{"meta":{"query_hash":"d7ed052de473","filters":{"topic":"Data Mining and Machine Learning Applications"},"cohort_total":280,"direct_labels_cover":0,"predictions_cover":280,"exported":280,"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/d7ed052de473","api":"https://metacan.xera.ac/api/v1/cohort?topic=Data+Mining+and+Machine+Learning+Applications"},"results":[{"id":"W1536345696","doi":"10.21831/gm.v11i1.3567","title":"PEMENFAATAN SISTEM INFORMASI GEOGRAFIS UNTUK EVALUASI KEMAMPUAN LAHAN DAN ARAHAN PENGGUNAAN LAHAN DI KECAMATAN SAMIGALUH KABUPATEN KULON PROGO","year":2015,"lang":"id","type":"article","venue":"Geomedia Majalah Ilmiah dan Informasi Kegeografian","topic":"Data Mining and Machine Learning 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":"WiLAN (Canada)","funders":"","keywords":"Forestry; Physics; Geography","score_opus":0.02933751243510622,"score_gpt":0.27412860991449584,"score_spread":0.24479109747938962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1536345696","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":[0.5738158,0.007389177,0.020301167,0.022195091,0.023788167,0.02142642,0.0014899069,0.014527992,0.31506628],"genre_scores_gemma":[0.9268402,0.0011564739,0.015353322,0.0022382904,0.0025908689,0.0024048467,0.018138362,0.0007051979,0.030572461],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9803622,0.0009232211,0.0047146687,0.003418804,0.0049582436,0.0056228954],"domain_scores_gemma":[0.9805896,0.00048265202,0.003072335,0.008874497,0.001902028,0.0050788475],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","research_integrity"],"category_scores_codex":[0.0065400507,0.0032003745,0.0028057506,0.0021771265,0.0025365753,0.005217674,0.011371436,0.0014967821,0.000049360206],"category_scores_gemma":[0.0011580584,0.0032519929,0.0011633128,0.0053991033,0.0021340086,0.007500037,0.006736953,0.0039829127,0.0016461221],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00070668914,0.0029225498,0.18575424,0.0022905725,0.0019206981,0.00052649825,0.07107134,0.0012591741,0.00034496363,0.060112614,0.016794033,0.6562966],"study_design_scores_gemma":[0.0057191197,0.0027121594,0.073315084,0.0008833862,0.00063178246,0.0005556182,0.007163142,0.036903847,0.00029147428,0.00026575715,0.8676006,0.0039579878],"about_ca_topic_score_codex":0.0007191614,"about_ca_topic_score_gemma":0.0013975104,"teacher_disagreement_score":0.8508066,"about_ca_system_score_codex":0.001239077,"about_ca_system_score_gemma":0.0031442537,"threshold_uncertainty_score":0.9997995},"labels":[],"label_agreement":null},{"id":"W2557517892","doi":"10.21609/jsi.v12i2.481","title":"VISUALISASI DATA INTERAKTIF DATA TERBUKA PEMERINTAH PROVINSI DKI JAKARTA: TOPIK EKONOMI DAN KEUANGAN DAERAH","year":2016,"lang":"en","type":"article","venue":"Jurnal Sistem Informasi","topic":"Data Mining and Machine Learning Applications","field":"Computer Science","cited_by":26,"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":"Visualization; Computer science; Data science; Data visualization; Quarter (Canadian coin); World Wide Web; Data mining; Geography","score_opus":0.06894903330201307,"score_gpt":0.3238826768715423,"score_spread":0.25493364356952924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2557517892","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":[0.16278005,0.000276833,0.7348547,0.024707224,0.0032891494,0.0014647479,0.00083079597,0.0021335424,0.06966295],"genre_scores_gemma":[0.9713989,0.00008631919,0.01895478,0.0018530493,0.00079064636,0.00006908729,0.0018956074,0.000055327837,0.0048962687],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973902,0.00008227317,0.0007296292,0.00086276006,0.00041222232,0.00052290206],"domain_scores_gemma":[0.99322426,0.00020620276,0.0003976121,0.0057986667,0.000099270896,0.00027397324],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00091196963,0.00030242413,0.00030745222,0.00014926755,0.00035331436,0.00071779225,0.008151279,0.000092998045,0.000006927117],"category_scores_gemma":[0.00030927928,0.00021490062,0.00006399228,0.00030802534,0.00010560105,0.0051967856,0.006173058,0.00033346776,0.00014406508],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027060778,0.00012688234,0.011557419,0.000053253367,0.000088846675,0.000013758936,0.0007510571,0.000006751555,0.0004436678,0.035784233,0.015356739,0.9357903],"study_design_scores_gemma":[0.0005658751,0.000119572076,0.012054098,0.00012245755,0.000022686212,0.00014725472,0.00010170054,0.014739194,0.00026979708,0.000020457488,0.9714659,0.00037099424],"about_ca_topic_score_codex":0.000077436904,"about_ca_topic_score_gemma":0.00012294092,"teacher_disagreement_score":0.95610917,"about_ca_system_score_codex":0.000088063025,"about_ca_system_score_gemma":0.0002459793,"threshold_uncertainty_score":0.9972151},"labels":[],"label_agreement":null},{"id":"W2569301778","doi":"","title":"ARTIFICIAL NEURAL NETWORK APPLICATION IN GROSS DOMESTIC PRODUCT FORECASTING AN INDONESIA CASE","year":2012,"lang":"en","type":"article","venue":"Journal of Theoretical and Applied Information Technology","topic":"Data Mining and Machine Learning Applications","field":"Computer Science","cited_by":4,"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":"Gross domestic product; Real gross domestic product; Inflation (cosmology); Benchmark (surveying); Economic forecasting; Economics; Population; Government (linguistics); Economic indicator; Artificial neural network; Economic stability; Exchange rate; Econometrics; Macroeconomics; Computer science; Artificial intelligence; Geography","score_opus":0.009700565042861733,"score_gpt":0.25451588219322696,"score_spread":0.24481531715036522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2569301778","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":[0.5877054,0.000029307717,0.41058317,0.0012043901,0.00007243754,0.00012632523,9.3317686e-7,0.000059857884,0.00021816659],"genre_scores_gemma":[0.9628945,0.0000028333693,0.036799252,0.00013112354,0.00013898093,0.000024157884,0.00000503196,0.0000037835016,3.4053096e-7],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99895114,0.000030987758,0.0005388682,0.00009444982,0.0001192519,0.0002652934],"domain_scores_gemma":[0.9991578,0.000096100215,0.00034855452,0.00023897529,0.00006347434,0.00009512918],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010144893,0.00009751869,0.00017081904,0.000285075,0.00013676484,0.000084098145,0.00033388464,0.00009147186,0.0000017111241],"category_scores_gemma":[0.00012843909,0.000079175305,0.000018628765,0.0005847149,0.00019067047,0.0010880749,0.00014168328,0.00039879562,0.0000068704758],"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":[0.000011651935,0.000032859843,0.0008802625,0.000006397266,0.0000024334033,0.000003243246,0.0002673394,0.000761457,0.000051660838,0.6727513,0.000016890772,0.3252145],"study_design_scores_gemma":[0.00092264544,0.00043620475,0.0044783573,0.000041471943,0.000043658965,0.023644596,0.0009886217,0.43229097,0.0016495712,0.53280103,0.0021851745,0.00051770994],"about_ca_topic_score_codex":0.0000018088435,"about_ca_topic_score_gemma":6.60901e-7,"teacher_disagreement_score":0.4315295,"about_ca_system_score_codex":0.000021462722,"about_ca_system_score_gemma":0.000020776053,"threshold_uncertainty_score":0.3228675},"labels":[],"label_agreement":null},{"id":"W2725171488","doi":"10.1038/nmeth.4346","title":"Principal component analysis","year":2017,"lang":"en","type":"article","venue":"Nature Methods","topic":"Data Mining and Machine Learning Applications","field":"Computer Science","cited_by":1399,"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":"Principal component analysis; Component (thermodynamics); Computational biology; Computer science; Biology; Artificial intelligence; Physics","score_opus":0.026833545214579806,"score_gpt":0.4465176621825136,"score_spread":0.4196841169679338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2725171488","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025311185,0.00012441137,0.98109716,0.002764844,0.00031026552,0.000049772443,0.0000042760166,0.00016089268,0.012957284],"genre_scores_gemma":[0.2795486,0.0000033088627,0.7194675,0.0002094708,0.000053072043,0.000009713109,0.000009866034,0.0000035450732,0.00069494965],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9989833,0.00019938058,0.00011765418,0.00037125018,0.00016410573,0.00016429223],"domain_scores_gemma":[0.9972376,0.00017515373,0.00016339499,0.0022893099,0.000053962132,0.00008057408],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014039887,0.00009144628,0.00017619031,0.00013322159,0.00055920717,0.00039753743,0.0021887391,0.00012597731,0.000011826458],"category_scores_gemma":[0.00056827546,0.00007710826,0.00011148876,0.00027928682,0.000044315144,0.00022241756,0.0005903717,0.0005618266,0.000029477744],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025045845,0.00006099746,0.007355157,0.000005565767,0.00030475264,0.0000061131195,0.00027428064,0.00022418528,0.0013335232,0.26060167,0.0017127885,0.7281185],"study_design_scores_gemma":[0.00017244482,0.000018778257,0.43012938,0.000004322633,0.00015675629,0.000006438401,0.0000044073413,0.14870217,0.0012800944,0.0033775356,0.41593233,0.00021535023],"about_ca_topic_score_codex":0.000061514496,"about_ca_topic_score_gemma":0.00000933129,"teacher_disagreement_score":0.7279031,"about_ca_system_score_codex":0.00001511561,"about_ca_system_score_gemma":0.000023211987,"threshold_uncertainty_score":0.43010262},"labels":[],"label_agreement":null},{"id":"W2743864734","doi":"10.26486/mercumatika.v1i1.188","title":"COMPARISON OF TREND PROJECTION METHODS AND BACKPROPAGATION PROJECTIONS METHODS TREND IN PREDICTING THE NUMBER OF VICTIMS DIED IN TRAFFIC ACCIDENT IN TIMOR TENGAH REGENCY, NUSA TENGGARA","year":2016,"lang":"en","type":"article","venue":"Jurnal Mercumatika Jurnal Penelitian Matematika dan Pendidikan Matematika","topic":"Data Mining and Machine Learning 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":"WiLAN (Canada)","funders":"","keywords":"Backpropagation; Statistics; Projection (relational algebra); Road accident; Mathematics; Computer science; Engineering; Transport engineering; Artificial intelligence; Artificial neural network; Algorithm","score_opus":0.03829513014845653,"score_gpt":0.41115637433561597,"score_spread":0.37286124418715944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2743864734","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":[0.94604623,0.00031729141,0.049443997,0.0010396114,0.00028245468,0.0015818501,0.000046932862,0.0001345087,0.0011071031],"genre_scores_gemma":[0.89171124,0.000119975055,0.1075789,0.000019541405,0.000048419537,0.00038908282,0.000028346241,0.000053176973,0.000051316303],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99036413,0.0035351256,0.0036486,0.00093987625,0.0007891514,0.0007231044],"domain_scores_gemma":[0.9940287,0.0022457803,0.002247934,0.0011380917,0.00016087473,0.00017860581],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.008180585,0.0005863172,0.0014641945,0.0013860172,0.00037145842,0.00021453988,0.0013061761,0.0002445238,0.00004726279],"category_scores_gemma":[0.0011157772,0.0003945106,0.00019673661,0.0020268208,0.00024935356,0.0015848008,0.00048835715,0.0008564157,0.000009822106],"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":[0.0003228348,0.0023813215,0.5968896,0.0053422707,0.00034347238,0.000038749382,0.076581255,0.0029532649,0.05564339,0.027596924,0.0002992315,0.23160768],"study_design_scores_gemma":[0.0038556822,0.0005723888,0.8086636,0.009145676,0.00019700744,0.00095215725,0.009886923,0.14424433,0.015790941,0.0052674357,0.00016005005,0.0012638081],"about_ca_topic_score_codex":0.00052341196,"about_ca_topic_score_gemma":0.0013342936,"teacher_disagreement_score":0.23034388,"about_ca_system_score_codex":0.00029374548,"about_ca_system_score_gemma":0.00020647705,"threshold_uncertainty_score":0.9998507},"labels":[],"label_agreement":null},{"id":"W2767913911","doi":"10.31253/te.v1i1.20","title":"Analisis Performance Fuzzy Tsukamoto Dalam Klasifikasi Bantuan Kemiskinan","year":2017,"lang":"en","type":"article","venue":"Tech-E","topic":"Data Mining and Machine Learning 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":"Poverty; Fuzzy inference system; Fuzzy logic; Meaning (existential); Statistics; Mathematics; Computer science; Econometrics; Psychology; Economics; Artificial intelligence; Economic growth; Fuzzy control system; Adaptive neuro fuzzy inference system","score_opus":0.018293729970326356,"score_gpt":0.27754147962605646,"score_spread":0.2592477496557301,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767913911","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":[0.7647765,0.00009011633,0.093251035,0.005293571,0.00048205815,0.00030464158,0.000017048127,0.0013719234,0.13441306],"genre_scores_gemma":[0.97723556,0.000045017372,0.021045608,0.000118901786,0.00009035734,0.000041975305,0.000012513722,0.000012799925,0.0013972721],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9988576,0.000021704487,0.00016793856,0.00044155563,0.00021527747,0.00029590607],"domain_scores_gemma":[0.9970554,0.00003516638,0.00018545952,0.0025697625,0.000052832558,0.000101348436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036745347,0.00014245578,0.00014504252,0.00008342168,0.000995623,0.00046439515,0.002774497,0.000061312545,0.000013558842],"category_scores_gemma":[0.00014187775,0.00013276236,0.000050811384,0.00014727621,0.000100899044,0.0006599066,0.0006163237,0.00023040333,0.00026226148],"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":[0.0000063748353,0.00014858427,0.14731237,0.000057074627,0.000036932925,0.000017365011,0.00072822033,0.00007561247,0.001541764,0.110589504,0.018494867,0.7209913],"study_design_scores_gemma":[0.0005022894,0.00017209661,0.7636689,0.000086427855,0.000021434715,0.000056876997,0.00004216507,0.043661345,0.0031930064,0.002233058,0.18578115,0.0005812649],"about_ca_topic_score_codex":0.00019856615,"about_ca_topic_score_gemma":0.000010858649,"teacher_disagreement_score":0.72041005,"about_ca_system_score_codex":0.00002563215,"about_ca_system_score_gemma":0.00004750421,"threshold_uncertainty_score":0.76576275},"labels":[],"label_agreement":null},{"id":"W2779556253","doi":"10.26798/jiko.2016.v1i1.10","title":"PENERAPAN NAÃVE BAYES UNTUK PREDIKSI KELAYAKAN KREDIT","year":2016,"lang":"id","type":"article","venue":"JIKO (Jurnal Informatika dan Komputer)","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"Agricultural science; Environmental science","score_opus":0.011935461879385788,"score_gpt":0.24596263615894826,"score_spread":0.23402717427956246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2779556253","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":[0.070647165,0.00050428143,0.87718695,0.014474742,0.005529209,0.0009799735,0.0005409757,0.0014615319,0.028675146],"genre_scores_gemma":[0.91334355,0.0007758603,0.061537005,0.0041357568,0.004513,0.00019667918,0.00038085404,0.00016818235,0.0149491215],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99431914,0.0002780618,0.0017518766,0.0009967005,0.0012072298,0.0014469614],"domain_scores_gemma":[0.99455965,0.0005826251,0.0011956875,0.002367519,0.00041809076,0.0008764407],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012798987,0.0008564241,0.0007983258,0.0006289628,0.000962977,0.0018267948,0.0039463956,0.00037507233,0.0002190192],"category_scores_gemma":[0.0001958444,0.0006394074,0.00041377763,0.001028036,0.0003483626,0.0050674393,0.0018893557,0.00096002617,0.003822695],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056848847,0.00035011378,0.0031151557,0.00020073558,0.0003753469,0.000046498084,0.008586854,0.00030314398,0.000786837,0.029874312,0.2668313,0.68947285],"study_design_scores_gemma":[0.0024711443,0.0011030716,0.018813908,0.0010687948,0.00011655968,0.0006864434,0.00022052288,0.08319094,0.0011535678,0.0005684135,0.88899386,0.0016127877],"about_ca_topic_score_codex":0.00010789681,"about_ca_topic_score_gemma":0.000018002247,"teacher_disagreement_score":0.84269637,"about_ca_system_score_codex":0.00027029443,"about_ca_system_score_gemma":0.0005621955,"threshold_uncertainty_score":0.9996057},"labels":[],"label_agreement":null},{"id":"W2779662374","doi":"10.4018/978-1-59140-557-3.ch125","title":"Interval Set Representations of Clusters","year":2005,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining and Machine Learning 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); Saint Mary's University","funders":"","keywords":"Categorization; Cluster analysis; Automatic summarization; Object (grammar); Computer science; Conceptual clustering; Artificial intelligence; Sample (material); Set (abstract data type); Process (computing); Pattern recognition (psychology); Data mining; Machine learning; Fuzzy clustering; CURE data clustering algorithm","score_opus":0.023869710132796065,"score_gpt":0.300199951054419,"score_spread":0.27633024092162295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2779662374","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":[0.000027321155,0.000063922314,0.06684083,0.00045150914,0.00020678733,0.0001633668,0.0002454314,0.00021051499,0.9317903],"genre_scores_gemma":[0.219542,0.0000138704745,0.12908363,0.0017120008,0.00067236274,0.00007833315,0.00016420933,0.00009293433,0.64864063],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99858475,0.000022189037,0.00039693768,0.00051082857,0.00029275223,0.00019253965],"domain_scores_gemma":[0.9981759,0.00005830261,0.00032392272,0.0012408155,0.00009531874,0.00010573873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001294159,0.00023218433,0.0002934857,0.000084760795,0.000080270554,0.00008658253,0.0012362918,0.00016083957,0.00002049934],"category_scores_gemma":[0.00002666594,0.00024275112,0.00016800399,0.000032060754,0.000099636025,0.00009294805,0.00058250484,0.00026890464,0.00022504557],"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":[0.0000027550207,0.000006633045,0.000008776906,0.0000111104,0.000046103632,0.00000433773,0.00016784422,0.000058352747,0.000004215356,0.94908357,0.014709707,0.03589662],"study_design_scores_gemma":[0.000684678,0.00020538988,0.00020430789,0.00039182394,0.00015176825,0.00016829646,0.000038643346,0.006332945,0.00006224091,0.35785168,0.63297814,0.0009300935],"about_ca_topic_score_codex":0.0001321805,"about_ca_topic_score_gemma":0.00005744716,"teacher_disagreement_score":0.61826843,"about_ca_system_score_codex":0.000080384954,"about_ca_system_score_gemma":0.00013986467,"threshold_uncertainty_score":0.9899103},"labels":[],"label_agreement":null},{"id":"W2787356029","doi":"10.20473/ijph.v12i2.2017.213-223","title":"APLIKASI PERAMALAN JUMLAH KELAHIRAN DENGAN METODE JARINGAN SYARAF TIRUAN","year":2018,"lang":"en","type":"article","venue":"The Indonesian Journal of Public Health","topic":"Data Mining and Machine Learning 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":"Encana (Canada)","funders":"","keywords":"Artificial neural network; Statistic; Statistics; Preprocessor; Computer science; Data pre-processing; Artificial intelligence; Mathematics","score_opus":0.058994279228169924,"score_gpt":0.3209810170725358,"score_spread":0.2619867378443659,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2787356029","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":[0.21744783,0.0002737738,0.65959483,0.11993143,0.0006839124,0.0002050623,0.000005046335,0.00015421887,0.0017038856],"genre_scores_gemma":[0.97387046,0.00003232925,0.022224024,0.002839882,0.00079902034,0.000005644675,0.000003778991,0.000022057271,0.00020283],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969318,0.00082624744,0.0007530748,0.00028308877,0.00055281806,0.000652953],"domain_scores_gemma":[0.9969687,0.00022720032,0.0008309321,0.0010320097,0.0003412714,0.00059988315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0072784475,0.00019027476,0.00035059132,0.00032262382,0.00088758883,0.0005056398,0.0027956509,0.00006431207,0.000015742706],"category_scores_gemma":[0.00034929634,0.00012998347,0.00011814451,0.00084696425,0.00020130862,0.00068269926,0.00024927792,0.00083515863,0.0000932694],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016654396,0.00032567428,0.011099112,0.00004296019,0.00015902001,0.000024334382,0.01870876,0.000028830624,0.00020805784,0.19641995,0.013590043,0.7593766],"study_design_scores_gemma":[0.0034970562,0.004179554,0.27212274,0.00032188333,0.00006982351,0.005992705,0.0033565287,0.019983679,0.0004024274,0.010247093,0.6786563,0.0011702457],"about_ca_topic_score_codex":0.00016474837,"about_ca_topic_score_gemma":0.000053289932,"teacher_disagreement_score":0.75820637,"about_ca_system_score_codex":0.00012635715,"about_ca_system_score_gemma":0.0011599442,"threshold_uncertainty_score":0.68267053},"labels":[],"label_agreement":null},{"id":"W2800761902","doi":"10.31253/te.v1i2.62","title":"Neural Network Modeling for Family Welfare Classification","year":2018,"lang":"en","type":"article","venue":"Tech-E","topic":"Data Mining and Machine Learning 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":"Artificial neural network; Backpropagation; Conjugate gradient method; Computer science; Gradient descent; Variable (mathematics); Welfare; MATLAB; Artificial intelligence; Test data; Machine learning; Data mining; Algorithm; Mathematics; Economics","score_opus":0.052290256736684866,"score_gpt":0.3071703694345403,"score_spread":0.25488011269785543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2800761902","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011169155,0.000030733776,0.9814416,0.0037772036,0.00020579416,0.00015295911,0.0000050346794,0.00056177104,0.0026557532],"genre_scores_gemma":[0.8265902,0.0000013815743,0.17254446,0.0003224697,0.00028714084,0.000077878954,0.000025980633,0.000008389305,0.00014212723],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99927276,0.00001590412,0.0001277952,0.00029010055,0.00008790932,0.00020550692],"domain_scores_gemma":[0.9992021,0.000030105337,0.000051504154,0.0005835817,0.00009095024,0.0000417895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023475653,0.00007374974,0.000070109265,0.00003745228,0.00038496507,0.000096933225,0.00063334417,0.000040753504,0.0000025888253],"category_scores_gemma":[0.000039029717,0.000070766415,0.000030466057,0.0002466195,0.000027789809,0.00017566324,0.00011004233,0.000084897925,0.000057704052],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000777236,0.00003543839,0.00016605573,0.0000093885,0.000010697686,2.7833116e-7,0.00027927215,0.009908517,0.0013545199,0.5603154,0.023073852,0.40483883],"study_design_scores_gemma":[0.00008744271,0.000051685438,0.0007696562,0.0000048848747,0.0000037199661,0.0000018462814,0.00001861566,0.93428165,0.000018586145,0.0041400087,0.06053715,0.00008473418],"about_ca_topic_score_codex":0.000028168732,"about_ca_topic_score_gemma":0.000004249493,"teacher_disagreement_score":0.92437315,"about_ca_system_score_codex":0.000013952071,"about_ca_system_score_gemma":0.00001758198,"threshold_uncertainty_score":0.2960879},"labels":[],"label_agreement":null},{"id":"W2802567206","doi":"10.34148/teknika.v6i1.58","title":"Seleksi Atribut Menggunakan Information Gain Untuk Clustering Penduduk Miskin Dengan Validity Index Xie Beni","year":2017,"lang":"id","type":"article","venue":"Teknika","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"Cluster analysis; Mathematics; Humanities; Statistics; Philosophy","score_opus":0.035398010630843225,"score_gpt":0.2972084007832998,"score_spread":0.26181039015245655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2802567206","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":[0.27623832,0.00016820227,0.6796055,0.0076295673,0.0024783548,0.0012502543,0.00044093392,0.0012099487,0.030978953],"genre_scores_gemma":[0.9880455,0.00007122005,0.007520335,0.00027076586,0.00040995533,0.00005113081,0.00031842638,0.000034044017,0.0032785963],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99682426,0.00026441243,0.00071400014,0.00070746517,0.00066410593,0.00082574907],"domain_scores_gemma":[0.9949881,0.00024883682,0.0010180586,0.003124068,0.00025344625,0.00036750722],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017754876,0.00046768598,0.00045584262,0.00023293425,0.0027221486,0.0028089997,0.0035071473,0.0002898306,0.0000820248],"category_scores_gemma":[0.0010764019,0.00050897937,0.00016806429,0.00028167188,0.00020497153,0.0032911815,0.0019957342,0.001021735,0.0021635538],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013059903,0.00066315866,0.046904515,0.0007840276,0.0004045253,0.0000773759,0.025960753,0.005130643,0.0019375838,0.023298817,0.07788893,0.8168191],"study_design_scores_gemma":[0.0020152929,0.0003145454,0.12165546,0.00030796992,0.00014582618,0.000099510056,0.00046951487,0.42556366,0.0019579306,0.0008065753,0.44521907,0.0014446392],"about_ca_topic_score_codex":0.0019435204,"about_ca_topic_score_gemma":0.00036221143,"teacher_disagreement_score":0.81537443,"about_ca_system_score_codex":0.00018715467,"about_ca_system_score_gemma":0.00030412455,"threshold_uncertainty_score":0.9997362},"labels":[],"label_agreement":null},{"id":"W2898179508","doi":"10.35799/dc.6.2.2017.17837","title":"Prediksi Tinggi Gelombang Laut di Perairan Laut Sulawesi Utara dengan Menggunakan Model Vector Autoregressive (VAR)","year":2017,"lang":"id","type":"article","venue":"d CARTESIAN","topic":"Data Mining and Machine Learning 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":"WiLAN (Canada)","funders":"","keywords":"Physics; Forestry; Geography","score_opus":0.023333061388323428,"score_gpt":0.28944220237634033,"score_spread":0.2661091409880169,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898179508","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":[0.66144353,0.0034857146,0.20832585,0.032194763,0.006207724,0.0034283113,0.0017748019,0.003935973,0.07920334],"genre_scores_gemma":[0.9754716,0.00004442719,0.009935282,0.00031917045,0.0008336634,0.0001468976,0.00022085973,0.000118309224,0.0129097905],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99523485,0.00029903668,0.0006711894,0.0017252966,0.00079015637,0.0012794605],"domain_scores_gemma":[0.99338126,0.00019724856,0.0008760027,0.004637804,0.00028856465,0.00061910535],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00082788576,0.0007638404,0.00072790164,0.00019969052,0.0033076878,0.0026665665,0.004432418,0.0003871746,0.00003791517],"category_scores_gemma":[0.0005208889,0.0007879765,0.00031989816,0.00021832612,0.00049195916,0.0012577219,0.0012548409,0.0012406014,0.0006664299],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019049288,0.0026287623,0.061196122,0.0011530202,0.0017409933,0.0011572108,0.13378878,0.025103532,0.020883115,0.2172714,0.09887023,0.43601635],"study_design_scores_gemma":[0.0011129398,0.0002333928,0.052596793,0.00037046825,0.00019067878,0.00008105383,0.00022059423,0.905279,0.0008746561,0.0005786115,0.03730416,0.0011576769],"about_ca_topic_score_codex":0.0007072907,"about_ca_topic_score_gemma":0.00019490569,"teacher_disagreement_score":0.8801755,"about_ca_system_score_codex":0.0001723755,"about_ca_system_score_gemma":0.00061150064,"threshold_uncertainty_score":0.9994571},"labels":[],"label_agreement":null},{"id":"W2900961417","doi":"10.37676/jmi.v14i1.468","title":"Korelasi Faktor Penyebab Tindak Kekerasan dalam Rumah Tangga Menggunakan Data Mining Algoritma A Priori","year":2018,"lang":"id","type":"article","venue":"JURNAL MEDIA INFOTAMA","topic":"Data Mining and Machine Learning 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":"Encana (Canada)","funders":"","keywords":"Humanities; Physics; Philosophy","score_opus":0.046737267300961005,"score_gpt":0.31099303613737916,"score_spread":0.26425576883641816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900961417","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":[0.6084287,0.0044482686,0.22217767,0.03110428,0.03876067,0.0036750496,0.0022895904,0.0033012189,0.08581453],"genre_scores_gemma":[0.66793436,0.00057018764,0.29929003,0.0021410836,0.01781028,0.00018534904,0.002370393,0.00032196048,0.0093763545],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9930544,0.0004004874,0.0014326158,0.0020087154,0.0015639131,0.0015399061],"domain_scores_gemma":[0.99105024,0.001162318,0.0010637837,0.0051414026,0.00054049655,0.0010417703],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022619786,0.0008328568,0.0008335776,0.00038978993,0.0012885102,0.0015380036,0.007499065,0.00044729028,0.0003906704],"category_scores_gemma":[0.0027446677,0.0008291246,0.00018816646,0.0015508706,0.0007543983,0.002042831,0.0042346255,0.0016649454,0.0032000316],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006004035,0.0005394766,0.017114865,0.00009924789,0.00031795594,0.00011681511,0.021395981,0.0000048756606,0.00063180795,0.003559079,0.0958516,0.86030823],"study_design_scores_gemma":[0.0019082549,0.0009316702,0.06358675,0.00057569117,0.00025109437,0.00041190156,0.0007954749,0.069751635,0.00031532743,0.00014357195,0.8600037,0.001324902],"about_ca_topic_score_codex":0.00021536752,"about_ca_topic_score_gemma":0.00029072468,"teacher_disagreement_score":0.85898334,"about_ca_system_score_codex":0.00018306916,"about_ca_system_score_gemma":0.0011326491,"threshold_uncertainty_score":0.9994985},"labels":[],"label_agreement":null},{"id":"W2909881582","doi":"10.24843/mite.2018.v17i03.p16","title":"Genetic K-Means Algorithms, ASSU Analisis Peningkatan Kompetensi Mahasiswa Menggunakan Model Pembelajaran ASSURE berbasis Project-Based Learning","year":2018,"lang":"id","type":"article","venue":"Majalah Ilmiah Teknologi Elektro","topic":"Data Mining and Machine Learning 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":"Innovation Cluster (Canada)","funders":"","keywords":"Computer science; Humanities; Mathematics; Philosophy","score_opus":0.02416811254329771,"score_gpt":0.28561373461707595,"score_spread":0.26144562207377825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2909881582","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13287564,0.0019460712,0.8327864,0.009593986,0.0016099928,0.002461914,0.00058745954,0.004436653,0.013701878],"genre_scores_gemma":[0.69859934,0.00017980461,0.28945807,0.001146993,0.0008999249,0.0003376729,0.00040524398,0.0002477659,0.008725181],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9889699,0.0013085513,0.0016382182,0.003682748,0.001602232,0.0027983184],"domain_scores_gemma":[0.9924869,0.00056146196,0.0012596963,0.0038774048,0.0011722385,0.0006423079],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0018672171,0.0015927964,0.0015177154,0.0012032317,0.0026654995,0.001503268,0.004503545,0.0010214545,0.00019735827],"category_scores_gemma":[0.001120672,0.001641585,0.0006237683,0.003134869,0.0011540479,0.0008003049,0.0014471003,0.0030817115,0.0014800066],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00051693065,0.0032526732,0.10398436,0.00066454004,0.0024658407,0.00084028556,0.012725189,0.092758685,0.010064118,0.0066653467,0.2954682,0.4705938],"study_design_scores_gemma":[0.00181305,0.001763085,0.018395944,0.00021732677,0.00053678436,0.00016631458,0.0004589495,0.8552983,0.001063244,0.00014843226,0.11832685,0.0018117485],"about_ca_topic_score_codex":0.0012201479,"about_ca_topic_score_gemma":0.00033914973,"teacher_disagreement_score":0.76253957,"about_ca_system_score_codex":0.00044077268,"about_ca_system_score_gemma":0.0015255467,"threshold_uncertainty_score":0.999682},"labels":[],"label_agreement":null},{"id":"W2910038901","doi":"10.24843/mite.2018.v17i03.p12","title":"Sistem Informasi Geografis Pemetaan Persebaran Alumni dengan Analisa Clustering","year":2018,"lang":"id","type":"article","venue":"Majalah Ilmiah Teknologi Elektro","topic":"Data Mining and Machine Learning 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":"Innovation Cluster (Canada)","funders":"","keywords":"Cluster analysis; Physics; Cluster (spacecraft); Computer science; Database; Operating system; Statistics; Mathematics","score_opus":0.02035813353643767,"score_gpt":0.2701337795502442,"score_spread":0.24977564601380653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2910038901","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":[0.49224973,0.0026133845,0.35290208,0.014390877,0.0073066675,0.0028771684,0.0002043372,0.006297117,0.12115863],"genre_scores_gemma":[0.9420469,0.00017935202,0.026258476,0.0016751903,0.0011155261,0.00014250529,0.00021098976,0.0000996697,0.028271439],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99398655,0.0004631071,0.0011652036,0.001692853,0.0008283782,0.0018639402],"domain_scores_gemma":[0.99498945,0.0002805483,0.0006933043,0.0030251092,0.0004767884,0.00053477107],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015320296,0.00088909507,0.0008584815,0.0005927544,0.0017808133,0.0013078747,0.00384766,0.00054039655,0.00020803022],"category_scores_gemma":[0.0005943319,0.000883737,0.0004038916,0.0016527079,0.0009889344,0.001109101,0.0022032633,0.001446473,0.003134023],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028509038,0.0016105404,0.09450794,0.00068632426,0.0019489675,0.00038276194,0.028010657,0.0007930802,0.009747543,0.045751132,0.078199595,0.7380764],"study_design_scores_gemma":[0.0017750354,0.0018584215,0.057224773,0.00024131397,0.00033710117,0.00045299597,0.0014906857,0.098101236,0.0021156282,0.00017542878,0.83435637,0.0018710232],"about_ca_topic_score_codex":0.00035834973,"about_ca_topic_score_gemma":0.0005580344,"teacher_disagreement_score":0.75615674,"about_ca_system_score_codex":0.00025547066,"about_ca_system_score_gemma":0.00031611463,"threshold_uncertainty_score":0.99972886},"labels":[],"label_agreement":null},{"id":"W2912648573","doi":"10.1007/978-1-4842-3988-9_12","title":"Stacks and Queues","year":2019,"lang":"en","type":"book-chapter","venue":"Apress eBooks","topic":"Data Mining and Machine Learning 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":"Hamilton Health Sciences","funders":"","keywords":"Queue; Computer science; Distributed computing; Theoretical computer science; Data structure; Programming language","score_opus":0.01469525053696328,"score_gpt":0.23386014326234902,"score_spread":0.21916489272538575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912648573","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":[0.000022126746,0.0003159693,0.02094672,0.00014481797,0.00015157249,0.00017173699,0.000034373898,0.0002665068,0.97794616],"genre_scores_gemma":[0.0024985913,0.000032723798,0.006862311,0.0002963581,0.000084454194,0.000013944803,0.000031597905,0.00003419277,0.9901458],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989927,0.000012211469,0.00015809076,0.00050972373,0.0001680241,0.00015926347],"domain_scores_gemma":[0.99860865,0.00010119369,0.00013079046,0.0010439716,0.000039538914,0.000075868484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000107958585,0.0002081135,0.00021600295,0.000084174455,0.000091600035,0.00019176886,0.00073734333,0.00015500226,0.000013751794],"category_scores_gemma":[0.000009076187,0.00019945858,0.000044408473,0.0000051635166,0.00007026784,0.000074834425,0.00059556164,0.00034673116,0.0002540027],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.3267776e-7,0.0000018064674,0.000002900265,0.000021084918,0.000021148266,0.0000025987542,0.00018413435,0.0000017041381,0.000021954525,0.88496125,0.004706355,0.11007426],"study_design_scores_gemma":[0.00009840269,0.000034164055,0.000017697088,0.000080327256,0.000017562574,0.000012722897,0.0000016608184,0.0007262902,0.000039630377,0.025206983,0.97350806,0.00025648501],"about_ca_topic_score_codex":0.000046517158,"about_ca_topic_score_gemma":0.0000068760137,"teacher_disagreement_score":0.96880174,"about_ca_system_score_codex":0.000010767597,"about_ca_system_score_gemma":0.000067158624,"threshold_uncertainty_score":0.8133685},"labels":[],"label_agreement":null},{"id":"W2936569492","doi":"10.31602/tji.v9i4.1537","title":"OPTIMASI MODEL KLASIFIKASI C4.5 DAN PARTICLE SWARM OPTIMIZATION UNTUK PREDIKSI SISWA BERMASALAH","year":2018,"lang":"id","type":"article","venue":"Technologia Jurnal Ilmiah","topic":"Data Mining and Machine Learning 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":"Institute of Particle Physics","funders":"","keywords":"Humanities; Physics; Philosophy","score_opus":0.02116555512425701,"score_gpt":0.2747728532495757,"score_spread":0.2536072981253187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2936569492","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15841962,0.00038639535,0.82630676,0.006086753,0.00054340274,0.000559103,0.000046649202,0.0026647253,0.0049865786],"genre_scores_gemma":[0.7837498,0.0002441307,0.21187904,0.0004098963,0.0002851592,0.00011359332,0.00006277239,0.00007526554,0.0031803423],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955712,0.0001389058,0.0009277774,0.0014461019,0.0007182677,0.0011977446],"domain_scores_gemma":[0.9958827,0.00013131426,0.0006398419,0.002470681,0.00053006876,0.00034538776],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00083330285,0.00062092295,0.00055568415,0.00037743294,0.0011030724,0.0006661273,0.003277837,0.0006600669,0.000048048165],"category_scores_gemma":[0.0005581603,0.0006199005,0.00018358252,0.002043158,0.0010297379,0.0010362573,0.0012314107,0.0013616194,0.00075263134],"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":[0.00016718073,0.0021870984,0.0078925835,0.00018154837,0.0004286177,0.00009251383,0.0038857686,0.6974357,0.015563614,0.09776095,0.027405676,0.1469988],"study_design_scores_gemma":[0.00074710796,0.000680339,0.00063027604,0.00013067978,0.00012136913,0.00010741316,0.00018182912,0.96808237,0.02170774,0.00083751563,0.006093642,0.00067972863],"about_ca_topic_score_codex":0.000062788575,"about_ca_topic_score_gemma":0.000012747789,"teacher_disagreement_score":0.62533015,"about_ca_system_score_codex":0.0002172175,"about_ca_system_score_gemma":0.0003740429,"threshold_uncertainty_score":0.9996252},"labels":[],"label_agreement":null},{"id":"W2937852761","doi":"10.31937/si.v9i2.991","title":"Visualisasi Data Penjualan dan Produksi PT Nitto Alam Indonesia Periode 2014-2018","year":2019,"lang":"en","type":"article","venue":"Ultima InfoSys Jurnal Ilmu Sistem Informasi","topic":"Data Mining and Machine Learning Applications","field":"Computer Science","cited_by":17,"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":"Dashboard; Production (economics); Visualization; Quarter (Canadian coin); Business; Data visualization; Computer science; Database; Marketing; Geography; Economics; Data mining","score_opus":0.02271163559400273,"score_gpt":0.2855543445041292,"score_spread":0.26284270891012645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2937852761","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":[0.73817515,0.00045588284,0.0801412,0.0053172396,0.004572631,0.0036509533,0.00031972906,0.0033037337,0.16406347],"genre_scores_gemma":[0.9456784,0.000058535992,0.042805903,0.0017841342,0.00049543317,0.00013319011,0.0018463932,0.00008338367,0.0071146023],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99618727,0.00011951136,0.0010673574,0.00091742084,0.0008877163,0.00082073355],"domain_scores_gemma":[0.99425846,0.00019626015,0.00068967586,0.0042062383,0.00026743283,0.0003819269],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013490902,0.00050129637,0.0005325216,0.00032154217,0.0005037902,0.0012212375,0.0052998243,0.00019757373,0.000045072953],"category_scores_gemma":[0.00019544225,0.00044743466,0.0001397617,0.0006348631,0.00012042701,0.004581845,0.002283481,0.0006242485,0.002133807],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025408337,0.0010409098,0.313236,0.0010996092,0.0006595453,0.00007674031,0.018568136,0.0019086672,0.0030827355,0.13751571,0.13438503,0.38817284],"study_design_scores_gemma":[0.0011208692,0.00024996893,0.04242899,0.00013280855,0.000039362538,0.00030086996,0.00035859313,0.080785505,0.00039246312,0.000025326997,0.8733604,0.00080486864],"about_ca_topic_score_codex":0.000092149974,"about_ca_topic_score_gemma":0.00002492902,"teacher_disagreement_score":0.73897535,"about_ca_system_score_codex":0.00011375256,"about_ca_system_score_gemma":0.00040709836,"threshold_uncertainty_score":0.9998156},"labels":[],"label_agreement":null},{"id":"W2947432535","doi":"10.24900/ijss/0301189198.2019.0501","title":"SUBSPACE CLUSTERING ANALYSIS USING DBSCAN AND SUBCLU FOR PROJECTING STMIK JAKARTA ALUMNI JOB","year":2019,"lang":"en","type":"article","venue":"International Journal of Safety Science","topic":"Data Mining and Machine Learning 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":"Cluster analysis; DBSCAN; Subspace topology; Computer science; Artificial intelligence; Fuzzy clustering","score_opus":0.016743408105029008,"score_gpt":0.329906611545044,"score_spread":0.313163203440015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947432535","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":[0.40170756,0.00003303981,0.5962404,0.0012498563,0.0004507856,0.000078744306,0.0000061962096,0.0000146685925,0.00021871571],"genre_scores_gemma":[0.8621376,0.000014085977,0.13756168,0.00010274848,0.000091125024,0.000001307913,0.0000013887808,0.0000044532676,0.00008556846],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984555,0.00002766341,0.00036271015,0.00030811137,0.00063991983,0.00020608582],"domain_scores_gemma":[0.99830425,0.00022965149,0.00045403518,0.00025493966,0.0006555865,0.000101563586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001930392,0.00009258972,0.00017645485,0.00066994823,0.00020927502,0.00042052558,0.0016187144,0.000022932974,0.000005551299],"category_scores_gemma":[0.00025795345,0.00008281431,0.000094964824,0.00093827647,0.00010238409,0.0013440088,0.00030641878,0.00015463014,0.0000028342292],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025329206,0.00020550027,0.43844938,0.000054966775,0.0011937459,0.000029323037,0.01442046,0.24277589,0.07922865,0.056496684,0.00017422921,0.16671787],"study_design_scores_gemma":[0.0004682934,0.00009086224,0.04965562,0.00006103845,0.00005468851,0.00020962334,0.00030435735,0.9467736,0.00048017586,0.00039622374,0.0013546253,0.00015090533],"about_ca_topic_score_codex":0.00009315849,"about_ca_topic_score_gemma":0.000025698551,"teacher_disagreement_score":0.7039977,"about_ca_system_score_codex":0.0001273467,"about_ca_system_score_gemma":0.0002379226,"threshold_uncertainty_score":0.4055138},"labels":[],"label_agreement":null},{"id":"W2952308251","doi":"10.35585/inspir.v7i2.2448","title":"Sistem Cerdas Dalam Penentuan Daun Kelor Sebagai Imunustimulan","year":2017,"lang":"id","type":"article","venue":"Inspiration Jurnal Teknologi Informasi dan Komunikasi","topic":"Data Mining and Machine Learning 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":"Computer science","score_opus":0.04020599185130958,"score_gpt":0.3059219055050172,"score_spread":0.2657159136537076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952308251","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":[0.54193145,0.0008138673,0.09965071,0.02534182,0.0072014118,0.0028168363,0.00015266759,0.0027508803,0.31934038],"genre_scores_gemma":[0.9681082,0.00034150033,0.012473668,0.0010457446,0.0006827115,0.00011440017,0.00044645887,0.000079165904,0.01670818],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9949378,0.00028464082,0.0015998449,0.0010248792,0.0009748824,0.001177968],"domain_scores_gemma":[0.9914047,0.00024121298,0.0024340802,0.004781818,0.00060105417,0.0005371248],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0014745396,0.000827662,0.00074789167,0.00044382186,0.005263736,0.0051439963,0.0064793304,0.00058355456,0.000029041119],"category_scores_gemma":[0.0013756896,0.0008030765,0.00036203873,0.0004517069,0.0007421728,0.005286409,0.0024506005,0.0018555758,0.00067421515],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009604307,0.00065649534,0.03923329,0.00024230813,0.00035883323,0.00018207623,0.0060083834,0.0025193444,0.0012337504,0.17887235,0.00401898,0.76657814],"study_design_scores_gemma":[0.0018699259,0.00094062777,0.1202642,0.00028356822,0.00012955128,0.00035530384,0.00045949162,0.05918439,0.0012085503,0.00022386375,0.8138945,0.0011859951],"about_ca_topic_score_codex":0.0001214205,"about_ca_topic_score_gemma":0.00014734585,"teacher_disagreement_score":0.80987555,"about_ca_system_score_codex":0.0002847793,"about_ca_system_score_gemma":0.00066950894,"threshold_uncertainty_score":0.99944204},"labels":[],"label_agreement":null},{"id":"W2965064908","doi":"10.33480/jitk.v5i1.613","title":"PENERAPAN METODE K-NEAREST NEIGHBOR DAN INFORMATION GAIN PADA KLASIFIKASI KINERJA SISWA","year":2019,"lang":"en","type":"article","venue":"JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer)","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"k-nearest neighbors algorithm; Information gain; Computer science; Large margin nearest neighbor; Artificial intelligence; Pattern recognition (psychology); Data mining","score_opus":0.01131267473939492,"score_gpt":0.24065144561813412,"score_spread":0.2293387708787392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2965064908","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":[0.6031149,0.00032538784,0.37417188,0.007027376,0.0018416456,0.0011414263,0.000064796644,0.0020695014,0.010243056],"genre_scores_gemma":[0.89025444,0.00008108031,0.105956435,0.0018623405,0.0003751154,0.0000921806,0.0003350715,0.00004753127,0.0009957964],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961227,0.00033899816,0.00092748477,0.0009498892,0.0007341313,0.00092677143],"domain_scores_gemma":[0.9961586,0.0003656464,0.00068527064,0.002171184,0.0002639033,0.00035537235],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009125232,0.00056197797,0.0005975905,0.00058371236,0.00045611852,0.0011047289,0.0033204756,0.00027591534,0.000049574937],"category_scores_gemma":[0.00021958479,0.00050614437,0.00025462612,0.001016607,0.00012159029,0.003006803,0.0012377087,0.001021875,0.0013864607],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000088458364,0.0009070141,0.03666865,0.00030904877,0.000490326,0.00011877636,0.005784797,0.014745034,0.01347843,0.12530221,0.072176605,0.72993064],"study_design_scores_gemma":[0.0021527892,0.0010299236,0.08952087,0.0001444152,0.00007596903,0.0004206646,0.0003138062,0.3082815,0.0035989985,0.0013601691,0.5914944,0.0016065179],"about_ca_topic_score_codex":0.00020462417,"about_ca_topic_score_gemma":0.000036694873,"teacher_disagreement_score":0.7283241,"about_ca_system_score_codex":0.00014978343,"about_ca_system_score_gemma":0.00022888601,"threshold_uncertainty_score":0.9999322},"labels":[],"label_agreement":null},{"id":"W2979739058","doi":"10.33322/kilat.v8i2.551","title":"Penerapan Metode Triple Exponential Smoothing Pada Sistem Prediksi Keuntungan Bisnis Ayam Broiler Guna Meningkatkan Pengelolaan Keuangan Peternak","year":2019,"lang":"en","type":"article","venue":"Kilat","topic":"Data Mining and Machine Learning 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":"WiLAN (Canada)","funders":"","keywords":"Monte Carlo method; Exponential smoothing; Mathematics; Value (mathematics); Statistics; Profit (economics); Bankruptcy; Exponential function; Smoothing; Econometrics; Applied mathematics; Economics; Microeconomics; Mathematical analysis; Finance","score_opus":0.008298942351034243,"score_gpt":0.2282417158129216,"score_spread":0.21994277346188737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979739058","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":[0.88529575,0.0002894281,0.08830358,0.002010799,0.002383539,0.00079039636,0.00004506839,0.0014597923,0.019421631],"genre_scores_gemma":[0.959419,0.000015462898,0.028266992,0.000313238,0.0002725758,0.00007182039,0.00011923431,0.000057369158,0.011464287],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970781,0.00019107615,0.0004695206,0.0010297056,0.0005925278,0.00063902786],"domain_scores_gemma":[0.99748653,0.00015949998,0.00027956313,0.0017292371,0.00008433766,0.0002608336],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00062133954,0.00035762237,0.00039025114,0.00022333532,0.00043212264,0.00062537217,0.0018613749,0.00013433778,0.00007079338],"category_scores_gemma":[0.000072827184,0.00035030072,0.00016239402,0.00048924977,0.000050799797,0.00091414625,0.0006260695,0.0005230967,0.00054439966],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023547128,0.0015020489,0.03501928,0.00040399205,0.0008179339,0.00011825405,0.030826453,0.0029149775,0.39712337,0.10824417,0.06523673,0.3575573],"study_design_scores_gemma":[0.004505561,0.0007458708,0.01897524,0.00029156232,0.00016257791,0.00018903882,0.00050962553,0.27551714,0.02041305,0.0007041211,0.675747,0.0022392028],"about_ca_topic_score_codex":0.0004979754,"about_ca_topic_score_gemma":0.00007643903,"teacher_disagreement_score":0.6105103,"about_ca_system_score_codex":0.000085696265,"about_ca_system_score_gemma":0.0001029115,"threshold_uncertainty_score":0.9998949},"labels":[],"label_agreement":null},{"id":"W2989613929","doi":"10.14203/oseana.2018.vol.43no.2.16","title":"KARAKTERISTIK DAN DAMPAK SIKLON TROPIS YANG TUMBUH DI SEKITAR WILAYAH INDONESIA","year":2018,"lang":"en","type":"article","venue":"OSEANA","topic":"Data Mining and Machine Learning 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":"WiLAN (Canada)","funders":"","keywords":"Tropical cyclone; Cyclone (programming language); Extratropical cyclone; Climatology; Environmental science; Equator; Tropical cyclone scales; Latitude; Geography; Geology","score_opus":0.010287183616090555,"score_gpt":0.2599549192476049,"score_spread":0.24966773563151434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2989613929","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":[0.692494,0.00007880964,0.28823203,0.002917457,0.0004186512,0.00019395961,0.000022908602,0.000723308,0.014918889],"genre_scores_gemma":[0.98494416,0.000006193558,0.013698585,0.00035668878,0.0003212475,0.000025759406,0.000055969456,0.00001955513,0.0005718314],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9985785,0.00008934287,0.00019879924,0.00052511616,0.00024851007,0.00035971653],"domain_scores_gemma":[0.99842703,0.00007543642,0.00009634847,0.001169683,0.000073639,0.00015787974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024436144,0.00016400903,0.00016211552,0.0001056805,0.00035810604,0.00022083857,0.0012198692,0.000057535584,0.000014268333],"category_scores_gemma":[0.00006713745,0.00015635088,0.000053701744,0.00045469802,0.00013142588,0.0003497774,0.00039639176,0.00021005097,0.00053164817],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004139264,0.00052228797,0.082610644,0.00007487068,0.00013990782,0.00008466514,0.0073063453,0.00013264314,0.010364599,0.16662508,0.0973008,0.63479674],"study_design_scores_gemma":[0.0011423175,0.0007690543,0.47474048,0.00010197093,0.000052934643,0.00009919444,0.00017176107,0.0872961,0.0031644197,0.0019822435,0.4293255,0.001154017],"about_ca_topic_score_codex":0.00026819052,"about_ca_topic_score_gemma":0.000040342646,"teacher_disagreement_score":0.63364273,"about_ca_system_score_codex":0.000036946585,"about_ca_system_score_gemma":0.0000635484,"threshold_uncertainty_score":0.68334395},"labels":[],"label_agreement":null},{"id":"W2992213878","doi":"10.30865/komik.v3i1.1677","title":"ANALISIS METODE K-MEANS PADA PENGELOMPOKAN PERGURUAN TINGGI MENURUT PROVINSI BERDASARKAN FASILITAS YANG DIMILIKI DESA","year":2019,"lang":"en","type":"article","venue":"KOMIK (Konferensi Nasional Teknologi Informasi dan Komputer)","topic":"Data Mining and Machine Learning 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":"Innovation Cluster (Canada)","funders":"","keywords":"Workforce; Cluster (spacecraft); Government (linguistics); Agency (philosophy); Indonesian; Higher education; Quality (philosophy); Geography; Political science; Library science; Business; Sociology; Computer science; Social science; Physics","score_opus":0.013022031228560446,"score_gpt":0.24158666403790052,"score_spread":0.22856463280934008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2992213878","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":[0.8625479,0.00029381897,0.10260862,0.0057310155,0.0018122456,0.0016751689,0.00012116627,0.002828647,0.022381416],"genre_scores_gemma":[0.89366007,0.0000632554,0.102860816,0.0014171947,0.00023591213,0.00010353497,0.0006390892,0.00006361874,0.00095649256],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99484193,0.00027066516,0.0011242398,0.0014690185,0.0010216947,0.0012724552],"domain_scores_gemma":[0.99540013,0.0006449327,0.0005724526,0.0024596357,0.0004417951,0.00048107878],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009791913,0.00081659935,0.00086966774,0.0006316655,0.0006598417,0.0006834919,0.0033037935,0.00040283962,0.000037098576],"category_scores_gemma":[0.0003400732,0.0007174274,0.00038336986,0.0010522874,0.00021561132,0.0019227687,0.0021645972,0.0011726051,0.00058194035],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018165763,0.0009875507,0.047939427,0.00035858163,0.00076253666,0.00017634171,0.0074887653,0.0050844555,0.0063427533,0.45716065,0.0356006,0.4379167],"study_design_scores_gemma":[0.0038452132,0.0016776694,0.15257744,0.00041967278,0.00015455154,0.0009055256,0.0018218878,0.3450032,0.0042884443,0.0020652832,0.48393846,0.0033026624],"about_ca_topic_score_codex":0.00015432326,"about_ca_topic_score_gemma":0.00007158123,"teacher_disagreement_score":0.45509535,"about_ca_system_score_codex":0.00023886026,"about_ca_system_score_gemma":0.00053763104,"threshold_uncertainty_score":0.9995277},"labels":[],"label_agreement":null},{"id":"W2994231404","doi":"10.30865/komik.v3i1.1675","title":"PEMANFAATAN DATAMINING PADA PENGELOMPOKAN PROVINSI TERHADAP PENCEMARAN LINGKUNGAN HIDUP","year":2019,"lang":"en","type":"article","venue":"KOMIK (Konferensi Nasional Teknologi Informasi dan Komputer)","topic":"Data Mining and Machine Learning 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":"Innovation Cluster (Canada)","funders":"","keywords":"Pollution; Geography; Java; Environmental pollution; Environmental protection; Ecology; Computer science; Biology","score_opus":0.01530618588813311,"score_gpt":0.24308824167758164,"score_spread":0.22778205578944852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994231404","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":[0.7523385,0.0002442571,0.20850614,0.006171017,0.0033701314,0.0022268912,0.000079437865,0.0039645517,0.023099035],"genre_scores_gemma":[0.8805441,0.000052220355,0.11524006,0.0011382006,0.00027687615,0.00007544584,0.0008835842,0.000054198128,0.0017352642],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99535584,0.00017114979,0.0010459564,0.0014014832,0.0009077148,0.0011178721],"domain_scores_gemma":[0.9955796,0.00052144594,0.00059229723,0.002600331,0.00031338359,0.0003929234],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00087447005,0.0007103074,0.0007457711,0.0004888406,0.0005811317,0.00087413687,0.0038322215,0.00033595067,0.000024645298],"category_scores_gemma":[0.0002568679,0.00062703167,0.00022428516,0.0007522346,0.00018659756,0.0024753949,0.0027238212,0.0012029179,0.000647931],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011376989,0.00062910037,0.019876562,0.00029451042,0.00028244554,0.00021558869,0.0041934005,0.0015484085,0.0073557245,0.57131106,0.015512169,0.37866727],"study_design_scores_gemma":[0.0036838076,0.0016393735,0.07883927,0.0005443824,0.00006938555,0.0015031385,0.0010631616,0.27024835,0.0039046416,0.0016577876,0.6339664,0.0028803318],"about_ca_topic_score_codex":0.000037030844,"about_ca_topic_score_gemma":0.00002005441,"teacher_disagreement_score":0.6184542,"about_ca_system_score_codex":0.00013840485,"about_ca_system_score_gemma":0.00059643295,"threshold_uncertainty_score":0.9996181},"labels":[],"label_agreement":null},{"id":"W2997912748","doi":"10.29303/emj.v1i2.37","title":"Analisis Dependensi Faktor Makroekonomi terhadap Tingkat Harga Emas Dunia dengan Pendekatan Copula","year":2019,"lang":"en","type":"article","venue":"EIGEN MATHEMATICS JOURNAL","topic":"Data Mining and Machine Learning 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":"McGill University","keywords":"Copula (linguistics); Econometrics; Gumbel distribution; Economics; Tail dependence; Mathematics; Statistics; Extreme value theory; Multivariate statistics","score_opus":0.010606650693331358,"score_gpt":0.24496437403034518,"score_spread":0.23435772333701382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997912748","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":[0.4735582,0.000144902,0.5165754,0.0010139499,0.0006331642,0.00029326463,0.000017048638,0.0002552588,0.007508819],"genre_scores_gemma":[0.759414,0.000022253811,0.23855698,0.0002210902,0.00020921744,0.000008598383,0.000016474616,0.00004036202,0.0015109865],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978839,0.00011376943,0.00060397905,0.00040272067,0.0005241704,0.00047147428],"domain_scores_gemma":[0.9977262,0.00021179415,0.0005220059,0.0011236328,0.00013727554,0.00027911377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011804983,0.00026088062,0.00035964668,0.00021318324,0.0004359412,0.0008619408,0.0016972007,0.00009401692,0.00023569852],"category_scores_gemma":[0.00016736399,0.00023009893,0.00015388658,0.00030813,0.000032726755,0.0005758913,0.0004011436,0.0006786357,0.00067128893],"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":[0.000051902985,0.0024178957,0.06774451,0.0009017669,0.0016013894,0.00074138533,0.03832939,0.007822609,0.02650041,0.6243076,0.12035479,0.10922639],"study_design_scores_gemma":[0.0074208486,0.0014387895,0.04490302,0.001631172,0.0007420199,0.023840483,0.014678492,0.6177407,0.010674171,0.13361388,0.13702576,0.0062906905],"about_ca_topic_score_codex":0.000013579621,"about_ca_topic_score_gemma":0.000008195893,"teacher_disagreement_score":0.60991806,"about_ca_system_score_codex":0.00009518683,"about_ca_system_score_gemma":0.00015009823,"threshold_uncertainty_score":0.9383162},"labels":[],"label_agreement":null},{"id":"W2999803802","doi":"10.18860/mat.v11i2.7821","title":"Implementasi Data Mining Dalam Memprediksi Transaksi Penjualan Menggunakan Algoritma Apriori (Studi Kasus PT.Arma Anugerah Abadi Cabang Sei Rampah)","year":2020,"lang":"id","type":"article","venue":"Matics Jurnal Ilmu Komputer dan Teknologi Informasi (Journal of Computer Science and Information Technology)","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"Association rule learning; Apriori algorithm; Data mining; Database transaction; Computer science; Value (mathematics); Transaction data; Set (abstract data type); Database; Machine learning","score_opus":0.02852857661632966,"score_gpt":0.2779659687974227,"score_spread":0.24943739218109304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2999803802","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09298538,0.0004457282,0.884269,0.018191699,0.00211346,0.0008321404,0.00013124112,0.0005235353,0.00050782546],"genre_scores_gemma":[0.23786989,0.001504455,0.7524589,0.0067444867,0.0010605883,0.000022743197,0.00024909092,0.000054507676,0.000035354136],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9914422,0.0001451311,0.0038108223,0.00088345946,0.0022114224,0.0015069867],"domain_scores_gemma":[0.99121094,0.0002582767,0.0036412661,0.0019922315,0.0019999363,0.0008973378],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.004407417,0.0009225025,0.001300624,0.002323823,0.0015273455,0.0032432885,0.010156818,0.00049025327,0.0000085474385],"category_scores_gemma":[0.000618407,0.0008229602,0.00020666752,0.0043412508,0.0015258873,0.021133613,0.005773775,0.0022603509,0.00004798299],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058177666,0.00016598983,0.001758366,0.00034889526,0.00033391695,0.00007459893,0.028179234,0.00088248897,0.00014646782,0.006009929,0.011128464,0.9509135],"study_design_scores_gemma":[0.0027830687,0.0031362372,0.0018610219,0.0004056183,0.00020189102,0.0024265703,0.0034775287,0.6825674,0.000990542,0.00013941678,0.30095062,0.0010600312],"about_ca_topic_score_codex":0.000007946257,"about_ca_topic_score_gemma":0.0000019173037,"teacher_disagreement_score":0.9498534,"about_ca_system_score_codex":0.00026537143,"about_ca_system_score_gemma":0.0016567241,"threshold_uncertainty_score":0.99977255},"labels":[],"label_agreement":null},{"id":"W3007013628","doi":"10.24198/jppm.v6i3.22975","title":"PENTINGNYA PEMBENTUKAN PROGRAM SEKOLAH SIAGA BENCANA BAGI KABUPATEN BANDUNG BARAT","year":2020,"lang":"id","type":"article","venue":"Prosiding Penelitian dan Pengabdian kepada Masyarakat","topic":"Data Mining and Machine Learning 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":"Encana (Canada)","funders":"","keywords":"Humanities; Psychology; Geography; Political science; Art","score_opus":0.03719362288462801,"score_gpt":0.2768442814581239,"score_spread":0.23965065857349588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3007013628","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":[0.7189571,0.011697585,0.045778368,0.103899635,0.0074855266,0.018365553,0.0017928751,0.014162401,0.07786093],"genre_scores_gemma":[0.97198784,0.00026250738,0.018602606,0.0023587006,0.0013579986,0.0006790566,0.00091853156,0.00029729656,0.0035354404],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9890667,0.0009949134,0.0017580551,0.0038134889,0.0015724667,0.0027943598],"domain_scores_gemma":[0.99294126,0.00044440854,0.0010392236,0.0026724548,0.00046075857,0.0024418905],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.00158906,0.0015878313,0.0014039198,0.00043186397,0.0024187907,0.0045590713,0.004981643,0.0005143501,0.00032580283],"category_scores_gemma":[0.0010338438,0.0017803687,0.0006322344,0.0026770053,0.00042734027,0.0022123,0.002451385,0.0026136443,0.0019023534],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045869002,0.003480966,0.15028341,0.0053209695,0.0013527168,0.0020925608,0.062977545,0.0012937019,0.029466098,0.032401856,0.124873385,0.5859981],"study_design_scores_gemma":[0.0054795477,0.0035517027,0.083419286,0.0022946107,0.0010358697,0.0005491412,0.0040508336,0.28792664,0.012911291,0.00041847784,0.5908722,0.007490396],"about_ca_topic_score_codex":0.0008520503,"about_ca_topic_score_gemma":0.00023640651,"teacher_disagreement_score":0.5785077,"about_ca_system_score_codex":0.00039562272,"about_ca_system_score_gemma":0.0009975976,"threshold_uncertainty_score":0.9996874},"labels":[],"label_agreement":null},{"id":"W3013665147","doi":"","title":"JARINGAN SYARAF TIRUAN UNTUK MEMPREDIKSI NILAI KELULUSAN SIDANG (STUDI KASUS : STMIK KAPUTAMA BINJAI )","year":2019,"lang":"ms","type":"article","venue":"","topic":"Data Mining and Machine Learning 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":"Computer science; Graduation (instrument); Software; Artificial neural network; Session (web analytics); Statistics; Machine learning; Mathematics","score_opus":0.005362795913257296,"score_gpt":0.2239698196112107,"score_spread":0.2186070236979534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013665147","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":[0.54690784,0.0014438885,0.1447328,0.015555981,0.006837263,0.0026554978,0.00022473617,0.003491989,0.27815],"genre_scores_gemma":[0.9163967,0.00008307278,0.014039618,0.0012885582,0.00050662836,0.00007123073,0.00012508864,0.00009968421,0.06738942],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99427605,0.0003105533,0.00092835026,0.002127555,0.00097517367,0.0013823162],"domain_scores_gemma":[0.9946923,0.00049294083,0.00046695778,0.0035115746,0.00025764605,0.00057857495],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012538817,0.0007737407,0.00081537355,0.00040215036,0.00074332993,0.0011811029,0.0033561916,0.00034739764,0.00085673685],"category_scores_gemma":[0.00019851436,0.00074166816,0.00029012558,0.0015533247,0.00020990739,0.00094184093,0.002374229,0.0012150027,0.011534009],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013978066,0.0023531737,0.06666824,0.00066687295,0.0010678786,0.00012917165,0.013774214,0.0063415007,0.013390205,0.32309026,0.14007634,0.43230236],"study_design_scores_gemma":[0.0031493523,0.0014827556,0.04452659,0.00048071268,0.00028547196,0.00014912087,0.0013912265,0.34262943,0.0026105638,0.0014469194,0.598942,0.00290588],"about_ca_topic_score_codex":0.002017175,"about_ca_topic_score_gemma":0.00015194457,"teacher_disagreement_score":0.45886564,"about_ca_system_score_codex":0.0001832371,"about_ca_system_score_gemma":0.00038429748,"threshold_uncertainty_score":0.99985576},"labels":[],"label_agreement":null},{"id":"W3013936196","doi":"","title":"ANALISA DAN PERBANDINGAN METODE ALGORITMA APRIORI DAN FP-GROWTH UNTUK MENCARI POLA DAERAH STRATEGIS PENGENALAN KAMPUS STUDI KASUS DI STKIP ADZKIA PADANG","year":2018,"lang":"id","type":"article","venue":"","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"Humanities; Computer science; Mathematics; Philosophy","score_opus":0.0259836335049272,"score_gpt":0.29265416584268533,"score_spread":0.2666705323377581,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013936196","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":[0.37450373,0.0024772712,0.48084497,0.010853709,0.0056608343,0.0026209364,0.000501602,0.0028282923,0.119708635],"genre_scores_gemma":[0.9624571,0.0002189467,0.024912512,0.00072220434,0.0016507256,0.00006899912,0.00041244662,0.00012669055,0.009430331],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9921205,0.00079708913,0.0012235842,0.002615254,0.0014143586,0.0018292065],"domain_scores_gemma":[0.99398994,0.00052953773,0.00069581077,0.0030769915,0.00071720657,0.0009905271],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0020196633,0.0011281124,0.0010671603,0.0004955542,0.0022796977,0.0021712536,0.004020843,0.000394526,0.00018012385],"category_scores_gemma":[0.00035995015,0.0010487151,0.00033786823,0.0022257152,0.00074166723,0.0012487874,0.0016951464,0.0013956943,0.000612763],"study_design_candidate":"not_applicable","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":[0.00024045283,0.003952062,0.103891976,0.0005645068,0.0041803904,0.00044983343,0.06829102,0.00016424636,0.019297192,0.486323,0.13723971,0.1754056],"study_design_scores_gemma":[0.009817769,0.010094967,0.27389756,0.0011271536,0.003271384,0.000798372,0.028363599,0.27843183,0.018729914,0.003796691,0.36074778,0.010922962],"about_ca_topic_score_codex":0.0070874896,"about_ca_topic_score_gemma":0.0010948824,"teacher_disagreement_score":0.5879534,"about_ca_system_score_codex":0.00034917242,"about_ca_system_score_gemma":0.000723228,"threshold_uncertainty_score":0.9995244},"labels":[],"label_agreement":null},{"id":"W3016217016","doi":"10.30645/kesatria.v1i1.11","title":"Penerapan K-Means Dalam Mengelompokkan Nilai Tambah Industri Besar/Sedang Menurut Kabupaten/Kota","year":2020,"lang":"en","type":"article","venue":"KESATRIA Jurnal Penerapan Sistem Informasi (Komputer & Manajemen)","topic":"Data Mining and Machine Learning 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":"Government (linguistics); Quarter (Canadian coin); Centroid; Tertiary sector of the economy; Business; Service (business); Manufacturing; Geography; Marketing; Computer science","score_opus":0.028259910491412212,"score_gpt":0.23704429164497878,"score_spread":0.20878438115356657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3016217016","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":[0.12519607,0.0011888928,0.72696525,0.051904112,0.0039202063,0.003342998,0.00009906563,0.0045306846,0.0828527],"genre_scores_gemma":[0.89369,0.00019153295,0.08469487,0.008119281,0.0026750392,0.00024973333,0.00073466834,0.00017644002,0.009468437],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9941666,0.00027926735,0.001611774,0.0013776243,0.0012446698,0.0013200704],"domain_scores_gemma":[0.99592024,0.00017889321,0.0008347047,0.0017393016,0.00029636538,0.0010304688],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0011063693,0.0008663087,0.0008930011,0.00042905335,0.0009964481,0.0015484117,0.0039197854,0.00032024877,0.00006151735],"category_scores_gemma":[0.00008162033,0.0008396846,0.00046311834,0.0016354808,0.00013653257,0.0029411076,0.0014878348,0.0013175552,0.00037295514],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016863599,0.0006157817,0.009644332,0.00040303613,0.001158404,0.00019728806,0.015497301,0.0164565,0.0038149843,0.20361523,0.05762022,0.6908083],"study_design_scores_gemma":[0.0026540847,0.00060887873,0.005227497,0.000093786606,0.00012387204,0.00013197729,0.00025096684,0.17247851,0.0010928485,0.00017277304,0.8159043,0.0012604655],"about_ca_topic_score_codex":0.000064119464,"about_ca_topic_score_gemma":0.00003564535,"teacher_disagreement_score":0.76849395,"about_ca_system_score_codex":0.00019059553,"about_ca_system_score_gemma":0.00036290308,"threshold_uncertainty_score":0.99948806},"labels":[],"label_agreement":null},{"id":"W3019608078","doi":"10.59697/jsik.v3i2.768","title":"PENGKLASTERAN DOKUMEN DENGAN MENGGUNAKAN ALGORITMA SUPPORT VECTOR CLUSTERING","year":2019,"lang":"en","type":"article","venue":"Jurnal Sistem Informasi Kaputama (JSIK)","topic":"Data Mining and Machine Learning 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":"Cluster analysis; Computer science; Artificial intelligence","score_opus":0.007554466004666319,"score_gpt":0.2339956613068401,"score_spread":0.22644119530217377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3019608078","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":[0.4082572,0.00016107011,0.30477867,0.0041771363,0.004708958,0.002077371,0.000058558697,0.0026702527,0.2731108],"genre_scores_gemma":[0.9715379,0.000012999952,0.017085312,0.0008342986,0.00025704326,0.00006539876,0.00009666311,0.00004130912,0.01006911],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971653,0.00008263326,0.00077613816,0.00056724943,0.0006606511,0.0007480149],"domain_scores_gemma":[0.99771285,0.00015631356,0.0003908674,0.001237266,0.00013642684,0.00036628856],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008129606,0.00037992193,0.00041700143,0.00024220739,0.00039662354,0.0008140336,0.0018694067,0.00014798122,0.00010612576],"category_scores_gemma":[0.000049236045,0.00035474374,0.00019616446,0.0005186463,0.00004457967,0.0018862376,0.0008090175,0.00066363544,0.0013641815],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000117685944,0.00043584048,0.032597575,0.00062760885,0.00044827067,0.000117160314,0.017078668,0.006096631,0.0045769867,0.06950278,0.008937227,0.8594636],"study_design_scores_gemma":[0.0017600837,0.0006050684,0.031805668,0.00012866211,0.000036400168,0.0005703445,0.00033789847,0.1290905,0.0007881431,0.00008902549,0.8338467,0.0009414838],"about_ca_topic_score_codex":0.000027044513,"about_ca_topic_score_gemma":0.00001587213,"teacher_disagreement_score":0.85852206,"about_ca_system_score_codex":0.00014329732,"about_ca_system_score_gemma":0.00019312878,"threshold_uncertainty_score":0.99989045},"labels":[],"label_agreement":null},{"id":"W3019826397","doi":"10.59697/jsik.v1i2.744","title":"DATA MINING UNTUK MENENTUKAN KORELASI (CONFIDENCE DAN SUPPORT) JURUSAN SISWA PADA TINGKAT SEKOLAH MENENGAH TERHADAP INDEKS PRESTASI KUMULATIF (IPK) DI PERGURUAN TINGGI SEBAGAI SOLUSI TEPAT PEMILIHAN PROGRAM STUDI DI PERGURUAN TINGGI","year":2017,"lang":"id","type":"article","venue":"Jurnal Sistem Informasi Kaputama (JSIK)","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"Humanities; Physics; Philosophy","score_opus":0.0600760371404558,"score_gpt":0.3364232073136976,"score_spread":0.27634717017324184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3019826397","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":[0.8854296,0.0012160036,0.008313227,0.0054799747,0.0058838557,0.0063974774,0.0009799192,0.0034232372,0.082876675],"genre_scores_gemma":[0.96800476,0.0003409203,0.014991151,0.00055818306,0.0013859791,0.0003692954,0.0025981476,0.00033886667,0.011412686],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9831495,0.0008579959,0.004325989,0.0040457784,0.0036281596,0.0039925706],"domain_scores_gemma":[0.9789745,0.001134126,0.006046225,0.010764351,0.0010550183,0.0020257677],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":["metaepi_narrow","open_science"],"category_scores_codex":[0.00635908,0.002594121,0.0024759907,0.00071341306,0.009103415,0.010325009,0.015618203,0.0011170886,0.00008597099],"category_scores_gemma":[0.0023740344,0.0025114587,0.00082090794,0.0011727795,0.0012583466,0.00800809,0.014416098,0.0040697698,0.0002314402],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026984853,0.0018907001,0.23810782,0.0014292224,0.001594504,0.00044820228,0.02669543,0.0015548704,0.0005877125,0.0026550514,0.00773936,0.71702725],"study_design_scores_gemma":[0.0038920245,0.0023959938,0.21056926,0.0026520623,0.0011544207,0.0008782772,0.005699171,0.28806412,0.00047125592,0.00004985437,0.4799492,0.004224344],"about_ca_topic_score_codex":0.0008126248,"about_ca_topic_score_gemma":0.0012308146,"teacher_disagreement_score":0.71280295,"about_ca_system_score_codex":0.000786496,"about_ca_system_score_gemma":0.0021859806,"threshold_uncertainty_score":0.9986794},"labels":[],"label_agreement":null},{"id":"W3020786358","doi":"10.33558/piksel.v8i1.2018","title":"Logistic Model Tree and Decision Tree J48 Algorithms for Predicting the Length of Study Period","year":2020,"lang":"en","type":"article","venue":"PIKSEL Penelitian Ilmu Komputer Sistem Embedded and Logic","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"C4.5 algorithm; Accreditation; Decision