541,0.0052044503,0.06117845,0.9117968],"study_design_scores_gemma":[0.00015318673,0.00003204916,0.0004150676,0.00005873292,0.000007185976,0.000003854664,0.0007827266,0.92117625,0.000028289469,0.0000038815456,0.07723146,0.00010733682],"about_ca_topic_score_codex":0.00015635656,"about_ca_topic_score_gemma":0.000001921347,"teacher_disagreement_score":0.9488869,"about_ca_system_score_codex":0.000024177361,"about_ca_system_score_gemma":0.00006183321,"threshold_uncertainty_score":0.96414167},"labels":[],"label_agreement":null},{"id":"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000052569507,0.00009147624,0.9974197,0.0007785821,0.00011397898,0.00022851866,0.00081212725,0.00019347979,0.00030956516],"genre_scores_gemma":[0.011697369,0.000008046491,0.9874089,0.00011727031,0.00008977668,0.00013177031,0.0003587016,0.000009269385,0.00017889285],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99897015,0.000004256125,0.0002083834,0.0005368866,0.0001361758,0.000144143],"domain_scores_gemma":[0.9984883,0.00014918514,0.0000466293,0.0012167565,0.000057021894,0.000042129053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002969404,0.00008168168,0.00009463859,0.00006197236,0.000052079544,0.00014953865,0.0015529227,0.000031172003,0.0000022860131],"category_scores_gemma":[0.000013365911,0.00007258146,0.000025786292,0.0003596131,0.000029212053,0.0005949369,0.00047124302,0.00004293649,0.000011182479],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.53719e-8,0.000031268013,0.0000062093436,0.000023061993,0.000009977097,2.9840263e-7,0.000092844406,0.000005012141,0.0014000257,0.01803305,0.0020890164,0.97830915],"study_design_scores_gemma":[0.00008269289,0.000019068593,0.000026535172,0.000025008603,0.000007532039,0.000009486481,0.000023558854,0.96503335,0.0005102066,0.0003799002,0.033793762,0.00008892576],"about_ca_topic_score_codex":0.00011865196,"about_ca_topic_score_gemma":0.00000625075,"teacher_disagreement_score":0.9782202,"about_ca_system_score_codex":0.00001265931,"about_ca_system_score_gemma":0.0000673715,"threshold_uncertainty_score":0.2959786},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030239053,0.00006113418,0.9684256,0.00006179583,0.00008865533,0.0003708503,0.0005278506,0.00012751066,0.00009756101],"genre_scores_gemma":[0.29602894,0.000004693881,0.7029697,0.000019371128,0.00010987785,0.000056570392,0.00070511695,0.000014822421,0.000090939146],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848044,0.000026638223,0.00030685923,0.0006358485,0.00040402616,0.0001461981],"domain_scores_gemma":[0.99829364,0.0000378159,0.000105555846,0.0013669556,0.0000696737,0.00012638608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002689883,0.00012270824,0.00015971123,0.00013694342,0.00004197257,0.00014583467,0.0019232742,0.000038726026,0.0000034579964],"category_scores_gemma":[0.000010028422,0.000105959705,0.000017722632,0.00063176616,0.000026621614,0.0010457698,0.000618446,0.00006955035,0.00000803255],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010021305,0.00032329033,0.0020364511,0.00006412454,0.000115749506,0.0000012846994,0.0023205376,0.000031576943,0.0009822162,0.0007697726,0.0042061685,0.9891388],"study_design_scores_gemma":[0.00030425534,0.00043230518,0.012205706,0.00013658068,0.000054215554,0.000010655219,0.00048464732,0.97630864,0.0008085491,0.0000692528,0.009022609,0.0001625579],"about_ca_topic_score_codex":0.00022335649,"about_ca_topic_score_gemma":0.000010758255,"teacher_disagreement_score":0.98897624,"about_ca_system_score_codex":0.000027331595,"about_ca_system_score_gemma":0.00009141702,"threshold_uncertainty_score":0.43209112},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035322292,0.00021573358,0.99196935,0.00041939697,0.00008304824,0.00042998552,0.0024292842,0.00012841394,0.0007925575],"genre_scores_gemma":[0.04793612,0.00012570067,0.94152105,0.00007858591,0.000051989817,0.0002911832,0.0097572785,0.000012541047,0.0002255765],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981494,0.000024389288,0.0002766074,0.0012273453,0.00011731123,0.00020492777],"domain_scores_gemma":[0.99818504,0.000060683906,0.00007333336,0.001587679,0.000038807506,0.000054461758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000770784,0.00015595279,0.00028205093,0.00048089333,0.00006554925,0.0004739429,0.0012227257,0.00012358709,0.000005931309],"category_scores_gemma":[0.000013995409,0.0001406412,0.00007164071,0.0009325263,0.000023663686,0.00018378055,0.0044784495,0.00026021444,0.000010461959],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014792001,0.0015454384,0.003997877,0.0034906801,0.002990874,0.000022589498,0.0030292748,0.0015126836,0.0000933117,0.019702332,0.03806051,0.9255396],"study_design_scores_gemma":[0.00010442031,0.0000065336917,0.000942449,0.000036729776,0.00025439335,0.0000028147572,0.000049322392,0.976055,0.000009322671,0.021974886,0.00037238403,0.00019170373],"about_ca_topic_score_codex":0.00020506106,"about_ca_topic_score_gemma":0.0002755126,"teacher_disagreement_score":0.9745424,"about_ca_system_score_codex":0.000011926796,"about_ca_system_score_gemma":0.000041389932,"threshold_uncertainty_score":0.57351816},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035322292,0.00021573358,0.99196935,0.00041939697,0.00008304824,0.00042998552,0.0024292842,0.00012841394,0.0007925575],"genre_scores_gemma":[0.04793612,0.00012570067,0.94152105,0.00007858591,0.000051989817,0.0002911832,0.0097572785,0.000012541047,0.0002255765],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981494,0.000024389288,0.0002766074,0.0012273453,0.00011731123,0.00020492777],"domain_scores_gemma":[0.99818504,0.000060683906,0.00007333336,0.001587679,0.000038807506,0.000054461758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000770784,0.00015595279,0.00028205093,0.00048089333,0.00006554925,0.0004739429,0.0012227257,0.00012358709,0.000005931309],"category_scores_gemma":[0.000013995409,0.0001406412,0.00007164071,0.0009325263,0.000023663686,0.00018378055,0.0044784495,0.00026021444,0.000010461959],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014792001,0.0015454384,0.003997877,0.0034906801,0.002990874,0.000022589498,0.0030292748,0.0015126836,0.0000933117,0.019702332,0.03806051,0.9255396],"study_design_scores_gemma":[0.00010442031,0.0000065336917,0.000942449,0.000036729776,0.00025439335,0.0000028147572,0.000049322392,0.976055,0.000009322671,0.021974886,0.00037238403,0.00019170373],"about_ca_topic_score_codex":0.00020506106,"about_ca_topic_score_gemma":0.0002755126,"teacher_disagreement_score":0.9745424,"about_ca_system_score_codex":0.000011926796,"about_ca_system_score_gemma":0.000041389932,"threshold_uncertainty_score":0.57351816},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016969816,0.07128609,0.8946773,0.00011825564,0.0029495351,0.0014336435,0.00123698,0.00028575934,0.026315494],"genre_scores_gemma":[0.87911475,0.01818743,0.007830784,0.0001358143,0.0008532628,0.00033526396,0.00008975387,0.00008771316,0.093365245],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973173,0.000030202953,0.00090609014,0.00091495615,0.00054973667,0.00028170063],"domain_scores_gemma":[0.9980584,0.0004077228,0.0003063387,0.0008253896,0.00029665424,0.000105505045],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00071867125,0.0003862791,0.0010389702,0.00080770586,0.00026531104,0.0003377558,0.000535144,0.00019560213,0.000006965198],"category_scores_gemma":[0.000046669764,0.00031054113,0.00015933214,0.0005752044,0.00015934272,0.0002564229,0.00045207722,0.00036078438,0.000026691481],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047356196,0.0003086168,0.026135998,0.0023937628,0.06535262,0.00095124415,0.015454256,0.11370825,0.000020745929,0.3650081,0.023837462,0.3863554],"study_design_scores_gemma":[0.000495436,0.00007384395,0.00037722065,0.0011056017,0.0012456953,0.000023438728,0.00029652278,0.97848487,2.3139667e-7,0.002153707,0.0154418135,0.00030163815],"about_ca_topic_score_codex":0.000019814943,"about_ca_topic_score_gemma":0.000084631014,"teacher_disagreement_score":0.8868465,"about_ca_system_score_codex":0.00022993222,"about_ca_system_score_gemma":0.000082813385,"threshold_uncertainty_score":0.9999347},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019477276,0.0015095167,0.9948637,0.00030452665,0.00035702542,0.00031800964,0.0005052206,0.00016160477,0.000032673106],"genre_scores_gemma":[0.46517822,0.00008571172,0.52938527,0.0001248775,0.0014406289,0.00009291951,0.0036110112,0.000029554883,0.000051848012],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987315,0.000012811148,0.00019090754,0.0008296935,0.00009562796,0.00013943821],"domain_scores_gemma":[0.99820167,0.00004456126,0.000057357225,0.0015747737,0.00007385167,0.00004780921],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003405378,0.0001031935,0.00009246212,0.00009380088,0.00023942445,0.0013840826,0.0026047896,0.000042970893,6.889459e-7],"category_scores_gemma":[0.00001964889,0.00009364561,0.000008938414,0.0005402999,0.000036329882,0.0034343104,0.0009339004,0.00006631351,0.000002330334],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.460067e-7,0.000015933298,0.000011018641,0.00008677023,0.000006969845,3.530887e-7,0.00009029515,0.000075995704,0.005686735,0.00223983,0.008440872,0.98334455],"study_design_scores_gemma":[0.00008166218,0.0000036689682,0.000027319009,0.000029700928,0.00002453325,0.0000118528615,0.0000042151423,0.9633909,0.0013612692,0.0016539389,0.03329418,0.000116794996],"about_ca_topic_score_codex":0.000049011076,"about_ca_topic_score_gemma":0.00005043521,"teacher_disagreement_score":0.9832278,"about_ca_system_score_codex":0.000013295712,"about_ca_system_score_gemma":0.00012926442,"threshold_uncertainty_score":0.99965256},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008335113,0.000093938215,0.9819408,0.0024900238,0.00029416432,0.00023128834,0.000076814016,0.00048502773,0.006052817],"genre_scores_gemma":[0.65514606,0.00003882202,0.33919024,0.0004286761,0.00037921246,0.0002645176,0.000059869224,0.00002369262,0.004468903],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915916,0.0000095557025,0.00011085127,0.000338105,0.00016091431,0.00022140979],"domain_scores_gemma":[0.9994087,0.00009970824,0.000012668805,0.00036820967,0.00003627827,0.00007440456],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017533892,0.00008714107,0.00007459476,0.00008655828,0.00012445741,0.00031536212,0.0006114792,0.000035704998,0.00001635564],"category_scores_gemma":[0.000009347926,0.0000678787,0.000044950524,0.00036012987,0.000032526026,0.00028256146,0.00015108736,0.00011837317,0.00006495243],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003017998,0.000066738474,0.00036610296,0.00018124515,0.000041546653,0.0000051858087,0.0011255895,0.0003144397,0.00010311168,0.12754264,0.018860068,0.8513903],"study_design_scores_gemma":[0.00015149075,0.00015613768,0.0018684868,0.000081428036,0.000008051892,0.000022629814,0.00007543811,0.7235043,0.001632964,0.0011882753,0.271118,0.00019283414],"about_ca_topic_score_codex":0.000010570966,"about_ca_topic_score_gemma":0.000004640336,"teacher_disagreement_score":0.8511975,"about_ca_system_score_codex":0.000017842522,"about_ca_system_score_gemma":0.00007530918,"threshold_uncertainty_score":0.30410442},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027893994,0.000043632088,0.9689339,0.00024679324,0.00045365546,0.0009907141,0.0006379644,0.00040209974,0.00039728775],"genre_scores_gemma":[0.9063145,0.00004530641,0.09073227,0.000095682204,0.00018650576,0.000061325365,0.0009235094,0.00004209439,0.0015988258],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99778795,0.000054994445,0.00024904357,0.0014018691,0.00012807694,0.00037804258],"domain_scores_gemma":[0.99787056,0.0002646405,0.00019750618,0.0013841846,0.00013722236,0.00014590796],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002792247,0.00035042793,0.0002829907,0.00034096665,0.00023261075,0.0002549383,0.0014914948,0.00021900808,0.000012004994],"category_scores_gemma":[0.000041871856,0.00037870058,0.00022905924,0.00060641713,0.00006037512,0.00021960858,0.0019787245,0.00038445575,0.00013739477],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052559226,0.0009710685,0.00040632853,0.00045802997,0.00035363433,0.00024503848,0.000602027,0.15246314,0.00010949045,0.22566779,0.014200751,0.60447013],"study_design_scores_gemma":[0.00045360092,0.00013526011,0.00083159766,0.000105328305,0.0000610791,0.000001531083,0.00004205304,0.8713418,0.000121921774,0.123628385,0.0029177128,0.00035972567],"about_ca_topic_score_codex":0.00015696323,"about_ca_topic_score_gemma":0.00014067211,"teacher_disagreement_score":0.8784205,"about_ca_system_score_codex":0.00023800599,"about_ca_system_score_gemma":0.00015635541,"threshold_uncertainty_score":0.9998665},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000045223263,0.00028276068,0.9868124,0.002409713,0.0008879454,0.00020869417,0.000023841747,0.00031889754,0.009010502],"genre_scores_gemma":[0.004844094,0.000036078,0.988431,0.0007584773,0.00044902047,0.000024244046,0.000022574668,0.00004290805,0.005391608],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967129,0.000011492883,0.00034751606,0.0014156718,0.000981996,0.00053039903],"domain_scores_gemma":[0.99799985,0.00040068448,0.00024920693,0.001046069,0.00017852391,0.000125698],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007355409,0.00038952494,0.0003504151,0.0005615645,0.00024987874,0.0012437331,0.002370944,0.00023337442,0.000013390354],"category_scores_gemma":[0.000046241395,0.00032385217,0.000072772,0.00064839417,0.00025320327,0.00062747754,0.00087325677,0.0006306878,0.00015933898],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000157368,0.000022901706,0.00009552254,0.00004361393,0.00004359348,0.00007963998,0.0013375514,0.00621459,0.000032703672,0.056149043,0.00044823412,0.935531],"study_design_scores_gemma":[0.00012434162,0.00011752375,0.00009839527,0.0005685523,0.000023356259,0.000047545516,5.201257e-7,0.8962201,0.00014736276,0.087231226,0.014826395,0.0005946971],"about_ca_topic_score_codex":0.000022111526,"about_ca_topic_score_gemma":0.00005863442,"teacher_disagreement_score":0.93493634,"about_ca_system_score_codex":0.0004783514,"about_ca_system_score_gemma":0.00048732857,"threshold_uncertainty_score":0.9999214},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000032818672,0.00012856675,0.9926568,0.0022585362,0.0036648114,0.0005953381,0.000087172426,0.0002419701,0.0003339802],"genre_scores_gemma":[0.0039547356,0.00002404554,0.99182284,0.0007184006,0.00077476125,0.00017680503,0.00013019014,0.00005686834,0.0023413342],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99676526,0.000014955841,0.0005607751,0.0016788976,0.0004409101,0.0005391827],"domain_scores_gemma":[0.9980721,0.00034430818,0.00022195905,0.001026623,0.00017582573,0.00015917454],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00064958597,0.0004413475,0.00040535134,0.0006071491,0.00030097296,0.00074569543,0.0023500137,0.00026556166,0.000021209888],"category_scores_gemma":[0.00004280434,0.00043018063,0.00016571551,0.000389987,0.00014211444,0.000534474,0.0011554813,0.0005607112,0.000041991945],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014396801,0.000048627113,0.0000277575,0.000040916086,0.0000082502775,0.000016178512,0.00040155058,0.00026647,0.00007239283,0.0065007843,0.0002782311,0.9923374],"study_design_scores_gemma":[0.00029779752,0.00014772142,0.0000740978,0.0002927148,0.000035911733,0.00006075381,4.1005646e-7,0.93712485,0.00026322337,0.008888829,0.052103017,0.0007106737],"about_ca_topic_score_codex":0.000059107722,"about_ca_topic_score_gemma":0.00008621285,"teacher_disagreement_score":0.99162674,"about_ca_system_score_codex":0.0009423467,"about_ca_system_score_gemma":0.00026876436,"threshold_uncertainty_score":0.999815},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014679941,0.011218144,0.9808696,0.005535557,0.00056135975,0.00010001304,0.00005292817,0.000037390826,0.00015700255],"genre_scores_gemma":[0.9705067,0.004851556,0.020512754,0.00021169375,0.0022937872,0.000028003244,0.000046687917,0.000030721043,0.0015180733],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986928,0.000019704625,0.00018790369,0.00023003358,0.00015162285,0.00071790203],"domain_scores_gemma":[0.999002,0.00017652827,0.00006702277,0.0006745413,0.000049368256,0.000030551433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019205143,0.00007078709,0.000082160186,0.000053066975,0.00019067392,0.00028173177,0.0022428886,0.000022062632,9.095768e-7],"category_scores_gemma":[0.00005410437,0.000045923447,0.00004815557,0.0002691507,0.000025757443,0.0004366998,0.0002732494,0.00053028413,0.000009076947],"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":[6.903477e-7,0.0000068159516,0.0000027212716,0.0000029979312,0.00003193434,1.1764848e-7,0.00006679737,0.000014783776,0.000029743398,0.44692922,0.001042907,0.5518713],"study_design_scores_gemma":[0.00034970848,0.00025314707,0.00015913321,0.00014332453,0.00007120029,0.00060838053,0.00068224524,0.26531124,0.0002816743,0.4470985,0.2847973,0.00024416493],"about_ca_topic_score_codex":0.000030386944,"about_ca_topic_score_gemma":0.00017690136,"teacher_disagreement_score":0.9690387,"about_ca_system_score_codex":0.00007531832,"about_ca_system_score_gemma":0.0010561247,"threshold_uncertainty_score":0.41678822},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00880575,0.00004047636,0.9880055,0.0009084036,0.00017085385,0.00013558657,0.00003645413,0.00022171754,0.0016752661],"genre_scores_gemma":[0.5351066,0.000012861875,0.464191,0.00007793398,0.00010284123,0.00012350555,0.00012495165,0.000015438867,0.00024484584],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901146,0.000015401338,0.00018637207,0.0004961596,0.0001881035,0.00010250585],"domain_scores_gemma":[0.9987305,0.000016825923,0.00009990152,0.0010332925,0.00007056049,0.000048940597],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013731713,0.00012644815,0.00014251294,0.00009799908,0.000028502574,0.0002709869,0.0008460979,0.000065289976,0.000009322098],"category_scores_gemma":[0.0000020233635,0.00009740065,0.000026759139,0.00017110366,0.000022637358,0.00047936194,0.000847892,0.00016353441,0.000024727626],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.8920785e-7,0.000094636605,0.000066312365,0.00015294222,0.00004057612,0.0000073583283,0.004907243,0.000782912,0.00012709582,0.033625953,0.0010194656,0.95917463],"study_design_scores_gemma":[0.00008015287,0.00014675532,0.00018333294,0.0003169255,0.000023018561,0.0000048809134,0.00036820245,0.98223037,0.0019852729,0.013363247,0.00099147,0.00030639773],"about_ca_topic_score_codex":0.00012853877,"about_ca_topic_score_gemma":0.00003854713,"teacher_disagreement_score":0.98144746,"about_ca_system_score_codex":0.000011727256,"about_ca_system_score_gemma":0.00009841267,"threshold_uncertainty_score":0.3971883},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15269206,0.024216076,0.78443074,0.021442985,0.005901461,0.000581989,0.0001697058,0.0001199074,0.010445066],"genre_scores_gemma":[0.9677927,0.0009125513,0.003502867,0.000071585244,0.