tree; Logistic regression; Decision tree learning; Informatics; ID3 algorithm; Point (geometry); Computer science; Medical education; Machine learning; Medicine; Mathematics; Engineering; Incremental decision tree; Naive Bayes classifier","score_opus":0.07151672977805348,"score_gpt":0.30942943676012563,"score_spread":0.23791270698207215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3020786358","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04937579,0.00035511344,0.94659644,0.002339348,0.0000940625,0.0006749309,0.00003916083,0.00017071825,0.0003544141],"genre_scores_gemma":[0.80331326,0.00002253363,0.19583736,0.0005320309,0.00012781375,0.00009483285,0.0000139858375,0.00001574513,0.000042421252],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99802554,0.00011430443,0.00047116342,0.00081171485,0.00026186544,0.0003154447],"domain_scores_gemma":[0.998335,0.0005394503,0.00021301334,0.0006170462,0.00010889002,0.00018658717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006409916,0.0002569297,0.00037870527,0.00007093241,0.0004188788,0.00032167594,0.0008759258,0.00007260099,0.0000015060018],"category_scores_gemma":[0.00016343083,0.00018369035,0.00008496179,0.0002459109,0.000116257776,0.00024396014,0.00057539233,0.00020636924,0.0000026938296],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007187495,0.00032688526,0.001332953,0.00019093238,0.00012767503,0.000012836796,0.027100578,0.010847598,0.000120001496,0.0221119,0.0012848743,0.9364719],"study_design_scores_gemma":[0.0010301005,0.00069875934,0.0035895156,0.000034236327,0.000062011764,0.000028348652,0.0010610253,0.9882121,0.000007776018,0.004571322,0.0004909798,0.00021380094],"about_ca_topic_score_codex":0.00002202161,"about_ca_topic_score_gemma":0.000015720241,"teacher_disagreement_score":0.97736454,"about_ca_system_score_codex":0.000012572825,"about_ca_system_score_gemma":0.00005773346,"threshold_uncertainty_score":0.7490675},"labels":[],"label_agreement":null},{"id":"W3026810776","doi":"10.33795/jip.v6i3.318","title":"PENGEMBANGAN SISTEM INFORMASI PEMETAAN INFRASTRUKTUR SISTEM INFORMASI DI KOTA PROBOLINGGO","year":2020,"lang":"id","type":"article","venue":"Jurnal Informatika Polinema","topic":"Data Mining and Machine Learning 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":"WiLAN (Canada)","funders":"","keywords":"Cluster analysis; Computer science; Humanities; Artificial intelligence; Art","score_opus":0.029299961967562526,"score_gpt":0.26549451447543193,"score_spread":0.23619455250786942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3026810776","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":[0.10802013,0.0022246835,0.23375586,0.08826029,0.0061038616,0.0070002805,0.00043169077,0.0060740686,0.54812914],"genre_scores_gemma":[0.9261879,0.0007102264,0.028044652,0.024123041,0.003386046,0.00031522947,0.0014031772,0.00023303546,0.015596747],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99221534,0.0001785187,0.00340583,0.0007614204,0.0016287762,0.0018100975],"domain_scores_gemma":[0.9931476,0.00028805173,0.002323317,0.0017833574,0.000697238,0.0017604321],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011627001,0.0011987753,0.0012868796,0.00051137555,0.0012556284,0.002686079,0.00411556,0.0005057123,0.000048407437],"category_scores_gemma":[0.000869949,0.0011239693,0.00063829153,0.0021185903,0.0003083235,0.006446047,0.002385326,0.0026446215,0.0015107328],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003633176,0.0006974426,0.008347677,0.0056878575,0.001294468,0.00009962518,0.121422,0.015886866,0.00034406473,0.23119189,0.06747198,0.5471928],"study_design_scores_gemma":[0.0017433658,0.00088109093,0.0072839013,0.00033754017,0.00016332068,0.00032291992,0.0014897608,0.22703585,0.0002884938,0.000054766144,0.75915784,0.0012411344],"about_ca_topic_score_codex":0.000049506358,"about_ca_topic_score_gemma":0.000023230874,"teacher_disagreement_score":0.8181677,"about_ca_system_score_codex":0.00021833004,"about_ca_system_score_gemma":0.0012295607,"threshold_uncertainty_score":0.9996563},"labels":[],"label_agreement":null},{"id":"W3031570094","doi":"10.33633/joins.v5i1.3469","title":"Analisis Persebaran UMKM Kota Malang Menggunakan Cluster K-means","year":2020,"lang":"id","type":"article","venue":"JOINS (Journal of Information System)","topic":"Data Mining and Machine Learning 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":"Innovation Cluster (Canada)","funders":"","keywords":"Humanities; Physics; Cluster (spacecraft); Computer science; Art; Operating system","score_opus":0.018451868212467016,"score_gpt":0.24220383224002523,"score_spread":0.2237519640275582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3031570094","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":[0.023695264,0.00019707915,0.91743004,0.025026228,0.0015491128,0.0005409043,0.00016608147,0.00022809669,0.031167164],"genre_scores_gemma":[0.98461354,0.00004314141,0.011123031,0.0032874236,0.0006707362,0.00000886443,0.00005759436,0.000020058653,0.00017560973],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99603873,0.00030961054,0.0020229735,0.00022556564,0.0010170626,0.00038604444],"domain_scores_gemma":[0.9955427,0.00012598217,0.0024223712,0.000612095,0.0007698865,0.0005269678],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015145304,0.00032042322,0.00061601854,0.0004992552,0.00035343997,0.0010832521,0.0014299874,0.00016502179,0.00006849656],"category_scores_gemma":[0.00036891105,0.00028131876,0.00033854952,0.0010334275,0.000055744473,0.0040232483,0.00028754186,0.0007395313,0.0012559328],"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":[0.00048727955,0.0002724973,0.013395629,0.004139378,0.0014901008,0.00011711226,0.29578274,0.032034785,0.00039155706,0.034357168,0.55116695,0.06636482],"study_design_scores_gemma":[0.0027365936,0.0008171453,0.0065620155,0.0010515003,0.00024217539,0.0010956796,0.022801135,0.46923026,0.000110628745,0.000005602005,0.49469188,0.0006553713],"about_ca_topic_score_codex":0.000052154774,"about_ca_topic_score_gemma":0.0000029904807,"teacher_disagreement_score":0.96091825,"about_ca_system_score_codex":0.0002045521,"about_ca_system_score_gemma":0.00036537644,"threshold_uncertainty_score":0.9999639},"labels":[],"label_agreement":null},{"id":"W3043360572","doi":"10.35145/joisie.v4i1.510","title":"MENENTUKAN STRATEGI PROMOSI MENGGUNAKAN ALGORITMA CLUSTERING K-MEANS","year":2020,"lang":"id","type":"article","venue":"JOISIE (Journal Of Information Systems And Informatics Engineering)","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"Humanities; Physics; Psychology; Art","score_opus":0.012594896725026731,"score_gpt":0.21837336000592758,"score_spread":0.20577846328090085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3043360572","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006017663,0.00043661208,0.98728746,0.0010240045,0.001153066,0.00046397364,0.00006589582,0.0001377955,0.003413505],"genre_scores_gemma":[0.90061176,0.0010113181,0.09606153,0.0010506132,0.00092591014,0.000033832974,0.000108393404,0.00005332104,0.00014330681],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99587476,0.00004583616,0.0027503145,0.0001154483,0.0007866417,0.00042701137],"domain_scores_gemma":[0.9962931,0.000099270685,0.002065291,0.00038152141,0.00056038337,0.00060042774],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0012007803,0.00039998905,0.00065207627,0.00041755178,0.00020014662,0.0018847306,0.0008401549,0.00018776671,0.00000734467],"category_scores_gemma":[0.00025260373,0.00036351106,0.00013893256,0.00061054097,0.000037135233,0.00706171,0.00030496356,0.0007866972,0.00010538564],"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":[0.000071101094,0.000106744206,0.00021308033,0.008394605,0.00078993535,0.000020745598,0.16932297,0.70891714,0.00026006924,0.032166917,0.01985112,0.059885547],"study_design_scores_gemma":[0.000750491,0.00047612324,0.00020085381,0.0004407013,0.00004772711,0.00035206677,0.0030282466,0.7800201,0.000033199558,0.0000031462823,0.21433413,0.0003132145],"about_ca_topic_score_codex":0.000025573023,"about_ca_topic_score_gemma":4.7344153e-7,"teacher_disagreement_score":0.89459413,"about_ca_system_score_codex":0.00009323973,"about_ca_system_score_gemma":0.00023978125,"threshold_uncertainty_score":0.9998817},"labels":[],"label_agreement":null},{"id":"W3049554888","doi":"","title":"IMPLEMENTASI DATA MINING UNTUK MEMPREDIKSI POLA PEMBELIAN SEPEDA MOTOR PADA SHOWROOM CV. VIVA MAS MOTORS DENGAN METODE ALGORITMA C4.5","year":2018,"lang":"id","type":"article","venue":"","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"Physics; Humanities; Art","score_opus":0.0597598858227308,"score_gpt":0.34246123632559844,"score_spread":0.28270135050286765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3049554888","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16503586,0.0011198762,0.7709073,0.014732552,0.0085041,0.003153095,0.00845886,0.0031986048,0.024889749],"genre_scores_gemma":[0.51590693,0.00015944781,0.4381288,0.0026499561,0.003438589,0.00014605718,0.0034065503,0.00024073858,0.035922922],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99173695,0.0005867548,0.0013623221,0.003168114,0.0012753103,0.0018705477],"domain_scores_gemma":[0.9898824,0.0006496813,0.0006483639,0.0074702916,0.00038957052,0.0009596702],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002357086,0.0010040358,0.000856403,0.0005171243,0.0017892298,0.0016921454,0.008848964,0.00033855598,0.0013418905],"category_scores_gemma":[0.00048991956,0.000996976,0.00021548639,0.0015766077,0.00046773348,0.0022627718,0.0071522747,0.00092253403,0.0019160683],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008951761,0.0009878873,0.017782925,0.00021352645,0.0011700493,0.000095053874,0.009942967,0.000020390191,0.019420473,0.0070712967,0.50384635,0.43935958],"study_design_scores_gemma":[0.0016687636,0.0011639202,0.009781638,0.0001892176,0.00044804343,0.00015456496,0.0030311053,0.27838445,0.004272751,0.00018870304,0.6987906,0.001926244],"about_ca_topic_score_codex":0.0068190787,"about_ca_topic_score_gemma":0.0014216554,"teacher_disagreement_score":0.43743333,"about_ca_system_score_codex":0.00021338479,"about_ca_system_score_gemma":0.00070747425,"threshold_uncertainty_score":0.9997946},"labels":[],"label_agreement":null},{"id":"W3087761078","doi":"","title":"Data Of Disaster In Indonesia","year":2010,"lang":"en","type":"article","venue":"","topic":"Data Mining and Machine Learning 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":"Archipelago; Geography; Natural disaster; Character (mathematics); Position (finance); History; Archaeology; Meteorology; Economics","score_opus":0.030061759664045118,"score_gpt":0.3128677088796724,"score_spread":0.2828059492156273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3087761078","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":[0.5139753,0.0000041515777,0.4690701,0.0018963586,0.00012891156,0.000060878287,0.000019499717,0.00008427014,0.014760521],"genre_scores_gemma":[0.907149,3.8469622e-7,0.0925917,0.000062975174,0.000009993359,0.0000024712383,0.000023555087,0.000001601865,0.00015829872],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9996133,0.000009707376,0.000088860535,0.00016746744,0.000057609217,0.00006305798],"domain_scores_gemma":[0.99863017,0.000043819968,0.000025808378,0.0012721235,0.000008795402,0.000019302926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020371066,0.000028829902,0.000045632794,0.00004363173,0.000011571816,0.000021772927,0.001356348,0.000017054597,0.000013488247],"category_scores_gemma":[0.000034307785,0.000023691418,0.0000047176154,0.00016773544,0.00001891926,0.00025490983,0.00053593173,0.00011522195,0.000032977132],"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":[0.0000018910301,0.00021350582,0.1380393,0.000010615132,0.0000054683237,0.0000031983132,0.00087235466,0.000017726556,0.012177153,0.5681076,0.009565963,0.27098525],"study_design_scores_gemma":[0.0006010819,0.000039889168,0.63473535,0.000013825161,0.0000040302716,0.00002985149,0.000072464994,0.2646273,0.0010282709,0.003254228,0.095320895,0.00027280202],"about_ca_topic_score_codex":0.000104834806,"about_ca_topic_score_gemma":0.0002130792,"teacher_disagreement_score":0.56485337,"about_ca_system_score_codex":7.792648e-7,"about_ca_system_score_gemma":0.000017770184,"threshold_uncertainty_score":0.25204545},"labels":[],"label_agreement":null},{"id":"W3095412205","doi":"","title":"Peramalan Data Intermiten Curah Hujan Menggunakan Metode Penggabungan Arima Dan Group Method Of Data Handling (GMDH) (Studi Kasus: Stasiun Meteorologi Perak)","year":2018,"lang":"id","type":"dissertation","venue":"","topic":"Data Mining and Machine Learning 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":"Autoregressive integrated moving average; Statistics; Mathematics; Computer science; Time series","score_opus":0.0966138278553158,"score_gpt":0.4045287471285599,"score_spread":0.3079149192732441,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095412205","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021458888,0.0013488497,0.9569838,0.0014848447,0.0023386693,0.0019310862,0.005050573,0.0008882877,0.008515015],"genre_scores_gemma":[0.0968111,0.00048779737,0.7734592,0.00036877024,0.0008434546,0.000115777446,0.122652456,0.0002204939,0.005040982],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9863385,0.0019759918,0.002611975,0.0059420997,0.0016217775,0.0015096563],"domain_scores_gemma":[0.97661763,0.0018468323,0.0023999368,0.017537298,0.0010129822,0.0005853429],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":["metaepi_narrow","open_science"],"category_scores_codex":[0.009251078,0.0016201676,0.0023163955,0.0008739846,0.0014118428,0.0014509512,0.025756763,0.0008116101,0.00023301764],"category_scores_gemma":[0.0027786922,0.0014899997,0.00030971065,0.0015841697,0.000486148,0.0037351223,0.012348396,0.0023571607,0.0001926022],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045710424,0.0027686483,0.003208407,0.0017106794,0.004546978,0.00006841656,0.029138941,0.000112952985,0.014522477,0.025201531,0.0450259,0.87323797],"study_design_scores_gemma":[0.0028569575,0.0022389207,0.008020302,0.0012455523,0.0035936872,0.0002117444,0.015247828,0.73183215,0.0026774046,0.0005222576,0.2276883,0.0038648979],"about_ca_topic_score_codex":0.005028293,"about_ca_topic_score_gemma":0.0033925602,"teacher_disagreement_score":0.8693731,"about_ca_system_score_codex":0.00013649277,"about_ca_system_score_gemma":0.0008028847,"threshold_uncertainty_score":0.99994445},"labels":[],"label_agreement":null},{"id":"W3097249123","doi":"10.17977/um071v25i22020p1-10","title":"ANALISA MODEL HIDROGRAF BANJIR KALI NGOTOK DENGAN METODE SCS, SNYDER DAN NAKAYASU","year":2020,"lang":"id","type":"article","venue":"BANGUNAN","topic":"Data Mining and Machine Learning 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":"WiLAN (Canada)","funders":"","keywords":"Physics; Forestry; Geography","score_opus":0.043499859984141985,"score_gpt":0.28105210807228354,"score_spread":0.23755224808814154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3097249123","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":[0.114879735,0.0032110568,0.79011863,0.063371286,0.0010565725,0.00170588,0.0006123311,0.0027991573,0.022245327],"genre_scores_gemma":[0.9349807,0.00008558303,0.050416917,0.008354282,0.00058778684,0.00011219744,0.00038200474,0.00011383127,0.004966711],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957375,0.0003120543,0.00067384436,0.0015801914,0.0007556034,0.00094082317],"domain_scores_gemma":[0.9966209,0.00015353513,0.00034333437,0.0018338354,0.00018442575,0.0008639563],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00055820757,0.0005878157,0.00058443553,0.00018464391,0.0006893413,0.0008241697,0.0027495062,0.00023880022,0.00008348319],"category_scores_gemma":[0.00035015028,0.00061033043,0.00029778085,0.0014091484,0.0002168431,0.0006653834,0.0010503323,0.0009250988,0.0010673223],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009578162,0.0015070275,0.008602512,0.0005316022,0.0008530799,0.0002735271,0.049984645,0.024466129,0.013368437,0.12236331,0.56000525,0.21794869],"study_design_scores_gemma":[0.0006726062,0.00020612059,0.0019173523,0.00007678258,0.00016344467,0.000027456152,0.00025552494,0.7335192,0.0011808902,0.00038058014,0.26077026,0.0008297475],"about_ca_topic_score_codex":0.0005590384,"about_ca_topic_score_gemma":0.000081095815,"teacher_disagreement_score":0.82010096,"about_ca_system_score_codex":0.00008391624,"about_ca_system_score_gemma":0.0003885193,"threshold_uncertainty_score":0.99971044},"labels":[],"label_agreement":null},{"id":"W3107245183","doi":"","title":"SELEKSI FITUR FORWARD SELECTION PADA ALGORITMA NAIVE BAYES UNTUK KLASIFIKASI BENIH GANDUM","year":2018,"lang":"ms","type":"article","venue":"","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"Feature selection; Naive Bayes classifier; Selection (genetic algorithm); Pattern recognition (psychology); Artificial intelligence; Bayes' theorem; Mathematics; Computer science; Statistics; Bayesian probability; Support vector machine","score_opus":0.013579500672133019,"score_gpt":0.2728697177487945,"score_spread":0.25929021707666144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3107245183","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016016688,0.00022148936,0.9453762,0.005344182,0.0021821228,0.00058522954,0.000099067336,0.0011466006,0.0290284],"genre_scores_gemma":[0.80369973,0.00013935707,0.13804029,0.0014616942,0.0024138386,0.00009505583,0.00017367874,0.00007765402,0.053898696],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962887,0.00021958412,0.00059201545,0.0014050788,0.00057857425,0.00091602904],"domain_scores_gemma":[0.997281,0.00026459817,0.0003228554,0.0012031322,0.00055932597,0.0003690875],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00069691206,0.00049984467,0.00043927418,0.0002609036,0.0011803642,0.0007847559,0.0014963485,0.0002989069,0.00065173],"category_scores_gemma":[0.00023370971,0.00047091427,0.00017293743,0.001494759,0.00027860753,0.000879563,0.00060368737,0.00066065235,0.0034050518],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004632822,0.0005117123,0.0058680046,0.000101805854,0.0002928066,0.000010102808,0.0050272783,0.00012483686,0.0017654398,0.048123684,0.30514178,0.63298625],"study_design_scores_gemma":[0.0008626948,0.001318888,0.0072715515,0.00010930472,0.00012853413,0.00012651744,0.00035160093,0.33577356,0.0070295273,0.0020995853,0.6439265,0.0010017534],"about_ca_topic_score_codex":0.0023009856,"about_ca_topic_score_gemma":0.00046062094,"teacher_disagreement_score":0.8073359,"about_ca_system_score_codex":0.00013070062,"about_ca_system_score_gemma":0.00034606276,"threshold_uncertainty_score":0.9997743},"labels":[],"label_agreement":null},{"id":"W3107651044","doi":"10.30595/jrst.v4i2.7546","title":"Metode Boost-K-means untuk Clustering Puskesmas berdasarkan Persentase Bayi yang Diimunisasi","year":2020,"lang":"id","type":"article","venue":"JRST (Jurnal Riset dan Sain Teknologi)","topic":"Data Mining and Machine Learning 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":"Humanities; Mathematics; Philosophy","score_opus":0.03308089082681665,"score_gpt":0.2794984714068098,"score_spread":0.24641758057999313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3107651044","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":[0.35589388,0.0034531462,0.49513292,0.102728255,0.0033732592,0.002340605,0.0018331041,0.0037921532,0.03145268],"genre_scores_gemma":[0.956295,0.0007049638,0.033229887,0.0051407246,0.0013731001,0.00010084745,0.0006990316,0.00018443058,0.0022720068],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99327546,0.0009152338,0.0012402239,0.0020229714,0.00094006606,0.0016060626],"domain_scores_gemma":[0.995075,0.0006911169,0.0008347393,0.002018308,0.00020638852,0.0011744346],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011761995,0.0009815464,0.0010360079,0.00036463878,0.0014023316,0.0012132634,0.004093191,0.00047036886,0.0001836281],"category_scores_gemma":[0.0013440949,0.0009802853,0.00049409224,0.0015290413,0.0005703533,0.0009448366,0.0027554578,0.002504206,0.0017195146],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009734409,0.003070978,0.079383686,0.0013361201,0.0025924526,0.004645856,0.07107438,0.014889874,0.035631068,0.027159369,0.25348017,0.5057626],"study_design_scores_gemma":[0.0031229903,0.0018054568,0.015297341,0.0004413967,0.00054491643,0.00066507916,0.0072027585,0.3247567,0.0020367417,0.00032233546,0.641148,0.0026563252],"about_ca_topic_score_codex":0.00041092807,"about_ca_topic_score_gemma":0.00020167508,"teacher_disagreement_score":0.60040116,"about_ca_system_score_codex":0.0003483094,"about_ca_system_score_gemma":0.00040815398,"threshold_uncertainty_score":0.9998977},"labels":[],"label_agreement":null},{"id":"W3110743749","doi":"10.31963/sinergi.v18i2.2627","title":"Studi Estimasi Beban Puncak Hari Libur Nasional Sistem Interkoneksi Sulselbar Menggunakan Jaringan Syaraf Tiruan Propagasi Balik","year":2020,"lang":"en","type":"article","venue":"Jurnal Teknik Mesin Sinergi","topic":"Data Mining and Machine Learning 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":"WiLAN (Canada)","funders":"","keywords":"Electricity; Power network; Backpropagation; Mains electricity; Population; Computer science; Power (physics); Electric power system; Artificial neural network; Reliability engineering; Environmental economics; Engineering; Electrical engineering; Artificial intelligence; Economics; Voltage","score_opus":0.026588096355348867,"score_gpt":0.24708510828498403,"score_spread":0.22049701192963517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3110743749","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":[0.30859306,0.002074213,0.54031676,0.113037854,0.0024298402,0.0019871758,0.00015267407,0.005474646,0.025933767],"genre_scores_gemma":[0.94068265,0.000030088575,0.053192515,0.0023453778,0.0006251898,0.000080444544,0.000098555705,0.0000757668,0.0028694123],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99617803,0.00024974992,0.0007750324,0.0012080569,0.00088522444,0.0007038806],"domain_scores_gemma":[0.99744195,0.00019384133,0.000393076,0.0010754613,0.00024409007,0.0006515723],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007026228,0.0005190824,0.0005721038,0.00019259153,0.0005887136,0.0007168158,0.0024094,0.00014931105,0.000023041663],"category_scores_gemma":[0.00047791985,0.00045862808,0.00022359868,0.0010642919,0.00014391259,0.00083077163,0.0011175763,0.0009583464,0.0003201644],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003147818,0.002264402,0.012128188,0.00049780915,0.00093458843,0.00083933206,0.011035734,0.0063018114,0.06701609,0.35968876,0.15877435,0.38020414],"study_design_scores_gemma":[0.0028714514,0.0014664878,0.028154435,0.00043136496,0.0002140162,0.000547266,0.0003483376,0.22073676,0.0077338484,0.0011998493,0.73419356,0.0021026433],"about_ca_topic_score_codex":0.000058833146,"about_ca_topic_score_gemma":0.000013354953,"teacher_disagreement_score":0.6320896,"about_ca_system_score_codex":0.00011914283,"about_ca_system_score_gemma":0.00031577112,"threshold_uncertainty_score":0.99978656},"labels":[],"label_agreement":null},{"id":"W3111488477","doi":"10.26418/bbimst.v8i4.36633","title":"ANALISIS CLUSTER NON-HIRARKI DENGAN METODE K-MODES","year":2019,"lang":"id","type":"article","venue":"Bimaster Buletin Ilmiah Matematika Statistika dan Terapannya","topic":"Data Mining and Machine Learning 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":"Innovation Cluster (Canada)","funders":"","keywords":"Physics; Cluster (spacecraft); Humanities; Philosophy; Computer science","score_opus":0.010089807253493179,"score_gpt":0.2592732145749008,"score_spread":0.24918340732140765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111488477","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":[0.31254295,0.0012260487,0.6341942,0.007984225,0.00289766,0.0046705515,0.0023132323,0.0013010746,0.03287009],"genre_scores_gemma":[0.82452977,0.00012643011,0.13923691,0.0042579356,0.00037467893,0.0004215793,0.0011520871,0.00030957398,0.029591052],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9907575,0.0011667309,0.0021220911,0.0026565213,0.0014802172,0.001816923],"domain_scores_gemma":[0.9921868,0.001106473,0.0014201016,0.004100609,0.0004842012,0.0007018309],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.0020205325,0.0014151197,0.0016630129,0.00083062344,0.00071355054,0.0029119637,0.003703414,0.00043932043,0.0009882284],"category_scores_gemma":[0.00024434595,0.001373767,0.0004154223,0.0014148862,0.00034146183,0.0014289833,0.0017038936,0.0012846043,0.010311768],"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":[0.00051828293,0.00274709,0.05139502,0.012711437,0.0026795357,0.00042656416,0.04052887,0.0025853293,0.014965873,0.06409877,0.699238,0.10810522],"study_design_scores_gemma":[0.009603942,0.0022586593,0.07811993,0.006060331,0.0011185261,0.000758308,0.0050575747,0.42529583,0.0058927196,0.0019456085,0.4559573,0.0079312725],"about_ca_topic_score_codex":0.00053183665,"about_ca_topic_score_gemma":0.000039593622,"teacher_disagreement_score":0.5119868,"about_ca_system_score_codex":0.00021860006,"about_ca_system_score_gemma":0.00032062377,"threshold_uncertainty_score":0.999925},"labels":[],"label_agreement":null},{"id":"W3112269874","doi":"10.37535/101007120201","title":"Sosialisasi Mitigasi Bencana oleh Badan Penanggulangan Bencana Daerah Kota Ambon","year":2020,"lang":"id","type":"article","venue":"Communicare Journal of Communication Studies","topic":"Data Mining and Machine Learning 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":"Encana (Canada)","funders":"","keywords":"Humanities; Sociology; Political science; Art","score_opus":0.09912961771542043,"score_gpt":0.3519504096740539,"score_spread":0.25282079195863344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3112269874","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":[0.08108847,0.39614102,0.015622651,0.4842797,0.0016822356,0.0013613425,0.00031069195,0.0005609013,0.018953003],"genre_scores_gemma":[0.926946,0.042746007,0.02594559,0.003486031,0.00029332508,0.000023311766,0.00008502243,0.00006616989,0.00040858207],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99315226,0.002630554,0.0020811225,0.00049448735,0.0010286636,0.0006129195],"domain_scores_gemma":[0.98741585,0.002028751,0.0026872433,0.005053489,0.0022244677,0.00059020764],"candidate_categories":["metaepi_narrow","sts","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00228416,0.00062035676,0.0014018776,0.00030254296,0.0018544311,0.00058891816,0.011344546,0.00021028229,0.00004331668],"category_scores_gemma":[0.0017712235,0.0005892092,0.0005033607,0.0012691825,0.0009367483,0.0011533202,0.006079595,0.0027110393,0.00009705411],"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":[0.00027239788,0.0013481354,0.009572317,0.0007515592,0.0049194656,0.000097955366,0.2319852,0.0010975482,0.0013415638,0.04162632,0.5310927,0.17589483],"study_design_scores_gemma":[0.0036366822,0.0022099388,0.027608411,0.0033030875,0.0015414315,0.000410226,0.061034553,0.0077159703,0.00062249205,0.002070058,0.88793904,0.001908124],"about_ca_topic_score_codex":0.00033627628,"about_ca_topic_score_gemma":0.0003257678,"teacher_disagreement_score":0.8458575,"about_ca_system_score_codex":0.000274839,"about_ca_system_score_gemma":0.0005772242,"threshold_uncertainty_score":0.9996559},"labels":[],"label_agreement":null},{"id":"W3112291925","doi":"10.46880/methoda.vol9no3.pp156-164","title":"JARINGAN SYARAF TIRUAN MEMPREDIKSI LAJU PERTUMBUHAN PENDUDUK KOTA BINJAI METODE BACKPROPAGATION","year":2019,"lang":"id","type":"article","venue":"Majalah Ilmiah METHODA","topic":"Data Mining and Machine Learning 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":"Forestry; Mathematics; Geography","score_opus":0.021135250400268327,"score_gpt":0.29343205224412927,"score_spread":0.27229680184386096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3112291925","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":[0.325785,0.001328007,0.570474,0.010954436,0.0075081913,0.0029091486,0.00024644568,0.0020207039,0.078774005],"genre_scores_gemma":[0.6717426,0.00019175473,0.23525628,0.0015481333,0.0008628091,0.00020965483,0.00045461062,0.00023628975,0.08949787],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9921697,0.0017406587,0.0011235407,0.0024279146,0.0011724266,0.0013657934],"domain_scores_gemma":[0.9932828,0.0011155558,0.0007746981,0.0038505169,0.00037111458,0.0006053008],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0041027498,0.00089789805,0.001050301,0.0005644459,0.0007299097,0.0011982409,0.0033579643,0.0005013353,0.0007101096],"category_scores_gemma":[0.00084243243,0.00091344386,0.0003968464,0.0017696916,0.00020784125,0.0012256887,0.0016765388,0.0016916761,0.008039977],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025730414,0.0019371435,0.034792744,0.0013965897,0.0012131484,0.0001335244,0.023030695,0.0031055063,0.13815407,0.13861418,0.03740242,0.6199627],"study_design_scores_gemma":[0.003435111,0.0012483633,0.043731965,0.0007383536,0.0005973014,0.0002675981,0.0010296324,0.30575463,0.019521952,0.002691575,0.6175247,0.0034588033],"about_ca_topic_score_codex":0.0012804513,"about_ca_topic_score_gemma":0.00006666023,"teacher_disagreement_score":0.6165039,"about_ca_system_score_codex":0.00026651876,"about_ca_system_score_gemma":0.0004850169,"threshold_uncertainty_score":0.9998386},"labels":[],"label_agreement":null},{"id":"W3116447295","doi":"","title":"Uji Inter-Rater Reliability Western Ontario and Mcmaster University (WOMAC) Osteoarthritis Index pada Pasien Osteoarthritis Knee","year":2020,"lang":"en","type":"article","venue":"","topic":"Data Mining and Machine Learning 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":"WOMAC; Osteoarthritis; Medicine; Reliability (semiconductor); Physical therapy; Alternative medicine; Physics","score_opus":0.010899595294045508,"score_gpt":0.2035786696402266,"score_spread":0.1926790743461811,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3116447295","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":[0.6840357,0.00008621901,0.26624572,0.020663248,0.00024368078,0.000592854,0.00006469138,0.000870416,0.027197447],"genre_scores_gemma":[0.9814887,0.000010455509,0.00937718,0.0019531567,0.000050450944,0.000008460675,0.000026787677,0.000013530869,0.0070712543],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99839365,0.000113905924,0.0002248911,0.00077792146,0.00018555541,0.0003040971],"domain_scores_gemma":[0.9988761,0.0000821112,0.00008086828,0.0005897455,0.00008098316,0.00029019814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016410045,0.00020279629,0.00022960201,0.000058023208,0.00020158429,0.00027306017,0.00066131377,0.00008761796,0.00031070886],"category_scores_gemma":[0.00004022983,0.0002053626,0.000050003277,0.00028297678,0.00011249235,0.00080534583,0.0009845862,0.00037629934,0.0001770176],"study_design_candidate":"not_applicable","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":[0.000050853905,0.00005827279,0.22206348,0.000021428925,0.000017042956,0.000055998713,0.0073251985,0.00002450535,0.00010306113,0.0010903075,0.0025776268,0.76661223],"study_design_scores_gemma":[0.0021341757,0.0009660519,0.12025652,0.000040211355,0.000017442726,0.00006571937,0.00039019203,0.0025127435,0.0001062037,0.00023332848,0.87275225,0.0005251564],"about_ca_topic_score_codex":0.0058802264,"about_ca_topic_score_gemma":0.018026218,"teacher_disagreement_score":0.87017465,"about_ca_system_score_codex":0.00006527119,"about_ca_system_score_gemma":0.00009918594,"threshold_uncertainty_score":0.99989223},"labels":[],"label_agreement":null},{"id":"W3119877664","doi":"10.20956/ejsa.v2i1.12504","title":"Model Regresi Data Panel Pada Kasus Infeksi Saluran Pernapasan Akut (ISPA) di Provinsi Nusa Tenggara Timur","year":2021,"lang":"en","type":"article","venue":"ESTIMASI Journal of Statistics and Its Application","topic":"Data Mining and Machine Learning 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":"Encana (Canada)","funders":"","keywords":"Breastfeeding; Medicine; Panel data; Veterinary medicine; Geography; Statistics; Pediatrics; Mathematics","score_opus":0.060240733191206555,"score_gpt":0.30619861105060137,"score_spread":0.24595787785939482,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3119877664","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0146136265,0.0005579445,0.9818213,0.0021298327,0.00006988587,0.00015525031,0.00037908534,0.000043671,0.00022940186],"genre_scores_gemma":[0.7045983,0.00044625622,0.294103,0.0001747488,0.00011534964,0.000012969787,0.00038584042,0.000021002115,0.00014252674],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998306,0.00006635381,0.00052365276,0.00046805857,0.00041399253,0.00022198561],"domain_scores_gemma":[0.9974981,0.00020321552,0.00055502274,0.0009693503,0.00057111453,0.00020320214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005000765,0.0001829394,0.00026147717,0.000089781526,0.0002540636,0.000298768,0.0010790676,0.00006674208,0.000001757636],"category_scores_gemma":[0.00043965972,0.0001670144,0.000027465028,0.00025905838,0.000052250478,0.0006178092,0.0004653015,0.0003908244,0.000008902066],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027250715,0.00037931433,0.002043241,0.00013558078,0.000092516704,0.00007482727,0.00080554455,0.008663471,0.013261943,0.2738774,0.012081369,0.6885575],"study_design_scores_gemma":[0.00041071072,0.00008832385,0.008582859,0.000041860327,0.00006135963,0.00028165165,0.0000289306,0.9742365,0.00034583977,0.0031046844,0.012615334,0.00020197837],"about_ca_topic_score_codex":0.000025149504,"about_ca_topic_score_gemma":0.00001468913,"teacher_disagreement_score":0.965573,"about_ca_system_score_codex":0.00003339704,"about_ca_system_score_gemma":0.00037952056,"threshold_uncertainty_score":0.6810649},"labels":[],"label_agreement":null},{"id":"W3120311022","doi":"10.51903/e-bisnis.v13i1.282","title":"PENGGUNAAN ASSOSIATION RULE MINING DALAM PENETAPAN HARGA PROMOSI, STOK, DAN PENATAAN PRODUK PADA ETALASE","year":2020,"lang":"en","type":"article","venue":"E-Bisnis Jurnal Ilmiah Ekonomi dan Bisnis","topic":"Data Mining and Machine Learning Applications","field":"Computer Science","cited_by":2,"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":"Business; Product (mathematics); Quarter (Canadian coin); Promotion (chess); Marketing; Advertising; Mathematics; Geography","score_opus":0.023050890648107284,"score_gpt":0.2503542801341849,"score_spread":0.22730338948607764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3120311022","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":[0.9462435,0.000172939,0.029208757,0.01615132,0.00047670884,0.00086432794,0.00007898489,0.0009754173,0.0058279946],"genre_scores_gemma":[0.9863641,0.000035782698,0.0106143,0.0012357488,0.0005940241,0.00019102084,0.00043357024,0.00009876036,0.0004326492],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9953807,0.00032050145,0.00093966676,0.001678928,0.0007443536,0.00093584094],"domain_scores_gemma":[0.99657804,0.00015625448,0.0007368793,0.0015494436,0.00019651215,0.00078285974],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007342076,0.0006478982,0.00062869553,0.00025804827,0.0009841203,0.001229944,0.002280253,0.0002094545,0.000017449469],"category_scores_gemma":[0.00042100108,0.0006632303,0.00025797865,0.0010034575,0.0001655422,0.0017162805,0.00091158814,0.0009996423,0.00022168735],"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":[0.00036703717,0.0022937804,0.4146228,0.00056012085,0.000994818,0.00056431553,0.038735036,0.0037001355,0.071667545,0.0315207,0.054732237,0.38024145],"study_design_scores_gemma":[0.004879195,0.0021027932,0.47722083,0.0003005973,0.00035894205,0.000574158,0.001409671,0.14792126,0.025274409,0.00010057093,0.33620796,0.003649623],"about_ca_topic_score_codex":0.00012117415,"about_ca_topic_score_gemma":0.00003933397,"teacher_disagreement_score":0.37659183,"about_ca_system_score_codex":0.00019513302,"about_ca_system_score_gemma":0.00042249655,"threshold_uncertainty_score":0.9998069},"labels":[],"label_agreement":null},{"id":"W3126367634","doi":"","title":"PENGELOMPOKAN PERLOMBAAN KSN (KOMPETISI SAINS NASIONAL) JENJANG SMP BERDASARKAN CABANG LOMBA MENGGUNAKAN METODE CLUSTERING (STUDI KASUS : DINAS PENDIDIKAN KAB.LANGKAT)","year":2021,"lang":"id","type":"article","venue":"","topic":"Data Mining and Machine Learning 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":"Competition (biology); Cluster analysis; Computer science; Artificial intelligence; Ecology","score_opus":0.022024775275084767,"score_gpt":0.27766313600299997,"score_spread":0.2556383607279152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3126367634","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":[0.26488706,0.016306203,0.28900352,0.06227842,0.009425031,0.0037584323,0.0010114654,0.005127067,0.3482028],"genre_scores_gemma":[0.858869,0.0005649904,0.05597938,0.0015755128,0.0011922847,0.00019568208,0.001015672,0.00022666396,0.08038081],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99054503,0.00094982836,0.0015199444,0.0032423441,0.0016364799,0.002106345],"domain_scores_gemma":[0.99300224,0.0009331224,0.0006387391,0.0036882798,0.00064454187,0.0010931055],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.0017002787,0.0013043091,0.0013536093,0.00053805584,0.0022529715,0.0018281757,0.0032574167,0.00043601397,0.0011980706],"category_scores_gemma":[0.0006235815,0.001364225,0.00063132116,0.0020522852,0.00032172256,0.0011427184,0.004465886,0.0018079784,0.0019844389],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024872486,0.006540154,0.018472888,0.0020174438,0.0040702773,0.0055934903,0.06424587,0.0044277553,0.053515557,0.18700431,0.16343994,0.49042356],"study_design_scores_gemma":[0.0043917736,0.00087896636,0.05914164,0.0012005093,0.0008275772,0.002181418,0.008822893,0.1008216,0.006618694,0.00076707045,0.8094441,0.00490373],"about_ca_topic_score_codex":0.0029819952,"about_ca_topic_score_gemma":0.0044369707,"teacher_disagreement_score":0.6460042,"about_ca_system_score_codex":0.0005771078,"about_ca_system_score_gemma":0.0010014182,"threshold_uncertainty_score":0.99997085},"labels":[],"label_agreement":null},{"id":"W3127240281","doi":"10.1007/s00453-021-00804-z","title":"Special Issue on Algorithms and Data Structures (WADS 2019)","year":2021,"lang":"en","type":"article","venue":"Algorithmica","topic":"Data Mining and Machine Learning 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":"Carleton University; University of Alberta","funders":"Division of Mathematical Sciences; University of Alberta","keywords":"Computer science; Theory of computation; Algorithm","score_opus":0.02182395656702545,"score_gpt":0.30746161241249775,"score_spread":0.2856376558454723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127240281","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032775712,0.0011631476,0.8501369,0.04735019,0.007295479,0.0005673103,0.0015194366,0.001319156,0.08737084],"genre_scores_gemma":[0.0043673236,0.0001720441,0.9674293,0.0025286116,0.01666079,0.000016760607,0.0011119881,0.00004156123,0.0076716403],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998506,0.000065841035,0.00016095175,0.0007928433,0.00023653271,0.00023783642],"domain_scores_gemma":[0.99775195,0.00013544784,0.000058611986,0.001881984,0.00005404235,0.000117981865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018609184,0.00014511435,0.00015594078,0.000059409613,0.00020869456,0.00029213986,0.0013065322,0.00006230084,0.00011149475],"category_scores_gemma":[0.00012614446,0.00013801639,0.00002095447,0.00027583458,0.00005760922,0.00032322772,0.0011960755,0.00025651674,0.0002353039],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.2325945e-7,0.000027032442,0.000016686814,0.0000024892393,0.000013944704,0.000021830612,0.000103821774,0.0000064989727,0.000030700397,0.01116157,0.21377827,0.77483624],"study_design_scores_gemma":[0.00023258288,0.000045269535,0.0028906197,0.000009260141,0.00001109931,0.00009889172,0.000024924917,0.03152507,0.000539138,0.0027967703,0.96162724,0.00019911896],"about_ca_topic_score_codex":0.00006324456,"about_ca_topic_score_gemma":0.0000063359407,"teacher_disagreement_score":0.7746371,"about_ca_system_score_codex":0.000012272473,"about_ca_system_score_gemma":0.000088348526,"threshold_uncertainty_score":0.56281453},"labels":[],"label_agreement":null},{"id":"W3127245612","doi":"","title":"JARINGAN SARAF TIRUAN MEMPREDIKSI PENJUALAN MAKANAN DAN MINUMAN DENGAN MENGGUNAKAN METODE BACKPROPAGATION (STUDI KASUS : PONDOK JATI RESTO BINJAI","year":2021,"lang":"id","type":"article","venue":"","topic":"Data Mining and Machine Learning 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":"Backpropagation; Popularity; Advertising; Food science; Business; Mathematics; Computer science; Artificial neural network; Artificial intelligence; Psychology; Chemistry","score_opus":0.025608696566026424,"score_gpt":0.2805885057824232,"score_spread":0.2549798092163968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127245612","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":[0.6883694,0.0025668447,0.12777719,0.0310157,0.004286127,0.0025648593,0.00028227209,0.0031962425,0.13994135],"genre_scores_gemma":[0.88794094,0.0001734856,0.05052887,0.001194008,0.0007593114,0.00015389352,0.001066064,0.00015758426,0.05802585],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9922441,0.0010579142,0.0013534796,0.0026454888,0.0013025062,0.0013964729],"domain_scores_gemma":[0.9934929,0.0005393567,0.00066311297,0.0038051875,0.00072047143,0.0007789451],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001740093,0.0009475504,0.00094618485,0.00047663524,0.0016944567,0.0016866076,0.0026348145,0.00037804194,0.00028010897],"category_scores_gemma":[0.00085117476,0.0009867739,0.00033470723,0.0023580228,0.00028250006,0.0010901288,0.0020842755,0.001387088,0.0012570319],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018983863,0.0049404856,0.038244233,0.0010456615,0.0024333294,0.0012570281,0.041822717,0.0012909574,0.116599075,0.2144434,0.18207575,0.39565754],"study_design_scores_gemma":[0.0062873117,0.0018747492,0.13749255,0.0009858719,0.0013149596,0.00094880286,0.008048519,0.11275526,0.073321044,0.0027442886,0.64835614,0.005870494],"about_ca_topic_score_codex":0.0016719964,"about_ca_topic_score_gemma":0.0022499606,"teacher_disagreement_score":0.4662804,"about_ca_system_score_codex":0.00031941757,"about_ca_system_score_gemma":0.0008997556,"threshold_uncertainty_score":0.9996052},"labels":[],"label_agreement":null},{"id":"W3128100849","doi":"","title":"PREDIKSI PENDAPATAN ASLI DAERAH (PAD) KABUPATEN LANGKAT MENGGUNAKAN METODE BACKPROPAGATION NEURAL NETWORK","year":2021,"lang":"id","type":"article","venue":"","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"Backpropagation; Artificial neural network; Revenue; Government (linguistics); Training (meteorology); Computer science; Artificial intelligence; Finance; Business; Geography","score_opus":0.022997310646278555,"score_gpt":0.26906342821008694,"score_spread":0.2460661175638084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3128100849","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":[0.075297326,0.0035503514,0.6874901,0.049905524,0.007610651,0.0016695379,0.00044874486,0.0032518841,0.17077588],"genre_scores_gemma":[0.811666,0.00023052905,0.0996003,0.0019133196,0.0021943299,0.00012143705,0.0025286337,0.00011482267,0.08163064],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99576306,0.0005823993,0.0006727211,0.0014144244,0.0006483749,0.0009189985],"domain_scores_gemma":[0.99668825,0.00029836703,0.00031501913,0.002022945,0.00030237445,0.00037302484],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008494966,0.0004642228,0.000476164,0.000100755184,0.0007137011,0.001091781,0.0014158713,0.00020730995,0.0012288812],"category_scores_gemma":[0.00019074739,0.00045807066,0.00018392195,0.0010937484,0.000104108134,0.0008991176,0.0011668652,0.00077513134,0.0015082491],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007399933,0.0011484695,0.027810663,0.00032279786,0.0006901435,0.00042030335,0.0050140778,0.02585151,0.00452007,0.09926469,0.48381704,0.35106623],"study_design_scores_gemma":[0.0011243679,0.00031596236,0.041269884,0.00017678374,0.00024600906,0.00025390362,0.00036131934,0.6784599,0.002428271,0.0012724873,0.2728513,0.0012398572],"about_ca_topic_score_codex":0.0004359458,"about_ca_topic_score_gemma":0.0002737937,"teacher_disagreement_score":0.73636866,"about_ca_system_score_codex":0.00009973055,"about_ca_system_score_gemma":0.00035156385,"threshold_uncertainty_score":0.99994516},"labels":[],"label_agreement":null},{"id":"W3128320926","doi":"","title":"JARINGAN SYARAF TIRUAN MEMPREDIKSI KEBUTUHAN OBAT-OBATAN MENGGUNAKAN METODE BACKPROPAGATION","year":2021,"lang":"id","type":"article","venue":"","topic":"Data Mining and Machine Learning 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":"Backpropagation; Process (computing); Government (linguistics); Artificial neural network; Computer science; Layer (electronics); Autonomy; Artificial intelligence","score_opus":0.01959398461914506,"score_gpt":0.2700725048600768,"score_spread":0.2504785202409317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3128320926","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":[0.040571734,0.0010428136,0.774222,0.019520957,0.0028419043,0.0007939167,0.00017532465,0.0019160997,0.15891522],"genre_scores_gemma":[0.8398685,0.00023058546,0.07570273,0.0014717622,0.0008223927,0.000098526245,0.0009293077,0.00009759392,0.0807786],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99508864,0.0005060209,0.0008330936,0.0018260203,0.00082189316,0.0009243182],"domain_scores_gemma":[0.99540097,0.0003519785,0.00036427527,0.0028668072,0.00050277833,0.0005131731],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010508017,0.00056599354,0.00056171446,0.00021480136,0.0008631363,0.0013382448,0.0018605161,0.0002711124,0.0006160602],"category_scores_gemma":[0.0006175594,0.000591597,0.00022990034,0.001623702,0.00015624813,0.0009917166,0.0014396635,0.0008605823,0.0026074662],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041869996,0.002022717,0.0065210783,0.000548579,0.000897921,0.00032051918,0.011198272,0.0017257832,0.042260516,0.48509118,0.07509585,0.3742757],"study_design_scores_gemma":[0.0020417585,0.0005283254,0.019575939,0.00041883512,0.00045675688,0.00031338722,0.0011362098,0.24635127,0.061914645,0.0044310037,0.66028064,0.0025512099],"about_ca_topic_score_codex":0.00055906817,"about_ca_topic_score_gemma":0.00027296276,"teacher_disagreement_score":0.7992968,"about_ca_system_score_codex":0.0001835525,"about_ca_system_score_gemma":0.00067577366,"threshold_uncertainty_score":0.99969846},"labels":[],"label_agreement":null},{"id":"W3128430428","doi":"","title":"JARINGAN SYARAF TIRUAN PREDIKSI JUMLAH PENGIRIMAN BARANG MENGGUNAKAN METODE BACKPROPAGATION ( STUDIKASUS: KANTOR POS BINJAI )","year":2021,"lang":"id","type":"article","venue":"","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"Backpropagation; Artificial neural network; Computer science; Artificial intelligence; Benchmark (surveying); Process (computing); Machine learning; Indonesian; Geography","score_opus":0.019187938014615966,"score_gpt":0.2743457013183178,"score_spread":0.2551577633037018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3128430428","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":[0.14780268,0.0037799736,0.63121456,0.027579822,0.0045388113,0.0024206887,0.00029219332,0.003161154,0.17921011],"genre_scores_gemma":[0.89507234,0.00016997839,0.048854142,0.00091293536,0.0008160999,0.000159371,0.0005592743,0.00011190818,0.053343922],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9943095,0.00062192,0.0009870607,0.002031685,0.0009995652,0.001050294],"domain_scores_gemma":[0.9953769,0.00037618322,0.0004199927,0.0026553967,0.00065648503,0.0005150367],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012939282,0.00068172376,0.0007048188,0.00029892413,0.001065468,0.0013774657,0.001898798,0.00027208653,0.00050122663],"category_scores_gemma":[0.0005697571,0.0006940122,0.00027797677,0.0016702785,0.00017183523,0.0011588704,0.0015014415,0.0009874537,0.002417359],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014129901,0.0063667884,0.015077753,0.0016580448,0.0029746692,0.0005657434,0.031706885,0.0031162968,0.09808704,0.38840333,0.1800009,0.27190125],"study_design_scores_gemma":[0.00758046,0.0020370265,0.12395568,0.0014426224,0.0017893569,0.00078105973,0.0067041,0.31778082,0.08224891,0.0029550556,0.4460911,0.0066338265],"about_ca_topic_score_codex":0.0004460809,"about_ca_topic_score_gemma":0.00021822106,"teacher_disagreement_score":0.7472697,"about_ca_system_score_codex":0.00022073512,"about_ca_system_score_gemma":0.00075327686,"threshold_uncertainty_score":0.9996592},"labels":[],"label_agreement":null},{"id":"W3129040632","doi":"","title":"JARINGAN SARAF TIRUAN UNTUK MEMPREDIKSI JUMLAH PENGANGGURAN DI KOTA BINJAI DENGAN MENGGUNAKAN METODE BACKPROPAGATION","year":2021,"lang":"id","type":"article","venue":"","topic":"Data Mining and Machine Learning 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":"Government (linguistics); Backpropagation; Unemployment; Mathematics; Workforce; Unemployment rate; Statistics; Artificial neural network; Artificial intelligence; Computer science; Economics; Economic growth","score_opus":0.02070062486407227,"score_gpt":0.27061587242326185,"score_spread":0.2499152475591896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3129040632","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":[0.35868168,0.0023982343,0.46504468,0.033230282,0.0053280676,0.001975996,0.00033895051,0.0036079565,0.12939414],"genre_scores_gemma":[0.92174286,0.00021703844,0.027397769,0.0010551744,0.0007236825,0.00009926111,0.00081874244,0.0001206089,0.04782486],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9936109,0.0008772913,0.0010682868,0.0022096278,0.0010527383,0.0011811096],"domain_scores_gemma":[0.9944037,0.0005421391,0.00047894556,0.0032733954,0.0006348095,0.00066699035],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014893401,0.00077835756,0.00078116456,0.00033445124,0.0013525556,0.0016916231,0.002340318,0.00036428674,0.0005206504],"category_scores_gemma":[0.0007444893,0.00080226106,0.00032244058,0.0021292828,0.00022742317,0.0012092607,0.0015936228,0.0014298875,0.002629781],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000110921515,0.004172475,0.022067524,0.0010209423,0.0018610359,0.00064796594,0.030071108,0.0028928763,0.16763861,0.22956665,0.122509964,0.41743994],"study_design_scores_gemma":[0.0041874554,0.0008855662,0.06581929,0.0006631719,0.0008979216,0.00063011394,0.00406024,0.32215574,0.14015436,0.0023662047,0.4537222,0.00445772],"about_ca_topic_score_codex":0.00089419924,"about_ca_topic_score_gemma":0.00053993706,"teacher_disagreement_score":0.5630612,"about_ca_system_score_codex":0.00021715279,"about_ca_system_score_gemma":0.000807442,"threshold_uncertainty_score":0.99994755},"labels":[],"label_agreement":null},{"id":"W3132451862","doi":"10.6000/1929-4409.2021.10.54","title":"Biresponses Kernel Nonparametric Regression: Inflation and Economic Growth","year":2020,"lang":"en","type":"article","venue":"International Journal of Criminology and Sociology","topic":"Data Mining and Machine Learning 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":"Inflation (cosmology); Econometrics; Economics; Kernel (algebra); Statistics; Mathematics","score_opus":0.04628639768748586,"score_gpt":0.3249820525022005,"score_spread":0.27869565481471464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3132451862","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":[0.9194305,0.00047294496,0.046340562,0.03324431,0.00032239384,0.000020175827,0.000003160881,0.000019566725,0.00014640202],"genre_scores_gemma":[0.99020827,0.00038601627,0.0076751774,0.0015242983,0.00018471839,0.0000013311426,0.000002765645,0.000002847929,0.0000145815275],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99936134,0.000115865325,0.00023272865,0.0001466202,0.00006348808,0.00007997697],"domain_scores_gemma":[0.99907583,0.00043236054,0.00025129126,0.00006204045,0.000110241686,0.000068211746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020491178,0.000066332446,0.00014465388,0.00015815228,0.000060602968,0.000035303463,0.00040728986,0.00008992454,0.000009254561],"category_scores_gemma":[0.0004445076,0.00005524391,0.000028715052,0.000013707405,0.00019008729,0.0002349738,0.0001684539,0.00022582589,0.000011004405],"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":[0.00019001933,0.000034662084,0.03139654,0.0000088891,0.00019992952,0.00006774841,0.0067888945,0.000092436356,0.0008553393,0.8655436,0.0033682967,0.09145362],"study_design_scores_gemma":[0.0032896253,0.0015983391,0.5842683,0.000045117682,0.00009019868,0.0033643593,0.00034479832,0.030358642,0.00085973286,0.34121287,0.034100786,0.0004672622],"about_ca_topic_score_codex":0.000011017417,"about_ca_topic_score_gemma":2.0563661e-7,"teacher_disagreement_score":0.5528717,"about_ca_system_score_codex":0.000016181659,"about_ca_system_score_gemma":0.00006747014,"threshold_uncertainty_score":0.22527812},"labels":[],"label_agreement":null},{"id":"W3135071512","doi":"","title":"Pengelompokan Provinsi di Indonesia Menggunakan Algoritma Partitioning Around Medoids (PAM) Terhadap Indikator Pembentuk Indeks Pembangunan Manusia (IPM) Tahun 2020","year":2021,"lang":"id","type":"article","venue":"","topic":"Data Mining and Machine Learning 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":"Medoid; Quarter (Canadian coin); Liberian dollar; Cluster analysis; Geography; Business; Statistics; Mathematics; Finance","score_opus":0.01479335152922614,"score_gpt":0.2590098776813126,"score_spread":0.24421652615208647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135071512","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":[0.70764047,0.0031889707,0.19467758,0.020885102,0.004194569,0.0025575834,0.000294509,0.002559557,0.06400168],"genre_scores_gemma":[0.9568505,0.00022080839,0.024692062,0.0014048087,0.0010458966,0.00036180695,0.0011587865,0.00014926169,0.014116069],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9916462,0.0008721805,0.0014889869,0.0027443431,0.0015584646,0.0016898252],"domain_scores_gemma":[0.99426734,0.00042800064,0.0007874444,0.002948488,0.00060139515,0.00096732023],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012800432,0.0010666124,0.001037675,0.00034498598,0.0017112214,0.0028794983,0.0023788952,0.00054218253,0.0006555198],"category_scores_gemma":[0.00030320103,0.0011390686,0.00038978178,0.0021502646,0.00036168518,0.00168879,0.0021394275,0.0018700374,0.0011059636],"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":[0.00017661034,0.006967114,0.29644245,0.0014985388,0.0023379456,0.003515178,0.0384045,0.0012408488,0.01159938,0.13851936,0.102656856,0.39664122],"study_design_scores_gemma":[0.0067137503,0.0013647836,0.465183,0.0011715881,0.00092227355,0.001922174,0.01133698,0.13590103,0.011288819,0.0017338176,0.35629568,0.006166106],"about_ca_topic_score_codex":0.00055232336,"about_ca_topic_score_gemma":0.00053590717,"teacher_disagreement_score":0.3904751,"about_ca_system_score_codex":0.00031071724,"about_ca_system_score_gemma":0.0015742349,"threshold_uncertainty_score":0.9996718},"labels":[],"label_agreement":null},{"id":"W3135417175","doi":"10.51544/jurnalmi.v5i1.1190","title":"Penerapan Fuzzy Mamdani Dengan Particle Swarm Optimization (PSO) dan MAPE (Mean Absolute Percentage Error) Pada Penilaian Kinerja Pegawai","year":2020,"lang":"id","type":"article","venue":"JURNAL MAHAJANA INFORMASI","topic":"Data Mining and Machine Learning 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":"Humanities; Mathematics; Art","score_opus":0.02568928399654267,"score_gpt":0.2595295183230668,"score_spread":0.23384023432652415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135417175","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":[0.5040119,0.00080447685,0.38021985,0.05746969,0.0030029952,0.002589428,0.00023023917,0.0031284352,0.048542984],"genre_scores_gemma":[0.9655025,0.0002041831,0.024423506,0.0053134426,0.00079564576,0.000056053617,0.00043051038,0.000103992614,0.0031701396],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99490404,0.00023459653,0.0013919295,0.0010627052,0.001086773,0.0013199808],"domain_scores_gemma":[0.9962029,0.00012464651,0.0008017964,0.0013187552,0.00027415602,0.0012777555],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00068295083,0.0007453428,0.0006494127,0.00019640208,0.0012793103,0.0016527028,0.0024791686,0.00026025833,0.00011638085],"category_scores_gemma":[0.00019925498,0.00077022176,0.00033543233,0.0012994558,0.00020846199,0.0028328858,0.0010992603,0.0014314373,0.00081546436],"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":[0.00082688336,0.0020641387,0.024287699,0.00136253,0.0010598433,0.00060321967,0.11541967,0.5546642,0.009431477,0.07966703,0.072634086,0.13797924],"study_design_scores_gemma":[0.001646113,0.0006991145,0.012855672,0.00011134649,0.00016393252,0.00016575474,0.0019310508,0.7919677,0.0010625573,0.000018777075,0.18828848,0.0010895274],"about_ca_topic_score_codex":0.0002782699,"about_ca_topic_score_gemma":0.00012150639,"teacher_disagreement_score":0.46149063,"about_ca_system_score_codex":0.0002015388,"about_ca_system_score_gemma":0.00042163208,"threshold_uncertainty_score":0.9999625},"labels":[],"label_agreement":null},{"id":"W3152697490","doi":"","title":"JARINGAN SARAF TIRUAN UNTUK MEMPREDIKSI JUMLAH PASIEN RAWAT JALAN BAGI PENGGUNA NARKOBA MENGGUNAKAN METODE BACKPROPAGATION (STUDI KASUS : KANTOR BNN KOTA BINJAI)","year":2020,"lang":"id","type":"article","venue":"","topic":"Data Mining and Machine Learning 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":"Mathematics","score_opus":0.03420725686816811,"score_gpt":0.2583673266524203,"score_spread":0.22416006978425218,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3152697490","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":[0.2554414,0.002879068,0.3325633,0.19252501,0.0069032656,0.0072803376,0.0008522022,0.008662241,0.19289319],"genre_scores_gemma":[0.9584345,0.00019260583,0.025752125,0.0028478273,0.0015294541,0.00018841504,0.00061860314,0.00017484956,0.010261596],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99167484,0.0007798026,0.00150706,0.0029633634,0.00147553,0.0015994058],"domain_scores_gemma":[0.9942055,0.00052912766,0.0007971884,0.002676593,0.00047225787,0.0013193403],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015434626,0.0011577934,0.0011860579,0.00035346783,0.001404373,0.00145121,0.003954413,0.00042790239,0.0005555784],"category_scores_gemma":[0.0008759434,0.0011148864,0.00039326557,0.0023489401,0.0003396899,0.0013647582,0.0024130864,0.0016278224,0.003998603],"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":[0.0006248175,0.0030098285,0.03007245,0.001522393,0.0027317198,0.00033183984,0.075485505,0.0035993024,0.044613745,0.06968138,0.43739784,0.3309292],"study_design_scores_gemma":[0.004089383,0.0019705219,0.021597564,0.00027529546,0.00067410746,0.0000974131,0.002436623,0.38459477,0.007197979,0.0005284553,0.5732482,0.0032896576],"about_ca_topic_score_codex":0.001568375,"about_ca_topic_score_gemma":0.00022343946,"teacher_disagreement_score":0.70299315,"about_ca_system_score_codex":0.0002764546,"about_ca_system_score_gemma":0.00052085595,"threshold_uncertainty_score":0.9998957},"labels":[],"label_agreement":null},{"id":"W3153274639","doi":"10.31602/tji.v12i2.4573","title":"PENERAPAN ALGORITMA K-MEANS CLUSTERING ANALYSIS PADA KASUS PENDERITA HIV/AIDS (STUDI KASUS KABUPATEN BANJAR)","year":2021,"lang":"id","type":"article","venue":"Technologia Jurnal Ilmiah","topic":"Data Mining and Machine Learning 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":"WiLAN (Canada)","funders":"","keywords":"Physics; Humanities; Philosophy","score_opus":0.021149011494788542,"score_gpt":0.26902199164043883,"score_spread":0.2478729801456503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3153274639","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.103910856,0.00453493,0.8639317,0.012478676,0.0013543366,0.0005647905,0.00035677856,0.0033694068,0.009498486],"genre_scores_gemma":[0.86364543,0.0006572946,0.122704014,0.00029354062,0.00027600638,0.000104303734,0.00035044886,0.000088079236,0.011880849],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9936274,0.00035250848,0.0012404856,0.0022600268,0.0010224727,0.0014970748],"domain_scores_gemma":[0.9943388,0.0002869684,0.0007061834,0.0037222414,0.0005577226,0.00038807286],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0010609784,0.0008623331,0.0012695349,0.0011718187,0.0013079703,0.0011818268,0.0039656945,0.0007271858,0.00028625168],"category_scores_gemma":[0.0005472803,0.0008950602,0.0006987186,0.0073492867,0.00042500184,0.0006574523,0.0027591363,0.002424625,0.0007075632],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012879538,0.003224057,0.081042625,0.00046448942,0.012201763,0.0043323115,0.005364614,0.016269637,0.042692974,0.042609602,0.03533508,0.75633407],"study_design_scores_gemma":[0.0045273416,0.001656516,0.060346145,0.000623815,0.0065472247,0.0021414373,0.0076618944,0.75178576,0.019885086,0.0022653374,0.13715409,0.005405353],"about_ca_topic_score_codex":0.0004417114,"about_ca_topic_score_gemma":0.0003702302,"teacher_disagreement_score":0.75973463,"about_ca_system_score_codex":0.00033329625,"about_ca_system_score_gemma":0.00051656796,"threshold_uncertainty_score":0.9999922},"labels":[],"label_agreement":null},{"id":"W3155497351","doi":"10.1088/1742-6596/1863/1/012063","title":"New normal policy on the Rupiah exchange rate using Long Short-Term Memory","year":2021,"lang":"en","type":"article","venue":"Journal of Physics Conference Series","topic":"Data Mining and Machine Learning Applications","field":"Computer Science","cited_by":4,"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":"Exchange rate; Term (time); Recession; Government (linguistics); Economics; Coronavirus disease 2019 (COVID-19); Indonesian; Quarter (Canadian coin); Devaluation; Scale (ratio); Monetary economics; Econometrics; Macroeconomics; Geography; Medicine","score_opus":0.048784704919385406,"score_gpt":0.3033176084357681,"score_spread":0.2545329035163827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3155497351","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":[0.109963104,0.00008502596,0.8772996,0.009469394,0.00034926677,0.00006099172,0.000007694105,0.000037352747,0.0027275665],"genre_scores_gemma":[0.98395836,0.00008199067,0.013565072,0.0004901926,0.00091269996,0.0000017980487,0.0000043052514,0.000010954745,0.00097463833],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990186,0.00013203347,0.00023893165,0.00016108826,0.0002506261,0.00019873396],"domain_scores_gemma":[0.998782,0.000118272634,0.00023285647,0.00047241178,0.00028930698,0.00010519316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000298565,0.0001296836,0.00018243091,0.000055568475,0.00022395674,0.00042608357,0.0007721245,0.000030032883,0.000032566233],"category_scores_gemma":[0.00009662997,0.000095119154,0.00008672602,0.00037455728,0.000055690074,0.00087879965,0.00024312707,0.0003629625,0.000013516077],"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":[0.000015220668,0.00006828068,0.00038237098,0.000017079421,0.000074737545,0.00006284064,0.0028057313,0.0005815873,0.014221232,0.34544176,0.0012981757,0.635031],"study_design_scores_gemma":[0.0017346832,0.0013459952,0.05058625,0.0012006458,0.00023464386,0.002215196,0.002647032,0.02313248,0.789368,0.10150674,0.024150304,0.0018780772],"about_ca_topic_score_codex":0.00004858295,"about_ca_topic_score_gemma":0.000013815391,"teacher_disagreement_score":0.87399524,"about_ca_system_score_codex":0.000032654953,"about_ca_system_score_gemma":0.0011617822,"threshold_uncertainty_score":0.41087335},"labels":[],"label_agreement":null},{"id":"W3155993640","doi":"","title":"Implementasi SMOTE untuk mengatasi Imbalance Class pada Klasifikasi Car Evolution menggunakan K-NN","year":2021,"lang":"id","type":"article","venue":"","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"Mathematics; Artificial intelligence; Computer science","score_opus":0.015607217345850936,"score_gpt":0.2792210424184654,"score_spread":0.2636138250726145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3155993640","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":[0.048372265,0.0061740302,0.84499013,0.027929436,0.004283086,0.0013720709,0.0015004873,0.001851368,0.06352714],"genre_scores_gemma":[0.9076305,0.00080130575,0.053284217,0.001992809,0.0005856767,0.00013218579,0.0018158342,0.00009076631,0.03366673],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99448335,0.00064719206,0.000925823,0.0018716853,0.00086099113,0.0012109414],"domain_scores_gemma":[0.99551004,0.00032216104,0.0004183143,0.0028157127,0.0004539546,0.0004797872],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010579416,0.0006080431,0.00060208014,0.00017440751,0.001035308,0.00078537385,0.00175751,0.00023813192,0.00051348866],"category_scores_gemma":[0.00026682747,0.0006498252,0.00024515472,0.0015503779,0.00017595159,0.00084146066,0.0014473813,0.0009651214,0.0015014053],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044500495,0.0013943587,0.024486952,0.00053885556,0.00079951016,0.00029664743,0.0042333216,0.0006221084,0.018251672,0.5155877,0.28244162,0.15130274],"study_design_scores_gemma":[0.0017198987,0.0003043503,0.020985505,0.00017826179,0.00019690579,0.00023813632,0.0015733895,0.05018298,0.0066782394,0.0017343463,0.91491205,0.0012959337],"about_ca_topic_score_codex":0.0017588759,"about_ca_topic_score_gemma":0.0008875385,"teacher_disagreement_score":0.85925823,"about_ca_system_score_codex":0.0004543663,"about_ca_system_score_gemma":0.0010042054,"threshold_uncertainty_score":0.9995953},"labels":[],"label_agreement":null},{"id":"W3161342954","doi":"","title":"Peer Review: Kombinasi Metode Telusur (Tracking) dan Point Centered Quarter (PCQ) untuk Analisis Cadangan Karbon Mangrove Langka Kecamatan Mananggu Kabupaten Boalemo","year":2021,"lang":"id","type":"article","venue":"LAPORAN PENELITIAN","topic":"Data Mining and Machine Learning 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":"Quarter (Canadian coin); Mangrove; Point (geometry); Environmental science; Geography; Mathematics; Fishery; Biology; Archaeology","score_opus":0.027531708811864786,"score_gpt":0.28988275396514857,"score_spread":0.2623510451532838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3161342954","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":[0.14565247,0.069634765,0.032344535,0.553849,0.006936635,0.004971488,0.00576055,0.0035416782,0.17730889],"genre_scores_gemma":[0.9089346,0.0035521816,0.009369143,0.012270362,0.0008694106,0.00020315491,0.008600832,0.0002997237,0.05590062],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9920269,0.000996833,0.0014395386,0.0022872016,0.0017683731,0.0014811304],"domain_scores_gemma":[0.99295616,0.00020635015,0.000795391,0.003934432,0.0013338344,0.00077382737],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0020656865,0.0009436755,0.0013049573,0.00031040175,0.00065330026,0.0013278627,0.0024263784,0.00033707643,0.0007107663],"category_scores_gemma":[0.00059803785,0.0009938154,0.00060731726,0.0015595705,0.00019039404,0.0010284034,0.0009824896,0.0011869497,0.001128628],"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":[0.00008066573,0.0018754103,0.017445358,0.0039041922,0.0010970145,0.0034018646,0.010642729,0.000036434765,0.0030515597,0.022290241,0.8695416,0.066632956],"study_design_scores_gemma":[0.0025815545,0.00043714023,0.103958875,0.005356432,0.0009520647,0.0008094032,0.0029632158,0.0035795264,0.00278338,0.00088560465,0.8730698,0.0026230083],"about_ca_topic_score_codex":0.0039228094,"about_ca_topic_score_gemma":0.0023527087,"teacher_disagreement_score":0.7632821,"about_ca_system_score_codex":0.00026930193,"about_ca_system_score_gemma":0.00040680473,"threshold_uncertainty_score":0.99970883},"labels":[],"label_agreement":null},{"id":"W3163155380","doi":"10.5267/j.dsl.2021.1.003","title":"Simulation of generalized Gamma distribution with maximum likelihood estimation and expectation-maximization algorithm on right censored data type 1","year":2021,"lang":"en","type":"article","venue":"Decision Science Letters","topic":"Data Mining and Machine Learning 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":"Expectation–maximization algorithm; Estimator; Statistics; Mathematics; Generalized gamma distribution; Gamma distribution; Function (biology); Statistical inference; Hazard ratio; Hazard; Likelihood function; Inference; Algorithm; Estimation theory; Maximum likelihood; Computer science","score_opus":0.017803739976024018,"score_gpt":0.3043487851658008,"score_spread":0.28654504518977675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3163155380","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13449295,0.000013836286,0.8637377,0.0013939759,0.00012043691,0.00010932154,0.00004716777,0.00006141617,0.000023204686],"genre_scores_gemma":[0.5244091,0.0000064273413,0.47468182,0.00026887044,0.000017854094,0.000004531396,0.00060102,0.0000053952963,0.0000049270684],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99799687,0.000068321235,0.00027552544,0.0007297771,0.00073317275,0.00019631098],"domain_scores_gemma":[0.997762,0.00041002457,0.00020785243,0.0011791843,0.00035087336,0.000090037945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058249244,0.0001198168,0.0001395208,0.00017182129,0.0003162654,0.00029218436,0.0007655676,0.0000339861,0.000009247909],"category_scores_gemma":[0.00089418335,0.000100744495,0.000014000671,0.0017689985,0.00015934181,0.0012651901,0.00027927084,0.00009347568,0.000012983769],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028626502,0.00008590996,0.00038615832,0.0000055997757,0.000008346087,0.0000096329095,0.0003393964,0.291612,0.006555096,0.0026075207,0.00091853464,0.6974432],"study_design_scores_gemma":[0.0003916419,0.000056838107,0.0077524297,0.000039896677,0.000009324001,0.0000113666165,0.00002197959,0.9875657,0.0022054058,0.0010869997,0.0007322667,0.00012615265],"about_ca_topic_score_codex":0.000013970752,"about_ca_topic_score_gemma":0.0000022931615,"teacher_disagreement_score":0.69731706,"about_ca_system_score_codex":0.000046564062,"about_ca_system_score_gemma":0.00012324222,"threshold_uncertainty_score":0.41082412},"labels":[],"label_agreement":null},{"id":"W3164744365","doi":"","title":"Implementasi Exploratory Data Analysis Pada Dataset Video Trending Harian YouTube","year":2020,"lang":"id","type":"article","venue":"Jurnal STRATEGI - Jurnal Maranatha","topic":"Data Mining and Machine Learning 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":"Computer science; Categorical variable; Visualization; Tag cloud; Information retrieval; Exploratory data analysis; Meaning (existential); Data visualization; World Wide Web; Artificial intelligence; Data mining","score_opus":0.10334801785565154,"score_gpt":0.3393402811986106,"score_spread":0.23599226334295906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164744365","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":[0.056776494,0.0071269074,0.64813894,0.07182237,0.00393901,0.0021847363,0.19027044,0.0015701097,0.018171014],"genre_scores_gemma":[0.9522905,0.000558262,0.006015425,0.003325761,0.0016654974,0.000039324488,0.035684735,0.000100390185,0.00032014505],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9919402,0.00077736593,0.0017526896,0.0026497415,0.0015097901,0.0013702032],"domain_scores_gemma":[0.9929217,0.00032714196,0.0011980112,0.003838677,0.00017512905,0.0015393598],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0018954322,0.0009110005,0.0011759822,0.00062981516,0.0014498143,0.003484711,0.008278473,0.00024338215,0.00068365043],"category_scores_gemma":[0.0002209422,0.00090332417,0.00042474095,0.004437702,0.00022799837,0.004157559,0.0030759778,0.002084086,0.0005702283],"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":[0.00058816187,0.0019280995,0.022132777,0.000467666,0.013514438,0.0027289647,0.0077372994,0.0033542912,0.003337263,0.026662812,0.7640398,0.15350842],"study_design_scores_gemma":[0.002692152,0.0009971954,0.014963993,0.00016005333,0.0055125826,0.00024262845,0.0031078518,0.27796412,0.00017974724,0.0002666701,0.6917302,0.002182817],"about_ca_topic_score_codex":0.0014343091,"about_ca_topic_score_gemma":0.00054548105,"teacher_disagreement_score":0.89551395,"about_ca_system_score_codex":0.00017109713,"about_ca_system_score_gemma":0.0009224416,"threshold_uncertainty_score":0.99985015},"labels":[],"label_agreement":null},{"id":"W3167815843","doi":"10.6000/1929-4409.2021.10.66","title":"Impact of an Infrastructure Development Policy on Health, Poverty &amp; Crime Actions in Indonesia (Case Study in Majalengka District)","year":2021,"lang":"en","type":"article","venue":"International Journal of Criminology and Sociology","topic":"Data Mining and Machine Learning 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":"Toll; Poverty; Life expectancy; Population; Socioeconomics; Death toll; Welfare; Demography; Geography; Sociology; Economics; Economic