000085583306,0.000030505998,0.000008316922,0.000012043741,0.027583873],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99821377,0.000073351795,0.00060652196,0.00055634044,0.00020795313,0.0003420608],"domain_scores_gemma":[0.998377,0.00022932059,0.000095856776,0.0011532541,0.00008494426,0.00005958953],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006583134,0.00015720469,0.0002643493,0.00032378227,0.00011150864,0.00022724559,0.0012997292,0.0000874453,0.00023057708],"category_scores_gemma":[0.0000579299,0.00013357171,0.0002344608,0.0075402623,0.0002581278,0.00044044136,0.00035828634,0.0003123572,0.00036417853],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014678848,0.00017958,0.001751448,0.00021422301,0.00012323706,0.0000087322505,0.005343911,0.15504932,0.0003338356,0.101935305,0.00082741235,0.73423153],"study_design_scores_gemma":[0.0000067635738,0.000026035596,0.0032230816,0.00053937285,0.00015541796,0.000010393636,0.00023238723,0.9279806,0.0074028117,0.00042569998,0.059861626,0.00013578653],"about_ca_topic_score_codex":0.00029458542,"about_ca_topic_score_gemma":0.00009652923,"teacher_disagreement_score":0.8151006,"about_ca_system_score_codex":0.000073352385,"about_ca_system_score_gemma":0.00015518634,"threshold_uncertainty_score":0.54468966},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000022324986,0.000865479,0.9792589,0.00027956886,0.0003369246,0.0013572159,0.0004734841,0.0001846796,0.017221417],"genre_scores_gemma":[0.019903425,0.00017159239,0.963526,0.00010775986,0.0006272957,0.002143673,0.0011110306,0.00007456118,0.012334644],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974478,0.0000128337,0.0006757208,0.0012940655,0.00022418551,0.00034540272],"domain_scores_gemma":[0.99840736,0.000077095734,0.00017703553,0.0010651227,0.0001005178,0.00017285033],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004701868,0.00034830606,0.00039906133,0.0003380244,0.00030249485,0.00041229065,0.0010457954,0.0002715895,0.0000058863216],"category_scores_gemma":[0.000009644373,0.00036108991,0.000102600075,0.00026595552,0.00025239878,0.00017679318,0.00020114574,0.0003292369,0.00003046611],"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":[0.0000034946722,0.00009087395,0.0000059289105,0.00004664698,0.000014382924,7.770632e-7,0.00020770285,0.00046036442,0.0000047402796,0.6647981,0.0013277195,0.33303928],"study_design_scores_gemma":[0.000018218014,0.000044880886,0.000004732083,0.000046104735,0.00003112756,0.0000029470764,0.00024313509,0.5372704,0.00007776128,0.39221022,0.06969689,0.0003535449],"about_ca_topic_score_codex":0.00003661644,"about_ca_topic_score_gemma":0.000016789929,"teacher_disagreement_score":0.5368101,"about_ca_system_score_codex":0.00006970255,"about_ca_system_score_gemma":0.00009981636,"threshold_uncertainty_score":0.9998841},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039689243,0.00007087427,0.990357,0.001994957,0.00043808864,0.00029406266,0.000041557698,0.00049573317,0.002338816],"genre_scores_gemma":[0.6567472,0.0000066964863,0.34142834,0.001224066,0.00019429576,0.00021429271,0.000021762187,0.000017414683,0.00014594526],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99831545,0.000014222948,0.00028667494,0.00075277337,0.00029095312,0.00033992642],"domain_scores_gemma":[0.9986055,0.00022053206,0.000032284195,0.0009235947,0.000038356895,0.000179755],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00021348777,0.00019460272,0.00015483842,0.00015622881,0.00010181013,0.0005147844,0.0013579362,0.00008550093,0.00012625835],"category_scores_gemma":[0.00002555794,0.00018296747,0.000070037175,0.0009902924,0.000037763286,0.00014779062,0.00026907132,0.00024132199,0.0015003938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030227952,0.000044743232,0.000019849866,0.000022445334,0.000011989485,0.000015206266,0.0003954648,0.00020508334,0.0013573895,0.37365586,0.0014499296,0.622819],"study_design_scores_gemma":[0.00010997923,0.00023362073,0.00043096836,0.0004207635,0.00003634723,0.000016170776,0.00021640667,0.65343803,0.18642655,0.059472706,0.098072626,0.0011258436],"about_ca_topic_score_codex":0.00006707004,"about_ca_topic_score_gemma":0.0000145876365,"teacher_disagreement_score":0.65323293,"about_ca_system_score_codex":0.000042176423,"about_ca_system_score_gemma":0.0001003125,"threshold_uncertainty_score":0.99927706},"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.1438485e-8,0.00006334106,0.4239443,0.0016093724,0.000100479425,0.000068136134,0.000012277489,0.00014183893,0.57406026],"genre_scores_gemma":[0.000008534186,0.000092535825,0.12588882,0.00032518443,0.000050833245,0.000016276554,0.00007798795,0.000006280535,0.87353355],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99919105,0.0000026864093,0.00018334153,0.00040903958,0.00012234239,0.00009152213],"domain_scores_gemma":[0.99871767,0.00003464489,0.00007814783,0.0010603879,0.00007082188,0.00003835143],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00008061081,0.00012572345,0.00011823578,0.00009388102,0.00007303338,0.00012673576,0.0009035888,0.000103954524,0.000111557936],"category_scores_gemma":[0.0000067241376,0.00011703086,0.00004960466,0.00004716075,0.00002087064,0.00012346692,0.0002534308,0.00012359601,0.0008552232],"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":[5.8482012e-8,0.000002270636,4.17071e-8,0.000004235374,0.0000049559026,3.727816e-7,0.0000053098042,1.4801701e-7,0.0000026521177,0.64741284,0.08054764,0.2720195],"study_design_scores_gemma":[0.000021809321,0.0000051861234,0.0000048356023,0.000042031683,0.000007450576,0.0000015219432,4.2008074e-7,0.00790629,0.00004229501,0.068532005,0.923306,0.00013014645],"about_ca_topic_score_codex":0.000010562803,"about_ca_topic_score_gemma":0.000002763183,"teacher_disagreement_score":0.84275836,"about_ca_system_score_codex":0.000027829752,"about_ca_system_score_gemma":0.00008183874,"threshold_uncertainty_score":0.99992275},"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.6849069e-8,0.00013125253,0.0010860531,0.00052752206,0.0000060907696,0.00028250157,0.00022390386,0.0003840217,0.9973586],"genre_scores_gemma":[5.4594825e-8,0.0000010385459,0.014740627,0.00010278137,0.000303519,0.000046067627,0.00016258018,0.00005730994,0.984586],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980997,0.000010823772,0.00034397363,0.00081470556,0.00037721934,0.00035357126],"domain_scores_gemma":[0.99782526,0.00007236839,0.00012561744,0.0016317684,0.00008401253,0.00026095734],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00014822751,0.00037978624,0.0003595496,0.00020114955,0.00015677647,0.00028691744,0.0019750674,0.00022200226,0.9667105],"category_scores_gemma":[0.000010983823,0.00039397363,0.00013291053,0.00012065844,0.00005599829,0.00023446925,0.0005156451,0.0003194014,0.9959057],"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":[0.0000018526421,0.000012731369,4.4288412e-10,0.000003201326,0.000017903078,0.000007566544,0.000007899131,0.0000044026524,9.3524915e-7,0.0020435806,0.28013366,0.7177662],"study_design_scores_gemma":[0.000088133114,0.00008602833,4.976039e-7,0.000072095296,0.000022660039,0.000021506974,7.4072844e-8,0.0015424658,0.0000057944553,0.0014182833,0.99626917,0.0004733138],"about_ca_topic_score_codex":0.000016437893,"about_ca_topic_score_gemma":1.9537197e-7,"teacher_disagreement_score":0.7172929,"about_ca_system_score_codex":0.0000590996,"about_ca_system_score_gemma":0.000109230125,"threshold_uncertainty_score":0.9998512},"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.709807e-8,0.0001131651,0.0010406952,0.0005077452,0.0000063073135,0.00030636936,0.0002648753,0.00039160295,0.9973692],"genre_scores_gemma":[5.5611626e-8,8.709664e-7,0.014413213,0.000095074116,0.00030022673,0.000049740735,0.00019497647,0.00005727408,0.98488855],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980875,0.000010788237,0.00034580097,0.0008199507,0.00037469028,0.00036127036],"domain_scores_gemma":[0.9978238,0.00006512625,0.00012619543,0.0016420075,0.00008246791,0.00026045542],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00014701947,0.0003832688,0.00036078523,0.00020440941,0.00015813683,0.00028353214,0.002001119,0.0002235119,0.97117746],"category_scores_gemma":[0.000009523179,0.00039705503,0.00013531344,0.00011652131,0.000057140995,0.00022580825,0.00052353524,0.0003220834,0.99679023],"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":[0.0000020559587,0.000013561493,3.2896033e-10,0.000003203676,0.000018544815,0.000007926898,0.0000075457,0.000004428156,0.0000010437476,0.0020200443,0.27972162,0.7182],"study_design_scores_gemma":[0.000096724194,0.000089650945,4.2547467e-7,0.00006582602,0.000022757378,0.00002421967,7.2970614e-8,0.0015464856,0.00000556297,0.0010927082,0.99657875,0.00047682604],"about_ca_topic_score_codex":0.000013630103,"about_ca_topic_score_gemma":1.7725174e-7,"teacher_disagreement_score":0.7177232,"about_ca_system_score_codex":0.00005729326,"about_ca_system_score_gemma":0.000104541185,"threshold_uncertainty_score":0.9998481},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005470247,0.00020927681,0.9931527,0.00031389607,0.0006052546,0.00008322959,0.00003351272,0.00010522977,0.000026679796],"genre_scores_gemma":[0.22335362,0.00028280818,0.7755557,0.00010428185,0.0003002325,0.0000041986004,0.0003392473,0.000016632417,0.000043280274],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891275,0.000114236966,0.0003320838,0.00031247124,0.00020061151,0.00012785147],"domain_scores_gemma":[0.9988231,0.00048074938,0.00020682046,0.00024910807,0.00016923982,0.00007099898],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012952561,0.00016092636,0.00018473197,0.00032229035,0.00012003787,0.000378611,0.0007574523,0.00006951427,0.0000018438174],"category_scores_gemma":[0.00012124418,0.0001449806,0.000026498716,0.00020971434,0.000016506094,0.0013334645,0.00038124228,0.00051668915,3.887862e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006171289,0.0001121482,0.00009954975,0.0000148925565,0.00010017641,0.000011907544,0.00022463386,0.007670991,0.00079557806,0.00470537,0.00018485253,0.9860182],"study_design_scores_gemma":[0.0004663738,0.00014856172,0.0004079713,0.00025551036,0.0000121814255,0.00024381654,0.000046518773,0.9711709,0.001326637,0.00026624656,0.02551764,0.00013764785],"about_ca_topic_score_codex":0.000009060913,"about_ca_topic_score_gemma":7.482721e-7,"teacher_disagreement_score":0.98588055,"about_ca_system_score_codex":0.000063974825,"about_ca_system_score_gemma":0.0000306671,"threshold_uncertainty_score":0.59121376},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00037981177,0.0012155718,0.9848554,0.0036712,0.00057600613,0.00016281608,0.000041989664,0.00013259916,0.008964585],"genre_scores_gemma":[0.09475415,0.023755984,0.8251752,0.0037769205,0.0039304043,0.000489033,0.0010431046,0.00010097896,0.04697418],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971949,0.000041000294,0.0004828132,0.00035528615,0.000408077,0.0015179248],"domain_scores_gemma":[0.99851334,0.00005109126,0.0003570194,0.00076350116,0.00022060469,0.00009442406],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0014556869,0.00023940294,0.00023586025,0.00024989664,0.0003127083,0.00060785044,0.0027742467,0.00018363092,0.000009176841],"category_scores_gemma":[0.000050932656,0.00022850011,0.00016561929,0.00031574984,0.00003005054,0.00053996366,0.0013296462,0.003994519,0.00004820591],"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":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016112367,0.00004197939,0.000013044078,0.00001775641,0.00012381305,0.0000014201114,0.00013555889,0.0017731606,0.000002374574,0.8086033,0.0016902772,0.18759571],"study_design_scores_gemma":[0.00032552012,0.00006209744,0.00021914614,0.00013816026,0.00003514004,0.00041917188,0.00016506376,0.12789832,0.0000223643,0.8319771,0.038307417,0.0004304868],"about_ca_topic_score_codex":0.000045827983,"about_ca_topic_score_gemma":0.00009096908,"teacher_disagreement_score":0.18716523,"about_ca_system_score_codex":0.0008363918,"about_ca_system_score_gemma":0.009220334,"threshold_uncertainty_score":0.9983033},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.1358647e-7,0.002164698,0.014319843,0.00046021567,0.0004957687,0.00034750797,0.00028259205,0.00027255653,0.9816565],"genre_scores_gemma":[0.000017153718,0.00020321055,0.04212879,0.0009093996,0.00021227996,0.000073965806,0.00010882587,0.000024609837,0.9563218],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981234,0.000015879052,0.00044009968,0.00078626355,0.00032437203,0.00030997742],"domain_scores_gemma":[0.99785537,0.000115443465,0.00023788764,0.0015244663,0.0001443681,0.0001224698],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00019420672,0.0003819699,0.0004556262,0.00015074539,0.00020811612,0.0002474265,0.0018611263,0.00025023063,0.000050691855],"category_scores_gemma":[0.000018356546,0.00037219492,0.00016076,0.00004992277,0.00015424294,0.00014487449,0.0007680788,0.00045034182,0.000290598],"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":[3.49178e-7,0.0000035687572,5.53853e-7,0.00001942262,0.00002768034,0.0000069861762,0.000046013956,1.3849188e-7,0.0000012853652,0.31565082,0.005470312,0.67877287],"study_design_scores_gemma":[0.00013439351,0.000023072964,0.0000044446524,0.000364787,0.000027394839,0.000007119779,0.000001879458,0.00035737423,0.000032149615,0.026663434,0.97201353,0.0003703917],"about_ca_topic_score_codex":8.0684714e-7,"about_ca_topic_score_gemma":0.00001030395,"teacher_disagreement_score":0.96654326,"about_ca_system_score_codex":0.00008480351,"about_ca_system_score_gemma":0.00033788846,"threshold_uncertainty_score":0.999873},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.1310939e-7,0.0005310673,0.016825102,0.00022351704,0.0005092097,0.0003199773,0.00004750787,0.0002252545,0.9813182],"genre_scores_gemma":[0.000013458322,0.00007619626,0.028359039,0.00020105172,0.00022378634,0.00007097665,0.00006514525,0.000021621245,0.9709687],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99852085,0.000016963295,0.00035176176,0.0007065363,0.00020384812,0.00020004164],"domain_scores_gemma":[0.9980242,0.00009478355,0.00017026204,0.0014890181,0.00013348131,0.000088254565],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001610996,0.0002717492,0.00030495043,0.00022091236,0.00015393428,0.00019577527,0.001215123,0.00018640922,0.000024419078],"category_scores_gemma":[0.000016893819,0.0002731464,0.00015236597,0.00004635923,0.00006126068,0.000110689645,0.00066007435,0.00029785695,0.00060007395],"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":[3.2359864e-7,0.000005519791,2.5926352e-7,0.000017267754,0.000023999733,0.0000036350539,0.00013588341,1.3307276e-7,0.0000011458387,0.19680862,0.0060017784,0.7970014],"study_design_scores_gemma":[0.00009361904,0.000014040966,0.000007477129,0.00019382272,0.000030125993,0.0000054630473,0.0000018987079,0.0013717976,0.000026067422,0.023403639,0.97459966,0.00025239863],"about_ca_topic_score_codex":8.8817734e-7,"about_ca_topic_score_gemma":0.00000769659,"teacher_disagreement_score":0.9685979,"about_ca_system_score_codex":0.00006032817,"about_ca_system_score_gemma":0.00020699685,"threshold_uncertainty_score":0.99997205},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011981381,0.000016210824,0.9638239,0.022102281,0.00018264193,0.0010178026,0.0020103983,0.000083216466,0.010643718],"genre_scores_gemma":[0.0029445016,0.0000035203007,0.9870243,0.0020408225,0.00020834836,0.0007173524,0.0017391344,0.000013715751,0.0053083],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988907,0.00001574895,0.00014653639,0.00073327136,0.000083088235,0.00013068333],"domain_scores_gemma":[0.99426734,0.00022597905,0.00008234058,0.0053530117,0.000040120674,0.000031190655],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00047082585,0.00011682719,0.00011064137,0.000020586855,0.0002112207,0.0012817886,0.011996779,0.000057030913,0.000011351611],"category_scores_gemma":[0.000034202232,0.000070883754,0.000026270247,0.000078315956,0.000025761017,0.00019561246,0.021271762,0.00016844284,0.000030172805],"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":[3.809629e-7,0.00004315758,8.696487e-7,0.0000063202037,0.000009772657,0.000022692147,0.000030321717,0.000056756675,2.660839e-7,0.1873007,0.6552104,0.15731841],"study_design_scores_gemma":[0.00006974711,0.000011192124,0.000024591694,0.000018504805,0.000008190255,0.00005527929,0.000023076567,0.79672015,0.000024152532,0.011902628,0.19099757,0.00014489732],"about_ca_topic_score_codex":0.0023726695,"about_ca_topic_score_gemma":0.00016137831,"teacher_disagreement_score":0.7966634,"about_ca_system_score_codex":0.000012782281,"about_ca_system_score_gemma":0.00010168988,"threshold_uncertainty_score":0.99975497},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013556248,0.000092775124,0.9823748,0.0005423566,0.00287402,0.00022179328,0.000012958767,0.000055058863,0.00026998512],"genre_scores_gemma":[0.37810206,0.000009075585,0.6215344,0.00010882653,0.00021351369,0.000003361204,0.0000133792255,0.000011580439,0.0000037540572],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997521,0.000119533775,0.0011409669,0.00038971493,0.0005504886,0.0002782893],"domain_scores_gemma":[0.9967774,0.0010671946,0.0009818318,0.00038775557,0.00060690334,0.00017888608],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015236994,0.00028943352,0.0007404112,0.0006515866,0.000472021,0.00065397355,0.0006499735,0.00012865032,0.0000027798528],"category_scores_gemma":[0.00025210177,0.00027275467,0.00017262911,0.0013090785,0.00012006162,0.00029626073,0.00032033853,0.0003343914,4.2707404e-7],"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":[0.000026463145,0.0008112104,0.0002433194,0.000107314314,0.00050312007,0.000010244933,0.0005836129,0.036363944,0.00003088849,0.93572134,0.00022745797,0.025371062],"study_design_scores_gemma":[0.0021268777,0.00028870304,0.00025025566,0.00014882526,0.00020769771,0.000010093706,0.00007791646,0.8661748,0.00003789782,0.13031486,0.00015497759,0.00020710178],"about_ca_topic_score_codex":0.000014821023,"about_ca_topic_score_gemma":3.5278313e-7,"teacher_disagreement_score":0.82981086,"about_ca_system_score_codex":0.0000998851,"about_ca_system_score_gemma":0.00021364866,"threshold_uncertainty_score":0.99997246},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004057749,0.0004323044,0.9862484,0.00036118634,0.007190617,0.0003357668,0.000018770967,0.000032635067,0.0013226202],"genre_scores_gemma":[0.077444114,0.00006298514,0.92168343,0.000017860253,0.0007091742,0.00000638625,0.0000132690775,0.000022537677,0.000040270683],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974963,0.00027850247,0.001101276,0.00038223658,0.0004427755,0.0002989107],"domain_scores_gemma":[0.99277663,0.0048318147,0.0007473321,0.0008859205,0.0006558041,0.000102472986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0053298366,0.00019526308,0.0006195361,0.000527234,0.00036685402,0.00055562094,0.002248462,0.00013273775,9.296418e-7],"category_scores_gemma":[0.0009273173,0.00017307012,0.00010263694,0.0011224893,0.000110087516,0.0010744928,0.0016000726,0.00037812456,3.1069573e-7],"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":[0.000033268298,0.00065003755,0.000008654005,0.00020617679,0.00008629026,0.0000013692643,0.00047477934,0.000300897,0.00007258478,0.939047,0.0024697576,0.0566492],"study_design_scores_gemma":[0.002000856,0.0006110988,0.000014982405,0.0007677387,0.000049366063,0.000008433777,0.00036731895,0.7011122,0.0015137335,0.2903542,0.0030342047,0.00016586961],"about_ca_topic_score_codex":0.0000025497536,"about_ca_topic_score_gemma":4.4701117e-8,"teacher_disagreement_score":0.7008113,"about_ca_system_score_codex":0.000041803665,"about_ca_system_score_gemma":0.00045676334,"threshold_uncertainty_score":0.70575947},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45759144,0.0001583053,0.5338646,0.00039300157,0.0055793696,0.00035056876,0.000003888429,0.00004252942,0.0020162773],"genre_scores_gemma":[0.9640543,0.000025128758,0.035574734,0.000046156827,0.00027665094,0.000005701621,7.384933e-7,0.000012888429,0.0000037311877],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971111,0.0001633343,0.0011092586,0.000325915,0.0008756955,0.00041471017],"domain_scores_gemma":[0.9936903,0.004456478,0.0006077936,0.00053847744,0.000568813,0.00013812006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052857096,0.00023627406,0.0006236853,0.00080140925,0.0004353854,0.00074213877,0.0013100287,0.0001651586,0.0000013677588],"category_scores_gemma":[0.0006651978,0.00019496179,0.00012236029,0.0012608757,0.00010325178,0.00042580083,0.0002879223,0.0010830547,0.000003612986],"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":[0.000092180715,0.00067309005,0.0002103826,0.00004182265,0.000030447385,0.000013658354,0.0002752915,0.0007461442,0.000030738225,0.9643822,0.00031669863,0.03318735],"study_design_scores_gemma":[0.006312682,0.000682388,0.0010767771,0.0006838412,0.000018390852,0.000005901737,0.00044408572,0.21906325,0.00014864364,0.770928,0.00046871474,0.00016729654],"about_ca_topic_score_codex":0.000029340752,"about_ca_topic_score_gemma":0.0000025347636,"teacher_disagreement_score":0.5064628,"about_ca_system_score_codex":0.00014641065,"about_ca_system_score_gemma":0.0004490175,"threshold_uncertainty_score":0.7950311},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07295608,0.0005511621,0.92541414,0.00012633987,0.00024375199,0.00031833662,0.0001463196,0.00022344942,0.000020392024],"genre_scores_gemma":[0.78769505,0.00004606652,0.21187747,0.000023027736,0.000035547746,0.0000624635,0.00023736159,0.000014345434,0.000008682558],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998498,0.000037965678,0.0003750545,0.00070692843,0.000086226224,0.000295782],"domain_scores_gemma":[0.99878824,0.00018205169,0.000053608073,0.00088786054,0.000028951932,0.000059290425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007152041,0.00016479942,0.00027388017,0.00014582415,0.00014282958,0.00045630167,0.0009826123,0.00005540836,0.000002454028],"category_scores_gemma":[0.0000885028,0.00016765301,0.000022371361,0.00027419318,0.000017693932,0.0005961003,0.0016008755,0.00007452037,0.0000012899162],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053098243,0.0010712765,0.000004947848,0.0040300363,0.0008237108,0.00008988944,0.0015004718,0.16872308,0.15906382,0.1882626,0.00015159443,0.4762255],"study_design_scores_gemma":[0.0002887369,0.000009758949,0.00001612802,0.00023580101,0.00005411338,0.000034437748,0.0000047259196,0.993388,0.002359288,0.0024064346,0.0010251051,0.00017745142],"about_ca_topic_score_codex":0.000034111767,"about_ca_topic_score_gemma":0.000013509874,"teacher_disagreement_score":0.82466495,"about_ca_system_score_codex":0.000014110849,"about_ca_system_score_gemma":0.000023236124,"threshold_uncertainty_score":0.68366915},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0954111,0.0018864017,0.89665085,0.00011034334,0.0035864785,0.0004663841,0.0011773834,0.00070593716,0.0000051149777],"genre_scores_gemma":[0.8018661,0.000114018796,0.19649985,0.00024935816,0.0009068238,0.00027602536,0.000017295746,0.00006486103,0.0000056226195],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99689806,0.00012792283,0.0005949523,0.0015079087,0.0003280599,0.0005430809],"domain_scores_gemma":[0.99693495,0.00016977321,0.0004807585,0.0017465359,0.00044603867,0.0002219237],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00041289502,0.00053588534,0.00044703882,0.00045320866,0.00046222616,0.00078748335,0.0014386933,0.00042303005,0.0000068022932],"category_scores_gemma":[0.00006433879,0.0006019399,0.00018998595,0.0012337159,0.00008927627,0.00051964563,0.0014493155,0.0008575533,0.0000111483905],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001907239,0.0034311316,0.022790499,0.0020299938,0.0031097934,0.00033554647,0.00042849904,0.16612412,0.5088599,0.27139506,0.016460698,0.004844099],"study_design_scores_gemma":[0.0002792288,0.0000150564565,0.018621223,0.00022236425,0.00009002021,2.3797966e-8,0.0000017049001,0.97613984,0.0032833605,0.000044259858,0.00066295743,0.0006399767],"about_ca_topic_score_codex":0.00043400424,"about_ca_topic_score_gemma":0.000008886355,"teacher_disagreement_score":0.81001574,"about_ca_system_score_codex":0.00018294639,"about_ca_system_score_gemma":0.00058537093,"threshold_uncertainty_score":0.9996432},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00053793757,0.00070560264,0.9974191,0.00021721935,0.00044964816,0.00022220604,0.000058174057,0.00038501242,0.000005062931],"genre_scores_gemma":[0.00926976,0.00010134062,0.9900645,0.000069552036,0.00002407257,0.0003007437,0.000013911707,0.000011004928,0.00014513773],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909186,0.000039671195,0.00018667697,0.00037878248,0.000063103485,0.00023989078],"domain_scores_gemma":[0.9981087,0.0011940778,0.000028855007,0.0005637927,0.00004043142,0.00006413417],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005100722,0.00013432953,0.0001804355,0.00018322325,0.00011950767,0.000066211265,0.00048652253,0.00006849325,0.0000032395324],"category_scores_gemma":[0.00031245057,0.00013314959,0.00005908346,0.00029440687,0.000026621456,0.00014394519,0.000029334355,0.00019462554,0.0000022493762],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034175293,0.000036148856,0.0000022826002,0.000057395635,0.000022514336,0.000001067877,0.0012493926,0.0075777103,0.00008792853,0.00846764,0.00003799461,0.9824565],"study_design_scores_gemma":[0.0012852753,0.00061827723,0.00019430641,0.00045481342,0.00026362998,0.00012885951,0.0020457844,0.7949997,0.02517046,0.015374108,0.15803431,0.001430444],"about_ca_topic_score_codex":0.000014633285,"about_ca_topic_score_gemma":0.000003901292,"teacher_disagreement_score":0.98102605,"about_ca_system_score_codex":0.000020880314,"about_ca_system_score_gemma":0.00004066585,"threshold_uncertainty_score":0.5429683},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000032686635,0.00079257204,0.9075438,0.0025423719,0.00015770941,0.0002247501,0.00018890503,0.0001653281,0.08838133],"genre_scores_gemma":[0.07622865,0.0013530611,0.69175506,0.014069754,0.0006282233,0.0004861002,0.00044892708,0.00015565788,0.21487457],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980431,0.000029622353,0.00038664456,0.00088528846,0.00041911445,0.00023620496],"domain_scores_gemma":[0.99702144,0.0018968667,0.0001989483,0.00059173914,0.00017872163,0.00011229012],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00016188913,0.00040513373,0.0003617706,0.00029861298,0.00023480182,0.00034113388,0.0010086542,0.00020566079,0.000110559406],"category_scores_gemma":[0.000112359136,0.000367437,0.00014652697,0.000118396194,0.00018371185,0.00009917503,0.00018152766,0.0003470246,0.00010023927],"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":[0.000003853559,0.000015982945,4.7305423e-7,0.0000233664,0.000033251155,0.0000056459526,0.000022406826,0.007288778,0.0000014432543,0.49771458,0.002062813,0.49282742],"study_design_scores_gemma":[0.0000427478,0.000106151,0.000026367272,0.00072706427,0.000045261975,0.000015347105,0.000005255411,0.43680167,0.0007209686,0.42323348,0.13765194,0.00062375556],"about_ca_topic_score_codex":0.000015494019,"about_ca_topic_score_gemma":0.0000049367413,"teacher_disagreement_score":0.49220365,"about_ca_system_score_codex":0.000076305994,"about_ca_system_score_gemma":0.00034049485,"threshold_uncertainty_score":0.99987775},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3004274,0.0003117663,0.697271,0.0011514894,0.00021267367,0.0001663239,0.000060423252,0.000013248162,0.0003857183],"genre_scores_gemma":[0.9510218,0.0004987806,0.04832451,0.00008463812,0.000042612763,0.0000071645636,0.000006930003,0.0000020405232,0.000011513315],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99917775,0.000018406563,0.000285583,0.00016400631,0.00022241323,0.00013186024],"domain_scores_gemma":[0.998798,0.000106004816,0.00033122543,0.00014033861,0.0005558251,0.000068606336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001057294,0.00006842636,0.0001477508,0.00023823723,0.0002478541,0.00016665042,0.0003013401,0.000027398979,5.43827e-7],"category_scores_gemma":[0.00006608377,0.00005017681,0.000022097278,0.0006433458,0.00012919486,0.0014159901,0.00006397532,0.000105358224,1.7478122e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039697427,0.0005423057,0.00091304455,0.00019143466,0.000036215457,0.00028157025,0.0007382864,0.0007101405,0.0034217832,0.036329914,0.0054664905,0.95097184],"study_design_scores_gemma":[0.00292233,0.00038912083,0.0005961885,0.00062660646,0.00003865168,0.0032732035,0.00063167675,0.9756044,0.006679384,0.008096106,0.0009938378,0.00014849158],"about_ca_topic_score_codex":0.00022847418,"about_ca_topic_score_gemma":0.000051391966,"teacher_disagreement_score":0.9748943,"about_ca_system_score_codex":0.00003653018,"about_ca_system_score_gemma":0.00020476374,"threshold_uncertainty_score":0.2046151},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000035738696,0.003214963,0.98484147,0.010261913,0.0006875667,0.00031182053,0.0002982832,0.00007572693,0.00027252815],"genre_scores_gemma":[0.0041289204,0.0098294085,0.9719799,0.002499563,0.002436428,0.00025895805,0.0013245881,0.000042389103,0.007499854],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99704725,0.000058280722,0.00036020463,0.0007782248,0.00021746261,0.0015385975],"domain_scores_gemma":[0.99757326,0.00008916198,0.00026622365,0.0017951984,0.00020503202,0.00007113175],"candidate_categories":["open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0020464668,0.00022604574,0.00026344377,0.00016175893,0.00043680632,0.0006858223,0.0055103214,0.00013981057,0.0000018994218],"category_scores_gemma":[0.000088210014,0.00021410297,0.00010953241,0.00020534993,0.000028652168,0.00046833832,0.0031680255,0.0028592388,0.0000066776956],"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":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025355268,0.00003871714,0.000005437807,0.000017190212,0.00021800591,6.271542e-7,0.000085631415,0.00017788378,0.000014400267,0.60519886,0.009052904,0.3851878],"study_design_scores_gemma":[0.00021724233,0.00004742179,0.00000430359,0.000077565994,0.000040330462,0.0000486482,0.000053893677,0.39365414,0.000039596944,0.5696675,0.035929505,0.0002198571],"about_ca_topic_score_codex":0.000056801728,"about_ca_topic_score_gemma":0.00017314445,"teacher_disagreement_score":0.39347625,"about_ca_system_score_codex":0.0004891773,"about_ca_system_score_gemma":0.008868091,"threshold_uncertainty_score":0.99987036},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008241449,0.000046265424,0.9900966,0.006374823,0.00013421546,0.00017453649,0.0000022715014,0.00005777872,0.0022893115],"genre_scores_gemma":[0.092322566,0.00028565206,0.8794255,0.021985289,0.00018307801,0.00022683723,0.00005051438,0.000008686542,0.005511832],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99961567,0.000007547092,0.00012002968,0.00009581698,0.00006949676,0.00009146932],"domain_scores_gemma":[0.9994467,0.00022810473,0.00003179786,0.00023599029,0.000044182052,0.000013210838],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030890421,0.000042128657,0.000036401016,0.00003147949,0.00044804288,0.0005866241,0.00024181008,0.000017439148,4.0087937e-7],"category_scores_gemma":[0.0000885526,0.000027582044,0.000013223798,0.00019712231,0.000012030374,0.0003359801,0.00010360052,0.000045465662,0.0000032660168],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016840373,0.0000028635889,0.0000036057531,0.0000030874999,0.0000036015717,1.5842632e-8,0.000110273104,0.0000768932,0.000027215985,0.27113038,0.011953756,0.7166866],"study_design_scores_gemma":[0.00013224159,0.000009848623,0.000102254766,0.000018484534,0.0000020754117,3.2831602e-7,0.00006367686,0.79343206,0.00039693632,0.0013274061,0.20447434,0.000040319326],"about_ca_topic_score_codex":0.0000041303256,"about_ca_topic_score_gemma":0.0000029419357,"teacher_disagreement_score":0.79335517,"about_ca_system_score_codex":0.0000118967455,"about_ca_system_score_gemma":0.000023534189,"threshold_uncertainty_score":0.565683},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052118953,0.00003351033,0.9460859,0.00020167764,0.00014237923,0.00089202356,0.000018735782,0.000077741905,0.00042911814],"genre_scores_gemma":[0.0687788,0.000013483605,0.9279728,0.00020624945,0.00006162341,0.0019279293,0.0002656885,0.000008629525,0.00076481263],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908864,0.00003036009,0.00023516851,0.00035580093,0.00014566198,0.00014433372],"domain_scores_gemma":[0.9994766,0.000039450282,0.00005653591,0.0002493749,0.00014340658,0.00003462162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044892723,0.00008683202,0.00008536842,0.00012882525,0.00013789407,0.00024715738,0.00018636434,0.000053922424,0.000009808692],"category_scores_gemma":[0.000053302196,0.00008525972,0.00001470027,0.0004835869,0.00001555803,0.00055029773,0.000076599616,0.000043578588,0.0000026934179],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027026929,0.00013553954,0.0032909538,0.000028178818,0.0000069750736,4.013823e-7,0.0001057487,0.13739018,0.0009892976,0.029439123,0.002616794,0.82599413],"study_design_scores_gemma":[0.000431525,0.000023058567,0.014019072,0.000027762451,0.000018859508,0.0000021494868,0.000024459796,0.9836437,0.00053757266,0.0009716168,0.00022314925,0.000077037505],"about_ca_topic_score_codex":0.00018242332,"about_ca_topic_score_gemma":0.00007113311,"teacher_disagreement_score":0.8462536,"about_ca_system_score_codex":0.00006039499,"about_ca_system_score_gemma":0.00012283256,"threshold_uncertainty_score":0.34767908},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007486532,0.000023012928,0.97564214,0.021881513,0.00008493997,0.00027681966,0.00011897816,0.00006251782,0.001161445],"genre_scores_gemma":[0.0025088747,0.000007268531,0.99559623,0.0011344559,0.000023805987,0.00008133912,0.00009749801,0.0000029109262,0.00054759724],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992728,0.00002345219,0.00015408485,0.00030318648,0.00009914758,0.00014732112],"domain_scores_gemma":[0.9992008,0.00017144853,0.000060512153,0.00047128738,0.000052218285,0.000043683216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021322031,0.00013629059,0.00015594512,0.00012514324,0.00009450167,0.0005191383,0.00085311435,0.000068344656,0.0000013405687],"category_scores_gemma":[0.000010978571,0.00008408929,0.000016853504,0.00025774623,0.000041246076,0.00013297179,0.0016680144,0.0002141147,0.0000065466643],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002688019,0.00003868168,0.0001336113,0.000089856796,0.00004537616,0.0000017585073,0.005246842,0.16457863,0.0000018476221,0.12342592,0.010742663,0.6956921],"study_design_scores_gemma":[0.00008702722,0.000015439957,0.00039199527,0.00005341622,0.0000032173095,0.0000044804647,0.00010790285,0.98110896,0.0000025961103,0.010350459,0.007753625,0.00012088548],"about_ca_topic_score_codex":0.000059686383,"about_ca_topic_score_gemma":0.00012991988,"teacher_disagreement_score":0.81653035,"about_ca_system_score_codex":0.000021777096,"about_ca_system_score_gemma":0.00012845625,"threshold_uncertainty_score":0.50060624},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008127032,0.000048084887,0.9903803,0.0007315573,0.00006117887,0.00012077209,0.0000021417625,0.00014004139,0.00038893026],"genre_scores_gemma":[0.030744396,0.000008568687,0.9672453,0.00014311483,0.000019436031,0.000103236256,0.000008684492,0.000003695838,0.0017236029],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994025,0.000011565913,0.00009076499,0.00030048966,0.000069269656,0.00012539819],"domain_scores_gemma":[0.9995484,0.00016186277,0.000036508598,0.00015924478,0.000060454033,0.000033581244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012560208,0.00006696625,0.0000695894,0.00005915951,0.00027224136,0.0001543137,0.00017482828,0.000036278878,0.0000029194869],"category_scores_gemma":[0.000037291444,0.00005661211,0.000016573757,0.0003000512,0.000035879755,0.00022174174,0.00008336941,0.00007920985,0.000002668848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007562415,0.0000814211,0.016218822,0.00003372472,0.00003689126,9.570774e-7,0.0005243418,0.0003512721,0.0011655015,0.19252345,0.00026194693,0.7887941],"study_design_scores_gemma":[0.00021366226,0.000045024324,0.009863755,0.00006603924,0.000007719261,0.00000767079,0.00019088006,0.98409295,0.00017648077,0.0018931088,0.0033446352,0.00009808346],"about_ca_topic_score_codex":0.000022042672,"about_ca_topic_score_gemma":0.000026699605,"teacher_disagreement_score":0.98374164,"about_ca_system_score_codex":0.000014525745,"about_ca_system_score_gemma":0.000027114975,"threshold_uncertainty_score":0.23085748},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004362832,0.00004483206,0.9951541,0.00043406116,0.0006632924,0.0006719336,0.00017337484,0.0002099333,0.0026048345],"genre_scores_gemma":[0.008983987,0.000014669105,0.9883975,0.00084624713,0.00039095766,0.00011076569,0.00011280437,0.000032311593,0.0011107494],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99607295,0.000019246032,0.00047034,0.0018460387,0.0008744936,0.0007169359],"domain_scores_gemma":[0.99687195,0.00056631176,0.0004553854,0.0012575531,0.00067423464,0.00017459648],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009458275,0.0005033437,0.0005348115,0.00055245444,0.00044441564,0.00076252816,0.0025782366,0.00022156157,0.000007227682],"category_scores_gemma":[0.000054878343,0.00045957742,0.00010071031,0.0006040564,0.00023734117,0.0010123737,0.00056528964,0.00048343843,0.000010140591],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000701727,0.000054467728,0.000016160195,0.000019461208,0.000030452553,0.000017330829,0.00045907716,0.0016925451,0.000056213667,0.010656542,0.00027806687,0.9867127],"study_design_scores_gemma":[0.00045463414,0.000605086,0.000042951528,0.00027956045,0.000028507655,0.000028505134,0.0000010365522,0.9475609,0.0057761157,0.04364781,0.0008540707,0.0007208208],"about_ca_topic_score_codex":0.000021906433,"about_ca_topic_score_gemma":0.000037114332,"teacher_disagreement_score":0.98599184,"about_ca_system_score_codex":0.0005417832,"about_ca_system_