growth; Medicine","score_opus":0.06251480559639083,"score_gpt":0.4128866689188165,"score_spread":0.35037186332242565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3167815843","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":[0.9926154,0.000067693094,0.005038626,0.0020084556,0.00015931018,0.000047778212,0.000008225473,0.000006371097,0.000048133603],"genre_scores_gemma":[0.9947241,0.000045800924,0.0047763092,0.00037258,0.00005197773,0.000003897949,0.000015658308,0.0000033848823,0.00000630491],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99872935,0.00036272616,0.00046383828,0.00018293125,0.00011336958,0.00014781427],"domain_scores_gemma":[0.99909,0.00021141818,0.00030474406,0.00016222864,0.00016852439,0.000063078915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003223246,0.00009184142,0.00024635912,0.00049681857,0.000057815792,0.000017057275,0.00037902032,0.000097603464,0.000007574373],"category_scores_gemma":[0.0001843257,0.00007887904,0.000040900468,0.00006855854,0.000078837234,0.00017140263,0.00012565631,0.00048930617,9.68867e-7],"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":[0.00019786114,0.0028895396,0.5578226,0.000013766575,0.00041068028,0.0024658374,0.054797802,0.0020626646,0.00046038575,0.0832906,0.00038186682,0.29520643],"study_design_scores_gemma":[0.0009543944,0.0004666416,0.985965,0.00001264551,0.0000033886886,0.004408818,0.00070334744,0.00010960093,0.000017236129,0.007061614,0.00023403493,0.00006327687],"about_ca_topic_score_codex":0.00059035845,"about_ca_topic_score_gemma":0.0001449089,"teacher_disagreement_score":0.42814243,"about_ca_system_score_codex":0.00020246244,"about_ca_system_score_gemma":0.0010572143,"threshold_uncertainty_score":0.32165942},"labels":[],"label_agreement":null},{"id":"W3181421781","doi":"10.53514/jc.v1i1.15","title":"PENERAPAN METODE BAYES DALAM PREDIKSI SEGEMENTASI PASAR PENJUALAN SMARTPHONE","year":2021,"lang":"id","type":"article","venue":"Journal Computer Science and Informatic Systems J-Cosys","topic":"Data Mining and Machine Learning 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":"Encana (Canada)","funders":"","keywords":"Humanities; Computer science; Physics; Art","score_opus":0.014764724786798161,"score_gpt":0.25256630566495386,"score_spread":0.2378015808781557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3181421781","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":[0.100895494,0.0025602712,0.8743469,0.004136302,0.010064283,0.00083898276,0.00006932582,0.00029461476,0.006793811],"genre_scores_gemma":[0.92639023,0.0009481388,0.06519443,0.0021298486,0.0021435292,0.000062158666,0.000072314535,0.00005012641,0.003009244],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.993606,0.00039865216,0.0017460721,0.00083932944,0.002267223,0.0011427712],"domain_scores_gemma":[0.9946584,0.0002774367,0.001184301,0.0014524779,0.0015174274,0.0009099178],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.005984987,0.0005355368,0.0007928493,0.0006372722,0.0026895013,0.009815879,0.0027010492,0.00013797508,0.00002762014],"category_scores_gemma":[0.00032298354,0.000458407,0.0001604836,0.0023094167,0.00043107852,0.005990366,0.0018714007,0.0009435168,0.00030732475],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049344675,0.0015049068,0.009692331,0.003472789,0.0011017618,0.00067236176,0.0878199,0.009790869,0.004972287,0.03621603,0.31444436,0.53026307],"study_design_scores_gemma":[0.0011254719,0.0005289759,0.0048115277,0.0010026032,0.000091422844,0.008034861,0.0013347844,0.87289697,0.000505804,0.0001581816,0.108746424,0.000762968],"about_ca_topic_score_codex":0.00008393751,"about_ca_topic_score_gemma":0.000011034626,"teacher_disagreement_score":0.86310613,"about_ca_system_score_codex":0.00028269168,"about_ca_system_score_gemma":0.0019507698,"threshold_uncertainty_score":0.9997868},"labels":[],"label_agreement":null},{"id":"W3184829629","doi":"10.31001/tekinfo.v9i2.1182","title":"Peramalan Produksi Beras di Provinsi Jawa Tengah","year":2021,"lang":"id","type":"article","venue":"Tekinfo Jurnal Ilmiah Teknik Industri dan Informasi","topic":"Data Mining and Machine Learning 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":"Encana (Canada); WiLAN (Canada)","funders":"","keywords":"Mathematics; Exponential smoothing; Statistics","score_opus":0.02228511384724377,"score_gpt":0.26210005563186195,"score_spread":0.23981494178461818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3184829629","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":[0.40306032,0.002474787,0.020932287,0.036185943,0.0069994014,0.004187055,0.0004366624,0.0039456543,0.52177787],"genre_scores_gemma":[0.84843224,0.00047114995,0.00828837,0.00439727,0.002540687,0.0003488277,0.0016763355,0.00024143154,0.13360369],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99269116,0.00033768365,0.0019598927,0.0014802003,0.0016232955,0.0019077745],"domain_scores_gemma":[0.99298316,0.00034436735,0.0011525936,0.0031344064,0.0013360704,0.0010494057],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0013872125,0.0010966228,0.0009981251,0.000526327,0.0017282664,0.0030408006,0.0031385643,0.00092782534,0.00007327663],"category_scores_gemma":[0.001591617,0.001094902,0.00043433826,0.0028298767,0.00045020625,0.003321725,0.0022348347,0.005170198,0.0007655075],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011444564,0.0014700446,0.040748246,0.0004635867,0.0006351315,0.0007689723,0.013981204,0.0010651392,0.0021104617,0.070957616,0.062298447,0.8053867],"study_design_scores_gemma":[0.0017811538,0.00051073876,0.035980918,0.0005110588,0.00018426153,0.0017920025,0.0010671713,0.008595238,0.0069464743,0.000039762934,0.94110477,0.0014864404],"about_ca_topic_score_codex":0.00017829183,"about_ca_topic_score_gemma":0.000053243395,"teacher_disagreement_score":0.87880635,"about_ca_system_score_codex":0.00047692013,"about_ca_system_score_gemma":0.0041878936,"threshold_uncertainty_score":0.9995713},"labels":[],"label_agreement":null},{"id":"W3197894897","doi":"10.32938/jitu.v1i2.1472","title":"Penerapan Data Mining Korelasi Penjualan Spare Part Mobil Menggunakan Metode Algoritma Apriori (Studi Kasus: CV. Citra Kencana Mobil)","year":2021,"lang":"en","type":"article","venue":"Journal of Information and Technology","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"Spare part; Database transaction; Computer science; Database; Apriori algorithm; Association rule learning; Data mining; Operations research; Operations management; Engineering","score_opus":0.018841039279559522,"score_gpt":0.26718807610382983,"score_spread":0.2483470368242703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197894897","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":[0.3315718,0.0034576217,0.595001,0.05873748,0.0018353998,0.0004993316,0.00020241209,0.000808057,0.007886906],"genre_scores_gemma":[0.719581,0.0011805929,0.27747178,0.0009119582,0.00021801893,0.000021803038,0.000274368,0.000015730819,0.00032475463],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985499,0.000048438742,0.00069005974,0.00020178975,0.0002772331,0.00023259784],"domain_scores_gemma":[0.99794376,0.00008515934,0.0006138469,0.0008827566,0.00036593564,0.00010856395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073772465,0.00014264075,0.00027766926,0.0004448935,0.00023896585,0.00023282213,0.0012506339,0.00013201011,0.000017993741],"category_scores_gemma":[0.00045051306,0.00012711427,0.000036273625,0.0007928766,0.00008052473,0.0018335204,0.0007137556,0.00045667755,0.000018631972],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009912426,0.000118860655,0.0039956365,0.000048488673,0.00018500013,0.00003852107,0.0024097455,0.00020696872,0.00039018918,0.034435257,0.035855554,0.9223059],"study_design_scores_gemma":[0.0016155504,0.00039257674,0.0022297085,0.00012808385,0.000080670965,0.0022218584,0.0057992805,0.05432357,0.0013621515,0.0018925186,0.9295455,0.00040853542],"about_ca_topic_score_codex":0.000014110068,"about_ca_topic_score_gemma":0.000015348744,"teacher_disagreement_score":0.92189735,"about_ca_system_score_codex":0.000034382665,"about_ca_system_score_gemma":0.00026208695,"threshold_uncertainty_score":0.5183569},"labels":[],"label_agreement":null},{"id":"W3198215115","doi":"10.5614/jts.2021.28.2.5","title":"Analisis Tren Perubahan Intensitas Hujan (Studi Kasus: Jakarta dan Bogor)","year":2021,"lang":"en","type":"article","venue":"Jurnal Teknik Sipil","topic":"Data Mining and Machine Learning 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":"WiLAN (Canada)","funders":"","keywords":"Flood myth; Indonesian; Drainage; Environmental science; Intensity (physics); Hydrology (agriculture); Meteorology; Geography; Statistics; Mathematics; Engineering; Geotechnical engineering","score_opus":0.014793033003692764,"score_gpt":0.26470974073355585,"score_spread":0.2499167077298631,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3198215115","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":[0.6740839,0.00340708,0.17976975,0.07800005,0.002272735,0.00044423793,0.00014091619,0.0020719476,0.059809398],"genre_scores_gemma":[0.9797126,0.000081943195,0.015834741,0.0018452017,0.00035369338,0.000025486223,0.00009923876,0.000028093584,0.0020189844],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.997998,0.0001508953,0.00035425383,0.00067293044,0.0004051902,0.00041873983],"domain_scores_gemma":[0.99795926,0.00015898571,0.00015604758,0.0012165583,0.00027027776,0.00023886013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000398287,0.00022365134,0.00029232292,0.00014428023,0.00040888847,0.0004462945,0.001066957,0.00007628045,0.000038509344],"category_scores_gemma":[0.00035649564,0.00021038702,0.00015632185,0.00090142107,0.000065891625,0.00043604083,0.00061721547,0.0004645854,0.0002142706],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032188786,0.001116078,0.03559844,0.00007262825,0.0006120983,0.0007055353,0.0077082003,0.00032226025,0.018036494,0.11773212,0.36511073,0.45295322],"study_design_scores_gemma":[0.0013311775,0.00033610425,0.108199224,0.00015995797,0.0001610399,0.0008698524,0.0024396714,0.017223652,0.0060197585,0.0018168,0.8602985,0.0011442461],"about_ca_topic_score_codex":0.00011111777,"about_ca_topic_score_gemma":0.000065398526,"teacher_disagreement_score":0.4951878,"about_ca_system_score_codex":0.00006118869,"about_ca_system_score_gemma":0.00018937894,"threshold_uncertainty_score":0.85793334},"labels":[],"label_agreement":null},{"id":"W3204091503","doi":"10.32534/jsfk.v14i01.1521","title":"RADIO SEBAGAI MEDIA KOMUNIKASI LINGKUNGAN DAN MITIGASI BENCANA BANJIR DI KOTA SAMARINDA","year":2020,"lang":"id","type":"article","venue":"SOSFILKOM Jurnal Sosial Filsafat dan Komunikasi","topic":"Data Mining and Machine Learning 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":"Encana (Canada)","funders":"","keywords":"Physics; Humanities; Art","score_opus":0.02349902128384234,"score_gpt":0.25220671223839786,"score_spread":0.2287076909545555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204091503","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":[0.82184625,0.005813188,0.046798334,0.07907503,0.009836501,0.003947622,0.0026665977,0.004028403,0.02598805],"genre_scores_gemma":[0.9571298,0.00087263674,0.027565118,0.0043313364,0.0061253663,0.00012789534,0.0015628188,0.00042096915,0.0018640985],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9878916,0.0015589938,0.002404866,0.0032160147,0.0021209673,0.0028075196],"domain_scores_gemma":[0.989579,0.0014600025,0.0014289392,0.0036510057,0.00062476436,0.0032562723],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.001710148,0.0019286814,0.001995254,0.0005861245,0.0031518692,0.0027481762,0.0070918477,0.0009410363,0.00028172173],"category_scores_gemma":[0.0020023598,0.002067486,0.0010608265,0.0033591636,0.0010351393,0.0017319489,0.0032827961,0.005099225,0.0010513467],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006644194,0.0021475658,0.018142952,0.00094498135,0.0023579285,0.010083117,0.078313515,0.0018622462,0.012944073,0.058972884,0.13131844,0.6822479],"study_design_scores_gemma":[0.0051137744,0.0019318616,0.015492773,0.00096222054,0.0011686407,0.0051507303,0.0050853896,0.07775905,0.0047761416,0.0005814161,0.8769454,0.005032654],"about_ca_topic_score_codex":0.0018387805,"about_ca_topic_score_gemma":0.0005480969,"teacher_disagreement_score":0.7456269,"about_ca_system_score_codex":0.00043747827,"about_ca_system_score_gemma":0.0015018944,"threshold_uncertainty_score":0.9997265},"labels":[],"label_agreement":null},{"id":"W3205940441","doi":"10.59934/jaiea.v1i1.55","title":"Family Economic Correlation To Students Learning Achievment Using Apriori Method","year":2021,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Apriori algorithm; Association rule learning; A priori and a posteriori; Value (mathematics); Transactional leadership; Association (psychology); Computer science; Psychology; Mathematics education; Artificial intelligence; Machine learning; Social psychology","score_opus":0.03430572548805251,"score_gpt":0.3403847677304493,"score_spread":0.3060790422423968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205940441","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055190418,0.00016699405,0.94378805,0.0004613896,0.00018504345,0.0001101685,0.000002481438,0.00005051175,0.000044913144],"genre_scores_gemma":[0.4654988,0.00008528668,0.5340309,0.00007903583,0.00021708834,0.000022173734,0.000005237439,0.000015796542,0.000045682646],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987612,0.000046451947,0.00052305416,0.00027431693,0.00020945474,0.00018552628],"domain_scores_gemma":[0.999012,0.00016977027,0.00020792826,0.0003011748,0.00014821654,0.0001609053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068876985,0.00012942188,0.00019974222,0.00023019218,0.00020341697,0.00030433366,0.00049162866,0.000053838812,0.000004705526],"category_scores_gemma":[0.00008686279,0.00014015008,0.0000647427,0.0004302235,0.0000132368405,0.00029263945,0.00019686352,0.0003270089,0.000046359677],"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":[0.0000035481792,0.00005876007,0.0003219859,0.000008800988,0.00003489606,0.0000032340167,0.00049669505,0.77297145,0.01682737,0.025179844,0.000036337427,0.1840571],"study_design_scores_gemma":[0.00005201525,0.00010758734,0.0019883248,0.000065391985,0.00005032896,0.00014897305,0.00045672967,0.96366936,0.006395489,0.0014176101,0.025376942,0.00027124755],"about_ca_topic_score_codex":0.00003512962,"about_ca_topic_score_gemma":0.0000028106033,"teacher_disagreement_score":0.4103084,"about_ca_system_score_codex":0.000101903875,"about_ca_system_score_gemma":0.000103798855,"threshold_uncertainty_score":0.57151544},"labels":[],"label_agreement":null},{"id":"W3214719112","doi":"10.18280/mmep.080516","title":"The Application of Copula Continuous Extension Technique for Bivariate Discrete Data: A Case Study on Dependence Modeling of Seismicity Data","year":2021,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Data Mining and Machine Learning 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":"Institut Teknologi Bandung; Lembaga Pengelola Dana Pendidikan","keywords":"Copula (linguistics); Bivariate analysis; Induced seismicity; Random variable; Econometrics; Extension (predicate logic); Continuous variable; Tail dependence; Mathematics; Applied mathematics; Statistics; Computer science; Seismology; Statistical physics; Geology; Multivariate statistics; Physics","score_opus":0.0734760502229931,"score_gpt":0.3092667859674979,"score_spread":0.23579073574450482,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214719112","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013288347,0.00009752649,0.9857507,0.00013314313,0.000019765093,0.0005778378,0.000052161813,0.00007162845,0.000008899254],"genre_scores_gemma":[0.7217212,0.00001207435,0.27811208,0.0000041538733,0.000008317909,0.00009117425,0.00003485306,0.000010816656,0.0000053683325],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987426,0.000033302713,0.00040430293,0.00049854297,0.00016473392,0.0001565302],"domain_scores_gemma":[0.9972259,0.0004849543,0.000115084906,0.0020221132,0.000106206964,0.000045778794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013466082,0.00012061315,0.00023476675,0.00003748141,0.00014163814,0.00007318572,0.0008140708,0.000043853095,5.994123e-8],"category_scores_gemma":[0.00021781707,0.00009127832,0.000020053365,0.00016356196,0.000021546019,0.00016592152,0.000667572,0.00015864149,3.823765e-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":[0.0000035177302,0.00013558622,0.000004827097,0.0002356783,0.000022336708,0.000005512255,0.00044884943,0.9713496,0.0011834599,0.024603967,0.0000055780456,0.0020011093],"study_design_scores_gemma":[0.00013871976,0.000057626898,7.997457e-7,0.00012817049,0.000033563356,0.00013039485,0.00012207746,0.99232465,0.00021596192,0.006692278,0.000059867773,0.00009591304],"about_ca_topic_score_codex":0.00016377674,"about_ca_topic_score_gemma":0.00000243484,"teacher_disagreement_score":0.7084328,"about_ca_system_score_codex":0.000005891259,"about_ca_system_score_gemma":0.00002535388,"threshold_uncertainty_score":0.3722222},"labels":[],"label_agreement":null},{"id":"W3216560246","doi":"10.37695/pkmcsr.v4i0.1133","title":"Pemanfaatan Excel untuk Analisis dan Visualisasi Data Kesehatan Masyarakat Kabupaten Sukoharjo","year":2021,"lang":"id","type":"article","venue":"Prosiding Konferensi Nasional Pengabdian Kepada Masyarakat dan Corporate Social Responsibility (PKM-CSR)","topic":"Data Mining and Machine Learning 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":"WiLAN (Canada)","funders":"","keywords":"Humanities; Computer science; Art","score_opus":0.1591427698515661,"score_gpt":0.3472932904234806,"score_spread":0.1881505205719145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216560246","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":[0.95046186,0.0023811765,0.009666981,0.018380366,0.0033946172,0.0028953634,0.008999427,0.0016339096,0.0021863112],"genre_scores_gemma":[0.9604811,0.00050782575,0.011135112,0.0010067683,0.0017189166,0.00022075119,0.017625226,0.00042250488,0.006881761],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.972943,0.0076976335,0.0036460212,0.0081944335,0.0040905834,0.0034282955],"domain_scores_gemma":[0.97764665,0.0037829797,0.0032972486,0.009816832,0.0033627767,0.002093518],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":["metaepi_narrow","open_science","research_integrity"],"category_scores_codex":[0.010172705,0.0026096588,0.0032532655,0.0010574369,0.005774629,0.0051174928,0.00857503,0.001452178,0.0003003292],"category_scores_gemma":[0.009821425,0.0029344072,0.001023492,0.0065092472,0.0016809329,0.003969411,0.010614245,0.0044449978,0.00074697944],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008167186,0.014191708,0.24210678,0.004290016,0.0040422236,0.012450023,0.02577318,0.0004677833,0.2152925,0.22227477,0.14825873,0.10268511],"study_design_scores_gemma":[0.01360937,0.0026046063,0.57567126,0.0035566383,0.0034121869,0.0024219684,0.019376907,0.10747054,0.04259845,0.025370056,0.18642256,0.01748546],"about_ca_topic_score_codex":0.0012141927,"about_ca_topic_score_gemma":0.0020998563,"teacher_disagreement_score":0.3335645,"about_ca_system_score_codex":0.0017406767,"about_ca_system_score_gemma":0.009652642,"threshold_uncertainty_score":0.99984413},"labels":[],"label_agreement":null},{"id":"W4205150246","doi":"10.46880/jmika.vol5no2.pp142-146","title":"RANCANGAN PENELITIAN MODEL HYBRID DETEKSI COVID-19 MENGGUNAKAN MARINE PREDATORS ALGORITHM (MPA) DAN INTERPOLASI LINIER","year":2021,"lang":"en","type":"article","venue":"METHOMIKA Jurnal Manajemen Informatika dan Komputerisasi Akuntansi","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"Outbreak; Coronavirus disease 2019 (COVID-19); Government (linguistics); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Interpolation (computer graphics); Computer science; Algorithm; Process (computing); Test (biology); Geography; Simulation; Operations research; Mathematics; Artificial intelligence; Medicine; Virology; Ecology; Biology; Pathology","score_opus":0.0188164560062636,"score_gpt":0.2902868972471394,"score_spread":0.2714704412408758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205150246","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016342897,0.00010457283,0.97225016,0.0026124392,0.0007931162,0.00049973506,0.00013556337,0.0008146221,0.0064469026],"genre_scores_gemma":[0.051939175,0.00018154719,0.93570334,0.009146418,0.00039723614,0.0001882488,0.0010179732,0.00010493282,0.0013211338],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9942443,0.00061753945,0.0017211654,0.0012081945,0.001009737,0.0011990678],"domain_scores_gemma":[0.9945618,0.00042039526,0.0008010142,0.0025459167,0.0003845368,0.0012863675],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002098737,0.0008218333,0.0009330253,0.00058545364,0.00092979963,0.0015700818,0.0030935663,0.00019739354,0.00005481136],"category_scores_gemma":[0.00048801728,0.00084202003,0.00039507353,0.0011579791,0.000186257,0.0028592607,0.0030419626,0.0011521674,0.00007760747],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004853568,0.0002823939,0.0010518907,0.00027779344,0.0004446471,0.00036340638,0.008025285,0.010842211,0.00027639684,0.027811809,0.009455347,0.94112027],"study_design_scores_gemma":[0.0015880415,0.00018071529,0.0009559148,0.00007643585,0.00008894732,0.0011069697,0.00064235163,0.7605949,0.0014660223,0.002174833,0.23016965,0.00095520035],"about_ca_topic_score_codex":0.00014079141,"about_ca_topic_score_gemma":0.000114055176,"teacher_disagreement_score":0.9401651,"about_ca_system_score_codex":0.0004477162,"about_ca_system_score_gemma":0.0011291703,"threshold_uncertainty_score":0.99946636},"labels":[],"label_agreement":null},{"id":"W4205822289","doi":"10.37250/newkiki.v5i3.133","title":"PENGELOMPOKKAN KABUPATEN/KOTA DI PROVINSI JAMBI BERDASARKAN KOMPONEN SEKTOR PENDIDIKAN","year":2022,"lang":"id","type":"article","venue":"Jurnal Khazanah Intelektual","topic":"Data Mining and Machine Learning 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":"Innovation Cluster (Canada)","funders":"","keywords":"Humanities; Cluster (spacecraft); Physics; Computer science; Art; Operating system","score_opus":0.01921830388733893,"score_gpt":0.26000949511294075,"score_spread":0.24079119122560183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205822289","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":[0.90397453,0.0021581503,0.021008994,0.025362635,0.0077099577,0.0023177958,0.0015651974,0.0016943548,0.034208383],"genre_scores_gemma":[0.98024374,0.000059267688,0.0017648233,0.0010101852,0.0009491742,0.00036771057,0.00051622564,0.0001545221,0.014934367],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99176353,0.0011738962,0.0014145254,0.0021147197,0.001955467,0.001577851],"domain_scores_gemma":[0.99495566,0.00046518398,0.0009308065,0.0024607102,0.00030693933,0.00088072364],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0019050713,0.0009301058,0.0009247029,0.0007346047,0.002788658,0.001178314,0.005389287,0.00017867998,0.0011297296],"category_scores_gemma":[0.000396017,0.001014434,0.00053127477,0.0016906848,0.0003529494,0.0009800406,0.0050052144,0.0037360764,0.001604385],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011360663,0.008301855,0.051349808,0.0005488158,0.001989613,0.0033084783,0.04098965,0.0030349696,0.013563855,0.079489835,0.39446893,0.40181813],"study_design_scores_gemma":[0.0024053848,0.0032645373,0.05582624,0.00017173555,0.00037146625,0.0028698412,0.0038689242,0.077862784,0.00080611114,0.00039874896,0.84944105,0.0027132016],"about_ca_topic_score_codex":0.001693907,"about_ca_topic_score_gemma":0.00019053878,"teacher_disagreement_score":0.45497212,"about_ca_system_score_codex":0.00064137194,"about_ca_system_score_gemma":0.0011326037,"threshold_uncertainty_score":0.999992},"labels":[],"label_agreement":null},{"id":"W4206111896","doi":"10.5267/j.dsl.2021.11.004","title":"Assessing the forecasting model ability in measuring the prevention transmission of COVID-19 pandemic: An application of visibility analysis using Inductive logic","year":2022,"lang":"en","type":"article","venue":"Decision Science Letters","topic":"Data Mining and Machine Learning 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":"Universitas Padjadjaran; Universiti Malaysia Terengganu","keywords":"Visibility; Computer science; Operations research; Transmission (telecommunications); Stakeholder; Pandemic; Econometrics; Coronavirus disease 2019 (COVID-19); Economics; Engineering; Geography; Meteorology; Telecommunications","score_opus":0.19682070045222974,"score_gpt":0.4296458553985255,"score_spread":0.23282515494629577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206111896","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":[0.49314165,0.000005129863,0.5061691,0.0004895625,0.000012712025,0.00016160394,0.0000019941563,0.000014221581,0.0000040193136],"genre_scores_gemma":[0.8856654,5.447611e-7,0.11402926,0.00025689875,0.000004388019,0.000036975962,0.0000033253687,0.0000028774584,3.2207203e-7],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997017,0.0005684971,0.00054179074,0.00066768145,0.0010031944,0.00020180746],"domain_scores_gemma":[0.9974156,0.0007502087,0.0005031686,0.0011575607,0.00010328974,0.000070171736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013538382,0.00009600185,0.00019033127,0.00041697235,0.0010215588,0.00012855166,0.002078447,0.000022760538,0.0000020881894],"category_scores_gemma":[0.00074286095,0.000063345644,0.00009561422,0.0050981212,0.00038831093,0.0010768865,0.00049542746,0.00031238998,1.0143923e-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":[0.000005798623,0.000061467785,0.022045352,0.000003966287,0.0000044347394,1.250732e-7,0.0028889745,0.813995,0.056901824,0.00044499204,6.9032876e-7,0.10364737],"study_design_scores_gemma":[0.0001012649,0.000018219387,0.030243762,0.000005954441,0.000024365863,0.0000046718624,0.0007759989,0.9607693,0.0002476673,0.0077331066,0.0000093560575,0.000066365756],"about_ca_topic_score_codex":0.00053539843,"about_ca_topic_score_gemma":0.000025844029,"teacher_disagreement_score":0.39252377,"about_ca_system_score_codex":0.0002980352,"about_ca_system_score_gemma":0.00029247612,"threshold_uncertainty_score":0.7857107},"labels":[],"label_agreement":null},{"id":"W4211121197","doi":"10.5539/hes.v12n1p105","title":"Big Data in Higher Education for Student Behavior Analytics (Big Data-HE-SBA System Architecture)","year":2022,"lang":"en","type":"article","venue":"Higher Education Studies","topic":"Data Mining and Machine Learning Applications","field":"Computer Science","cited_by":12,"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":"American Educational Research Association","keywords":"Big data; Data science; Analytics; Computer science; Architecture; Business intelligence; Data analysis; Learning analytics; Data collection; Business analytics; Nonprobability sampling; Knowledge management; Data mining; Statistics; Marketing; Sociology; Business; Mathematics","score_opus":0.23273825943962875,"score_gpt":0.4188529535437773,"score_spread":0.18611469410414852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211121197","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":[0.27946728,0.07224927,0.14506286,0.21096714,0.24703601,0.015214568,0.009283939,0.004311126,0.016407786],"genre_scores_gemma":[0.9303774,0.00006417992,0.024090935,0.0011935591,0.00212679,0.004240121,0.0037394888,0.00004596902,0.03412154],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974275,0.00019442831,0.0004991698,0.0011093029,0.00046237526,0.00030719565],"domain_scores_gemma":[0.9954361,0.0002725238,0.00030544953,0.0036836446,0.00021744783,0.000084868705],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087576977,0.00023158173,0.00030185838,0.00035487805,0.00060793833,0.00018467745,0.0034858973,0.00003620779,0.000022228127],"category_scores_gemma":[0.00003782579,0.00022816504,0.000036934078,0.00089977495,0.000056235207,0.00028582755,0.0033071514,0.00029537495,0.000025263313],"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":[0.000020216867,0.0038784214,0.02551982,0.00042423367,0.00036853564,0.0000025795387,0.0035380747,0.0005696347,0.00007440907,0.08171933,0.53379834,0.35008642],"study_design_scores_gemma":[0.00029047258,0.000058462905,0.0977651,0.00004207245,0.0001771883,0.000009950599,0.0027960956,0.00035098344,0.0000030037752,0.00030972404,0.8978973,0.00029963214],"about_ca_topic_score_codex":0.00027858658,"about_ca_topic_score_gemma":0.000057848258,"teacher_disagreement_score":0.65091014,"about_ca_system_score_codex":0.00032498504,"about_ca_system_score_gemma":0.00069919485,"threshold_uncertainty_score":0.93043},"labels":[],"label_agreement":null},{"id":"W4213149274","doi":"10.31219/osf.io/2gwrb","title":"IMPLEMENTASI METODE K-MEANS CLUSTERING DALAM PENGELOMPOKAN PENYEBARAN COVID-19 DI SURABAYA","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Data Mining and Machine Learning 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":"Innovation Cluster (Canada); WiLAN (Canada)","funders":"","keywords":"Silhouette; Cluster analysis; Coronavirus disease 2019 (COVID-19); Cluster (spacecraft); Corona (planetary geology); Geography; Index (typography); Computer science; Data mining; Cartography; Artificial intelligence; Physics; Medicine; World Wide Web","score_opus":0.05365274174165455,"score_gpt":0.360491461063218,"score_spread":0.3068387193215635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213149274","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022490737,0.00010980475,0.96411246,0.010239158,0.00092845573,0.00077373174,0.00033457854,0.0016331683,0.019619592],"genre_scores_gemma":[0.61627257,0.00019394114,0.35979226,0.0048499927,0.00041582345,0.0020454114,0.0057186354,0.00016206471,0.0105493255],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99573493,0.00042016312,0.00068013335,0.0017729232,0.00071426976,0.0006775596],"domain_scores_gemma":[0.99538445,0.00039588913,0.00040269224,0.0032468154,0.000058229056,0.00051190285],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015953926,0.0005245526,0.0005256779,0.000349221,0.0009601552,0.00082909066,0.0051504346,0.00014207637,0.001144341],"category_scores_gemma":[0.0002174024,0.0005469577,0.00026097012,0.0004469134,0.00006618546,0.00028861672,0.013773723,0.0015004907,0.000097917655],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005873489,0.0012034313,0.036668587,0.0017078612,0.0011977117,0.00031748693,0.02514324,0.26477364,0.0006245089,0.2745196,0.16248336,0.23130183],"study_design_scores_gemma":[0.00073943194,0.00011474396,0.004623452,0.00002862962,0.00008552622,0.000092038725,0.0006798368,0.32004508,0.000036492573,0.0027941987,0.66944784,0.0013127344],"about_ca_topic_score_codex":0.0038425378,"about_ca_topic_score_gemma":0.0008067734,"teacher_disagreement_score":0.6140235,"about_ca_system_score_codex":0.0004487397,"about_ca_system_score_gemma":0.000767812,"threshold_uncertainty_score":0.99976873},"labels":[],"label_agreement":null},{"id":"W4214747291","doi":"10.29303/jpmpi.v5i1.1302","title":"Edukasi Tanggap Bencana Melalui Kegiatan Sosialisasi Guna Mewujudkan Masyarakat Desa Pijot Yang Tangguh","year":2022,"lang":"id","type":"article","venue":"Jurnal Pengabdian Magister Pendidikan IPA","topic":"Data Mining and Machine Learning 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":"WiLAN (Canada)","funders":"","keywords":"Physics","score_opus":0.021266189529375694,"score_gpt":0.2629504459134862,"score_spread":0.2416842563841105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214747291","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":[0.29471788,0.013014677,0.087747306,0.14204393,0.03520856,0.009730253,0.010919059,0.0048093805,0.40180895],"genre_scores_gemma":[0.9398504,0.000175832,0.008529469,0.004475265,0.0024964367,0.0004915957,0.0010371022,0.00031324272,0.04263066],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98794657,0.0021340074,0.0019133484,0.0028931303,0.0026066967,0.0025062514],"domain_scores_gemma":[0.99195254,0.0006001122,0.0014754218,0.0041586068,0.00029657732,0.0015167514],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.0036046633,0.0013815875,0.001308154,0.00114488,0.0047191065,0.002668274,0.007201529,0.00029217193,0.005035211],"category_scores_gemma":[0.0003370693,0.0015999795,0.0007987564,0.0023406486,0.00057553547,0.0017989919,0.0042712614,0.004452286,0.0026040461],"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":[0.0005219876,0.0028153397,0.027272746,0.00059581205,0.0010965783,0.0033725658,0.025360245,0.0010574019,0.0038514365,0.07319853,0.72278047,0.13807692],"study_design_scores_gemma":[0.0022167775,0.0011001212,0.029316464,0.00020041515,0.0005014451,0.0020496773,0.002970518,0.0091283815,0.00028278193,0.0015325339,0.9479858,0.0027150484],"about_ca_topic_score_codex":0.0021432338,"about_ca_topic_score_gemma":0.0007075226,"teacher_disagreement_score":0.64513254,"about_ca_system_score_codex":0.0012007871,"about_ca_system_score_gemma":0.0013957123,"threshold_uncertainty_score":0.9998935},"labels":[],"label_agreement":null},{"id":"W4220774419","doi":"10.30659/jkr.v1i2.20023","title":"KAJIAN KERENTANAN SOSIAL TERHADAP BENCANA BANJIR","year":2022,"lang":"en","type":"article","venue":"Jurnal Kajian Ruang","topic":"Data Mining and Machine Learning 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":"Encana (Canada)","funders":"","keywords":"Flood myth; Geography; Population; Vulnerability (computing); Social vulnerability; Socioeconomics; Asset (computer security); Demography; Psychology; Sociology","score_opus":0.010289499464258804,"score_gpt":0.2402598692315065,"score_spread":0.2299703697672477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220774419","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":[0.42698273,0.00089229643,0.38812798,0.05360205,0.005697134,0.0011798149,0.00031705218,0.0024322323,0.12076869],"genre_scores_gemma":[0.98417056,0.0000041236854,0.011578612,0.0013233686,0.00023150883,0.0000758774,0.00006542795,0.000021682881,0.0025288565],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981862,0.00013821997,0.00027913792,0.00048766317,0.00048921054,0.000419614],"domain_scores_gemma":[0.9987749,0.00006117259,0.00015621298,0.0007715848,0.00002971235,0.00020643817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041380603,0.00016866942,0.00017006141,0.00019082158,0.0009966225,0.0002454247,0.001674685,0.000031857377,0.00028584094],"category_scores_gemma":[0.00002856649,0.00017542706,0.00010514438,0.00058113487,0.0000385307,0.00033342405,0.00080234354,0.00058882835,0.000104993516],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032917615,0.00060108915,0.019400055,0.00003170525,0.00014891726,0.00027661247,0.0059999963,0.002745625,0.0035490317,0.32074583,0.17744897,0.46901926],"study_design_scores_gemma":[0.0007574436,0.00035715467,0.043614306,0.000022075636,0.00003182329,0.00042425856,0.00067855173,0.03899102,0.00020843378,0.0026940748,0.91156125,0.0006595952],"about_ca_topic_score_codex":0.00026830228,"about_ca_topic_score_gemma":0.00005219944,"teacher_disagreement_score":0.73411226,"about_ca_system_score_codex":0.00013444459,"about_ca_system_score_gemma":0.00015634387,"threshold_uncertainty_score":0.7665315},"labels":[],"label_agreement":null},{"id":"W4220904311","doi":"10.35957/jatisi.v9i1.1542","title":"Perbandingan Kinerja Akurasi Klasifikasi K-NN, NB dan DT pada APK Android","year":2022,"lang":"id","type":"article","venue":"JATISI (Jurnal Teknik Informatika dan Sistem Informasi)","topic":"Data Mining and Machine Learning Applications","field":"Computer Science","cited_by":12,"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; Operating system; Malware; Humanities; Art","score_opus":0.015192763808830684,"score_gpt":0.24674220878380215,"score_spread":0.23154944497497146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220904311","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":[0.2972808,0.0045324424,0.072028786,0.009853512,0.012630834,0.007502184,0.0017751976,0.0051172096,0.58927906],"genre_scores_gemma":[0.9492847,0.000828304,0.013424608,0.0058895294,0.00088242977,0.000982768,0.0027958578,0.0002330613,0.02567877],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9891366,0.00054705323,0.0038849295,0.0010760599,0.0031571246,0.002198277],"domain_scores_gemma":[0.9913759,0.0007007416,0.003131624,0.0031369226,0.0005191339,0.0011356322],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0035323245,0.0014168062,0.001448622,0.0011414543,0.0052711936,0.0030620887,0.0058041965,0.00036758685,0.00016987661],"category_scores_gemma":[0.0005274532,0.0014481525,0.00076652464,0.0029625183,0.0004035561,0.006830865,0.004322641,0.0037159359,0.0006190521],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055854593,0.0013632795,0.01824817,0.00246247,0.0013034205,0.0002747751,0.11015894,0.010207271,0.0007055113,0.16267662,0.11888559,0.5731554],"study_design_scores_gemma":[0.0026559948,0.001307411,0.007906782,0.0002857325,0.00016122074,0.0025040312,0.009678742,0.050930914,0.000535173,0.00007964835,0.9221483,0.0018060459],"about_ca_topic_score_codex":0.00017849253,"about_ca_topic_score_gemma":0.00004177171,"teacher_disagreement_score":0.8032627,"about_ca_system_score_codex":0.0011715388,"about_ca_system_score_gemma":0.0012046756,"threshold_uncertainty_score":0.9998582},"labels":[],"label_agreement":null},{"id":"W4221136664","doi":"10.34123/icdsos.v2021i1.227","title":"Spatial Analysis of Crime in East Java Province in 2019","year":2022,"lang":"en","type":"article","venue":"Proceedings of The International Conference on Data Science and Official Statistics","topic":"Data Mining and Machine Learning 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":"Java; Negative binomial distribution; Overdispersion; Geography; Population; Demography; Quarter (Canadian coin); Unemployment; Harm; Statistics; Demographic economics; Socioeconomics; Economics; Economic growth; Sociology; Political science; Law; Mathematics; Poisson distribution; Computer science","score_opus":0.044968358247271065,"score_gpt":0.31454898333263465,"score_spread":0.26958062508536357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221136664","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":[0.843605,0.00004692393,0.11018446,0.011393471,0.001103948,0.0009987971,0.01265048,0.00006522251,0.019951709],"genre_scores_gemma":[0.99335855,0.000009946994,0.006432619,0.0000793729,0.000008897849,0.000006535975,0.00005396181,0.000002046972,0.000048076767],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99835116,0.000010459378,0.0002834148,0.0003883407,0.0008376689,0.00012894455],"domain_scores_gemma":[0.99907744,0.000066273155,0.0002659354,0.0002726354,0.00028956757,0.000028132265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011861387,0.00006803623,0.0001419913,0.0004767543,0.0001229344,0.00010849953,0.00402564,0.000011706344,0.000016641681],"category_scores_gemma":[0.00073473225,0.000059137335,0.000011725527,0.0013825166,0.0002424028,0.00043651776,0.0023433901,0.00018380553,6.818763e-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":[0.00002806625,0.0001797816,0.017225023,0.0000062294857,0.000018380482,6.5102876e-7,0.00058968505,0.00054912176,0.0026007923,0.95866567,0.0012224765,0.018914135],"study_design_scores_gemma":[0.00015592972,0.00007927965,0.11675141,0.000018621195,0.000020465248,0.000001576914,0.0003125787,0.8786319,0.0002687699,0.0029565736,0.00070896087,0.000093922295],"about_ca_topic_score_codex":0.0017093244,"about_ca_topic_score_gemma":0.00041358257,"teacher_disagreement_score":0.9557091,"about_ca_system_score_codex":0.00006564594,"about_ca_system_score_gemma":0.00045093446,"threshold_uncertainty_score":0.7480708},"labels":[],"label_agreement":null},{"id":"W4224304405","doi":"10.24843/jmat.2021.v11.i02.p140","title":"Pemanfaatan Big Data dalam Monitoring Pola Aktivitas Aviasi di Indonesia","year":2022,"lang":"en","type":"article","venue":"Jurnal Matematika","topic":"Data Mining and Machine Learning 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":"Aviation; Tourism; Big data; Productivity; Quarter (Canadian coin); Descriptive statistics; Business; Computer science; Engineering; Economics; Geography; Statistics; Mathematics; Economic growth; Data mining","score_opus":0.06176821490968058,"score_gpt":0.2987842646041334,"score_spread":0.23701604969445278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224304405","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":[0.5827638,0.00095300854,0.39230838,0.00847811,0.005749457,0.00088568695,0.0005015487,0.0017979982,0.0065620407],"genre_scores_gemma":[0.9890793,0.000011447884,0.009709617,0.00008896291,0.0003571741,0.00010373026,0.00015902452,0.00002628534,0.0004644623],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99783283,0.00022163766,0.0003822382,0.00060588,0.00060823833,0.00034914285],"domain_scores_gemma":[0.9970562,0.00016488493,0.00027315275,0.002337601,0.00003892695,0.00012927245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010357471,0.00018301717,0.00023433688,0.00018201912,0.00081900816,0.00040761358,0.0037901888,0.000030472314,0.000016689932],"category_scores_gemma":[0.00007930938,0.00017822643,0.000045897206,0.00063828734,0.000028681327,0.0006902147,0.0036070799,0.0005331813,0.0001038085],"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":[0.000048943588,0.0015945967,0.31337088,0.0007519657,0.00042497762,0.00044380684,0.0073476434,0.0030376515,0.010463497,0.13423961,0.046519224,0.4817572],"study_design_scores_gemma":[0.002013093,0.00053053594,0.6641031,0.00040577355,0.00017557372,0.002111232,0.001633229,0.110249154,0.0013739016,0.006377552,0.20880963,0.0022172558],"about_ca_topic_score_codex":0.000077505036,"about_ca_topic_score_gemma":0.0000020104137,"teacher_disagreement_score":0.47953993,"about_ca_system_score_codex":0.000069493115,"about_ca_system_score_gemma":0.000100063735,"threshold_uncertainty_score":0.72678626},"labels":[],"label_agreement":null},{"id":"W4225584334","doi":"10.5267/j.dsl.2022.3.002","title":"Predicting the weekly COVID-19 new cases using multilayer perceptron: An evidence from west Java, Indonesia","year":2022,"lang":"en","type":"article","venue":"Decision Science Letters","topic":"Data Mining and Machine Learning Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Direktorat Riset dan Pengabdian Masyarakat; Universitas Padjadjaran; Universiti Malaysia Terengganu; University of New South Wales; Institute for Catastrophic Loss Reduction; Australasian College for Emergency Medicine","keywords":"Coronavirus disease 2019 (COVID-19); Multilayer perceptron; Government (linguistics); Statistics; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; Medicine; Geography; Demography; Computer science; Disease; Mathematics; Artificial intelligence; Artificial neural network; Internal medicine; Virology","score_opus":0.09870304728022099,"score_gpt":0.37826747619917384,"score_spread":0.27956442891895283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225584334","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":[0.55468273,0.00004935693,0.42590618,0.018720848,0.00034218814,0.00014225313,0.000013913409,0.00013697782,0.000005540262],"genre_scores_gemma":[0.8757577,0.0000032411242,0.10271018,0.021296658,0.00015958905,0.000032202624,0.000006940541,0.000012133811,0.000021333892],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99590147,0.0003072491,0.0003744824,0.0012325072,0.0016827288,0.0005015402],"domain_scores_gemma":[0.99424815,0.002973735,0.00024981005,0.0019886384,0.000057360714,0.0004823146],"candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0029278933,0.0001957958,0.00016886195,0.0003031036,0.0038754963,0.0010992544,0.0055608572,0.000026963084,0.00014798572],"category_scores_gemma":[0.002414487,0.00015398595,0.000065986096,0.0021742177,0.00038986825,0.0022091663,0.0021084158,0.00051636394,0.000066678105],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000068392896,0.0001578594,0.18454365,0.0000049758537,0.000015519654,0.00021099638,0.03419787,0.35569486,0.14994547,0.00056006486,0.050311442,0.22428891],"study_design_scores_gemma":[0.0004584134,0.00015348564,0.12600803,0.000041857205,0.000022295008,0.00044885566,0.0025612675,0.84935534,0.00018856427,0.00024247417,0.020054657,0.00046477784],"about_ca_topic_score_codex":0.007584373,"about_ca_topic_score_gemma":0.000074724485,"teacher_disagreement_score":0.49366048,"about_ca_system_score_codex":0.00032857145,"about_ca_system_score_gemma":0.0007841991,"threshold_uncertainty_score":0.9999377},"labels":[],"label_agreement":null},{"id":"W4226076902","doi":"10.5430/wjel.v12n3p235","title":"Implementation of Efficient Online English Learning System and Student Performance Prediction Using Linear K-Nearest Neighbors (L-Knn) Method","year":2022,"lang":"en","type":"article","venue":"World Journal of English Language","topic":"Data Mining and Machine Learning 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":"Computer science; Machine learning; Artificial intelligence; k-nearest neighbors algorithm; Dimensionality reduction; Naive Bayes classifier; Normalization (sociology); Process (computing); Online learning; Curse of dimensionality; Multimedia; Support vector machine","score_opus":0.010444807087090524,"score_gpt":0.3118742563805611,"score_spread":0.3014294492934706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226076902","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":[0.94386566,0.00028966917,0.054721486,0.000026162916,0.0006892205,0.00011919177,0.000038011334,0.00007322631,0.00017739226],"genre_scores_gemma":[0.95551753,0.000010647919,0.043983243,0.000019773131,0.0003843707,0.0000055133164,0.000022831731,0.000012808481,0.000043253043],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99831945,0.00029555318,0.0005290528,0.00019915198,0.00048783826,0.00016895027],"domain_scores_gemma":[0.99852765,0.00013515579,0.0006697956,0.00023129565,0.0003579487,0.00007818209],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016173063,0.00011078156,0.00022247367,0.0003730634,0.00028656135,0.00006969218,0.00044213628,0.000016749871,0.000018006012],"category_scores_gemma":[0.00016273645,0.000107134394,0.000059919777,0.0005947022,0.000019567857,0.00027270362,0.00033703377,0.0005324146,2.039147e-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":[0.000046376757,0.00036748842,0.07170662,0.0001925911,0.00015864322,0.00003485785,0.14910674,0.6967592,0.0021479588,0.0025523435,0.00021879995,0.076708354],"study_design_scores_gemma":[0.0022184302,0.0008857756,0.04258458,0.00023619646,0.00017360269,0.0001344365,0.12949218,0.80760074,0.0011923595,0.0000020559328,0.01515806,0.0003215621],"about_ca_topic_score_codex":0.000097032134,"about_ca_topic_score_gemma":0.000012921566,"teacher_disagreement_score":0.11084154,"about_ca_system_score_codex":0.00013298176,"about_ca_system_score_gemma":0.00008152122,"threshold_uncertainty_score":0.4368814},"labels":[],"label_agreement":null},{"id":"W4241216943","doi":"10.36418/syntax-idea.v2i5.252","title":"","year":2020,"lang":"","type":"article","venue":"Syntax Idea","topic":"Data Mining and Machine Learning 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":"Encana (Canada); WiLAN (Canada)","funders":"","keywords":"Physics; Humanities; Philosophy","score_opus":0.028183832822652792,"score_gpt":0.266257758222473,"score_spread":0.2380739253998202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241216943","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":[0.055062495,0.0007371721,0.6808529,0.25989488,0.00050923525,0.0006039671,0.00014056536,0.0011003207,0.0010984864],"genre_scores_gemma":[0.9016017,0.0001262891,0.07502887,0.021756852,0.0009855267,0.00013771703,0.0000683888,0.0000749045,0.00021979409],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9913614,0.0007667255,0.0015449317,0.0033756439,0.0012100907,0.001741245],"domain_scores_gemma":[0.9928035,0.00062563247,0.00086453516,0.0031647636,0.00030389577,0.0022376755],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011923658,0.00095165224,0.0010061726,0.00018467352,0.0016652915,0.002385697,0.0073044905,0.00029989504,0.000076147066],"category_scores_gemma":[0.0024211896,0.0010680344,0.00043338657,0.003378444,0.00041009093,0.002518523,0.003939105,0.0018465467,0.0015734469],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001269744,0.00047361062,0.011012914,0.00033337504,0.00029529186,0.0002236473,0.038149703,0.0064892024,0.008267994,0.1422967,0.013659848,0.7786707],"study_design_scores_gemma":[0.0020168307,0.0015431507,0.021734083,0.00021391692,0.00020710926,0.0001393768,0.000983452,0.8511383,0.0022426497,0.0022591949,0.11551102,0.0020109082],"about_ca_topic_score_codex":0.0013853905,"about_ca_topic_score_gemma":0.00003620637,"teacher_disagreement_score":0.84653914,"about_ca_system_score_codex":0.00009571257,"about_ca_system_score_gemma":0.00063947414,"threshold_uncertainty_score":0.9996344},"labels":[],"label_agreement":null},{"id":"W4245087801","doi":"10.29122/alami.v2i2.3102","title":"SISTEM INFORMASI BENCANA TANAH LONGSOR (SI-BENAR) BERBASIS WEB UNTUK WILAYAH DESA CILILIN, KECAMATAN CILILIN, KABUPATEN BANDUNG BARAT","year":2018,"lang":"id","type":"article","venue":"Jurnal Alami Jurnal Teknologi Reduksi Risiko Bencana","topic":"Data Mining and Machine Learning 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":"Encana (Canada)","funders":"","keywords":"Physics; Humanities","score_opus":0.017840921147246787,"score_gpt":0.2650661396347061,"score_spread":0.24722521848745932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245087801","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":[0.9379912,0.005176358,0.0063633174,0.0104634315,0.0049152393,0.0017660941,0.00065857277,0.0015569736,0.031108795],"genre_scores_gemma":[0.97364086,0.0026836183,0.0059991977,0.0017495784,0.0023908166,0.00015548314,0.00040527637,0.00023596265,0.01273921],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98522747,0.0010116606,0.0038937994,0.0033136052,0.002749843,0.0038036173],"domain_scores_gemma":[0.9875912,0.0009273995,0.0027844787,0.004386381,0.0021520646,0.002158491],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","research_integrity"],"category_scores_codex":[0.0031975145,0.0022463088,0.0023106914,0.0015495246,0.0034660818,0.002376449,0.007909863,0.0014341663,0.00034775652],"category_scores_gemma":[0.0016059986,0.002078018,0.0010954404,0.004544882,0.0020270103,0.0030643048,0.0026307532,0.0045057763,0.0014228506],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008970117,0.0027207476,0.187063,0.0008852567,0.003574987,0.002287093,0.008643637,0.0014533448,0.008552929,0.025085252,0.1519737,0.606863],"study_design_scores_gemma":[0.005414828,0.0059064673,0.21766488,0.002120545,0.0016022511,0.004313415,0.0028275417,0.14215052,0.0055316524,0.0009139853,0.60561347,0.0059404373],"about_ca_topic_score_codex":0.0013794963,"about_ca_topic_score_gemma":0.0038190023,"teacher_disagreement_score":0.6009226,"about_ca_system_score_codex":0.0015558084,"about_ca_system_score_gemma":0.003585706,"threshold_uncertainty_score":0.9998622},"labels":[],"label_agreement":null},{"id":"W4253327752","doi":"10.32920/ryerson.14646978.v1","title":"Estimation of Weibull parameters using artificial neural network","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Data Mining and Machine Learning 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":"Weibull distribution; Artificial neural network; Parametric statistics; MATLAB; Shape parameter; Reliability (semiconductor); Computer science; Test data; Parametric model; Estimation theory; Data set; Scale (ratio); Algorithm; Statistics; Mathematics; Machine learning; Artificial intelligence; Power (physics)","score_opus":0.048811740744402095,"score_gpt":0.31215566791495974,"score_spread":0.26334392717055766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253327752","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17170106,0.000047587404,0.8267526,0.0003750966,0.00052818813,0.00010857735,0.0000050127524,0.00014724483,0.00033464326],"genre_scores_gemma":[0.4959461,0.0000018771607,0.5038228,0.00006287938,0.000045351688,0.000009149773,0.000086480664,0.000006229443,0.000019130426],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986581,0.000104282866,0.0003558919,0.00048640498,0.00020007484,0.00019524402],"domain_scores_gemma":[0.9984485,0.00011426397,0.00028839713,0.0010280879,0.00006767359,0.0000531146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030274005,0.000152476,0.00024787922,0.000068293026,0.00009144067,0.0002855255,0.0007736812,0.00011744762,0.000010339127],"category_scores_gemma":[0.00008486219,0.00015677178,0.00009714381,0.00027444394,0.000038795275,0.00014694616,0.0012539914,0.0003805584,0.000006307021],"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":[8.6434414e-7,0.000024100833,0.000048721384,0.000023037413,0.000015828604,0.000001424518,0.00011987265,0.90642333,0.00005274622,0.012349496,0.00023108312,0.0807095],"study_design_scores_gemma":[0.000026725073,0.000012636342,0.00023629073,0.00006171025,0.000021590795,0.0000066729726,0.000014525187,0.9938604,0.00033792818,0.005226554,0.000049452738,0.00014550232],"about_ca_topic_score_codex":0.0005291454,"about_ca_topic_score_gemma":0.000013586998,"teacher_disagreement_score":0.32424504,"about_ca_system_score_codex":0.000024728277,"about_ca_system_score_gemma":0.00015145556,"threshold_uncertainty_score":0.63929677},"labels":[],"label_agreement":null},{"id":"W4255036626","doi":"10.32920/ryerson.14646978","title":"Estimation of Weibull parameters using artificial neural network","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Data Mining and Machine Learning 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":"Weibull distribution; Artificial neural network; Parametric statistics; MATLAB; Shape parameter; Reliability (semiconductor); Computer science; Parametric model; Test data; Estimation theory; Data set; Algorithm; Scale (ratio); Statistics; Mathematics; Machine learning; Artificial intelligence; Power (physics)","score_opus":0.048811740744402095,"score_gpt":0.31215566791495974,"score_spread":0.26334392717055766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255036626","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17170106,0.000047587404,0.8267526,0.0003750966,0.00052818813,0.00010857735,0.0000050127524,0.00014724483,0.00033464326],"genre_scores_gemma":[0.4959461,0.0000018771607,0.5038228,0.00006287938,0.000045351688,0.000009149773,0.000086480664,0.000006229443,0.000019130426],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986581,0.000104282866,0.0003558919,0.00048640498,0.00020007484,0.00019524402],"domain_scores_gemma":[0.9984485,0.00011426397,0.00028839713,0.0010280879,0.00006767359,0.0000531146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030274005,0.000152476,0.00024787922,0.000068293026,0.00009144067,0.0002855255,0.0007736812,0.00011744762,0.000010339127],"category_scores_gemma":[0.00008486219,0.00015677178,0.00009714381,0.00027444394,0.000038795275,0.00014694616,0.0012539914,0.0003805584,0.000006307021],"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":[8.6434414e-7,0.000024100833,0.000048721384,0.000023037413,0.000015828604,0.000001424518,0.00011987265,0.90642333,0.00005274622,0.012349496,0.00023108312,0.0807095],"study_design_scores_gemma":[0.000026725073,0.000012636342,0.00023629073,0.00006171025,0.000021590795,0.0000066729726,0.000014525187,0.9938604,0.00033792818,0.005226554,0.000049452738,0.00014550232],"about_ca_topic_score_codex":0.0005291454,"about_ca_topic_score_gemma":0.000013586998,"teacher_disagreement_score":0.32424504,"about_ca_system_score_codex":0.000024728277,"about_ca_system_score_gemma":0.00015145556,"threshold_uncertainty_score":0.63929677},"labels":[],"label_agreement":null},{"id":"W4282963579","doi":"10.25124/idealog.v7i1.4787","title":"EIGHT ASPECT DESIGNS OF BOARDING SCHOOL BASED ON PREFERENCE IN NEW NORMAL ERA OF COVID-19, KENDARI CITY AND BANDUNG AS CASE STUDIES","year":2022,"lang":"id","type":"article","venue":"Idealog Ide dan Dialog Desain Indonesia","topic":"Data Mining and Machine Learning 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":"Encana (Canada)","funders":"Universitas Lampung","keywords":"Mathematics; Humanities; Philosophy","score_opus":0.06716321374863958,"score_gpt":0.3222149295977828,"score_spread":0.2550517158491432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282963579","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":[0.9456778,0.0014637582,0.04690533,0.0031121457,0.00041068826,0.0011941098,0.0004196601,0.00013493266,0.0006815873],"genre_scores_gemma":[0.99149275,0.000101494246,0.0068703103,0.001076951,0.00007900628,0.00015186476,0.000102122176,0.000035976525,0.000089527246],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99455726,0.0016868593,0.0011436994,0.001191127,0.00074590574,0.0006751374],"domain_scores_gemma":[0.9942388,0.0029163216,0.00087081443,0.0012464478,0.00015129142,0.00057630177],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0031205888,0.0004985338,0.0009908356,0.0007077058,0.0009510535,0.00014685905,0.0012013621,0.00014872901,0.000060018505],"category_scores_gemma":[0.0031023384,0.000544024,0.00015350351,0.00160404,0.00044462882,0.00033086992,0.0011468412,0.0014575102,0.000008454716],"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":[0.0012738357,0.0016342187,0.8170408,0.0012862708,0.0005751026,0.007040006,0.019774191,0.05009829,0.002722437,0.040480647,0.011913334,0.04616087],"study_design_scores_gemma":[0.030351838,0.013528228,0.7177576,0.0022483608,0.0014028822,0.009212513,0.0064072236,0.17068179,0.00626751,0.025755329,0.010091979,0.0062947823],"about_ca_topic_score_codex":0.0105532305,"about_ca_topic_score_gemma":0.001081756,"teacher_disagreement_score":0.1205835,"about_ca_system_score_codex":0.0005087451,"about_ca_system_score_gemma":0.0029061022,"threshold_uncertainty_score":0.99970114},"labels":[],"label_agreement":null},{"id":"W4285009242","doi":"10.36341/rabit.v7i2.2489","title":"IMPLEMENTASI ALGORITMA C4.5 UNTUK KLASIFIKASI PRODUK LARIS SEPEDA MOTOR HONDA PADA CV CENDANA MOTOR CEPIRING","year":2022,"lang":"id","type":"article","venue":"Rabit Jurnal Teknologi dan Sistem Informasi Univrab","topic":"Data Mining and Machine Learning 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":"WiLAN (Canada)","funders":"","keywords":"Physics; Humanities; Art","score_opus":0.020359378687038472,"score_gpt":0.2628968829321344,"score_spread":0.24253750424509596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285009242","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":[0.7569111,0.0079632765,0.087618984,0.030840276,0.01672591,0.012125662,0.005787487,0.008050892,0.073976405],"genre_scores_gemma":[0.8835586,0.0010930385,0.030991744,0.0030387966,0.0012681928,0.0012149275,0.0022747805,0.0003545492,0.07620541],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9905084,0.0008879346,0.0023622143,0.0018872892,0.0019315302,0.0024226792],"domain_scores_gemma":[0.9930553,0.0005090447,0.0019267857,0.0032537072,0.00044068974,0.00081448443],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0026987095,0.0012503428,0.0012628465,0.0009510665,0.0042470032,0.0012578623,0.005871825,0.00036455717,0.00022650551],"category_scores_gemma":[0.00042002226,0.0013203556,0.00069196254,0.0024646865,0.00041029204,0.0020860003,0.0055133263,0.003690514,0.000256927],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00069826585,0.0031452272,0.049158633,0.0017789905,0.0022895983,0.0013902701,0.016729947,0.0030725717,0.013696649,0.09127197,0.050051883,0.766716],"study_design_scores_gemma":[0.0022741968,0.0021749192,0.011279596,0.00013744939,0.000205581,0.0012221577,0.00603603,0.013354927,0.0010179799,0.00010178761,0.96061504,0.001580323],"about_ca_topic_score_codex":0.00046593318,"about_ca_topic_score_gemma":0.00007592375,"teacher_disagreement_score":0.9105632,"about_ca_system_score_codex":0.0016114402,"about_ca_system_score_gemma":0.0014755477,"threshold_uncertainty_score":0.9997789},"labels":[],"label_agreement":null},{"id":"W4285479393","doi":"10.35315/informatika.v13i1.8369","title":"PENERAPAN K-MEANS CLUSTERING PADA PENDAFTARAN ANGGOTA PERPUSTAKAAN DI DINAS KEARSIPAN DAN PERPUSTAKAAN PROVINSI JAWA TENGAH","year":2021,"lang":"id","type":"article","venue":"Jurnal Dinamika Informatika","topic":"Data Mining and Machine Learning 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":"Encana (Canada)","funders":"","keywords":"Cluster (spacecraft); Humanities; Computer science; Art; Operating system","score_opus":0.016664405094667007,"score_gpt":0.2542756422225722,"score_spread":0.2376112371279052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285479393","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":[0.5314411,0.0023004552,0.36452353,0.011907721,0.005277191,0.0024192824,0.0007893362,0.0020161343,0.07932524],"genre_scores_gemma":[0.95451725,0.00050992385,0.020562937,0.0014830921,0.00061798486,0.00012616052,0.0009973713,0.00016444673,0.021020865],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99278235,0.0004803062,0.0019070638,0.0013967074,0.001462442,0.0019711081],"domain_scores_gemma":[0.99385357,0.00026083642,0.0010802026,0.002916218,0.00083216827,0.0010570079],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0012666989,0.0011436567,0.0011009044,0.00056937564,0.0023041342,0.0035131145,0.0030112085,0.00042703425,0.00015825979],"category_scores_gemma":[0.0005589218,0.0011628475,0.00059049984,0.0018782191,0.0003711255,0.0042468025,0.0025638617,0.002474074,0.00070646545],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022562488,0.00372718,0.06363515,0.0036391923,0.0015059063,0.0015838918,0.11880132,0.0131396735,0.008594471,0.03269945,0.03923473,0.7132134],"study_design_scores_gemma":[0.002443161,0.0005171522,0.11292912,0.0008252009,0.00024586183,0.0018947133,0.0080881845,0.5224075,0.0006617093,0.00004050984,0.34784442,0.0021024982],"about_ca_topic_score_codex":0.00080803764,"about_ca_topic_score_gemma":0.0008070174,"teacher_disagreement_score":0.7111109,"about_ca_system_score_codex":0.0004972123,"about_ca_system_score_gemma":0.0013935,"threshold_uncertainty_score":0.99982727},"labels":[],"label_agreement":null},{"id":"W4285664007","doi":"10.24912/computatio.v4i1.7190","title":"Program Pendeteksi Perubahan Fungsi Lahan Menggunakan Metode Ridge Regression Dan Support Vector Machine (Studi Kasus: 95 Kecamatan Di Wilayah Bekasi, Depok Dan Tangerang)","year":2020,"lang":"id","type":"article","venue":"Computatio Journal of Computer Science and Information Systems","topic":"Data Mining and Machine Learning 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":"WiLAN (Canada)","funders":"","keywords":"Forestry; Physics; Geography; Mathematics; Humanities; Art","score_opus":0.020290741934838274,"score_gpt":0.2797459611494528,"score_spread":0.25945521921461456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285664007","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":[0.13665508,0.0024706502,0.84688574,0.0061216913,0.0042191367,0.001946669,0.00014914805,0.00048749906,0.0010644109],"genre_scores_gemma":[0.978085,0.0002424861,0.01920974,0.0012388806,0.0009911675,0.000032421052,0.00015004996,0.000031384418,0.000018910678],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99279726,0.00043955748,0.0024884013,0.00075088604,0.002657885,0.0008660415],"domain_scores_gemma":[0.9923286,0.00026172324,0.0030570384,0.00077702006,0.002373457,0.0012021477],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0030805331,0.00067189115,0.0010814577,0.0007199642,0.0014506407,0.0047666915,0.0029598905,0.00017110417,0.0000036613803],"category_scores_gemma":[0.0002846607,0.00055482367,0.00022336858,0.0025975024,0.00057659915,0.011737949,0.0011598197,0.0009923372,0.00006865966],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015964321,0.0005428406,0.0058941953,0.0013737539,0.0003744231,0.000117476375,0.06661126,0.021390209,0.00086673256,0.0040481277,0.022724535,0.8758968],"study_design_scores_gemma":[0.0014830404,0.0024819712,0.010989414,0.0005632702,0.000095135285,0.00097362924,0.0010655351,0.8558147,0.00016486004,0.000007767973,0.12574536,0.0006153608],"about_ca_topic_score_codex":0.000049106802,"about_ca_topic_score_gemma":0.000001879176,"teacher_disagreement_score":0.87528145,"about_ca_system_score_codex":0.00023324261,"about_ca_system_score_gemma":0.0012244716,"threshold_uncertainty_score":0.9998493},"labels":[],"label_agreement":null},{"id":"W4285738507","doi":"10.55537/jistr.v1i2.139","title":"Data Mining Grouping Of Drug Users By Age Using Clustering Method (Case Study: BNN Binjai City)","year":2022,"lang":"en","type":"article","venue":"Journal of Information Systems and Technology Research","topic":"Data Mining and Machine Learning 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":"Cluster analysis; Process (computing); Computer science; Data mining; Cluster (spacecraft); Artificial intelligence; Machine learning","score_opus":0.12218052955565686,"score_gpt":0.4221643529561197,"score_spread":0.2999838234004628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285738507","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":[0.57193804,0.00020325847,0.4270163,0.0003473317,0.00011694671,0.0002275574,0.000028598919,0.000039271403,0.00008273709],"genre_scores_gemma":[0.9528658,0.000010558248,0.047039006,0.000010230436,0.000016175418,0.0000140965685,0.000009769491,0.000005029653,0.000029372928],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99787855,0.00040041204,0.00076818804,0.00015343317,0.0005869924,0.00021244766],"domain_scores_gemma":[0.9979541,0.0002630073,0.00068525155,0.00069171377,0.00034746146,0.000058478236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009185952,0.00007893173,0.00025203213,0.0016827033,0.0006357627,0.00024109682,0.0014904451,0.000046846366,0.000001472198],"category_scores_gemma":[0.00032338733,0.00007278869,0.000016841215,0.0018299711,0.0000698331,0.0015516194,0.0024970786,0.00076502195,4.6949717e-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":[0.00013129174,0.0010205993,0.072465025,0.00095917145,0.0010644115,0.0021028398,0.07371286,0.02203118,0.008640788,0.017174011,0.02494511,0.7757527],"study_design_scores_gemma":[0.001173367,0.0005998399,0.000091513815,0.00013030495,0.000024614075,0.0141964685,0.13682981,0.8089768,0.00007666825,0.00007070808,0.037640937,0.00018893447],"about_ca_topic_score_codex":0.0005950088,"about_ca_topic_score_gemma":0.00001258023,"teacher_disagreement_score":0.78694564,"about_ca_system_score_codex":0.000067185785,"about_ca_system_score_gemma":0.0001374944,"threshold_uncertainty_score":0.4889837},"labels":[],"label_agreement":null},{"id":"W4285738513","doi":"10.55537/jistr.v1i2.136","title":"Implementation Of Data Mining Grouping Of Old Age Guarantee (Jht) Based On Region In Pandemic Period","year":2022,"lang":"en","type":"article","venue":"Journal of Information Systems and Technology Research","topic":"Data Mining and Machine Learning 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":"Cluster analysis; Process (computing); Computer science; Service (business); Cluster (spacecraft); Data mining; Big data; Life insurance; Business; Data science; Computer security; Actuarial science; Artificial intelligence; Marketing","score_opus":0.08611399575565673,"score_gpt":0.3969062118030297,"score_spread":0.31079221604737295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285738513","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":[0.94029635,0.00015903338,0.05741855,0.001550765,0.00007465341,0.00026661498,0.000024907637,0.0000242761,0.00018484621],"genre_scores_gemma":[0.99684495,0.000028530196,0.0030599274,0.00001323193,0.0000073798133,0.000016391248,0.000020005808,0.0000022701743,0.0000073101232],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984619,0.00016549422,0.00067995675,0.00009334786,0.00046918626,0.00013012915],"domain_scores_gemma":[0.99850416,0.0001498162,0.0006271285,0.0004502934,0.00025167185,0.000016944374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004006366,0.000048430742,0.00017748235,0.0017552685,0.00013949008,0.000046763722,0.0009179426,0.000044697405,0.0000015792542],"category_scores_gemma":[0.00016720835,0.000043721917,0.0000133012545,0.0012028384,0.00006331079,0.0007928495,0.00043754897,0.00044719988,4.5832167e-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":[0.0001426166,0.00019870387,0.21210392,0.0005306656,0.00007421583,0.00004745798,0.012376195,0.005381274,0.0024807213,0.095671296,0.0033320345,0.6676609],"study_design_scores_gemma":[0.0063548204,0.0042038723,0.039066833,0.0010673689,0.000021076938,0.0016692416,0.10658618,0.805343,0.0006062216,0.0009755571,0.03373018,0.00037567766],"about_ca_topic_score_codex":0.00017060769,"about_ca_topic_score_gemma":0.000008863591,"teacher_disagreement_score":0.7999617,"about_ca_system_score_codex":0.00005571357,"about_ca_system_score_gemma":0.0001664869,"threshold_uncertainty_score":0.19428858},"labels":[],"label_agreement":null},{"id":"W4286436713","doi":"10.18280/isi.270317","title":"Student Performance Prediction in Sebelas Maret University Based on the Random Forest Algorithm","year":2022,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Data Mining and Machine Learning 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":"Random forest; Support vector machine; Feature selection; Decision tree; Computer science; Machine learning; Data pre-processing; Artificial intelligence; Preprocessor; Statistical classification; Feature (linguistics); Data mining","score_opus":0.00804468182461166,"score_gpt":0.204745272260683,"score_spread":0.19670059043607135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286436713","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":[0.21849857,0.0000072913786,0.76748025,0.00064152456,0.0002819114,0.0005423058,0.00009164984,0.00024517777,0.01221129],"genre_scores_gemma":[0.99570674,0.0000042862134,0.0035462992,0.00029216052,0.000014475037,0.00008610482,0.0001730929,0.0000036165022,0.00017320667],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989651,0.00016815592,0.00022441025,0.00013108118,0.0003432247,0.00016804568],"domain_scores_gemma":[0.9992192,0.00014647644,0.00015512711,0.0003968514,0.000050847033,0.00003153861],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092435925,0.00009370226,0.000088273555,0.0002368702,0.00078598416,0.00015739776,0.0006824258,0.000025080202,0.000035490055],"category_scores_gemma":[0.00004937978,0.00008268457,0.000032093838,0.0006801996,0.00004252365,0.0013646712,0.00023059522,0.00026847151,0.00005170151],"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":[0.000101840604,0.00016144142,0.035993975,0.00005568498,0.000023202956,0.000004843372,0.012895875,0.5377764,0.000005472774,0.020647071,0.005094424,0.38723978],"study_design_scores_gemma":[0.00071599975,0.00014039346,0.07128498,0.00002195591,0.000003659017,0.0000076062674,0.0008938598,0.90452266,0.0000074951854,0.00015168943,0.02216307,0.00008665774],"about_ca_topic_score_codex":0.00007554624,"about_ca_topic_score_gemma":0.000006208086,"teacher_disagreement_score":0.7772082,"about_ca_system_score_codex":0.00036043784,"about_ca_system_score_gemma":0.000075060016,"threshold_uncertainty_score":0.6045234},"labels":[],"label_agreement":null},{"id":"W4290988756","doi":"10.47709/dsi.v2i1.1664","title":"Penggunaan Metode Backpropagation Pada Sistem Prediksi Kelulusan Mahasiswa STMIK Kaputama Binjai","year":2022,"lang":"id","type":"article","venue":"Data Sciences Indonesia (DSI)","topic":"Data Mining and Machine Learning 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":"Humanities; Physics; Philosophy","score_opus":0.06527736712589116,"score_gpt":0.31589579030056114,"score_spread":0.25061842317467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4290988756","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":[0.42873025,0.00640268,0.42163104,0.058395278,0.017900165,0.0076215663,0.021002982,0.003927638,0.03438839],"genre_scores_gemma":[0.9701242,0.000110163666,0.020822141,0.0010096373,0.0004423165,0.00031043997,0.0048434893,0.0000649344,0.0022727025],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9895711,0.001457253,0.0011840665,0.003554753,0.002838062,0.0013947727],"domain_scores_gemma":[0.9919876,0.00065544073,0.001048019,0.005648656,0.0001833188,0.00047696204],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0068187607,0.0006862821,0.00070941093,0.0006841953,0.005602792,0.0022901038,0.016293826,0.00015600753,0.00043817758],"category_scores_gemma":[0.00039603756,0.00069765304,0.00015499133,0.0051324205,0.0010945548,0.0037178071,0.012291019,0.0013546909,0.00053627044],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028392344,0.004294849,0.047940236,0.00063459616,0.00059604825,0.00035178184,0.0129147265,0.020835947,0.007463266,0.07163203,0.3825212,0.4505314],"study_design_scores_gemma":[0.0012418568,0.0009485104,0.01590943,0.000100078265,0.00021386394,0.00037494267,0.0024177572,0.53557384,0.00050775905,0.00041058348,0.44081655,0.0014848377],"about_ca_topic_score_codex":0.0009135126,"about_ca_topic_score_gemma":0.00012393357,"teacher_disagreement_score":0.54139394,"about_ca_system_score_codex":0.0002920192,"about_ca_system_score_gemma":0.0014764767,"threshold_uncertainty_score":0.9995475},"labels":[],"label_agreement":null},{"id":"W4291184287","doi":"10.51544/jlmk.v6i1.2454","title":"Mediatisasi