score_gemma":0.0010242987,"threshold_uncertainty_score":0.9997856},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029930098,0.000009830315,0.96849245,0.027131623,0.000024786947,0.00009716322,0.000008183915,0.00003208617,0.0012108493],"genre_scores_gemma":[0.024236657,0.0000014590127,0.9735529,0.0017521535,0.0000069759553,0.000020235162,0.00000976787,0.0000012909451,0.00041859224],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996625,0.00000969132,0.00007292513,0.00011640484,0.00004577414,0.00009267562],"domain_scores_gemma":[0.99965537,0.00010803631,0.000015673206,0.00017617778,0.000022552218,0.000022168699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011750351,0.000049690516,0.000056959398,0.00006488031,0.000084639534,0.00022065466,0.0003049166,0.000014823875,8.853689e-7],"category_scores_gemma":[0.0000068660247,0.000028922426,0.000005496161,0.0003446099,0.000027147473,0.00017398111,0.00019073319,0.000044448378,0.0000064570945],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015931066,0.000021045795,0.00032383506,0.000009579187,0.000011790733,6.2059513e-7,0.0019366603,0.011367167,0.00001335672,0.32108334,0.0092704855,0.65596056],"study_design_scores_gemma":[0.000105442494,0.000016517075,0.0015030364,0.0000097132515,0.0000010235293,0.0000031355717,0.00015674201,0.9801532,0.000008896563,0.0057067764,0.012288485,0.000047017613],"about_ca_topic_score_codex":0.000017265389,"about_ca_topic_score_gemma":0.000071430964,"teacher_disagreement_score":0.96878606,"about_ca_system_score_codex":0.000008145,"about_ca_system_score_gemma":0.00003263668,"threshold_uncertainty_score":0.21277781},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00330314,0.00007908673,0.9936314,0.00012614111,0.0013721538,0.0005719129,0.00010383363,0.00028045094,0.00053186767],"genre_scores_gemma":[0.42642823,0.0000019474237,0.5731959,0.000021031517,0.000023137733,0.000041275347,0.00025654677,0.0000032039582,0.00002874757],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986011,0.00006801071,0.0003823716,0.0006651889,0.000087999164,0.0001953676],"domain_scores_gemma":[0.99850494,0.0001383135,0.00011724791,0.0011014917,0.000105437706,0.00003257864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006408878,0.00013089311,0.00015699561,0.0002788287,0.0002472371,0.00018484669,0.001016648,0.000058037334,5.838712e-7],"category_scores_gemma":[0.00004761672,0.0001384714,0.0000400027,0.0007945972,0.000064495514,0.00024375957,0.00043242032,0.000105272804,0.000008965078],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005113296,0.000102617916,0.0009294462,0.00022151436,0.000021132777,8.5275565e-7,0.00010690482,0.0005024188,0.0000775772,0.06358873,0.00052767864,0.93391603],"study_design_scores_gemma":[0.0007628088,0.000010134426,0.0023786125,0.0002474134,0.000013448149,0.0000031423338,0.00022713763,0.9926076,0.0003893253,0.0003225178,0.0029145211,0.00012334477],"about_ca_topic_score_codex":0.000030412759,"about_ca_topic_score_gemma":0.0000221278,"teacher_disagreement_score":0.9921052,"about_ca_system_score_codex":0.00013609268,"about_ca_system_score_gemma":0.000072459865,"threshold_uncertainty_score":0.56467},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018630864,0.00015849051,0.98009175,0.00016548623,0.00037332793,0.00028279703,0.000010855505,0.00007246647,0.00021393837],"genre_scores_gemma":[0.5027389,0.00006484144,0.4968799,0.000029477516,0.00001544116,0.00009902165,0.00014024835,0.0000051691354,0.000026993574],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988834,0.000013694764,0.0006047485,0.00025153265,0.0000936154,0.00015299546],"domain_scores_gemma":[0.999168,0.000087341934,0.00010431401,0.0005282974,0.00009413249,0.000017948316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004293642,0.00011096176,0.00014623805,0.0007616698,0.00006102896,0.00021362232,0.0004112502,0.000054775574,3.53155e-7],"category_scores_gemma":[0.00017762481,0.00011983251,0.000007812515,0.001873685,0.000010672957,0.001984167,0.00017287733,0.000130725,0.0000013952077],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028824543,0.00003288335,0.0002864314,0.00007020525,0.000007913425,7.059561e-7,0.0004909378,0.35134208,0.003672543,0.2505696,0.000056497858,0.3934673],"study_design_scores_gemma":[0.00018034379,0.000003650658,0.0007503709,0.00041173946,0.000001692344,0.0000030330616,0.00050798076,0.99494207,0.00032659512,0.00011970298,0.0026446357,0.00010815624],"about_ca_topic_score_codex":0.00007888933,"about_ca_topic_score_gemma":0.0000100152965,"teacher_disagreement_score":0.64360005,"about_ca_system_score_codex":0.0001229701,"about_ca_system_score_gemma":0.000044994886,"threshold_uncertainty_score":0.4886628},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015502882,0.00018394098,0.9821101,0.0015904658,0.00019764525,0.00014348137,0.000004415941,0.000009129503,0.0002579551],"genre_scores_gemma":[0.4604657,0.0001106953,0.53918326,0.000029874493,0.00008412239,0.000011424872,3.3425863e-7,0.0000037052102,0.000110913825],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987627,0.00005050936,0.00045578345,0.00018909432,0.0002879736,0.000253889],"domain_scores_gemma":[0.99759555,0.0014098552,0.00008519874,0.00022490068,0.0005931821,0.00009131108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024983971,0.0000659358,0.00015508453,0.0003994027,0.00024252177,0.00046031683,0.0007864407,0.000043421816,0.000007970101],"category_scores_gemma":[0.00091109704,0.00005486376,0.000054587155,0.00054992025,0.00016290584,0.00039776374,0.00032248945,0.0002509863,0.0000046119826],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052991298,0.000052981955,0.000009149874,0.000010462216,0.000014847357,0.0000040296645,0.00032793978,0.00076762406,0.003281912,0.04425559,0.00061255,0.9506099],"study_design_scores_gemma":[0.00005134961,0.00030853826,0.00004185872,0.00019622572,0.000004899438,0.00003112603,0.0009745793,0.9211384,0.014969371,0.0588286,0.0033884486,0.00006658491],"about_ca_topic_score_codex":0.0000140060765,"about_ca_topic_score_gemma":0.000020419939,"teacher_disagreement_score":0.95054334,"about_ca_system_score_codex":0.0000419924,"about_ca_system_score_gemma":0.00021257505,"threshold_uncertainty_score":0.44388458},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019032734,0.0000069990556,0.9740998,0.0018801912,0.000055845343,0.000113882066,0.000021911676,0.000072357245,0.0047162925],"genre_scores_gemma":[0.13026585,0.000008411915,0.8377001,0.0014266497,0.000041275223,0.00024624058,0.000049415805,0.0000073025317,0.030254737],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995444,0.0000052738287,0.00010028393,0.00018392659,0.000047423084,0.00011872234],"domain_scores_gemma":[0.99965394,0.000060128546,0.000014699747,0.00024030301,0.0000149502885,0.000015994188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010317564,0.000047725127,0.00006523191,0.000055272376,0.000047380177,0.00013377232,0.0004470475,0.000018884639,0.000015996462],"category_scores_gemma":[0.000012343644,0.00004477595,0.000016996117,0.00017710017,0.000007602886,0.00026513243,0.00017178983,0.0000246548,0.000017506074],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008888573,0.00015217531,0.013599929,0.000041464977,0.000018133305,0.000005840954,0.0005343444,0.000044397326,0.0005227653,0.34330577,0.028078659,0.61368763],"study_design_scores_gemma":[0.0017613841,0.00018749264,0.07691586,0.00017291632,0.000010601294,0.000011374695,0.00018836773,0.62069243,0.008380158,0.02342816,0.2676334,0.0006178573],"about_ca_topic_score_codex":0.000024238667,"about_ca_topic_score_gemma":0.000016991475,"teacher_disagreement_score":0.620648,"about_ca_system_score_codex":0.000011927804,"about_ca_system_score_gemma":0.000027247774,"threshold_uncertainty_score":0.18259102},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007486532,0.000023012928,0.97564214,0.021881513,0.00008493997,0.00027681966,0.00011897816,0.00006251782,0.001161445],"genre_scores_gemma":[0.0025088747,0.000007268531,0.99559623,0.0011344559,0.000023805987,0.00008133912,0.00009749801,0.0000029109262,0.00054759724],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992728,0.00002345219,0.00015408485,0.00030318648,0.00009914758,0.00014732112],"domain_scores_gemma":[0.9992008,0.00017144853,0.000060512153,0.00047128738,0.000052218285,0.000043683216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021322031,0.00013629059,0.00015594512,0.00012514324,0.00009450167,0.0005191383,0.00085311435,0.000068344656,0.0000013405687],"category_scores_gemma":[0.000010978571,0.00008408929,0.000016853504,0.00025774623,0.000041246076,0.00013297179,0.0016680144,0.0002141147,0.0000065466643],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002688019,0.00003868168,0.0001336113,0.000089856796,0.00004537616,0.0000017585073,0.005246842,0.16457863,0.0000018476221,0.12342592,0.010742663,0.6956921],"study_design_scores_gemma":[0.00008702722,0.000015439957,0.00039199527,0.00005341622,0.0000032173095,0.0000044804647,0.00010790285,0.98110896,0.0000025961103,0.010350459,0.007753625,0.00012088548],"about_ca_topic_score_codex":0.000059686383,"about_ca_topic_score_gemma":0.00012991988,"teacher_disagreement_score":0.81653035,"about_ca_system_score_codex":0.000021777096,"about_ca_system_score_gemma":0.00012845625,"threshold_uncertainty_score":0.50060624},"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":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000056214185,0.7854112,0.21007964,0.0001545817,0.0011662067,0.0023855297,0.00015336281,0.000030337796,0.00061356346],"genre_scores_gemma":[0.00014147855,0.9712845,0.026893605,0.00022379197,0.00034259082,0.0009458355,0.00008349872,0.000034028995,0.000050687682],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9895606,0.0023232314,0.0036259855,0.002205064,0.0011834427,0.0011016965],"domain_scores_gemma":[0.9922948,0.0039879587,0.0011701816,0.0017428884,0.00059990643,0.00020424715],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00820536,0.0008732965,0.0036297876,0.0017259278,0.00026317718,0.0008913148,0.0026493936,0.00035973274,0.0000073279944],"category_scores_gemma":[0.00012904734,0.00077451195,0.00026163814,0.0047764843,0.0003652822,0.0014195727,0.0012914843,0.0014551944,0.000010267532],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028734828,0.00017864359,0.00001566173,0.18240614,0.000037640453,0.00005828773,0.00038727574,0.0019167778,3.4147968e-7,0.0065631117,0.0005023641,0.8079309],"study_design_scores_gemma":[0.00029351824,0.00039166497,0.0000056478693,0.60728335,0.000030006328,0.000045771223,0.00026102195,0.14765549,7.520385e-7,0.0007373749,0.24276774,0.0005277019],"about_ca_topic_score_codex":0.00030337504,"about_ca_topic_score_gemma":0.000036543297,"teacher_disagreement_score":0.8074032,"about_ca_system_score_codex":0.00023756806,"about_ca_system_score_gemma":0.0011652696,"threshold_uncertainty_score":0.9994706},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04606934,0.00030979473,0.94805616,0.00009154524,0.00016563115,0.00004761866,0.000009018984,0.0000909867,0.0051598987],"genre_scores_gemma":[0.9617516,0.0000078769135,0.037040304,0.000050934115,0.00005341293,0.000011119981,0.0000052059554,0.0000035773928,0.0010759676],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99950755,0.000040570318,0.00008074377,0.0001492862,0.00005720288,0.00016465169],"domain_scores_gemma":[0.99941695,0.00015401513,0.0000195734,0.00029284283,0.00003195078,0.00008466919],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005248739,0.000058100286,0.00006164919,0.000028408154,0.0000707471,0.00020056842,0.00031950296,0.000016688047,0.0000024550293],"category_scores_gemma":[0.00008414505,0.000044928227,0.000009701966,0.00017925708,0.000027111817,0.0009449041,0.0003092621,0.00004164815,0.00004629924],"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":[0.000001784305,0.00028102068,0.09613007,0.000014218137,0.00001776793,4.5328e-7,0.0022327404,4.9225264e-7,0.00019805138,0.1731368,0.010008373,0.71797824],"study_design_scores_gemma":[0.00027846798,0.00004012996,0.9313903,0.000034770674,0.0000066511598,0.000037561727,0.00012065725,0.024013594,0.0008890436,0.0007726351,0.042001914,0.00041428834],"about_ca_topic_score_codex":0.00016033472,"about_ca_topic_score_gemma":0.000095941235,"teacher_disagreement_score":0.91568226,"about_ca_system_score_codex":0.000007115571,"about_ca_system_score_gemma":0.000018341068,"threshold_uncertainty_score":0.1934086},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020477556,0.000093049515,0.9918966,0.00038343534,0.0005181944,0.00045981925,0.000027707049,0.00019287654,0.0062235016],"genre_scores_gemma":[0.07906385,0.0000106774905,0.9179877,0.0021940798,0.00031688897,0.000060862476,0.000026848767,0.000037421716,0.00030166277],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959174,0.00002650485,0.0005011383,0.0019682879,0.000791231,0.0007954453],"domain_scores_gemma":[0.99719995,0.0003306399,0.00011669842,0.0017813734,0.00016861284,0.00040269585],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00056354003,0.00053878437,0.0005486882,0.00063906383,0.0002886664,0.00067443907,0.004714483,0.00025505392,0.000011720078],"category_scores_gemma":[0.00008853458,0.00048180376,0.00009483622,0.0008218334,0.0005696034,0.00038096277,0.00200813,0.0006181609,0.00008738523],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000056233653,0.0001004859,0.000030357176,0.000025393058,0.000012462097,0.000023596576,0.0017487393,0.000499463,0.00013718753,0.13004473,0.00016834463,0.86720365],"study_design_scores_gemma":[0.00042648043,0.00032139663,0.0012670982,0.0005679738,0.000019189052,0.0001608769,8.025138e-7,0.94457495,0.00045888155,0.047297925,0.003483888,0.0014205301],"about_ca_topic_score_codex":0.000031777126,"about_ca_topic_score_gemma":0.00001687364,"teacher_disagreement_score":0.9440755,"about_ca_system_score_codex":0.00016004061,"about_ca_system_score_gemma":0.00026552932,"threshold_uncertainty_score":0.99976337},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016439168,0.00004479034,0.9954139,0.002374472,0.000042167227,0.00012881406,0.00002127205,0.000039191953,0.00029148135],"genre_scores_gemma":[0.46976578,0.0000035617654,0.5299191,0.00014714121,0.000036531892,0.000009799935,0.00007846266,0.000001422977,0.00003821333],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995541,0.0000071456648,0.00011701904,0.0001762488,0.000076218734,0.0000692694],"domain_scores_gemma":[0.9989484,0.00019354094,0.00006083444,0.00075146515,0.00003204234,0.00001370281],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022757277,0.000038855218,0.00005313908,0.000017746104,0.00010973715,0.00005848753,0.0009427832,0.000010964026,0.0000011595066],"category_scores_gemma":[0.000048072874,0.00002535487,0.000012388872,0.00016314439,0.000009042417,0.00061758194,0.00014242993,0.000019319032,0.0000013340216],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.740345e-7,0.000021697104,0.00004008543,0.0000014170347,0.00000497866,5.320014e-8,0.0005262122,0.000041968433,0.00016231141,0.19078082,0.002094301,0.80632526],"study_design_scores_gemma":[0.00009367766,0.000044598273,0.0054589477,0.000008004399,0.0000056900753,8.725383e-7,0.0003860884,0.9859116,0.00028648585,0.005616756,0.0021298302,0.000057412864],"about_ca_topic_score_codex":0.000025734544,"about_ca_topic_score_gemma":0.000008023322,"teacher_disagreement_score":0.98586965,"about_ca_system_score_codex":0.000003982024,"about_ca_system_score_gemma":0.000008027574,"threshold_uncertainty_score":0.17519414},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000041654548,0.0009886498,0.99603355,0.00017656691,0.0016193369,0.00060378335,0.00017389124,0.00014746758,0.00021508911],"genre_scores_gemma":[0.0022127028,0.000026842208,0.9957531,0.0005675745,0.0012342634,0.00003122249,0.000045365883,0.00004681375,0.00008211592],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99616194,0.00002082845,0.00059412385,0.0015186969,0.00077824557,0.00092616596],"domain_scores_gemma":[0.99714273,0.00046048773,0.00042422375,0.0014501446,0.00027124124,0.0002511548],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007562794,0.0005762348,0.0005498345,0.00073278946,0.00050834235,0.000756365,0.0032573184,0.0003198209,0.000012316072],"category_scores_gemma":[0.000050295297,0.00053543603,0.00016381413,0.00063139957,0.0004052103,0.0007899712,0.0012241707,0.00048770272,0.000010585901],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.6513456e-7,0.00001805662,0.000008883901,0.000018344028,0.000011254911,0.000007524904,0.000483175,0.0036486874,0.00007108713,0.006548402,0.000036277936,0.98914766],"study_design_scores_gemma":[0.00022663201,0.00008220811,0.000032184154,0.00016262945,0.00002077128,0.0000890845,6.328273e-7,0.95028055,0.00044485767,0.043103952,0.0048839813,0.00067249424],"about_ca_topic_score_codex":0.00005508636,"about_ca_topic_score_gemma":0.000018642982,"teacher_disagreement_score":0.98847514,"about_ca_system_score_codex":0.00032300386,"about_ca_system_score_gemma":0.00048108384,"threshold_uncertainty_score":0.9997097},"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":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9653994,0.00029227065,0.02463958,0.003997004,0.00044479157,0.00033986795,0.00017856306,0.00036273655,0.0043457774],"genre_scores_gemma":[0.001357149,0.00017688167,0.31609237,0.000019263045,0.000023503928,5.267665e-7,0.00052914623,0.00001369569,0.6817875],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990232,0.000012018472,0.00006463535,0.00044000067,0.000251424,0.0002087314],"domain_scores_gemma":[0.9989617,0.000017467804,0.0001873014,0.00061997364,0.00012758467,0.00008598103],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000054328633,0.00017815112,0.00025431145,0.00018053802,0.00027715843,0.00003558615,0.0012696054,0.00022616684,0.000009645685],"category_scores_gemma":[0.0000045479273,0.000212847,0.000115341885,0.00026760722,0.000043372653,0.00039842617,0.00014529508,0.00020253063,0.00004224822],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000478952,0.00025097083,0.00008096179,0.00030456044,0.00022596348,0.0001561175,0.53034794,0.0012232647,0.0033633162,0.009564328,0.3196761,0.13475859],"study_design_scores_gemma":[0.0010094929,0.00015036076,0.0018837677,0.00042633153,0.00015235327,0.000031176678,0.08996433,0.8853011,0.0016800758,0.0006018845,0.017470753,0.0013283374],"about_ca_topic_score_codex":0.0022324282,"about_ca_topic_score_gemma":0.0032727625,"teacher_disagreement_score":0.96404225,"about_ca_system_score_codex":0.000033544777,"about_ca_system_score_gemma":0.00013769092,"threshold_uncertainty_score":0.86796486},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90269417,0.00046453,0.024163518,0.00053895114,0.0012093519,0.00083289103,0.0003653585,0.0002007434,0.06953049],"genre_scores_gemma":[0.98964226,0.00023288454,0.0011308235,0.0000025779975,0.00012371199,0.000009500051,0.0003254605,0.000019362627,0.008513437],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99787843,0.00017787324,0.00023447201,0.00066804356,0.0006202585,0.00042092393],"domain_scores_gemma":[0.998082,0.00014342344,0.00019465825,0.0009713401,0.0003681216,0.00024049665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003335617,0.00019785234,0.00027131801,0.0006119564,0.00060905097,0.0001768001,0.0015040135,0.0002673911,0.00001043229],"category_scores_gemma":[0.000058408124,0.00021938288,0.00009511025,0.0009076279,0.00023499517,0.0004224509,0.00030902267,0.0009443682,0.000011463796],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012753379,0.0014276105,0.092804566,0.0009357612,0.0010406361,0.0013168592,0.0037606235,0.0000019507997,0.13085252,0.33955988,0.0062209424,0.42195112],"study_design_scores_gemma":[0.0014418593,0.00083313236,0.81399596,0.0005141855,0.00020515248,0.000085735315,0.0020764456,0.001634785,0.11440813,0.010943411,0.052444503,0.0014167211],"about_ca_topic_score_codex":0.011521492,"about_ca_topic_score_gemma":0.008752006,"teacher_disagreement_score":0.72119135,"about_ca_system_score_codex":0.00015180193,"about_ca_system_score_gemma":0.0006461086,"threshold_uncertainty_score":0.99506086},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005183038,0.00020174152,0.0041919616,0.0023692132,0.002452773,0.0012785573,0.0025968559,0.00017727606,0.9862133],"genre_scores_gemma":[0.008375054,0.00001676083,0.009105779,0.00033986443,0.0006665995,0.000032912656,0.0003482473,0.00006552195,0.98104924],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99725085,0.00003351601,0.0006837159,0.0009748547,0.0006740251,0.00038306],"domain_scores_gemma":[0.9957987,0.0010520641,0.00149845,0.0010689993,0.00048514197,0.00009662351],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00061911787,0.0004082427,0.000474303,0.000120963545,0.0004125303,0.0005396809,0.004260379,0.00022454356,0.0000070914525],"category_scores_gemma":[0.00052113825,0.00034891965,0.000107387306,0.0000992291,0.00006616118,0.0003176043,0.002301766,0.0004499191,0.000009882399],"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":[0.0000044640815,0.00006511415,0.00030419294,0.00007233255,0.0002235789,5.28997e-7,0.0006698079,0.000008523782,0.000011862402,0.03735219,0.9297746,0.03151285],"study_design_scores_gemma":[0.00073704263,0.000081430066,0.0013567368,0.0006232959,0.0001301367,0.000009265483,0.000028869015,0.2974429,0.000040142197,0.0021557217,0.69670135,0.00069312786],"about_ca_topic_score_codex":0.007891564,"about_ca_topic_score_gemma":0.028230606,"teacher_disagreement_score":0.2974344,"about_ca_system_score_codex":0.0005834778,"about_ca_system_score_gemma":0.0009100815,"threshold_uncertainty_score":0.9998963},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8640985,0.00028328632,0.12958556,0.0013950239,0.0013494992,0.00034132504,0.00006771067,0.00028897403,0.002590146],"genre_scores_gemma":[0.97281766,0.0000046831824,0.026717499,0.0000793642,0.000007810884,0.00002651536,0.00003643233,0.00001210278,0.00029792485],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988264,0.00003835411,0.00029843114,0.00033415243,0.00025452414,0.00024812948],"domain_scores_gemma":[0.99890435,0.00013207983,0.00015250135,0.00067618594,0.00006700492,0.00006789164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017977165,0.00013751164,0.00019386523,0.00006870576,0.00009520871,0.000092045084,0.0008186375,0.000046479232,0.000005701449],"category_scores_gemma":[0.000017629247,0.0001355669,0.00006744571,0.00035014396,0.000057621564,0.00029347008,0.00022253013,0.00008945189,0.000024269264],"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":[0.000004436433,0.00060898246,0.004145891,0.000021451855,0.00004137984,0.00001150923,0.00024556206,0.000058895057,0.014672869,0.87680966,0.06400097,0.039378412],"study_design_scores_gemma":[0.005161593,0.0005111467,0.07355709,0.00016157197,0.00007520689,0.000034415905,0.00014118891,0.21309817,0.04073729,0.5964138,0.06840475,0.0017038045],"about_ca_topic_score_codex":0.00035523402,"about_ca_topic_score_gemma":0.000006304011,"teacher_disagreement_score":0.28039587,"about_ca_system_score_codex":0.00004070715,"about_ca_system_score_gemma":0.000025383995,"threshold_uncertainty_score":0.55282575},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08183807,0.00048570512,0.91316664,0.00018784807,0.0004952222,0.00032156822,0.0010696929,0.00011196397,0.00232327],"genre_scores_gemma":[0.6774954,0.000054838274,0.31673345,0.00025225827,0.00036592985,0.00016361877,0.0032499137,0.000040426006,0.0016441314],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99812156,0.0000776983,0.0003436356,0.00093053,0.00013715237,0.00038940847],"domain_scores_gemma":[0.99812084,0.000289954,0.00013304988,0.0012467358,0.000093345865,0.00011609072],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056778506,0.00022913975,0.00023570674,0.00009745618,0.00041138215,0.000747923,0.0010486611,0.00009689187,0.000009227666],"category_scores_gemma":[0.0001803538,0.00022345771,0.000042540174,0.0003102046,0.00007577762,0.002597721,0.0007349769,0.00010970427,0.000015624852],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042378426,0.000638014,0.002969009,0.00024811734,0.00019218812,0.000019679961,0.008129,0.000022600114,0.0059254537,0.025191743,0.0393478,0.917274],"study_design_scores_gemma":[0.0029954636,0.00031198395,0.0031160028,0.0003780765,0.00016830763,0.000120008415,0.0013010158,0.8845803,0.0018612089,0.0009784411,0.103007734,0.0011814277],"about_ca_topic_score_codex":0.000014483548,"about_ca_topic_score_gemma":0.00011831549,"teacher_disagreement_score":0.9160926,"about_ca_system_score_codex":0.000024406027,"about_ca_system_score_gemma":0.00021403204,"threshold_uncertainty_score":0.91123414},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.103528455,7.2762975e-7,0.20591815,0.0035609936,0.0012217998,0.0009870987,0.00010198703,0.0024547146,0.68222606],"genre_scores_gemma":[0.21558833,0.0001735967,0.10625563,0.00071362243,0.00034946256,0.0011988889,0.00018743092,0.00008460967,0.6754484],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971361,0.00017259236,0.0003637433,0.0016224199,0.0003015709,0.00040357045],"domain_scores_gemma":[0.99488115,0.00023835084,0.0001244801,0.004524678,0.000072716735,0.00015862686],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0031201635,0.0001728195,0.00021310739,0.00014768181,0.00021861316,0.00038076137,0.0026246475,0.00009399623,0.10293861],"category_scores_gemma":[0.00063716824,0.00018639078,0.00007080983,0.0006740089,0.00006715135,0.00047798184,0.0030852458,0.0001500895,0.9366379],"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":[0.000012613571,0.00029707712,0.0014903318,0.00007361409,0.00011684079,0.00007056696,0.0022913727,0.00040690627,0.072339974,0.13511449,0.42980266,0.35798356],"study_design_scores_gemma":[0.00057535875,0.000001249345,0.032389194,0.00006841454,0.000024949575,0.000068407375,0.00010430631,0.024473673,0.114286974,0.03748622,0.78974634,0.0007749178],"about_ca_topic_score_codex":0.0001017675,"about_ca_topic_score_gemma":0.0000044025087,"teacher_disagreement_score":0.8336993,"about_ca_system_score_codex":0.000055186993,"about_ca_system_score_gemma":0.000080851954,"threshold_uncertainty_score":0.89788145},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000013379744,0.00062399823,0.99009067,0.0041693207,0.00063457957,0.0010277524,0.002505972,0.0002164144,0.0007179432],"genre_scores_gemma":[0.0001925279,0.00092301826,0.032097686,0.00055233465,0.00008506365,0.00040597134,0.000055621113,0.000026235402,0.9656615],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99761075,0.00005190144,0.0004117683,0.0009041305,0.0004996329,0.0005218447],"domain_scores_gemma":[0.9980097,0.0003490495,0.00014386902,0.0013194216,0.000060029583,0.000117961994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005529147,0.0003151772,0.00036359223,0.00010527197,0.0003117459,0.000069171816,0.0021296341,0.00016462972,0.00087255106],"category_scores_gemma":[0.0000667454,0.00017970121,0.00021438938,0.00042494558,0.0006408481,0.00022136157,0.00032096938,0.00015768482,0.00022109998],"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":[0.0000056727145,0.00013413906,0.000007038867,0.000029701025,0.000017361737,7.829314e-7,0.000021368347,0.000013946613,0.000112207556,0.006607563,0.00022169383,0.99282855],"study_design_scores_gemma":[0.00027766568,0.00022833448,0.00011283314,0.0000491795,0.000027252436,0.0000032136327,0.00001713231,0.0017178501,0.000083680876,0.00093728147,0.99629503,0.00025055933],"about_ca_topic_score_codex":0.00010691962,"about_ca_topic_score_gemma":0.000009317612,"teacher_disagreement_score":0.9960733,"about_ca_system_score_codex":0.000047494406,"about_ca_system_score_gemma":0.00008096067,"threshold_uncertainty_score":0.9553822},"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":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25181723,0.0004435507,0.00561004,0.00009366102,0.00006105502,0.00034071042,0.741606,0.000020234982,0.000007548597],"genre_scores_gemma":[0.06672116,0.0018747649,0.004984712,0.00005655143,0.0001923002,0.000015893036,0.926118,0.0000134577895,0.000023153254],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973241,0.00023209212,0.00058853655,0.0011419895,0.00038839597,0.00032490178],"domain_scores_gemma":[0.9948292,0.00056801335,0.00080280367,0.0036061148,0.00007923071,0.00011463988],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0008616574,0.0003368552,0.00065222476,0.000062720996,0.00068461726,0.00014549206,0.005080936,0.00014012578,0.000012355976],"category_scores_gemma":[0.000018466972,0.00026431013,0.000037451646,0.00022801105,0.00036654266,0.0007932361,0.018420942,0.00038347204,9.993248e-7],"study_design_candidate":"not_applicable","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":[0.00013012068,0.0005913709,0.09120842,0.0027647878,0.0005816061,0.0000038552034,0.008151251,0.00007330346,0.00027556252,0.00007216676,0.82554543,0.07060212],"study_design_scores_gemma":[0.00077707105,0.00018219014,0.37216657,0.000523933,0.00032016757,0.000011499411,0.00084091665,0.42092183,0.000025136811,0.0002197689,0.20349742,0.0005134971],"about_ca_topic_score_codex":0.031823292,"about_ca_topic_score_gemma":0.028544692,"teacher_disagreement_score":0.622048,"about_ca_system_score_codex":0.000018468863,"about_ca_system_score_gemma":0.000042081538,"threshold_uncertainty_score":0.9999809},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023182472,0.00004149861,0.9643125,0.0014853409,0.00019129964,0.0010854377,0.00023540818,0.0006167319,0.008849313],"genre_scores_gemma":[0.9860677,0.000024611558,0.0117322365,0.00038181536,0.00054386107,8.272285e-7,0.0004525168,0.0005463058,0.000250089],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987546,0.00015768707,0.00019470305,0.00035882342,0.00025633673,0.0002778105],"domain_scores_gemma":[0.99862784,0.00012604581,0.000080222635,0.0006749464,0.00043231997,0.000058628164],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018464924,0.00009337203,0.000106315034,0.000083707244,0.002036859,0.001231642,0.001639574,0.00003084704,0.00041857347],"category_scores_gemma":[0.0008782375,0.00007500055,0.00003694403,0.0006137577,0.00012676214,0.00041575736,0.0009542116,0.00012713409,0.00077867805],"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":[0.00003797534,0.00009186667,0.000037157868,0.00004104151,0.000046577243,0.0000022164809,0.0021952537,0.000058342044,0.0018280887,0.01920016,0.17002872,0.8064326],"study_design_scores_gemma":[0.0006499259,0.00021345119,0.0021724012,0.000016939412,0.000009061148,0.000007052156,0.000094598465,0.09321913,0.0013032448,0.0005613956,0.90161824,0.0001345813],"about_ca_topic_score_codex":0.000026034571,"about_ca_topic_score_gemma":0.0000019422894,"teacher_disagreement_score":0.96288526,"about_ca_system_score_codex":0.00006955397,"about_ca_system_score_gemma":0.0000060064626,"threshold_uncertainty_score":0.99999934},"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.854057e-7,0.00039984728,0.094538614,0.0008096199,0.00024961386,0.00029784327,0.00036420985,0.0026102727,0.9007294],"genre_scores_gemma":[0.000058741323,0.00022761428,0.011451807,0.00019594099,0.00051096303,1.4593535e-7,0.0017194403,0.005938587,0.9798968],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99821895,0.000103887716,0.00020520997,0.0007620592,0.00036769296,0.00034219236],"domain_scores_gemma":[0.9983869,0.000010108761,0.00010942007,0.001185498,0.0001358611,0.00017221342],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00031565304,0.0002098121,0.0001764359,0.00039385163,0.0006101847,0.002038117,0.0029924407,0.0001268437,0.039428815],"category_scores_gemma":[0.00008991982,0.00021673137,0.00006614182,0.0006713719,0.00010941559,0.00018022471,0.002762866,0.0003567433,0.3361491],"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":[5.826998e-7,0.00003451032,1.3888028e-8,0.00005808033,0.000031144595,0.000011667382,0.00015399151,4.4411274e-7,0.000029141342,0.026021918,0.8334876,0.14017093],"study_design_scores_gemma":[0.00010727811,0.00005509283,0.0000030981312,0.00012626318,0.000012206641,0.00006455507,0.000021971828,0.0010932797,0.000017996566,0.0007698136,0.99749166,0.00023676107],"about_ca_topic_score_codex":0.000027155505,"about_ca_topic_score_gemma":4.1625808e-7,"teacher_disagreement_score":0.2967203,"about_ca_system_score_codex":0.00008341388,"about_ca_system_score_gemma":0.0000066022685,"threshold_uncertainty_score":0.99899787},"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":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000020209327,0.0004782301,0.0009187043,0.0008205258,0.00062102074,0.00039665584,0.9953825,0.00017520167,0.0012051804],"genre_scores_gemma":[4.7059052e-7,0.0007305724,0.0049012266,0.0011765524,0.00037529328,0.00059233705,0.9868942,0.000041779273,0.0052875765],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99644446,0.0001212834,0.0005889849,0.0013814791,0.0007718733,0.00069189846],"domain_scores_gemma":[0.9956945,0.00024370625,0.00035487433,0.0033018976,0.00009780477,0.0003071945],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003736382,0.00035702356,0.0005667067,0.000117435404,0.0007436317,0.0027425312,0.0049360595,0.00026462993,0.008666536],"category_scores_gemma":[0.00011050189,0.0005664575,0.00020236662,0.00054274104,0.00012700955,0.0004335828,0.0018787741,0.0005886363,0.000101395985],"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":[7.0389154e-7,0.00014221616,0.00000967802,0.000048103106,0.00005901143,0.000094689145,0.000026839783,0.000003403966,1.9346014e-7,0.00014158804,0.9830674,0.01640619],"study_design_scores_gemma":[0.00020097333,0.000065733206,0.00025524225,0.00006323307,0.00006512324,0.000105802785,0.0000203757,0.00047030294,3.6283603e-7,0.00025379466,0.9978411,0.0006579414],"about_ca_topic_score_codex":0.88692355,"about_ca_topic_score_gemma":0.8364408,"teacher_disagreement_score":0.05048274,"about_ca_system_score_codex":0.00012577612,"about_ca_system_score_gemma":0.00027782808,"threshold_uncertainty_score":0.9996787},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000001176735,0.00008735896,0.29667348,0.0004501928,0.00012703403,0.000300273,0.0002838139,0.001582686,0.700494],"genre_scores_gemma":[0.00048693057,0.00023590852,0.04298446,0.00037325986,0.0005353309,1.5383026e-7,0.0041554486,0.010802586,0.94042593],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984022,0.00012242433,0.00018535994,0.0006266777,0.00035121216,0.00031212613],"domain_scores_gemma":[0.9981403,0.000013865034,0.00015116026,0.0014045235,0.00015616186,0.00013400725],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00029814066,0.00018177254,0.0001809993,0.00028726168,0.000706359,0.0013021937,0.0032191006,0.00011710058,0.007625985],"category_scores_gemma":[0.00008876231,0.00018900126,0.000049941067,0.0004987293,0.000074669566,0.00020731345,0.002122729,0.00025433773,0.056853388],"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":[7.1413547e-7,0.000040985648,2.639451e-8,0.000028555894,0.00001920217,0.0000024962444,0.00014267245,0.000004527341,0.000036188878,0.040270776,0.8177835,0.1416704],"study_design_scores_gemma":[0.00016240215,0.00005897336,0.000004000071,0.00005150675,0.0000066985453,0.00003316287,0.000023864037,0.00773414,0.000013097352,0.00020947344,0.9914867,0.00021594318],"about_ca_topic_score_codex":0.000035174984,"about_ca_topic_score_gemma":2.7763275e-7,"teacher_disagreement_score":0.25368902,"about_ca_system_score_codex":0.00006242475,"about_ca_system_score_gemma":0.000006347498,"threshold_uncertainty_score":0.9997345},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032768026,0.00017319298,0.47531915,0.034982514,0.0013843959,0.0019657083,0.0017737233,0.022370698,0.4292626],"genre_scores_gemma":[0.8902699,0.0007500489,0.060809176,0.0019412402,0.0014512949,0.0000012884288,0.012097062,0.0054342244,0.027245808],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99828756,0.00014056961,0.00021730657,0.0005520751,0.00035947957,0.00044303542],"domain_scores_gemma":[0.9984355,0.00003314858,0.00006206889,0.0009976268,0.000274944,0.00019669483],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00063699856,0.0001318967,0.00012361097,0.00023508239,0.0020605433,0.0015314176,0.0026043234,0.00005484673,0.0028671839],"category_scores_gemma":[0.00027554898,0.00013767906,0.000047625294,0.0015916582,0.00008829422,0.00056218903,0.0025481046,0.00020371018,0.029421883],"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":[0.0000035036517,0.000065847365,8.916737e-7,0.000012960986,0.00002103708,0.0000138639425,0.0009123941,0.000016753807,0.0063827746,0.037003,0.70352674,0.2520402],"study_design_scores_gemma":[0.0002065546,0.00007247225,0.0006317501,0.000010223829,0.0000046952678,0.00005616507,0.00010221362,0.024177492,0.00032058818,0.0003814029,0.9738692,0.0001672501],"about_ca_topic_score_codex":0.000015564972,"about_ca_topic_score_gemma":2.4480178e-7,"teacher_disagreement_score":0.8575018,"about_ca_system_score_codex":0.000062132436,"about_ca_system_score_gemma":0.000006483038,"threshold_uncertainty_score":0.9995051},"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":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.77363e-7,0.00001477361,0.031392183,0.0003170619,0.000042777967,0.00010482588,0.96795166,0.00010047148,0.00007587517],"genre_scores_gemma":[0.0002434385,3.44156e-8,0.17815585,0.00008793475,0.00014674643,0.0011255433,0.81984043,0.0000059763474,0.0003940202],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99940306,0.0000066636635,0.000099424855,0.00025001453,0.00013762643,0.00010322378],"domain_scores_gemma":[0.99873066,0.0009379926,0.00003411553,0.00013982937,0.00012495829,0.000032435808],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00001843424,0.00006744875,0.00005932872,0.0000615034,0.00007830698,0.00009285695,0.0002388859,0.000048240814,0.8841665],"category_scores_gemma":[0.00034817692,0.00006234201,0.000050654584,0.00035769976,0.000005452818,0.00017645552,0.00005295278,0.00007735634,0.0009037242],"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":[8.4299376e-7,0.00001742641,5.763972e-9,0.000027396967,0.0000041153485,5.1310883e-7,0.0000051854445,0.00006514959,0.00001736309,0.0017275795,0.91568494,0.08244951],"study_design_scores_gemma":[0.0000056385984,0.000