Politik dan Perilaku Pemilih: Penggunaan Google Trend Sebagai Metode Alternatif Memprediksi Kemenangan Kandidat","year":2022,"lang":"en","type":"article","venue":"JURNAL LENSA MUTIARA KOMUNIKASI","topic":"Data Mining and Machine Learning 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":"Popularity; Victory; Governor; Presidential system; Context (archaeology); Indonesian; Geography; Political science; Advertising; Politics; Business; Law; Engineering","score_opus":0.011875900699884468,"score_gpt":0.25019256789027594,"score_spread":0.23831666719039146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4291184287","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":[0.89317083,0.0014191453,0.028392307,0.018607086,0.0031551786,0.0010018826,0.0011638429,0.0019407035,0.05114903],"genre_scores_gemma":[0.9793524,0.00007622549,0.014428762,0.0014246224,0.00047172623,0.00024761225,0.0005696844,0.000070386406,0.0033585464],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99547493,0.00058047776,0.0006965167,0.0010858276,0.0012046789,0.00095754827],"domain_scores_gemma":[0.99665666,0.00033129388,0.00043966115,0.0020276443,0.00008917184,0.00045558522],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0012036017,0.0004634935,0.0005100608,0.0004523857,0.00166178,0.00044045772,0.0032299394,0.00009114251,0.0002431079],"category_scores_gemma":[0.00015404663,0.0004716442,0.00024857378,0.00097388745,0.00015249416,0.00081816054,0.00206352,0.0012980852,0.00008764882],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016007967,0.002035775,0.019246912,0.00013226792,0.0009013377,0.00066486414,0.036352947,0.0063914554,0.0137658985,0.3148426,0.10064441,0.5048615],"study_design_scores_gemma":[0.0019106482,0.0005639174,0.014107581,0.000037883212,0.00012976002,0.0008841835,0.0017587291,0.049240272,0.0022256302,0.001875269,0.9260301,0.0012360492],"about_ca_topic_score_codex":0.0007428155,"about_ca_topic_score_gemma":0.00012813993,"teacher_disagreement_score":0.8253857,"about_ca_system_score_codex":0.00032051103,"about_ca_system_score_gemma":0.00028822044,"threshold_uncertainty_score":0.9997735},"labels":[],"label_agreement":null},{"id":"W4292692863","doi":"10.21154/elbarka.v4i1.3016","title":"Forecasting of Indonesia's Gross Domestic Product Amid Covid-19 Pandemic","year":2021,"lang":"en","type":"article","venue":"El-Barka Journal of Islamic Economics and Business","topic":"Data Mining and Machine Learning Applications","field":"Computer Science","cited_by":2,"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":"Quarter (Canadian coin); Autoregressive integrated moving average; Christian ministry; Coronavirus disease 2019 (COVID-19); Pandemic; Gross domestic product; Geography; Indonesian; Business; Economic growth; Economics; Political science; Statistics; Mathematics; Time series; Medicine","score_opus":0.03030405680275415,"score_gpt":0.2809412956502209,"score_spread":0.25063723884746675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292692863","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":[0.9078078,0.00093555864,0.08843618,0.0021789726,0.00036233553,0.00005860161,0.000011311233,0.000015747743,0.00019343497],"genre_scores_gemma":[0.9864568,0.0010976471,0.011927996,0.0002359435,0.00020779786,0.0000024186872,0.000009243678,0.000011887553,0.00005023983],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880093,0.000058039255,0.00059156655,0.0002829405,0.00008024433,0.00018627041],"domain_scores_gemma":[0.99819237,0.00028990232,0.0007300226,0.0003700784,0.00032833256,0.000089288435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008318119,0.00013663767,0.00035806803,0.00016365854,0.0001421861,0.0001483055,0.0005207024,0.000046518842,0.000004110555],"category_scores_gemma":[0.00060815935,0.00012631828,0.00006153235,0.00034864031,0.0000980637,0.00042155705,0.00023263134,0.0002189138,0.000001513343],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013256665,0.0006941785,0.21280701,0.001103584,0.0004946547,0.0004052818,0.0053680725,0.08031877,0.005851894,0.15105177,0.001379295,0.54039294],"study_design_scores_gemma":[0.012420588,0.00065755425,0.2904168,0.001206505,0.00049530633,0.062735096,0.0010756766,0.39592177,0.0025189759,0.17257065,0.057180855,0.0028002334],"about_ca_topic_score_codex":0.000039225706,"about_ca_topic_score_gemma":0.000022521876,"teacher_disagreement_score":0.53759265,"about_ca_system_score_codex":0.000067814566,"about_ca_system_score_gemma":0.00078093016,"threshold_uncertainty_score":0.515111},"labels":[],"label_agreement":null},{"id":"W4292959236","doi":"10.5267/j.ijdns.2022.6.004","title":"The implementation of the ARIMA-ARCH model using data mining for forecasting rainfall in Bandung city","year":2022,"lang":"en","type":"article","venue":"International Journal of Data and Network Science","topic":"Data Mining and Machine Learning 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":"Universitas Padjadjaran","keywords":"Autoregressive integrated moving average; Univariate; Autoregressive model; Heteroscedasticity; Time series; Multivariate statistics; Moving average; Moving-average model; Variance (accounting); Statistics; Box–Jenkins; Mean absolute percentage error; Computer science; Econometrics; Data mining; Mathematics; Mean squared error","score_opus":0.15870991631891126,"score_gpt":0.41844338052449254,"score_spread":0.2597334642055813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292959236","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":[0.3272002,0.0001666721,0.66927916,0.0023891837,0.0005712623,0.00013207225,0.00022297207,0.000003904691,0.000034566416],"genre_scores_gemma":[0.8734964,0.000015787009,0.12625785,0.000106395564,0.00008711303,0.0000027013903,0.000026086002,0.0000022897405,0.000005389245],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986792,0.000057221634,0.00033735266,0.0002216526,0.00055137597,0.00015317152],"domain_scores_gemma":[0.99836564,0.00040348794,0.00046345327,0.00058940554,0.0001508237,0.000027195982],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0054375366,0.000046654095,0.00007181338,0.00007749826,0.0006531748,0.00019077,0.006811029,0.000006427897,9.094417e-7],"category_scores_gemma":[0.00024816094,0.000031664036,0.000015610543,0.00040697283,0.00012478596,0.001169181,0.004738214,0.00015199964,1.2289694e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005286548,0.0000577935,0.0875012,0.0000057667344,0.000053019587,0.0000022983022,0.0027386104,0.3332849,0.0010464226,0.008322365,0.0041223103,0.56281245],"study_design_scores_gemma":[0.00022619742,0.000020354195,0.0029156213,0.000018516936,0.0000060308657,0.000060674265,0.00029388786,0.99365854,0.000021571805,0.0012051193,0.001537457,0.000036004614],"about_ca_topic_score_codex":0.000084467785,"about_ca_topic_score_gemma":0.00009750311,"teacher_disagreement_score":0.6603736,"about_ca_system_score_codex":0.000045093493,"about_ca_system_score_gemma":0.00043756605,"threshold_uncertainty_score":0.9985626},"labels":[],"label_agreement":null},{"id":"W4293015891","doi":"10.55601/jsm.v17i2.336","title":"Integrasi Density Based Feature Selection dan Adaptive Boosting dalam Mengatasi Ketidakseimbangan Kelas","year":2016,"lang":"id","type":"article","venue":"Jurnal SIFO Mikroskil","topic":"Data Mining and Machine Learning 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":"Tellabs (Canada)","funders":"","keywords":"AdaBoost; Artificial intelligence; Computer science; Classifier (UML)","score_opus":0.014496429529068239,"score_gpt":0.2534770109623909,"score_spread":0.23898058143332265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293015891","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":[0.16807194,0.0004265523,0.8079885,0.01612781,0.0015672044,0.0007514245,0.00017774224,0.00097589707,0.003912898],"genre_scores_gemma":[0.95389414,0.00005129175,0.033889543,0.00070354424,0.0007454412,0.000052258223,0.0000894746,0.00008010944,0.010494213],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9955711,0.0006778577,0.000583909,0.0013926446,0.0007895273,0.0009849833],"domain_scores_gemma":[0.9963231,0.00089325843,0.0006826546,0.0010843065,0.0005111547,0.00050551153],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0013042577,0.00064475957,0.00054176466,0.00028528692,0.0014077238,0.0006313589,0.0014286289,0.0003855664,0.000044194567],"category_scores_gemma":[0.0010363229,0.0004964935,0.000288559,0.0010897621,0.0002552804,0.00084818143,0.00049559824,0.001524317,0.00038048718],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050276105,0.0015081443,0.118450075,0.00015829789,0.0005642107,0.00014519,0.0029903129,0.00031335352,0.1126965,0.028945226,0.09582611,0.6378998],"study_design_scores_gemma":[0.0057695555,0.002766693,0.4691172,0.0031552622,0.0006023758,0.0008343085,0.000549616,0.08375818,0.0542996,0.0010948284,0.37455443,0.0034979563],"about_ca_topic_score_codex":0.00025274762,"about_ca_topic_score_gemma":0.00033985885,"teacher_disagreement_score":0.78582215,"about_ca_system_score_codex":0.00045774376,"about_ca_system_score_gemma":0.0006031471,"threshold_uncertainty_score":0.9998923},"labels":[],"label_agreement":null},{"id":"W4293180824","doi":"10.47995/jian.v4i1.70","title":"Pengembangan Sumber Daya Manusia Dalam Manajemen Bencana (Studi Di BPBD Kabupaten Bangka)","year":2022,"lang":"id","type":"article","venue":"Jurnal Studia Administrasi","topic":"Data Mining and Machine Learning 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":"Encana (Canada)","funders":"","keywords":"Political science; Humanities; Business; Art","score_opus":0.024006512055807866,"score_gpt":0.2839719924616195,"score_spread":0.2599654804058117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293180824","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":[0.72881085,0.004129954,0.0057384553,0.02651519,0.007473355,0.00266805,0.0012306136,0.0012533246,0.22218023],"genre_scores_gemma":[0.9746329,0.00017820283,0.0007921799,0.00043408087,0.00057211425,0.00043841082,0.00034608325,0.000100585334,0.022505421],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99345416,0.0006167497,0.0010591315,0.0017857285,0.0016917689,0.001392472],"domain_scores_gemma":[0.9961737,0.00035889412,0.00077072077,0.001867596,0.00017456234,0.00065453764],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0013779864,0.00077459693,0.00081782223,0.00027791917,0.0034285744,0.0007496385,0.0036800585,0.00013692192,0.00047889983],"category_scores_gemma":[0.00013488889,0.00085254054,0.00037216427,0.0014734785,0.00024982187,0.00046800004,0.0037871036,0.002011074,0.00034562286],"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":[0.000210527,0.006153326,0.49453014,0.00033203617,0.002512437,0.00292767,0.013598546,0.00061687303,0.0004226554,0.11752396,0.21599473,0.1451771],"study_design_scores_gemma":[0.0008769329,0.001133875,0.47880667,0.000039081846,0.00026815024,0.00030691864,0.0011939874,0.00085985666,0.00003705449,0.000078533754,0.51557946,0.0008194727],"about_ca_topic_score_codex":0.00043079487,"about_ca_topic_score_gemma":0.00034084916,"teacher_disagreement_score":0.29958475,"about_ca_system_score_codex":0.0004697591,"about_ca_system_score_gemma":0.0010495842,"threshold_uncertainty_score":0.9993925},"labels":[],"label_agreement":null},{"id":"W4293214428","doi":"10.5267/j.ijdns.2022.4.008","title":"Data quality analytics, business ethics, and cyber risk management on operational performance and fintech sustainability","year":2022,"lang":"en","type":"article","venue":"International Journal of Data and Network Science","topic":"Data Mining and Machine Learning 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":"","keywords":"Business; LISREL; Structural equation modeling; Operational risk management; Analytics; Accounting; Risk management; Operational risk; Quality (philosophy); Sustainability; Descriptive statistics; Knowledge management; Process management; Computer science; Finance; Data science; Statistics","score_opus":0.06215650915473732,"score_gpt":0.38296671872973004,"score_spread":0.32081020957499273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293214428","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":[0.41139215,0.0008113105,0.5416112,0.04206872,0.0015090762,0.0003103064,0.0014196527,0.00004947592,0.00082813785],"genre_scores_gemma":[0.9572606,0.0010061936,0.040841457,0.0005735985,0.00013360658,0.0000025066374,0.00011341469,0.0000030881845,0.00006551505],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979538,0.00017342472,0.00031936078,0.00051747734,0.00088398514,0.00015196197],"domain_scores_gemma":[0.99786675,0.00039945293,0.00029253756,0.0008774177,0.00047662642,0.00008723242],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008924146,0.00008424652,0.00011400044,0.00014676296,0.00089689693,0.00046091378,0.0038733217,0.00001649454,0.000006335258],"category_scores_gemma":[0.0007881727,0.00007312029,0.0000075770868,0.00043913294,0.00034821272,0.0018059786,0.00676479,0.0005748888,6.192204e-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":[0.00013919099,0.0002905854,0.12115952,0.000045760728,0.0001591431,0.000034375094,0.0010554879,0.024486542,0.000011767371,0.1319131,0.016965,0.7037395],"study_design_scores_gemma":[0.000526598,0.00012693506,0.3749745,0.000047368485,0.00002758417,0.00022791585,0.0003417539,0.5184596,0.0000025062914,0.005423941,0.09964333,0.0001979807],"about_ca_topic_score_codex":0.00006713141,"about_ca_topic_score_gemma":0.000012997921,"teacher_disagreement_score":0.7035416,"about_ca_system_score_codex":0.00006217371,"about_ca_system_score_gemma":0.00027647772,"threshold_uncertainty_score":0.8431827},"labels":[],"label_agreement":null},{"id":"W4293768517","doi":"10.33395/sinkron.v7i2.11401","title":"Predictions of Indonesia Economic Phenomena Based on Online News Using Random Forest","year":2022,"lang":"en","type":"article","venue":"SinkrOn","topic":"Data Mining and Machine Learning Applications","field":"Computer Science","cited_by":8,"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":"Quarter (Canadian coin); Random forest; Recession; Variance (accounting); Indonesian; Econometrics; Overfitting; Real gross domestic product; Statistics; Computer science; Business; Economics; Geography; Mathematics; Artificial intelligence; Accounting; Macroeconomics","score_opus":0.017706452439641838,"score_gpt":0.2625500304331479,"score_spread":0.24484357799350606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293768517","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":[0.3379849,0.00002785001,0.65776366,0.001486168,0.00038063593,0.0002598337,0.00023888187,0.00020815188,0.001649948],"genre_scores_gemma":[0.9851376,0.0000013074908,0.014304322,0.00021204604,0.0000774425,0.000034845703,0.00015082976,0.00001033601,0.000071275674],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999206,0.000084129126,0.0001929718,0.00025458334,0.00012840917,0.0001338868],"domain_scores_gemma":[0.99914473,0.00010467483,0.00013642176,0.00055853423,0.000012035404,0.00004357843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019472235,0.00008096446,0.00012566842,0.00014880333,0.0002699706,0.00002944084,0.0004991323,0.000016476182,0.000030440844],"category_scores_gemma":[0.000013020417,0.00008584551,0.000048062346,0.0001997138,0.000026393436,0.00010465951,0.0001791112,0.00017074215,0.000008817576],"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":[0.00002968375,0.00019021929,0.00512954,0.0000052052624,0.00000912137,7.3061636e-7,0.00014362378,0.97923964,0.00016402583,0.0039770114,0.00086633017,0.010244875],"study_design_scores_gemma":[0.0009367828,0.0001523601,0.006416748,0.0000062716053,0.000009884622,0.0000038197413,0.00003993683,0.9819843,0.00001699051,0.00017931534,0.010171103,0.00008244098],"about_ca_topic_score_codex":0.00035329393,"about_ca_topic_score_gemma":0.000038388014,"teacher_disagreement_score":0.6471527,"about_ca_system_score_codex":0.00010797448,"about_ca_system_score_gemma":0.00014731365,"threshold_uncertainty_score":0.35006782},"labels":[],"label_agreement":null},{"id":"W4296106886","doi":"10.35957/jatisi.v9i3.2799","title":"Perbandingan Metode K-Means dan GA K-Means untuk Clustering Dataset Heart Disease Patients","year":2022,"lang":"id","type":"article","venue":"JATISI (Jurnal Teknik Informatika dan Sistem Informasi)","topic":"Data Mining and Machine Learning 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":"Innovation Cluster (Canada)","funders":"","keywords":"Mathematics; Medicine","score_opus":0.015771339921378365,"score_gpt":0.2579603977869958,"score_spread":0.24218905786561745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296106886","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":[0.18934223,0.0029206264,0.46898335,0.020875793,0.022143364,0.018030029,0.086604655,0.007116234,0.1839837],"genre_scores_gemma":[0.875972,0.00031821066,0.021789348,0.017510675,0.0008565838,0.001455235,0.07466628,0.0003472374,0.0070844716],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9905243,0.000521337,0.0031422924,0.0010170069,0.0028835332,0.0019115598],"domain_scores_gemma":[0.99234486,0.00043617323,0.002060385,0.0032561154,0.00036444422,0.001538043],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0023456588,0.0012053822,0.0011429617,0.00092393754,0.004823093,0.0025732461,0.0047686426,0.0001966001,0.00013613685],"category_scores_gemma":[0.0004747546,0.001268672,0.0005096088,0.0019430559,0.00030134572,0.0071693608,0.005700401,0.002576554,0.0004925881],"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":[0.0013026653,0.0030820216,0.10144574,0.0038683985,0.0012593826,0.00017538122,0.07648049,0.10873388,0.00006754396,0.03947318,0.48794472,0.17616658],"study_design_scores_gemma":[0.0019997742,0.00068241055,0.018538635,0.00024718186,0.00016803038,0.00019507263,0.0025192683,0.2053186,0.00001935996,0.00002535886,0.7690256,0.0012606911],"about_ca_topic_score_codex":0.000117742464,"about_ca_topic_score_gemma":0.000039496586,"teacher_disagreement_score":0.6866297,"about_ca_system_score_codex":0.0010339479,"about_ca_system_score_gemma":0.0008849746,"threshold_uncertainty_score":0.99972457},"labels":[],"label_agreement":null},{"id":"W4311237010","doi":"10.18280/mmep.090508","title":"A Comparative Study of Regression Machine Learning Algorithms: Tradeoff Between Accuracy and Computational Complexity","year":2022,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Data Mining and Machine Learning Applications","field":"Computer Science","cited_by":30,"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":"Random forest; Machine learning; Computer science; Support vector machine; Artificial intelligence; Artificial neural network; Mean squared error; Regression; Perceptron; Multilayer perceptron; Regression analysis; Linear regression; Algorithm; Computational complexity theory; Statistics; Mathematics","score_opus":0.08228267693032645,"score_gpt":0.2974609950454966,"score_spread":0.21517831811517016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311237010","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":[0.24616112,0.00011019807,0.7532337,0.0001100951,0.000011969733,0.00019639681,0.000010134963,0.00013112604,0.000035304412],"genre_scores_gemma":[0.8340712,0.000004097161,0.16580692,0.0000038282333,0.000008912283,0.00005598409,0.000022905593,0.000009580514,0.000016530807],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883217,0.00008669219,0.00032434615,0.00031757387,0.00027414734,0.0001650717],"domain_scores_gemma":[0.99904275,0.00053567503,0.00011859472,0.00019146767,0.000027648255,0.00008386882],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004964884,0.00014935958,0.0003298922,0.00011059264,0.0003422734,0.00006875736,0.00026516232,0.00002204246,0.0000041340545],"category_scores_gemma":[0.00002956002,0.00013557637,0.000022716844,0.00022603998,0.00003768515,0.00012485425,0.0003763999,0.00042863077,9.765167e-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":[0.0000019611186,0.0001733409,0.00020534861,0.000093488066,0.000031362124,7.685975e-7,0.009185371,0.9759665,0.00001889824,0.012560468,0.000005398182,0.001757109],"study_design_scores_gemma":[0.0003546914,0.00025295108,0.00026094945,0.000047493842,0.00001733135,0.000017950259,0.00028489702,0.98597103,0.000005824015,0.012495986,0.00015174809,0.00013911883],"about_ca_topic_score_codex":0.000045652243,"about_ca_topic_score_gemma":2.660403e-7,"teacher_disagreement_score":0.5879101,"about_ca_system_score_codex":0.000014187886,"about_ca_system_score_gemma":0.000010915166,"threshold_uncertainty_score":0.55286443},"labels":[],"label_agreement":null},{"id":"W4312336244","doi":"10.30865/json.v3i4.4198","title":"Sistem Prediksi Pertumbuhan Ekonomi Kabupaten Musi Rawas, Kabupaten Musi Rawas Utara Dan Kota Lubuklinggau Dengan Metode Regresi Linier","year":2022,"lang":"en","type":"article","venue":"Jurnal Sistem Komputer dan Informatika (JSON)","topic":"Data Mining and Machine Learning 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":"Quarter (Canadian coin); Business; Goods and services; Economic welfare; Welfare; Geography; Economy; Economics","score_opus":0.01380890243024287,"score_gpt":0.22981892473826598,"score_spread":0.2160100223080231,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312336244","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":[0.78740263,0.00063108635,0.17812786,0.006367611,0.004755396,0.0021780736,0.00028336214,0.0030461282,0.017207885],"genre_scores_gemma":[0.9672317,0.00005807662,0.025500828,0.0028229929,0.00093723304,0.0006322052,0.00079769606,0.00015161982,0.0018676416],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9926613,0.0006541437,0.0022151035,0.0013776011,0.0015958804,0.0014959961],"domain_scores_gemma":[0.9938557,0.0004752265,0.0015420422,0.0029855894,0.00033639095,0.00080501445],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0022828025,0.0009768202,0.0011079926,0.000789406,0.0025416468,0.0018412368,0.005595262,0.00026988745,0.00003378966],"category_scores_gemma":[0.00014042293,0.00095038343,0.0006251863,0.0015663044,0.00016700463,0.0029920673,0.004103923,0.0020227535,0.00014752896],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041623943,0.0016424255,0.043115787,0.0011159304,0.0019442415,0.00054565415,0.06433886,0.07295988,0.0008925924,0.051726528,0.054675918,0.70662594],"study_design_scores_gemma":[0.0020294,0.00062364683,0.024716625,0.00018256507,0.00015226741,0.0009995751,0.001263918,0.4199243,0.00028416008,0.00009967939,0.5481821,0.001541829],"about_ca_topic_score_codex":0.00023638552,"about_ca_topic_score_gemma":0.00003256608,"teacher_disagreement_score":0.70508415,"about_ca_system_score_codex":0.00066181266,"about_ca_system_score_gemma":0.00056662736,"threshold_uncertainty_score":0.99978495},"labels":[],"label_agreement":null},{"id":"W4312917662","doi":"10.21512/commit.v16i2.8144","title":"Observing Pre-Trained Convolutional Neural Network (CNN) Layers as Feature Extractor for Detecting Bias in Image Classification Data","year":2022,"lang":"en","type":"article","venue":"CommIT (Communication and Information Technology) Journal","topic":"Data Mining and Machine Learning Applications","field":"Computer Science","cited_by":2,"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":"Convolutional neural network; MNIST database; Computer science; Feature (linguistics); Artificial intelligence; Extractor; Kernel (algebra); Pattern recognition (psychology); Feature extraction; Workflow; Layer (electronics); Image (mathematics); Convolution (computer science); Deep learning; Artificial neural network; Database; Mathematics; Engineering","score_opus":0.060045005044452746,"score_gpt":0.31412283156967197,"score_spread":0.2540778265252192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312917662","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12177827,0.0018163089,0.7864371,0.08505287,0.0005093071,0.0013492681,0.00017089886,0.0010109694,0.0018750211],"genre_scores_gemma":[0.82515615,0.00021322565,0.17303367,0.0006519016,0.000034186633,0.00017968782,0.0006751476,0.000010201836,0.00004582031],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99843335,0.00025854592,0.0005779783,0.00021730881,0.00023368132,0.00027914974],"domain_scores_gemma":[0.9971126,0.00038837825,0.00070160156,0.0015374508,0.00018912615,0.00007089893],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0026100522,0.00014611993,0.00017124468,0.0004704895,0.0017510642,0.00045943775,0.003135144,0.00011757953,0.000018212811],"category_scores_gemma":[0.00093809445,0.00015580303,0.00003831548,0.0009280138,0.0001014817,0.0041379645,0.001721706,0.0013561309,0.0000069050748],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013826723,0.00021144688,0.0138578005,0.00007792402,0.00008085775,0.0000016739451,0.0025979306,0.008316264,0.0011218434,0.29072407,0.03560482,0.6472671],"study_design_scores_gemma":[0.0010218435,0.00010950768,0.031290997,0.00004196084,0.000012055897,0.0002604417,0.0016698657,0.75954443,0.000020972202,0.0074512367,0.1983497,0.0002269729],"about_ca_topic_score_codex":0.000018780818,"about_ca_topic_score_gemma":0.000012935689,"teacher_disagreement_score":0.7512282,"about_ca_system_score_codex":0.00013606097,"about_ca_system_score_gemma":0.00014318181,"threshold_uncertainty_score":0.9995485},"labels":[],"label_agreement":null},{"id":"W4313184267","doi":"10.55719/mv.v4i2.466","title":"PENGELOMPOKAN KEBUTUHAN JUMLAH AIR AKIBAT KEKERINGAN DI KABUPATEN TUBAN PADA TAHUN 2020 DENGAN ALGORITMA K-MEANS","year":2022,"lang":"id","type":"article","venue":"Mathvision Jurnal Matematika","topic":"Data Mining and Machine Learning 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":"Encana (Canada)","funders":"","keywords":"Physics; Humanities; Art","score_opus":0.012340352216344698,"score_gpt":0.2538633530516606,"score_spread":0.2415230008353159,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313184267","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":[0.7293015,0.003713298,0.1928351,0.027722772,0.012198783,0.0049815946,0.0021754575,0.004479451,0.022592045],"genre_scores_gemma":[0.9745667,0.00019040062,0.014968588,0.0007616765,0.00055819517,0.0004101549,0.00046287285,0.00021661208,0.007864819],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99117607,0.0013449534,0.0018497887,0.0019358926,0.0022322342,0.0014610739],"domain_scores_gemma":[0.9942654,0.00050103315,0.0012941816,0.0028253887,0.00028061547,0.0008333768],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0027575989,0.0010160193,0.0011669742,0.00053021923,0.0036638305,0.001281017,0.004750969,0.00022647751,0.0012035168],"category_scores_gemma":[0.00024929296,0.0010405277,0.00047648352,0.0019195427,0.0001820494,0.0009758289,0.0045075114,0.0025478906,0.0020136933],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004977829,0.007982976,0.012984782,0.00604709,0.0016299625,0.0037819305,0.07913312,0.027363217,0.019974446,0.07158185,0.31503436,0.45398846],"study_design_scores_gemma":[0.0034092492,0.002127823,0.07404508,0.0015247773,0.00045556322,0.0030191005,0.0046658614,0.45523685,0.0015405888,0.0025330894,0.4476017,0.00384032],"about_ca_topic_score_codex":0.00042418344,"about_ca_topic_score_gemma":0.000022011478,"teacher_disagreement_score":0.45014817,"about_ca_system_score_codex":0.00046274622,"about_ca_system_score_gemma":0.00043362592,"threshold_uncertainty_score":0.99975574},"labels":[],"label_agreement":null},{"id":"W4313402405","doi":"10.55227/ijhet.v1i3.56","title":"Application of the K-Means Method for Clustering Land and Building Tax Payments Based on Tax Types (Case Study: BPKPAD Binjai City)","year":2022,"lang":"en","type":"article","venue":"International Journal of Health Engineering and Technology","topic":"Data Mining and Machine Learning 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":"Payment; Revenue; Cluster analysis; Government (linguistics); Agency (philosophy); Business; Computer science; Artificial intelligence; Finance; Linguistics","score_opus":0.013547411418460328,"score_gpt":0.3235766641325516,"score_spread":0.31002925271409126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313402405","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":[0.102554455,0.000085281754,0.8899737,0.0070010833,0.00018916927,0.00015036268,0.00001723604,0.00002648012,0.0000022187546],"genre_scores_gemma":[0.9075376,0.00000564843,0.092293344,0.0000927713,0.000019697403,0.000039769235,0.0000010390972,0.000005332074,0.0000047978456],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99933726,0.000040738934,0.00025533192,0.00012830991,0.00015218675,0.000086172484],"domain_scores_gemma":[0.9993075,0.0001587697,0.0002801245,0.00015287308,0.00007638013,0.000024358164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007374111,0.00006019387,0.00012279829,0.00035238222,0.00013731922,0.000021041316,0.00040662594,0.000020272537,4.2002327e-7],"category_scores_gemma":[0.00010378335,0.000049559934,0.00001994789,0.0002160105,0.0000129795235,0.000045162356,0.00020341905,0.00022026987,3.3070666e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033800112,0.00031339243,0.02163229,0.000070163675,0.00014655273,0.000031412084,0.00062495924,0.24361905,0.001107113,0.013837435,0.00011559866,0.71846825],"study_design_scores_gemma":[0.00063651096,0.0004345395,0.0011599391,0.00003247802,0.000008362071,0.00073167484,0.00011102987,0.9880085,0.00010623857,0.00047921092,0.008234501,0.000056998073],"about_ca_topic_score_codex":0.00011170442,"about_ca_topic_score_gemma":0.000006662903,"teacher_disagreement_score":0.80498314,"about_ca_system_score_codex":0.0000464225,"about_ca_system_score_gemma":0.000044365195,"threshold_uncertainty_score":0.20209955},"labels":[],"label_agreement":null},{"id":"W4313827595","doi":"10.20956/j.v19i2.22266","title":"Weibull Regression Model on Hospitalization Time Data of COVID-19 Patients at Abdul Wahab Sjahranie Hospital Samarinda","year":2023,"lang":"en","type":"article","venue":"Jurnal Matematika Statistika dan Komputasi","topic":"Data Mining and Machine Learning 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":"Cegep de Sept Iles","funders":"","keywords":"Weibull distribution; Proportional hazards model; Statistics; Estimator; Logistic regression; Regression; Regression analysis; Survival analysis; Kaplan–Meier estimator; Hazard ratio; Medicine; Demography; Mathematics; Confidence interval","score_opus":0.029786001844867526,"score_gpt":0.3155936730658143,"score_spread":0.2858076712209468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313827595","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":[0.1946787,0.000038318474,0.7954224,0.0024953843,0.0004805975,0.00093912176,0.003913041,0.0009803056,0.0010521656],"genre_scores_gemma":[0.8147945,0.00012231067,0.16251132,0.00084428414,0.0001308847,0.000116441275,0.019142965,0.0001541542,0.0021831687],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964071,0.00021605633,0.0008543998,0.0010291361,0.0010151205,0.00047818467],"domain_scores_gemma":[0.9960077,0.00048489252,0.0008597064,0.0020755695,0.00020026547,0.00037186148],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008575924,0.00037569928,0.0004912,0.00037378396,0.0004970409,0.00023522216,0.0024210482,0.00011899531,0.00003333862],"category_scores_gemma":[0.0009024823,0.00032738686,0.00007417289,0.0009229775,0.00010421377,0.0007343773,0.0020056495,0.0002623104,0.00063481496],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012332069,0.0012647168,0.012124242,0.001341747,0.00019505728,0.00008626057,0.0037690755,0.08234508,0.00030528056,0.058669914,0.7894993,0.050276045],"study_design_scores_gemma":[0.0010057121,0.0004179958,0.015388583,0.00026466677,0.000035982666,0.000010973111,0.000031853855,0.9725685,0.00008443306,0.005542163,0.0041813846,0.00046774888],"about_ca_topic_score_codex":0.000069411464,"about_ca_topic_score_gemma":0.0000045906827,"teacher_disagreement_score":0.89022344,"about_ca_system_score_codex":0.00022439599,"about_ca_system_score_gemma":0.00022515398,"threshold_uncertainty_score":0.9999178},"labels":[],"label_agreement":null},{"id":"W4317401399","doi":"10.18280/mmep.090633","title":"Implementation of Data Analytics for the Accuracy of Service Time Prediction Models","year":2022,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Data Mining and Machine Learning 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; C4.5 algorithm; Tracing; Service (business); Decision tree; Data mining; Data collection; Analytics; Confusion matrix; Software; Service provider; Data processing; Database; Machine learning; Naive Bayes classifier; Statistics","score_opus":0.08055274505914424,"score_gpt":0.29163134049696227,"score_spread":0.21107859543781804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317401399","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025157887,0.00007385775,0.996432,0.00053034397,0.00001648266,0.0002274466,0.00013084378,0.000055530505,0.000017689168],"genre_scores_gemma":[0.65869135,0.000018588597,0.3410054,0.000020547788,0.000013187509,0.00011971995,0.00009658884,0.000012179725,0.000022388396],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931693,0.00001102469,0.00025717675,0.00016912125,0.00014757577,0.00009819037],"domain_scores_gemma":[0.9988693,0.00044615826,0.00009934914,0.0005207149,0.000042249892,0.000022221568],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064347475,0.00006298771,0.00011279079,0.00004400396,0.000104834,0.000025148829,0.000582648,0.000013176834,0.0000038185276],"category_scores_gemma":[0.00002005132,0.000051449508,0.000018031433,0.00019169199,0.000008691377,0.00021108074,0.00036045682,0.000086074826,4.3118018e-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":[8.638999e-7,0.000019742829,0.0000014999816,0.00016861226,0.000020595528,1.3266818e-8,0.000763001,0.95293385,0.0001677098,0.04293981,0.000053153,0.002931143],"study_design_scores_gemma":[0.00011287722,0.000034139295,0.0000030773824,0.000020046247,0.000031284835,0.0000032044907,0.000060656213,0.9842566,0.000040413135,0.015029003,0.0003625886,0.000046066707],"about_ca_topic_score_codex":0.000048350405,"about_ca_topic_score_gemma":3.7730288e-7,"teacher_disagreement_score":0.6561756,"about_ca_system_score_codex":0.0000071176923,"about_ca_system_score_gemma":0.000019168912,"threshold_uncertainty_score":0.209805},"labels":[],"label_agreement":null},{"id":"W4319211093","doi":"10.56248/marostek.v1i1.19","title":"Jaringan Syaraf Tiruan Memprediksi Tingkat Penggunaan Sosial Media Dimasa Pandemi Menggunakan Metode Backpropagation","year":2022,"lang":"id","type":"article","venue":"Jurnal Teknik Komputer Agroteknologi Dan Sains","topic":"Data Mining and Machine Learning 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":"Humanities; Computer science; Art","score_opus":0.024016437154597333,"score_gpt":0.2535587334676701,"score_spread":0.22954229631307277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319211093","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":[0.5273631,0.0022199596,0.42195797,0.022110488,0.011076192,0.003380038,0.00085094204,0.004505598,0.006535688],"genre_scores_gemma":[0.9634049,0.0002149585,0.027745718,0.0016992505,0.0029195407,0.00045016667,0.0009968379,0.000202316,0.0023662911],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98879594,0.0021434461,0.0018832214,0.0028857961,0.0021725125,0.0021191144],"domain_scores_gemma":[0.9933307,0.0010615647,0.0015384214,0.0028681518,0.00034978037,0.00085135456],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0034973207,0.0012873122,0.0012949905,0.0009455707,0.0036652407,0.0013515047,0.006015305,0.0004933427,0.00020460361],"category_scores_gemma":[0.0006270211,0.0013171739,0.0006491024,0.0022318328,0.0005037613,0.0012703437,0.006656409,0.0045785676,0.0005169142],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041186556,0.0038186694,0.012572833,0.0004103726,0.0016715142,0.0010073984,0.039526623,0.0125738485,0.020332495,0.049368795,0.07374445,0.78456116],"study_design_scores_gemma":[0.0060243057,0.003748481,0.10036408,0.00042677653,0.0007972511,0.0021036144,0.0025911024,0.24320252,0.003971783,0.003921541,0.62773764,0.005110907],"about_ca_topic_score_codex":0.0004442701,"about_ca_topic_score_gemma":0.0001305642,"teacher_disagreement_score":0.77945024,"about_ca_system_score_codex":0.0010068082,"about_ca_system_score_gemma":0.00082286494,"threshold_uncertainty_score":0.99998784},"labels":[],"label_agreement":null},{"id":"W4319262744","doi":"10.36080/skanika.v6i1.2982","title":"PENERAPAN METODE CLUSTERING DENGAN ALGORITMA K-MEANS PADA PENGELOMPOKAN INDEKS PRESTASI AKADEMIK MAHASISWA","year":2023,"lang":"id","type":"article","venue":"SKANIKA Sistem Komputer dan Teknik Informatika","topic":"Data Mining and Machine Learning 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":"Innovation Cluster (Canada)","funders":"","keywords":"Mathematics; Selection (genetic algorithm); Artificial intelligence; Computer science","score_opus":0.023886758785360455,"score_gpt":0.26678034185287447,"score_spread":0.24289358306751402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319262744","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07123455,0.0013359835,0.8296853,0.0093062585,0.010062366,0.005286873,0.00096989784,0.012421414,0.059697416],"genre_scores_gemma":[0.79017955,0.0008593542,0.16446501,0.0036157824,0.002741651,0.0010135741,0.003736904,0.00057069684,0.03281746],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9911612,0.00046574677,0.0024965967,0.0017912101,0.0016726836,0.0024125343],"domain_scores_gemma":[0.9927149,0.00063955726,0.0013215567,0.0038997438,0.0004044736,0.0010197926],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0025653304,0.0014115687,0.0013140977,0.0011554122,0.0018743786,0.0030788046,0.005603668,0.0006790703,0.00004708399],"category_scores_gemma":[0.00017830351,0.0014889289,0.00060572487,0.0033385297,0.00030045747,0.0037634817,0.004531779,0.0021359494,0.0041923122],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006390349,0.00047224035,0.0015879245,0.0021729288,0.0011081796,0.00022865072,0.05600732,0.0137590915,0.0008452216,0.01015575,0.17507342,0.7385254],"study_design_scores_gemma":[0.0012881875,0.00032684076,0.007881485,0.0005505361,0.00015217542,0.00028466937,0.001598393,0.55450135,0.0007756934,0.0001126062,0.43089062,0.0016374281],"about_ca_topic_score_codex":0.00045169482,"about_ca_topic_score_gemma":0.00024594745,"teacher_disagreement_score":0.73688793,"about_ca_system_score_codex":0.00040066443,"about_ca_system_score_gemma":0.0006245742,"threshold_uncertainty_score":0.99986345},"labels":[],"label_agreement":null},{"id":"W4319994597","doi":"10.18280/ria.360604","title":"Study of Climate Change in the Mandalika International Circuit Area Using Neural Network Backpropagation","year":2022,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Data Mining and Machine Learning 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":"Backpropagation; Climate change; Artificial neural network; MATLAB; Computer science; Activation function; Environmental science; Artificial intelligence; Ecology","score_opus":0.11063249195125102,"score_gpt":0.32725792649952945,"score_spread":0.21662543454827843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319994597","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":[0.88113344,0.00008053078,0.11453346,0.0010118482,0.0008005282,0.0007445151,0.000015617277,0.000068296715,0.0016117619],"genre_scores_gemma":[0.99871296,0.000013282046,0.0007976572,0.00016608092,0.00009429211,0.00016703054,0.000017779423,0.0000065347663,0.000024362827],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866194,0.00022031658,0.00034085382,0.00030572733,0.00026379625,0.00020734759],"domain_scores_gemma":[0.99904746,0.00012970794,0.00018233474,0.00057104416,0.00004953586,0.000019927016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010476366,0.000085973596,0.00011023611,0.000106952124,0.00031929743,0.00007632335,0.0012689356,0.000014365934,0.000053514283],"category_scores_gemma":[0.00003888271,0.000077754055,0.00003533902,0.0008297048,0.00002316009,0.00020648491,0.00046154618,0.00024129768,0.000011227466],"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":[0.000009108264,0.0005978365,0.017392742,0.00001068505,0.00000914605,0.000017314627,0.024794912,0.8515606,0.00011323195,0.020127336,0.00009108242,0.085276045],"study_design_scores_gemma":[0.00004871185,0.0001481385,0.0029349283,0.000016371496,0.0000056941058,0.00003269116,0.0041230014,0.9910706,0.00003105103,0.0006272537,0.0008728358,0.00008869455],"about_ca_topic_score_codex":0.00020693209,"about_ca_topic_score_gemma":0.000035814126,"teacher_disagreement_score":0.13951007,"about_ca_system_score_codex":0.000039882474,"about_ca_system_score_gemma":0.000013186019,"threshold_uncertainty_score":0.31707183},"labels":[],"label_agreement":null},{"id":"W4322098178","doi":"10.29100/jipi.v7i4.3237","title":"DATA MINING K-MEDOIDS DAN K-MEANS UNTUK PENGELOMPOKAN POTENSI PRODUKSI KELAPA SAWIT DI INDONESIA","year":2022,"lang":"id","type":"article","venue":"JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika)","topic":"Data Mining and Machine Learning 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":"Encana (Canada)","funders":"","keywords":"Physics; Forestry; Horticulture; Biology; Mathematics; Geography","score_opus":0.029388178758155227,"score_gpt":0.27441745852925076,"score_spread":0.24502927977109554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322098178","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":[0.7667599,0.0044481508,0.06554084,0.026314566,0.010059531,0.006191482,0.013890051,0.0035320413,0.10326345],"genre_scores_gemma":[0.952764,0.0003181942,0.022928212,0.004269165,0.0016506799,0.0005498876,0.012344286,0.00031139355,0.0048642014],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.986373,0.0012661521,0.0034068553,0.0027045985,0.0034463678,0.0028030174],"domain_scores_gemma":[0.9863313,0.00062215,0.0024349606,0.008565458,0.0006203354,0.0014258102],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","open_science"],"category_scores_codex":[0.004337547,0.0016506193,0.0016970872,0.0014147118,0.005737295,0.0030414849,0.013797771,0.0004245797,0.00046394728],"category_scores_gemma":[0.0005588021,0.0018532972,0.0005157891,0.0034036576,0.00068243674,0.006417392,0.011991782,0.0047040195,0.00090793293],"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":[0.0010978912,0.0037849476,0.06718607,0.0025294195,0.002477527,0.0013382845,0.11095042,0.017706923,0.0015050517,0.027441846,0.4296298,0.3343518],"study_design_scores_gemma":[0.004074429,0.0011652741,0.08779285,0.0005660141,0.00042629315,0.0027561216,0.011382687,0.23099358,0.000061537,0.000092423135,0.65762204,0.0030667759],"about_ca_topic_score_codex":0.00058358273,"about_ca_topic_score_gemma":0.00016849385,"teacher_disagreement_score":0.33128506,"about_ca_system_score_codex":0.00072646624,"about_ca_system_score_gemma":0.0022671362,"threshold_uncertainty_score":0.99987},"labels":[],"label_agreement":null},{"id":"W4324317520","doi":"10.47747/jpsii.v4i2.1097","title":"Sentiment Analysis Tweet KTT G-20 di Media Sosial Twitter Menggunakan Metode Naïve Bayes","year":2023,"lang":"en","type":"article","venue":"Jurnal Pengembangan Sistem Informasi dan Informatika","topic":"Data Mining and Machine Learning 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":"Summit; Naive Bayes classifier; China; Value (mathematics); Class (philosophy); Political science; Geography; Psychology; Artificial intelligence; Law; Statistics; Computer science; Cartography; Mathematics","score_opus":0.019221288016385164,"score_gpt":0.2697926494353669,"score_spread":0.25057136141898173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4324317520","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":[0.50050366,0.0002009509,0.25714195,0.010908322,0.003358944,0.0023257302,0.00039523485,0.007971495,0.21719368],"genre_scores_gemma":[0.98202497,0.00005128317,0.01010902,0.0015479795,0.00046596705,0.00025044038,0.0019751508,0.000051709012,0.0035235013],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99566925,0.00011490348,0.0014708044,0.00046702047,0.0012971589,0.0009808423],"domain_scores_gemma":[0.9965433,0.00036411552,0.00077305787,0.0015821699,0.00023450048,0.0005028861],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00157365,0.00052254664,0.00069305144,0.0014492652,0.00077393034,0.001235276,0.0023473979,0.00018189728,0.000027453505],"category_scores_gemma":[0.00014286995,0.00046024757,0.0005187852,0.0032728387,0.000115231305,0.0036102445,0.0011588953,0.0007276523,0.0009209191],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016092183,0.0005572396,0.047032468,0.000939197,0.007975208,0.00017704914,0.19903982,0.03475732,0.00059521344,0.12127654,0.19909759,0.38839144],"study_design_scores_gemma":[0.0015562389,0.0002319704,0.053841848,0.00009312799,0.0006191492,0.00010269509,0.0036534052,0.26371366,0.0011205666,0.0001948489,0.6735161,0.001356382],"about_ca_topic_score_codex":0.000035901423,"about_ca_topic_score_gemma":0.000054253014,"teacher_disagreement_score":0.48152128,"about_ca_system_score_codex":0.00015522176,"about_ca_system_score_gemma":0.00018787089,"threshold_uncertainty_score":0.999857},"labels":[],"label_agreement":null},{"id":"W4360989199","doi":"10.18280/ria.370110","title":"Personality Classification Based on Textual Data using Indonesian Pre-Trained Language Model and Ensemble Majority Voting","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Data Mining and Machine Learning 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":"Indonesian; Voting; Computer science; Natural language processing; Artificial intelligence; Personality; Linguistics; Psychology; Social psychology; Political science","score_opus":0.11892163892071406,"score_gpt":0.35440679258156993,"score_spread":0.23548515366085587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360989199","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":[0.18010642,0.000015424674,0.8173984,0.0012439598,0.000043902557,0.00016148695,0.000057052417,0.00031047448,0.0006628521],"genre_scores_gemma":[0.96717024,0.0000046171426,0.032043926,0.0001268994,0.000052407708,0.0000147563505,0.0002251201,0.000013486379,0.00034855795],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99836016,0.00009763204,0.0002782288,0.0007602027,0.0002103812,0.00029342205],"domain_scores_gemma":[0.99808055,0.00028109667,0.0001234838,0.0013684363,0.00004791675,0.00009853615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001132513,0.00014513437,0.0001449507,0.00014898599,0.00037049726,0.00019241865,0.0010003654,0.00006692258,0.0000065106483],"category_scores_gemma":[0.00030455439,0.00015013851,0.00003070157,0.0007401486,0.00006962621,0.00031738813,0.00037700025,0.00023739536,0.00010277019],"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":[0.000025453155,0.00027342234,0.0022963958,0.00013755352,0.000019148147,0.000015503034,0.0066722026,0.7104944,0.033625763,0.05840352,0.0012221022,0.18681452],"study_design_scores_gemma":[0.0000385981,0.000027092254,0.0015861792,0.000046950012,0.000008331629,0.0000062935796,0.0005912391,0.9961415,0.0009939729,0.00023496382,0.00016190672,0.00016299049],"about_ca_topic_score_codex":0.00017695478,"about_ca_topic_score_gemma":0.00003406251,"teacher_disagreement_score":0.78706384,"about_ca_system_score_codex":0.000033654764,"about_ca_system_score_gemma":0.0000800876,"threshold_uncertainty_score":0.6122471},"labels":[],"label_agreement":null},{"id":"W4362497045","doi":"10.1109/iconat57137.2023.10080277","title":"Open Dots: Securely Connecting Like-Minded People Using Machine Learning","year":2023,"lang":"en","type":"article","venue":"","topic":"Data Mining and Machine Learning 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":"Favourite; Computer science; Active listening; Internet privacy; Social media; World Wide Web; Artificial intelligence; Sociology; Political science","score_opus":0.044831437712548966,"score_gpt":0.32675476551074184,"score_spread":0.28192332779819285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362497045","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":[0.20159732,0.000051445833,0.7778367,0.0033107346,0.00045939517,0.00043062164,0.000012287383,0.003001686,0.013299831],"genre_scores_gemma":[0.85377,0.000010805187,0.1406303,0.00043607788,0.00006806053,0.000034055385,0.00012168498,0.000036177753,0.0048928093],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984421,0.00012149218,0.0002405541,0.00058864855,0.00021350839,0.000393658],"domain_scores_gemma":[0.9987349,0.0002929598,0.00013782838,0.00065779086,0.000059031623,0.000117505086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094266504,0.00015899347,0.00020310575,0.00018251612,0.0007750295,0.0008794025,0.0020737825,0.000057696136,0.000075191296],"category_scores_gemma":[0.00028315326,0.0001509664,0.000046820096,0.0014944929,0.000015337857,0.00072128663,0.0025324328,0.0003866585,0.0005943923],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047904872,0.0004901863,0.07652122,0.00017086722,0.00036341304,0.00012581171,0.03722433,0.11177939,0.0271274,0.35984978,0.034394413,0.35190526],"study_design_scores_gemma":[0.00033857595,0.000045372308,0.0017119615,0.00002125709,0.0000084028015,0.000044910474,0.00028823968,0.9393917,0.0002547352,0.0006356874,0.057007477,0.00025171723],"about_ca_topic_score_codex":0.0030655367,"about_ca_topic_score_gemma":0.00034921736,"teacher_disagreement_score":0.8276123,"about_ca_system_score_codex":0.000032223787,"about_ca_system_score_gemma":0.00007758507,"threshold_uncertainty_score":0.8480099},"labels":[],"label_agreement":null},{"id":"W4366420847","doi":"10.36595/jire.v6i1.726","title":"ALGORITMA APRIORI UNTUK MENENTUKAN PAKET PENJUALAN BARANG DI UMKM BINAAN DISPERINDAG KABUPATEN GROBOGAN","year":2023,"lang":"id","type":"article","venue":"Jurnal Informatika dan Rekayasa Elektronik","topic":"Data Mining and Machine Learning 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":"WiLAN (Canada)","funders":"","keywords":"Humanities; Physics; Computer science; Art","score_opus":0.019202075184702988,"score_gpt":0.2778728063360395,"score_spread":0.25867073115133654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366420847","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":[0.8570046,0.0012304919,0.05242497,0.018128717,0.0067392094,0.0032408945,0.0013840677,0.006038641,0.053808425],"genre_scores_gemma":[0.97396183,0.0016263757,0.0050219325,0.0011745738,0.0013336997,0.00032029828,0.0027544997,0.00023980971,0.01356697],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9923571,0.00036496128,0.0020369887,0.0011868298,0.0016350579,0.0024190738],"domain_scores_gemma":[0.99432474,0.00044348283,0.0011450818,0.0027153112,0.00030193315,0.0010694242],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0020135571,0.0011081542,0.0010988011,0.0010250661,0.0018050747,0.0022667083,0.0040894845,0.0004373468,0.00013849189],"category_scores_gemma":[0.00029376906,0.0010746362,0.0005073277,0.0031140547,0.0003631568,0.0033739954,0.0021699334,0.0020995862,0.006508608],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021745024,0.0009239095,0.0364015,0.001293973,0.0012625528,0.0005555728,0.05161433,0.0045224433,0.001649858,0.06560063,0.14620803,0.6897498],"study_design_scores_gemma":[0.0025958088,0.0009845498,0.12775175,0.0005548757,0.0002177588,0.00045399854,0.0031441273,0.21816914,0.0005236128,0.00034814663,0.6430357,0.0022205121],"about_ca_topic_score_codex":0.00056361407,"about_ca_topic_score_gemma":0.00007685016,"teacher_disagreement_score":0.68752927,"about_ca_system_score_codex":0.00043717722,"about_ca_system_score_gemma":0.0006829053,"threshold_uncertainty_score":0.99949443},"labels":[],"label_agreement":null},{"id":"W4377138337","doi":"10.30587/e-link.v18i1.5330","title":"PENERAPAN METODE K-MEANS CLUSTERING DALAM MENGELOMPOKKAN JUMLAH PESERTA BPJS KESEHATAN JKN/KIS DI KABUPATEN CIREBON","year":2023,"lang":"id","type":"article","venue":"E-Link Jurnal Teknik Elektro dan Informatika","topic":"Data Mining and Machine Learning 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":"WiLAN (Canada)","funders":"","keywords":"Humanities; Mathematics; Forestry; Geography; Art","score_opus":0.023598668400786192,"score_gpt":0.27758442665108846,"score_spread":0.2539857582503023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377138337","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":[0.44293657,0.0030370445,0.29223108,0.037872765,0.01176245,0.0054930313,0.001570886,0.012590913,0.19250526],"genre_scores_gemma":[0.9179018,0.0033069972,0.033366136,0.0013848868,0.0028557584,0.00061128853,0.003651426,0.0004725709,0.03644913],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9916966,0.00042464482,0.0023807155,0.0013482803,0.0017962303,0.0023535462],"domain_scores_gemma":[0.99348384,0.0005123729,0.0013729862,0.0031548005,0.0004168528,0.0010591547],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0027050974,0.0012160637,0.0012097743,0.0012958663,0.0022007239,0.0026024107,0.005138805,0.0004771353,0.00013510593],"category_scores_gemma":[0.00043241275,0.0012189755,0.00055571477,0.0029230292,0.00030170692,0.0046471693,0.0027804484,0.0024659906,0.005466176],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000222332,0.00053485204,0.009293488,0.0012733038,0.0012608,0.00022202241,0.051194783,0.012089914,0.0056058117,0.015995635,0.05500925,0.8472978],"study_design_scores_gemma":[0.0019240289,0.0006186078,0.025025029,0.0006465358,0.00019974083,0.00029127157,0.0016459209,0.6299589,0.0012485456,0.00022960412,0.33637008,0.0018417443],"about_ca_topic_score_codex":0.00041162496,"about_ca_topic_score_gemma":0.00021355349,"teacher_disagreement_score":0.84545606,"about_ca_system_score_codex":0.00038164222,"about_ca_system_score_gemma":0.0006342878,"threshold_uncertainty_score":0.9998354},"labels":[],"label_agreement":null},{"id":"W4380449813","doi":"10.5267/j.ijdns.2023.5.011","title":"Machine learning approach to uncover customer plastic bag usage patterns in a grocery store","year":2023,"lang":"en","type":"article","venue":"International Journal of Data and Network Science","topic":"Data Mining and Machine Learning 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":"Plastic bag; Grocery store; Grocery shopping; Business; Plastic waste; Plastic packaging; Computer science; Waste management; Marketing; Engineering","score_opus":0.03246723159389275,"score_gpt":0.3137140246888943,"score_spread":0.28124679309500156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380449813","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":[0.23497957,0.00017714067,0.76001877,0.001935167,0.001588717,0.00011673045,0.00010371736,0.00008937575,0.0009908258],"genre_scores_gemma":[0.9772083,0.00013831082,0.021992898,0.00024459782,0.0002591568,0.0000029046143,0.000051590898,0.0000060579846,0.00009615165],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99826515,0.000052379713,0.00029711664,0.00039234376,0.00072719215,0.00026579676],"domain_scores_gemma":[0.9989036,0.0002716049,0.0001823365,0.000355627,0.00013557976,0.00015130619],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021972153,0.00009525055,0.00013490624,0.0005097706,0.0001474449,0.0003670575,0.0036157784,0.000022258411,0.000004155249],"category_scores_gemma":[0.0004455978,0.000080565354,0.00001860828,0.0013528456,0.00007549914,0.0015910371,0.0018040456,0.00033242322,0.000030227156],"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":[0.00007555984,0.0002541292,0.3046004,0.000022864513,0.00007961289,0.00017866398,0.002984363,0.40711084,0.00056759134,0.014786174,0.02246975,0.24687007],"study_design_scores_gemma":[0.000398747,0.0000751584,0.10077288,0.00012228022,0.0000063227703,0.00019257824,0.00007199429,0.85724366,0.000008473208,0.0002813417,0.040656663,0.00016991943],"about_ca_topic_score_codex":0.000057870388,"about_ca_topic_score_gemma":0.000017624567,"teacher_disagreement_score":0.74222875,"about_ca_system_score_codex":0.000046506368,"about_ca_system_score_gemma":0.00013856168,"threshold_uncertainty_score":0.6719076},"labels":[],"label_agreement":null},{"id":"W4381234164","doi":"10.36982/jiig.v13i1.2060","title":"Penerapan Data Mining untuk Memprediksi Jumlah Produk Terlaris Menggunakan Algoritma Naive Bayes Studi Kasus (Toko Prapti)","year":2022,"lang":"en","type":"article","venue":"Jurnal Ilmiah Informatika Global","topic":"Data Mining and Machine Learning 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":"Confusion matrix; Naive Bayes classifier; Computer science; Nave; Confusion; Quarter (Canadian coin); Database; Data mining; Artificial intelligence","score_opus":0.02775443352960149,"score_gpt":0.2931667686138043,"score_spread":0.2654123350842028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381234164","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":[0.32636884,0.0021007978,0.4731484,0.023402939,0.008889087,0.0047705476,0.00885342,0.00519153,0.14727442],"genre_scores_gemma":[0.81536263,0.000053254877,0.1783903,0.002354068,0.00058991974,0.00045434624,0.001879725,0.000044572826,0.0008712125],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959282,0.0002280141,0.0009333743,0.00082568993,0.0012896493,0.0007950701],"domain_scores_gemma":[0.99605495,0.00012518294,0.0006607012,0.002667373,0.00017479771,0.0003170085],"candidate_categories":["metaepi_narrow","sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.0015956757,0.00041308388,0.0004349413,0.00020198796,0.0016299229,0.00078329234,0.005786199,0.00008693196,0.00006532745],"category_scores_gemma":[0.00022592535,0.0004062621,0.00010950688,0.0013965062,0.000107603344,0.0031174559,0.006114161,0.0008256412,0.00010686743],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008505046,0.00055765535,0.013813798,0.00009604845,0.0005013511,0.000080302016,0.012679927,0.004731708,0.000054642493,0.030365476,0.29241112,0.6446229],"study_design_scores_gemma":[0.0017784502,0.00073870434,0.010522851,0.00005014307,0.000097951386,0.00087189564,0.0037422883,0.26108786,0.000045241988,0.0006289935,0.719427,0.0010086257],"about_ca_topic_score_codex":0.0004042972,"about_ca_topic_score_gemma":0.000029875258,"teacher_disagreement_score":0.6436143,"about_ca_system_score_codex":0.00032008777,"about_ca_system_score_gemma":0.00054378534,"threshold_uncertainty_score":0.99983895},"labels":[],"label_agreement":null},{"id":"W4381950811","doi":"10.29303/ipr.v6i1.196","title":"APPLICATION OF SUPPORT VECTOR MACHINE ON DROUGHT CODE CLASSIFICATION IN NORTH SUMATRA INDONESIA","year":2022,"lang":"en","type":"article","venue":"Indonesian Physical Review","topic":"Data Mining and Machine Learning 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":"Support vector machine; Code (set theory); Computer science; Meteorology; Data mining; Geography; Climatology; Artificial intelligence; Geology","score_opus":0.019095591909607874,"score_gpt":0.3020399888117014,"score_spread":0.28294439690209355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381950811","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":[0.63578814,0.006608187,0.30673054,0.0352431,0.00043975626,0.006737574,0.0008039161,0.0011258811,0.0065228706],"genre_scores_gemma":[0.99704045,0.00031898313,0.00073561125,0.0006881574,0.000036506288,0.0008187969,0.00032618755,0.000018192373,0.000017134967],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99804515,0.00025997052,0.00046558704,0.0005373796,0.00046854658,0.0002233861],"domain_scores_gemma":[0.99827194,0.0001583873,0.0003603292,0.0010863346,0.00004314564,0.00007987127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004320928,0.00017633438,0.0004082611,0.00013285983,0.00013580991,0.000021656198,0.0011535228,0.000019948082,0.000011569225],"category_scores_gemma":[0.00004067605,0.00017173916,0.00010726452,0.0015892341,0.000041651034,0.0001737092,0.00023508751,0.00043295338,0.00008162984],"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":[0.000031333184,0.0024704738,0.044269726,0.0011152813,0.000031556105,0.000011668717,0.000663695,0.00062675675,0.0014942142,0.39838904,0.0019679724,0.54892826],"study_design_scores_gemma":[0.0011189663,0.0007086499,0.78325623,0.00037721472,0.00007753006,0.000043334956,0.000028077207,0.11962623,0.00026688995,0.001989365,0.09169949,0.0008080406],"about_ca_topic_score_codex":0.000059808943,"about_ca_topic_score_gemma":0.000026787175,"teacher_disagreement_score":0.7389865,"about_ca_system_score_codex":0.00009064997,"about_ca_system_score_gemma":0.000097161894,"threshold_uncertainty_score":0.7003319},"labels":[],"label_agreement":null},{"id":"W4382072563","doi":"10.59934/jaiea.v1i1.46","title":"Classification Analysis of Student Ability in Learning Using Clustering Method at SMA Tunas Pelita","year":2021,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Absenteeism; SMA*; Attendance; Centroid; Cluster (spacecraft); Mathematics education; Jigsaw; Statistics; Mathematics; Class (philosophy); Cluster analysis; Psychology; Computer science; Artificial intelligence; Social psychology; Political science","score_opus":0.0654176616932491,"score_gpt":0.3663670895138872,"score_spread":0.3009494278206381,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382072563","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":[0.24385495,0.00019851455,0.7556004,0.00018444887,0.000042608215,0.000068757654,0.00000286088,0.00002122344,0.000026243395],"genre_scores_gemma":[0.8120211,0.00008323276,0.18780684,0.0000086503605,0.000038208556,0.000013923598,0.000007824144,0.000007864364,0.000012390008],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983334,0.00009523737,0.00084002386,0.0003098841,0.00024498405,0.00017649545],"domain_scores_gemma":[0.9984524,0.00035797575,0.00038254718,0.00043308793,0.0002836819,0.00009030027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011712706,0.00012527825,0.00034817035,0.000554954,0.00012108943,0.00009844968,0.0004139658,0.000065663975,0.0000083961395],"category_scores_gemma":[0.00016891117,0.00013308543,0.00012530561,0.0020266774,0.00003477896,0.00023144655,0.00020908774,0.0003168104,0.0000025863123],"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":[0.00000534582,0.00013579482,0.006728964,0.000031642747,0.00013585913,0.000002777459,0.0012964697,0.8375088,0.07180764,0.010215501,0.0000019213714,0.07212931],"study_design_scores_gemma":[0.000029789304,0.000030324361,0.027497953,0.000034670007,0.00014418788,0.000029665169,0.0006196796,0.9663681,0.004259679,0.00028851462,0.00057450467,0.00012296434],"about_ca_topic_score_codex":0.000047041158,"about_ca_topic_score_gemma":0.00004126827,"teacher_disagreement_score":0.56816614,"about_ca_system_score_codex":0.00012785026,"about_ca_system_score_gemma":0.000072410425,"threshold_uncertainty_score":0.5427066},"labels":[],"label_agreement":null},{"id":"W4384208855","doi":"10.20885/teknisia.vol28.iss1.art5","title":"KAJIAN PERUBAHAN IKLIM DI DKI JAKARTA BERDASARKAN DATA CURAH HUJAN","year":2023,"lang":"en","type":"article","venue":"Teknisia","topic":"Data Mining and Machine Learning Applications","field":"Computer Science","cited_by":2,"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":"Downscaling; Environmental science; Flooding (psychology); Climatology; Climate change; Monsoon; Wet season; Global warming; Climate model; Meteorology; Geography; Precipitation; Geology","score_opus":0.06478516333902466,"score_gpt":0.3331030571871688,"score_spread":0.26831789384814414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384208855","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":[0.32212433,0.00069706666,0.4584028,0.095235474,0.0031827383,0.0017483365,0.0014656619,0.019308059,0.09783553],"genre_scores_gemma":[0.97181463,0.000041398216,0.017327882,0.0006598889,0.0003044233,0.000052749623,0.0016072877,0.000047608253,0.008144148],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980113,0.00008428732,0.0002455582,0.00085300044,0.0003299397,0.00047594332],"domain_scores_gemma":[0.9958444,0.00016256476,0.00009531783,0.0036748855,0.00003885901,0.00018395948],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00067335716,0.00018807162,0.00018165351,0.00017867114,0.00039935656,0.00034487233,0.0040073227,0.000065875836,0.000038123064],"category_scores_gemma":[0.00017287207,0.00018149955,0.000044929064,0.0010750182,0.0000679641,0.00064966653,0.002034674,0.0002948953,0.0042043286],"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":[0.0000053877116,0.00015858341,0.0076220995,0.000036916605,0.000067112895,0.000060474486,0.002707522,0.0001450118,0.0013819685,0.082308985,0.4798327,0.42567325],"study_design_scores_gemma":[0.0002914969,0.00006533845,0.048469156,0.000030620322,0.000018756851,0.000032294236,0.00012284954,0.14058988,0.00009907796,0.0015453366,0.80834025,0.00039498],"about_ca_topic_score_codex":0.00031361525,"about_ca_topic_score_gemma":0.000065127715,"teacher_disagreement_score":0.6496903,"about_ca_system_score_codex":0.000019702986,"about_ca_system_score_gemma":0.00009247822,"threshold_uncertainty_score":0.996571},"labels":[],"label_agreement":null},{"id":"W4384347863","doi":"10.59697/jsik.v6i2.162","title":"PENERAPAN DATA MINING PENGELOMPOKAN JAMINAN HARI TUA (JHT) BERDASARKAN WILAYAH DALAM MASA PANDEMI (STUDI KASUS : BPJS KETENAGAKERJAAN CABANG LANGKAT)","year":2022,"lang":"en","type":"article","venue":"Jurnal Sistem Informasi Kaputama (JSIK)","topic":"Data Mining and Machine Learning 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":"Cluster analysis; Cluster (spacecraft); Service (business); Process (computing); Computer science; Business; Data mining; Computer security; Artificial intelligence; Marketing","score_opus":0.03627094670691457,"score_gpt":0.268303613621552,"score_spread":0.23203266691463742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384347863","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":[0.7349758,0.0023074835,0.047088508,0.017539557,0.0053153555,0.002960731,0.0010689814,0.0043374714,0.18440607],"genre_scores_gemma":[0.9759081,0.000056568308,0.012158173,0.0012180285,0.00048442525,0.00024184668,0.0018437145,0.00008471658,0.0080044335],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9947997,0.00028724156,0.0011679429,0.0012283976,0.0013481224,0.0011686245],"domain_scores_gemma":[0.99498606,0.0003620501,0.00081031804,0.0032025478,0.00015999576,0.00047902614],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0022001823,0.000600601,0.00066222483,0.00041196856,0.0024741336,0.00090069626,0.005173846,0.00014673069,0.00006732087],"category_scores_gemma":[0.00020468181,0.0005898107,0.000221817,0.0012929986,0.00013362881,0.0021290877,0.006077525,0.0013375841,0.00009340121],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019559484,0.0011669216,0.087070666,0.00040629826,0.0009836812,0.00071547064,0.028574858,0.009081992,0.0015218529,0.04462492,0.12078123,0.7048765],"study_design_scores_gemma":[0.0013377746,0.00036370233,0.03153975,0.00007501023,0.00009521704,0.0010038348,0.0021256474,0.089204825,0.00006705775,0.000043594002,0.8732039,0.00093971007],"about_ca_topic_score_codex":0.00020839935,"about_ca_topic_score_gemma":0.00013779367,"teacher_disagreement_score":0.75242263,"about_ca_system_score_codex":0.00033480406,"about_ca_system_score_gemma":0.0004884015,"threshold_uncertainty_score":0.9996553},"labels":[],"label_agreement":null},{"id":"W4384347896","doi":"10.59697/jsik.v6i2.166","title":"PENERAPAN DATA MINING PENGELOMPOKAN PESERTA BPJS KETENAGAKERJAAN BERDASARKAN PROGRAM YANG DIAMBIL MENGGUNAKAN METODE CLUSTERING","year":2022,"lang":"en","type":"article","venue":"Jurnal Sistem Informasi Kaputama (JSIK)","topic":"Data Mining and Machine Learning 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":"Social security; Cluster analysis; Competence (human resources); Computer science; Process (computing); Wage; Business; Data collection; Minimum wage; Artificial intelligence; Management; Economics; Statistics; Mathematics","score_opus":0.03912985820783694,"score_gpt":0.29960386367299424,"score_spread":0.2604740054651573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384347896","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":[0.51044923,0.0022392431,0.20317315,0.027193252,0.0073331585,0.007148707,0.00091824064,0.011012702,0.23053232],"genre_scores_gemma":[0.89319265,0.00003648895,0.09814523,0.0011575324,0.0004834654,0.00066881086,0.0016204269,0.00009754093,0.004597849],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9949775,0.00030991714,0.0011234717,0.0011703615,0.0012825154,0.0011362889],"domain_scores_gemma":[0.99513227,0.0002818762,0.0007140437,0.0032386128,0.00013602179,0.0004971813],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.002293076,0.0005438376,0.000573183,0.00043654244,0.0023727017,0.0012837995,0.00655715,0.000110170695,0.00007270826],"category_scores_gemma":[0.00016894107,0.000540132,0.00021393542,0.0013615858,0.00009873393,0.0029935918,0.007473832,0.0011533863,0.00005516718],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058557805,0.0005114307,0.0037412466,0.00014196416,0.00026968092,0.00008145612,0.0068704677,0.006886014,0.00049198803,0.0054163868,0.0091574425,0.9663734],"study_design_scores_gemma":[0.00081332936,0.00039218596,0.004355305,0.000052033807,0.00005564796,0.00044264758,0.0011420024,0.36242583,0.000068213514,0.00003558361,0.62954044,0.00067676837],"about_ca_topic_score_codex":0.00017178853,"about_ca_topic_score_gemma":0.000120876015,"teacher_disagreement_score":0.9656966,"about_ca_system_score_codex":0.0002506649,"about_ca_system_score_gemma":0.00034024683,"threshold_uncertainty_score":0.99975294},"labels":[],"label_agreement":null},{"id":"W4384347902","doi":"10.59697/jsik.v6i2.167","title":"PENERAPAN DATA MINING PENGELOMPOKAN DATA PENGGUNA AIR BERSIH BERDASARKAN KELUHANNYA MENGGUNAKAN METODE CLUSTERING PADA PDAM LANGKAT","year":2022,"lang":"id","type":"article","venue":"Jurnal Sistem Informasi Kaputama (JSIK)","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"Cluster (spacecraft); Cluster analysis; Humanities; Computer science; Art; Operating system; Artificial intelligence","score_opus":0.0625656695631132,"score_gpt":0.30097430176038975,"score_spread":0.23840863219727654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384347902","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":[0.23811334,0.014331862,0.21019098,0.06614495,0.031226262,0.011541001,0.028905855,0.008656735,0.39088902],"genre_scores_gemma":[0.89564276,0.00026772238,0.041821975,0.003714854,0.002167552,0.0002853215,0.02721008,0.00031957857,0.028570173],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98920095,0.00084686675,0.0023404786,0.0028569708,0.002637739,0.0021170059],"domain_scores_gemma":[0.9855598,0.00072230434,0.0018537564,0.0105877165,0.00026144314,0.0010149882],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":["open_science"],"category_scores_codex":[0.0054080994,0.0012368062,0.0013480566,0.00075362576,0.004670977,0.0019411583,0.020083,0.00028995282,0.000385332],"category_scores_gemma":[0.0004173512,0.0013591466,0.0003200295,0.0020774822,0.00027533618,0.0060784793,0.035725754,0.0028790045,0.0003324856],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005321294,0.0020218638,0.007533485,0.0014793987,0.0023782933,0.0007728213,0.039821427,0.029964564,0.0012883244,0.004794285,0.33580208,0.5736113],"study_design_scores_gemma":[0.0012711075,0.00037022034,0.0021927624,0.00015913179,0.000280997,0.0007821116,0.0034301102,0.33653814,0.000051902764,0.000011977104,0.65373564,0.0011758865],"about_ca_topic_score_codex":0.0007701244,"about_ca_topic_score_gemma":0.0005565685,"teacher_disagreement_score":0.6575294,"about_ca_system_score_codex":0.00062499236,"about_ca_system_score_gemma":0.0012203625,"threshold_uncertainty_score":0.9994214},"labels":[],"label_agreement":null},{"id":"W4384573777","doi":"10.59697/jsik.v6i2.197","title":"PENERAPAN METODE CLUSTERING UNTUK PENGELOMPOKAN DATA PESERTA DIDIK BARU (PPDB) DI SMP SWASTA GOTONG ROYONG KUALA","year":2022,"lang":"id","type":"article","venue":"Jurnal Sistem Informasi Kaputama (JSIK)","topic":"Data Mining and Machine Learning 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":"Humanities; Physics; Art","score_opus":0.03947436998063242,"score_gpt":0.28631222327093864,"score_spread":0.24683785329030622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384573777","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":[0.31234217,0.007520248,0.25588894,0.023923231,0.01912588,0.007429679,0.004650457,0.00492929,0.3641901],"genre_scores_gemma":[0.9661775,0.00020051803,0.006524096,0.0010785878,0.00084696396,0.0003311421,0.0027436146,0.00017947645,0.021918096],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99031776,0.0007428999,0.0023590396,0.002122367,0.0024083944,0.0020495325],"domain_scores_gemma":[0.9906069,0.0006203966,0.0016353254,0.005846815,0.0002934596,0.0009970914],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":["open_science"],"category_scores_codex":[0.0036899657,0.001160331,0.0012416521,0.00069757167,0.004527905,0.00289223,0.011477253,0.00027110399,0.00045994628],"category_scores_gemma":[0.00035051955,0.0012392828,0.00045945408,0.0021582155,0.00025511536,0.0042632315,0.017848091,0.0031743257,0.00041476145],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008037488,0.0030099177,0.022266373,0.0021227857,0.0024987406,0.0008436841,0.04128117,0.123789914,0.0032422554,0.030167682,0.05709421,0.71287954],"study_design_scores_gemma":[0.0012788787,0.00045195263,0.0077166734,0.00015669868,0.00018639595,0.00076995627,0.0018093777,0.4290429,0.000110575565,0.000022962717,0.55727977,0.0011738562],"about_ca_topic_score_codex":0.0007420865,"about_ca_topic_score_gemma":0.00045135556,"teacher_disagreement_score":0.7117057,"about_ca_system_score_codex":0.0006959846,"about_ca_system_score_gemma":0.0010769101,"threshold_uncertainty_score":0.99912536},"labels":[],"label_agreement":null},{"id":"W4384573781","doi":"10.59697/jsik.v6i2.191","title":"Pemamfaatan