023315579,0.00002270227,0.0004222604,0.0000010837364,0.0000022091783,9.3811417e-7,0.44136488,0.00072053866,0.00095209613,0.5564327,0.000051613923],"about_ca_topic_score_codex":0.000001195581,"about_ca_topic_score_gemma":0.000002052462,"teacher_disagreement_score":0.88326275,"about_ca_system_score_codex":0.000015725935,"about_ca_system_score_gemma":0.00016658088,"threshold_uncertainty_score":0.9998742},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85378337,0.0026653751,0.13755634,0.00078690227,0.0011442463,0.0005155968,0.0025206024,0.00016530906,0.00086228445],"genre_scores_gemma":[0.93343127,0.0053209756,0.058783434,0.0003483533,0.0005026139,0.000087976034,0.0011853611,0.00006634838,0.00027367764],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99692196,0.00015702679,0.0009122697,0.00078623963,0.0008320895,0.00039043685],"domain_scores_gemma":[0.99604577,0.0003426777,0.0008371757,0.0024024444,0.00014913999,0.0002227965],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001426569,0.00025239892,0.000555909,0.000529699,0.00023286144,0.0012639092,0.0127793765,0.000071663686,0.00067534734],"category_scores_gemma":[0.00014753663,0.00023996283,0.000099657096,0.0013004192,0.00009624435,0.0030039954,0.008074092,0.00022587192,0.000034679488],"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":[0.000032711043,0.00046467356,0.27625537,0.00007694589,0.00045535155,0.00008905918,0.0008387071,0.00021716638,0.06510288,0.0007347184,0.19452451,0.4612079],"study_design_scores_gemma":[0.0009242457,0.000019398223,0.9260212,0.000756027,0.000089912144,0.000013121607,0.00033242683,0.029566178,0.016448459,0.0071725766,0.017954435,0.0007020231],"about_ca_topic_score_codex":0.003425541,"about_ca_topic_score_gemma":0.000115007,"teacher_disagreement_score":0.64976585,"about_ca_system_score_codex":0.00004831811,"about_ca_system_score_gemma":0.00013580671,"threshold_uncertainty_score":0.99994844},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044691853,0.000020680565,0.9520725,0.0002647698,0.000072910756,0.00015973498,0.00013041393,0.00023258667,0.0023545248],"genre_scores_gemma":[0.99265164,4.9768727e-7,0.007109885,0.000104220606,0.000027303602,0.000023043825,0.000038297378,0.0000027685378,0.000042326028],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993803,0.000029789511,0.00025135113,0.00013977771,0.00008743629,0.000111369875],"domain_scores_gemma":[0.99964845,0.000009092115,0.00008604454,0.00016836273,0.000023656476,0.00006441368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014873953,0.00008050384,0.00010503558,0.00008496933,0.00007767676,0.00031642395,0.00020882544,0.000017794431,0.0000014154086],"category_scores_gemma":[0.000019179326,0.00006805844,0.000013188982,0.00029051007,0.000011669149,0.002134223,0.00025770374,0.00008177721,0.00018703187],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019088116,0.000009296395,0.5596055,0.00089390896,0.000031084353,0.000008158859,0.32131797,0.0002854916,0.000007006801,0.046446174,0.00039612438,0.07098022],"study_design_scores_gemma":[0.0006160664,0.000039500115,0.021406371,0.0000984851,0.000004215805,0.000021521251,0.0039954735,0.9579878,0.00008851047,0.0000010578282,0.015539504,0.00020153378],"about_ca_topic_score_codex":0.000013001488,"about_ca_topic_score_gemma":3.4554114e-7,"teacher_disagreement_score":0.9577023,"about_ca_system_score_codex":0.00001701985,"about_ca_system_score_gemma":0.000020400106,"threshold_uncertainty_score":0.30512834},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030331262,0.000121277044,0.000015832376,0.00013897529,0.000008073258,0.00017654784,0.99646664,0.0000152858,0.000024260646],"genre_scores_gemma":[0.72776896,0.0000018332094,0.00051156536,0.000060265877,0.000015253819,0.00035150675,0.27124393,0.0000058021405,0.000040855928],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9993972,0.000020200458,0.00017120452,0.00016069537,0.00013180624,0.00011889485],"domain_scores_gemma":[0.99890536,0.000562352,0.000103854516,0.00021551026,0.00006912829,0.00014378397],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000027583472,0.000064785614,0.00009161391,0.00007644719,0.00007054525,0.000032768054,0.00025112892,0.000027884405,0.20584396],"category_scores_gemma":[0.0005014375,0.000046558387,0.00005263572,0.00019356894,0.000017841116,0.00014640624,0.00009393359,0.000072859075,0.000009857877],"study_design_candidate":"not_applicable","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":[8.033625e-7,0.0000062801564,0.00032735104,0.00023401722,0.000017426739,0.0000024315746,0.00045770308,0.00003698376,0.0000052172013,0.00003804114,0.9930477,0.0058260276],"study_design_scores_gemma":[0.00025041087,0.0003907208,0.65496635,0.0074566123,0.000010340104,0.00008430197,0.00036924705,0.038883492,0.00015525898,0.000299503,0.29679087,0.00034292386],"about_ca_topic_score_codex":0.032853276,"about_ca_topic_score_gemma":0.019834941,"teacher_disagreement_score":0.7252227,"about_ca_system_score_codex":0.000107023974,"about_ca_system_score_gemma":0.001116507,"threshold_uncertainty_score":0.9980505},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.105475746,0.0027724267,0.004408759,0.0003392676,0.0068117958,0.0060587986,0.08088937,0.0035818536,0.789662],"genre_scores_gemma":[0.07016315,0.0005649649,0.7964846,0.00037605193,0.00035317344,0.00091519253,0.09053391,0.0003402428,0.04026874],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99473184,0.00015044386,0.00086331525,0.0022566998,0.0013280504,0.00066963333],"domain_scores_gemma":[0.9939452,0.00019950466,0.0006919921,0.0045641554,0.00027203638,0.00032713162],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011027751,0.0006786632,0.00052247284,0.00043212247,0.0012732367,0.00048119633,0.0046449215,0.0003128277,0.00004594124],"category_scores_gemma":[0.000090130125,0.0006660638,0.000082640705,0.0009878716,0.00004387769,0.0034155077,0.0012260802,0.0008897492,0.0004367152],"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":[0.000029052768,0.00021839033,0.00000749869,0.00027858617,0.00030767894,0.000120404446,0.000007699933,0.00016277673,0.00016938137,0.6346974,0.00034075492,0.36366037],"study_design_scores_gemma":[0.0013405001,0.00012336225,0.0009912531,0.0017883133,0.00041805385,0.00016428772,0.0006192671,0.033167943,0.0003914876,0.0009900312,0.95789784,0.0021076738],"about_ca_topic_score_codex":0.00011359796,"about_ca_topic_score_gemma":0.00046916795,"teacher_disagreement_score":0.9575571,"about_ca_system_score_codex":0.00032126246,"about_ca_system_score_gemma":0.00008837181,"threshold_uncertainty_score":0.9995791},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028299367,0.000082296385,0.21606635,0.006326544,0.0010546496,0.00042450533,0.00014076229,0.0002562943,0.7473492],"genre_scores_gemma":[0.32906553,0.000033608623,0.64917,0.00029990877,0.010099149,0.00006391382,0.000019827046,0.000017352511,0.011230739],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99948823,0.000011254544,0.00011251291,0.00015319184,0.0001414874,0.00009329305],"domain_scores_gemma":[0.99947983,0.00002944764,0.0000456887,0.0003862955,0.000024743757,0.000033992746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000086645094,0.00004756261,0.000074045485,0.00002871171,0.00003807199,0.000053112726,0.00046885782,0.000020059599,0.000077659046],"category_scores_gemma":[0.0000084312405,0.000041813277,0.000016922055,0.00008978777,0.000018506089,0.00013936679,0.000071163086,0.000041102743,0.00047906957],"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":[0.0000012666318,0.00008943495,0.000011193883,0.000008361431,0.000005454024,6.25766e-7,0.0003682436,0.00015862138,0.0014157706,0.2863578,0.10471441,0.6068688],"study_design_scores_gemma":[0.000102000085,0.000044732635,0.00032438387,0.000022162227,0.0000018613805,0.0000029061823,0.00001922936,0.070787944,0.003700695,0.0009453104,0.9239737,0.00007509273],"about_ca_topic_score_codex":0.00000737383,"about_ca_topic_score_gemma":0.0000010908168,"teacher_disagreement_score":0.8192593,"about_ca_system_score_codex":0.000012462449,"about_ca_system_score_gemma":0.00001638811,"threshold_uncertainty_score":0.615763},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61575955,0.00005718851,0.3747875,0.0020371506,0.00006501337,0.000347362,0.005749498,0.00015612051,0.0010406214],"genre_scores_gemma":[0.66601366,0.00007673436,0.3242393,0.000058229056,0.00016421385,3.0622277e-7,0.0007198118,0.000040692634,0.008687051],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99811876,0.00008438943,0.00023721629,0.00073623034,0.0004246192,0.00039878272],"domain_scores_gemma":[0.99745786,0.00023825739,0.00059701444,0.0012417451,0.0003053908,0.000159703],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007693208,0.00023034375,0.0004274466,0.00022188896,0.00044378996,0.000039803785,0.002366655,0.00019778137,0.00011142528],"category_scores_gemma":[0.000057657362,0.00027973723,0.00018013103,0.00028741788,0.000167836,0.0003035431,0.000944822,0.00013737279,0.0004977298],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010850049,0.0028854602,0.19142362,0.00062841136,0.002539879,0.00009037829,0.29789346,0.0066514057,0.0017153388,0.010715273,0.030620964,0.45375082],"study_design_scores_gemma":[0.008954962,0.00024245329,0.014787453,0.0004014033,0.0006205553,0.000016383576,0.14744945,0.6553786,0.00015634557,0.0012049406,0.1690863,0.001701164],"about_ca_topic_score_codex":0.0021981765,"about_ca_topic_score_gemma":0.0008415776,"teacher_disagreement_score":0.6487272,"about_ca_system_score_codex":0.00012276467,"about_ca_system_score_gemma":0.00012699675,"threshold_uncertainty_score":0.9999655},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036281846,0.00002377345,0.95998317,0.00014684681,0.000046985446,0.00006839931,0.0000031879529,0.00005658536,0.0033892195],"genre_scores_gemma":[0.52543473,0.0000017226854,0.47435528,0.000009942907,0.00004276438,0.000012626853,0.0000051505003,0.0000033707488,0.00013443516],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994529,0.0000082939,0.00014590297,0.00016529254,0.0001099148,0.00011771256],"domain_scores_gemma":[0.999444,0.00021513224,0.00006904289,0.00021267588,0.000042424865,0.000016703149],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021296246,0.000047364283,0.00007952913,0.00004714899,0.000110761925,0.000056031913,0.00034982638,0.000020527377,0.000006942465],"category_scores_gemma":[0.000045756027,0.000043753353,0.000037432917,0.00015689674,0.000014252872,0.00015764676,0.00009259935,0.000042164764,0.0000042400125],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024407125,0.000030369336,0.00056626386,0.0000060545876,0.0000029632772,5.9698823e-7,0.000102544334,0.0005998409,0.034794938,0.07748275,0.0021782327,0.884233],"study_design_scores_gemma":[0.00055481924,0.00008009579,0.0060779667,0.000064990476,0.0000075605067,0.0000066044813,0.000031558186,0.8559715,0.013280731,0.08167879,0.04207792,0.00016741753],"about_ca_topic_score_codex":0.000024854784,"about_ca_topic_score_gemma":0.000008164101,"teacher_disagreement_score":0.88406557,"about_ca_system_score_codex":0.000008114646,"about_ca_system_score_gemma":0.0000158867,"threshold_uncertainty_score":0.178421},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29241621,0.0023824961,0.013237963,0.00018756732,0.012640203,0.006042466,0.10454571,0.005628845,0.56291854],"genre_scores_gemma":[0.046494942,0.00013487448,0.91138995,0.00016435768,0.0002456659,0.00018202781,0.033458073,0.0001906971,0.0077394284],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9945038,0.00018354882,0.0010752945,0.0023040806,0.0012205333,0.00071276847],"domain_scores_gemma":[0.99394435,0.00018178826,0.00078090245,0.0045195385,0.0002469938,0.00032644148],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0013777907,0.00068343745,0.0005466341,0.00051933934,0.0017085483,0.00037677525,0.004880353,0.00038178952,0.000046354882],"category_scores_gemma":[0.00012077289,0.00077745115,0.00014041655,0.0010340031,0.000035688434,0.003530198,0.0019335421,0.00087321945,0.00039781712],"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":[0.000011704818,0.00012942396,0.0000033439903,0.00035411154,0.00019580526,0.00009345482,0.000006096325,0.000106345455,0.0006865691,0.60738313,0.000084596184,0.3909454],"study_design_scores_gemma":[0.0018169119,0.00007854136,0.00086692686,0.0041317735,0.0009282939,0.00033268155,0.0016671735,0.36348146,0.00211067,0.0016464771,0.61919606,0.0037430208],"about_ca_topic_score_codex":0.00010560821,"about_ca_topic_score_gemma":0.0002354007,"teacher_disagreement_score":0.898152,"about_ca_system_score_codex":0.00071869465,"about_ca_system_score_gemma":0.00009411147,"threshold_uncertainty_score":0.9995911},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05104456,0.00068581215,0.015574029,0.038649127,0.0020394223,0.0010981802,0.0012100305,0.00022648035,0.88947237],"genre_scores_gemma":[0.7398179,0.00021451319,0.06558917,0.0011606592,0.00033248824,0.00005972396,0.000050834224,0.000037592097,0.19273709],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998734,0.000008134993,0.00024155731,0.00052232563,0.0002947034,0.00019928742],"domain_scores_gemma":[0.9985779,0.00015455288,0.00013269881,0.000923684,0.00013293291,0.000078257945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012761667,0.00014236638,0.00013554381,0.000040765433,0.00014332325,0.00029798364,0.003520759,0.000034719596,0.0001344581],"category_scores_gemma":[0.00012899132,0.000099336896,0.000017648186,0.00024670694,0.000081007296,0.000986067,0.0016646124,0.0001134355,0.000033361157],"study_design_candidate":"not_applicable","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":[0.0000017687024,0.00012860724,0.00059360446,0.000012649636,0.000031511147,7.461757e-7,0.00057804846,0.0000014162457,0.00017934758,0.04733937,0.9241074,0.027025579],"study_design_scores_gemma":[0.00058982044,0.00007657371,0.010780748,0.00021251867,0.000026886835,0.000030848358,0.0003802266,0.63352364,0.0012583481,0.00037971674,0.35223585,0.0005048254],"about_ca_topic_score_codex":0.037872367,"about_ca_topic_score_gemma":0.09998615,"teacher_disagreement_score":0.69673526,"about_ca_system_score_codex":0.000038988255,"about_ca_system_score_gemma":0.00013602036,"threshold_uncertainty_score":0.9685345},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007241667,0.000014128977,0.97125185,0.026626062,0.00009049464,0.0001655271,0.0004097978,0.0001231063,0.0012466132],"genre_scores_gemma":[0.0033531857,0.000013437338,0.9947166,0.00077856553,0.0003609469,0.000049460563,0.0005896625,0.000009784851,0.00012835208],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99868274,0.000018399945,0.00018113913,0.0006781105,0.00018149277,0.00025809702],"domain_scores_gemma":[0.99566174,0.00046707378,0.00007736776,0.0036581205,0.000035531935,0.00010014136],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037631256,0.00009188544,0.00011380638,0.000027846056,0.00015295073,0.0002451327,0.0035303084,0.000057482677,0.000038997965],"category_scores_gemma":[0.0004613077,0.000086397784,0.00001588306,0.00016530261,0.000035727462,0.0014030184,0.002047958,0.00013248017,0.00011548765],"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":[0.0000027638116,0.000099347366,0.000016042111,0.0000044070944,0.000016982363,0.0000021568778,0.00013929162,0.000016286385,0.000044125263,0.27724674,0.27481493,0.4475969],"study_design_scores_gemma":[0.00009701198,0.000014434047,0.000033269527,0.000009296931,0.000008052847,0.000010139238,0.000017340377,0.6324194,0.000009243297,0.0058942204,0.36140475,0.00008286197],"about_ca_topic_score_codex":0.0000031047518,"about_ca_topic_score_gemma":0.000006836272,"teacher_disagreement_score":0.63240314,"about_ca_system_score_codex":0.000012184281,"about_ca_system_score_gemma":0.0001047906,"threshold_uncertainty_score":0.65602505},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01081458,0.0041500996,0.115305506,0.17088456,0.00034058344,0.0012819723,0.0011855979,0.0004364363,0.6956007],"genre_scores_gemma":[0.52528065,0.0016883141,0.05306113,0.002358824,0.002469672,0.0014466685,0.00067998504,0.0006711205,0.41234362],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9943112,0.0013534612,0.0009272711,0.0012513718,0.001316135,0.00084053323],"domain_scores_gemma":[0.9928484,0.004226376,0.00093444565,0.0011054701,0.00017101534,0.00071429537],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00175079,0.0008363408,0.00067150575,0.0008305439,0.0010890964,0.0010391563,0.0022734543,0.00035116897,0.0005450715],"category_scores_gemma":[0.0017822527,0.0009165666,0.00034682735,0.0011718186,0.00082847785,0.001112788,0.0011104655,0.0006739579,0.00012424542],"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":true,"study_design_scores_codex":[0.00007525355,0.002984715,0.003171968,0.0002701179,0.00032628895,0.00006599185,0.025945771,0.00057001365,0.0029957395,0.27920988,0.6771266,0.0072576534],"study_design_scores_gemma":[0.0019284205,0.00020639005,0.024143524,0.0006294256,0.00010767532,0.0003619402,0.001790481,0.02801067,0.00057894876,0.0045248508,0.9367268,0.0009908483],"about_ca_topic_score_codex":0.5808292,"about_ca_topic_score_gemma":0.8631005,"teacher_disagreement_score":0.51446605,"about_ca_system_score_codex":0.016431427,"about_ca_system_score_gemma":0.25109354,"threshold_uncertainty_score":0.99999785},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051788595,0.00077594374,0.059666168,0.020278575,0.0004915595,0.0005653804,0.0009249413,0.000046187986,0.91207236],"genre_scores_gemma":[0.13173206,0.001284624,0.2099457,0.0022805165,0.00043730577,0.00010702917,0.0001649993,0.00014697229,0.6539008],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979315,0.0001453686,0.00029073108,0.0004444786,0.0008830377,0.00030487552],"domain_scores_gemma":[0.99860924,0.00037073632,0.00029697988,0.00047264807,0.0000020482055,0.00024836385],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00004463953,0.00025955142,0.00022881704,0.000035234152,0.00026157073,0.00016770576,0.00064168015,0.00009062319,0.000107950036],"category_scores_gemma":[0.000016347203,0.00026712808,0.000022914717,0.00014698878,0.00026749625,0.0005444406,0.00023778857,0.00027762144,2.4652515e-8],"study_design_candidate":"not_applicable","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":[0.000018258736,0.0000614214,0.0019650029,0.00022371669,0.00004817657,0.000017094098,0.00031291816,0.000054641056,0.013324893,0.810773,0.0038111808,0.16938971],"study_design_scores_gemma":[0.00019984487,0.000040581912,0.095806725,0.00033671164,0.00003419049,0.000034276258,0.00024781155,0.027249455,0.017461471,0.004352003,0.85384464,0.00039229434],"about_ca_topic_score_codex":0.012250123,"about_ca_topic_score_gemma":0.06399959,"teacher_disagreement_score":0.85003346,"about_ca_system_score_codex":0.000011862557,"about_ca_system_score_gemma":0.004528399,"threshold_uncertainty_score":0.99997807},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08058751,0.003894267,0.051219814,0.12083698,0.003227198,0.03451867,0.00035125905,0.017324755,0.68803954],"genre_scores_gemma":[0.37154928,0.0006325101,0.0031066642,0.0013512694,0.0013