Metode Clustering Pada Nasabah Peminjaman Modal (Studi Kasus: PT. Faderal International Finance Binjai)","year":2022,"lang":"id","type":"article","venue":"Jurnal Sistem Informasi Kaputama (JSIK)","topic":"Data Mining and Machine Learning 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":"Humanities; Mathematics; Art","score_opus":0.015560884170836354,"score_gpt":0.26040499583465326,"score_spread":0.24484411166381692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384573781","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":[0.39528733,0.004027414,0.29787531,0.045539394,0.030711597,0.004468995,0.0025045217,0.003165039,0.2164204],"genre_scores_gemma":[0.95591474,0.00020282593,0.008243367,0.0020844943,0.0011290192,0.0004330455,0.00068306923,0.00010466142,0.031204777],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9927386,0.0003255016,0.0019159503,0.0013202771,0.0022572435,0.0014424326],"domain_scores_gemma":[0.9957668,0.00031959615,0.0014697177,0.0016585919,0.00035472013,0.00043056885],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0018212105,0.0008936682,0.0008664324,0.0006146496,0.0030124816,0.0016289295,0.004928558,0.0002217591,0.0003022752],"category_scores_gemma":[0.00021347195,0.00097245467,0.0005705915,0.0014449385,0.0002315897,0.002327067,0.005580017,0.002536744,0.00029679845],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009488816,0.0026503212,0.01558648,0.00090473815,0.0022461966,0.0009231671,0.03953291,0.18962926,0.0016932742,0.08138161,0.093394935,0.5711082],"study_design_scores_gemma":[0.00170965,0.0005349169,0.0061895233,0.00015778338,0.00008796662,0.00095957186,0.0014155896,0.27957463,0.000109939305,0.000098517485,0.7080994,0.0010624764],"about_ca_topic_score_codex":0.00022875593,"about_ca_topic_score_gemma":0.000079620586,"teacher_disagreement_score":0.6147045,"about_ca_system_score_codex":0.0010588269,"about_ca_system_score_gemma":0.0007127487,"threshold_uncertainty_score":0.99976444},"labels":[],"label_agreement":null},{"id":"W4384573789","doi":"10.59697/jsik.v6i2.168","title":"DATA MINING PENGELOMPOKAN PENGGUNA NARKOBA BERDASARKAN USIA MENGGUNAKAN METODE CLUSTERING (STUDI KASUS : BNN KOTA BINJAI)","year":2022,"lang":"id","type":"article","venue":"Jurnal Sistem Informasi Kaputama (JSIK)","topic":"Data Mining and Machine Learning 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":"Humanities; Cluster analysis; Computer science; Artificial intelligence; Philosophy","score_opus":0.05239758656391054,"score_gpt":0.29940200320461513,"score_spread":0.2470044166407046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384573789","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":[0.3592314,0.014692998,0.105690375,0.039899778,0.026445001,0.009595847,0.0076585864,0.0067254915,0.43006054],"genre_scores_gemma":[0.9382599,0.00035437153,0.032277778,0.0023101622,0.0017334191,0.0004999555,0.0036275873,0.00031201117,0.020624826],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98825544,0.00093407225,0.0029227827,0.002538375,0.0029111623,0.0024381503],"domain_scores_gemma":[0.9893853,0.0008441221,0.002241664,0.0060712476,0.00037073463,0.0010869304],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":["metaepi_narrow","open_science"],"category_scores_codex":[0.0054875547,0.001421303,0.0015159427,0.0009532048,0.0058261114,0.0025652333,0.011757062,0.0003200972,0.00036207118],"category_scores_gemma":[0.00051593536,0.0015597084,0.00051661616,0.0028601356,0.00032309408,0.003826723,0.02112364,0.0032813821,0.00036324866],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008122398,0.0025261673,0.012981255,0.0020774922,0.003320379,0.0011111926,0.05496452,0.030852757,0.0009969147,0.009135442,0.13488917,0.74633247],"study_design_scores_gemma":[0.0017998762,0.00067252526,0.0058838655,0.00022279524,0.00031527967,0.0012720181,0.004064923,0.23984446,0.00003025388,0.000023776427,0.7443748,0.0014954113],"about_ca_topic_score_codex":0.00031490377,"about_ca_topic_score_gemma":0.00026164332,"teacher_disagreement_score":0.74483705,"about_ca_system_score_codex":0.00096673117,"about_ca_system_score_gemma":0.0013215366,"threshold_uncertainty_score":0.99985373},"labels":[],"label_agreement":null},{"id":"W4384573862","doi":"10.59697/jsik.v6i2.179","title":"DATA MINING DALAM PENGELOMPOKKAN JUMLAH DATA PRODUKTIVITAS TANAMAN PANGAN MENGGUNAKAN METODE CLUSTRING K-MEANS ( STUDI KASUS : BADAN PUSAT STATISTIK KOTA BINJAI)","year":2022,"lang":"id","type":"article","venue":"Jurnal Sistem Informasi Kaputama (JSIK)","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"Physics; Horticulture; Humanities; Forestry; Geography; Biology","score_opus":0.08366420916862938,"score_gpt":0.31647698394751217,"score_spread":0.2328127747788828,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384573862","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":[0.23373136,0.014436657,0.35833153,0.06627549,0.038053542,0.020709911,0.09095852,0.009699022,0.16780397],"genre_scores_gemma":[0.8684278,0.00036397536,0.06875107,0.0012861615,0.0023464432,0.0005465542,0.037567444,0.000434416,0.020276112],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9858479,0.001296602,0.0030836626,0.003709043,0.0035200357,0.002542739],"domain_scores_gemma":[0.98252285,0.0012066605,0.0025612325,0.012209606,0.0003935463,0.001106135],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":["metaepi_narrow","open_science"],"category_scores_codex":[0.008641819,0.0014915937,0.0016070218,0.0008886784,0.0057524596,0.0029046386,0.019788684,0.0002707639,0.00014890174],"category_scores_gemma":[0.0011925865,0.0016002317,0.00026991736,0.0031337554,0.00041346246,0.0060163,0.03374936,0.003607232,0.00016910008],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041912973,0.0023787,0.016528336,0.0012502649,0.002919437,0.0007888607,0.0266303,0.008664949,0.00039958913,0.014142973,0.21893921,0.70693827],"study_design_scores_gemma":[0.0017167489,0.0008053316,0.0072295265,0.00023558618,0.0005077726,0.000678723,0.0058915582,0.2568888,0.000029855782,0.000025598818,0.7244555,0.0015350052],"about_ca_topic_score_codex":0.00051214074,"about_ca_topic_score_gemma":0.0008224136,"teacher_disagreement_score":0.7054032,"about_ca_system_score_codex":0.00095320656,"about_ca_system_score_gemma":0.0020052153,"threshold_uncertainty_score":0.99978334},"labels":[],"label_agreement":null},{"id":"W4384573865","doi":"10.59697/jsik.v6i2.170","title":"Clustering Peserta Kb Aktif Di Kota Binjai Menggunakan Metode K-Means (Study Kasus BKKBN Kota Binjai)","year":2022,"lang":"id","type":"article","venue":"Jurnal Sistem Informasi Kaputama (JSIK)","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"Humanities; Mathematics; Art","score_opus":0.019029427660449842,"score_gpt":0.2670985144926001,"score_spread":0.24806908683215023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384573865","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":[0.72930706,0.00201243,0.085533544,0.016557084,0.014256766,0.007988648,0.000897894,0.0038887614,0.13955781],"genre_scores_gemma":[0.96416444,0.00007740382,0.0032906763,0.0012606615,0.000838213,0.00078768336,0.00036137344,0.00019746523,0.029022062],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9887991,0.00096941495,0.002885616,0.001991057,0.0030054029,0.0023493862],"domain_scores_gemma":[0.9922192,0.00063614984,0.0018721846,0.0037437978,0.00042195816,0.0011066828],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0039600343,0.0014118761,0.0014813448,0.0011125803,0.005110311,0.0025898325,0.0067085717,0.00030061073,0.0003402541],"category_scores_gemma":[0.00035726788,0.0014658936,0.00077552226,0.003436912,0.0002468867,0.0023482186,0.007677456,0.003521249,0.0006691276],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015056778,0.013923761,0.085547715,0.0017981845,0.0047876737,0.0015550896,0.14533855,0.16695121,0.0018186821,0.019975409,0.042886846,0.5139112],"study_design_scores_gemma":[0.0036781535,0.002748276,0.028369773,0.00018584738,0.00042327485,0.00093435275,0.0077242814,0.30212575,0.00008449344,0.000046053152,0.6516462,0.0020335596],"about_ca_topic_score_codex":0.00078046834,"about_ca_topic_score_gemma":0.00030611551,"teacher_disagreement_score":0.60875934,"about_ca_system_score_codex":0.0010426429,"about_ca_system_score_gemma":0.0009798461,"threshold_uncertainty_score":0.99986315},"labels":[],"label_agreement":null},{"id":"W4384573869","doi":"10.59697/jsik.v6i2.198","title":"Penerapan Sistem Pakar Menentukan Covid-19 Dengan Metode KNN (K Nearest Neighbor) Berbasis Web (Studi Kasus : RSU Sylvani)","year":2022,"lang":"id","type":"article","venue":"Jurnal Sistem Informasi Kaputama (JSIK)","topic":"Data Mining and Machine Learning 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":"Physics; Humanities; Gynecology; Philosophy; Medicine","score_opus":0.027225169967204893,"score_gpt":0.28312449294971587,"score_spread":0.25589932298251095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384573869","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":[0.5125159,0.014931424,0.056834515,0.10475564,0.021861516,0.011255756,0.0037087363,0.009058705,0.2650778],"genre_scores_gemma":[0.95237136,0.00043326084,0.004275154,0.008261862,0.00089696265,0.00089904503,0.000772207,0.00021091258,0.03187926],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9887915,0.0012555857,0.002708447,0.0019671957,0.0030015525,0.002275711],"domain_scores_gemma":[0.99105895,0.0010875791,0.0021422477,0.0031428398,0.00043667492,0.0021317333],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0039113485,0.001390456,0.0015000866,0.0008815197,0.007180587,0.002444354,0.005626386,0.00037131942,0.00038457115],"category_scores_gemma":[0.0006943506,0.0014716259,0.0009789013,0.003315421,0.0003928261,0.0019391205,0.0048886715,0.0030763445,0.0005517374],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012000332,0.0053055612,0.04463466,0.003002198,0.004658767,0.0015881971,0.05332591,0.077466905,0.0032889931,0.23504516,0.23336707,0.33711654],"study_design_scores_gemma":[0.0026758872,0.001039853,0.0049698655,0.00010158044,0.00040096705,0.00100569,0.002665176,0.052311186,0.00014133593,0.00008540726,0.9330223,0.0015807298],"about_ca_topic_score_codex":0.00057022984,"about_ca_topic_score_gemma":0.0003487538,"teacher_disagreement_score":0.69965523,"about_ca_system_score_codex":0.002242749,"about_ca_system_score_gemma":0.0032903994,"threshold_uncertainty_score":0.9998846},"labels":[],"label_agreement":null},{"id":"W4384573875","doi":"10.59697/jsik.v6i2.189","title":"Data Mining Pengelompokan Pasien Rawat Inap Berdasarkan Kelas Bpjs Menggunakan Metode Clustering (Studi Kasus : Rumah Sakit Umum Daerah Dr. Rm. Djoelham Binjai)","year":2022,"lang":"id","type":"article","venue":"Jurnal Sistem Informasi Kaputama (JSIK)","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"Medicine","score_opus":0.05099651351982436,"score_gpt":0.3015151187729321,"score_spread":0.2505186052531077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384573875","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":[0.31631547,0.010752614,0.1420504,0.058997333,0.02927255,0.010857173,0.006937639,0.007362421,0.4174544],"genre_scores_gemma":[0.93934095,0.00036298129,0.02068241,0.0028333182,0.0019603295,0.0006524407,0.004417084,0.00036137505,0.029389143],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9868663,0.0010518492,0.0033284787,0.002777606,0.003111784,0.002863987],"domain_scores_gemma":[0.98857564,0.0009774812,0.00252776,0.0062655183,0.00041028988,0.0012433069],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":["metaepi_narrow","open_science"],"category_scores_codex":[0.0057902816,0.0016264266,0.001751249,0.0011179984,0.0061345226,0.0029336773,0.011615953,0.00040758122,0.0003547982],"category_scores_gemma":[0.00057477044,0.0017480901,0.0005862364,0.0030787038,0.0004008249,0.004354203,0.021397628,0.003757037,0.0004389329],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00088848313,0.0025312891,0.014759266,0.001679597,0.003320722,0.0009851279,0.055809785,0.030263774,0.0011225329,0.008233322,0.17257464,0.70783144],"study_design_scores_gemma":[0.002394529,0.00093562814,0.007109235,0.0003119334,0.00035251852,0.0011728071,0.004314919,0.18984604,0.00006745826,0.000030770778,0.7917127,0.0017514676],"about_ca_topic_score_codex":0.00040933056,"about_ca_topic_score_gemma":0.00034580185,"teacher_disagreement_score":0.70608,"about_ca_system_score_codex":0.0012244334,"about_ca_system_score_gemma":0.0013581465,"threshold_uncertainty_score":0.99964833},"labels":[],"label_agreement":null},{"id":"W4384573886","doi":"10.59697/jsik.v6i2.169","title":"PENERAPAN DATA MINING PENGELOMPOKAN DATA PASIEN BERDASRKAN JENIS PENYAKIT MENGGUNAKAN METODE CLUSTERING (STUDI KASUS KLINIK MITRA ND)","year":2022,"lang":"id","type":"article","venue":"Jurnal Sistem Informasi Kaputama (JSIK)","topic":"Data Mining and Machine Learning 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":"Humanities; Art","score_opus":0.08241776119678437,"score_gpt":0.31599800420573826,"score_spread":0.2335802430089539,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384573886","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":[0.271477,0.02024098,0.18208717,0.07154097,0.03576298,0.013856081,0.023243628,0.00877885,0.37301233],"genre_scores_gemma":[0.90649587,0.0003431631,0.050505217,0.002401644,0.0026791804,0.000382947,0.016524818,0.00032385936,0.020343313],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9874248,0.0009555542,0.0030187748,0.0032893096,0.0029466767,0.0023648846],"domain_scores_gemma":[0.98383,0.00095377304,0.0022891818,0.011532624,0.00031273707,0.0010817264],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":["metaepi_narrow","open_science"],"category_scores_codex":[0.0067925956,0.001370514,0.0015294738,0.0007753322,0.005551835,0.0029512856,0.022315964,0.00031074998,0.0003629599],"category_scores_gemma":[0.00062994944,0.0014984236,0.00039105717,0.0023227946,0.00034398222,0.0058103404,0.031714775,0.0031827101,0.00031191268],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00052270584,0.002106813,0.010199377,0.001156526,0.0028703073,0.0006823024,0.03752123,0.017780745,0.00065167743,0.0039274762,0.17310931,0.74947155],"study_design_scores_gemma":[0.0017205697,0.00055186526,0.0037838866,0.00017354524,0.00038847685,0.00091244694,0.0029617597,0.29988623,0.000036070367,0.00001620812,0.688178,0.0013909424],"about_ca_topic_score_codex":0.00068747293,"about_ca_topic_score_gemma":0.00047394857,"teacher_disagreement_score":0.7480806,"about_ca_system_score_codex":0.00059381867,"about_ca_system_score_gemma":0.0014185666,"threshold_uncertainty_score":0.9999046},"labels":[],"label_agreement":null},{"id":"W4385150416","doi":"10.58860/jti.v2i1.11","title":"Penerapan Algoritma K-Means Untuk Menentukan Jumlah Produksi Kayu Bulat Berdasarkan Jenis Kayu Di Provinsi Jawa Barat","year":2023,"lang":"en","type":"article","venue":"Jurnal Teknik Indonesia","topic":"Data Mining and Machine Learning 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":"Java; Quarter (Canadian coin); Production (economics); Forestry; Service (business); Geography; Mathematics; Computer science; Business; Operating system; Archaeology; Economics","score_opus":0.015280256741213825,"score_gpt":0.26333768993788437,"score_spread":0.24805743319667053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385150416","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":[0.9247974,0.00028055467,0.05072308,0.012108695,0.0014692832,0.0012439825,0.000095773285,0.0032743837,0.006006842],"genre_scores_gemma":[0.9875084,0.00008656056,0.007241438,0.00047741612,0.0007041108,0.00028970154,0.0002536822,0.00009549255,0.0033431791],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9959784,0.00022792643,0.0006697879,0.0012543892,0.0008790025,0.0009904756],"domain_scores_gemma":[0.9970067,0.00018488776,0.00034059453,0.001839028,0.00019915198,0.00042959972],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00086807855,0.0004974649,0.00049328804,0.0005383405,0.0009062046,0.0006887036,0.0022819815,0.00018662786,0.000014579144],"category_scores_gemma":[0.000108219654,0.00046335903,0.00020661742,0.0021605827,0.0001307813,0.00091255695,0.0008152361,0.00076386146,0.0010274719],"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":[0.00011408767,0.0014555578,0.22916785,0.000333189,0.00048741009,0.0007692579,0.009380563,0.0046597742,0.0420406,0.06699946,0.13639744,0.5081948],"study_design_scores_gemma":[0.0026889283,0.00075370213,0.5109522,0.00022138447,0.00014846903,0.00069896324,0.000299867,0.16103831,0.0075674807,0.0013995458,0.31197047,0.0022606943],"about_ca_topic_score_codex":0.0002793056,"about_ca_topic_score_gemma":0.000067403744,"teacher_disagreement_score":0.5059341,"about_ca_system_score_codex":0.00014473547,"about_ca_system_score_gemma":0.00032537655,"threshold_uncertainty_score":0.9997818},"labels":[],"label_agreement":null},{"id":"W4386418425","doi":"10.60076/indotech.v1i2.50","title":"Application of the K-Means Algorithm in Traffic Violations In Langkat District (Case Study: Langkat Police)","year":2023,"lang":"id","type":"article","venue":"Indonesian Journal of Education And Computer Science","topic":"Data Mining and Machine Learning 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":"Physics; Humanities; Art","score_opus":0.013650060545352028,"score_gpt":0.3015916856091888,"score_spread":0.2879416250638368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386418425","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":[0.88937366,0.00008673441,0.10802273,0.0014560542,0.00066842383,0.00033890552,0.0000061914297,0.000017193728,0.000030111836],"genre_scores_gemma":[0.9937771,0.000020909016,0.0059030736,0.0000792057,0.00014358024,0.000017535362,0.0000028322281,0.0000073768138,0.000048367165],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99794906,0.00022877661,0.0007146774,0.00037839054,0.00046021974,0.00026886546],"domain_scores_gemma":[0.9982612,0.00018642457,0.00059161393,0.0005667782,0.00025031413,0.0001436465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016854336,0.00015092597,0.00024718264,0.0010452104,0.00037818204,0.00020275605,0.0012712049,0.000048921735,0.000001211548],"category_scores_gemma":[0.000049675647,0.00012319212,0.0000588338,0.0055384315,0.00024342326,0.00058942917,0.00037762642,0.00038051116,0.0000076034225],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003911545,0.0011617461,0.13386731,0.000025595875,0.000009954765,0.000030476376,0.045158427,0.0040591485,0.000051934676,0.0006255698,0.00022012585,0.8147858],"study_design_scores_gemma":[0.00046830607,0.00014871267,0.5968829,0.00013099602,0.000014490756,0.0008664602,0.005258015,0.39572614,0.000011034073,0.00006614002,0.00029863746,0.00012819059],"about_ca_topic_score_codex":0.0010825252,"about_ca_topic_score_gemma":0.00041009605,"teacher_disagreement_score":0.8146576,"about_ca_system_score_codex":0.00010361943,"about_ca_system_score_gemma":0.0009976026,"threshold_uncertainty_score":0.5023629},"labels":[],"label_agreement":null},{"id":"W4386418457","doi":"10.60076/indotech.v1i2.43","title":"Data Mining Analysis For Medical Record Data Clasterization Using K-Means Algorithm In Sylvani Binjai Hospital","year":2023,"lang":"id","type":"article","venue":"Indonesian Journal of Education And Computer Science","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"Medicine; Gynecology","score_opus":0.056628583958170414,"score_gpt":0.36053715378425627,"score_spread":0.30390856982608583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386418457","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.119901456,0.00014926639,0.87325466,0.0035887784,0.0027897647,0.00018095027,0.000099294884,0.00002689579,0.000008946115],"genre_scores_gemma":[0.32199413,0.0002063974,0.6757658,0.0003924689,0.0010746391,0.000006629415,0.00047166154,0.000021780248,0.00006645506],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996323,0.00018640247,0.0010336107,0.0010718277,0.0009239374,0.0004612077],"domain_scores_gemma":[0.9960281,0.00037320642,0.0009093774,0.0017734909,0.00048580766,0.0004299823],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0054363646,0.00021961526,0.00043412426,0.0020219812,0.00046502394,0.0011080004,0.005872738,0.00010201585,0.000007366253],"category_scores_gemma":[0.0006065959,0.00021804008,0.00006163876,0.006943952,0.0003415881,0.0031037263,0.0022372263,0.00034207944,0.000006066821],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006534122,0.00033584243,0.026369859,0.00003313042,0.00008703892,0.0000124048565,0.0027532969,0.0005930249,0.000019935096,0.00017891372,0.0017587407,0.9678513],"study_design_scores_gemma":[0.00038618027,0.00018736487,0.062996134,0.00026768967,0.00012796644,0.00011580382,0.00065630925,0.9324276,0.0000030947933,0.000053937503,0.0025553105,0.00022261615],"about_ca_topic_score_codex":0.0000704378,"about_ca_topic_score_gemma":0.000033930373,"teacher_disagreement_score":0.96762866,"about_ca_system_score_codex":0.00008224385,"about_ca_system_score_gemma":0.0035062123,"threshold_uncertainty_score":0.99992895},"labels":[],"label_agreement":null},{"id":"W4386549972","doi":"10.5267/j.msl.2023.8.001","title":"Profession recommendation based on multiple intelligence for high school students","year":2023,"lang":"en","type":"article","venue":"Management Science Letters","topic":"Data Mining and Machine Learning 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":"Ranking (information retrieval); Computer science; Value (mathematics); Intrapersonal communication; Psychology; Preference; Mathematics education; Artificial intelligence; Interpersonal communication; Social psychology; Mathematics; Statistics; Machine learning","score_opus":0.02489048906363034,"score_gpt":0.3343035252737238,"score_spread":0.3094130362100935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386549972","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038561452,2.3007073e-7,0.9213736,0.037949484,0.00055783073,0.0006870266,0.000005270168,0.00049122376,0.00037384732],"genre_scores_gemma":[0.91944027,0.0000022874801,0.071715385,0.0077870404,0.000036005466,0.00046335685,0.000074080555,0.000009393117,0.00047216724],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817437,0.000040287436,0.00018377916,0.00067703903,0.00054592453,0.00037860166],"domain_scores_gemma":[0.9988927,0.00021238854,0.00009357028,0.0006881846,0.000022348193,0.000090780144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016187446,0.00011441513,0.00007749812,0.0005436644,0.00064146303,0.00042319988,0.0020920765,0.00001656108,0.000009211056],"category_scores_gemma":[0.00022211972,0.00010493899,0.000027748372,0.0018404627,0.00007991771,0.00052624074,0.00055030163,0.0001079288,0.00040736122],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040810573,0.0004146029,0.045400318,0.000131562,0.000026739086,0.0000104966,0.0005759787,0.058656253,0.005234526,0.053138528,0.12363165,0.7127385],"study_design_scores_gemma":[0.00047425937,0.00010991718,0.12497488,0.000078972414,0.000008002824,2.2770915e-7,0.00014303856,0.8565029,0.0013089692,0.0008455062,0.015273154,0.00028017614],"about_ca_topic_score_codex":0.000015473594,"about_ca_topic_score_gemma":0.0000010663816,"teacher_disagreement_score":0.8808788,"about_ca_system_score_codex":0.00009529506,"about_ca_system_score_gemma":0.000012320365,"threshold_uncertainty_score":0.523594},"labels":[],"label_agreement":null},{"id":"W4386686627","doi":"10.30591/jpit.v8i2.5216","title":"Pemanfaatan Algoritma K-Means untuk Membuktikan Implementasi Undang-Undang Pelanggaran Hukum Korupsi di Pengadilan Negeri Banjarmasin","year":2023,"lang":"en","type":"article","venue":"Jurnal Informatika Jurnal Pengembangan IT","topic":"Data Mining and Machine Learning 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":"Innovation Cluster (Canada)","funders":"","keywords":"Law enforcement; Language change; Enforcement; Silhouette; State (computer science); Law; Value (mathematics); Research method; Political science; Business; Mathematics; Computer science; Statistics; Algorithm; Artificial intelligence; Business administration","score_opus":0.025239064978015473,"score_gpt":0.29870975837232905,"score_spread":0.27347069339431357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386686627","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":[0.33028787,0.00081299694,0.31007156,0.06787845,0.0072486764,0.0041831736,0.0016990664,0.010258031,0.26756018],"genre_scores_gemma":[0.9502941,0.00054873526,0.023198606,0.005702295,0.0021087562,0.00029235508,0.002794609,0.00027520073,0.014785377],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9946939,0.0002566245,0.0014801647,0.0007349132,0.0013144895,0.0015199357],"domain_scores_gemma":[0.99619836,0.00039212685,0.00076586154,0.001632932,0.00025373997,0.00075697154],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002022956,0.00069260626,0.0006860392,0.0009765255,0.0016011359,0.0016897268,0.0033501023,0.0001984263,0.00024810698],"category_scores_gemma":[0.0002007934,0.00065814506,0.00038344887,0.0021915822,0.00017151242,0.003323936,0.0012117864,0.0015211633,0.0036069842],"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":[0.00009988113,0.000403489,0.005316101,0.00045606616,0.00064443843,0.0005408108,0.026661063,0.0033325874,0.0013424131,0.068216786,0.67692405,0.2160623],"study_design_scores_gemma":[0.0016902629,0.00047380244,0.022461155,0.0001890493,0.000099157776,0.00091922417,0.0035671769,0.08867979,0.0004981834,0.0006532144,0.87953925,0.0012297519],"about_ca_topic_score_codex":0.00026416843,"about_ca_topic_score_gemma":0.00020132419,"teacher_disagreement_score":0.6200062,"about_ca_system_score_codex":0.00026965304,"about_ca_system_score_gemma":0.00040013518,"threshold_uncertainty_score":0.99969864},"labels":[],"label_agreement":null},{"id":"W4387139003","doi":"10.29303/jppipa.v9i9.4771","title":"Trends and Issues of Ethnoscience Research from 2008 to 2023: A Bibliometric Analysis","year":2023,"lang":"en","type":"article","venue":"Jurnal Penelitian Pendidikan IPA","topic":"Data Mining and Machine Learning Applications","field":"Computer Science","cited_by":4,"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; Scopus; Publishing; Distribution (mathematics); Russian federation; Political science; Geography; Regional science; Computer science; Mathematics; MEDLINE; Law","score_opus":0.08062731783390474,"score_gpt":0.41605343295987385,"score_spread":0.3354261151259691,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387139003","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":[0.93979895,0.0012151132,0.032498255,0.018745672,0.000245126,0.00019547332,0.00049013394,0.0003631529,0.006448125],"genre_scores_gemma":[0.9813684,0.0002763073,0.013453812,0.00011481032,0.000100741585,0.000032070762,0.00007543881,0.000011526765,0.0045668436],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99706745,0.00022390613,0.00037291195,0.0007650633,0.0010264177,0.00054425263],"domain_scores_gemma":[0.99766725,0.00060770154,0.00011764993,0.0010134907,0.00022041299,0.0003734823],"candidate_categories":["bibliometrics"],"consensus_categories":["bibliometrics"],"category_scores_codex":[0.0022280938,0.000144638,0.00031781069,0.08363015,0.00037745223,0.0004313013,0.0016903384,0.00006354843,0.00013786982],"category_scores_gemma":[0.0005437424,0.00013731117,0.00010339679,0.29235092,0.00015014978,0.00045347944,0.00096487213,0.00035126775,0.00037747112],"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":[0.000026565493,0.00020249536,0.07646281,0.000031839103,0.0003559796,0.00009878806,0.0054509346,0.0009316184,0.006298211,0.009988447,0.19678256,0.70336974],"study_design_scores_gemma":[0.00016179422,0.000159513,0.9489035,0.000026147674,0.0000444064,0.00000624864,0.00019179082,0.01763643,0.00049172086,0.0010252527,0.031152481,0.00020073459],"about_ca_topic_score_codex":0.006197063,"about_ca_topic_score_gemma":0.00027913446,"teacher_disagreement_score":0.87244064,"about_ca_system_score_codex":0.000028779144,"about_ca_system_score_gemma":0.000085620435,"threshold_uncertainty_score":0.93681467},"labels":[],"label_agreement":null},{"id":"W4387210621","doi":"10.59697/jik.v5i1.304","title":"IMPLEMENTASI DATA MINING PENGELOMPOKAN JENIS PENYAKIT PASIEN MENGGUNAKAN METODE CLUSTERING (STUDI KASUS : PUSKESMAS SAMBIREJO)","year":2021,"lang":"id","type":"article","venue":"Jurnal Informatika Kaputama (JIK)","topic":"Data Mining and Machine Learning 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":"Medicine","score_opus":0.06700875177334037,"score_gpt":0.3317793721214635,"score_spread":0.26477062034812315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387210621","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":[0.21358538,0.006656576,0.4606669,0.051585197,0.012723328,0.0042904154,0.006406188,0.0035897077,0.2404963],"genre_scores_gemma":[0.82814306,0.0009298879,0.15047316,0.0036665348,0.0022908323,0.00020908836,0.0068726367,0.00023633067,0.007178474],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9913408,0.0005286675,0.0026605527,0.0017344962,0.0017280586,0.0020074055],"domain_scores_gemma":[0.99093586,0.0007323454,0.0015681551,0.0052971602,0.00056529266,0.00090118643],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.0029640507,0.0010940448,0.0012160508,0.0005362921,0.002209203,0.003371354,0.006359292,0.00033798718,0.0005585528],"category_scores_gemma":[0.0007650765,0.001159945,0.0003500154,0.0018835001,0.00027868064,0.005788846,0.009318966,0.0018161987,0.0012047889],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012491344,0.0008800676,0.007346409,0.0011134616,0.0019137489,0.00064079615,0.05280007,0.003376641,0.0008161262,0.0029504902,0.19998294,0.72805434],"study_design_scores_gemma":[0.0023845546,0.0003426691,0.009116494,0.0005721444,0.00039705372,0.0014374276,0.007429744,0.27399692,0.0006354983,0.00007115022,0.7019517,0.0016646517],"about_ca_topic_score_codex":0.00070068554,"about_ca_topic_score_gemma":0.0005953594,"teacher_disagreement_score":0.7263897,"about_ca_system_score_codex":0.00037944567,"about_ca_system_score_gemma":0.0013355417,"threshold_uncertainty_score":0.9995729},"labels":[],"label_agreement":null},{"id":"W4387216697","doi":"10.59697/jik.v4i1.351","title":"PEMANFAATAN DUA METODE CLUSTERING DAN ASSOCIATION RULE TERHADAP PRESTASI BELAJAR BERDASARKAN NILAI MATA PELAJARAN SISWA","year":2020,"lang":"en","type":"article","venue":"Jurnal Informatika Kaputama (JIK)","topic":"Data Mining and Machine Learning 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":"Centroid; Cluster analysis; Association rule learning; Apriori algorithm; Computer science; Student achievement; Process (computing); k-means clustering; A priori and a posteriori; Educational data mining; Mathematics education; Data mining; Artificial intelligence; Psychology; Academic achievement","score_opus":0.016140677021709335,"score_gpt":0.24762581250232085,"score_spread":0.2314851354806115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387216697","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":[0.12013655,0.00019648838,0.763471,0.040124886,0.0009393199,0.0011194012,0.00022193769,0.0023967207,0.07139368],"genre_scores_gemma":[0.91506785,0.0000651934,0.07572711,0.006510702,0.0005429473,0.000110627785,0.00048252507,0.000070593655,0.0014224512],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99672407,0.00014258355,0.0009912848,0.00052017655,0.0009042925,0.0007176035],"domain_scores_gemma":[0.99738324,0.0002189503,0.0008155626,0.00093761244,0.0001703363,0.00047430707],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00086120376,0.00039962307,0.00045551054,0.00020120255,0.0006437378,0.0012005403,0.002046178,0.00018326085,0.000048544833],"category_scores_gemma":[0.00037408812,0.00039340713,0.00018228158,0.00075411046,0.00004209906,0.0031451713,0.001159912,0.00086504663,0.0004849441],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020371108,0.0007854622,0.03845735,0.001315267,0.0012932492,0.0001387304,0.08537892,0.04456361,0.0038094858,0.04533361,0.29904246,0.47967812],"study_design_scores_gemma":[0.0012850463,0.00027158894,0.020203616,0.00012275079,0.00009005624,0.00013285938,0.0007217506,0.59602445,0.00068637717,0.00028943966,0.37928212,0.0008899477],"about_ca_topic_score_codex":0.00008115382,"about_ca_topic_score_gemma":0.000017765067,"teacher_disagreement_score":0.7949313,"about_ca_system_score_codex":0.00022024516,"about_ca_system_score_gemma":0.00015599608,"threshold_uncertainty_score":0.99985176},"labels":[],"label_agreement":null},{"id":"W4387217147","doi":"10.59697/jik.v5i1.310","title":"IDENTIFIKASI JENIS BUNGA MENGGUNAKAN EKSTRAKSI CIRI ORDE SATU DAN ALGORITMA MULTI SUPPORT-VECTOR MACHINES (MULTISVM)","year":2021,"lang":"id","type":"article","venue":"Jurnal Informatika Kaputama (JIK)","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"Physics; Humanities; Art","score_opus":0.022408678746330592,"score_gpt":0.290960837281374,"score_spread":0.26855215853504344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387217147","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":[0.36432254,0.003915362,0.5107516,0.02357799,0.01939581,0.0039043922,0.004676772,0.0044022393,0.065053284],"genre_scores_gemma":[0.73964703,0.0013072153,0.18414915,0.005422181,0.0023619414,0.0003619629,0.005076852,0.00036553442,0.061308153],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9918727,0.0005056689,0.002670145,0.0014237532,0.0016662825,0.0018614237],"domain_scores_gemma":[0.99290943,0.0005219609,0.0015556996,0.0028336497,0.0010080904,0.0011711576],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015086917,0.0012280415,0.0012312676,0.00060260657,0.0017224585,0.004044582,0.003282579,0.0005673102,0.0006217992],"category_scores_gemma":[0.00086347054,0.0012603016,0.00068862655,0.0020568424,0.0003575484,0.0041977265,0.0020882385,0.0025665301,0.0033746457],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010267789,0.002387573,0.0060865083,0.0012024605,0.0012823815,0.0010687839,0.029451953,0.0014318371,0.0073298477,0.011731473,0.102270216,0.83565426],"study_design_scores_gemma":[0.0038850505,0.0005796855,0.03261424,0.0005413421,0.0003597434,0.0027140975,0.0014432697,0.25215197,0.0051603545,0.00012423114,0.6980054,0.0024206461],"about_ca_topic_score_codex":0.00056764355,"about_ca_topic_score_gemma":0.0003116949,"teacher_disagreement_score":0.83323365,"about_ca_system_score_codex":0.0002955196,"about_ca_system_score_gemma":0.001440204,"threshold_uncertainty_score":0.9997346},"labels":[],"label_agreement":null},{"id":"W4387217162","doi":"10.59697/jik.v5i1.318","title":"IMPLEMENTASI DATA MINING PENGELOMPOKAN JUMLAH DATA PRODUKTIVITAS UBINAN TANAMAN PANGAN BERDASARKAN JENIS UBINAN DENGAN METODE CLUSTERING DIKAB LANGKAT (STUDI KASUS : BADAN PUSAT STATISTIK LANGKAT)","year":2021,"lang":"id","type":"article","venue":"Jurnal Informatika Kaputama (JIK)","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"Horticulture; Mathematics; Biology","score_opus":0.09280023390331626,"score_gpt":0.3454898411828032,"score_spread":0.2526896072794869,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387217162","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":[0.39928448,0.01096335,0.37319785,0.04285747,0.012246508,0.008592723,0.08045879,0.00479554,0.06760328],"genre_scores_gemma":[0.73699015,0.00089008827,0.18569803,0.0029743179,0.0017494687,0.00019973402,0.06386301,0.00037788315,0.007257279],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9893542,0.0008410806,0.002730936,0.002699108,0.0020237141,0.0023509383],"domain_scores_gemma":[0.98557776,0.00089241815,0.0018529135,0.010124788,0.0005429018,0.0010092446],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":["metaepi_narrow","open_science"],"category_scores_codex":[0.004011603,0.0013932892,0.0015319468,0.000624223,0.0024615317,0.0038977514,0.010510239,0.00034558962,0.00023065253],"category_scores_gemma":[0.001194596,0.0014360546,0.0002291781,0.0020305766,0.00031051552,0.007268995,0.019023353,0.002126277,0.0007328007],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012802915,0.001001105,0.011414101,0.0014290613,0.0018132853,0.0010210393,0.028133666,0.000450989,0.0010476862,0.003183224,0.39457712,0.5558007],"study_design_scores_gemma":[0.0029595583,0.00054662186,0.016845217,0.0009890093,0.0008596891,0.0017556383,0.01194197,0.19465843,0.00065277226,0.00007693544,0.76623887,0.0024752915],"about_ca_topic_score_codex":0.002526471,"about_ca_topic_score_gemma":0.0071736393,"teacher_disagreement_score":0.5533254,"about_ca_system_score_codex":0.0004795505,"about_ca_system_score_gemma":0.001505808,"threshold_uncertainty_score":0.99988174},"labels":[],"label_agreement":null},{"id":"W4387364736","doi":"10.59934/jaiea.v3i1.268","title":"Grouping Patient Data Based On Work And Place Of Residence On Perceived Complaints","year":2023,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Cluster analysis; Residence; Work (physics); Anticipation (artificial intelligence); Cluster (spacecraft); Medicine; Data mining; Computer science; Artificial intelligence; Engineering","score_opus":0.058064489240473895,"score_gpt":0.2981837313356661,"score_spread":0.24011924209519223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387364736","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":[0.11381882,0.00006148289,0.88420856,0.0015266377,0.00009107511,0.00014965427,0.000018897423,0.00007821027,0.000046679663],"genre_scores_gemma":[0.9646642,0.00007133283,0.035100866,0.00006186158,0.000055441895,0.000015786909,0.000014081125,0.000010098833,0.0000062925924],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99887824,0.00002703061,0.00041900828,0.00027658633,0.00024319731,0.00015590971],"domain_scores_gemma":[0.9984008,0.0005721371,0.00020636659,0.00063512503,0.00008682872,0.00009876239],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005383062,0.00011535689,0.00017157209,0.0003190057,0.00013749051,0.00008274146,0.0006295066,0.00004106652,0.000002058079],"category_scores_gemma":[0.00020460172,0.00010825548,0.00002766625,0.0007216776,0.000052834013,0.00018725224,0.00016795857,0.0002485429,0.00001634054],"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":[0.000047644153,0.00016629546,0.00017904773,0.000061310486,0.000029345118,0.000008030434,0.0012318785,0.57501173,0.002444788,0.046301838,0.00087781524,0.37364027],"study_design_scores_gemma":[0.000045295154,0.0002679976,0.005938649,0.00029312662,0.000016326205,0.000014071441,0.00017940097,0.9872113,0.0009996749,0.00065659045,0.004203511,0.0001740802],"about_ca_topic_score_codex":0.000012159444,"about_ca_topic_score_gemma":0.0000016538719,"teacher_disagreement_score":0.8508454,"about_ca_system_score_codex":0.000021220614,"about_ca_system_score_gemma":0.000032935044,"threshold_uncertainty_score":0.44145304},"labels":[],"label_agreement":null},{"id":"W4387364743","doi":"10.59934/jaiea.v3i1.325","title":"Prediction Of New Students Using The Exponential Smoothing Method (Case Study: STMIK Kaputama)","year":2023,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Exponential smoothing; Computer science; Smoothing; Alpha (finance); Exponential function; Value (mathematics); Statistics; Mathematics; Machine learning","score_opus":0.10180338037341921,"score_gpt":0.3727623027873869,"score_spread":0.2709589224139677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387364743","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":[0.2757831,0.00005122722,0.7235446,0.00021770094,0.00014286839,0.0001878622,0.0000042632514,0.0000647188,0.0000036926897],"genre_scores_gemma":[0.9133352,0.000035427565,0.08629196,0.000012823932,0.0002654847,0.000023607243,0.0000021798967,0.000014037038,0.000019274132],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985635,0.00005525008,0.00063210743,0.00021599511,0.0003588347,0.00017430297],"domain_scores_gemma":[0.9987726,0.00025083928,0.00031168028,0.00042060314,0.00013966074,0.000104574916],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013502253,0.00012328988,0.0001935733,0.00032679253,0.00025972442,0.00020164366,0.00071963185,0.000045971843,0.0000023945524],"category_scores_gemma":[0.00009085291,0.000102540915,0.000070903676,0.0010944797,0.000030639214,0.00032131735,0.00021604598,0.00030000223,0.000005858162],"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":[0.000015392596,0.0004176726,0.0011071927,0.0000429652,0.00023598583,0.00006874183,0.014002955,0.5006121,0.018673856,0.012205451,0.00033789015,0.4522798],"study_design_scores_gemma":[0.000106212334,0.00022072197,0.0012540957,0.000059229646,0.00013037963,0.0008785021,0.006270078,0.98345417,0.003132159,0.0019925062,0.002328486,0.00017348872],"about_ca_topic_score_codex":0.00020961108,"about_ca_topic_score_gemma":0.0000053259887,"teacher_disagreement_score":0.63755214,"about_ca_system_score_codex":0.000026370613,"about_ca_system_score_gemma":0.00006931593,"threshold_uncertainty_score":0.4181497},"labels":[],"label_agreement":null},{"id":"W4387376623","doi":"10.59934/jaiea.v3i1.296","title":"Application of the Clustering Algorithm for the Classification of General Criminal Cases at the Binjai District Attorney's Office","year":2023,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Cluster analysis; Commission; Mathematics; Law; Computer science; Artificial intelligence; Political science","score_opus":0.04791890014761653,"score_gpt":0.304206370956922,"score_spread":0.2562874708093055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387376623","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020740071,0.00021283218,0.9768847,0.0015656521,0.00014137756,0.0003690262,0.00003911746,0.00003304635,0.000014182411],"genre_scores_gemma":[0.97637653,0.00018066732,0.022834597,0.000029302877,0.00024413699,0.0002322407,0.000015618267,0.000015279935,0.000071632596],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988169,0.000029883176,0.00057341385,0.0001839215,0.00023774676,0.00015814195],"domain_scores_gemma":[0.9977526,0.0008710275,0.00048858573,0.0006046357,0.00023882595,0.000044316363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007474489,0.00011368125,0.0001537823,0.00011679259,0.0003663268,0.00006530811,0.00094621646,0.000046726924,0.0000013056701],"category_scores_gemma":[0.00014706938,0.00006892339,0.000117008276,0.00092280336,0.00013063496,0.00012535792,0.00019164488,0.0001778106,0.000005550467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011883015,0.00006284523,0.0000874952,0.000057248464,0.000050586325,2.3465842e-7,0.00058324327,0.10411156,0.026335236,0.035036344,0.00049120246,0.83317214],"study_design_scores_gemma":[0.000031233885,0.00005544953,0.007503312,0.000023287052,0.00007306082,0.000046552777,0.0003188421,0.9688802,0.009010708,0.00036254287,0.013607255,0.000087570086],"about_ca_topic_score_codex":0.0000658448,"about_ca_topic_score_gemma":0.000015084934,"teacher_disagreement_score":0.95563644,"about_ca_system_score_codex":0.00003757692,"about_ca_system_score_gemma":0.000053084004,"threshold_uncertainty_score":0.28175268},"labels":[],"label_agreement":null},{"id":"W4387376745","doi":"10.59934/jaiea.v3i1.284","title":"Regional Data Mining Implementation Of Contraceptive Equipment Users In The City Of Binjai By Type Using Clustering method","year":2023,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"Government (linguistics); Family planning; Population; Medicine; Environmental health; Research methodology","score_opus":0.1408120687750516,"score_gpt":0.40910919133443485,"score_spread":0.26829712255938326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387376745","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1270232,0.00009427743,0.87216204,0.00051271456,0.00004388752,0.00012437145,0.000020387006,0.000013723819,0.000005402087],"genre_scores_gemma":[0.8474504,0.000105022365,0.152333,0.000022526769,0.00004358666,0.000011011585,0.000025417541,0.0000066131443,0.0000024605836],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988875,0.000045325007,0.00055256305,0.00016926347,0.000210752,0.00013461997],"domain_scores_gemma":[0.9988028,0.00034841802,0.00033194764,0.00036495738,0.000116304494,0.000035589972],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014360097,0.00008211894,0.00016351363,0.00023749762,0.000068410634,0.000045693287,0.000734443,0.000031767344,0.0000024698636],"category_scores_gemma":[0.000065578184,0.000071561335,0.00002860549,0.0009399017,0.00003606762,0.00027007048,0.00016098193,0.00014633224,0.0000010201804],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003473802,0.00021626047,0.0021044048,0.0001222967,0.00014898262,0.000003647627,0.012591304,0.19514744,0.13715582,0.02118645,0.0009875161,0.6303012],"study_design_scores_gemma":[0.00007982519,0.00012789153,0.0025505829,0.00008945577,0.00004132937,0.00003526712,0.0059801545,0.980011,0.007600002,0.0006922679,0.0026451761,0.00014703826],"about_ca_topic_score_codex":0.00016556692,"about_ca_topic_score_gemma":0.000019167648,"teacher_disagreement_score":0.7848636,"about_ca_system_score_codex":0.000022574359,"about_ca_system_score_gemma":0.00006121774,"threshold_uncertainty_score":0.29181868},"labels":[],"label_agreement":null},{"id":"W4387376856","doi":"10.59934/jaiea.v3i1.259","title":"Diagnosis of Herpes Zoster Using Bayes Theorem Method","year":2023,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Bayes' theorem; Itching; Disease; Conditional probability; Shingles; Blisters; Medicine; Dermatology; Mathematics; Computer science; Artificial intelligence; Pathology; Statistics; Immunology; Virus","score_opus":0.045417730179383595,"score_gpt":0.3322193396993053,"score_spread":0.2868016095199217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387376856","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032012388,0.00019157806,0.9668278,0.0006643442,0.00009259466,0.00009334959,0.000007071941,0.00007636606,0.000034492852],"genre_scores_gemma":[0.6678625,0.00027190053,0.33160326,0.000029515084,0.0001549385,0.000041605097,0.0000033058682,0.000015980093,0.000017052986],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99892664,0.000031320964,0.0005055195,0.00018347935,0.00018100037,0.00017202683],"domain_scores_gemma":[0.9987444,0.00044494166,0.00024439266,0.00032544674,0.00015311866,0.00008768282],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079063646,0.000112247144,0.00020791405,0.00036231615,0.00010806957,0.00009447756,0.00052086776,0.00005226807,0.0000059378767],"category_scores_gemma":[0.00012156667,0.00010306221,0.000079302605,0.0009820528,0.000042948308,0.00026846718,0.00012347833,0.00015416632,0.00001670033],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004229897,0.00007783692,0.00017751337,0.000044657194,0.000050320377,0.0000025579127,0.0008485234,0.092336796,0.007412015,0.118411005,0.00016319305,0.7804713],"study_design_scores_gemma":[0.000046143166,0.0001048347,0.0009463274,0.00014243682,0.000063898864,0.000088183246,0.0004684379,0.91382486,0.04269615,0.021103526,0.020232702,0.00028248507],"about_ca_topic_score_codex":0.000022932034,"about_ca_topic_score_gemma":0.0000011560021,"teacher_disagreement_score":0.8214881,"about_ca_system_score_codex":0.00001646741,"about_ca_system_score_gemma":0.00003976603,"threshold_uncertainty_score":0.42027548},"labels":[],"label_agreement":null},{"id":"W4387376949","doi":"10.59934/jaiea.v3i1.264","title":"Classification Of Population Data On Status In The Family Based On Last Education And Work Using The Clustering Method (Case Study: Sei Prison Village Office)","year":2023,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Census; Population; Cluster (spacecraft); Geography; Work (physics); Cluster analysis; Demography; Computer science; Sociology; Statistics; Engineering; Mathematics","score_opus":0.10250219213536535,"score_gpt":0.37866437402385333,"score_spread":0.27616218188848796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387376949","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":[0.33441216,0.000039807623,0.6647272,0.00043042327,0.00006663244,0.00028273862,0.000005398494,0.000024245675,0.000011352842],"genre_scores_gemma":[0.9671438,0.000028231394,0.032627165,0.000050534705,0.000081985476,0.00003717873,0.000019087045,0.000010285746,0.0000017595266],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987292,0.00012737594,0.00049098604,0.0002616799,0.00024562184,0.00014508986],"domain_scores_gemma":[0.9981454,0.00069965597,0.00028752172,0.0007402004,0.000080693404,0.00004649881],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017330959,0.00011476549,0.00014437415,0.00036693097,0.00020556431,0.00016712317,0.00056353456,0.000040947787,3.7435882e-7],"category_scores_gemma":[0.00015328734,0.0000838124,0.000023837427,0.0013021012,0.000025426261,0.00021561942,0.00010237678,0.00028035298,0.0000021402695],"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":[0.00001833349,0.00031029945,0.0015803338,0.000026744297,0.000013717628,0.000004494577,0.002365694,0.5311729,0.001019269,0.004096884,0.000055090128,0.45933628],"study_design_scores_gemma":[0.000038017948,0.00010554467,0.030424856,0.00007076021,0.000024347217,0.000039138697,0.004073764,0.96419775,0.000039403105,0.00016063453,0.00073795154,0.000087842905],"about_ca_topic_score_codex":0.000323822,"about_ca_topic_score_gemma":0.000051017458,"teacher_disagreement_score":0.6327316,"about_ca_system_score_codex":0.000036149515,"about_ca_system_score_gemma":0.00005979102,"threshold_uncertainty_score":0.34177706},"labels":[],"label_agreement":null},{"id":"W4387377047","doi":"10.59934/jaiea.v3i1.286","title":"The Grouping Of Types Of Tax Revenue In Binjai City Uses The K-Means Clustering Method Algorithm","year":2023,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"Revenue; Government (linguistics); Tax revenue; Finance; Business; Economics; Public economics","score_opus":0.03634477815363503,"score_gpt":0.3177911543725026,"score_spread":0.2814463762188676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387377047","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0074973535,0.00023031114,0.9908586,0.0011662391,0.000089595684,0.00010859771,0.0000132393325,0.000020808306,0.000015219],"genre_scores_gemma":[0.7810422,0.00072344416,0.21792667,0.00002307725,0.00015842362,0.00005456935,0.0000027707636,0.000015197079,0.000053633674],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99899775,0.000044797962,0.0005231689,0.00012489155,0.00016351587,0.00014589631],"domain_scores_gemma":[0.99854076,0.00069959665,0.00027551543,0.00033585785,0.00011200201,0.000036254358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014816343,0.00008094952,0.00016158882,0.00019238317,0.00014421591,0.00006302436,0.0006640898,0.000034981294,6.540913e-7],"category_scores_gemma":[0.00019035241,0.00005725878,0.000055631994,0.001043943,0.000063596424,0.00013478677,0.0001382897,0.0002402157,0.0000028885386],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000045337565,0.000040607258,0.0001346186,0.000035332454,0.000036019694,0.000001203475,0.0015538203,0.17810448,0.006922303,0.025360452,0.00014404216,0.7876626],"study_design_scores_gemma":[0.000023386974,0.00005013338,0.0015387913,0.00009174951,0.00001654367,0.000024779092,0.00047381688,0.9804455,0.0050798883,0.0048789536,0.007287708,0.00008875879],"about_ca_topic_score_codex":0.00012752281,"about_ca_topic_score_gemma":0.000041939904,"teacher_disagreement_score":0.80234104,"about_ca_system_score_codex":0.000015079013,"about_ca_system_score_gemma":0.000037657104,"threshold_uncertainty_score":0.23349454},"labels":[],"label_agreement":null},{"id":"W4387377085","doi":"10.59934/jaiea.v3i1.275","title":"Clustering Disease on Settlements Inhabitant In place seedy With Use Clustering Method","year":2023,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Cluster analysis; Slum; Environmental health; Cluster (spacecraft); Data mining; Human settlement; Computer science; Medicine; Geography; Machine learning; Population","score_opus":0.03741071132049064,"score_gpt":0.31052754917784164,"score_spread":0.273116837857351,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387377085","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030793166,0.000029229981,0.9676283,0.0011495275,0.000074773285,0.00018318546,0.000010155061,0.00011085677,0.000020818328],"genre_scores_gemma":[0.81194085,0.0001008975,0.18755291,0.00009391818,0.00011374558,0.000102405764,0.000011350369,0.000027425462,0.000056486984],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871624,0.000034882523,0.0004619136,0.0002848217,0.00024335289,0.00025881612],"domain_scores_gemma":[0.9988857,0.00031935514,0.00016380927,0.00038193367,0.00007669023,0.0001725385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007014113,0.00015715192,0.0001868048,0.00051937805,0.0001223396,0.00023454547,0.00041876797,0.00003307521,0.0000020664982],"category_scores_gemma":[0.0001066953,0.00014198523,0.000040595627,0.0010501678,0.000023571893,0.0004271073,0.00015151029,0.00031858566,0.000028995053],"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":[0.000033414224,0.00007556027,0.00039023624,0.000036780453,0.000022320486,0.00002829563,0.00056124583,0.90001523,0.0010181931,0.0067646564,0.000080691694,0.09097337],"study_design_scores_gemma":[0.0000635781,0.00011131463,0.0042274585,0.00015935462,0.0000145587765,0.0000413582,0.00015888512,0.99047947,0.000402021,0.00042964978,0.0037235902,0.00018874086],"about_ca_topic_score_codex":0.000028034534,"about_ca_topic_score_gemma":0.000021720633,"teacher_disagreement_score":0.7811477,"about_ca_system_score_codex":0.000060876504,"about_ca_system_score_gemma":0.000055839122,"threshold_uncertainty_score":0.578999},"labels":[],"label_agreement":null},{"id":"W4387377094","doi":"10.59934/jaiea.v3i1.326","title":"Diagnosing a Paper Dryer Malfunction in PT.Bamindo Agrapersada Using the Method DecisionTree","year":2023,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Decision tree; Computer science; Tree (set theory); Field (mathematics); Outcome (game theory); Production (economics); Operations research; Artificial intelligence; Machine learning; Engineering; Mathematics; Economics; Mathematical economics","score_opus":0.04294819572451351,"score_gpt":0.3238831046280934,"score_spread":0.28093490890357986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387377094","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026314832,0.000196212,0.9709031,0.0021732312,0.00016514341,0.00015279106,0.0000026179416,0.00006659361,0.00002546195],"genre_scores_gemma":[0.79997075,0.00031974106,0.1991037,0.0001654499,0.0003034404,0.00008390727,0.000005382111,0.000023228566,0.000024430637],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985285,0.000049433234,0.00072928483,0.00023223716,0.00023155914,0.00022898226],"domain_scores_gemma":[0.9982175,0.0008836546,0.00033096867,0.0003788361,0.000109149536,0.00007988032],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015576631,0.00012979087,0.00019656363,0.00042293177,0.00022229439,0.00021627363,0.0005454567,0.00006135574,0.000006568525],"category_scores_gemma":[0.00043682574,0.00010078466,0.00007857666,0.0015893413,0.000028363895,0.00040916173,0.00012249751,0.00035991718,0.000029584244],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000074575646,0.000055292094,0.00025280347,0.000013189396,0.000029317252,0.000007883357,0.0012986274,0.31140947,0.016405368,0.039349835,0.00025037356,0.6309204],"study_design_scores_gemma":[0.000046511806,0.000051740677,0.002682391,0.00009015023,0.00003087581,0.000116473115,0.0008219702,0.9693393,0.0025102596,0.007261293,0.016849147,0.00019988243],"about_ca_topic_score_codex":0.000078471574,"about_ca_topic_score_gemma":0.00001699435,"teacher_disagreement_score":0.7736559,"about_ca_system_score_codex":0.000046025045,"about_ca_system_score_gemma":0.00005085474,"threshold_uncertainty_score":0.4109879},"labels":[],"label_agreement":null},{"id":"W4387377172","doi":"10.59934/jaiea.v3i1.278","title":"Grouping Data On Infrastructure Development In Langkat District Using The Clustering Method (Case Study: PUPR, Langkat Regency)","year":2023,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Cluster analysis; Service (business); Business; Computer science; Marketing; Artificial intelligence","score_opus":0.09027193488319984,"score_gpt":0.3640210726523097,"score_spread":0.27374913776910986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387377172","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12025418,0.00005982887,0.87895215,0.0003429742,0.000101899,0.00020304682,0.0000060200214,0.00006810717,0.000011821604],"genre_scores_gemma":[0.83503616,0.000035131492,0.16466062,0.000032577987,0.00015796637,0.000037030844,0.000013424623,0.000016387332,0.000010701877],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871016,0.000050175524,0.0005127927,0.00029750422,0.00021692188,0.00021243143],"domain_scores_gemma":[0.9987112,0.00029424124,0.0001809149,0.00068208354,0.00005861395,0.000072915056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012386418,0.00013936014,0.00017439155,0.00035185707,0.0002556597,0.0001802719,0.00093412533,0.00004446787,0.0000016493315],"category_scores_gemma":[0.000111615365,0.00011037258,0.00002694484,0.0012402618,0.00001890522,0.00027967064,0.0004280561,0.00039041598,0.000010210979],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005605493,0.000096389864,0.00045020887,0.000028250468,0.000045189394,0.00012736618,0.0036288744,0.4176251,0.0008995822,0.005092964,0.00012883205,0.57187164],"study_design_scores_gemma":[0.0000429616,0.000049206712,0.0014134498,0.00006068731,0.000020240072,0.00058390916,0.002443516,0.9877293,0.0002846258,0.00030741468,0.0068954458,0.00016924662],"about_ca_topic_score_codex":0.00012879509,"about_ca_topic_score_gemma":0.00006861089,"teacher_disagreement_score":0.714782,"about_ca_system_score_codex":0.000058890735,"about_ca_system_score_gemma":0.000060925347,"threshold_uncertainty_score":0.45008633},"labels":[],"label_agreement":null},{"id":"W4387377178","doi":"10.59934/jaiea.v3i1.270","title":"Grouping Number of Library Members For Determining the Location of Socialization Using Clustering Method","year":2023,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Socialization; Cluster analysis; Computer science; Process (computing); Selection (genetic algorithm); Reading (process); Data science; Data mining; Information retrieval; Machine learning; Sociology; Political science; Social science","score_opus":0.05408183807825251,"score_gpt":0.3507933883314947,"score_spread":0.2967115502532422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387377178","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019113895,0.00004370146,0.9802163,0.00029896564,0.0000911215,0.00016712066,0.0000046149394,0.000046227135,0.000018005403],"genre_scores_gemma":[0.63725084,0.00004644576,0.362512,0.000016037988,0.00011672517,0.000027773804,0.000007647381,0.000014629034,0.000007890433],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900883,0.000027907765,0.0005596492,0.00013388891,0.00014247876,0.00012725445],"domain_scores_gemma":[0.9986354,0.00044609516,0.0004269805,0.00021418027,0.00023798159,0.000039375678],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069585623,0.00008653856,0.00017169314,0.00019321688,0.00014631441,0.000062973646,0.0003829753,0.00004704193,0.0000015893753],"category_scores_gemma":[0.00016053228,0.00007697613,0.00005975733,0.0011412364,0.000038242335,0.0003847567,0.00009795416,0.0001093491,0.0000013185845],"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":[0.000011929925,0.000050575414,0.00051735755,0.00022825784,0.000056174387,2.229339e-7,0.0022736057,0.6328254,0.009318269,0.10510964,0.000077540804,0.24953105],"study_design_scores_gemma":[0.000030727435,0.000027739834,0.00060420245,0.000089359164,0.000032547516,0.000011182094,0.00031045967,0.9891753,0.006149857,0.0024678358,0.0010189031,0.0000818722],"about_ca_topic_score_codex":0.000012571774,"about_ca_topic_score_gemma":0.0000010885942,"teacher_disagreement_score":0.61813694,"about_ca_system_score_codex":0.000014773987,"about_ca_system_score_gemma":0.00006407555,"threshold_uncertainty_score":0.31389955},"labels":[],"label_agreement":null},{"id":"W4387377357","doi":"10.59934/jaiea.v3i1.246","title":"Implementation of Mechine Learning Eligibility for Customer Credit Payments at Bank BTN Using the K – Nearst Neighbor Algorithm","year":2023,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Arrears; Loan; Payment; Business; Finance; Credit card interest; Algorithm; Computer science; Credit card","score_opus":0.03925350321741575,"score_gpt":0.3541133314538884,"score_spread":0.3148598282364726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387377357","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07383753,0.00007546067,0.92505276,0.0005598355,0.00012597334,0.00025921248,0.000021360536,0.000059316088,0.000008519379],"genre_scores_gemma":[0.870581,0.00014673537,0.12880698,0.000025128202,0.00027159668,0.000080043385,0.000026937541,0.000021232207,0.00004035257],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874926,0.000028163693,0.00057852274,0.00021072151,0.00022499062,0.0002083368],"domain_scores_gemma":[0.9987444,0.000317135,0.0003528583,0.00030109566,0.00020961749,0.00007488562],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009783036,0.0001204066,0.00018300813,0.00021062474,0.0003244419,0.00009666505,0.0004565903,0.000044094275,0.0000071362547],"category_scores_gemma":[0.000082591396,0.00009894643,0.00008724475,0.00077149837,0.000047099922,0.00023851021,0.00014712659,0.00020297385,0.000010994216],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015619145,0.0000622623,0.0007551286,0.000078813246,0.00012007139,0.0000013005005,0.001804077,0.15692484,0.04959888,0.032834634,0.0005136446,0.7572907],"study_design_scores_gemma":[0.00007641246,0.000117364165,0.0013622789,0.000028713657,0.000055588844,0.000028287714,0.00064763287,0.96108705,0.018596744,0.0020099394,0.015828975,0.00016103957],"about_ca_topic_score_codex":0.000063124804,"about_ca_topic_score_gemma":0.0000060176767,"teacher_disagreement_score":0.8041622,"about_ca_system_score_codex":0.000052740696,"about_ca_system_score_gemma":0.00006711662,"threshold_uncertainty_score":0.40349182},"labels":[],"label_agreement":null},{"id":"W4387377409","doi":"10.59934/jaiea.v3i1.295","title":"Categorying Sugarcane Production Based On Factors Affecting Productivity With The K-Nearest Neighbor Algorithm","year":2023,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Production (economics); Productivity; Computer science; Saccharum; Process (computing); Crop; Agricultural engineering; Algorithm; Agronomy; Engineering; Biology; Programming language; Economics","score_opus":0.02537274216048275,"score_gpt":0.2627660222889876,"score_spread":0.23739328012850486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387377409","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":[0.08537336,0.000026643282,0.9098325,0.00418988,0.00014547381,0.00023923133,0.0000032878893,0.00016490527,0.00002473314],"genre_scores_gemma":[0.97916955,0.000014487787,0.020403938,0.00002222748,0.00029335625,0.0000486337,0.0000071879767,0.00001636929,0.000024265939],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891806,0.00003648013,0.00026102268,0.0002941172,0.0002717885,0.00021850748],"domain_scores_gemma":[0.99878055,0.00033611743,0.00020254134,0.0004449766,0.00015307117,0.00008273531],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008294763,0.0001470546,0.00014884598,0.00028603303,0.00039203357,0.00020448858,0.00044113162,0.000037067486,0.0000013668631],"category_scores_gemma":[0.00017303448,0.00010132644,0.000044141176,0.0013030518,0.000058670237,0.00027008614,0.000053601547,0.00039456142,0.000014960578],"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":[0.000012405736,0.0001364636,0.0003313962,0.000041610696,0.000040575243,0.0000047669637,0.0015975224,0.60557514,0.00506939,0.007037925,0.0004081271,0.37974465],"study_design_scores_gemma":[0.000050319253,0.00036051817,0.007177288,0.00009749426,0.00004537704,0.00007068411,0.0012432551,0.95873165,0.024730988,0.00063260924,0.0065109604,0.00034883726],"about_ca_topic_score_codex":0.000027007478,"about_ca_topic_score_gemma":0.00000616273,"teacher_disagreement_score":0.89379615,"about_ca_system_score_codex":0.00003727533,"about_ca_system_score_gemma":0.00006640892,"threshold_uncertainty_score":0.41319725},"labels":[],"label_agreement":null},{"id":"W4387377709","doi":"10.59934/jaiea.v3i1.279","title":"Application of Data Mining in Analyzing the Effect of Parents' Employment and Education Level on Student Behavior Using the A PRIORI Method (Case Study: SDN 024769 Binjai)","year":2023,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"Value (mathematics); Certainty; Psychology; Set (abstract data type); Value of time; Mathematics; Social psychology; Developmental psychology; Statistics; Computer science; Engineering; Travel time","score_opus":0.10297270742085946,"score_gpt":0.4264688336021232,"score_spread":0.3234961261812637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387377709","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":[0.5091621,0.00010012505,0.4901498,0.00013297405,0.000037811533,0.00039655826,0.0000068647846,0.000012457618,0.0000012601552],"genre_scores_gemma":[0.97361785,0.000046687644,0.02609873,0.000005633095,0.000057818237,0.0001541619,0.00000621257,0.000010389273,0.0000025098304],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858177,0.00011801198,0.00065147056,0.00027375456,0.00023880614,0.00013617385],"domain_scores_gemma":[0.99799037,0.0007094916,0.00039963392,0.0007556024,0.00009501074,0.000049909184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023541274,0.00012932332,0.00022902858,0.000356822,0.00016853597,0.000089709734,0.00080803747,0.000034810568,3.2760258e-7],"category_scores_gemma":[0.0000990427,0.000089356276,0.00003568034,0.0011446151,0.00004682408,0.00021446127,0.00028812696,0.00022910241,8.796298e-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":[0.000010682287,0.00032010852,0.017535005,0.000037451937,0.000057186066,0.000004497778,0.0039255605,0.05033924,0.0041348203,0.0017352974,0.0000122587135,0.9218879],"study_design_scores_gemma":[0.00019297158,0.0007708505,0.042981964,0.00021236938,0.00037114063,0.000338089,0.011222981,0.9384027,0.0044307034,0.0002739915,0.00050344574,0.00029876974],"about_ca_topic_score_codex":0.00028807964,"about_ca_topic_score_gemma":0.00002814744,"teacher_disagreement_score":0.92158914,"about_ca_system_score_codex":0.0000313925,"about_ca_system_score_gemma":0.00005861618,"threshold_uncertainty_score":0.36438432},"labels":[],"label_agreement":null},{"id":"W4387377888","doi":"10.59934/jaiea.v3i1.274","title":"Sentiment Analysis Using Text Mining Techniques On Social Media Using the Support Vector Machine Method Case Study Seagames 2023 Football Final","year":2023,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"Sentiment analysis; Social media; Support vector machine; Football; Computer science; Event (particle physics); Data science; Data mining; Artificial intelligence; World Wide Web; Political science","score_opus":0.10842578325431523,"score_gpt":0.38559440816632634,"score_spread":0.2771686249120111,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387377888","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":[0.20953964,0.000032440177,0.78963286,0.00037027276,0.00008493649,0.0002071175,0.000015008864,0.0001076599,0.000010104427],"genre_scores_gemma":[0.8800646,0.000016210408,0.11951112,0.000026170044,0.00029448583,0.000046439884,0.0000070052765,0.000018844888,0.000015133152],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982831,0.0000980084,0.00065317174,0.00033052333,0.00036079547,0.00027444036],"domain_scores_gemma":[0.99837536,0.00061220286,0.00033760112,0.0004075056,0.00016082788,0.00010652289],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016497903,0.00019827478,0.00032200446,0.0007476188,0.0005419475,0.00028374855,0.00057771266,0.000062685904,0.0000087313065],"category_scores_gemma":[0.00010481525,0.00016316309,0.00015618377,0.0025484208,0.00004720701,0.00020259153,0.00018932602,0.00037314766,0.000008615913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027081087,0.00061587925,0.0007385628,0.000039617018,0.0011237236,0.0003354824,0.016664313,0.3713369,0.011328648,0.0077822558,0.0003653452,0.5896422],"study_design_scores_gemma":[0.0000434943,0.00013349556,0.00065715,0.000021318609,0.00048429403,0.0005861149,0.004629952,0.9892477,0.0025357027,0.00021427147,0.0011917779,0.00025473244],"about_ca_topic_score_codex":0.00011793277,"about_ca_topic_score_gemma":0.000032202697,"teacher_disagreement_score":0.67052495,"about_ca_system_score_codex":0.00006799971,"about_ca_system_score_gemma":0.000070609196,"threshold_uncertainty_score":0.66535974},"labels":[],"label_agreement":null},{"id":"W4387377943","doi":"10.59934/jaiea.v3i1.257","title":"Occupational Correlation to the Level of Community Welfare Using The Apriori Algorithm (Case Study: Mangga Village)","year":2023,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Welfare; Business; Work (physics); Government (linguistics); Value (mathematics); Social Welfare; Public economics; Demographic economics; Labour economics; Economic growth; Economics; Political science; Engineering; Statistics; Market economy; Law; Mathematics","score_opus":0.13855540123068774,"score_gpt":0.35911067017365755,"score_spread":0.2205552689429698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387377943","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":[0.15935218,0.000025883295,0.8386276,0.0015583354,0.000116764735,0.000252981,0.000020393087,0.000039258433,0.000006605165],"genre_scores_gemma":[0.96389383,0.000010371826,0.03586765,0.000037423877,0.0001249848,0.000039167076,0.000005468296,0.000009408813,0.000011688216],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891675,0.00008849652,0.00048371658,0.00011588197,0.00025486486,0.00014032205],"domain_scores_gemma":[0.9985424,0.00038290097,0.0002311051,0.0005294259,0.00024664833,0.00006749989],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014057496,0.00010626311,0.00013971208,0.00023118674,0.0007174324,0.00012803118,0.00072722556,0.000035485496,0.0000022252996],"category_scores_gemma":[0.00012172154,0.00007545645,0.000053887296,0.0012664993,0.000044889734,0.00018271092,0.00021444554,0.0003838957,0.000012615252],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004832399,0.00014212224,0.00018032678,0.000012137781,0.00005065606,0.000008934206,0.0071232296,0.47990832,0.0005087097,0.015447295,0.00021135632,0.49640208],"study_design_scores_gemma":[0.00004519777,0.00016095913,0.0069166794,0.000026721451,0.00005634894,0.00053843524,0.012184929,0.9716029,0.00036851675,0.0007822474,0.0071552307,0.00016182696],"about_ca_topic_score_codex":0.000387437,"about_ca_topic_score_gemma":0.000041567466,"teacher_disagreement_score":0.80454165,"about_ca_system_score_codex":0.000028809623,"about_ca_system_score_gemma":0.000057807192,"threshold_uncertainty_score":0.5517983},"labels":[],"label_agreement":null},{"id":"W4387378003","doi":"10.59934/jaiea.v3i1.309","title":"Classification Of Diseases In Patients Based On Factors Environment Using The K-Means Algorithm At Puskesmas Subdistrict Selesai","year":2023,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Public health; Environmental health; Cluster analysis; Disease; Medicine; Medical diagnosis; Environmental pollution; Business; Computer science; Environmental protection; Geography; Pathology; Artificial intelligence","score_opus":0.031156596573927883,"score_gpt":0.26142109984972656,"score_spread":0.23026450327579867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387378003","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":[0.21179087,0.000025418318,0.7876818,0.00024587696,0.000050082854,0.0001435742,0.000028230123,0.000028908069,0.0000052089454],"genre_scores_gemma":[0.9835621,0.000038247428,0.016277337,0.000009684865,0.000039360657,0.000024774772,0.000032153344,0.000010171158,0.0000061695378],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891996,0.00003106791,0.00044547452,0.0001891001,0.00026107824,0.00015329766],"domain_scores_gemma":[0.999,0.00026759895,0.00024621587,0.00035400517,0.000059455488,0.000072683906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002907376,0.00011292379,0.00014538218,0.0003055801,0.00013809286,0.000049489936,0.0004189351,0.000040418257,0.0000026299394],"category_scores_gemma":[0.00006547869,0.00009003461,0.000058147856,0.00073834497,0.00004965143,0.00012838539,0.00006840579,0.00016946485,0.00000957294],"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":[0.000011950025,0.00038397193,0.024429185,0.000026655936,0.000023740731,0.0000011098231,0.0005355526,0.81174016,0.0021306884,0.008272621,0.00008050267,0.15236387],"study_design_scores_gemma":[0.000038413134,0.00007247861,0.094664685,0.000024835133,0.000016079252,0.0000010594696,0.0001050801,0.902765,0.0010145468,0.00029918068,0.00090760353,0.00009105949],"about_ca_topic_score_codex":0.000016236914,"about_ca_topic_score_gemma":0.0000011315042,"teacher_disagreement_score":0.77177125,"about_ca_system_score_codex":0.00008825909,"about_ca_system_score_gemma":0.00003424925,"threshold_uncertainty_score":0.36715052},"labels":[],"label_agreement":null},{"id":"W4387378051","doi":"10.59934/jaiea.v3i1.273","title":"The Effect of Social Media on Student Learning Motivation Using the Apriori Method","year":2023,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"Association rule learning; Apriori algorithm; Class (philosophy); Association (psychology); Social media; Computer science; Psychology; A priori and a posteriori; Artificial intelligence; Mathematics education; Machine learning","score_opus":0.03680484049623135,"score_gpt":0.34474144680684266,"score_spread":0.3079366063106113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387378051","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":[0.10052225,0.000061221916,0.89810055,0.0009496429,0.00014776016,0.00013722137,0.000001451301,0.00005561321,0.000024279889],"genre_scores_gemma":[0.99046856,0.00006883202,0.009116739,0.000009947281,0.00027268473,0.000034402947,0.0000025587763,0.00001211661,0.000014128968],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99886835,0.000108168504,0.00042179227,0.00014396888,0.0002950758,0.00016262033],"domain_scores_gemma":[0.9967757,0.0025430592,0.0002946746,0.00023658507,0.00010672669,0.000043291126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001985507,0.000106059255,0.00015960888,0.00016963363,0.00052587554,0.00014821345,0.00061862444,0.000042461586,8.446537e-7],"category_scores_gemma":[0.00047062867,0.000066805216,0.00007492122,0.0008723999,0.000053896663,0.00011897701,0.00010706801,0.00037971875,0.000008665161],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014164553,0.00003083123,0.00023077431,0.000019265324,0.00006514324,9.998553e-7,0.0038619554,0.37168184,0.009780612,0.09866269,0.0001050072,0.5155467],"study_design_scores_gemma":[0.0000985449,0.00040153338,0.007908248,0.00007757559,0.000098798235,0.000038735325,0.001812153,0.94535744,0.023376154,0.0030651446,0.017502245,0.00026345561],"about_ca_topic_score_codex":0.000005600954,"about_ca_topic_score_gemma":9.398316e-7,"teacher_disagreement_score":0.88994634,"about_ca_system_score_codex":0.000028057117,"about_ca_system_score_gemma":0.000025807936,"threshold_uncertainty_score":0.40446627},"labels":[],"label_agreement":null},{"id":"W4387401916","doi":"10.59934/jaiea.v3i1.370","title":"Clustering Data On Underage Marriage Using The Clustering Method","year":2023,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Cluster analysis; Paragraph; The Internet; Psychology; Computer science; Law; Political science; Artificial intelligence; World Wide Web","score_opus":0.11467333694435099,"score_gpt":0.3709716232035928,"score_spread":0.2562982862592418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387401916","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019864456,0.00008790786,0.99562025,0.001729248,0.00021527126,0.00014722996,0.000012084128,0.00013306092,0.00006852216],"genre_scores_gemma":[0.5521841,0.00028193695,0.44648042,0.00020609603,0.0006739634,0.0000407531,0.00002294204,0.00004315223,0.00006662366],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866384,0.000048491405,0.00048554654,0.00031273998,0.00024141301,0.0002479695],"domain_scores_gemma":[0.9981276,0.0004978142,0.00021133307,0.0009880645,0.00007453853,0.00010069091],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001481539,0.00014839009,0.00017946133,0.00029018195,0.0003467416,0.00033497845,0.0015217762,0.000052794614,0.0000035431892],"category_scores_gemma":[0.00014321743,0.00011985547,0.000050571343,0.0009424827,0.000034992037,0.0003788692,0.00058774697,0.00039263125,0.00002660698],"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":[0.0000047316407,0.0000280424,0.0000064822475,0.000022500111,0.000034683042,0.000005495661,0.00044047128,0.62116224,0.0034718858,0.016704435,0.00022417236,0.35789487],"study_design_scores_gemma":[0.000020486854,0.000036532267,0.00008916287,0.000056848716,0.000020466076,0.000096698604,0.00023572368,0.988884,0.0006299707,0.0014776484,0.008324574,0.00012793034],"about_ca_topic_score_codex":0.000031364183,"about_ca_topic_score_gemma":0.000007888327,"teacher_disagreement_score":0.55019766,"about_ca_system_score_codex":0.000035269928,"about_ca_system_score_gemma":0.00004719388,"threshold_uncertainty_score":0.48875642},"labels":[],"label_agreement":null},{"id":"W4387407474","doi":"10.59934/jaiea.v3i1.357","title":"Artificial Neural Network for Classification of Dengue Fever Using Backpropagation Algorithm","year":2023,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"Dengue fever; Malaria; Artificial neural network; Backpropagation; Human being; Yellow fever; Medicine; Artificial intelligence; Computer science; Virology; Immunology","score_opus":0.0656925434078984,"score_gpt":0.31593810041157194,"score_spread":0.25024555700367357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387407474","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030936277,0.00010425517,0.9678784,0.0004926651,0.00022835778,0.0002542843,0.000015643838,0.000084314815,0.0000058273],"genre_scores_gemma":[0.60670745,0.00006647151,0.39242727,0.000020666343,0.0006346403,0.0000748771,0.000032032258,0.000022268021,0.000014332938],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99859697,0.000025079698,0.0007123054,0.00022953295,0.00020223366,0.00023387896],"domain_scores_gemma":[0.99862254,0.0002751916,0.0003983716,0.00030917412,0.00030353895,0.0000911636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008118729,0.000129837,0.00021315156,0.0002959276,0.00020027497,0.000110781824,0.00043440209,0.000075918026,0.0000019135084],"category_scores_gemma":[0.000114125774,0.00013163812,0.00009070248,0.0011025886,0.0000491404,0.0003355715,0.00006609278,0.00018932945,0.000009862208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000536707,0.00005745161,0.00007758013,0.00003905523,0.000032146254,7.5469046e-7,0.00027471693,0.2684189,0.026426109,0.06739993,0.00024775363,0.63702023],"study_design_scores_gemma":[0.000021924998,0.00004739922,0.0010002352,0.000032357075,0.000031018048,0.000022348253,0.000115171,0.983255,0.0042879744,0.008378601,0.00268017,0.00012779328],"about_ca_topic_score_codex":0.000013365202,"about_ca_topic_score_gemma":0.0000022534257,"teacher_disagreement_score":0.71483606,"about_ca_system_score_codex":0.000032924247,"about_ca_system_score_gemma":0.00006528118,"threshold_uncertainty_score":0.5368047},"labels":[],"label_agreement":null},{"id":"W4387433555","doi":"10.59934/jaiea.v3i1.384","title":"Implementation of the Smart Method in Selection of Contraceptive Devices in Couples of Childbearing Age Case Study: Datar City Health Center","year":2023,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"Family planning; Agency (philosophy); Population; Wife; Government (linguistics); Family medicine; Medicine; Reproductive health; Psychology; Demography; Political science; Sociology; Environmental health; Research methodology; Law; Social science","score_opus":0.04973595209175206,"score_gpt":0.38013044567764576,"score_spread":0.3303944935858937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387433555","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":[0.5983323,0.000030991698,0.40115422,0.00021482541,0.000025816362,0.00022036686,0.000010785958,0.000008543009,0.0000021653193],"genre_scores_gemma":[0.98322076,0.00004537102,0.016679097,0.000006901018,0.000016278434,0.000022601413,0.000003403758,0.0000045988527,9.929096e-7],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9988416,0.000064125816,0.0006980179,0.00013644568,0.00014494477,0.00011489263],"domain_scores_gemma":[0.99908024,0.00018118772,0.000426038,0.00019220627,0.00008956547,0.00003078449],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001265751,0.00007127587,0.00020971378,0.00032888717,0.00005629615,0.000020635967,0.00028273335,0.000022688942,0.0000014429759],"category_scores_gemma":[0.000043539792,0.000062269275,0.000034959896,0.001135629,0.00002661568,0.00017390173,0.00008636188,0.00018271175,3.2782629e-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":[0.00002554979,0.00090192305,0.20841976,0.00024077953,0.00012270406,0.000015936306,0.025224881,0.20144199,0.015454257,0.017451206,0.000040392853,0.5306606],"study_design_scores_gemma":[0.00038983443,0.0005309085,0.5535557,0.000330267,0.000046397585,0.00025300705,0.025797246,0.3937886,0.023430275,0.0010857661,0.000525861,0.00026608977],"about_ca_topic_score_codex":0.0022925835,"about_ca_topic_score_gemma":0.0020851053,"teacher_disagreement_score":0.53039455,"about_ca_system_score_codex":0.000031217274,"about_ca_system_score_gemma":0.00006440891,"threshold_uncertainty_score":0.34657156},"labels":[],"label_agreement":null},{"id":"W4387455703","doi":"10.24843/jmat.2022.v12.i02.p153","title":"","year":2023,"lang":"","type":"article","venue":"Jurnal Matematika","topic":"Data Mining and Machine Learning 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":"WiLAN (Canada)","funders":"","keywords":"Mathematics; Statistics","score_opus":0.02751477272838946,"score_gpt":0.3025241774432975,"score_spread":0.27500940471490803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387455703","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":[0.5938593,0.00045086214,0.32929817,0.06479689,0.0030310631,0.001412181,0.00019184123,0.0052745137,0.0016851795],"genre_scores_gemma":[0.97707117,0.00063182885,0.015810363,0.0014673305,0.00065298605,0.00045402723,0.0001506214,0.000121501034,0.0036402058],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98922694,0.001049819,0.0026608075,0.0023267174,0.002130688,0.0026050198],"domain_scores_gemma":[0.9909643,0.0013053166,0.001589582,0.004467079,0.00050849095,0.0011652092],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006355448,0.0010536726,0.0013096493,0.001567518,0.0028370302,0.004584572,0.006881435,0.00036863645,0.000052478128],"category_scores_gemma":[0.001385487,0.0010356939,0.0005260059,0.01019845,0.00033741718,0.0036216239,0.003907852,0.001678868,0.008402265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012625786,0.001317694,0.019180177,0.004504731,0.0009060149,0.0013800317,0.04231257,0.03591608,0.0088983765,0.42241842,0.0864295,0.37661016],"study_design_scores_gemma":[0.0015682781,0.0005286563,0.16290496,0.0015286532,0.00014763654,0.0006387148,0.0010492827,0.8019276,0.0006539758,0.01409953,0.01344391,0.0015087714],"about_ca_topic_score_codex":0.00033799486,"about_ca_topic_score_gemma":0.0000199769,"teacher_disagreement_score":0.76601154,"about_ca_system_score_codex":0.00016121383,"about_ca_system_score_gemma":0.0005175361,"threshold_uncertainty_score":0.99920934},"labels":[],"label_agreement":null},{"id":"W4387653892","doi":"10.59934/jaiea.v3i1.396","title":"Classification For Predicting Heart Disease Using The K Nearest Neighbor Method Sylvani General Hospital Binjai City","year":2023,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Dyslipidemia; Coronary arteries; Pattern recognition (psychology); Diabetes mellitus; Artificial intelligence; Medicine; Mathematics; Computer science; Cardiology; Internal medicine; Disease; Artery","score_opus":0.05904955458637984,"score_gpt":0.34343415474508393,"score_spread":0.2843846001587041,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387653892","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044459682,0.00010728338,0.94999975,0.004729063,0.00021303237,0.00032864712,0.000023079876,0.00013329595,0.0000061393525],"genre_scores_gemma":[0.7294722,0.000050604627,0.269513,0.00009312579,0.00064313866,0.00016047923,0.000017831511,0.000022816279,0.000026738597],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874794,0.000035110395,0.00048681477,0.0002720661,0.00021001103,0.0002480534],"domain_scores_gemma":[0.99852395,0.00043505843,0.00024061468,0.00042635106,0.00021519588,0.0001588535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009575939,0.0001377854,0.0001647195,0.0002126916,0.00044842734,0.00029598153,0.00058845564,0.000049831495,0.0000015140107],"category_scores_gemma":[0.00028470554,0.00011463087,0.00009747842,0.0008538914,0.00004807599,0.00034395448,0.00010941687,0.00025373392,0.000008393379],"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":[0.000028166047,0.00024245991,0.002526065,0.00009245417,0.00010627521,0.000003558283,0.0016960723,0.46668634,0.02735633,0.28447583,0.0016678097,0.21511863],"study_design_scores_gemma":[0.000027547982,0.00005823376,0.0045942557,0.000027031221,0.000039859213,0.00001648042,0.00019156006,0.98030406,0.0006436327,0.0043704435,0.009600305,0.00012656092],"about_ca_topic_score_codex":0.00002270564,"about_ca_topic_score_gemma":0.0000010849209,"teacher_disagreement_score":0.6850126,"about_ca_system_score_codex":0.000039894963,"about_ca_system_score_gemma":0.000094615934,"threshold_uncertainty_score":0.46745113},"labels":[],"label_agreement":null},{"id":"W4387786091","doi":"10.46880/methoda.vol13no2.pp189-194","title":"PENERAPAN ALGORITMA C4.5 DALAM MENGUKUR TINGKAT KEPUASAN NASABAH PADA PT BANK MUAMALAT INDONESIA KCU MEDAN BARU BERBASIS WEB","year":2023,"lang":"en","type":"article","venue":"Majalah Ilmiah METHODA","topic":"Data Mining and Machine Learning 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":"Business; Sharia; Service (business); Product (mathematics); Service quality; Quality (philosophy); Customer satisfaction; Database; Business administration; Marketing; Computer science; Islam; Mathematics","score_opus":0.0276948109373371,"score_gpt":0.31076168787917413,"score_spread":0.283066876941837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387786091","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":[0.56797993,0.0005582287,0.37675726,0.016552934,0.003576792,0.0015901071,0.00020708975,0.007977878,0.024799787],"genre_scores_gemma":[0.50713366,0.00012288957,0.480789,0.000842618,0.00063647766,0.00045661445,0.00041221996,0.00015421424,0.009452284],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9944455,0.0010945532,0.00078737305,0.001568063,0.00091953215,0.0011849992],"domain_scores_gemma":[0.9952454,0.0012376541,0.00036117862,0.0024922993,0.00017584894,0.0004876426],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0036601268,0.00060414727,0.0006905236,0.0006090016,0.0008825228,0.0006020942,0.002806328,0.000275896,0.000105613995],"category_scores_gemma":[0.0005751244,0.0005925329,0.00027571918,0.0029772336,0.00014105633,0.00072220527,0.0013984111,0.00090325845,0.0009766088],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015974698,0.00019164255,0.013488247,0.00009136841,0.00019593252,0.0001141596,0.0037607632,0.0009542609,0.015226939,0.018107098,0.033850648,0.91400295],"study_design_scores_gemma":[0.0025803207,0.0003705145,0.074152,0.00018283301,0.00018759962,0.00021576339,0.00075531186,0.32433474,0.012058247,0.0038998644,0.5788311,0.0024317617],"about_ca_topic_score_codex":0.00036084632,"about_ca_topic_score_gemma":0.00006156268,"teacher_disagreement_score":0.9115712,"about_ca_system_score_codex":0.000107306754,"about_ca_system_score_gemma":0.0002635103,"threshold_uncertainty_score":0.9998012},"labels":[],"label_agreement":null},{"id":"W4388002338","doi":"10.52303/jb.v5i2.115","title":"Aplikasi Sistem Pendukung Keputusan Menggunakan Algoritma C5 Untuk Menentukan Penerima Bantuan Sosial","year":2023,"lang":"en","type":"article","venue":"Jurnal Ilmiah Binary STMIK Bina Nusantara Jaya Lubuklinggau","topic":"Data Mining and Machine Learning 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":"WiLAN (Canada)","funders":"","keywords":"Poverty; Underdevelopment; Unemployment; Settlement (finance); Selection (genetic algorithm); Social assistance; Business; Operations management; Economic growth; Computer science; Engineering; Economics; Artificial intelligence; Finance","score_opus":0.018962813083599518,"score_gpt":0.273473503354432,"score_spread":0.25451069027083245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388002338","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":[0.9131055,0.00128127,0.03606521,0.012636038,0.0062919497,0.0016839379,0.00028526623,0.0064753965,0.022175428],"genre_scores_gemma":[0.97722244,0.00060956995,0.014796201,0.0008000057,0.0011628871,0.00024009794,0.00077863876,0.00018066076,0.0042095203],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9931058,0.0004395497,0.0012540765,0.0020000434,0.0013936069,0.0018069032],"domain_scores_gemma":[0.99548095,0.00044196396,0.0006564983,0.0023695491,0.00024786766,0.0008031425],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015992065,0.00093852595,0.00092749874,0.001058833,0.0017693918,0.0011554738,0.0037160043,0.00036094445,0.00009796594],"category_scores_gemma":[0.00013651774,0.0009361123,0.00047444925,0.0030753352,0.00026382608,0.0017802033,0.0016778914,0.0013956671,0.001467205],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007586414,0.0035341557,0.013508834,0.00079095404,0.001549421,0.0048373137,0.014115805,0.015812512,0.082509734,0.13388665,0.21067502,0.518021],"study_design_scores_gemma":[0.0050210897,0.0028014574,0.06520167,0.0006207095,0.00037449918,0.0012914534,0.0015893212,0.4036491,0.0046362104,0.0041799457,0.5064356,0.0041989787],"about_ca_topic_score_codex":0.00050159293,"about_ca_topic_score_gemma":0.000040887746,"teacher_disagreement_score":0.51382196,"about_ca_system_score_codex":0.00034088315,"about_ca_system_score_gemma":0.00047434212,"threshold_uncertainty_score":0.99988145},"labels":[],"label_agreement":null},{"id":"W4388426509","doi":"10.33480/techno.v20i2.4613","title":"COMPARISON OF KNN, NAIVE BAYES, DECISION TREE, ENSEMBLE, REGRESSION METHODS FOR INCOME PREDICTION","year":2023,"lang":"en","type":"article","venue":"Jurnal Techno Nusa Mandiri","topic":"Data Mining and Machine Learning 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":"Decision tree; Naive Bayes classifier; Computer science; Machine learning; Artificial intelligence; Marital status; Data mining; Support vector machine; Econometrics; Mathematics; Demography","score_opus":0.04245837613401201,"score_gpt":0.43107834020490904,"score_spread":0.38861996407089705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388426509","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03902858,0.00013333844,0.95819926,0.00053660467,0.00033361145,0.00030965483,0.00003101335,0.0008147238,0.0006132024],"genre_scores_gemma":[0.4736717,0.00005792205,0.52570647,0.000019629226,0.00006447091,0.00010479523,0.00006318966,0.000018466644,0.00029332755],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99834406,0.00008084022,0.0005234059,0.0004603514,0.00031916928,0.00027218653],"domain_scores_gemma":[0.9977546,0.0008351526,0.000363528,0.0008224342,0.00013535297,0.00008892956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001302749,0.00016888317,0.0003342553,0.00053904613,0.0003044616,0.00008228975,0.0009812558,0.00015217398,0.0000027858243],"category_scores_gemma":[0.000534309,0.00014010201,0.00011462133,0.0013415688,0.000046081823,0.00029729426,0.00042191197,0.00030163737,0.000028030234],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003775339,0.0000848054,0.00524518,0.000039838207,0.000020268722,0.0000014750726,0.00032754784,0.00030206123,0.008049244,0.01193169,0.014111378,0.95984876],"study_design_scores_gemma":[0.0010886868,0.0006604135,0.034504533,0.00047787715,0.000050813214,0.000032478787,0.00017130624,0.808791,0.026106149,0.030492388,0.09729093,0.00033342093],"about_ca_topic_score_codex":0.000017207856,"about_ca_topic_score_gemma":0.0000042225265,"teacher_disagreement_score":0.95951533,"about_ca_system_score_codex":0.00004776606,"about_ca_system_score_gemma":0.000045490673,"threshold_uncertainty_score":0.5713194},"labels":[],"label_agreement":null},{"id":"W4389507606","doi":"10.32493/inovasi.v10i2.p479-487.36202","title":"Analisis Pemilihan Merchant Menggunakan Metode Segmentation Model Two Step Clustering pada Bank X","year":2023,"lang":"id","type":"article","venue":"INOVASI","topic":"Data Mining and Machine Learning 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":"WiLAN (Canada)","funders":"","keywords":"Humanities; Physics; Art","score_opus":0.04877756835809113,"score_gpt":0.33058388843312686,"score_spread":0.2818063200750357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389507606","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":[0.10383897,0.00019041749,0.8856957,0.004097951,0.00076957786,0.0005083425,0.0001809138,0.0010298702,0.0036882637],"genre_scores_gemma":[0.9226299,0.00022531368,0.070776045,0.0006567482,0.00034492172,0.00020599827,0.00057716214,0.00007878369,0.0045051295],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966047,0.00022511884,0.00062134553,0.0010755843,0.0007028766,0.0007703998],"domain_scores_gemma":[0.997717,0.00022565702,0.00028563442,0.0013562326,0.00016626561,0.00024920577],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012573057,0.00039789773,0.00039283844,0.0005009735,0.0006069636,0.0005280768,0.0013145516,0.00011930203,0.000044327287],"category_scores_gemma":[0.00011253618,0.0004297202,0.00015878685,0.0020025389,0.00008867701,0.00067036954,0.0010702516,0.00050382357,0.0008681276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058471316,0.00041336857,0.0021227128,0.00040744184,0.0006604909,0.00010771666,0.030950876,0.3404199,0.034413036,0.012574135,0.05484359,0.52302825],"study_design_scores_gemma":[0.0006529067,0.00008076875,0.0015012948,0.00009788924,0.00009863013,0.000018590084,0.00070977275,0.9893926,0.0014921082,0.0002912083,0.0051966566,0.00046761945],"about_ca_topic_score_codex":0.0013247643,"about_ca_topic_score_gemma":0.00042382776,"teacher_disagreement_score":0.8187909,"about_ca_system_score_codex":0.00015629937,"about_ca_system_score_gemma":0.00021947038,"threshold_uncertainty_score":0.9999098},"labels":[],"label_agreement":null},{"id":"W4390402833","doi":"10.34123/icdsos.v2023i1.384","title":"Comparative Analysis of Retriever and Reader for Open Domain Questions Answering on BPS Knowledge in Indonesian","year":2023,"lang":"en","type":"article","venue":"Proceedings of The International Conference on Data Science and Official Statistics","topic":"Data Mining and Machine Learning 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":"Question answering; Computer science; Information retrieval; Open domain; Domain (mathematical analysis); Indonesian; Labrador Retriever; World Wide Web; Natural language processing; Linguistics; Medicine; Mathematics","score_opus":0.13102030798385447,"score_gpt":0.409913994277417,"score_spread":0.2788936862935625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390402833","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":[0.8574822,0.00001996066,0.11075534,0.008653709,0.00043260373,0.0012150975,0.0065299133,0.00007276074,0.014838401],"genre_scores_gemma":[0.9811466,0.00002374806,0.018639263,0.00004553581,0.000010758652,0.000014457712,0.0000643597,0.000002071321,0.00005325002],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998979,0.0000075096136,0.00021206854,0.00037041007,0.0003158616,0.00011514909],"domain_scores_gemma":[0.998875,0.000235686,0.00018062994,0.00020861145,0.00046221982,0.00003784068],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011461806,0.000071715556,0.00016923166,0.00039254728,0.00016747855,0.00025521085,0.0025650384,0.000020187781,0.0000015055844],"category_scores_gemma":[0.00067218073,0.000057360856,0.000009368126,0.0015694561,0.0003077971,0.00051351683,0.0013136737,0.00009348063,8.9508507e-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":[0.000023138451,0.000051539202,0.0020819556,0.000006932011,0.000026417541,8.584398e-8,0.001036822,0.000051889936,0.0011282393,0.9900524,0.0012264824,0.0043140873],"study_design_scores_gemma":[0.00034931238,0.00016373288,0.13594534,0.00014490094,0.000048901198,0.0000010000305,0.0013142874,0.84195507,0.0008724554,0.017312866,0.0017316586,0.00016048702],"about_ca_topic_score_codex":0.00015454523,"about_ca_topic_score_gemma":0.00017008865,"teacher_disagreement_score":0.9727395,"about_ca_system_score_codex":0.000025770936,"about_ca_system_score_gemma":0.00017577846,"threshold_uncertainty_score":0.47665223},"labels":[],"label_agreement":null},{"id":"W4390719718","doi":"10.24815/jts.v12i2.32097","title":"ANALISA DERET WAKTU CURAH HUJAN DAN KARAKTERISTIK IKLIM DI KOTA MAJALENGKA","year":2023,"lang":"id","type":"article","venue":"Jurnal Teknik Sipil","topic":"Data Mining and Machine Learning 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":"Encana (Canada)","funders":"","keywords":"Physics","score_opus":0.029240995359646763,"score_gpt":0.29823446345855004,"score_spread":0.2689934680989033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390719718","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":[0.888136,0.0018195953,0.043333173,0.027031057,0.004906687,0.0011124344,0.0008970392,0.003770731,0.028993277],"genre_scores_gemma":[0.9634634,0.000722801,0.0030308354,0.0010893206,0.0014918194,0.00011228585,0.0005995693,0.00013763864,0.02935229],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948854,0.00040363555,0.000938276,0.0014376997,0.0010105036,0.0013245165],"domain_scores_gemma":[0.99587005,0.00045409094,0.00055765687,0.0022414636,0.00021269043,0.0006640563],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012660119,0.0006488088,0.00065303454,0.0005152064,0.0011569884,0.001259398,0.0030194153,0.00027184864,0.00010121008],"category_scores_gemma":[0.00040811306,0.0006523266,0.0003282702,0.0024818664,0.00028306563,0.0007988558,0.001463338,0.0013352827,0.0054680835],"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":[0.00009002269,0.0009908809,0.03635454,0.0004357509,0.0005749851,0.000746712,0.0067553376,0.00063202577,0.0078100082,0.026597273,0.54422444,0.37478805],"study_design_scores_gemma":[0.0010933767,0.00048653025,0.16300751,0.00033831914,0.00014663757,0.0002631121,0.0005161999,0.049243916,0.00052443927,0.00069457333,0.782412,0.0012733807],"about_ca_topic_score_codex":0.00026990118,"about_ca_topic_score_gemma":0.00005025833,"teacher_disagreement_score":0.37351465,"about_ca_system_score_codex":0.00015344171,"about_ca_system_score_gemma":0.0003653413,"threshold_uncertainty_score":0.9997774},"labels":[],"label_agreement":null},{"id":"W4390974934","doi":"10.5267/j.ijdns.2024.1.004","title":"Deep learning approaches to predict sea surface height above geoid in Pekalongan","year":2024,"lang":"en","type":"article","venue":"International Journal of Data and Network Science","topic":"Data Mining and Machine Learning 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":"Universitas Padjadjaran","keywords":"Artificial neural network; Marine ecosystem; Ecosystem; Computer science; Term (time); Geoid; Meteorology; Artificial intelligence; Environmental science; Environmental resource management; Geography; Geology; Ecology; Geophysics","score_opus":0.053802655216782735,"score_gpt":0.3082655685391671,"score_spread":0.25446291332238435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390974934","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":[0.0826822,0.0020554536,0.9051959,0.007875183,0.0012208446,0.00008435115,0.000024240158,0.00006073121,0.000801104],"genre_scores_gemma":[0.9209529,0.00019414377,0.07826995,0.00013705941,0.0003459155,0.0000011920439,0.000017067017,0.0000053944973,0.00007636359],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983755,0.000054226493,0.00029576969,0.0004235114,0.000621692,0.0002293079],"domain_scores_gemma":[0.9990756,0.00021883455,0.00010557582,0.0003504102,0.00009961523,0.00014995901],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025312093,0.000090649315,0.00011698933,0.00023619737,0.00012870108,0.00088287506,0.003528234,0.000023277262,0.000004556278],"category_scores_gemma":[0.00018877083,0.00007514299,0.000020064314,0.00088519696,0.00011120759,0.0022274721,0.0012839966,0.0003863948,0.00001334303],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029619125,0.00009256056,0.04515187,0.000015980095,0.000074311145,0.00018192102,0.00306852,0.23186257,0.00026903726,0.04057381,0.006344877,0.6723349],"study_design_scores_gemma":[0.00011079024,0.00006892826,0.014687559,0.00015159752,0.0000052433757,0.00025862362,0.000060694045,0.94650257,0.000021616275,0.000855912,0.03717458,0.00010188045],"about_ca_topic_score_codex":0.000030134688,"about_ca_topic_score_gemma":0.000025489016,"teacher_disagreement_score":0.8382707,"about_ca_system_score_codex":0.00004742786,"about_ca_system_score_gemma":0.0001938352,"threshold_uncertainty_score":0.8513585},"labels":[],"label_agreement":null},{"id":"W4391359236","doi":"10.20956/ejsa.v5i1.12489","title":"Pendugaan Koefisien Regresi Logistik Biner Menggunakan Algoritma Least Angle Regression","year":2024,"lang":"en","type":"article","venue":"ESTIMASI Journal of Statistics and Its Application","topic":"Data Mining and Machine Learning 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":"WiLAN (Canada)","funders":"","keywords":"Mathematics","score_opus":0.01698570667548426,"score_gpt":0.29863740016989626,"score_spread":0.281651693494412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391359236","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001641327,0.0018353699,0.99315655,0.0023883807,0.00019046616,0.00012420278,0.00006874917,0.00007740575,0.0005175296],"genre_scores_gemma":[0.685241,0.00045950638,0.31326184,0.00007916898,0.00023443146,0.000017852759,0.0000712995,0.000022303144,0.000612633],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987435,0.000046569505,0.000405882,0.0003151738,0.00031069928,0.00017818333],"domain_scores_gemma":[0.99883604,0.000198368,0.00027650796,0.00030183353,0.0002282903,0.00015898605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053556496,0.00015423047,0.00018970492,0.00018618799,0.00018106472,0.0003063707,0.0004672981,0.000058777205,0.000010892146],"category_scores_gemma":[0.00014366172,0.000119207696,0.000034033907,0.00033540963,0.00005108326,0.00042106735,0.0001228777,0.00032925856,0.000038420098],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000064772807,0.000055729026,0.00010725971,0.00006151557,0.000024673389,0.000030384033,0.00032592006,0.00017800828,0.002111482,0.41977438,0.017779427,0.55954474],"study_design_scores_gemma":[0.00043343473,0.00041113477,0.0063351383,0.00024787596,0.00007621403,0.0006183861,0.00005486618,0.769424,0.0006191752,0.02802371,0.1933962,0.00035985644],"about_ca_topic_score_codex":0.000020741005,"about_ca_topic_score_gemma":0.0000023512882,"teacher_disagreement_score":0.769246,"about_ca_system_score_codex":0.00003628763,"about_ca_system_score_gemma":0.00010145368,"threshold_uncertainty_score":0.48611486},"labels":[],"label_agreement":null},{"id":"W4391487553","doi":"10.30998/jrami.v5i1.10605","title":"Sistem Pakar untuk Identifikasi Fase Quarter Life Crisis pada Usia 20-29 Tahun Menggunakan Algoritma Certainty Factor","year":2024,"lang":"id","type":"article","venue":"Jurnal Riset dan Aplikasi Mahasiswa Informatika (JRAMI)","topic":"Data Mining and Machine Learning 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":"Quarter (Canadian coin); Computer science; History","score_opus":0.016506658649001957,"score_gpt":0.27314171010656013,"score_spread":0.25663505145755816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391487553","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":[0.4220843,0.01097659,0.38911048,0.053277675,0.025529,0.008290691,0.017701298,0.00991325,0.06311672],"genre_scores_gemma":[0.96222186,0.0010948248,0.018092077,0.0053653466,0.0019792705,0.00056725653,0.0030877772,0.0003555206,0.0072360598],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98831356,0.0006643526,0.003774436,0.002107381,0.0026635933,0.0024767006],"domain_scores_gemma":[0.9910164,0.00096952997,0.0014742622,0.0037847792,0.0006753491,0.0020796792],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0019944026,0.0018760804,0.0017179064,0.0014007058,0.001794008,0.009350159,0.0045661647,0.000848913,0.00077645335],"category_scores_gemma":[0.00054050144,0.0017823603,0.0012214851,0.0029349201,0.00042156456,0.006157295,0.0016873964,0.0035285826,0.0064350297],"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":[0.00015238715,0.0008069481,0.0010488584,0.0027146812,0.0018346895,0.00058340107,0.029505411,0.00084650714,0.0003391303,0.016222132,0.63472074,0.3112251],"study_design_scores_gemma":[0.0016078682,0.0006450238,0.004078831,0.001088037,0.00057259353,0.00062063645,0.009483704,0.20138271,0.00039550738,0.0004461461,0.7771914,0.0024875472],"about_ca_topic_score_codex":0.0007458517,"about_ca_topic_score_gemma":0.00014343145,"teacher_disagreement_score":0.5401375,"about_ca_system_score_codex":0.00072490354,"about_ca_system_score_gemma":0.0014589116,"threshold_uncertainty_score":0.9995055},"labels":[],"label_agreement":null},{"id":"W4391938375","doi":"10.59697/jtik.v6i2.299","title":"DATA MINING PENGELOMPOKAN INDUSTRI KECIL DAN MENENGAH BERDASARKAN HASIL PRODUKSI MENGGUNAKAN METODE CLUSTERING DI KABUPATEN LANGKAT","year":2022,"lang":"id","type":"article","venue":"JTIK (Jurnal Teknik Informatika Kaputama)","topic":"Data Mining and Machine Learning 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":"Cluster analysis; Mathematics; Statistics","score_opus":0.06936193266199289,"score_gpt":0.29842058222492684,"score_spread":0.22905864956293395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391938375","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":[0.6257701,0.005630861,0.102547325,0.041050952,0.013749068,0.008566604,0.016726792,0.006874305,0.17908402],"genre_scores_gemma":[0.9387975,0.00027429708,0.036666855,0.0020981487,0.0019052932,0.00069676613,0.008262549,0.00031441092,0.010984219],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99020326,0.00090321543,0.0024095913,0.0018849456,0.0026099202,0.0019890834],"domain_scores_gemma":[0.9906562,0.00060513604,0.0019903365,0.005561018,0.00030139575,0.00088589115],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":["open_science"],"category_scores_codex":[0.005165749,0.0011780269,0.0012083052,0.0009870417,0.00413817,0.0023874617,0.010660224,0.00034163837,0.000304607],"category_scores_gemma":[0.0007083326,0.001253295,0.000288229,0.0024937475,0.00027198804,0.0049854377,0.016081033,0.00409912,0.00044597176],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026238512,0.0012340556,0.008677363,0.00073039107,0.0013656141,0.0003005847,0.057447094,0.020355351,0.0011352478,0.0017452821,0.25240907,0.6543375],"study_design_scores_gemma":[0.0017482297,0.0005833152,0.005376228,0.00025718982,0.00023480799,0.0008340579,0.0064662965,0.33766258,0.00021913457,0.00003311797,0.6450994,0.001485637],"about_ca_topic_score_codex":0.00047584902,"about_ca_topic_score_gemma":0.00012974262,"teacher_disagreement_score":0.6528519,"about_ca_system_score_codex":0.0007702522,"about_ca_system_score_gemma":0.0012938723,"threshold_uncertainty_score":0.99899167},"labels":[],"label_agreement":null},{"id":"W4392200058","doi":"10.18280/isi.290118","title":"Labeling Consistency Test of Multi-Label Data for Aspect and Sentiment Classification Using the Cohen Kappa Method","year":2024,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Data Mining and Machine Learning 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":"Universitas Diponegoro","keywords":"Kappa; Consistency (knowledge bases); Computer science; Class (philosophy); Artificial intelligence; Process (computing); Labeled data; Cohen's kappa; Test data; Data mining; Machine learning; Pattern recognition (psychology); Natural language processing; Mathematics","score_opus":0.08785438586259763,"score_gpt":0.3523426165322655,"score_spread":0.26448823066966787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392200058","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028904558,0.00044898002,0.99510634,0.00035779888,0.00014368136,0.00039768047,0.00020584092,0.00015299358,0.00029624233],"genre_scores_gemma":[0.29755938,0.000025960559,0.70191896,0.00006438139,0.000027933167,0.00005256318,0.00031336382,0.000007630127,0.000029834451],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990108,0.000056972625,0.00043041815,0.00021168597,0.00014810057,0.00014202703],"domain_scores_gemma":[0.9982783,0.0005979587,0.00022030021,0.00071137265,0.00015913368,0.000032933334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001348836,0.00010491355,0.00012701326,0.00012866817,0.00034829343,0.0004926827,0.0005756801,0.000044821416,0.0000011669686],"category_scores_gemma":[0.00055985886,0.00008161839,0.00001937812,0.00035973964,0.00009226314,0.0019887174,0.00028855144,0.00010258145,0.0000065310037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000049754512,0.00005464034,0.00033949758,0.00071034825,0.00009521963,3.5015486e-7,0.007537483,0.0005399381,0.009787137,0.09624207,0.00093006645,0.88375825],"study_design_scores_gemma":[0.00017562335,0.000034427983,0.00040189372,0.00013771154,0.000044385193,0.000028658114,0.00046759113,0.9925012,0.0003959682,0.0012205106,0.004497693,0.000094335854],"about_ca_topic_score_codex":0.00009636152,"about_ca_topic_score_gemma":0.000004356448,"teacher_disagreement_score":0.99196124,"about_ca_system_score_codex":0.000057218716,"about_ca_system_score_gemma":0.00012131699,"threshold_uncertainty_score":0.47509506},"labels":[],"label_agreement":null},{"id":"W4393021754","doi":"10.58169/jwikal.v1i2.85","title":"Pemanfaatan Analisis Sig Untuk Pemetaan Potensi Air Tanah Di Kabupaten Keerom","year":2022,"lang":"id","type":"article","venue":"JURNAL WILAYAH KOTA DAN LINGKUNGAN BERKELANJUTAN","topic":"Data Mining and Machine Learning 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":"Encana (Canada); WiLAN (Canada)","funders":"","keywords":"Forestry; Physics; Humanities; Geography","score_opus":0.01434284218366586,"score_gpt":0.2516627936304627,"score_spread":0.23731995144679682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393021754","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":[0.94523,0.002909885,0.010475221,0.021949712,0.0046737264,0.0013957258,0.0022195447,0.0015455097,0.009600677],"genre_scores_gemma":[0.98654634,0.0001627792,0.0024861824,0.00274798,0.0013164473,0.0001487677,0.0012074368,0.00026732066,0.005116756],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98897415,0.0015569286,0.0019166735,0.0028598444,0.0026004997,0.0020918709],"domain_scores_gemma":[0.99202555,0.00065203325,0.0015876627,0.003980515,0.00047929143,0.0012749509],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.002720004,0.0013343735,0.0015168434,0.0010564212,0.0046137497,0.0012778976,0.005984324,0.00032027176,0.00026851523],"category_scores_gemma":[0.00046665137,0.0014703296,0.00081818487,0.0035952814,0.00041603067,0.0010471662,0.0038141657,0.004066471,0.00037453906],"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":[0.0015505031,0.010368956,0.24240452,0.0010771503,0.008898943,0.0076280697,0.051262196,0.07902913,0.047775127,0.06903259,0.29797834,0.18299448],"study_design_scores_gemma":[0.004515537,0.004167475,0.21296449,0.0004695298,0.0026203056,0.0036584544,0.0076808394,0.15704973,0.0019727838,0.0011230741,0.5975328,0.006244996],"about_ca_topic_score_codex":0.00085474335,"about_ca_topic_score_gemma":0.00010010266,"teacher_disagreement_score":0.29955444,"about_ca_system_score_codex":0.0007569204,"about_ca_system_score_gemma":0.00085000286,"threshold_uncertainty_score":0.99994075},"labels":[],"label_agreement":null},{"id":"W4394938811","doi":"10.5267/j.ijdns.2024.1.016","title":"Neuroinformatics approach: Hierarchical cluster analysis of indonesian provinces based on people's welfare indicators in the realm of data science and network studies","year":2024,"lang":"en","type":"article","venue":"International Journal of Data and Network Science","topic":"Data Mining and Machine Learning 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":"Direktorat Riset dan Pengabdian Masyarakat; Universitas Padjadjaran","keywords":"Indonesian; Realm; Cluster (spacecraft); Neuroinformatics; Regional science; Welfare; Data science; Geography; Computer science; Political science; Law","score_opus":0.03720505541214228,"score_gpt":0.34879381920707303,"score_spread":0.3115887637949307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394938811","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":[0.46737334,0.0023813387,0.4884341,0.037344817,0.00141632,0.0006180718,0.000792363,0.000053040163,0.0015866017],"genre_scores_gemma":[0.9639603,0.00023026981,0.03541485,0.0002606052,0.00008649582,0.0000016243869,0.000042383166,0.0000023555526,0.0000011260798],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973885,0.000099584584,0.0005308696,0.00040223042,0.0013846746,0.00019416133],"domain_scores_gemma":[0.99763227,0.0007324225,0.00039958674,0.0009382131,0.00022546768,0.00007204761],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.008037339,0.00009641275,0.00024344095,0.001153446,0.0002162324,0.00042442762,0.006982337,0.000019918685,5.7437586e-7],"category_scores_gemma":[0.00054775993,0.000060178296,0.000022875603,0.005618055,0.0010501135,0.0026703004,0.0021673522,0.000297172,1.1382509e-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":[0.00015094054,0.00045506973,0.12597583,0.00020268498,0.0007212682,0.000041805764,0.01205989,0.142661,0.00003564798,0.16135396,0.0056326077,0.5507093],"study_design_scores_gemma":[0.000116788695,0.00008719484,0.07101557,0.00012126675,0.00007046389,0.000038289465,0.00025701046,0.92645717,0.0000015370206,0.0002045988,0.0015686504,0.00006148076],"about_ca_topic_score_codex":0.000021647651,"about_ca_topic_score_gemma":0.000032058862,"teacher_disagreement_score":0.78379613,"about_ca_system_score_codex":0.000024913596,"about_ca_system_score_gemma":0.0004959459,"threshold_uncertainty_score":0.9983904},"labels":[],"label_agreement":null},{"id":"W4395093169","doi":"10.29313/bcsurp.v4i1.10929","title":"Identifikasi Kerentanan Bencana Bajir di Kecamatan Bojoangsoang Kabupaten Bandung","year":2024,"lang":"en","type":"article","venue":"Bandung Conference Series Urban & Regional Planning","topic":"Data Mining and Machine Learning 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":"Encana (Canada)","funders":"","keywords":"Forestry; Environmental science; Physics; Geography","score_opus":0.032940953370885394,"score_gpt":0.27993213160979974,"score_spread":0.24699117823891434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395093169","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":[0.16636534,0.013753042,0.7314889,0.021133773,0.005052077,0.0013593227,0.00038123864,0.0073081353,0.053158212],"genre_scores_gemma":[0.9841536,0.00008304306,0.0052707535,0.00021096636,0.00035929665,0.00009236062,0.0004986354,0.00004873732,0.009282569],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99702084,0.00010910171,0.00049533416,0.0010939764,0.00059437903,0.00068635575],"domain_scores_gemma":[0.9982466,0.00024280757,0.00015565686,0.00092562736,0.00014397991,0.00028532906],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00042494593,0.00042790262,0.00036901658,0.00033468075,0.00060260744,0.0018470918,0.0015573803,0.00014984711,0.00007876752],"category_scores_gemma":[0.00006905595,0.00040642868,0.00015065534,0.00077718316,0.00019106542,0.0020648744,0.00042729362,0.0006369011,0.00015960529],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052558273,0.00008357481,0.015971217,0.00023840755,0.0002771827,0.0004906403,0.009119736,0.00031218745,0.0028802666,0.7333539,0.19322395,0.043996368],"study_design_scores_gemma":[0.0007180017,0.00034642336,0.079753935,0.0025508825,0.00016970992,0.0009907458,0.002068411,0.09508728,0.0010934549,0.009821858,0.80525166,0.0021476448],"about_ca_topic_score_codex":0.00030525253,"about_ca_topic_score_gemma":0.000045241235,"teacher_disagreement_score":0.8177883,"about_ca_system_score_codex":0.000102490485,"about_ca_system_score_gemma":0.00035458448,"threshold_uncertainty_score":0.99983877},"labels":[],"label_agreement":null},{"id":"W4395112667","doi":"10.18280/ria.380222","title":"Supervised Machine Learning Entity Sentiment Analysis: Prediction of Support for 2024 Indonesian Presidential Candidates","year":2024,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Data Mining and Machine Learning 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":"Indonesian; Sentiment analysis; Presidential system; Artificial intelligence; Computer science; Natural language processing; Machine learning; Political science; Linguistics; Politics","score_opus":0.02197993026861135,"score_gpt":0.2828063807510679,"score_spread":0.26082645048245656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395112667","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":[0.015478838,0.00037448408,0.9819997,0.0004111547,0.00044765696,0.0003034721,0.00014381178,0.00025324992,0.0005876587],"genre_scores_gemma":[0.98462486,0.000060149585,0.007470559,0.000014136421,0.00008162213,0.00010062285,0.0003192616,0.000014773734,0.0073139966],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99839604,0.00007209978,0.0005001025,0.0005706529,0.00020497954,0.0002561319],"domain_scores_gemma":[0.99896705,0.00019323408,0.000106518055,0.00055384944,0.00009704246,0.000082330145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072031823,0.00014743638,0.00023593342,0.0004100013,0.00018784501,0.00026460178,0.00057028956,0.00006113057,0.00022377606],"category_scores_gemma":[0.0000829882,0.00014654637,0.0002220667,0.001310099,0.000049702,0.0003485371,0.00017594945,0.00021498278,0.00012660933],"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":[0.000102408645,0.0011563618,0.06152843,0.0020026895,0.0033783317,0.000047781617,0.01963859,0.47811544,0.045329373,0.10565604,0.015319403,0.26772514],"study_design_scores_gemma":[0.000034235476,0.00012764159,0.0003687519,0.000048260015,0.0002441353,0.000007452157,0.0001198111,0.9590429,0.022860773,0.0004372427,0.016590241,0.00011857187],"about_ca_topic_score_codex":0.00029102337,"about_ca_topic_score_gemma":0.000049540067,"teacher_disagreement_score":0.9745291,"about_ca_system_score_codex":0.00003362884,"about_ca_system_score_gemma":0.00007461927,"threshold_uncertainty_score":0.5975988},"labels":[],"label_agreement":null},{"id":"W4395463128","doi":"10.18280/isi.290205","title":"Sentiment Analysis: Classifying Public Comments on YouTube in Disaster Management Simulation in Indonesia Using Naïve Bayes and Support Vector Machine","year":2024,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Data Mining and Machine Learning 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":"Universitas Diponegoro","keywords":"Naive Bayes classifier; Support vector machine; Sentiment analysis; Computer science; Bayes' theorem; Emergency management; Artificial intelligence; Machine learning; Bayesian probability; Political science","score_opus":0.025753812257756213,"score_gpt":0.2888518961292369,"score_spread":0.2630980838714807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395463128","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":[0.32761028,0.000059050264,0.6702976,0.0003530456,0.00013455724,0.00033914382,0.00001672683,0.00018328794,0.0010062666],"genre_scores_gemma":[0.9927053,0.00001025383,0.006811574,0.00017350478,0.000010957696,0.00005674591,0.00020666445,0.000007241975,0.000017774573],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986055,0.00009010983,0.00052917236,0.00026310375,0.0002624647,0.0002496718],"domain_scores_gemma":[0.99934,0.000089713256,0.00013130544,0.00034789715,0.00003291143,0.00005820393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061324757,0.00016336658,0.00018705764,0.0014160951,0.00012988583,0.0009890813,0.00028889682,0.00005822576,0.0000051402117],"category_scores_gemma":[0.00002537628,0.00015760306,0.000043171414,0.0016399169,0.000027437083,0.0034277872,0.00023821804,0.00017664857,0.00002289392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002181419,0.00019625569,0.15106478,0.0008150203,0.0004809097,0.000032002314,0.031140763,0.16674301,0.000037523285,0.06677871,0.00008679291,0.5826024],"study_design_scores_gemma":[0.00026682677,0.000028732702,0.0855487,0.00015323733,0.00003261747,0.0000043453947,0.0003057835,0.91236126,0.000009135919,0.00033799376,0.0007990355,0.00015233949],"about_ca_topic_score_codex":0.00008102743,"about_ca_topic_score_gemma":0.000022373308,"teacher_disagreement_score":0.7456182,"about_ca_system_score_codex":0.0003394261,"about_ca_system_score_gemma":0.000029499019,"threshold_uncertainty_score":0.9537734},"labels":[],"label_agreement":null},{"id":"W4399542840","doi":"10.62828/jpb.v3i2.104","title":"8. SEGMENTASI TINGGI BADAN DAN BERAT BADAN KADET MAHASISWA MENGGUNAKAN K-MEANS CLUSTERING","year":2024,"lang":"id","type":"article","venue":"TNI Angkatan Udara","topic":"Data Mining and Machine Learning 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":"Innovation Cluster (Canada)","funders":"","keywords":"Humanities; Physics; Philosophy","score_opus":0.01682313875548924,"score_gpt":0.2804938767749291,"score_spread":0.26367073801943985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399542840","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":[0.060617995,0.014242558,0.7366104,0.030678945,0.010814202,0.0022950852,0.0012464835,0.0062463437,0.137248],"genre_scores_gemma":[0.92187834,0.0003604037,0.03586974,0.0018502306,0.001449347,0.00018585646,0.0010709694,0.00028042038,0.0370547],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9947628,0.0003367124,0.0009070746,0.001988564,0.00076015235,0.0012447058],"domain_scores_gemma":[0.99658495,0.00033555724,0.000220881,0.0022854472,0.00009736069,0.00047582437],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011919877,0.0007860455,0.0006178498,0.00051384757,0.001027871,0.0030912415,0.0023748067,0.00028498264,0.00019321029],"category_scores_gemma":[0.000094961484,0.0008232835,0.0002998634,0.0016915483,0.00026486578,0.0010798527,0.0015280358,0.0014220009,0.0019299359],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005764254,0.0006293593,0.0019279773,0.0014549616,0.0009808077,0.0008191132,0.019028338,0.0007048792,0.01194481,0.07071549,0.19635546,0.69538116],"study_design_scores_gemma":[0.0005906841,0.00029466854,0.002201208,0.0012462758,0.00025915637,0.0002916973,0.0010477552,0.23280974,0.0009953032,0.00036342422,0.7587297,0.0011704069],"about_ca_topic_score_codex":0.0004912344,"about_ca_topic_score_gemma":0.00028045144,"teacher_disagreement_score":0.86126035,"about_ca_system_score_codex":0.00038524996,"about_ca_system_score_gemma":0.00045146348,"threshold_uncertainty_score":0.9994218},"labels":[],"label_agreement":null},{"id":"W4399571588","doi":"10.46880/mtk.v10i1.2811","title":"ANALISIS CLUSTERING STUNTING DENGAN DISTANCE EUCLID","year":2024,"lang":"en","type":"article","venue":"METHODIKA Jurnal Teknik Informatika dan Sistem Informasi","topic":"Data Mining and Machine Learning 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":"Malnutrition; Government (linguistics); Cluster analysis; Cluster (spacecraft); Environmental health; Population; Developing country; Geography; Business; Medicine; Economic growth; Computer science; Artificial intelligence; Economics","score_opus":0.021437874536998053,"score_gpt":0.3044356924922677,"score_spread":0.2829978179552697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399571588","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042771194,0.0004832074,0.93722075,0.0006998844,0.00073571474,0.00025621016,0.000013439404,0.0014194606,0.054894198],"genre_scores_gemma":[0.49459305,0.00032771996,0.5011805,0.0017089122,0.00037766917,0.000173738,0.00015680646,0.00007317709,0.0014083749],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99662876,0.00015193534,0.0013124085,0.00042533278,0.0007282494,0.0007533347],"domain_scores_gemma":[0.99743164,0.0005365894,0.0003985168,0.001159821,0.00016128547,0.00031216664],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002824883,0.00042953755,0.00044134317,0.00052458403,0.0007108614,0.002729062,0.0019658154,0.00013706271,0.0000063037683],"category_scores_gemma":[0.00035219372,0.00037787744,0.00027059752,0.0015436638,0.00008719557,0.0058658356,0.0008857387,0.00092952757,0.00015570926],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012632777,0.00003220325,0.0008848304,0.00064054556,0.00013222975,0.000028497667,0.008497707,0.0020983198,0.00017193325,0.20470056,0.0019875772,0.780813],"study_design_scores_gemma":[0.00023706614,0.00007105024,0.0015441932,0.00035616875,0.000034894525,0.0003215065,0.0009671017,0.34795693,0.0010393797,0.00018701807,0.64676046,0.0005242212],"about_ca_topic_score_codex":0.000017150174,"about_ca_topic_score_gemma":0.0000106611715,"teacher_disagreement_score":0.78028876,"about_ca_system_score_codex":0.0001803167,"about_ca_system_score_gemma":0.00020702906,"threshold_uncertainty_score":0.9998673},"labels":[],"label_agreement":null},{"id":"W4399895491","doi":"10.18280/ria.380306","title":"The Impact of Oversampling and Undersampling on Aspect-Based Sentiment Analysis of Indramayu Tourism Using Logistic Regression","year":2024,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Data Mining and Machine Learning 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":"Undersampling; Logistic regression; Oversampling; Tourism; Statistics; Econometrics; Mathematics; Computer science; Artificial intelligence; Geography","score_opus":0.0827132864789696,"score_gpt":0.37776844915022006,"score_spread":0.2950551626712505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399895491","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":[0.14754982,0.00041625768,0.8514531,0.00021472939,0.00007316698,0.00008220433,0.000010580649,0.00004271826,0.00015737658],"genre_scores_gemma":[0.9927197,0.000027767861,0.007155701,0.000008347927,0.000015178147,0.0000032948842,0.0000069859307,0.000006899969,0.00005609661],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896055,0.000054692497,0.0003308792,0.0003307826,0.0001548441,0.00016823632],"domain_scores_gemma":[0.99815756,0.0009936562,0.00015422457,0.0005929489,0.000054615888,0.00004699458],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005500689,0.00011187173,0.00019064601,0.00029286472,0.0001870764,0.00014801684,0.00035563036,0.00003907079,0.000011140543],"category_scores_gemma":[0.00013997419,0.000075956894,0.000157373,0.0012410164,0.00010371154,0.00007796824,0.000110328154,0.00015946184,0.000006310168],"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":[0.0000076527,0.000051902192,0.0004742816,0.0000320771,0.00018710925,0.0000030534418,0.0006466347,0.9485756,0.0048427125,0.017484313,0.00005305035,0.027641602],"study_design_scores_gemma":[0.000013172329,0.00008571056,0.00032247626,0.00019923704,0.000101062804,0.000002076896,0.00015677363,0.9892595,0.0085202,0.0011851599,0.00007828947,0.00007637764],"about_ca_topic_score_codex":0.00036678472,"about_ca_topic_score_gemma":0.000004763247,"teacher_disagreement_score":0.8451699,"about_ca_system_score_codex":0.000060026665,"about_ca_system_score_gemma":0.00007389962,"threshold_uncertainty_score":0.3097432},"labels":[],"label_agreement":null},{"id":"W4399974175","doi":"10.33772/anoatik.v2i1.30","title":"PENERAPAN METODE NAIVE BAYES UNTUK KLASIFIKASI KATEGORI OLAH PANGAN (STUDI KASUS DINAS KESEHATAN KOTA PALEMBANG)","year":2024,"lang":"id","type":"article","venue":"AnoaTIK Jurnal Teknologi Informasi dan Komputer","topic":"Data Mining and Machine Learning 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":"Crosslight Software (Canada)","funders":"","keywords":"Statistics; Mathematics; Psychology","score_opus":0.01979618669687207,"score_gpt":0.2763024918371026,"score_spread":0.25650630514023054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399974175","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":[0.2916784,0.029426448,0.5341353,0.029703146,0.021269672,0.004083479,0.0007338789,0.0092219,0.07974777],"genre_scores_gemma":[0.94615304,0.0033496781,0.027424717,0.0016471188,0.0023988816,0.00025211464,0.0007650631,0.0002157255,0.01779368],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99266946,0.00043167523,0.0017732113,0.001929685,0.0012014628,0.0019945265],"domain_scores_gemma":[0.9949905,0.00083245797,0.0006767689,0.002385231,0.00044450248,0.00067053793],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0015358484,0.0013062595,0.0011310676,0.0009846142,0.0013692989,0.003563421,0.0041455277,0.0006352735,0.00008005929],"category_scores_gemma":[0.00029566418,0.0011290308,0.0006471854,0.002364669,0.0005952362,0.0035958637,0.0025168783,0.0026435193,0.0016655189],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007878389,0.0006645382,0.011505265,0.0009389448,0.0018668462,0.0012567246,0.01827215,0.000634059,0.0012149453,0.17974742,0.12438893,0.6594314],"study_design_scores_gemma":[0.0011963779,0.0018625619,0.019371275,0.0008694638,0.00038123294,0.0016175517,0.0010927179,0.07304717,0.0028680328,0.0011942553,0.89427465,0.002224724],"about_ca_topic_score_codex":0.0002108424,"about_ca_topic_score_gemma":0.00008161306,"teacher_disagreement_score":0.7698857,"about_ca_system_score_codex":0.0003477702,"about_ca_system_score_gemma":0.00080751156,"threshold_uncertainty_score":0.9999689},"labels":[],"label_agreement":null},{"id":"W4400058260","doi":"10.47467/dawatuna.v4i4.1975","title":"Klasifikasi penentuan siswa berprestasi menggunakan algoritma naive bayes classifier di PT Yes study education group indonesia","year":2024,"lang":"id","type":"article","venue":"Da watuna Journal of Communication and Islamic Broadcasting","topic":"Data Mining and Machine Learning 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":"Naive Bayes classifier; Artificial intelligence; Computer science; Psychology; Mathematics; Support vector machine","score_opus":0.021841685881258992,"score_gpt":0.30480103022020677,"score_spread":0.28295934433894776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400058260","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":[0.85634774,0.050913285,0.07350288,0.009955671,0.0025793344,0.001176268,0.00004858461,0.00031694694,0.005159294],"genre_scores_gemma":[0.985785,0.0036111583,0.009262768,0.00013983191,0.00035020197,0.000037040703,0.00009927211,0.000060121558,0.00065460213],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99550307,0.0012971642,0.0014381941,0.0006350698,0.00067595067,0.0004505656],"domain_scores_gemma":[0.99550426,0.0011818939,0.0010888381,0.001499016,0.0005160651,0.00020995589],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0022052962,0.00046753685,0.00059263513,0.00066444546,0.0009922795,0.0021476005,0.0021583948,0.00018377166,0.000024970437],"category_scores_gemma":[0.00037456636,0.00043907293,0.00019159119,0.00096356473,0.00026194844,0.0017675007,0.0010262034,0.0018319896,0.000040923318],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004079204,0.001392921,0.007082181,0.0002276197,0.00042816624,0.00002199807,0.0379714,0.0001100829,0.0012198036,0.016293745,0.0037222672,0.93148905],"study_design_scores_gemma":[0.004733617,0.0033658156,0.2747649,0.011053192,0.00223636,0.0033256162,0.06439282,0.43465763,0.0002379867,0.009950197,0.18814594,0.0031359391],"about_ca_topic_score_codex":0.0003281205,"about_ca_topic_score_gemma":0.000040649786,"teacher_disagreement_score":0.9283531,"about_ca_system_score_codex":0.00016868602,"about_ca_system_score_gemma":0.0006021749,"threshold_uncertainty_score":0.9998061},"labels":[],"label_agreement":null},{"id":"W4400886911","doi":"10.32493/informatika.v8i3.34442","title":"Implementasi Data Mining Association Rules Menggunakan Algoritma Fp-Growth untuk Data Penjualan Keramik","year":2023,"lang":"en","type":"article","venue":"Jurnal Informatika Universitas Pamulang","topic":"Data Mining and Machine Learning 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":"Discovery Air (Canada)","funders":"","keywords":"Association rule learning; Computer science; Data mining; Association (psychology); Database; Psychology","score_opus":0.05903051429802764,"score_gpt":0.3155196995995282,"score_spread":0.25648918530150056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400886911","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":[0.35549885,0.0004892419,0.45293128,0.027452331,0.0034350639,0.0022678294,0.02845281,0.008711804,0.12076079],"genre_scores_gemma":[0.7617326,0.00038802298,0.16508587,0.0013853183,0.00056457554,0.000012418291,0.069093466,0.00006531342,0.001672455],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979138,0.00009617894,0.00040420506,0.00047022506,0.0005980732,0.0005175102],"domain_scores_gemma":[0.9968012,0.0002916118,0.00041722195,0.0022009239,0.00011739656,0.00017164694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015104949,0.00020324191,0.00022254683,0.0003901031,0.0006207333,0.00060860213,0.0049190205,0.00008478309,0.000060128543],"category_scores_gemma":[0.00025537258,0.00021121913,0.000039757928,0.00089468167,0.000024129791,0.0051498534,0.0047513554,0.00032823958,0.0007274981],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010989515,0.00006308037,0.018229425,0.000060335686,0.00030910352,0.000054583576,0.0078079877,0.00027700476,0.000047748843,0.0211445,0.8367706,0.11522467],"study_design_scores_gemma":[0.0012339728,0.00009548346,0.021159105,0.0000760113,0.000118296484,0.00004452415,0.009837877,0.5915799,0.000021026844,0.00034275567,0.37485796,0.0006330609],"about_ca_topic_score_codex":0.0002516623,"about_ca_topic_score_gemma":0.000022467817,"teacher_disagreement_score":0.59130293,"about_ca_system_score_codex":0.00017758494,"about_ca_system_score_gemma":0.00015142563,"threshold_uncertainty_score":0.9350759},"labels":[],"label_agreement":null},{"id":"W4400931357","doi":"10.52362/ijiems.v2i2.1202","title":"Student Character Grouping Based on Six Dimensions of Pancasila Student Profile Using Clustering Method (Case Study of SMK Swasta Setia Budi Binjai)","year":2023,"lang":"en","type":"article","venue":"International Journal of Informatics Economics Management and Science","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"Character (mathematics); Cluster analysis; Psychology; Mathematics; Computer science; Artificial intelligence","score_opus":0.03155691135943124,"score_gpt":0.3489949930942264,"score_spread":0.31743808173479515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400931357","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":[0.83806086,0.0000023879916,0.1610537,0.00009312142,0.00036289362,0.00018389699,0.0000065109907,0.000012124802,0.00022452217],"genre_scores_gemma":[0.93078846,0.000025616802,0.06906584,0.0000744961,0.000019610157,0.0000047291164,0.0000017460899,0.0000043088826,0.0000151872255],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99836326,0.000033021286,0.000852151,0.00014508612,0.00045683538,0.0001496665],"domain_scores_gemma":[0.99828047,0.00012632336,0.0009820033,0.00029774147,0.00024519736,0.000068261405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021437448,0.00010602685,0.00019968186,0.0009260086,0.0001466321,0.0002560519,0.0012131656,0.0000149903435,0.0000016506808],"category_scores_gemma":[0.000035688267,0.00008778464,0.000046072797,0.00037446275,0.000063579966,0.0008383129,0.0010122448,0.00012002813,0.0000023607033],"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":[0.00005504331,0.0011927424,0.02986418,0.00014496091,0.00048551618,0.0001970288,0.03611622,0.8428419,0.00074803917,0.009854663,0.00008326165,0.078416444],"study_design_scores_gemma":[0.00071130827,0.00022401717,0.016463362,0.000119364195,0.000026238124,0.00010575845,0.008776855,0.97322446,0.00013005504,0.000049278377,0.00006997032,0.00009931751],"about_ca_topic_score_codex":0.000023716548,"about_ca_topic_score_gemma":0.000005756386,"teacher_disagreement_score":0.13038258,"about_ca_system_score_codex":0.00007917049,"about_ca_system_score_gemma":0.000057819187,"threshold_uncertainty_score":0.35797536},"labels":[],"label_agreement":null},{"id":"W4401429991","doi":"10.36040/jati.v8i4.10337","title":"PREDIKSI ADOPSI HEWAN PELIHARAAN MENGGUNAKAN METODE XGBOOST","year":2024,"lang":"id","type":"article","venue":"JATI (Jurnal Mahasiswa Teknik Informatika)","topic":"Data Mining and Machine Learning 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":0.014178107892912144,"score_gpt":0.27191717378272207,"score_spread":0.25773906588980994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401429991","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":[0.024834052,0.010685046,0.38209423,0.041182183,0.011190689,0.0034870303,0.0020575535,0.006852947,0.5176163],"genre_scores_gemma":[0.8703629,0.00094052,0.053534042,0.0034457415,0.0028040607,0.00048316448,0.0009953172,0.00027449912,0.06715976],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99340117,0.00031250188,0.0020155965,0.0011511437,0.0016086025,0.0015110103],"domain_scores_gemma":[0.9952121,0.0006115877,0.00069178245,0.0022438997,0.0003723774,0.000868258],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019224479,0.0010257006,0.0008798461,0.001066629,0.0011173253,0.0050266804,0.003357043,0.00043539485,0.0003796955],"category_scores_gemma":[0.0004355582,0.0009627921,0.0005555891,0.0024302518,0.00030466059,0.0051290044,0.0013824245,0.0023393913,0.008754387],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006713768,0.00039881124,0.0003777467,0.0019656166,0.00091861316,0.00017995338,0.026752153,0.0006311678,0.00050108123,0.061722577,0.43019366,0.47629148],"study_design_scores_gemma":[0.00070754724,0.00032726562,0.0021144252,0.0011091619,0.00022473054,0.000467532,0.0007542417,0.11741108,0.0006242898,0.000813884,0.8742709,0.0011749406],"about_ca_topic_score_codex":0.00018197061,"about_ca_topic_score_gemma":0.000043049975,"teacher_disagreement_score":0.84552884,"about_ca_system_score_codex":0.00033889373,"about_ca_system_score_gemma":0.0014426832,"threshold_uncertainty_score":0.9999623},"labels":[],"label_agreement":null},{"id":"W4401465316","doi":"10.62951/bridge.v2i3.169","title":"Klasifikasi Tingkat Minat Belanja Online Melalui Media Sosial pada Masyarakat di Kota Binjai Meggunakan Algoritma K-Means","year":2024,"lang":"en","type":"article","venue":"Bridge","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"Social media; Cluster analysis; Advertising; Computer science; Psychology; Business; Artificial intelligence; World Wide Web","score_opus":0.021986074319053216,"score_gpt":0.28352882076883296,"score_spread":0.26154274644977976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401465316","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":[0.19306836,0.0038988611,0.76014394,0.023718817,0.0058412505,0.00076959375,0.0013575153,0.0048701945,0.0063314834],"genre_scores_gemma":[0.9364288,0.00017772133,0.05624915,0.00062940543,0.001564987,0.00007867642,0.0010106114,0.00009370005,0.0037669854],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973311,0.00012490145,0.0004237272,0.0009989559,0.00052739796,0.00059392065],"domain_scores_gemma":[0.9978993,0.00047228538,0.000093527466,0.0011965306,0.00007630374,0.00026208567],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00054579787,0.00033605436,0.00030406186,0.00023998707,0.00029290828,0.0005420404,0.0016224184,0.0001321126,0.000043617903],"category_scores_gemma":[0.00020620498,0.00031430385,0.00015543008,0.00086678023,0.00010441198,0.00050528394,0.00063322025,0.00060736143,0.0008337918],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007512116,0.00026301463,0.0007582279,0.00011448363,0.000095978176,0.00022334355,0.0036957462,0.00011324736,0.001062895,0.03502342,0.07438815,0.884254],"study_design_scores_gemma":[0.00054107263,0.00016564791,0.037695237,0.00023594008,0.00009007278,0.00031305148,0.00012649898,0.32078335,0.000699746,0.0010684415,0.63743794,0.0008429887],"about_ca_topic_score_codex":0.0005565078,"about_ca_topic_score_gemma":0.00013889158,"teacher_disagreement_score":0.883411,"about_ca_system_score_codex":0.000079378995,"about_ca_system_score_gemma":0.00017909742,"threshold_uncertainty_score":0.99994415},"labels":[],"label_agreement":null},{"id":"W4401636466","doi":"10.51544/jurnalmi.v5i1.1197","title":"PENERAPAN DATA MINING KORELASI UMUR, PANGKAT DAN PENDIDIKAN TERHADAP JABATAN PADA POLRES BINJAI MENGGUNAKAN METODE ALGORITMA APRIORI","year":2020,"lang":"id","type":"article","venue":"JURNAL MAHAJANA INFORMASI","topic":"Data Mining and Machine Learning 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":"Computer science; Mathematics","score_opus":0.059936757247500014,"score_gpt":0.2953231961000846,"score_spread":0.2353864388525846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401636466","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":[0.22652094,0.010606345,0.34567022,0.17541993,0.013255193,0.006797312,0.0039280527,0.0069430466,0.21085897],"genre_scores_gemma":[0.84849566,0.0011194678,0.12135676,0.01022478,0.0041196505,0.00011699864,0.005688917,0.00030385936,0.00857389],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9924165,0.00032182134,0.0019133242,0.001939763,0.0016549256,0.0017536901],"domain_scores_gemma":[0.99247134,0.00041001572,0.0012519729,0.004021805,0.0002536165,0.001591227],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0013969615,0.0011077153,0.001094945,0.00042580641,0.001531611,0.0023735974,0.008736252,0.0003765625,0.000117351345],"category_scores_gemma":[0.000673253,0.0010900373,0.00032749053,0.0018227348,0.00033135348,0.0052254423,0.0053378316,0.002013499,0.00048053297],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000267147,0.0007657232,0.010805921,0.0006508642,0.001302612,0.00040505303,0.032287307,0.0007779385,0.0022948342,0.028049994,0.13985248,0.78254014],"study_design_scores_gemma":[0.0014571216,0.0008311676,0.0060161273,0.00020890404,0.00028614694,0.0002483169,0.0026392192,0.2021484,0.00068921427,0.000030923125,0.78408116,0.001363314],"about_ca_topic_score_codex":0.00045120873,"about_ca_topic_score_gemma":0.000120079174,"teacher_disagreement_score":0.7811768,"about_ca_system_score_codex":0.00017749623,"about_ca_system_score_gemma":0.0009214078,"threshold_uncertainty_score":0.99976826},"labels":[],"label_agreement":null},{"id":"W4402174099","doi":"10.2139/ssrn.4945024","title":"Enhancing Flood Forecasting Accuracy Using Prophet: A Comparative Analysis with Arima","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Data Mining and Machine Learning 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":"Autoregressive integrated moving average; Flood myth; Econometrics; Flood forecasting; Computer science; Statistics; Time series; Meteorology; Geography; Mathematics","score_opus":0.033355504373969995,"score_gpt":0.31410380842014046,"score_spread":0.28074830404617046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402174099","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":[0.17732744,0.0018578012,0.81923354,0.00044280075,0.00017019633,0.00023130763,0.000010785647,0.00019902336,0.00052708236],"genre_scores_gemma":[0.9204304,0.00012278708,0.07870161,0.0000328046,0.00032229448,0.0000346179,0.00003742831,0.000030612944,0.00028740682],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958005,0.00019708108,0.0005685485,0.00093476166,0.00051142985,0.0019876717],"domain_scores_gemma":[0.9978308,0.00017535662,0.00074938947,0.00086870795,0.00023861903,0.00013711615],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0020867873,0.00043901746,0.0006297681,0.0007282807,0.0005490201,0.0012634972,0.0016324631,0.00014566786,0.0000046251494],"category_scores_gemma":[0.00009269646,0.00035207966,0.00030988795,0.0015134439,0.000055213088,0.00031265026,0.001452212,0.007738097,0.000025948293],"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":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001077611,0.00049365114,0.001841555,0.0004164688,0.02574365,0.00017070245,0.019137232,0.44529247,0.0021549081,0.37229693,0.00012815969,0.13221651],"study_design_scores_gemma":[0.0003126824,0.0002701487,0.000087410175,0.00045777805,0.0021207638,0.0014536553,0.0010663763,0.862326,0.00033045321,0.13056165,0.0002799759,0.0007330736],"about_ca_topic_score_codex":0.0004622486,"about_ca_topic_score_gemma":0.0015340903,"teacher_disagreement_score":0.743103,"about_ca_system_score_codex":0.0010577651,"about_ca_system_score_gemma":0.00684908,"threshold_uncertainty_score":0.9998931},"labels":[],"label_agreement":null},{"id":"W4402318875","doi":"10.47861/jkpu-nalanda.v2i5.1287","title":"Prediksi Disleksia pada Anak menggunakan Metode Naive Bayes","year":2024,"lang":"en","type":"article","venue":"Jurnal Kajian dan Penelitian Umum","topic":"Data Mining and Machine Learning 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":"Naive Bayes classifier; Psychology; Computer science; Artificial intelligence; Support vector