869642,0.000028802522,0.0011364514,0.0047021178,0.6161059],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969514,0.00040728532,0.00027481277,0.00087343826,0.0008579931,0.00063509156],"domain_scores_gemma":[0.99788016,0.000058090733,0.00014951667,0.001467004,0.00024978194,0.00019541844],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0011158349,0.00030775197,0.00024899945,0.0004706798,0.00063521974,0.0014985107,0.0037437172,0.00011779389,0.0019082446],"category_scores_gemma":[0.000038566308,0.00022461716,0.000052043913,0.0016421118,0.00018153434,0.00038775083,0.001174357,0.0005232661,0.0024217519],"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":[0.000043795924,0.00053506513,0.000044081444,0.0002442966,0.00020752728,0.000120108976,0.0040537505,0.00018935103,0.00006934658,0.31944796,0.63338494,0.04165979],"study_design_scores_gemma":[0.0009111063,0.00035564494,0.00045842404,0.00025353517,0.000015866977,0.000028028891,0.0001531772,0.00020807731,0.00045154526,0.0010495707,0.9955837,0.0005312988],"about_ca_topic_score_codex":0.00020185782,"about_ca_topic_score_gemma":0.000040388903,"teacher_disagreement_score":0.3621988,"about_ca_system_score_codex":0.00020603146,"about_ca_system_score_gemma":0.00005640791,"threshold_uncertainty_score":0.999538},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7836527,0.00022782486,0.06765205,0.05843053,0.03737389,0.00245879,0.0041342364,0.0011550708,0.04491487],"genre_scores_gemma":[0.8080521,0.00039235462,0.16379103,0.0051457835,0.00092710485,0.00006997928,0.007174518,0.00007894615,0.014368178],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99751383,0.000056063567,0.00042238,0.0012544707,0.00044048377,0.00031274557],"domain_scores_gemma":[0.99677,0.00037855865,0.00025381712,0.0022064368,0.00013890259,0.00025223888],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00043421492,0.0002699593,0.00020901843,0.00009842595,0.000294637,0.00070291996,0.0023917137,0.000091009955,0.000474777],"category_scores_gemma":[0.00049863703,0.0002520297,0.000014371144,0.00022235069,0.000046526497,0.0023711,0.0016946248,0.00034053347,0.000012493763],"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":[0.000024199147,0.00011623118,0.0029642012,0.000009875525,0.0000888198,0.00001097836,0.0003721558,0.0000069808466,0.00029204934,0.00027207332,0.6861676,0.30967486],"study_design_scores_gemma":[0.00061432715,0.000048911344,0.05305733,0.00020617284,0.00003266873,0.00007571256,0.00085805776,0.37952203,0.00007518766,0.0000039852434,0.565065,0.0004405853],"about_ca_topic_score_codex":0.054606803,"about_ca_topic_score_gemma":0.3403945,"teacher_disagreement_score":0.37951505,"about_ca_system_score_codex":0.000120173274,"about_ca_system_score_gemma":0.0002140054,"threshold_uncertainty_score":0.9999932},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023265742,0.000033651086,0.94454944,0.005763591,0.000022959879,0.000018982519,0.0000036507427,0.00013392555,0.04924114],"genre_scores_gemma":[0.037694927,0.0000062865042,0.9466322,0.0014993926,0.0000589001,0.00001052,0.00000739872,0.000002146525,0.014088249],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9997145,0.0000023832936,0.00004604408,0.00011184397,0.000053439595,0.000071794275],"domain_scores_gemma":[0.99968797,0.000009976904,0.000008668459,0.00025073809,0.000008906955,0.00003373652],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00003580805,0.000026736912,0.00002401242,0.00000918331,0.000042488722,0.00006557264,0.00038728962,0.000009263654,0.000102201186],"category_scores_gemma":[0.0000014352489,0.000020963695,0.000008031974,0.00008756913,0.00000774046,0.00024300361,0.00006035328,0.000020500125,0.0007824746],"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":[2.5432294e-8,0.000017563938,0.0000055886803,1.3109245e-7,8.287812e-7,8.413301e-8,0.000022320353,7.7849955e-7,0.0003132353,0.10816317,0.5456065,0.3458698],"study_design_scores_gemma":[0.00003587931,0.000004147136,0.000034372806,3.8980986e-7,2.7977194e-7,0.0000017168978,0.0000015637969,0.109368905,0.004041309,0.00032698116,0.8861462,0.000038298036],"about_ca_topic_score_codex":0.000009358203,"about_ca_topic_score_gemma":0.0000018402741,"teacher_disagreement_score":0.3458315,"about_ca_system_score_codex":0.0000054429233,"about_ca_system_score_gemma":0.000006356855,"threshold_uncertainty_score":0.9999955},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01364246,0.0000039875345,0.9217958,0.0010405249,0.00013867645,0.00004785385,0.0000020391503,0.00021471699,0.063113935],"genre_scores_gemma":[0.37220228,0.0000026676548,0.6104453,0.0008411334,0.00011877451,0.0000075358503,0.000012857478,0.000006218426,0.016363204],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99924046,0.000005224165,0.00014144107,0.00019554204,0.00020338646,0.00021396881],"domain_scores_gemma":[0.9994432,0.00006882032,0.00006481507,0.00030971545,0.000050411545,0.00006304252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077332027,0.000055082564,0.00006122824,0.00004557793,0.000089565045,0.000118476586,0.00040242355,0.000040447252,0.000047813606],"category_scores_gemma":[0.000028805305,0.00004994587,0.000021101896,0.00023745743,0.0000066190787,0.00033600166,0.00010729265,0.000049784245,0.00016581993],"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":[0.0000016783995,0.00012209297,0.15046549,0.0000033883243,0.000040555944,0.0000100466905,0.0012471386,0.000008662283,0.0008293962,0.19342344,0.13898858,0.51485956],"study_design_scores_gemma":[0.0011795285,0.00024166568,0.16642453,0.000025951078,0.000035151013,0.00007211754,0.0005519139,0.14952585,0.012009073,0.005017195,0.6638383,0.0010787381],"about_ca_topic_score_codex":0.000020473115,"about_ca_topic_score_gemma":0.00003147148,"teacher_disagreement_score":0.5248497,"about_ca_system_score_codex":0.000047210775,"about_ca_system_score_gemma":0.000026674647,"threshold_uncertainty_score":0.21313351},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05095464,0.0000065575155,0.9439292,0.00088721246,0.00007713201,0.0001174288,0.0000038592902,0.00009007412,0.0039338963],"genre_scores_gemma":[0.88959867,0.000002443537,0.10869574,0.00009338664,0.000024575982,0.000056931003,0.000012251977,0.000004057711,0.0015119183],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99940366,0.000015018014,0.00010599416,0.00018101734,0.00008147083,0.00021282441],"domain_scores_gemma":[0.9994769,0.000023290582,0.000035769564,0.0003813449,0.00002218665,0.000060510476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014174309,0.00006993494,0.00007082131,0.00007590907,0.000054849308,0.00014298632,0.00029575385,0.0000258492,0.0000040477394],"category_scores_gemma":[0.000008992633,0.00005109638,0.000019063315,0.00037038574,0.000023072462,0.0016210708,0.00010573383,0.00007770018,0.000020144005],"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":[0.000008750351,0.000626383,0.002931451,0.000008996122,0.000017674349,0.0000011524055,0.00070810394,0.00003934052,0.0052976776,0.8910109,0.0010229303,0.09832669],"study_design_scores_gemma":[0.0010162832,0.00010537296,0.15118396,0.000038073566,0.00000951862,0.000023196715,0.00039210173,0.8421918,0.0009926356,0.0013873221,0.0022784579,0.0003812731],"about_ca_topic_score_codex":0.00013663215,"about_ca_topic_score_gemma":0.000080033344,"teacher_disagreement_score":0.8896235,"about_ca_system_score_codex":0.000028225066,"about_ca_system_score_gemma":0.000023844013,"threshold_uncertainty_score":0.208365},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011284825,0.000016986009,0.9699628,0.003431214,0.00004389118,0.00005326146,7.902396e-7,0.00015370901,0.01505257],"genre_scores_gemma":[0.55394363,0.0000016418602,0.44540563,0.00040681864,0.000034764365,0.000009602382,5.38908e-7,0.000002159644,0.00019519294],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99952817,0.0000050057106,0.00010141698,0.00016680876,0.00006596097,0.00013263032],"domain_scores_gemma":[0.9996503,0.00001603742,0.000014900807,0.00028787073,0.000007730063,0.000023164988],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009999612,0.000042730015,0.00004576169,0.00004782673,0.000038040478,0.0001095881,0.00041266278,0.000015058083,0.00003090096],"category_scores_gemma":[0.0000044202106,0.000039687566,0.0000106407115,0.00019212402,0.0000065988934,0.00038892715,0.00014763785,0.000051175575,0.00019824413],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.8584463e-7,0.000039553073,0.0003219382,0.0000021803896,0.0000013800834,0.000003289049,0.00064467744,0.0004164058,0.00063392456,0.078010716,0.0013528041,0.91857296],"study_design_scores_gemma":[0.00010365715,0.0000065361105,0.00490131,0.00001883514,4.209551e-7,0.000010292621,0.000030996784,0.928559,0.00034041263,0.0005900615,0.06533046,0.00010798839],"about_ca_topic_score_codex":0.000023223012,"about_ca_topic_score_gemma":0.000051951436,"teacher_disagreement_score":0.9281426,"about_ca_system_score_codex":0.000019233348,"about_ca_system_score_gemma":0.000011999266,"threshold_uncertainty_score":0.25480932},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000021288915,0.00009277053,0.98843384,0.0022880218,0.00062806817,0.0005960969,0.001682483,0.000099575795,0.006157858],"genre_scores_gemma":[0.25192818,0.0007548082,0.4666351,0.009740481,0.013924331,0.001340033,0.24043117,0.00041369014,0.0148322135],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980308,0.00007316465,0.00042898173,0.00087657606,0.00022113774,0.00036936754],"domain_scores_gemma":[0.9989043,0.00020132327,0.0002416368,0.0005320287,0.00007129211,0.000049450922],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00032410384,0.00035204494,0.00041224962,0.00018522849,0.0001961252,0.0001408261,0.0007637352,0.00054895744,0.0000523455],"category_scores_gemma":[0.000030162064,0.00034186707,0.000052650015,0.00045003212,0.00011755487,0.00016705004,0.00043608062,0.0010857821,0.000005756404],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003764273,0.000046730256,0.00008078261,0.000030819923,0.000041385145,0.000016635433,0.00023711685,0.00060565025,0.0000015476072,0.044115726,0.011561336,0.9432246],"study_design_scores_gemma":[0.0024792056,0.00019569423,0.0016230597,0.0010191569,0.00014032886,0.000014293894,0.000011435389,0.2831646,0.000066404675,0.08890782,0.620188,0.0021899734],"about_ca_topic_score_codex":0.0002880651,"about_ca_topic_score_gemma":0.0012734887,"teacher_disagreement_score":0.9410347,"about_ca_system_score_codex":0.00018577478,"about_ca_system_score_gemma":0.00021979492,"threshold_uncertainty_score":0.9999033},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5857655,0.00014330211,0.056639872,0.0028964235,0.00036405041,0.0016386145,0.0013748442,0.00019721803,0.35098022],"genre_scores_gemma":[0.6281534,0.0004582781,0.1727776,0.000077351186,0.0018969851,0.000001068324,0.000082496685,0.0001030314,0.19644982],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9975264,0.00023785183,0.0002083301,0.0008338348,0.00072726293,0.00046633967],"domain_scores_gemma":[0.9978762,0.00016855147,0.00028499105,0.0009713641,0.00040159465,0.00029727683],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0013231824,0.00021471517,0.0003698981,0.0004891179,0.00078018947,0.0000868492,0.0034333088,0.00016065905,0.009677136],"category_scores_gemma":[0.00006821343,0.00026950188,0.00011557692,0.00095569884,0.0011425907,0.00051919173,0.00246038,0.0004276808,0.0017157645],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014804495,0.0017068278,0.010326647,0.00022178737,0.0006626375,0.0007131656,0.23636697,0.00006354272,0.0006479911,0.020751871,0.1038204,0.6232377],"study_design_scores_gemma":[0.0017117395,0.00093714625,0.0018313392,0.00027866638,0.000098488075,0.00006633807,0.72800493,0.009186634,0.00035217038,0.0017742154,0.25483844,0.00091992185],"about_ca_topic_score_codex":0.0023278059,"about_ca_topic_score_gemma":0.00077870546,"teacher_disagreement_score":0.6223178,"about_ca_system_score_codex":0.000045268476,"about_ca_system_score_gemma":0.00021949493,"threshold_uncertainty_score":0.99997574},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24907075,0.00007740646,0.7442694,0.0006062827,0.000061117484,0.00060066156,0.000055180317,0.0000045229244,0.0052546966],"genre_scores_gemma":[0.6446824,0.000008201983,0.35464993,0.000010637102,0.0000050797084,0.000054677876,0.000014766212,0.0000020556054,0.000572243],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994629,0.000022411698,0.00017677617,0.00020301677,0.00007593425,0.000058953156],"domain_scores_gemma":[0.99915886,0.00005146099,0.00012384179,0.00049632136,0.00015280354,0.000016713644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021210534,0.00005188727,0.00011751043,0.000054279295,0.0000628127,0.000059449634,0.00045732272,0.00001338337,0.000009096411],"category_scores_gemma":[0.00002079588,0.000043573604,0.00001078623,0.00052540033,0.000053865577,0.0006251271,0.00019875466,0.000029041417,0.000008145145],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027249722,0.00034486188,0.00011841936,0.00004867247,0.00011643182,0.000037801365,0.009911517,0.00042179401,0.0037304636,0.035379015,0.0007631182,0.9491007],"study_design_scores_gemma":[0.0098556485,0.0016251891,0.0012573352,0.0015726127,0.00043868364,0.0004240847,0.0495335,0.34159568,0.49441567,0.008609709,0.08929031,0.001381574],"about_ca_topic_score_codex":0.00010545308,"about_ca_topic_score_gemma":0.00009474351,"teacher_disagreement_score":0.9477191,"about_ca_system_score_codex":0.000013615445,"about_ca_system_score_gemma":0.00010966321,"threshold_uncertainty_score":0.177688},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.1225141e-8,0.00004710144,0.49237826,0.0002625213,0.000038895505,0.000101472375,0.00012720958,0.00020272033,0.50684184],"genre_scores_gemma":[0.0000012457792,0.00007304121,0.5184093,0.00017509043,0.0000947731,0.000019447625,0.00031351158,0.000014967904,0.48089862],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987013,0.0000031500076,0.00021101715,0.00073463575,0.00019028588,0.00015966194],"domain_scores_gemma":[0.9961877,0.000047759993,0.00010475601,0.0035486245,0.000038627324,0.000072569375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020070317,0.000186286,0.00017327191,0.000098761186,0.00008054212,0.00017436649,0.0039548515,0.00015482456,0.00024168854],"category_scores_gemma":[0.000008757628,0.00017198904,0.000031856976,0.00005390495,0.000035173685,0.0003395639,0.0022223403,0.00018460282,0.00035817767],"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":[8.853503e-8,0.000005281131,1.895526e-7,0.0000030462288,0.000009784591,0.000014369959,0.000007627185,6.671303e-8,0.000004246022,0.5591492,0.11572268,0.32508343],"study_design_scores_gemma":[0.000027041033,0.000012176456,6.9168846e-7,0.000053791413,0.000007508066,0.00006687297,0.0000013133638,0.009489945,0.000009286309,0.011807357,0.97830075,0.00022327335],"about_ca_topic_score_codex":0.000013659164,"about_ca_topic_score_gemma":0.0000124420085,"teacher_disagreement_score":0.8625781,"about_ca_system_score_codex":0.000017972707,"about_ca_system_score_gemma":0.000083773106,"threshold_uncertainty_score":0.7349164},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007041269,0.0018405056,0.6471066,0.000018447912,0.00043988423,0.0007642426,0.0014224475,0.000090209185,0.34824726],"genre_scores_gemma":[0.12938148,0.000051216437,0.84507775,0.00035971712,0.00084322575,0.00051780324,0.00016805732,0.00011638942,0.023484366],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99707574,0.000033343003,0.00068592775,0.0006002745,0.0013756256,0.00022908534],"domain_scores_gemma":[0.9970285,0.00056612596,0.0005135143,0.0009974105,0.0008198421,0.00007459025],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014218932,0.00029089104,0.00043418957,0.00008946386,0.00014482456,0.00026906034,0.0011134244,0.00025572663,0.0000044746503],"category_scores_gemma":[0.00021939928,0.00027637774,0.00016716689,0.000028804372,0.00005089856,0.00013977707,0.00019598185,0.000094035255,0.00002812215],"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":[0.0000036814179,0.0000059475296,7.994382e-8,0.0000089707755,0.00001839216,3.807625e-7,0.000023377794,0.00003077729,0.0000023659275,0.5275772,0.0063559595,0.46597284],"study_design_scores_gemma":[0.00026803894,0.00009969139,0.0000053578024,0.0012928502,0.00011784725,0.00001620866,0.000019755667,0.05181824,0.000009419868,0.9027817,0.0432591,0.00031175566],"about_ca_topic_score_codex":0.0000370473,"about_ca_topic_score_gemma":0.000012363012,"teacher_disagreement_score":0.46566108,"about_ca_system_score_codex":0.0002524536,"about_ca_system_score_gemma":0.00032040387,"threshold_uncertainty_score":0.9999688},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64634603,0.000052488063,0.20803648,0.03100269,0.00097956,0.0017412187,0.000030148642,0.00047241987,0.11133898],"genre_scores_gemma":[0.95324445,0.000012566574,0.045900304,0.00029453746,0.00005843819,0.000097742966,6.342208e-7,0.0000091640395,0.00038219566],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998444,0.000008560461,0.00041438453,0.0004532009,0.00037037648,0.00030947363],"domain_scores_gemma":[0.998495,0.00006530479,0.00029001894,0.00038170675,0.00066915835,0.00009885181],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002529046,0.00017907938,0.00019733397,0.00008945903,0.00020704113,0.00045801193,0.0025391832,0.00006397749,0.00012448127],"category_scores_gemma":[0.00023319988,0.00013135718,0.00008399993,0.0006361335,0.00020833664,0.00066553935,0.0005065596,0.00017623654,0.000346082],"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":[0.0000025872491,0.00007010172,0.000108732354,0.000009802112,0.000008266858,1.2709049e-7,0.00084801984,0.0000042154034,0.013512555,0.6844893,0.000979754,0.29996654],"study_design_scores_gemma":[0.000030443634,0.00022198938,0.0023469308,0.00019940025,0.000013779327,0.000009140629,0.0014731687,0.22251198,0.5602335,0.21190849,0.00065191387,0.00039931675],"about_ca_topic_score_codex":0.00016918882,"about_ca_topic_score_gemma":0.0000041003864,"teacher_disagreement_score":0.5467209,"about_ca_system_score_codex":0.000027736103,"about_ca_system_score_gemma":0.00009207987,"threshold_uncertainty_score":0.5356591},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000022447693,0.000110431,0.17530812,0.00044034637,0.00025128055,0.00017303156,0.000078754856,0.00024686928,0.82338893],"genre_scores_gemma":[0.005482984,0.00002435199,0.50334936,0.002575538,0.00177405,0.00009974773,0.0000280758,0.00007599608,0.48658988],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99827665,0.0000083675795,0.00033363892,0.0006689535,0.00038257783,0.00032982338],"domain_scores_gemma":[0.99850744,0.000025066956,0.00013090197,0.0010882849,0.000044275665,0.00020401651],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00010358857,0.00031529902,0.00027657594,0.00004882508,0.00013278566,0.00032369394,0.0013967883,0.00020678923,0.000029969131],"category_scores_gemma":[0.0000040651403,0.00031270576,0.00013685842,0.00001984991,0.00006912297,0.000110022134,0.0009790428,0.0002975149,0.00060526415],"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":[9.511651e-