machine","score_opus":0.010308268511159827,"score_gpt":0.26898512650521045,"score_spread":0.2586768579940506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402318875","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":[0.079280995,0.0041794376,0.76688933,0.051921282,0.0042763064,0.0010031498,0.00068759324,0.00497059,0.08679129],"genre_scores_gemma":[0.9727467,0.000055255245,0.022278821,0.0006963349,0.00076370355,0.00007323125,0.00013342456,0.00005176526,0.0032007801],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974043,0.00015310686,0.000434053,0.00091688865,0.00049027096,0.0006014222],"domain_scores_gemma":[0.9980987,0.0002015643,0.000103520855,0.0011341933,0.000078757694,0.0003832645],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00051660347,0.000319989,0.00027670845,0.00029793484,0.00038000467,0.0012078974,0.0016539145,0.0001018268,0.00006531344],"category_scores_gemma":[0.00009988443,0.00029003184,0.00018120297,0.0008112709,0.000098696895,0.0010128295,0.00045970397,0.00062829227,0.00047504215],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017036473,0.00019994786,0.0013054436,0.0002142282,0.00032516205,0.0005348949,0.005081454,0.0003289114,0.0027864347,0.45330724,0.11062486,0.42527437],"study_design_scores_gemma":[0.0004331783,0.0002954432,0.019279582,0.00039011167,0.00009763926,0.00046770956,0.00037151968,0.104039915,0.0010681578,0.010918816,0.86168605,0.00095184904],"about_ca_topic_score_codex":0.0001621247,"about_ca_topic_score_gemma":0.000034205103,"teacher_disagreement_score":0.8934657,"about_ca_system_score_codex":0.00010194528,"about_ca_system_score_gemma":0.00025091207,"threshold_uncertainty_score":0.9999552},"labels":[],"label_agreement":null},{"id":"W4402380046","doi":"10.62951/bridge.v2i4.200","title":"Penerapan Algoritma Apriori Mengetahui Pola Tindakan Kriminal Berdasarkan Wilayah ( Studi Kasus : Polsek Sunggal)","year":2024,"lang":"en","type":"article","venue":"Bridge","topic":"Data Mining and Machine Learning 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":"Computer science","score_opus":0.02093933713468355,"score_gpt":0.29716706979221097,"score_spread":0.2762277326575274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402380046","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":[0.38888413,0.008115831,0.4893755,0.03311138,0.0056257104,0.0013730265,0.00041237567,0.0065520625,0.066549994],"genre_scores_gemma":[0.9780896,0.000050523864,0.016564937,0.0003734448,0.00061486417,0.000068550915,0.000100273675,0.00004234381,0.004095518],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99780244,0.0001025666,0.00031041095,0.00084939954,0.00041023732,0.00052493147],"domain_scores_gemma":[0.99845403,0.00015545657,0.00007138079,0.0010392284,0.00006381608,0.00021605898],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005330203,0.00026766234,0.00023650259,0.00020339004,0.00034563857,0.0007242314,0.0012664028,0.000075005075,0.000024116825],"category_scores_gemma":[0.000056523495,0.00025896222,0.000120476645,0.0006894825,0.00007273773,0.00052693527,0.0004897955,0.00044950302,0.00075001776],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009086139,0.00023597594,0.0017461621,0.00009736516,0.00017635497,0.00018397017,0.0045285267,0.000085075306,0.0022366114,0.12628102,0.09702901,0.76739085],"study_design_scores_gemma":[0.00045778163,0.00024755907,0.0642907,0.00010855111,0.000084582505,0.0002976525,0.000089949965,0.05252754,0.0006659454,0.00077359634,0.87972564,0.00073048804],"about_ca_topic_score_codex":0.00072184415,"about_ca_topic_score_gemma":0.000047860707,"teacher_disagreement_score":0.78269666,"about_ca_system_score_codex":0.00007324317,"about_ca_system_score_gemma":0.00020553292,"threshold_uncertainty_score":0.99998623},"labels":[],"label_agreement":null},{"id":"W4402380079","doi":"10.62951/bridge.v2i4.214","title":"Jaringan Saraf Tiruan (JST) Memprediksi Penjualan UMKM Kota Binjai dengan menggunakan Metode Backpropagation","year":2024,"lang":"en","type":"article","venue":"Bridge","topic":"Data Mining and Machine Learning 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":"Mathematics","score_opus":0.020545820692999546,"score_gpt":0.2887313858410391,"score_spread":0.26818556514803954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402380079","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":[0.32321155,0.0010153578,0.63480526,0.011078497,0.0021889117,0.00081185927,0.00012764684,0.004965682,0.021795243],"genre_scores_gemma":[0.9820538,0.000024918481,0.0139751965,0.00029880207,0.00039548264,0.0000695325,0.00019074156,0.000040577663,0.0029509154],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99796796,0.00012398393,0.00032174744,0.0008125573,0.00036969554,0.0004040678],"domain_scores_gemma":[0.99841434,0.00016717563,0.00007841237,0.0010930988,0.000063811865,0.00018314297],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007076731,0.0002382588,0.00020171578,0.00023642692,0.00029952344,0.0007849106,0.0011785816,0.00008523304,0.00002775624],"category_scores_gemma":[0.00012078127,0.00022847892,0.00009599219,0.0007529359,0.000054144984,0.0006609763,0.00042381813,0.00044062475,0.0010989688],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013980947,0.00028888637,0.003337404,0.00023253198,0.00025817865,0.00012923914,0.0075815255,0.00046557916,0.02444351,0.25245035,0.16401252,0.5467863],"study_design_scores_gemma":[0.0004913292,0.00021880407,0.05107993,0.00019595747,0.00009012916,0.00020681239,0.00006910324,0.34340942,0.0076485258,0.0029258553,0.59273785,0.0009262528],"about_ca_topic_score_codex":0.000347659,"about_ca_topic_score_gemma":0.00003787658,"teacher_disagreement_score":0.65884227,"about_ca_system_score_codex":0.00007629251,"about_ca_system_score_gemma":0.00014727324,"threshold_uncertainty_score":0.9996788},"labels":[],"label_agreement":null},{"id":"W4402380092","doi":"10.62951/bridge.v2i4.199","title":"Pengelompokan Data Kasus Keracunan Makanan Biologis Berdasarkan Faktor Penyebab Menggunakan Metode Clustering","year":2024,"lang":"en","type":"article","venue":"Bridge","topic":"Data Mining and Machine Learning 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":"Cluster analysis; Mathematics; Computer science; Statistics","score_opus":0.084808803073497,"score_gpt":0.34755435878523777,"score_spread":0.26274555571174074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402380092","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021927752,0.002480349,0.92438424,0.016087323,0.0023481292,0.0006545591,0.00095965323,0.0039166072,0.027241403],"genre_scores_gemma":[0.9394865,0.00008107666,0.05673709,0.00041074303,0.00050834526,0.0000555154,0.00093877653,0.000045004956,0.0017369487],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99746454,0.00013076693,0.00035337757,0.0012634849,0.0002775854,0.00051022216],"domain_scores_gemma":[0.9966551,0.00023152794,0.00008228209,0.002805354,0.000039282684,0.00018644048],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00086562743,0.00027566793,0.00025433375,0.00021000327,0.00030969258,0.0008325066,0.0035334649,0.000087397326,0.000039536433],"category_scores_gemma":[0.00014718658,0.00024951444,0.00007772614,0.00062820927,0.000073221774,0.00087431836,0.0024948034,0.0004141142,0.00077099906],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010735316,0.0001352198,0.0006380011,0.00015255764,0.00020694552,0.00017789671,0.0017343645,0.00019949647,0.0025183957,0.052914847,0.20041946,0.74089205],"study_design_scores_gemma":[0.00018990325,0.00007157838,0.009248578,0.000079179044,0.00003923581,0.00013369932,0.00004140694,0.2650281,0.0001374654,0.00038021078,0.7242178,0.00043292198],"about_ca_topic_score_codex":0.0007861735,"about_ca_topic_score_gemma":0.00013554626,"teacher_disagreement_score":0.9175587,"about_ca_system_score_codex":0.000060002974,"about_ca_system_score_gemma":0.00013555905,"threshold_uncertainty_score":0.9999957},"labels":[],"label_agreement":null},{"id":"W4402396375","doi":"10.54066/jptis.v2i3.2378","title":"Pengelompokan Data Rekam Medis pada Pasien Penyakit dalam Untuk Meningkatkan Manajemen Informasi Kesehatan Berdasarkan Wilayah Kota Binjai Menggunakan Algoritma Clustering K- Means","year":2024,"lang":"en","type":"article","venue":"Jurnal Penelitian Teknologi Informasi dan Sains","topic":"Data Mining and Machine Learning 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":"Cluster analysis; Medicine; Computer science; Artificial intelligence","score_opus":0.03144444726078466,"score_gpt":0.2944329510787421,"score_spread":0.26298850381795746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402396375","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":[0.04900909,0.002998834,0.6088097,0.037806563,0.007267823,0.004300142,0.001062706,0.012972276,0.27577287],"genre_scores_gemma":[0.88730174,0.001463414,0.08929431,0.0024490957,0.0018557895,0.0005443548,0.007908979,0.00030321826,0.008879131],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.992962,0.00022764815,0.0018230281,0.0017151699,0.0013951623,0.0018770038],"domain_scores_gemma":[0.99337965,0.0003606079,0.00058645435,0.004614971,0.00022540304,0.000832923],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0025546562,0.000982504,0.0008373554,0.0008805859,0.0012250801,0.0027122542,0.00860526,0.00040864246,0.000034697357],"category_scores_gemma":[0.00045526214,0.0008959833,0.00026863883,0.0017045358,0.00038529222,0.007125684,0.005983985,0.0020534396,0.00016380461],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044067732,0.0002882018,0.0048028626,0.0006012743,0.00079073414,0.000672771,0.015961338,0.0016417572,0.00040383483,0.1898445,0.015176431,0.76977223],"study_design_scores_gemma":[0.0007850427,0.00039187836,0.008585217,0.00035625053,0.00011212776,0.0006773363,0.0018731828,0.26778442,0.00017262202,0.00036676388,0.7177606,0.0011345536],"about_ca_topic_score_codex":0.00012739279,"about_ca_topic_score_gemma":0.0006479796,"teacher_disagreement_score":0.8382926,"about_ca_system_score_codex":0.00044306586,"about_ca_system_score_gemma":0.0007295654,"threshold_uncertainty_score":0.99934906},"labels":[],"label_agreement":null},{"id":"W4402396503","doi":"10.54066/jptis.v2i3.2381","title":"Pengelompokan Data Keluhan Masyarakat Terhadap Fasilitas Umum diKota Binjai Menggunakan Metode Clustering","year":2024,"lang":"en","type":"article","venue":"Jurnal Penelitian Teknologi Informasi dan Sains","topic":"Data Mining and Machine Learning 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":"Cluster analysis; Mathematics; Statistics","score_opus":0.04054197551269858,"score_gpt":0.3077262751672757,"score_spread":0.26718429965457713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402396503","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":[0.036887027,0.0033838842,0.8465488,0.022522822,0.0034730665,0.0013206521,0.0006442687,0.0068817213,0.07833774],"genre_scores_gemma":[0.9421971,0.00026551157,0.051490083,0.0012649728,0.00066538714,0.00009121438,0.001309118,0.0000798386,0.0026367845],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959058,0.0001608024,0.00095357397,0.0012375823,0.0006569079,0.0010852983],"domain_scores_gemma":[0.9954423,0.0003206572,0.0002297228,0.003484859,0.000103496895,0.0004189886],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0014635783,0.000548486,0.0004705149,0.00055418524,0.00064287137,0.0017589983,0.00573807,0.00022203366,0.000030288787],"category_scores_gemma":[0.0003315232,0.00048057546,0.00017426662,0.0009817149,0.0002103638,0.0036727365,0.0039978153,0.0012465131,0.0003296489],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040362385,0.0002985349,0.0024578813,0.0005006699,0.00050195743,0.0005662375,0.0068150843,0.0014919932,0.0017534681,0.2317617,0.035432234,0.71837986],"study_design_scores_gemma":[0.0004711646,0.000290126,0.007821082,0.00026046307,0.00006960349,0.0007756261,0.0010515542,0.31512177,0.00029709077,0.0008363467,0.6721303,0.0008748744],"about_ca_topic_score_codex":0.00009619683,"about_ca_topic_score_gemma":0.00015377226,"teacher_disagreement_score":0.90531003,"about_ca_system_score_codex":0.0002115769,"about_ca_system_score_gemma":0.0003753947,"threshold_uncertainty_score":0.9997646},"labels":[],"label_agreement":null},{"id":"W4402423213","doi":"10.54066/jptis.v2i3.2380","title":"Penerapan Metode Bayes untuk Mendiagnosa Penyakit Saraf Kejepit","year":2024,"lang":"en","type":"article","venue":"Jurnal Penelitian Teknologi Informasi dan Sains","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"Mathematics","score_opus":0.013870255732707806,"score_gpt":0.27537412040487513,"score_spread":0.26150386467216735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402423213","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":[0.16392508,0.004889285,0.5313197,0.03626497,0.0041924384,0.0014603742,0.00034767052,0.010257813,0.2473427],"genre_scores_gemma":[0.9622114,0.0004799525,0.029558128,0.0016390332,0.00053579215,0.00015039253,0.00026141142,0.00005104406,0.0051128925],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971069,0.00011357569,0.0006829306,0.0007338708,0.00051360787,0.000849126],"domain_scores_gemma":[0.99777496,0.00036894836,0.00017935128,0.0012399633,0.00010642958,0.00033035697],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00080419634,0.00040916933,0.00037402817,0.0005186823,0.00052384665,0.00139879,0.0022851527,0.00019307224,0.00007366807],"category_scores_gemma":[0.00025674936,0.00035408977,0.00023267399,0.00095283147,0.00016315353,0.002114044,0.00076874846,0.0009416267,0.0008773924],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000820661,0.00009845612,0.001174486,0.00009176489,0.00015217764,0.00020889037,0.0028791882,0.00044875575,0.0006094858,0.61436707,0.03616226,0.34379926],"study_design_scores_gemma":[0.0003595032,0.00029030655,0.0076602227,0.00013348197,0.000041126565,0.0005165756,0.0003865458,0.03122775,0.0012923902,0.0030335425,0.9543952,0.00066335476],"about_ca_topic_score_codex":0.0000943768,"about_ca_topic_score_gemma":0.00008203263,"teacher_disagreement_score":0.9182329,"about_ca_system_score_codex":0.00016965867,"about_ca_system_score_gemma":0.00036147554,"threshold_uncertainty_score":0.9999005},"labels":[],"label_agreement":null},{"id":"W4402424058","doi":"10.21776/ub.jasds.2024.001.01.2","title":"Support Vector Machine for Sentiment Analysis of PT. Paragon Technology and Innovation (Case Study of Brand Make Over and Emina Product Users on Female Daily Page – Beauty Review)","year":2024,"lang":"en","type":"article","venue":"Journal of Applied Statistics and Data Science.","topic":"Data Mining and Machine Learning 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":"Workplace Health, Safety and Compensation Commission","funders":"","keywords":"Beauty; Product (mathematics); Sentiment analysis; Support vector machine; Advertising; Computer science; Business; Artificial intelligence; Art; Mathematics; Aesthetics","score_opus":0.03181511011537253,"score_gpt":0.3593926463475298,"score_spread":0.3275775362321573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402424058","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":[0.77532446,0.0011927129,0.22045705,0.00045082028,0.00010260792,0.0005748851,0.0018391246,0.000015130603,0.00004320267],"genre_scores_gemma":[0.94575125,0.0004263549,0.053664196,0.00004230234,0.000011775067,0.0000075852017,0.000079580816,0.000004414044,0.000012530646],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986057,0.000014255606,0.0005223317,0.0004235166,0.0003099603,0.00012423516],"domain_scores_gemma":[0.99865866,0.00016931826,0.00041489082,0.00054516894,0.00015716419,0.000054772296],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00224187,0.00009930164,0.00033541518,0.0010411044,0.00013035203,0.00011044654,0.00042231407,0.000018762246,0.0000027126605],"category_scores_gemma":[0.0001928772,0.00007585386,0.000011491105,0.0025677374,0.00020427843,0.00022155518,0.00032762604,0.00013144767,1.03109734e-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":[0.00014801309,0.0011354255,0.012297827,0.0018406283,0.0010175571,0.00021714042,0.004851057,0.00020741422,0.010401349,0.24554588,0.009576974,0.71276075],"study_design_scores_gemma":[0.006520429,0.01004742,0.099436544,0.0013970963,0.008315661,0.0018409312,0.0038322455,0.81904376,0.003154269,0.010236094,0.034639493,0.0015360842],"about_ca_topic_score_codex":0.000022130409,"about_ca_topic_score_gemma":0.000015758491,"teacher_disagreement_score":0.81883633,"about_ca_system_score_codex":0.000011402603,"about_ca_system_score_gemma":0.00011007226,"threshold_uncertainty_score":0.30932307},"labels":[],"label_agreement":null},{"id":"W4402695324","doi":"10.61132/jupiter.v2i5.558","title":"Penerapan Metode Certainty Factor untuk Mendiagnosa penyakit Tanaman Tomat","year":2024,"lang":"en","type":"article","venue":"Jupiter Publikasi Ilmu Keteknikan Industri Teknik Elektro dan Informatika","topic":"Data Mining and Machine Learning 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":"Mathematics; Horticulture; Biology","score_opus":0.015016606617569915,"score_gpt":0.2627086477529379,"score_spread":0.24769204113536797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402695324","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":[0.515815,0.0025248209,0.23858011,0.054026693,0.00957231,0.006194566,0.0024760272,0.026331108,0.14447932],"genre_scores_gemma":[0.94612795,0.00011043963,0.03778144,0.002709495,0.0011069487,0.0008266373,0.0013201297,0.0001933858,0.009823568],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9938647,0.00025168288,0.0015564935,0.0013363159,0.0013141851,0.0016766145],"domain_scores_gemma":[0.99520594,0.0005048551,0.00048872485,0.002788974,0.00028782384,0.00072369166],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011601013,0.00096461654,0.00081119145,0.0016326455,0.00081989565,0.0059732604,0.0041725268,0.0005807642,0.00038336153],"category_scores_gemma":[0.00039736016,0.0008749421,0.00041028982,0.0030592286,0.00020617782,0.008147348,0.001331717,0.0021547012,0.0015887924],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011819169,0.0001612342,0.00089202647,0.00018621863,0.00029165955,0.00006460804,0.0052288515,0.00015831507,0.00028344188,0.07687111,0.37502518,0.54082555],"study_design_scores_gemma":[0.00070205407,0.00026547548,0.0015540103,0.0001917869,0.000059639377,0.00021663017,0.0004969023,0.059241522,0.0011523704,0.00054974156,0.93440205,0.0011678084],"about_ca_topic_score_codex":0.000464662,"about_ca_topic_score_gemma":0.00006436608,"teacher_disagreement_score":0.5593769,"about_ca_system_score_codex":0.0004917689,"about_ca_system_score_gemma":0.0006749965,"threshold_uncertainty_score":0.99937016},"labels":[],"label_agreement":null},{"id":"W4403084003","doi":"10.60076/indotech.v2i2.644","title":"Pengelompokan Data Siswa Berdasarkan Profil Pelajar Pancasila Menggunakan Metode Clustering (Studi Kasus SMK Putra Anda Binjai)","year":2024,"lang":"id","type":"article","venue":"Indonesian Journal of Education And Computer Science","topic":"Data Mining and Machine Learning 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":"Cluster analysis; Mathematics; Psychology; Humanities; Statistics; Philosophy","score_opus":0.03387993591077443,"score_gpt":0.33033838514335156,"score_spread":0.29645844923257714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403084003","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":[0.13470192,0.0100765,0.82454306,0.015630547,0.012943842,0.0005591629,0.000048055736,0.00019193563,0.0013049743],"genre_scores_gemma":[0.9052812,0.00033778773,0.0913098,0.000708753,0.001862751,0.000012566539,0.000021051483,0.000035672136,0.00043042836],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99526525,0.0002943119,0.0011557629,0.0014561646,0.0011152675,0.00071327604],"domain_scores_gemma":[0.9958645,0.00029968336,0.0007047928,0.0017646813,0.0006418754,0.0007244841],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004080936,0.00046567002,0.0005516177,0.001145597,0.0010050265,0.0041645262,0.004842579,0.00011404881,0.000019338107],"category_scores_gemma":[0.00014971,0.00041837798,0.0001228443,0.0026502782,0.0006697704,0.0037357628,0.0020067962,0.0009862588,0.000057636917],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026238675,0.0006999919,0.0026095158,0.00034771033,0.0001671033,0.000092042326,0.012709812,0.00018292823,0.0006771618,0.005478874,0.013595698,0.96341294],"study_design_scores_gemma":[0.0013949518,0.0014759836,0.085967384,0.0028943552,0.00044218486,0.008396343,0.0022448548,0.72726244,0.00048131717,0.0011337629,0.16661626,0.0016901921],"about_ca_topic_score_codex":0.000058242225,"about_ca_topic_score_gemma":0.000011271884,"teacher_disagreement_score":0.96172273,"about_ca_system_score_codex":0.00020112278,"about_ca_system_score_gemma":0.004751164,"threshold_uncertainty_score":0.9998268},"labels":[],"label_agreement":null},{"id":"W4403514960","doi":"10.61132/merkurius.v2i5.298","title":"Penerapan Metode Clustering Pada Kasus Kecelakaan Kerja","year":2024,"lang":"en","type":"article","venue":"Merkurius Jurnal Riset Sistem Informasi dan Teknik Informatika","topic":"Data Mining and Machine Learning 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":"Cluster analysis; Computer science; Humanities; Artificial intelligence; Art","score_opus":0.011898916162933338,"score_gpt":0.25743990956867696,"score_spread":0.24554099340574362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403514960","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":[0.02268506,0.0016905568,0.6816803,0.003731557,0.003312095,0.001084482,0.00012436455,0.0049061645,0.2807854],"genre_scores_gemma":[0.9331591,0.00033909242,0.0554815,0.001880009,0.0004898308,0.00029571925,0.00053361896,0.00010177825,0.0077193608],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99613285,0.000081937265,0.0014197686,0.00048701538,0.0009350238,0.0009433756],"domain_scores_gemma":[0.99727064,0.00024524497,0.00040226057,0.0014339389,0.00017002942,0.00047789598],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0012410124,0.0005588447,0.00049933157,0.00064676336,0.0007788823,0.0024260895,0.0023280536,0.00018561207,0.000020800282],"category_scores_gemma":[0.00012138985,0.0004866637,0.00032120862,0.0012290811,0.00011522823,0.0055792406,0.0009872305,0.0009888945,0.0007383745],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032761232,0.000088087705,0.00023819807,0.0008666006,0.00034828382,0.000084266874,0.013531817,0.0056897667,0.00036740443,0.11299899,0.030442841,0.835311],"study_design_scores_gemma":[0.0003818349,0.00013104273,0.0005228035,0.00020474468,0.000042729305,0.0005688656,0.00036578823,0.27854195,0.00071390584,0.00012640131,0.7178376,0.0005623597],"about_ca_topic_score_codex":0.00007360644,"about_ca_topic_score_gemma":0.00004030891,"teacher_disagreement_score":0.910474,"about_ca_system_score_codex":0.00022350288,"about_ca_system_score_gemma":0.00037653814,"threshold_uncertainty_score":0.9997585},"labels":[],"label_agreement":null},{"id":"W4403905133","doi":"10.59934/jaiea.v4i1.541","title":"Clustering of Student Expertise Fields Using the K-Means Algorithm (Case Study: STMIK Kaputama Binjai)","year":2024,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Cluster analysis; Computer science; Artificial intelligence; Algorithm","score_opus":0.048199583186461205,"score_gpt":0.34262629008193896,"score_spread":0.29442670689547773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403905133","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09099376,0.0006910364,0.90744674,0.0003516641,0.00022701324,0.00021327724,0.000004747316,0.000062128514,0.000009655109],"genre_scores_gemma":[0.9041212,0.00007751911,0.09550177,0.000019327324,0.00021799418,0.000036828587,7.232414e-7,0.000014157277,0.000010462127],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871314,0.000034427117,0.00060952903,0.00023128334,0.00024143264,0.0001701858],"domain_scores_gemma":[0.99899936,0.0002118742,0.00014986664,0.00042739208,0.00012555456,0.00008596216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063861493,0.00014087162,0.00019362838,0.00025469114,0.00018976703,0.00030437,0.0005928399,0.000048196758,0.0000038358603],"category_scores_gemma":[0.00002597018,0.00010923075,0.00008261146,0.0006532796,0.00004883642,0.00029225252,0.0001885641,0.00034809066,0.00000421616],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027545148,0.00019959675,0.000039502083,0.0000389855,0.000104781335,0.000103721904,0.008144424,0.2669754,0.0014685467,0.004072279,0.000044656987,0.7188054],"study_design_scores_gemma":[0.000023279208,0.0001403614,0.000049369708,0.00007126255,0.000052839692,0.0010570749,0.003029755,0.9933512,0.00060239166,0.00025201534,0.0012506006,0.00011982966],"about_ca_topic_score_codex":0.00011515067,"about_ca_topic_score_gemma":0.000011581341,"teacher_disagreement_score":0.81312746,"about_ca_system_score_codex":0.000038163056,"about_ca_system_score_gemma":0.000059326147,"threshold_uncertainty_score":0.44543007},"labels":[],"label_agreement":null},{"id":"W4403905285","doi":"10.59934/jaiea.v4i1.546","title":"Classification Of Students Based On Factors That Affect Student Learning Achievement Using The K-Means Clustering Algorithm (Case Study: STMIK Kaputama Binjai)","year":2024,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"Cluster analysis; Affect (linguistics); k-means clustering; Computer science; Artificial intelligence; Algorithm; Mathematics education; Machine learning; Mathematics; Psychology","score_opus":0.05838127959992512,"score_gpt":0.35260760487212855,"score_spread":0.29422632527220344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403905285","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":[0.35619596,0.000082955805,0.6430584,0.0001531241,0.00014663764,0.00029209934,0.000004213397,0.00006188071,0.000004696517],"genre_scores_gemma":[0.9773247,0.000027852902,0.022443976,0.000013707352,0.00010399399,0.000050915834,0.0000037571788,0.000022636677,0.000008453279],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981831,0.00010068783,0.00061156607,0.0003369129,0.00055692584,0.00021085682],"domain_scores_gemma":[0.99852186,0.0005113762,0.00028352637,0.00046039716,0.000119635566,0.000103219296],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012744697,0.00021114846,0.000241606,0.00043622332,0.00032601313,0.0004882995,0.000769032,0.000054281783,0.0000026086338],"category_scores_gemma":[0.00004744976,0.00016104546,0.00010848379,0.00075053034,0.000050251972,0.0002749671,0.00016931588,0.0005410483,0.000004135785],"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":[0.000009396062,0.0007021123,0.0053887772,0.00007039006,0.00017605569,0.00004895983,0.005073881,0.75518644,0.0028363308,0.0024969764,0.000011313288,0.22799939],"study_design_scores_gemma":[0.000049057828,0.00036808875,0.004052565,0.00012881638,0.00008603892,0.00010059421,0.005335174,0.98828495,0.0007168812,0.000047612084,0.0006709228,0.00015932611],"about_ca_topic_score_codex":0.00007268777,"about_ca_topic_score_gemma":0.000008591941,"teacher_disagreement_score":0.62112874,"about_ca_system_score_codex":0.00009593478,"about_ca_system_score_gemma":0.00006295331,"threshold_uncertainty_score":0.65672433},"labels":[],"label_agreement":null},{"id":"W4403905604","doi":"10.59934/jaiea.v4i1.630","title":"Classification of Factors Causing the Decline in Student Learning Achievement in The Post-Pandemic Period Using the C4.5 Algorithm (Case Study: STMIK Kaputama)","year":2024,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Pandemic; Period (music); Coronavirus disease 2019 (COVID-19); Algorithm; Computer science; Medicine; Physics","score_opus":0.055532046166779925,"score_gpt":0.3518284865430537,"score_spread":0.2962964403762738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403905604","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":[0.52969366,0.00030036893,0.4684357,0.0012339003,0.00006384752,0.00025031943,0.00000195108,0.000018155848,0.000002092613],"genre_scores_gemma":[0.99431914,0.000065746055,0.005421631,0.000030125291,0.00009710835,0.000049468075,0.0000026345663,0.000011221843,0.0000028974305],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984101,0.00014186036,0.00071588176,0.00022648781,0.0003246641,0.00018099044],"domain_scores_gemma":[0.99868786,0.0005715803,0.00021598632,0.00037569378,0.000111687164,0.000037176524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002260944,0.00014273047,0.0001755194,0.0002947233,0.0002709832,0.00036010533,0.0006666991,0.00004289806,0.0000012530488],"category_scores_gemma":[0.00008890595,0.00008383637,0.00006276237,0.0010999521,0.0000680629,0.0002457252,0.00015280412,0.00072800997,0.000001305021],"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":[0.000009504176,0.000773785,0.013204723,0.000053038213,0.00011929513,0.00011194962,0.07129529,0.48094705,0.0072719404,0.013688924,0.000011613148,0.4125129],"study_design_scores_gemma":[0.000049089205,0.00015972828,0.016305532,0.000086788794,0.00005761775,0.0006286307,0.04544872,0.9354987,0.00012811474,0.0003489827,0.0011496375,0.00013842001],"about_ca_topic_score_codex":0.0003857228,"about_ca_topic_score_gemma":0.00014150266,"teacher_disagreement_score":0.4646255,"about_ca_system_score_codex":0.000072869545,"about_ca_system_score_gemma":0.000093206145,"threshold_uncertainty_score":0.3472504},"labels":[],"label_agreement":null},{"id":"W4403905843","doi":"10.59934/jaiea.v4i1.646","title":"Application of Data Mining to Measure the Level of Satisfaction with Public Facilities and Services at STMIK Kaputama Binjai Using Linear Regression Method","year":2024,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"Measure (data warehouse); Linear regression; Regression analysis; Statistics; Computer science; Econometrics; Mathematics; Data mining","score_opus":0.15451711705701066,"score_gpt":0.35913242812025375,"score_spread":0.2046153110632431,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403905843","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.076878555,0.0006215097,0.92129296,0.00089347677,0.000038332586,0.00017515852,0.000062186315,0.00003291395,0.0000049231944],"genre_scores_gemma":[0.6829782,0.00006272327,0.31684083,0.000011700523,0.00006142035,0.00001743559,0.000008712003,0.000009560407,0.000009410528],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880946,0.00003704848,0.00047788068,0.00028164292,0.00026609466,0.00012785898],"domain_scores_gemma":[0.9985944,0.0003058201,0.0002426357,0.0005560684,0.00021891303,0.00008215957],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000951701,0.00012641789,0.00019644856,0.00027551217,0.00015958682,0.0001304951,0.0005635678,0.00005126716,0.0000014414121],"category_scores_gemma":[0.000049149738,0.000088823675,0.0000280816,0.00072221155,0.000057150304,0.0005656861,0.00025167802,0.00017973698,0.0000017096137],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020706175,0.00003173903,0.0005307641,0.00027204107,0.00008161984,6.1551884e-7,0.0027426053,0.034984507,0.048156537,0.01338884,0.00003860597,0.8997514],"study_design_scores_gemma":[0.000024580559,0.00008889226,0.0010140941,0.0002516362,0.00005581889,0.00010641463,0.0009347642,0.9845614,0.006337564,0.00032857695,0.0061692004,0.00012704781],"about_ca_topic_score_codex":0.00022086348,"about_ca_topic_score_gemma":0.00006656321,"teacher_disagreement_score":0.9495769,"about_ca_system_score_codex":0.000028785931,"about_ca_system_score_gemma":0.00006853621,"threshold_uncertainty_score":0.36221242},"labels":[],"label_agreement":null},{"id":"W4403905923","doi":"10.59934/jaiea.v4i1.670","title":"Classification of Tile Productivity Data Based on Tile Type Using Random Forest Algorithm in Langkat Regency","year":2024,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Tile; Productivity; Random forest; Type (biology); Computer science; Algorithm; Artificial intelligence; Geography; Archaeology; Geology; Economics","score_opus":0.06789879905150313,"score_gpt":0.3270601109828655,"score_spread":0.2591613119313624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403905923","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014233429,0.0003438728,0.98448235,0.00050588255,0.00016462214,0.00016129804,0.000021260146,0.000043008476,0.000044301512],"genre_scores_gemma":[0.88731486,0.000051923722,0.112393804,0.000008302186,0.00016492118,0.00001544064,0.00002599728,0.000011517821,0.000013243088],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99895465,0.000026355598,0.00042939984,0.0002817534,0.00018204,0.00012578994],"domain_scores_gemma":[0.99887633,0.00021647176,0.00013754236,0.0006055722,0.00011028018,0.000053771186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078352715,0.000101143116,0.00016701315,0.0003540445,0.00005465915,0.000100358346,0.000573254,0.000048375423,0.0000036949527],"category_scores_gemma":[0.00014072799,0.00009371251,0.000032612883,0.00087081967,0.000035229634,0.00036238847,0.00007629282,0.00025635396,0.0000118660955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024268555,0.00027678828,0.00024933592,0.00012379837,0.000029705216,0.0000053882295,0.00035689704,0.25790074,0.017295761,0.031867467,0.00026303894,0.6916068],"study_design_scores_gemma":[0.000030358495,0.000058360554,0.00061602204,0.00011601688,0.000016548573,0.000016874867,0.000034064276,0.9913679,0.001670588,0.00097526546,0.005010218,0.000087813605],"about_ca_topic_score_codex":0.00003427004,"about_ca_topic_score_gemma":0.000008548649,"teacher_disagreement_score":0.87308145,"about_ca_system_score_codex":0.00003731227,"about_ca_system_score_gemma":0.000103497434,"threshold_uncertainty_score":0.3821485},"labels":[],"label_agreement":null},{"id":"W4403905927","doi":"10.59934/jaiea.v4i1.651","title":"Data Mining Predicts the Number of Scout Enthusiasts in Binjai City Using the Linear Regression Method","year":2024,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Linear regression; Mathematics; Statistics; Regression; Regression analysis; Artificial intelligence; Pattern recognition (psychology); Data mining; Computer science","score_opus":0.09483445175576917,"score_gpt":0.3973343773830146,"score_spread":0.3024999256272454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403905927","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029193565,0.0006363464,0.9684655,0.0013253585,0.00016111055,0.00012969773,0.000018133269,0.000034999313,0.000035294725],"genre_scores_gemma":[0.7308425,0.00016081858,0.26869306,0.000026345266,0.00023240711,0.000014534793,0.0000057360494,0.000011749579,0.000012858428],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987481,0.00005774249,0.0005555941,0.00024389215,0.00023775027,0.00015692224],"domain_scores_gemma":[0.99835116,0.0005985731,0.0001884259,0.00071624614,0.00009137601,0.000054247917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001733307,0.00011518846,0.00016457793,0.00016307397,0.00014210041,0.00016588117,0.0012297649,0.000051048457,0.000004496058],"category_scores_gemma":[0.00017823868,0.00007084231,0.00004659112,0.0009185844,0.000068839865,0.0003851607,0.000327231,0.0004102232,0.000004263709],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015076507,0.00016365455,0.0006337588,0.00014221837,0.000115687515,0.000010831907,0.007132069,0.15945964,0.013734218,0.05811599,0.00054281903,0.759934],"study_design_scores_gemma":[0.000014218669,0.000015470734,0.0002200054,0.00023936288,0.000030672825,0.00012222485,0.0003232495,0.9900466,0.0016376239,0.00080255314,0.0064699207,0.0000780562],"about_ca_topic_score_codex":0.00005467246,"about_ca_topic_score_gemma":0.0000070959018,"teacher_disagreement_score":0.830587,"about_ca_system_score_codex":0.000023716484,"about_ca_system_score_gemma":0.00010104507,"threshold_uncertainty_score":0.28888658},"labels":[],"label_agreement":null},{"id":"W4403944575","doi":"10.18280/ijsse.140529","title":"Adaptation and Mitigation Model for Flood Disaster Resilience in West Malangke District, North Luwu Regency, Indonesia","year":2024,"lang":"en","type":"article","venue":"International Journal of Safety and Security Engineering","topic":"Data Mining and Machine Learning Applications","field":"Computer Science","cited_by":1,"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":"Flood myth; Resilience (materials science); Adaptation (eye); Environmental science; Geography; Water resource management; Psychology; Archaeology","score_opus":0.007866341085951389,"score_gpt":0.23624847032476498,"score_spread":0.2283821292388136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403944575","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":[0.2765381,0.00031922726,0.7218447,0.0010469179,0.00015210304,0.000043101256,0.000025758623,0.000017700651,0.000012394598],"genre_scores_gemma":[0.9857388,0.0002453607,0.013878655,0.000020356336,0.00007506146,0.0000047869025,0.000019966636,0.00000487108,0.0000121402045],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99937636,0.00000918531,0.00024665316,0.00013393135,0.00015565666,0.00007819079],"domain_scores_gemma":[0.999641,0.000119091324,0.00006085389,0.00006164349,0.000073269555,0.000044123113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020841655,0.00006810377,0.000081875216,0.00017243954,0.00002875553,0.0001340479,0.00022013101,0.000026728505,4.7263546e-7],"category_scores_gemma":[0.000059450253,0.00006511468,0.000025281524,0.00011834929,0.000012679742,0.0006086175,0.000056199984,0.00015666008,4.3114588e-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":[0.00011965523,0.000121580226,0.013295225,0.00024613892,0.00013208999,0.000060550457,0.024829892,0.55798465,0.00064755266,0.16023743,0.00014564738,0.24217956],"study_design_scores_gemma":[0.00020159812,0.000023661327,0.026621012,0.0001220751,0.000005696261,0.00007588871,0.000050115592,0.97170407,0.000014783066,0.0007007276,0.0004149567,0.00006542166],"about_ca_topic_score_codex":0.000009367003,"about_ca_topic_score_gemma":0.000024855633,"teacher_disagreement_score":0.7092007,"about_ca_system_score_codex":0.0000330077,"about_ca_system_score_gemma":0.000029508663,"threshold_uncertainty_score":0.26552993},"labels":[],"label_agreement":null},{"id":"W4404337033","doi":"10.61132/mars.v2i5.341","title":"Diagnosa Penyakit Kanker Prostat menggunakan Metode Certainty Factor","year":2024,"lang":"en","type":"article","venue":"Mars Jurnal Teknik Mesin Industri Elektro Dan Ilmu Komputer","topic":"Data Mining and Machine Learning 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":"Medicine; Traditional medicine","score_opus":0.018136464185171664,"score_gpt":0.2755021337210353,"score_spread":0.25736566953586365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404337033","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":[0.23784114,0.0028248343,0.69734436,0.04198381,0.00544423,0.002155116,0.0005544966,0.0052709435,0.006581046],"genre_scores_gemma":[0.8863392,0.00018137258,0.09557056,0.0024645592,0.0031004243,0.00040679108,0.00034335614,0.00022791591,0.011365822],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955061,0.00034461997,0.00075349334,0.001474958,0.0008565271,0.0010643111],"domain_scores_gemma":[0.9969649,0.0006689132,0.0002164606,0.0014930195,0.00015634699,0.0005004087],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00081735634,0.0006242195,0.00052137306,0.0006025181,0.00047597563,0.0020459008,0.0022061158,0.0003416905,0.000098378965],"category_scores_gemma":[0.00017107537,0.00054572127,0.00027925518,0.0014646187,0.00013869596,0.0013406845,0.00087094185,0.0018457551,0.0005133222],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000117356885,0.00018593983,0.0017298395,0.00006146678,0.0002300829,0.00029925824,0.0011629632,0.00030988088,0.00084656617,0.01690747,0.2530823,0.7251725],"study_design_scores_gemma":[0.0005387678,0.00020613999,0.0057032136,0.00022902952,0.00006499377,0.0002789319,0.000043105967,0.03587018,0.0012720597,0.0008341859,0.9541477,0.0008117178],"about_ca_topic_score_codex":0.0001223265,"about_ca_topic_score_gemma":0.000009103506,"teacher_disagreement_score":0.72436076,"about_ca_system_score_codex":0.00027234084,"about_ca_system_score_gemma":0.00047411377,"threshold_uncertainty_score":0.9996994},"labels":[],"label_agreement":null},{"id":"W4404337077","doi":"10.61132/saturnus.v2i4.330","title":"Diagnosa Penyakit Chikungunya Menggunakan Metode Certainty Factor","year":2024,"lang":"en","type":"article","venue":"Saturnus","topic":"Data Mining and Machine Learning 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":"Chikungunya; Medicine; Virology; Dengue fever","score_opus":0.01026035784574771,"score_gpt":0.27721111196304,"score_spread":0.2669507541172923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404337077","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":[0.123308524,0.0127200475,0.7164329,0.04742296,0.008004443,0.0012973088,0.0005209716,0.011113537,0.07917925],"genre_scores_gemma":[0.9796303,0.00004991604,0.01732464,0.00033447624,0.0003579654,0.000059531005,0.000052744308,0.000021829726,0.0021685835],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986247,0.000066123415,0.00017832076,0.0005669972,0.00023966591,0.00032418847],"domain_scores_gemma":[0.9986697,0.0002846819,0.000037994276,0.0008381279,0.000029981216,0.00013955106],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00021528373,0.00017318204,0.0001480902,0.0001398088,0.00016363304,0.00054114533,0.0009589567,0.00006877441,0.0000861524],"category_scores_gemma":[0.00012651054,0.00014571896,0.00009277588,0.00051010627,0.000035164478,0.0003831951,0.0002882978,0.00041361354,0.000895705],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028112695,0.00007318456,0.0004671138,0.00005578428,0.000097382996,0.000096483695,0.0032049203,0.00010031535,0.00091679144,0.17719688,0.06536146,0.75242686],"study_design_scores_gemma":[0.00015297419,0.00006484258,0.009500114,0.0000601506,0.000020775116,0.00005364779,0.000031169347,0.037129045,0.00062648096,0.004748847,0.94724786,0.00036411628],"about_ca_topic_score_codex":0.0001697344,"about_ca_topic_score_gemma":0.00002092119,"teacher_disagreement_score":0.88188636,"about_ca_system_score_codex":0.000045812205,"about_ca_system_score_gemma":0.00009558486,"threshold_uncertainty_score":0.9998822},"labels":[],"label_agreement":null},{"id":"W4404337160","doi":"10.61132/saturnus.v2i4.364","title":"Penerapan Metode Naïve Bayes untuk Memprediksi Tingkat Kesehatan Mental Siswa Menjelang Akhir Masa Sekolah","year":2024,"lang":"en","type":"article","venue":"Saturnus","topic":"Data Mining and Machine Learning 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":"Psychology; Humanities; Philosophy","score_opus":0.007202501419436377,"score_gpt":0.2626098753072627,"score_spread":0.2554073738878263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404337160","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":[0.37054813,0.0228153,0.34078893,0.04021257,0.013816309,0.002198383,0.0011286582,0.014425236,0.1940665],"genre_scores_gemma":[0.9598466,0.00006331836,0.033913046,0.00028835103,0.00036633608,0.000062849234,0.00018703038,0.000042589203,0.0052298787],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980214,0.000097959084,0.0002685702,0.0007730227,0.00039219417,0.0004468531],"domain_scores_gemma":[0.9986446,0.00017883163,0.00007007359,0.0008937118,0.00004084758,0.00017193066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047705678,0.0002535166,0.00021746224,0.0002019061,0.00031200078,0.0007326126,0.0011433241,0.00009726502,0.00009746809],"category_scores_gemma":[0.00006277147,0.00022431146,0.00011695768,0.0006539165,0.00006109354,0.00060289266,0.000508145,0.00047519174,0.0005887279],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018016188,0.00020628875,0.0009532099,0.00018036726,0.00040095384,0.0001788411,0.014679913,0.00029135373,0.027603574,0.1053119,0.1745475,0.67562807],"study_design_scores_gemma":[0.00054583076,0.00021988529,0.002972874,0.00025102543,0.00009592763,0.00031868415,0.00058146333,0.17249492,0.009285723,0.004550357,0.80768543,0.0009978968],"about_ca_topic_score_codex":0.00027846885,"about_ca_topic_score_gemma":0.000033624983,"teacher_disagreement_score":0.67463017,"about_ca_system_score_codex":0.000093153765,"about_ca_system_score_gemma":0.000108685774,"threshold_uncertainty_score":0.9147156},"labels":[],"label_agreement":null},{"id":"W4404337323","doi":"10.61132/saturnus.v2i4.321","title":"Penerapan Metode Clustering pada Status Gizi Ibu Hamil","year":2024,"lang":"en","type":"article","venue":"Saturnus","topic":"Data Mining and Machine Learning 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":"Cluster analysis; Psychology; Medicine; Mathematics; Statistics","score_opus":0.013210374357872,"score_gpt":0.27541829582721206,"score_spread":0.2622079214693401,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404337323","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016067583,0.0042451946,0.9444091,0.0041216738,0.0019936748,0.00018313994,0.000053330423,0.0021136482,0.026812686],"genre_scores_gemma":[0.91974366,0.00007849878,0.07523266,0.0003737125,0.00019801807,0.00003721359,0.00004491322,0.000023727815,0.0042676167],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988031,0.00004548229,0.00015261018,0.0004580952,0.00019079335,0.00034995814],"domain_scores_gemma":[0.99904317,0.00010151622,0.00002995829,0.0006785701,0.00002484186,0.00012194911],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022733562,0.0001312613,0.00011331912,0.00011649714,0.00015532624,0.00055024645,0.00061078963,0.000047511083,0.000022768452],"category_scores_gemma":[0.00004147894,0.00011755064,0.00005646302,0.00044813045,0.000027691083,0.0003648687,0.00032848422,0.0003141299,0.00037025218],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032014511,0.000035421956,0.00011773422,0.00006192572,0.0000570786,0.000059390113,0.0023529402,0.0009534148,0.0042390605,0.050502934,0.043116838,0.8985001],"study_design_scores_gemma":[0.00011823518,0.000042831478,0.0016523529,0.000051976735,0.000012399245,0.000053706834,0.000038206894,0.23077726,0.0004910685,0.0016187157,0.7649083,0.0002349022],"about_ca_topic_score_codex":0.00038451995,"about_ca_topic_score_gemma":0.000075866585,"teacher_disagreement_score":0.90367603,"about_ca_system_score_codex":0.00004627705,"about_ca_system_score_gemma":0.00009961506,"threshold_uncertainty_score":0.5306039},"labels":[],"label_agreement":null},{"id":"W4404337365","doi":"10.61132/saturnus.v2i4.359","title":"Diagnosa Penyakit Paru-Paru dengan Metode Naive Bayes","year":2024,"lang":"en","type":"article","venue":"Saturnus","topic":"Data Mining and Machine Learning 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":"Naive Bayes classifier; Medicine; Computer science; Artificial intelligence","score_opus":0.008964728313065952,"score_gpt":0.27219024333253766,"score_spread":0.2632255150194717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404337365","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":[0.097675264,0.014766907,0.7973402,0.026724873,0.0053963186,0.00083598867,0.0002201929,0.006883171,0.050157063],"genre_scores_gemma":[0.96646094,0.00008825757,0.030295387,0.00045930065,0.0002939142,0.0000799334,0.000051206564,0.000021268894,0.0022497596],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99867046,0.000075748685,0.00016963354,0.0005565172,0.00022338952,0.0003042514],"domain_scores_gemma":[0.9986341,0.0003966014,0.000039841314,0.0007719065,0.000035071436,0.00012249428],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00032639163,0.00015845116,0.00014212716,0.00012668975,0.00018853451,0.00055644056,0.00094803853,0.00006703455,0.000038490398],"category_scores_gemma":[0.00016602206,0.00013798273,0.00008018896,0.0005223143,0.000043917316,0.00039934323,0.00031324674,0.00041695128,0.0011800308],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030186834,0.0000769667,0.0008485324,0.00006043288,0.000100145284,0.0001789175,0.003449577,0.00012297674,0.0009681907,0.2793744,0.17325985,0.541557],"study_design_scores_gemma":[0.00015378132,0.00007810214,0.006662343,0.000105898784,0.00003743238,0.00010351541,0.00007237379,0.032431137,0.0015613661,0.009869813,0.94852287,0.00040135515],"about_ca_topic_score_codex":0.00015323503,"about_ca_topic_score_gemma":0.000028839722,"teacher_disagreement_score":0.86878574,"about_ca_system_score_codex":0.0000337571,"about_ca_system_score_gemma":0.000096717784,"threshold_uncertainty_score":0.99959767},"labels":[],"label_agreement":null},{"id":"W4404578712","doi":"10.62951/router.v2i3.261","title":"Prediksi Tingkat Motivasi Belajar Siswa Menggunakan Metode Backpropagation","year":2024,"lang":"en","type":"article","venue":"Router","topic":"Data Mining and Machine Learning 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":"Backpropagation; Computer science; Artificial intelligence; Artificial neural network","score_opus":0.0065740543760495285,"score_gpt":0.2476142256226717,"score_spread":0.2410401712466222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404578712","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0237338,0.00019986085,0.95732063,0.005244149,0.00049844466,0.00017119582,0.000016169599,0.0012848141,0.011530936],"genre_scores_gemma":[0.920572,0.000010460766,0.07144756,0.00036835638,0.00036178046,0.00006534629,0.0000854515,0.000025319174,0.007063739],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99885046,0.00005771355,0.00017991984,0.00047841648,0.00020982696,0.00022363181],"domain_scores_gemma":[0.99914825,0.000097222524,0.000037317237,0.0006060508,0.000035357574,0.00007579946],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003303114,0.00012817449,0.00010396101,0.000109066146,0.00013289807,0.0004543015,0.00057924417,0.000052891384,0.00004536855],"category_scores_gemma":[0.000043773798,0.00011049351,0.00005946424,0.00035992227,0.000021314632,0.0005860262,0.00023819238,0.0002178906,0.0009458898],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036478918,0.00012060035,0.0008749676,0.00012446968,0.00013965962,0.000026752517,0.005908084,0.0011450344,0.0053724144,0.14267305,0.06710456,0.7765068],"study_design_scores_gemma":[0.00020132623,0.00009249511,0.0029680945,0.00010167891,0.00003527462,0.000035856672,0.00004503587,0.48243192,0.004977567,0.0031079059,0.5056087,0.00039416668],"about_ca_topic_score_codex":0.000043462256,"about_ca_topic_score_gemma":0.000002876802,"teacher_disagreement_score":0.8968382,"about_ca_system_score_codex":0.00003925788,"about_ca_system_score_gemma":0.00004654952,"threshold_uncertainty_score":0.999832},"labels":[],"label_agreement":null},{"id":"W4404578729","doi":"10.62951/bridge.v2i4.249","title":"Prediksi Pengaruh Kegiatan MBKM terhadap Mahasiswa menggunakan Metode K-Nearest Neighbor","year":2024,"lang":"en","type":"article","venue":"Bridge","topic":"Data Mining and Machine Learning 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":"Computer science","score_opus":0.02010417519584809,"score_gpt":0.2862554780101067,"score_spread":0.2661513028142586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404578729","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":[0.016675105,0.0016975005,0.895103,0.019422643,0.0017743598,0.000540155,0.00021199007,0.003892221,0.060683023],"genre_scores_gemma":[0.9663153,0.000036925943,0.02707331,0.00055344985,0.0004579454,0.00009752896,0.00013435583,0.000040186176,0.005290941],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998267,0.00008188595,0.00025084455,0.0007127348,0.00030461562,0.00038290463],"domain_scores_gemma":[0.9984117,0.00024589596,0.0000492199,0.0010831442,0.000039891645,0.00017013309],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00041610896,0.00020300709,0.00017455111,0.00014402655,0.00022466402,0.0007631991,0.0012255359,0.000066805,0.00006712688],"category_scores_gemma":[0.00012077411,0.0001880593,0.00009364248,0.00055116555,0.00005010586,0.0005775664,0.0004299335,0.0003734682,0.0010128665],"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":[0.0000061111923,0.00015547806,0.0005641962,0.0001174929,0.000120190314,0.00013560163,0.0019860312,0.000229284,0.0012678297,0.30399376,0.3891897,0.30223435],"study_design_scores_gemma":[0.00017828644,0.00008012665,0.021326635,0.00007517403,0.000031335254,0.00009891211,0.00002390439,0.107569575,0.00043177564,0.0009631356,0.8688815,0.00033961135],"about_ca_topic_score_codex":0.00017474381,"about_ca_topic_score_gemma":0.000015044479,"teacher_disagreement_score":0.9496403,"about_ca_system_score_codex":0.00005158057,"about_ca_system_score_gemma":0.00013572312,"threshold_uncertainty_score":0.999765},"labels":[],"label_agreement":null},{"id":"W4404578736","doi":"10.62951/modem.v2i4.231","title":"Diagnosa Penyakit Epilepsi Menggunakan Metode Bayes","year":2024,"lang":"en","type":"article","venue":"Modem","topic":"Data Mining and Machine Learning 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":"Naive Bayes classifier; Computer science; Natural language processing; Statistics; Artificial intelligence; Mathematics","score_opus":0.008658869767127033,"score_gpt":0.26821267035290774,"score_spread":0.2595538005857807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404578736","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0055118706,0.0007424049,0.96989584,0.00799106,0.00036356642,0.00009828615,0.00002059482,0.001235821,0.014140545],"genre_scores_gemma":[0.93430585,0.00004114161,0.061946873,0.00036831718,0.00020579399,0.000097199445,0.000032029933,0.000017180944,0.002985611],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989569,0.000047764206,0.00013928294,0.00045771693,0.000174064,0.00022427687],"domain_scores_gemma":[0.9989849,0.00022414576,0.000022275113,0.0006624172,0.000019647667,0.000086652355],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00030326395,0.00011359453,0.00010765437,0.0000884726,0.00013237284,0.0003826918,0.0007835832,0.000041143845,0.000041759176],"category_scores_gemma":[0.0000577836,0.000100453326,0.000056338587,0.00034797346,0.000024228702,0.00039866837,0.0002681973,0.00021509663,0.00095992745],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.56995e-7,0.000046838704,0.00026040757,0.000028370789,0.000037474412,0.000030247746,0.0014333489,0.0010373838,0.00033255006,0.5203634,0.10397628,0.37245283],"study_design_scores_gemma":[0.000059247468,0.000030064375,0.00071438815,0.000032074324,0.000011857672,0.0000141434075,0.000011672603,0.5593601,0.00036807562,0.012697133,0.42653066,0.00017057275],"about_ca_topic_score_codex":0.00007600054,"about_ca_topic_score_gemma":0.0000071900527,"teacher_disagreement_score":0.92879397,"about_ca_system_score_codex":0.000023407556,"about_ca_system_score_gemma":0.0000515891,"threshold_uncertainty_score":0.99981797},"labels":[],"label_agreement":null},{"id":"W4404578742","doi":"10.62951/modem.v2i4.233","title":"Penerapan Algoritma K-Nearest Neighbor untuk Klasifikasi Usaha Masyarakat Berdasarkan Jenis Izin Usaha","year":2024,"lang":"en","type":"article","venue":"Modem","topic":"Data Mining and Machine Learning 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":"Computer science","score_opus":0.009817038144430183,"score_gpt":0.2595088432161351,"score_spread":0.2496918050717049,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404578742","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033444542,0.0016901805,0.9306324,0.011913835,0.0012388154,0.00035602314,0.00011702067,0.0021232571,0.018483909],"genre_scores_gemma":[0.9025078,0.00007816913,0.085435495,0.0006377162,0.00043207285,0.00013755192,0.00012982544,0.000061268875,0.010580111],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99774307,0.000099468045,0.00031213107,0.0009423223,0.000386046,0.0005169492],"domain_scores_gemma":[0.99823356,0.00018061107,0.00006010566,0.0012504247,0.000055361787,0.00021991372],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004170876,0.00027583813,0.00024170503,0.0001911118,0.00033826084,0.0008442069,0.0014643956,0.00011193015,0.00008590058],"category_scores_gemma":[0.000047689027,0.000258717,0.00012133401,0.0007998755,0.00007785577,0.000679167,0.00048160998,0.00046242608,0.0015277977],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008471431,0.00020903068,0.0013527334,0.00011972829,0.00012020967,0.00013099409,0.0024835633,0.0030101186,0.0035495113,0.31757307,0.090602346,0.58084023],"study_design_scores_gemma":[0.00016695254,0.000076360884,0.0015611668,0.000051116283,0.000022338952,0.0000579193,0.000024946481,0.6288141,0.00064947706,0.0035615165,0.364664,0.00035010785],"about_ca_topic_score_codex":0.00042175772,"about_ca_topic_score_gemma":0.000040003622,"teacher_disagreement_score":0.86906326,"about_ca_system_score_codex":0.00007088541,"about_ca_system_score_gemma":0.00014861638,"threshold_uncertainty_score":0.9999865},"labels":[],"label_agreement":null},{"id":"W4404578748","doi":"10.62951/repeater.v2i4.206","title":"Pengelompokan Menggunakan Metode Clustering Pada Pola Hidup Pengguna KB","year":2024,"lang":"en","type":"article","venue":"Repeater","topic":"Data Mining and Machine Learning 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":"Cluster analysis; Computer science; Artificial intelligence","score_opus":0.01299247283139889,"score_gpt":0.2716875922174776,"score_spread":0.25869511938607875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404578748","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":[0.03039979,0.0010875827,0.90564543,0.011944723,0.0017841813,0.00035585059,0.0000330668,0.0032768839,0.045472514],"genre_scores_gemma":[0.9568478,0.000022669909,0.03586456,0.00033252736,0.00028827874,0.000052230633,0.000040405022,0.000032825174,0.0065186885],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99840903,0.0000799057,0.00024193495,0.0006700341,0.00024386021,0.0003552177],"domain_scores_gemma":[0.9987033,0.00010113989,0.000039213373,0.0010017721,0.000030349413,0.00012419588],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00042077477,0.00018856351,0.00016217421,0.0001605797,0.00018736286,0.00066262233,0.00085284346,0.000059399186,0.000068006855],"category_scores_gemma":[0.000031159005,0.00016075418,0.000087749184,0.00033579962,0.000029552994,0.00052167155,0.0005161394,0.00031015446,0.00085908413],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015151399,0.00015963193,0.0010473217,0.0003786572,0.00032149217,0.0004449757,0.011033744,0.00096930336,0.02107454,0.09168097,0.08600668,0.78686756],"study_design_scores_gemma":[0.00022114333,0.000085062515,0.0020561721,0.00014746794,0.00003680424,0.00024249016,0.000057929326,0.23653986,0.0021603743,0.0015336889,0.75638485,0.000534145],"about_ca_topic_score_codex":0.00018325943,"about_ca_topic_score_gemma":0.000013509159,"teacher_disagreement_score":0.92644805,"about_ca_system_score_codex":0.00005244317,"about_ca_system_score_gemma":0.00005845529,"threshold_uncertainty_score":0.9999189},"labels":[],"label_agreement":null},{"id":"W4404578760","doi":"10.62951/repeater.v2i4.207","title":"Pengelompokan Data Penerima Bantuan untuk Disabilitas di Kota Binjai Menggunakan Metode Clustering Algoritma K-Means","year":2024,"lang":"en","type":"article","venue":"Repeater","topic":"Data Mining and Machine Learning 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":"Cluster analysis; Mathematics; Computer science; Artificial intelligence","score_opus":0.039997800082536145,"score_gpt":0.316627815176801,"score_spread":0.2766300150942649,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404578760","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02065183,0.000847403,0.95143765,0.01169833,0.0014720139,0.0004376596,0.00038320382,0.0023412276,0.010730703],"genre_scores_gemma":[0.9253295,0.000057906258,0.070220485,0.0002567535,0.00050397246,0.00007839529,0.0007602534,0.000068713336,0.0027240363],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99720794,0.00014018516,0.00038710277,0.0014127197,0.00035382825,0.00049820665],"domain_scores_gemma":[0.99579734,0.00020688816,0.00005622771,0.0037164744,0.00004200796,0.00018106049],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084846094,0.00028630355,0.00026354074,0.00015601823,0.00026563386,0.000995515,0.0027799984,0.000077737335,0.000081821505],"category_scores_gemma":[0.00010925138,0.00024213795,0.000084540414,0.0004800457,0.00008946968,0.0012810441,0.002480908,0.0003727707,0.00061386335],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021002785,0.00041169304,0.0022189002,0.00052854646,0.00044755705,0.0002597029,0.008668023,0.001571285,0.007285914,0.041459966,0.07353393,0.86359346],"study_design_scores_gemma":[0.00015160999,0.00006886987,0.0018850741,0.00009984673,0.000044295302,0.00010116402,0.000073904455,0.65078706,0.00025264084,0.0005113764,0.34562635,0.00039778213],"about_ca_topic_score_codex":0.00031626003,"about_ca_topic_score_gemma":0.000050178278,"teacher_disagreement_score":0.9046776,"about_ca_system_score_codex":0.000072863935,"about_ca_system_score_gemma":0.00008510221,"threshold_uncertainty_score":0.9874099},"labels":[],"label_agreement":null},{"id":"W4404578764","doi":"10.62951/modem.v2i4.238","title":"Pemodelan K-Nearest Neighbor Untuk Identifikasi Pola Kepuasan Mahasiswa Terhadap Pelayanan Kampus (Studi Kasus : STMIK Kaputama)","year":2024,"lang":"en","type":"article","venue":"Modem","topic":"Data Mining and Machine Learning 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":"Computer science","score_opus":0.01215351908710249,"score_gpt":0.2669861271059505,"score_spread":0.254832608018848,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404578764","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":[0.06991459,0.0017619543,0.8991845,0.008858632,0.0016694327,0.00040900352,0.00009478426,0.0023005554,0.015806524],"genre_scores_gemma":[0.971782,0.000037238668,0.021562023,0.00034922757,0.00030367167,0.00008260544,0.00009862997,0.000057009882,0.0057275346],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971997,0.00012095075,0.00040947503,0.0011269706,0.0005161253,0.0006267637],"domain_scores_gemma":[0.9979495,0.00017888618,0.00009265904,0.0014508411,0.00007742751,0.00025069408],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00052306737,0.00034092256,0.00030703188,0.00024910783,0.0004440375,0.0012311708,0.0016857526,0.00013398191,0.000043873526],"category_scores_gemma":[0.00005968058,0.00032079552,0.00016044262,0.0008168861,0.00008931747,0.0007350214,0.00070248527,0.0005945451,0.0007597641],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000209925,0.00043003634,0.005214559,0.00022332103,0.00034837704,0.0003246192,0.0070817955,0.008423759,0.0017835476,0.51283586,0.077890866,0.38542226],"study_design_scores_gemma":[0.0003238182,0.00011615644,0.014392356,0.00012140779,0.00006452965,0.000111891095,0.00012639185,0.8261145,0.00012235058,0.008942696,0.14895979,0.0006041583],"about_ca_topic_score_codex":0.0003834633,"about_ca_topic_score_gemma":0.000051462222,"teacher_disagreement_score":0.90186745,"about_ca_system_score_codex":0.00010735432,"about_ca_system_score_gemma":0.00018706253,"threshold_uncertainty_score":0.9999244},"labels":[],"label_agreement":null},{"id":"W4404578772","doi":"10.62951/repeater.v2i4.260","title":"Penerapan Metode Apriori Pada Data Penduduk Berdasarkan Tingkat Kesejahteraan (Studi Kasus : Kantor Camat Sirapit)","year":2024,"lang":"en","type":"article","venue":"Repeater","topic":"Data Mining and Machine Learning 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":"Mathematics; Humanities; Philosophy","score_opus":0.04553532620402153,"score_gpt":0.3191663248131611,"score_spread":0.2736309986091396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404578772","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":[0.30367672,0.00899718,0.5417696,0.03685484,0.008398594,0.0019307006,0.00093537517,0.010011288,0.087425694],"genre_scores_gemma":[0.9547248,0.00007125359,0.032218173,0.0004221914,0.00050895306,0.000036569993,0.00041973245,0.000056096218,0.011542243],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973679,0.000121989266,0.0003576329,0.0012736717,0.0003879925,0.00049077324],"domain_scores_gemma":[0.9964289,0.00016245386,0.0000777113,0.0031134174,0.000053076947,0.0001644335],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007211375,0.00027504953,0.00025738712,0.00017657081,0.00030768698,0.0009937297,0.0025192345,0.000076909564,0.00009532533],"category_scores_gemma":[0.000077651974,0.00022777522,0.00008171717,0.00047970578,0.000052727097,0.0009726388,0.0017159889,0.00038570166,0.0009267365],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014942201,0.00021936273,0.002069489,0.0002659005,0.0004510484,0.00044210066,0.0068957633,0.00010905255,0.011367908,0.02608553,0.29186788,0.660211],"study_design_scores_gemma":[0.00026231902,0.00008242861,0.0016607242,0.00012767354,0.00007054693,0.00019300543,0.000072680865,0.09052703,0.0014510276,0.0005152923,0.90447253,0.0005647504],"about_ca_topic_score_codex":0.0006766577,"about_ca_topic_score_gemma":0.000070138536,"teacher_disagreement_score":0.6596463,"about_ca_system_score_codex":0.00006233766,"about_ca_system_score_gemma":0.0001225606,"threshold_uncertainty_score":0.99985117},"labels":[],"label_agreement":null},{"id":"W4404592877","doi":"10.62951/switch.v2i4.210","title":"Penggunaan Metode Rough Set Pada Pola Minat Dan Bakat Siswa Dalam Menentukan Tema P5","year":2024,"lang":"en","type":"article","venue":"Switch Jurnal Sains dan Teknologi Informasi","topic":"Data Mining and Machine Learning 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":"Theme (computing); Competence (human resources); Data collection; Set (abstract data type); Psychology; Mathematics education; Computer science; Sociology; Social science; Social psychology; World Wide Web","score_opus":0.016764824909974902,"score_gpt":0.2807323547552811,"score_spread":0.2639675298453062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404592877","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":[0.592371,0.003276347,0.2803227,0.022939024,0.004573124,0.0017374912,0.00015885354,0.008345783,0.08627572],"genre_scores_gemma":[0.97573924,0.00019406722,0.019248048,0.00067066425,0.0002796767,0.00010759673,0.00029442,0.000051429874,0.0034148525],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965924,0.00013839401,0.0007985653,0.0008184232,0.00067427167,0.0009779234],"domain_scores_gemma":[0.99747175,0.00028984202,0.00026035873,0.0015040126,0.00012553537,0.00034847218],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0010654757,0.0005114736,0.00043849568,0.00043256703,0.0006417415,0.0012162075,0.002718733,0.00023819087,0.000014068316],"category_scores_gemma":[0.00026276102,0.0004218631,0.00024027504,0.0012494472,0.00015837984,0.0020095005,0.0012038781,0.0012092392,0.00022553354],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028292356,0.00022807352,0.006155886,0.00024918493,0.00037193066,0.00032134366,0.008680474,0.00068805023,0.0025581992,0.33202145,0.02389117,0.6248059],"study_design_scores_gemma":[0.00049354724,0.00043862764,0.0132893305,0.00019305469,0.00007676605,0.00068806345,0.00095586525,0.045919366,0.0029015653,0.0014850742,0.9326963,0.0008624295],"about_ca_topic_score_codex":0.000101466765,"about_ca_topic_score_gemma":0.00007113613,"teacher_disagreement_score":0.90880513,"about_ca_system_score_codex":0.00025994997,"about_ca_system_score_gemma":0.00030459848,"threshold_uncertainty_score":0.99982333},"labels":[],"label_agreement":null},{"id":"W4404592910","doi":"10.62951/switch.v2i4.226","title":"Clustering Menggunakan Algoritma K-Means untuk Mengelompokan Data Perjudian Berdasarkan Wilayah di Kota Binjai (Studi Kasus : Pengadilan Negeri Binjai)","year":2024,"lang":"en","type":"article","venue":"Switch Jurnal Sains dan Teknologi Informasi","topic":"Data Mining and Machine Learning 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":"Cluster analysis; Centroid; Mathematics; Data mining; Artificial intelligence; Computer science","score_opus":0.03119145879757414,"score_gpt":0.2935334514744261,"score_spread":0.262341992676852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404592910","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":[0.17427535,0.004695961,0.6952849,0.029285055,0.0072797392,0.00276298,0.0010641869,0.011300677,0.07405113],"genre_scores_gemma":[0.9670496,0.0007009045,0.028189069,0.0007884142,0.0008020896,0.00012940838,0.0011974731,0.00011426616,0.0010287587],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9949134,0.00018487834,0.0011064762,0.0015057268,0.00083163707,0.0014578761],"domain_scores_gemma":[0.99493295,0.00036724977,0.00033511786,0.003641966,0.00015435842,0.0005683425],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0016637736,0.0007567909,0.0006486469,0.00069773966,0.0011924014,0.0017687161,0.006259323,0.00030060596,0.000016886055],"category_scores_gemma":[0.00035356256,0.0006690472,0.00020346616,0.0017688081,0.00025199263,0.0031020758,0.0044604945,0.0018857734,0.00029446857],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004864326,0.0003074039,0.008346589,0.00029568677,0.0006873687,0.00047615526,0.010212811,0.0019113093,0.0010160301,0.040436506,0.019825643,0.91643584],"study_design_scores_gemma":[0.00066417886,0.00043408474,0.009927732,0.00023704385,0.0000897982,0.0005861839,0.0010379333,0.38014546,0.0001663281,0.00021805686,0.60546225,0.0010309673],"about_ca_topic_score_codex":0.00025235373,"about_ca_topic_score_gemma":0.0005000366,"teacher_disagreement_score":0.9154049,"about_ca_system_score_codex":0.00035341966,"about_ca_system_score_gemma":0.0006520913,"threshold_uncertainty_score":0.9995761},"labels":[],"label_agreement":null},{"id":"W4404619263","doi":"10.62383/polygon.v2i5.238","title":"Pengelompokan Data Kriminal untuk Menentukan Pola Rawan Tindak Kriminal Menggunakan Algoritma K-Means","year":2024,"lang":"en","type":"article","venue":"Polygon Jurnal Ilmu Komputer dan Ilmu Pengetahuan Alam","topic":"Data Mining and Machine Learning 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":"Cluster analysis; Criminology; Socialization; Persecution; Computer security; Psychology; Business; Computer science; Political science; Social psychology; Law; Artificial intelligence; Politics","score_opus":0.03417709483029344,"score_gpt":0.30418327937490947,"score_spread":0.270006184544616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404619263","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04808771,0.0062184692,0.8897032,0.025504217,0.008194985,0.0015738964,0.0011004008,0.005033466,0.014583656],"genre_scores_gemma":[0.6525791,0.00048624174,0.33357248,0.0015490205,0.004753767,0.00015062751,0.0026979463,0.00033550148,0.00387528],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9918487,0.0005467421,0.0013565464,0.003039331,0.0014878463,0.001720821],"domain_scores_gemma":[0.9929817,0.0005099196,0.00042228377,0.004851176,0.00020353543,0.0010314105],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022022394,0.0010800917,0.00087921997,0.0009632044,0.0010006587,0.0031519474,0.00830017,0.00030181275,0.00013308738],"category_scores_gemma":[0.00011126716,0.0010476542,0.00037046502,0.0013955269,0.0003150759,0.0029481808,0.003946693,0.0020661852,0.0010286452],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004461633,0.0005336039,0.00077446556,0.00028532493,0.0005826394,0.00052915176,0.0055277008,0.00030731954,0.00196935,0.04514706,0.059164815,0.885134],"study_design_scores_gemma":[0.000782289,0.0004273327,0.0055896044,0.00034937743,0.00027097357,0.0012878694,0.00020568413,0.38817418,0.00050057814,0.0007049577,0.60038495,0.001322184],"about_ca_topic_score_codex":0.00043151187,"about_ca_topic_score_gemma":0.00012057676,"teacher_disagreement_score":0.8838118,"about_ca_system_score_codex":0.0002461309,"about_ca_system_score_gemma":0.0007546345,"threshold_uncertainty_score":0.9997492},"labels":[],"label_agreement":null},{"id":"W4404857462","doi":"10.54066/jpsi.v2i4.2452","title":"Diagnosa Tingkat Kolesterol Pada Remaja Menggunakan Metode Dempster Shafer","year":2024,"lang":"en","type":"article","venue":"JURNAL PENELITIAN SISTEM INFORMASI (JPSI)","topic":"Data Mining and Machine Learning 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":"Computer science; Artificial intelligence","score_opus":0.012439246898012273,"score_gpt":0.26582691237936446,"score_spread":0.25338766548135216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404857462","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":[0.07758077,0.0037047416,0.5176801,0.03466972,0.00536342,0.0017449749,0.00015867487,0.0058796788,0.35321793],"genre_scores_gemma":[0.96712625,0.000081316284,0.014842111,0.0033851385,0.0007245336,0.0001849545,0.00014359277,0.00006638436,0.013445735],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968726,0.00011792577,0.00088331115,0.0007096418,0.0006744367,0.0007420844],"domain_scores_gemma":[0.9976045,0.00037858586,0.00020843459,0.001283104,0.00013125826,0.00039411333],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010506093,0.0004139499,0.0003794439,0.00033827382,0.0004311643,0.00184735,0.0016754969,0.00016250285,0.000056208035],"category_scores_gemma":[0.00012415928,0.00035923335,0.00026843068,0.0007052712,0.00007829266,0.0023450928,0.0006457236,0.0007541399,0.00087046524],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027189495,0.0001493437,0.0030842016,0.00066297787,0.00035545387,0.000295568,0.0070560575,0.0007484092,0.0004612089,0.179218,0.052309576,0.75563204],"study_design_scores_gemma":[0.00038679419,0.00013430638,0.008222035,0.00041977855,0.000059207672,0.000479481,0.0001786022,0.03670956,0.00046713342,0.0006017178,0.9517425,0.0005989435],"about_ca_topic_score_codex":0.00005611364,"about_ca_topic_score_gemma":0.000039992516,"teacher_disagreement_score":0.89943284,"about_ca_system_score_codex":0.00014286465,"about_ca_system_score_gemma":0.0002454673,"threshold_uncertainty_score":0.9999075},"labels":[],"label_agreement":null},{"id":"W4404860754","doi":"10.18280/mmep.111114","title":"Prediction of Horticultural Production Using Machine Learning Regression Models: A Case Study from Indramayu Regency, Indonesia","year":2024,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Data Mining and Machine Learning Applications","field":"Computer