7,0.0000037709951,1.758664e-7,0.000004426463,0.00001753166,0.000015172649,0.000020228668,0.0000047355215,0.0000013409965,0.7413226,0.002459698,0.25614938],"study_design_scores_gemma":[0.00016688908,0.00004581235,0.000008920136,0.00009843672,0.000017580085,0.00008580929,9.484691e-7,0.0043245475,0.000008266939,0.39080688,0.6040232,0.0004126753],"about_ca_topic_score_codex":0.00002578129,"about_ca_topic_score_gemma":0.0000348905,"teacher_disagreement_score":0.6015635,"about_ca_system_score_codex":0.00020156305,"about_ca_system_score_gemma":0.00013489238,"threshold_uncertainty_score":0.9999325},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93012357,0.00012398903,0.06768318,0.00017105477,0.0004306136,0.00006584433,0.0000025390802,0.0000670538,0.0013321398],"genre_scores_gemma":[0.97087985,0.000013502209,0.029011168,0.000036103847,0.000003916214,0.0000016855042,0.0000011803523,0.0000037312132,0.00004886178],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99943787,0.000009190485,0.00013954002,0.00016887028,0.000121101795,0.00012341507],"domain_scores_gemma":[0.9993187,0.00022268339,0.000058324054,0.00030767923,0.000038352948,0.000054235046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039329394,0.00005641993,0.00008489117,0.000033815966,0.000072231334,0.000042964628,0.0003309706,0.000027165717,0.0000020773261],"category_scores_gemma":[0.00003374066,0.00005333349,0.000015118737,0.00019218732,0.000031113275,0.00020461439,0.00020822557,0.000056443878,0.0000065157947],"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":[7.073768e-7,0.000034915385,0.0007232788,0.0000053820095,0.0000029930106,0.0000015156845,0.00029299693,1.586746e-7,0.00087669154,0.92876875,0.00029310558,0.0689995],"study_design_scores_gemma":[0.0005404026,0.00010551105,0.093996234,0.00004628158,0.000006414939,0.000013199336,0.00011799327,0.003283044,0.018428765,0.8800854,0.0031699373,0.00020678129],"about_ca_topic_score_codex":0.000036249556,"about_ca_topic_score_gemma":0.0000015137125,"teacher_disagreement_score":0.093272954,"about_ca_system_score_codex":0.0000073940937,"about_ca_system_score_gemma":0.000011970686,"threshold_uncertainty_score":0.21748766},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010366473,0.000015229019,0.97572607,0.0010132351,0.00007290585,0.000085456486,0.00026155982,0.0001566344,0.012302408],"genre_scores_gemma":[0.05385992,0.0000011452153,0.94427675,0.00076999736,0.000088657376,0.0000599156,0.0005191528,0.00000420543,0.00042025745],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99916464,0.000007893031,0.00013208472,0.0003635092,0.00018248937,0.00014937916],"domain_scores_gemma":[0.9992364,0.00007323985,0.000023809338,0.00054386846,0.00003452954,0.000088126886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009113332,0.00007928082,0.00007572152,0.000053440992,0.0001298854,0.00020830333,0.0006045589,0.000013014196,0.000030796997],"category_scores_gemma":[0.00003185056,0.00007174688,0.000019124936,0.00025498954,0.000024185072,0.0005233056,0.0002979579,0.000036539022,0.00016731991],"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":[0.0000013279898,0.00017802692,0.00015430608,0.000003265773,0.0000160401,0.0000011239292,0.0017344506,0.00036174725,0.00013728383,0.93439907,0.012959781,0.050053585],"study_design_scores_gemma":[0.0014650478,0.00011838981,0.018897828,0.00009281305,0.000021299793,0.000041860498,0.0036290262,0.27890113,0.0029700384,0.034720335,0.6578749,0.0012673071],"about_ca_topic_score_codex":0.00091733364,"about_ca_topic_score_gemma":0.00003354144,"teacher_disagreement_score":0.8996787,"about_ca_system_score_codex":0.00002395718,"about_ca_system_score_gemma":0.00007843743,"threshold_uncertainty_score":0.29257527},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009298623,0.00095844094,0.09892998,0.00022461798,0.0005423591,0.00039945246,0.0002965865,0.00019660573,0.89835894],"genre_scores_gemma":[0.0007507626,0.000118067524,0.042918958,0.0005746889,0.0005210492,0.000102975544,0.00070967025,0.00010451054,0.9541993],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972166,0.000016270153,0.00069452304,0.0011938751,0.00041579347,0.00046296947],"domain_scores_gemma":[0.9980507,0.00028597465,0.00025722326,0.0011459882,0.00007000952,0.00019013404],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00060843304,0.00045297339,0.00046380426,0.0005706359,0.00011597616,0.00095093634,0.001836442,0.0005018437,0.000025694098],"category_scores_gemma":[0.00004948143,0.00043910206,0.000088797075,0.00008424591,0.00021060076,0.003167464,0.0016151719,0.0013866172,0.00006916985],"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":[0.0000033073372,0.0000133187905,0.00004360734,0.00002048087,0.000013537574,0.000021598284,0.000120438395,9.349535e-7,0.0000088317465,0.18174669,0.43771785,0.3802894],"study_design_scores_gemma":[0.00036670192,0.000022850774,0.00017040076,0.00026545153,0.000019906933,0.00004250699,0.000008304336,0.0014043527,0.000013084075,0.041904233,0.95524865,0.00053356553],"about_ca_topic_score_codex":0.00008770179,"about_ca_topic_score_gemma":0.00006219246,"teacher_disagreement_score":0.5175308,"about_ca_system_score_codex":0.00012682652,"about_ca_system_score_gemma":0.0003471381,"threshold_uncertainty_score":0.99980605},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000034568628,0.00006896736,0.99398214,0.00030641834,0.00064574636,0.00031640937,0.00006963471,0.0001785415,0.00439757],"genre_scores_gemma":[0.063674755,0.00004132598,0.93452775,0.0008591478,0.00033843514,0.00003354888,0.00006509584,0.000040841165,0.00041911087],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99640137,0.000027369788,0.0005707251,0.001598747,0.0007927197,0.00060904777],"domain_scores_gemma":[0.9970496,0.00045294652,0.00031277208,0.001659361,0.00029919,0.00022607535],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00072449475,0.00044926623,0.00040546735,0.0005112921,0.0002832564,0.00060092006,0.003497119,0.0002186957,0.00005527875],"category_scores_gemma":[0.000092080256,0.00042527652,0.00006457874,0.0004670416,0.0005032733,0.00053045637,0.00081180164,0.0005250734,0.00013378182],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014005224,0.00003161461,0.00007308746,0.000026268857,0.0000075857015,0.000037564925,0.00075371645,0.0006281651,0.00003448384,0.05123913,0.0000849214,0.94708204],"study_design_scores_gemma":[0.00033660093,0.00035939604,0.0017036492,0.0007461731,0.00002332331,0.00006616899,9.231921e-7,0.8415246,0.0010148739,0.14638741,0.006350896,0.0014859914],"about_ca_topic_score_codex":0.00006978595,"about_ca_topic_score_gemma":0.000041286843,"teacher_disagreement_score":0.9455961,"about_ca_system_score_codex":0.00017579044,"about_ca_system_score_gemma":0.00059002824,"threshold_uncertainty_score":0.99981993},"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000029649054,0.00031984327,0.06859294,0.00062090694,0.00010828562,0.00007577158,0.000005673677,0.00016682758,0.93010676],"genre_scores_gemma":[0.000038300386,0.00028918518,0.061204676,0.00014986131,0.000047050315,0.0000045988927,0.00002719677,0.000014421613,0.93822473],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991959,0.0000025512923,0.00016254398,0.00040433242,0.00011506418,0.000119626835],"domain_scores_gemma":[0.99916816,0.00004097101,0.00006704359,0.0006192091,0.000026882984,0.0000777444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000744264,0.00014764871,0.00013795024,0.00005756924,0.000078178506,0.00018459061,0.00046492214,0.00014783045,0.00052221975],"category_scores_gemma":[0.0000015248105,0.00013180834,0.00003243454,0.000058666494,0.00004948818,0.0001489885,0.000302253,0.00017664047,0.00065111474],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.3586528e-7,0.000002669451,8.507571e-7,0.0000012929466,0.000011334481,0.00000842913,0.000014020197,1.2932016e-7,2.0610003e-7,0.8015616,0.015108832,0.18329054],"study_design_scores_gemma":[0.00006400228,0.000013290593,0.000043698947,0.000040852414,0.000008483788,0.000050375224,0.0000017349752,0.0009281539,6.403217e-7,0.07554303,0.9231035,0.00020225244],"about_ca_topic_score_codex":0.000007198891,"about_ca_topic_score_gemma":0.0000016298349,"teacher_disagreement_score":0.9079946,"about_ca_system_score_codex":0.000014341324,"about_ca_system_score_gemma":0.000021483582,"threshold_uncertainty_score":0.836898},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022783608,0.000040748397,0.9627268,0.017343748,0.0013263461,0.0010042571,0.010579229,0.00067425525,0.0040262556],"genre_scores_gemma":[0.2136334,0.00016674546,0.7195568,0.018251447,0.01388954,0.000793485,0.031944826,0.00008483715,0.0016789286],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979203,0.00006783369,0.00031383525,0.00085852825,0.0003927108,0.00044680727],"domain_scores_gemma":[0.9979088,0.00035872715,0.00019050369,0.0013067671,0.00008672427,0.00014849639],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003968031,0.00023864573,0.0002922021,0.00022228951,0.0006463081,0.00029879692,0.00091520284,0.000051025785,0.000025388332],"category_scores_gemma":[0.00007568085,0.00023076622,0.00019314565,0.0012906151,0.0000439795,0.0008902167,0.00013034487,0.00015551595,0.00010207901],"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":[0.0001375708,0.00079502066,0.00005141616,0.000010362642,0.0002084154,0.00001403667,0.00013728012,0.0009125089,0.0011497037,0.46469226,0.5021152,0.029776232],"study_design_scores_gemma":[0.0015828343,0.0006823999,0.0032711932,0.00006645783,0.00044133866,0.0000082450015,0.00004963418,0.049968384,0.001734865,0.0011699523,0.9401074,0.0009172869],"about_ca_topic_score_codex":0.00004100798,"about_ca_topic_score_gemma":0.000023979843,"teacher_disagreement_score":0.46352232,"about_ca_system_score_codex":0.00005563279,"about_ca_system_score_gemma":0.000088768444,"threshold_uncertainty_score":0.94103736},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000016080507,0.000085885644,0.096179545,0.00057665195,0.00036012972,0.00020128665,0.00027237588,0.00019344446,0.9021146],"genre_scores_gemma":[0.024799986,0.000020523255,0.008484433,0.0037398103,0.00084210426,0.00004529041,0.00007389292,0.00004219125,0.9619518],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99826485,0.000012103068,0.00031722317,0.00058490847,0.00053088827,0.0002900046],"domain_scores_gemma":[0.9985902,0.000033091717,0.0003423404,0.00084422244,0.000079920785,0.00011024529],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00014333191,0.00028651927,0.00027092555,0.000039377883,0.00011297819,0.0004929258,0.0009902538,0.00026399322,0.000009463305],"category_scores_gemma":[0.000013840091,0.000289351,0.00017155067,0.000022784825,0.000016706563,0.00021669493,0.0003033676,0.00022666182,0.00075592723],"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":[4.7164679e-7,0.000008599299,0.000006135781,0.0000026507723,0.000027005432,0.000012282012,0.000016456272,0.0000011110019,0.0000014196885,0.7009889,0.007140964,0.29179403],"study_design_scores_gemma":[0.00020590654,0.00010560678,0.00026104992,0.00014927874,0.000046868805,0.000029288754,0.0000020999512,0.0007929189,0.000025617239,0.68248695,0.31533852,0.0005559167],"about_ca_topic_score_codex":0.000111896,"about_ca_topic_score_gemma":0.000034728135,"teacher_disagreement_score":0.30819756,"about_ca_system_score_codex":0.0005221611,"about_ca_system_score_gemma":0.00018150116,"threshold_uncertainty_score":0.9999559},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010210447,0.00015305632,0.9954204,0.001636488,0.0011230281,0.0006071532,0.00014329233,0.0001772303,0.0006372303],"genre_scores_gemma":[0.102943204,0.000012633487,0.89251107,0.0028057077,0.0010885746,0.0000315737,0.00011356503,0.00006799659,0.00042565662],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99594855,0.000027639995,0.0005911398,0.0018441337,0.0007783141,0.0008102193],"domain_scores_gemma":[0.99641263,0.0007514776,0.00040401347,0.0019407271,0.00024586858,0.00024528595],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006698658,0.00062600337,0.000648206,0.00061976304,0.00039533374,0.00086621515,0.0044766166,0.00031439355,0.000018778284],"category_scores_gemma":[0.00008600877,0.0005530082,0.0001744915,0.00048514025,0.0004508522,0.00036747084,0.0007471347,0.000556368,0.000016679931],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017965307,0.000013406787,0.000038228416,0.000035744248,0.000013316631,0.000010184627,0.00045802837,0.0056427857,0.000104437604,0.008105134,0.00033357771,0.9852434],"study_design_scores_gemma":[0.00041019917,0.00023951684,0.00015093411,0.0003552946,0.000015587684,0.00006399393,3.6433352e-7,0.9248852,0.0005261385,0.059552692,0.013003952,0.00079610804],"about_ca_topic_score_codex":0.00006466718,"about_ca_topic_score_gemma":0.00023107418,"teacher_disagreement_score":0.98444724,"about_ca_system_score_codex":0.00026969056,"about_ca_system_score_gemma":0.00042541398,"threshold_uncertainty_score":0.99969214},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004896261,0.00015423735,0.013970764,0.00023194191,0.00015718538,0.00023785964,0.00024887532,0.00039080705,0.98455936],"genre_scores_gemma":[0.024259862,0.000026673268,0.42846742,0.0033675379,0.0008853658,0.0000775716,0.000052750464,0.00011057097,0.54275227],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99794805,0.000010435992,0.00031744977,0.00085467065,0.0004581992,0.00041120837],"domain_scores_gemma":[0.9981093,0.000034258068,0.00023689705,0.0013156538,0.00009368438,0.00021024991],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00012357302,0.0004387425,0.0003882671,0.00007604955,0.00017476184,0.00036354442,0.0015476393,0.00024792916,0.000015367988],"category_scores_gemma":[0.0000051263714,0.00038826064,0.00010944773,0.00005265734,0.00010994975,0.0001420624,0.00034653203,0.00026718498,0.00028797865],"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":[0.0000025836857,0.000008406435,0.0000030797114,0.000005307056,0.000028928343,0.00007689505,0.00002919002,0.0000018371172,0.000007786276,0.82402045,0.007488652,0.16832691],"study_design_scores_gemma":[0.0006448035,0.00034439893,0.000047968493,0.00043064033,0.000078819576,0.00032231837,0.0000086946875,0.006037743,0.000019405863,0.11318284,0.8777728,0.0011095395],"about_ca_topic_score_codex":0.000016298533,"about_ca_topic_score_gemma":0.00006295782,"teacher_disagreement_score":0.8702842,"about_ca_system_score_codex":0.0001198138,"about_ca_system_score_gemma":0.00044545784,"threshold_uncertainty_score":0.99985695},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000003185966,0.00017687745,0.13732095,0.00027873958,0.00035289073,0.00016951171,0.0012796327,0.0002907558,0.86012745],"genre_scores_gemma":[0.0020118111,0.00002249933,0.7001007,0.0017904827,0.0016468652,0.000053473454,0.0010217533,0.00007710759,0.29327527],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99793047,0.000008403662,0.00037487462,0.00095999544,0.00044035143,0.0002859124],"domain_scores_gemma":[0.9966588,0.000044211294,0.00023229189,0.0028097378,0.000098466015,0.00015651855],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00015803346,0.00031086692,0.0002670461,0.0000680286,0.00016254764,0.0002455756,0.0030374108,0.0002007584,0.000026098607],"category_scores_gemma":[0.000019905136,0.00032489828,0.000061326566,0.00004040637,0.000056345267,0.00029602842,0.0015096823,0.00018306792,0.0004008144],"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":[6.792592e-7,0.0000055979067,0.000001130722,0.0000031019522,0.000025963096,0.000011626248,0.000031492134,8.2884986e-7,7.490327e-7,0.77861017,0.029357966,0.19195068],"study_design_scores_gemma":[0.00019445881,0.000025107047,0.000013121435,0.00010355973,0.00003367287,0.00005466814,0.000007854029,0.01689032,0.0000044080634,0.034220614,0.9479964,0.00045584966],"about_ca_topic_score_codex":0.000034261913,"about_ca_topic_score_gemma":0.00006301673,"teacher_disagreement_score":0.9186384,"about_ca_system_score_codex":0.00011415418,"about_ca_system_score_gemma":0.0002170807,"threshold_uncertainty_score":0.9999203},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012308492,0.000060565322,0.052151978,0.00045629236,0.00024300128,0.00017648283,0.0003101498,0.0003338393,0.9462554],"genre_scores_gemma":[0.0133075435,0.000005181186,0.5502475,0.006393636,0.00097534317,0.00007136649,0.00014956287,0.0000790284,0.42877087],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983082,0.000013345766,0.00033553684,0.00057024945,0.00044861218,0.00032410037],"domain_scores_gemma":[0.99855256,0.00007465753,0.00037475963,0.0007256964,0.00013357478,0.00013872856],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00020780129,0.0002942341,0.00030331005,0.000057637913,0.00014862014,0.0003204139,0.0007196084,0.00033020633,0.000015658206],"category_scores_gemma":[0.000028203278,0.0003216262,0.0001492714,0.00003182829,0.00004283584,0.000085056556,0.0001278997,0.00021125589,0.0002587498],"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":[6.8598746e-7,0.0000069825023,0.0000046293653,0.0000033985434,0.000021347678,0.000015735717,0.000013689436,0.0000029602832,0.0000040681903,0.7793652,0.006932914,0.2136284],"study_design_scores_gemma":[0.00081855006,0.00016797172,0.00016689725,0.00037737514,0.000109080036,0.000052146028,0.00000905061,0.011993056,0.0001114271,0.5048714,0.48003381,0.0012891913],"about_ca_topic_score_codex":0.000019606689,"about_ca_topic_score_gemma":0.000012351444,"teacher_disagreement_score":0.51748455,"about_ca_system_score_codex":0.00041571082,"about_ca_system_score_gemma":0.00035685115,"threshold_uncertainty_score":0.9999236},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016177461,0.0066562667,0.9492845,0.0001230301,0.0016853821,0.0006011675,0.0001434122,0.00012001218,0.03976849],"genre_scores_gemma":[0.6169532,0.0030349365,0.33447888,0.0008088355,0.0030745175,0.00016620365,0.00061722554,0.00026521884,0.040600978],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976968,0.00005969324,0.0008814379,0.0006429623,0.00045082977,0.0002682768],"domain_scores_gemma":[0.9975865,0.0006832113,0.0010017995,0.00052315084,0.00013149495,0.00007387567],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007978227,0.00031116517,0.0005639335,0.0002475039,0.00011142713,0.00014317037,0.0005455991,0.00019545092,0.000004153935],"category_scores_gemma":[0.00006062762,0.0003036837,0.0000869037,0.000077053126,0.00003910295,0.0001230844,0.0001568554,0.00023365117,0.000014193463],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000090602725,0.00006781455,0.0011143755,0.00051476073,0.00007501533,0.000010635957,0.00048453372,0.017963436,0.000034765828,0.5048349,0.00090822496,0.4739825],"study_design_scores_gemma":[0.00019676622,0.0001602148,0.00006337585,0.0019764074,0.000017812417,0.0000039589163,0.000041072144,0.81710863,0.00012030026,0.00088665925,0.17901607,0.00040874514],"about_ca_topic_score_codex":0.00003671469,"about_ca_topic_score_gemma":0.000010554521,"teacher_disagreement_score":0.79914516,"about_ca_system_score_codex":0.00015772087,"about_ca_system_score_gemma":0.000051521474,"threshold_uncertainty_score":0.9999415},"labels":[],"label_agreement":null}]}