Science","cited_by":1,"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":"Production (economics); Regression analysis; Computer science; Machine learning; Economics; Microeconomics","score_opus":0.05614858924883543,"score_gpt":0.25414423599674907,"score_spread":0.19799564674791365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404860754","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":[0.46285865,0.00042235144,0.5361618,0.000031514897,0.000068418514,0.0001531728,0.000003694596,0.00029355072,0.000006871134],"genre_scores_gemma":[0.8910767,0.000029039986,0.10874919,8.7287754e-7,0.000047168534,0.000037185702,0.00001157506,0.00002103481,0.000027225205],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987363,0.00004337529,0.00038032592,0.0004503889,0.00021185118,0.00017776195],"domain_scores_gemma":[0.99941444,0.00009533794,0.00006587215,0.00030392507,0.000045436103,0.00007497062],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042407212,0.00017922025,0.00022107865,0.0001427959,0.00013846213,0.00017041121,0.0001505154,0.00006973519,0.0000010628507],"category_scores_gemma":[0.000034364686,0.00013945269,0.00003911009,0.0003334572,0.000019791274,0.00045686364,0.00012375443,0.00037983005,0.0000019268061],"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":[0.0000015002114,0.00008737845,0.00010835751,0.0002626214,0.000040265902,0.000033016866,0.008051719,0.98525333,0.0014300615,0.0025805992,0.0000025294603,0.0021486005],"study_design_scores_gemma":[0.00009269876,0.00007318692,0.000008426337,0.00057749124,0.000055380213,0.0004922744,0.00020902953,0.9948717,0.0001220175,0.0033526376,0.000016114467,0.0001290872],"about_ca_topic_score_codex":0.00037243112,"about_ca_topic_score_gemma":0.0000015722524,"teacher_disagreement_score":0.42821807,"about_ca_system_score_codex":0.000025657155,"about_ca_system_score_gemma":0.000016163593,"threshold_uncertainty_score":0.5686716},"labels":[],"label_agreement":null},{"id":"W4405945861","doi":"10.18280/mmep.111217","title":"Integrating Decision Tree and BIRCH Clustering Algorithms of BERTopic for Analyzing Public Sentiment on Dirtyvote Movie","year":2024,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Data Mining and Machine Learning 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":"Lembaga Pengelola Dana Pendidikan","keywords":"Cluster analysis; Decision tree; Tree (set theory); Computer science; Decision tree learning; Artificial intelligence; Sentiment analysis; Machine learning; Mathematics; Combinatorics","score_opus":0.029677522972007955,"score_gpt":0.2646693444191699,"score_spread":0.23499182144716194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405945861","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012818829,0.0004804551,0.9858431,0.00033187287,0.00006560952,0.00016683499,0.0000036285671,0.00021231805,0.000077307865],"genre_scores_gemma":[0.46997485,0.000041889813,0.52984464,0.0000053825543,0.00002193615,0.000046743666,0.000003491179,0.00001533463,0.000045762325],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990067,0.00000933946,0.00029781496,0.0003466097,0.00013168066,0.00020785576],"domain_scores_gemma":[0.9990481,0.0005678558,0.000034841367,0.00023826107,0.0000271746,0.00008374483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051973836,0.00014440184,0.00020359365,0.00018480503,0.00008479189,0.0002957125,0.00018186998,0.000049543512,7.2858927e-7],"category_scores_gemma":[0.0000773509,0.000117348485,0.00004464449,0.00020145692,0.000017520333,0.00016275828,0.00012737287,0.00016311974,0.0000019917052],"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":[0.0000017253911,0.000044122335,0.000009706962,0.0012417987,0.000049826875,0.0000012013714,0.0014418721,0.52794486,0.00065643055,0.19340046,0.00001677019,0.27519122],"study_design_scores_gemma":[0.00009821872,0.000063082436,0.0000042850406,0.0008703676,0.000013726678,0.0000100912775,0.000009644634,0.984472,0.000101429374,0.013870687,0.00036716528,0.00011934049],"about_ca_topic_score_codex":0.000007109757,"about_ca_topic_score_gemma":5.3328074e-7,"teacher_disagreement_score":0.457156,"about_ca_system_score_codex":0.000016136526,"about_ca_system_score_gemma":0.000010503493,"threshold_uncertainty_score":0.47853324},"labels":[],"label_agreement":null},{"id":"W4407571247","doi":"10.59934/jaiea.v4i2.941","title":"Application of the K-Nearest Neighbor (KNN) Algorithm in Machine Learning to Predict the Selection of Undergraduate Study Programs Based on New KIP Lecture Students","year":2025,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Selection (genetic algorithm); Machine learning; Context (archaeology); Process (computing); Artificial intelligence; k-nearest neighbors algorithm; Government (linguistics); Algorithm","score_opus":0.01242456516495809,"score_gpt":0.2830565986293352,"score_spread":0.2706320334643771,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407571247","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":[0.024976188,0.000046132587,0.97185856,0.0023284787,0.00006497603,0.00068119046,0.000002455661,0.000029089593,0.000012953706],"genre_scores_gemma":[0.9835874,0.000013083784,0.016174465,0.000043435102,0.00004746783,0.00010000267,0.0000026925597,0.000008430651,0.000023067956],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998703,0.00006943167,0.00054767006,0.0002161144,0.00032430634,0.00013944792],"domain_scores_gemma":[0.99892366,0.00020260159,0.00028066747,0.00038578844,0.00015098389,0.000056303914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000673614,0.00012644287,0.0001893793,0.00028719526,0.00014466564,0.0000894209,0.00087812694,0.000044535056,6.223681e-7],"category_scores_gemma":[0.0001235811,0.00008865062,0.00005937213,0.0018050448,0.000033152173,0.00008722272,0.000115560695,0.00042638028,0.0000016316708],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017302957,0.00045463067,0.014538304,0.000020342783,0.000035433488,1.8836064e-7,0.0005183733,0.4574163,0.0012993352,0.0056239343,0.000020851547,0.520055],"study_design_scores_gemma":[0.000105635045,0.00038282364,0.020952981,0.00011577461,0.000041021292,0.0000037474838,0.00015556846,0.9718607,0.0030561641,0.0013308573,0.0018969055,0.00009781353],"about_ca_topic_score_codex":0.00022488779,"about_ca_topic_score_gemma":0.00007463273,"teacher_disagreement_score":0.9586112,"about_ca_system_score_codex":0.000047048663,"about_ca_system_score_gemma":0.00010277926,"threshold_uncertainty_score":0.36150673},"labels":[],"label_agreement":null},{"id":"W4409691907","doi":"10.21009//insight.131.01","title":"Teknik Menulis Ekspresif untuk Menurunkan Quarter-Life Crisis Mahasiswa","year":2025,"lang":"id","type":"article","venue":"Insight Jurnal Bimbingan Konseling","topic":"Data Mining and Machine Learning 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":"Quarter (Canadian coin); Psychology; History","score_opus":0.014599686422421801,"score_gpt":0.2739518329769424,"score_spread":0.2593521465545206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409691907","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":[0.19224767,0.016188558,0.5933426,0.0945214,0.010445614,0.0018232064,0.0002783778,0.0021916337,0.08896096],"genre_scores_gemma":[0.97787327,0.0005902688,0.010355522,0.005811989,0.00051793916,0.0000887115,0.000058305443,0.00007815193,0.004625843],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99361575,0.0007713982,0.0015539477,0.0018506994,0.000923171,0.0012850175],"domain_scores_gemma":[0.9948351,0.00090437237,0.0007112728,0.002399302,0.00046498838,0.00068496837],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001634422,0.0008491243,0.00095058564,0.0011522812,0.0020642115,0.0021279522,0.0030262663,0.00042833478,0.00014767812],"category_scores_gemma":[0.0008590283,0.0008916835,0.00042413996,0.0026235038,0.00022372008,0.0009520544,0.0009471238,0.0019216909,0.0014985395],"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":[0.00029709193,0.0021900255,0.006749649,0.00079533504,0.0021323774,0.00045805876,0.03177185,0.0018799962,0.024645349,0.07770467,0.7803261,0.07104948],"study_design_scores_gemma":[0.004128675,0.0008468901,0.008897201,0.0029078051,0.001251364,0.00028595058,0.0063413316,0.069373034,0.011710595,0.004657322,0.8861149,0.0034849462],"about_ca_topic_score_codex":0.0009696074,"about_ca_topic_score_gemma":0.000074593016,"teacher_disagreement_score":0.7856256,"about_ca_system_score_codex":0.00025191225,"about_ca_system_score_gemma":0.0011994373,"threshold_uncertainty_score":0.9993534},"labels":[],"label_agreement":null},{"id":"W4410267720","doi":"10.63893/jetcom.v2i2.103","title":"Grouping Data of Patients Who Are Conducting Drugs Abuse Rehabilitation Using The Clustering Method (Case Study: BNNK Binjai)","year":2023,"lang":"en","type":"article","venue":"Journal of Engineering Technology and Computing (JETCom)","topic":"Data Mining and Machine Learning 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":"Cluster analysis; Rehabilitation; Medicine; Physical therapy; Computer science; Artificial intelligence","score_opus":0.04846993617071016,"score_gpt":0.33918485350391037,"score_spread":0.2907149173332002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410267720","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":[0.54979485,0.000047851,0.4495222,0.00027421847,0.00016933876,0.0000890142,0.0000023348261,0.00009906231,0.0000011227376],"genre_scores_gemma":[0.7459823,0.000005363501,0.25394475,0.000010169953,0.00004050424,0.0000012323757,0.000001817095,0.000012389227,0.0000014693737],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99849385,0.000120743156,0.00063559465,0.0003113528,0.00020428112,0.00023417742],"domain_scores_gemma":[0.99730206,0.00093335606,0.00069798966,0.0008307369,0.00019305354,0.000042824657],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025404317,0.0001527298,0.00034696347,0.00076906435,0.00031188523,0.000073195675,0.0011284124,0.00008480663,2.8127047e-7],"category_scores_gemma":[0.00087799376,0.0001269967,0.00004353041,0.0015184184,0.000056106244,0.00037192155,0.0011270366,0.0006021721,4.962607e-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":[0.000021341519,0.00041482886,0.107333966,0.00037370258,0.0005024182,0.00031513334,0.034326307,0.5403375,0.0016850872,0.0033323057,0.00022483926,0.31113255],"study_design_scores_gemma":[0.00044343967,0.00017259472,0.0038005023,0.00029395695,0.00004406601,0.0005070789,0.0056722783,0.9885518,0.00005276646,0.00010981993,0.00021652866,0.00013516708],"about_ca_topic_score_codex":0.000032818985,"about_ca_topic_score_gemma":0.0000027486456,"teacher_disagreement_score":0.44821426,"about_ca_system_score_codex":0.00002942778,"about_ca_system_score_gemma":0.000027549164,"threshold_uncertainty_score":0.5178775},"labels":[],"label_agreement":null},{"id":"W4410926602","doi":"10.63824/jptsp.v12i1.267","title":"TEKNIK EVALUASI PEMELIHARAAN JALAN LINGKUNGAN KAWASAN AKADEMI MILITER MENGGUNAKAN SISTEM INFORMASI GEOGRAFIS","year":2025,"lang":"id","type":"article","venue":"JURNAL TEKNIK SIPIL PERTAHANAN","topic":"Data Mining and Machine Learning 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":"Encana (Canada)","funders":"","keywords":"Humanities; Art","score_opus":0.011784760261831052,"score_gpt":0.28856116574388085,"score_spread":0.2767764054820498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410926602","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":[0.42584872,0.03903647,0.08413136,0.08925648,0.01728938,0.007912739,0.0006470396,0.0063744076,0.32950342],"genre_scores_gemma":[0.83886695,0.0011082845,0.0070626014,0.0062639476,0.001258338,0.00033877452,0.00055452803,0.00017755745,0.14436904],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99153906,0.0006765133,0.002156783,0.0020942425,0.0015095696,0.002023816],"domain_scores_gemma":[0.99342495,0.0006724699,0.0009182618,0.0033192777,0.0007101785,0.0009548362],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0026532758,0.0012896842,0.0012925278,0.0011888874,0.0020777055,0.0019055823,0.0044508544,0.0007074017,0.00008681644],"category_scores_gemma":[0.0008794383,0.0012412885,0.0008329032,0.0027138488,0.00046490238,0.0017672965,0.0016278005,0.002713128,0.00093188754],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029888347,0.0023520966,0.025566282,0.0018287377,0.0023099498,0.00017625271,0.022077933,0.00060425425,0.011623356,0.062170573,0.06098166,0.81001],"study_design_scores_gemma":[0.0018078156,0.00056960137,0.019642634,0.0011517901,0.00052395806,0.00011302976,0.0005822051,0.047821462,0.0016824412,0.00041183722,0.9242319,0.0014613582],"about_ca_topic_score_codex":0.0004096183,"about_ca_topic_score_gemma":0.0002881594,"teacher_disagreement_score":0.8632502,"about_ca_system_score_codex":0.00043772376,"about_ca_system_score_gemma":0.001151846,"threshold_uncertainty_score":0.9999855},"labels":[],"label_agreement":null},{"id":"W4412034880","doi":"10.18280/isi.300517","title":"Comparison of Anomaly Detection Using Statistical Method and Deep Learning Method in Jakarta Air Quality Index Data","year":2025,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Data Mining and Machine Learning 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":"Anomaly detection; Anomaly (physics); Index (typography); Computer science; Quality (philosophy); Artificial intelligence; Statistics; Data mining; Pattern recognition (psychology); Mathematics; Physics; World Wide Web","score_opus":0.047903631581716906,"score_gpt":0.4028932527735115,"score_spread":0.3549896211917946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412034880","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0548858,0.00006417258,0.9439347,0.000039496073,0.0000734663,0.0001589907,0.000019400823,0.00009579761,0.00072819524],"genre_scores_gemma":[0.64693016,0.0000030054794,0.3529173,0.000029481427,0.000005178305,0.000009497168,0.00009742419,0.0000027919825,0.000005156264],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998044,0.0005166577,0.0007928091,0.00026182694,0.0001923997,0.00019226622],"domain_scores_gemma":[0.9981704,0.00066354574,0.00041511795,0.00058252364,0.00012381512,0.000044639375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025284889,0.00012729605,0.00030802892,0.00040325106,0.00022827408,0.00016528803,0.0005292116,0.00009521314,0.000001953059],"category_scores_gemma":[0.0012970074,0.00013503684,0.000017889543,0.0007875176,0.00006996566,0.0022841766,0.0005266803,0.0003049517,0.0000026588873],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019465086,0.000030831692,0.050501045,0.00024166121,0.000021899876,2.1903371e-7,0.003913782,0.020355722,0.00039245439,0.018959044,0.000009665166,0.90555423],"study_design_scores_gemma":[0.000234631,0.00003226337,0.14869887,0.00006428561,0.00001288845,0.0000066828493,0.0006718081,0.8464389,0.00038275984,0.00242185,0.0009270881,0.00010797023],"about_ca_topic_score_codex":0.0020410249,"about_ca_topic_score_gemma":0.00017624258,"teacher_disagreement_score":0.90544623,"about_ca_system_score_codex":0.000102388745,"about_ca_system_score_gemma":0.00008131778,"threshold_uncertainty_score":0.55066425},"labels":[],"label_agreement":null},{"id":"W4412676143","doi":"10.58776/jriti.v2i3.158","title":"Klasifikasi Penentuan Siswa Berprestasi Menggunakan Algoritma Naïve Bayes Classifier DI PT.Yes Study Education Group Indonesia","year":2025,"lang":"en","type":"article","venue":"Jurnal Riset Informatika dan Teknologi Informasi","topic":"Data Mining and Machine Learning 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":"Naive Bayes classifier; Artificial intelligence; Computer science; Support vector machine","score_opus":0.008750255239420343,"score_gpt":0.28001262571037516,"score_spread":0.2712623704709548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412676143","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":[0.7603428,0.00045107884,0.15013544,0.002889316,0.0024855451,0.0027777771,0.0000675049,0.002277701,0.07857283],"genre_scores_gemma":[0.9828588,0.00017651668,0.0134506,0.001265879,0.00012369173,0.0006438214,0.00046873037,0.000026551792,0.0009854124],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.996097,0.00018381029,0.0015467033,0.0005567204,0.0007600811,0.00085565593],"domain_scores_gemma":[0.9963481,0.00031929766,0.00083588104,0.0018490558,0.00034475187,0.00030293138],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0010630647,0.0005992407,0.0005776325,0.0009804544,0.0010531074,0.0011629825,0.0031956125,0.00029065053,0.00000937016],"category_scores_gemma":[0.00039194466,0.00052201876,0.00020289596,0.0015752459,0.00018476923,0.004747545,0.001391562,0.0011815326,0.0001557877],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060406284,0.0010673179,0.10313744,0.00013934505,0.00024206332,0.000008033104,0.009698903,0.00026912254,0.000024939973,0.07527985,0.01517888,0.7948937],"study_design_scores_gemma":[0.0023608108,0.0009960599,0.5897434,0.00024077429,0.00015916894,0.00015082966,0.018763479,0.029108785,0.00030539752,0.0015076171,0.3553598,0.0013038967],"about_ca_topic_score_codex":0.000106608066,"about_ca_topic_score_gemma":0.00005255544,"teacher_disagreement_score":0.79358983,"about_ca_system_score_codex":0.0002484584,"about_ca_system_score_gemma":0.00077816594,"threshold_uncertainty_score":0.9998739},"labels":[],"label_agreement":null},{"id":"W4412878883","doi":"10.54082/jupin.1592","title":"Identifikasi Karakteristik Desain Temporary Modular Shelter pada Bencana di Indonesia melalui Nvivo dan Review Literatur","year":2025,"lang":"id","type":"article","venue":"Jurnal Penelitian Inovatif","topic":"Data Mining and Machine Learning 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":"Encana (Canada)","funders":"","keywords":"Modular design; Computer science; Operating system","score_opus":0.013161431137480053,"score_gpt":0.282983111128687,"score_spread":0.269821679991207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412878883","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":[0.4232351,0.22713153,0.23205723,0.06570671,0.009953765,0.0050397706,0.0012217984,0.0015204682,0.03413366],"genre_scores_gemma":[0.9350967,0.007186191,0.011766812,0.026325086,0.0011208476,0.00043179843,0.0015815715,0.0001563531,0.016334683],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99373037,0.000649903,0.001953062,0.0017369337,0.0009208672,0.0010088878],"domain_scores_gemma":[0.9949723,0.00027080398,0.0008449122,0.002876812,0.0006235558,0.00041163008],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0019741973,0.0008270424,0.001073145,0.00070683757,0.0009797215,0.0020955468,0.0032217344,0.00031203698,0.00011319413],"category_scores_gemma":[0.00038134467,0.000846313,0.0003682807,0.0032773276,0.00027022834,0.0014342983,0.0012708373,0.0016945429,0.0002997068],"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":[0.00007519301,0.00096910645,0.044845153,0.009406867,0.000885328,0.0007912225,0.0017571828,0.00007146477,0.0038996746,0.080085084,0.44179183,0.4154219],"study_design_scores_gemma":[0.001389694,0.00027406297,0.2274653,0.024139274,0.0005242593,0.00027780965,0.00014134946,0.009407552,0.00091228454,0.0031788147,0.7302075,0.0020820869],"about_ca_topic_score_codex":0.00078686234,"about_ca_topic_score_gemma":0.00004920708,"teacher_disagreement_score":0.51186156,"about_ca_system_score_codex":0.00024511945,"about_ca_system_score_gemma":0.0009970844,"threshold_uncertainty_score":0.99939877},"labels":[],"label_agreement":null},{"id":"W4412999135","doi":"10.31004/riggs.v4i2.1388","title":"Pemanfaatan Klasterisasi K-Means untuk Pengelompokan Berdasarkan Indikator Ekonomi, Digitalisasi, dan Produksi Komoditas","year":2025,"lang":"id","type":"article","venue":"RIGGS Journal of Artificial Intelligence and Digital Business","topic":"Data Mining and Machine Learning 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":"Canadian Steel Producers Association","funders":"","keywords":"Biology","score_opus":0.027787151281536925,"score_gpt":0.28725596706835244,"score_spread":0.2594688157868155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412999135","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":[0.56711304,0.0019292632,0.40525624,0.008914909,0.0034343586,0.00071365,0.00026839503,0.00015481125,0.012215337],"genre_scores_gemma":[0.99677736,0.0002708294,0.0009622946,0.0002325118,0.00063864747,0.000010715328,0.00006691026,0.000040721625,0.0009999998],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99582887,0.000113925125,0.0018508082,0.0008939199,0.000600193,0.000712262],"domain_scores_gemma":[0.99585015,0.00045772918,0.0011303702,0.0009326237,0.0012186299,0.00041047786],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00077033567,0.00062028837,0.0008995642,0.0007677354,0.0005965271,0.004663542,0.0018519461,0.00022481727,0.0000166537],"category_scores_gemma":[0.0010337995,0.00056684116,0.00024421638,0.0019946848,0.0006816447,0.0041171657,0.00079600053,0.00075006805,0.000118770506],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040411754,0.0017203334,0.006431559,0.00048922753,0.00046290585,0.00020884196,0.00408173,0.0010526102,0.0006320358,0.05023842,0.005153184,0.929125],"study_design_scores_gemma":[0.0022400972,0.005188981,0.07142473,0.012586695,0.0021179414,0.0038068197,0.026366534,0.05920475,0.02944015,0.05104495,0.72795445,0.008623888],"about_ca_topic_score_codex":0.000052664924,"about_ca_topic_score_gemma":0.000038287028,"teacher_disagreement_score":0.9205012,"about_ca_system_score_codex":0.00013200266,"about_ca_system_score_gemma":0.0009136666,"threshold_uncertainty_score":0.9996783},"labels":[],"label_agreement":null},{"id":"W4413228311","doi":"10.51401/jinteks.v7i2.5886","title":"METODE MFCC-SVM UNTUK PENGENALAN TINGKAT EMOSI MANUSIA BERDASARKAN BERAGAM DATASET","year":2025,"lang":"id","type":"article","venue":"Jurnal Informatika Teknologi dan Sains (Jinteks)","topic":"Data Mining and Machine Learning 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":"Humanities; Physics; Art","score_opus":0.017293482519200425,"score_gpt":0.29782982499089433,"score_spread":0.2805363424716939,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413228311","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":[0.20669477,0.0036659732,0.41497985,0.042273015,0.0078800665,0.0057970393,0.01613597,0.0048015574,0.29777175],"genre_scores_gemma":[0.81273276,0.0023052185,0.082171224,0.033332787,0.0013184075,0.000758032,0.02918086,0.00027713893,0.037923593],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99327135,0.00047386577,0.0022859436,0.0012858199,0.00094551285,0.001737489],"domain_scores_gemma":[0.9932808,0.00067710265,0.0013430833,0.0037339558,0.00040411882,0.00056091906],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0020347547,0.0011098871,0.0011744052,0.0012489883,0.0016242621,0.0022145896,0.006072403,0.00059177843,0.00020488053],"category_scores_gemma":[0.0009805439,0.0010352377,0.0004040275,0.0021750263,0.0005644384,0.0026416245,0.0041818605,0.0029191554,0.0026696897],"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":[0.00010947252,0.00066128286,0.005419887,0.00052043446,0.0008532621,0.0001483442,0.004977498,0.00075655535,0.00034434698,0.03460372,0.66973794,0.28186724],"study_design_scores_gemma":[0.0013695484,0.0004084998,0.012713881,0.00060595403,0.0002498434,0.0004293725,0.0012987853,0.055826668,0.000942065,0.00037879916,0.924619,0.0011575615],"about_ca_topic_score_codex":0.0006859582,"about_ca_topic_score_gemma":0.00037078522,"teacher_disagreement_score":0.606038,"about_ca_system_score_codex":0.0005079549,"about_ca_system_score_gemma":0.00083822105,"threshold_uncertainty_score":0.9996755},"labels":[],"label_agreement":null},{"id":"W4413230213","doi":"10.18280/isi.300606","title":"Performance Evaluation of Text Embedding Models for Ambiguity Classification in Indonesian News Corpus: A Comparative Study of TF-IDF, Word2Vec, FastText BERT, and GPT","year":2025,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Data Mining and Machine Learning 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":"Word2vec; Ambiguity; Indonesian; Artificial intelligence; Natural language processing; Computer science; Information retrieval; Embedding; Linguistics; Philosophy","score_opus":0.055225182397883835,"score_gpt":0.330857235527801,"score_spread":0.2756320531299172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413230213","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":[0.6987553,0.000027345808,0.29808766,0.00004001126,0.00004998626,0.0010814646,0.0000079449865,0.000033531585,0.0019167209],"genre_scores_gemma":[0.99130154,0.000012222609,0.008078543,0.000020458834,0.0000060055486,0.000494856,0.000068467954,0.0000038164103,0.000014071356],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983546,0.00016067183,0.0008010563,0.00020894266,0.00031546372,0.0001592568],"domain_scores_gemma":[0.9982281,0.00016211503,0.0006129689,0.000414165,0.0005522284,0.00003046865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013785461,0.00013971914,0.0002933786,0.0005244374,0.0001765981,0.00010790667,0.00035920469,0.0000656619,0.0000010474371],"category_scores_gemma":[0.00017393992,0.00014228844,0.000027950851,0.00084606215,0.0000773382,0.0025855314,0.000121558514,0.000116008814,0.0000018398688],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000080535734,0.00026052783,0.02665568,0.0003553967,0.000049683615,3.2606895e-8,0.051972244,0.08192484,0.0002455427,0.014996875,0.00008648757,0.8233722],"study_design_scores_gemma":[0.0011334415,0.00015854427,0.12430596,0.00018942116,0.000028898814,0.0000011256776,0.00564911,0.8665447,0.00019499929,0.0016384862,0.000053446387,0.000101846854],"about_ca_topic_score_codex":0.0003264357,"about_ca_topic_score_gemma":0.00013615016,"teacher_disagreement_score":0.8232703,"about_ca_system_score_codex":0.00015250425,"about_ca_system_score_gemma":0.00016571487,"threshold_uncertainty_score":0.5802354},"labels":[],"label_agreement":null},{"id":"W4413332798","doi":"10.29313/bcsurp.v5i2.20362","title":"Tingkat Resiliensi Masyarakat dalam Menghadapi Banjir Rob di Kawasan Pesisir Eretan Kabupaten Indramayu","year":2025,"lang":"en","type":"article","venue":"Bandung Conference Series Urban & Regional Planning","topic":"Data Mining and Machine Learning 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":"Encana (Canada)","funders":"","keywords":"Environmental science","score_opus":0.02428716182748476,"score_gpt":0.27331409998352363,"score_spread":0.24902693815603888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413332798","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":[0.30014312,0.00342339,0.5307467,0.02970726,0.0021630395,0.0016083233,0.00010809585,0.004133504,0.12796652],"genre_scores_gemma":[0.9702056,0.000037974514,0.014114941,0.000506943,0.00014230968,0.00008156574,0.00027707635,0.00003010708,0.014603467],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99695563,0.000190938,0.00055368827,0.001084723,0.0005059702,0.0007090698],"domain_scores_gemma":[0.9976756,0.0003454803,0.00028743467,0.0012177201,0.00026305244,0.00021073657],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00048915175,0.00045589553,0.00047695372,0.0003266908,0.00083395734,0.0007490267,0.0017787165,0.0002040948,0.000031257085],"category_scores_gemma":[0.0001971779,0.00044617022,0.00012513739,0.0008232103,0.00025253027,0.001058423,0.0006248201,0.00070647954,0.000049539492],"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":[0.00019512395,0.00016675609,0.07944961,0.00015748754,0.0002465435,0.00013189462,0.0065977047,0.001515301,0.0024290208,0.78505576,0.08174895,0.04230587],"study_design_scores_gemma":[0.0017595955,0.00044071104,0.33861265,0.001794266,0.00014527213,0.00026793257,0.002188165,0.054414745,0.002091649,0.009781587,0.5864094,0.0020940355],"about_ca_topic_score_codex":0.00012809463,"about_ca_topic_score_gemma":0.000033573026,"teacher_disagreement_score":0.77527416,"about_ca_system_score_codex":0.00008753267,"about_ca_system_score_gemma":0.00043586874,"threshold_uncertainty_score":0.999799},"labels":[],"label_agreement":null},{"id":"W4413332863","doi":"10.29313/bcsurp.v5i2.20184","title":"Analisis Spasio-Temporal Perkembangan Lahan Terbangun Menggunakan Pendekatan Machine Learning","year":2025,"lang":"en","type":"article","venue":"Bandung Conference Series Urban & Regional Planning","topic":"Data Mining and Machine Learning 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":"Encana (Canada)","funders":"","keywords":"Computer science; Environmental science","score_opus":0.024659855915155914,"score_gpt":0.2716429885445512,"score_spread":0.2469831326293953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413332863","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":[0.20422766,0.004935597,0.6953128,0.027820002,0.0014270284,0.0011861614,0.00016756561,0.004276654,0.06064652],"genre_scores_gemma":[0.9779233,0.000042270454,0.011695858,0.0006118958,0.0001302635,0.00006535519,0.00067195424,0.000027233154,0.008831898],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99725825,0.00023493641,0.00047920964,0.0009493211,0.00046611574,0.0006121787],"domain_scores_gemma":[0.9982251,0.00021934959,0.0002644212,0.0008860528,0.00019807651,0.00020699429],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005273544,0.0004271325,0.00044025618,0.00040736704,0.00094637304,0.00070850196,0.0015436619,0.00015540021,0.00005248464],"category_scores_gemma":[0.00017045565,0.00042017404,0.0001362686,0.00086396164,0.00018855478,0.0010769458,0.0005360263,0.000834917,0.00003403276],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021124142,0.00020863445,0.29980373,0.0001651347,0.00033758467,0.00017638822,0.008756285,0.0012173742,0.0023778994,0.58786297,0.075706005,0.023176735],"study_design_scores_gemma":[0.0015395704,0.0004656634,0.092988454,0.0009337904,0.00012032883,0.00022147206,0.0034012091,0.06672079,0.0009676838,0.00330697,0.8277199,0.001614152],"about_ca_topic_score_codex":0.0006057555,"about_ca_topic_score_gemma":0.00008514179,"teacher_disagreement_score":0.7736956,"about_ca_system_score_codex":0.0000815135,"about_ca_system_score_gemma":0.00031410012,"threshold_uncertainty_score":0.999825},"labels":[],"label_agreement":null},{"id":"W4413368007","doi":"10.18280/mmep.120708","title":"Modeling Malaria Risk Factors by Logistic Regression Among Hilly Communities in Rural East Nusa Tenggara Province, Indonesia","year":2025,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Data Mining and Machine Learning 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":"Logistic regression; Geography; Malaria; Socioeconomics; Statistics; Biology; Mathematics","score_opus":0.0200195610439639,"score_gpt":0.2280762288666865,"score_spread":0.20805666782272259,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413368007","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":[0.36262664,0.00013834034,0.63666236,0.00008451652,0.000029827084,0.00014251674,0.0000058521837,0.00022064029,0.00008927449],"genre_scores_gemma":[0.96324813,0.00006195412,0.036502175,0.000008293625,0.0000074118225,0.000060549806,0.000029646553,0.0000185084,0.00006334658],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99877024,0.000057456993,0.00040090247,0.0002691447,0.00015913644,0.00034311603],"domain_scores_gemma":[0.9990945,0.00022998269,0.00006405458,0.0004913096,0.000031346888,0.0000888124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047849392,0.00024462942,0.0003008112,0.00020759265,0.00020103551,0.00023468863,0.0005139911,0.00011994164,7.815229e-7],"category_scores_gemma":[0.00006385392,0.00020083568,0.0000387379,0.00027618292,0.000053552787,0.00025944924,0.0002440769,0.00059438084,0.0000024885364],"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":[0.0000016075289,0.00005619194,0.0019523875,0.00021101526,0.0000128857955,6.6034204e-7,0.0012416344,0.9655901,0.000033891924,0.030094173,0.000013171686,0.0007922626],"study_design_scores_gemma":[0.0001848693,0.000018893126,0.00029764447,0.0008667038,0.000014750197,0.0000025056916,0.00016783933,0.9929313,0.000007842352,0.005267295,0.0000307724,0.00020959004],"about_ca_topic_score_codex":0.0005994834,"about_ca_topic_score_gemma":0.0000067608858,"teacher_disagreement_score":0.60062146,"about_ca_system_score_codex":0.000036149904,"about_ca_system_score_gemma":0.00002497718,"threshold_uncertainty_score":0.81898415},"labels":[],"label_agreement":null},{"id":"W4413962022","doi":"10.30598/barekengvol19iss4pp2921-2936","title":"IMPUTATION OF MISSING DAILY RAINFALL DATA USING CONVOLUTIONAL NEURAL NETWORKS (CNN) WITH SPATIAL INTERPOLATION","year":2025,"lang":"en","type":"article","venue":"BAREKENG JURNAL ILMU MATEMATIKA DAN TERAPAN","topic":"Data Mining and Machine Learning 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":"Innovation Cluster (Canada)","funders":"","keywords":"Convolutional neural network; Missing data; Imputation (statistics); Interpolation (computer graphics); Computer science; Multivariate interpolation; Artificial intelligence; Spatial analysis; Pattern recognition (psychology); Artificial neural network; Cartography; Data mining; Remote sensing; Machine learning; Bilinear interpolation; Geography; Computer vision","score_opus":0.022142397035147716,"score_gpt":0.2952108729441247,"score_spread":0.273068475908977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413962022","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0894887,0.00009924851,0.90897846,0.00056271564,0.00021455337,0.00021642828,0.00003609145,0.00013651763,0.0002673084],"genre_scores_gemma":[0.8855765,0.0000023034581,0.11370005,0.00016922144,0.0000737529,0.000008603417,0.00042383408,0.000014587942,0.000031144897],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99811184,0.00019896076,0.0006104814,0.0005005414,0.0003101232,0.00026806176],"domain_scores_gemma":[0.9980552,0.0002094898,0.00046362466,0.0009992444,0.00019098342,0.000081438295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006190981,0.0002104481,0.00030064821,0.00027718046,0.00030883597,0.00036203794,0.0012270944,0.00007110906,0.000008319171],"category_scores_gemma":[0.00010144541,0.00018764498,0.000046070738,0.0005312974,0.00009349692,0.0010927392,0.0004794351,0.00028955148,0.0000020775226],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039294772,0.0007206554,0.058252595,0.0014007431,0.0008542998,0.000048711052,0.0053878245,0.23508123,0.012642783,0.0637073,0.005300745,0.61621016],"study_design_scores_gemma":[0.0004647568,0.00005598383,0.016977234,0.000402693,0.000048020498,0.00006169768,0.000077881494,0.98101187,0.00008204204,0.0004016428,0.00024004668,0.00017613103],"about_ca_topic_score_codex":0.0003286008,"about_ca_topic_score_gemma":0.000032457796,"teacher_disagreement_score":0.7960878,"about_ca_system_score_codex":0.00005232825,"about_ca_system_score_gemma":0.00017340465,"threshold_uncertainty_score":0.76519406},"labels":[],"label_agreement":null},{"id":"W4415303139","doi":"10.18280/isi.300817","title":"Recognition of Illegible Digits on Indonesian Election C1 Forms Using Convolutional Neural Network for Recapitulation Information System (SIREKAP)","year":2025,"lang":"","type":"article","venue":"Ingénierie des systèmes d information","topic":"Data Mining and Machine Learning 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":"Universitas Sriwijaya","keywords":"Convolutional neural network; Information system; Feature (linguistics); Artificial neural network; Indonesian; Key (lock)","score_opus":0.0212111104702927,"score_gpt":0.25652443746133274,"score_spread":0.23531332699104004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415303139","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":[0.1344268,0.0000751217,0.8553536,0.00017826821,0.0019462368,0.0019913148,0.0003784676,0.00035832493,0.0052918787],"genre_scores_gemma":[0.9776424,0.000020035064,0.018318333,0.00024880562,0.00021299954,0.00034152492,0.0031508803,0.000019238905,0.00004576588],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99580413,0.00020616682,0.0023052008,0.0003821515,0.00060517644,0.00069717946],"domain_scores_gemma":[0.9949152,0.0003271558,0.0022692515,0.00067894696,0.0016807755,0.00012866537],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0016058563,0.00048426888,0.00057719887,0.0012773555,0.0016005724,0.0009957536,0.0005738643,0.00042905254,0.0000059856807],"category_scores_gemma":[0.00060647936,0.00052186445,0.0002431761,0.0024066437,0.00019731677,0.012748378,0.00017100426,0.00039314452,0.000058617818],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047791575,0.00007599736,0.0008302347,0.0026729545,0.0001607898,1.8944012e-7,0.0030665996,0.24188708,0.000053629472,0.119729266,0.0013071056,0.6297383],"study_design_scores_gemma":[0.0015712159,0.00045912038,0.0075500305,0.002126915,0.0001386136,0.00003748487,0.00092923397,0.97706634,0.00055417337,0.0049103484,0.004165731,0.0004908056],"about_ca_topic_score_codex":0.00033819492,"about_ca_topic_score_gemma":0.000012871498,"teacher_disagreement_score":0.84321564,"about_ca_system_score_codex":0.0012060092,"about_ca_system_score_gemma":0.0006166188,"threshold_uncertainty_score":0.9997233},"labels":[],"label_agreement":null},{"id":"W4415349534","doi":"10.59934/jaiea.v5i1.1625","title":"Analysis of Student Satisfaction Sentiment Towards Lecturer Performance using the Naive Bayes Classifier Method (Case Study: STMIK KAPUTAMA)","year":2025,"lang":"","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Naive Bayes classifier; Classifier (UML); Weighting; Preprocessor; Python (programming language); Bayes' theorem; Terminology","score_opus":0.046450799770287605,"score_gpt":0.3716912860643848,"score_spread":0.3252404862940972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415349534","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":[0.36302322,0.0004471589,0.63552,0.0003491675,0.00022934399,0.00038437088,0.000011420832,0.000018566236,0.000016755497],"genre_scores_gemma":[0.9555843,0.00027785788,0.043860137,0.000040354724,0.00013076939,0.000060014794,0.0000028049378,0.000015122652,0.00002864619],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969734,0.00018789309,0.0014913556,0.0005013914,0.00052983395,0.00031615118],"domain_scores_gemma":[0.99713045,0.00044690588,0.000852974,0.0008349757,0.00060587993,0.0001288256],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0020246706,0.0003250962,0.0006526774,0.0011953764,0.00062299875,0.00041490217,0.00076310954,0.00012122453,0.000017682692],"category_scores_gemma":[0.00007496079,0.0002676694,0.00027846967,0.0038516608,0.0001275351,0.00037973895,0.00031230418,0.00072037155,0.0000025469149],"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":[0.000015031835,0.00034955694,0.0037460835,0.00004810782,0.0017499253,0.000009596553,0.004466473,0.559002,0.0016140193,0.0023788302,0.000016652633,0.42660373],"study_design_scores_gemma":[0.00006860779,0.00023611715,0.014697267,0.00009974993,0.0030192058,0.0001748745,0.0061162068,0.9720397,0.0025405558,0.00014955724,0.0006206823,0.00023749108],"about_ca_topic_score_codex":0.00043559057,"about_ca_topic_score_gemma":0.000040695726,"teacher_disagreement_score":0.59256107,"about_ca_system_score_codex":0.00015759568,"about_ca_system_score_gemma":0.0002475728,"threshold_uncertainty_score":0.9999775},"labels":[],"label_agreement":null},{"id":"W4415359958","doi":"10.59934/jaiea.v5i1.1520","title":"Data Mining Using K-Means Algorithm for Clustering Snack Sales at CV Sinar Pangan Utama","year":2025,"lang":"","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Cluster analysis; Purchasing; Product (mathematics); Production (economics); Component (thermodynamics); k-means clustering","score_opus":0.07832876410570443,"score_gpt":0.34116048551417494,"score_spread":0.2628317214084705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415359958","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0059913713,0.002097311,0.9887765,0.0014536952,0.00069977617,0.000548724,0.00031024034,0.00008686408,0.000035530993],"genre_scores_gemma":[0.1171106,0.0007321323,0.88062626,0.00011974417,0.0009046799,0.000076342876,0.00013138384,0.00006317461,0.00023570083],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99664176,0.000056898385,0.0015369973,0.0008308224,0.00033473232,0.0005988004],"domain_scores_gemma":[0.9963911,0.00075571326,0.0007143336,0.0014264194,0.00044883922,0.0002635923],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015260965,0.00042711085,0.00059858174,0.000677816,0.0009152875,0.000674846,0.0021460538,0.00021003392,0.000007102682],"category_scores_gemma":[0.00031188843,0.00047028114,0.00017338466,0.0012514979,0.00017986752,0.0008151852,0.0011563227,0.0005388205,0.000015603724],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021844706,0.00017473374,0.000038264647,0.00020065633,0.00019107945,0.000004580889,0.0007720086,0.11638637,0.0059207915,0.005074164,0.00058449875,0.870631],"study_design_scores_gemma":[0.0000950122,0.00012702595,0.00008143619,0.00047805873,0.00025672512,0.00014116325,0.00062665844,0.94360536,0.0013948543,0.0005721853,0.052236516,0.00038500433],"about_ca_topic_score_codex":0.000042612774,"about_ca_topic_score_gemma":0.000027992934,"teacher_disagreement_score":0.870246,"about_ca_system_score_codex":0.00020068986,"about_ca_system_score_gemma":0.00030430843,"threshold_uncertainty_score":0.9997749},"labels":[],"label_agreement":null},{"id":"W4415359962","doi":"10.59934/jaiea.v5i1.1489","title":"Application of the K-Means Clustering Method to Cluster Stunting Cases Based on Family Economics in Langkat Regency","year":2025,"lang":"","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Cluster analysis; Cluster (spacecraft); Quality (philosophy); Process (computing); Euclidean distance; Developing country","score_opus":0.025080138746559656,"score_gpt":0.3070625887070044,"score_spread":0.28198244996044475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415359962","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013218127,0.0002076666,0.9819267,0.0035732766,0.00024971607,0.00060855976,0.000020984384,0.000023390043,0.0001716233],"genre_scores_gemma":[0.86471474,0.00007803817,0.13448891,0.0003965207,0.00013915752,0.00011678284,0.0000029958824,0.000020855936,0.000042029886],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99764884,0.0001012265,0.001294852,0.00044906448,0.00020502483,0.00030101143],"domain_scores_gemma":[0.9974574,0.0008101134,0.0005498842,0.0008395376,0.00022783075,0.000115275805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015517443,0.0002557844,0.0004076594,0.0007543105,0.000217188,0.00017545182,0.0011205177,0.0001261566,0.0000019583495],"category_scores_gemma":[0.0002664909,0.00023660967,0.00014680195,0.0016334923,0.000061383165,0.00020253146,0.00028451966,0.0005531219,0.000009171982],"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":[0.000021257702,0.00011266337,0.00021303467,0.000071895294,0.000018229215,4.648421e-7,0.00035308884,0.6515037,0.0019778982,0.01535622,0.00003337291,0.33033818],"study_design_scores_gemma":[0.000070245864,0.00011198193,0.001908147,0.00040982358,0.000053016796,0.000014016399,0.00032383265,0.9841425,0.0039147865,0.00087999896,0.007974958,0.00019672136],"about_ca_topic_score_codex":0.0002178098,"about_ca_topic_score_gemma":0.00007200995,"teacher_disagreement_score":0.8514966,"about_ca_system_score_codex":0.00014439102,"about_ca_system_score_gemma":0.00020319548,"threshold_uncertainty_score":0.9648662},"labels":[],"label_agreement":null},{"id":"W4415359978","doi":"10.59934/jaiea.v5i1.1500","title":"Grouping of Flood Victim Data Based on Damage Rate Using K-Means Algorithm Case Study: Binjai City Social Service","year":2025,"lang":"","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Flood myth; Cluster analysis; Service (business); Cluster (spacecraft); Test data; Food aid","score_opus":0.07971519573225548,"score_gpt":0.34982066790619026,"score_spread":0.27010547217393477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415359978","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.106654085,0.00013064753,0.8910261,0.0010954435,0.00034364258,0.0005161296,0.0001472768,0.000055997265,0.000030672232],"genre_scores_gemma":[0.8744991,0.000042140106,0.12482999,0.00015658245,0.00038005767,0.000028885175,0.000023004539,0.00003157111,0.000008702553],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966058,0.00018371094,0.001604853,0.00075681374,0.00042497242,0.00042384883],"domain_scores_gemma":[0.99620736,0.00059995754,0.0008540213,0.0014616797,0.0006866373,0.00019032687],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0024823304,0.0004053428,0.00064432353,0.00091340067,0.00084069173,0.00041088197,0.0017593369,0.00017021518,0.000010344795],"category_scores_gemma":[0.00020577983,0.00044270494,0.0001288838,0.0029538686,0.00012480633,0.00068515306,0.00064860744,0.00095559866,0.000006615471],"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":[0.000046065394,0.0018989845,0.0002114422,0.00027694606,0.00034097256,0.00013011813,0.003603075,0.5087673,0.0025653942,0.0043563913,0.00006423033,0.47773907],"study_design_scores_gemma":[0.00016311284,0.00023294493,0.0003048789,0.0002746136,0.000368989,0.0001545523,0.003060742,0.9929325,0.0007628709,0.00021986183,0.001197064,0.0003278968],"about_ca_topic_score_codex":0.0007057279,"about_ca_topic_score_gemma":0.00005396627,"teacher_disagreement_score":0.767845,"about_ca_system_score_codex":0.00010823178,"about_ca_system_score_gemma":0.0004523995,"threshold_uncertainty_score":0.9998025},"labels":[],"label_agreement":null},{"id":"W4415360001","doi":"10.59934/jaiea.v5i1.1548","title":"Sentiment Analysis of Students on Campus Facilities and Infrastructure Using the Naïve Bayes Classifier Method (Case Study STMIK Kaputama)","year":2025,"lang":"","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Naive Bayes classifier; Classifier (UML); Sentiment analysis; Weighting; Precision and recall; Recall; The Internet","score_opus":0.030837187184120336,"score_gpt":0.36265678358909403,"score_spread":0.3318195964049737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415360001","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":[0.38399118,0.0003698787,0.6148691,0.00023941412,0.00013586182,0.0003342586,0.00003590862,0.000013612049,0.000010789336],"genre_scores_gemma":[0.9718217,0.00013894268,0.02779596,0.000041664975,0.00008097847,0.000038566817,0.000002623934,0.000012095904,0.00006745841],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99731684,0.00018054084,0.0012384993,0.000490935,0.00049727754,0.00027589197],"domain_scores_gemma":[0.9973211,0.0007699235,0.0006473133,0.0007480914,0.0003729487,0.0001406143],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001583541,0.00031701344,0.0006288635,0.0010913707,0.000541068,0.00052579254,0.0008213262,0.000115332194,0.000010874041],"category_scores_gemma":[0.00014132478,0.0002557424,0.00018615442,0.0023942809,0.00017689321,0.00024139571,0.00038730048,0.00066796463,0.0000011357204],"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":[0.000035343983,0.00066425925,0.0058251154,0.00010099186,0.0030180593,0.000029723895,0.011741808,0.6673328,0.0012329994,0.0145967165,0.000052358082,0.29536977],"study_design_scores_gemma":[0.00010643994,0.00033770295,0.005586305,0.00013236122,0.0024685173,0.00020305187,0.02326123,0.9639801,0.0010881906,0.0010392414,0.0015117452,0.00028512956],"about_ca_topic_score_codex":0.00029492297,"about_ca_topic_score_gemma":0.000034719542,"teacher_disagreement_score":0.58783054,"about_ca_system_score_codex":0.000083751824,"about_ca_system_score_gemma":0.00012942214,"threshold_uncertainty_score":0.9999895},"labels":[],"label_agreement":null},{"id":"W4415360182","doi":"10.59934/jaiea.v5i1.1567","title":"Predicting Population Growth Using Artificial Neural Network by Method Backpropagation (Case Study: Durian Lingga Village)","year":2025,"lang":"","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Backpropagation; Artificial neural network; Population; Test data; Rprop; Training set","score_opus":0.030589026747505427,"score_gpt":0.3254195862450864,"score_spread":0.29483055949758097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415360182","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":[0.23634537,0.00058680883,0.76089567,0.0006416902,0.00071183994,0.00068575173,0.000016979817,0.00009741532,0.000018466495],"genre_scores_gemma":[0.89804286,0.000078405734,0.10060996,0.000059274254,0.0010727493,0.000058685495,0.000018666398,0.00004058922,0.000018812749],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956639,0.00027958857,0.0022029376,0.0007800029,0.00047660017,0.000596966],"domain_scores_gemma":[0.99669117,0.00058855495,0.0011164246,0.000681507,0.00064387725,0.0002784609],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0026673493,0.0004732411,0.00064347294,0.0006727948,0.0012484659,0.0010147687,0.0007799808,0.0002379595,0.000008192679],"category_scores_gemma":[0.0003915765,0.0005185398,0.00018997464,0.0025528243,0.00008345789,0.00087961555,0.00030159557,0.0010454104,0.0000067991436],"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":[0.000037478774,0.0005071426,0.0020566196,0.00011679643,0.00019767969,0.000048562815,0.0012818213,0.5835301,0.0031876336,0.020716486,0.000084592815,0.38823503],"study_design_scores_gemma":[0.00008809807,0.00027511927,0.00047313597,0.00021554212,0.0003717741,0.0006613594,0.0016112155,0.99012053,0.0011711044,0.004209072,0.00039281943,0.00041025333],"about_ca_topic_score_codex":0.0010183823,"about_ca_topic_score_gemma":0.00006201573,"teacher_disagreement_score":0.6616975,"about_ca_system_score_codex":0.0001834669,"about_ca_system_score_gemma":0.00017307035,"threshold_uncertainty_score":0.9997266},"labels":[],"label_agreement":null},{"id":"W4415360187","doi":"10.59934/jaiea.v5i1.1555","title":"Analysis of the Pattern of the Relationship the Intensity of Playing Onilne Games and Learning Interest Using Association Rule Mining (Apriori) at STMIK KAPUTAMA","year":2025,"lang":"","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Association rule learning; Association (psychology); Process (computing); A priori and a posteriori; Intensity (physics); Dependency (UML)","score_opus":0.04197494850088286,"score_gpt":0.2905777059564659,"score_spread":0.24860275745558308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415360187","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":[0.62073874,0.00046480107,0.3775244,0.0009090707,0.0001750754,0.00015310771,0.000014202508,0.0000072023363,0.000013421371],"genre_scores_gemma":[0.997176,0.00010862133,0.0025447889,0.000026175665,0.000048009868,0.000008735608,0.0000026630532,0.000010846261,0.00007415063],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976524,0.00021066832,0.0013227325,0.0002771998,0.00032029438,0.00021670922],"domain_scores_gemma":[0.9949184,0.0019084634,0.0019432959,0.0006206589,0.0005599312,0.00004922968],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019910051,0.00019925695,0.00050829997,0.0004464365,0.0007133593,0.00012622654,0.0007911001,0.00013284948,0.0000045147085],"category_scores_gemma":[0.0014446046,0.00013947878,0.00027946677,0.0024647564,0.00024898694,0.00020234048,0.00061072054,0.000819177,6.252482e-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":[0.00002920758,0.00018313977,0.3878716,0.00020571679,0.0013264026,3.051445e-7,0.009814703,0.46161175,0.021833388,0.007156904,0.00003604941,0.10993083],"study_design_scores_gemma":[0.00006171198,0.0000545746,0.2420195,0.0006444466,0.0014638018,0.000014840204,0.0020347307,0.7438391,0.009063485,0.00035550262,0.00029230272,0.00015602491],"about_ca_topic_score_codex":0.00020975216,"about_ca_topic_score_gemma":0.00005250838,"teacher_disagreement_score":0.37643728,"about_ca_system_score_codex":0.00015158516,"about_ca_system_score_gemma":0.0001397934,"threshold_uncertainty_score":0.568778},"labels":[],"label_agreement":null},{"id":"W4415360468","doi":"10.59934/jaiea.v5i1.1491","title":"Clustering of PLN ULP Binjai Timur Customer Complaints using the K-Means Method","year":2025,"lang":"","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Complaint; Cluster analysis; Process (computing); Service (business); Cluster (spacecraft); Customer satisfaction","score_opus":0.0419261428328928,"score_gpt":0.34357737548929596,"score_spread":0.30165123265640315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415360468","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034102658,0.0008089219,0.99317193,0.0015706418,0.00042566765,0.00035059117,0.000033050415,0.00003973617,0.00018920105],"genre_scores_gemma":[0.68971866,0.00030990972,0.30943918,0.00008249862,0.00032054912,0.000027170383,0.000004649859,0.000026326137,0.00007102761],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970824,0.0001286028,0.0015780223,0.00042385393,0.00038310463,0.00040402467],"domain_scores_gemma":[0.9967681,0.00089478586,0.0008140807,0.0008468002,0.00050885906,0.00016734797],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001958913,0.00032535827,0.00058199686,0.0007035344,0.0005423359,0.00032985536,0.0014765976,0.00015806897,0.000015088165],"category_scores_gemma":[0.00020797188,0.0002831337,0.00021578454,0.0019726856,0.0002276579,0.00036325256,0.0004193219,0.00086709316,0.000016585618],"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":[0.000016927119,0.00014211638,0.000106873784,0.00016570967,0.00021330983,0.0000018667649,0.0013449123,0.55123425,0.0074833473,0.043889217,0.00013950578,0.395262],"study_design_scores_gemma":[0.000057961635,0.00007709855,0.0002979822,0.00039697858,0.00024922116,0.00008490293,0.00064965995,0.97634584,0.004864597,0.0015131598,0.015213389,0.00024919258],"about_ca_topic_score_codex":0.00012850924,"about_ca_topic_score_gemma":0.0000075541298,"teacher_disagreement_score":0.68630844,"about_ca_system_score_codex":0.000095984025,"about_ca_system_score_gemma":0.00024140904,"threshold_uncertainty_score":0.9999621},"labels":[],"label_agreement":null},{"id":"W4415360479","doi":"10.59934/jaiea.v5i1.1654","title":"Application of Sentiment Analysis on Product Reviews of the Binjai Langkat Buket Shop to Improve Customer Service using the Naive Bayes Method","year":2025,"lang":"","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Sentiment analysis; Naive Bayes classifier; Preprocessor; Product (mathematics); Service (business); Data pre-processing; Term (time); Social media","score_opus":0.02912346353215059,"score_gpt":0.34369016298416977,"score_spread":0.3145666994520192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415360479","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008928535,0.00083442486,0.9843116,0.0046153306,0.00021084053,0.0009957536,0.00003737156,0.000014319756,0.00005182106],"genre_scores_gemma":[0.90667915,0.00037161887,0.09210489,0.00031291065,0.00022733261,0.00018385795,0.000005395258,0.000020557365,0.00009426555],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972979,0.00016873314,0.0014439019,0.00046586178,0.00038031003,0.000243302],"domain_scores_gemma":[0.99635375,0.00041371828,0.0011115506,0.00135448,0.0006668811,0.00009964004],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021568495,0.0002626929,0.00061214325,0.0006426705,0.00029315462,0.00012502466,0.0013968541,0.00008021009,0.0000073219785],"category_scores_gemma":[0.00024379503,0.00018126592,0.00030199086,0.005506281,0.00008776021,0.00015838484,0.00032566895,0.00046799297,0.000012761668],"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":[0.00002653704,0.0002778473,0.0002336187,0.0002522533,0.0005446598,1.443902e-7,0.0017197136,0.510158,0.07652265,0.026832433,0.00016030982,0.38327187],"study_design_scores_gemma":[0.00004518952,0.00008982098,0.0009901009,0.00034352785,0.0015235619,0.000009115779,0.00049887813,0.875858,0.094415724,0.00066219445,0.025307463,0.00025642235],"about_ca_topic_score_codex":0.0002102462,"about_ca_topic_score_gemma":0.000019008952,"teacher_disagreement_score":0.8977506,"about_ca_system_score_codex":0.000084512896,"about_ca_system_score_gemma":0.00015050698,"threshold_uncertainty_score":0.7391809},"labels":[],"label_agreement":null},{"id":"W4415360486","doi":"10.59934/jaiea.v5i1.1672","title":"Application of Data Mining Using Apriori to Find Patterns of Asthma in Medical Record Data at the Health Center (Case Study: Datar City Health Center)","year":2025,"lang":"","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Medical record; Association rule learning; Community health center; Health care; Medical diagnosis; Public health; Service (business); Asthma; Health informatics","score_opus":0.11326588724308415,"score_gpt":0.4056239899540298,"score_spread":0.29235810271094564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415360486","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":[0.20385928,0.0005817011,0.7886905,0.005025481,0.0002165634,0.0008797259,0.00072828407,0.000015164255,0.0000032944972],"genre_scores_gemma":[0.9468399,0.00068513723,0.051724475,0.00026054753,0.00019522214,0.000036441197,0.00022356684,0.000024664861,0.000010013214],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9948585,0.00025614235,0.0027787916,0.0009548636,0.0006670088,0.00048466228],"domain_scores_gemma":[0.9939101,0.0005892598,0.0014493566,0.003446227,0.0002545213,0.00035054455],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0056092804,0.0003150492,0.0007744131,0.0006671312,0.00040475486,0.00014949199,0.0039929035,0.00011195902,0.000012088125],"category_scores_gemma":[0.00037754193,0.00029284882,0.00006715245,0.0017825078,0.00012449533,0.00063456193,0.0032964272,0.0007379131,0.0000032919077],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047374026,0.0012092931,0.013620613,0.00029133764,0.00011102742,0.000012855583,0.003190324,0.007794374,0.0001466679,0.0007126027,0.00034473062,0.9725188],"study_design_scores_gemma":[0.0002591228,0.00047429596,0.003758185,0.0011421274,0.000059801856,0.0005735263,0.0044176118,0.9719119,0.00009401046,0.000063999825,0.016947549,0.00029786502],"about_ca_topic_score_codex":0.0044656065,"about_ca_topic_score_gemma":0.0024444018,"teacher_disagreement_score":0.97222096,"about_ca_system_score_codex":0.00020540107,"about_ca_system_score_gemma":0.00080354343,"threshold_uncertainty_score":0.9999524},"labels":[],"label_agreement":null},{"id":"W4415360523","doi":"10.59934/jaiea.v5i1.1671","title":"Analysis of Public Sentiment on Twitter Social Media the Design of the Latest Jersey of the Indonesian Football Team using the Support Vector Machine (SVM) Method","year":2025,"lang":"","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Support vector machine; Social media; Football; Crawling; Indonesian; Preprocessor; Sentiment analysis; Data pre-processing","score_opus":0.06646702783838783,"score_gpt":0.3261573677013767,"score_spread":0.2596903398629889,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415360523","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":[0.023197075,0.00019853018,0.9682126,0.007491951,0.0003078663,0.00048663706,0.00004465564,0.000010220996,0.000050430943],"genre_scores_gemma":[0.99021196,0.00007002278,0.009426769,0.00009319923,0.00012099497,0.000032716755,0.000003219913,0.000014728322,0.000026388845],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970249,0.00041032693,0.0013845041,0.00030337746,0.00058899046,0.0002879064],"domain_scores_gemma":[0.9955372,0.001549061,0.0013608476,0.0010261246,0.0004574789,0.00006926742],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031276802,0.00025650839,0.00053629326,0.0004825716,0.0005858286,0.00016152381,0.002128165,0.000116297815,0.00001436855],"category_scores_gemma":[0.00036864707,0.00013986931,0.00044717724,0.004039132,0.00040370182,0.00013488438,0.0003945151,0.0007201162,0.0000011730401],"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":[0.000042180825,0.000619314,0.0017765089,0.00009548958,0.0020949212,4.0077995e-7,0.0100345295,0.81887037,0.02149045,0.04641649,0.00030294617,0.09825642],"study_design_scores_gemma":[0.0000788672,0.00009236556,0.010729843,0.00013833061,0.0019891623,0.0000144880705,0.0014725883,0.9615917,0.021047305,0.001034936,0.001615651,0.00019475666],"about_ca_topic_score_codex":0.000093441646,"about_ca_topic_score_gemma":0.000025522651,"teacher_disagreement_score":0.9670149,"about_ca_system_score_codex":0.0000757663,"about_ca_system_score_gemma":0.00033811003,"threshold_uncertainty_score":0.5703705},"labels":[],"label_agreement":null},{"id":"W4415360527","doi":"10.59934/jaiea.v5i1.1436","title":"Application of the Apriori Algorithm to Determine Public Service Patterns at the Subdistrict Office","year":2025,"lang":"","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Service (business); Government (linguistics); Association rule learning; Apriori algorithm; Type of service; Queue","score_opus":0.023772280508773877,"score_gpt":0.2727495034042238,"score_spread":0.24897722289544993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415360527","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":[0.021058986,0.0006367092,0.96192676,0.015098659,0.00039551995,0.0007044449,0.00007953186,0.000035753616,0.000063646716],"genre_scores_gemma":[0.9805929,0.0002725163,0.017878765,0.00052193156,0.000313347,0.000195845,0.000013063367,0.000025978135,0.00018563271],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972383,0.0000891989,0.0013328134,0.00048012202,0.00046774783,0.00039186253],"domain_scores_gemma":[0.99620646,0.0005856722,0.00077863486,0.0014276716,0.0007999653,0.00020159071],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011265251,0.00030976054,0.00039008987,0.00038360342,0.00065640395,0.0003370577,0.0024022863,0.00013762101,0.000011182755],"category_scores_gemma":[0.00025363098,0.00023036054,0.00018503229,0.0033693914,0.00012939244,0.00028111172,0.0008455346,0.000627096,0.000042418178],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013529825,0.00019876641,0.0004130202,0.00011996786,0.00009396544,5.580489e-7,0.00068708893,0.026088435,0.005246915,0.02109975,0.0003089307,0.9457291],"study_design_scores_gemma":[0.00009555047,0.00014264732,0.008873739,0.00029171153,0.0002583575,0.000100421814,0.0005029812,0.83725756,0.014933065,0.0010611424,0.13605519,0.00042765174],"about_ca_topic_score_codex":0.00022201995,"about_ca_topic_score_gemma":0.0001059159,"teacher_disagreement_score":0.95953393,"about_ca_system_score_codex":0.0001579617,"about_ca_system_score_gemma":0.00026375553,"threshold_uncertainty_score":0.93938303},"labels":[],"label_agreement":null},{"id":"W4415360528","doi":"10.59934/jaiea.v5i1.1658","title":"Prediction of Criminal Theft Locations at the Binjai Police Station using Historical Data and the KNN Algorithm","year":2025,"lang":"","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Government (linguistics); Traffic police; Pattern recognition (psychology); Statistical classification; Contextual design","score_opus":0.0659592560163019,"score_gpt":0.3140605746167451,"score_spread":0.24810131860044318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415360528","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006875114,0.0028776156,0.984438,0.0048269015,0.00037749513,0.00039974268,0.00014501746,0.000024134542,0.000035966706],"genre_scores_gemma":[0.8966772,0.00363235,0.098290116,0.0001661189,0.0007367284,0.000088331835,0.000071083414,0.00003434821,0.00030370994],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977062,0.00013086587,0.0011742219,0.00039946905,0.00034914995,0.00024010924],"domain_scores_gemma":[0.99670976,0.0009521066,0.00068659236,0.0011204974,0.00042603316,0.00010498602],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019136884,0.00021927766,0.00033677192,0.00034645668,0.00082308135,0.00025800292,0.0012666249,0.000103987986,0.0000055325568],"category_scores_gemma":[0.00025642858,0.00015863556,0.000082971856,0.0010922259,0.0004343713,0.00046116975,0.0006114613,0.0005448982,0.0000037335885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006800147,0.0002533181,0.000105389605,0.00016050022,0.00024785462,5.909934e-7,0.0062439493,0.067432396,0.002580378,0.08226921,0.001055859,0.83958256],"study_design_scores_gemma":[0.00011154233,0.000067826215,0.00048371073,0.00013261262,0.000463496,0.00009291573,0.0011619929,0.9783922,0.0006274089,0.0017079725,0.016633535,0.0001247852],"about_ca_topic_score_codex":0.0008200194,"about_ca_topic_score_gemma":0.000039197126,"teacher_disagreement_score":0.9109598,"about_ca_system_score_codex":0.00020895155,"about_ca_system_score_gemma":0.00026508875,"threshold_uncertainty_score":0.646897},"labels":[],"label_agreement":null},{"id":"W4415360709","doi":"10.59934/jaiea.v5i1.1669","title":"Clustering of High-Achieving Students Based on Scores at Junior High School Level Using K-Means Algorithm","year":2025,"lang":"","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Cluster analysis; Variance (accounting); k-means clustering; MATLAB; Process (computing); Quality (philosophy); Educational data mining","score_opus":0.037044006440008624,"score_gpt":0.31505614537899007,"score_spread":0.27801213893898147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415360709","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061644945,0.0003875389,0.93609947,0.00069965963,0.00062009227,0.00039336339,0.000080796424,0.000050453928,0.000023689341],"genre_scores_gemma":[0.70099515,0.00018776371,0.29830712,0.00008771038,0.0002583747,0.0000342541,0.000010329221,0.000031236967,0.000088087276],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965778,0.00008770556,0.001606862,0.0005960199,0.0006676145,0.00046397498],"domain_scores_gemma":[0.9970032,0.0004830724,0.00084759097,0.00091763836,0.00045746495,0.0002910274],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011789583,0.00041843136,0.0006604609,0.0011106916,0.00056575343,0.00042960315,0.0015365932,0.00018455065,0.0000238817],"category_scores_gemma":[0.00028026433,0.00044399087,0.00019260436,0.0015786785,0.00017315669,0.00040173603,0.00055239134,0.0007791646,0.00001917411],"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":[0.000040595933,0.00035060692,0.00043974502,0.0001609325,0.00012411363,0.000004458858,0.00019660419,0.7148492,0.0053851744,0.005042708,0.00005460211,0.27335128],"study_design_scores_gemma":[0.0001637557,0.0002500995,0.004583501,0.0011441819,0.00019035384,0.000028209075,0.00012635077,0.9851977,0.0065593864,0.00048814455,0.0009125559,0.00035574104],"about_ca_topic_score_codex":0.00028159286,"about_ca_topic_score_gemma":0.00001596227,"teacher_disagreement_score":0.6393502,"about_ca_system_score_codex":0.00029196983,"about_ca_system_score_gemma":0.00031847786,"threshold_uncertainty_score":0.99980116},"labels":[],"label_agreement":null},{"id":"W4415360714","doi":"10.59934/jaiea.v5i1.1665","title":"Application of Apriori Algorithm to Find Patterns of Population Mortality Data (Case Study: Disdukcapil Stabat)","year":2025,"lang":"","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Data Mining and Machine Learning 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":"Association rule learning; Apriori algorithm; Lift (data mining); Population; A priori and a posteriori","score_opus":0.05159913931514169,"score_gpt":0.3551423865809216,"score_spread":0.3035432472657799,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415360714","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":[0.27018175,0.0002645204,0.7280979,0.00027872357,0.00018805447,0.00072933483,0.00022712302,0.00002526778,0.0000073028723],"genre_scores_gemma":[0.9457631,0.00015290291,0.053706788,0.00001907246,0.00017377778,0.00007691399,0.000067771674,0.000020378386,0.000019290694],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99628633,0.000091063936,0.0021343695,0.00068804953,0.00050290994,0.00029727546],"domain_scores_gemma":[0.9956404,0.00035851015,0.0010766571,0.0020941717,0.00061849976,0.00021176584],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001845391,0.00031302657,0.0006548927,0.0007479594,0.00022919355,0.00016843458,0.0016454008,0.00013106938,0.0000057971606],"category_scores_gemma":[0.00024604314,0.0003348665,0.00011146809,0.0017581355,0.000072775234,0.0005838203,0.0007221406,0.00048050913,0.0000053424033],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015952723,0.0010417766,0.007251788,0.00023354609,0.00022996911,0.00001035897,0.0017031804,0.042508658,0.0017071945,0.011807261,0.000033461278,0.93345684],"study_design_scores_gemma":[0.00014320745,0.00046463465,0.03318397,0.00031656298,0.0005166117,0.00014181444,0.0032886574,0.9564347,0.0020596157,0.0013207169,0.0017067128,0.00042276474],"about_ca_topic_score_codex":0.0024792717,"about_ca_topic_score_gemma":0.00012153183,"teacher_disagreement_score":0.93303406,"about_ca_system_score_codex":0.000073441675,"about_ca_system_score_gemma":0.00016312134,"threshold_uncertainty_score":0.99991035},"labels":[],"label_agreement":null},{"id":"W4416450850","doi":"10.29244/xplore.v12i3.1150","title":"Penerapan Algoritma C4.5 dan Random Forest pada Tingkat Penjualan Serum Somethinc di Shopee","year":2023,"lang":"","type":"article","venue":"Xplore Journal of Statistics","topic":"Data Mining and Machine Learning 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":"Random forest; Product (mathematics); Class (philosophy); Order (exchange); Decision tree; Quarter (Canadian coin)","score_opus":0.03505902659280467,"score_gpt":0.3033430336342516,"score_spread":0.2682840070414469,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416450850","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043214865,0.00036666877,0.9464034,0.0044003595,0.003680541,0.00032734123,0.0010820865,0.00017170684,0.00035305446],"genre_scores_gemma":[0.7801799,0.0019303274,0.2122121,0.00040485561,0.0020695478,0.000020800984,0.000353089,0.0001405595,0.0026888344],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99447685,0.000543873,0.0018429271,0.0006542984,0.001485444,0.0009966283],"domain_scores_gemma":[0.9933493,0.0020437785,0.001889145,0.0010700136,0.0009664088,0.0006813594],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0034934247,0.0005507578,0.000982407,0.0006921894,0.0009616788,0.0010765217,0.0025097139,0.00019465045,0.00009410136],"category_scores_gemma":[0.001935301,0.00051003444,0.00026339415,0.0016906341,0.00029544707,0.00095822534,0.00084735773,0.0017158613,0.0003236574],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019734967,0.0005025848,0.0125524085,0.00031545045,0.00060197595,0.0010524899,0.014297705,0.01699425,0.0004089805,0.028027283,0.15388596,0.7711636],"study_design_scores_gemma":[0.0065972647,0.0019793217,0.060609363,0.00070593075,0.0006341313,0.00088976056,0.0023371817,0.8165153,0.00021068733,0.015082217,0.09312012,0.0013187045],"about_ca_topic_score_codex":0.00013987384,"about_ca_topic_score_gemma":0.000094466035,"teacher_disagreement_score":0.7995211,"about_ca_system_score_codex":0.00012403513,"about_ca_system_score_gemma":0.00076848775,"threshold_uncertainty_score":0.9999605},"labels":[],"label_agreement":null},{"id":"W4416631721","doi":"10.62951/bridge.v3i4.685","title":"Implementasi Sistem Temu Balik Informasi Data Cryptocurrency Berbasis Atribut Menggunakan Vector Space Model (VSM)","year":2025,"lang":"","type":"article","venue":"Bridge","topic":"Data Mining and Machine Learning 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":"Vector space model; Cosine similarity; Weighting; Cryptocurrency; Preprocessor; Consistency (knowledge bases); Information system; Similarity (geometry); Data retrieval","score_opus":0.06077041168444132,"score_gpt":0.3555866888063148,"score_spread":0.29481627712187347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416631721","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040605115,0.0018554612,0.94635576,0.016487854,0.0015088343,0.0014618867,0.0045027817,0.0006761637,0.02309077],"genre_scores_gemma":[0.90079147,0.00070492516,0.072476946,0.001735756,0.00043855936,0.00029779278,0.006426472,0.00008195776,0.017046109],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99424064,0.00023631618,0.0013574922,0.0020332907,0.0007979646,0.0013342679],"domain_scores_gemma":[0.991644,0.00037948095,0.00060416217,0.0066474318,0.00028749337,0.00043743462],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0016572446,0.00074150896,0.00072586833,0.00037520725,0.0012446615,0.0012768821,0.0070759556,0.00022751743,0.000046436253],"category_scores_gemma":[0.0005520869,0.00081804424,0.00023198017,0.0019046385,0.00019303168,0.0020432614,0.0073109292,0.00092647626,0.0003020062],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026665779,0.00040705633,0.0027768086,0.0003462423,0.00030974566,0.000008285948,0.0014240462,0.0015166393,0.00009487295,0.25742927,0.26621038,0.46944997],"study_design_scores_gemma":[0.0008060093,0.0000746361,0.007045452,0.00018102452,0.00019156725,0.000012515503,0.000071294744,0.50730604,0.000108950895,0.00032332606,0.48332784,0.00055135053],"about_ca_topic_score_codex":0.00051018386,"about_ca_topic_score_gemma":0.00012136226,"teacher_disagreement_score":0.89673096,"about_ca_system_score_codex":0.00028158387,"about_ca_system_score_gemma":0.0015924313,"threshold_uncertainty_score":0.9997599},"labels":[],"label_agreement":null},{"id":"W4417142765","doi":"10.56971/jwi.v9i2.323","title":"ANALISIS KLASIFIKASI SARAN PESERTA PELATIHAN MENGGUNAKAN PENDEKATAN MACHINE LEARNING","year":2024,"lang":"","type":"article","venue":"Jurnal Kewidyaiswaraan/Jurnal kewidyaiswaraan","topic":"Data Mining and Machine Learning 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":"WiLAN (Canada)","funders":"","keywords":"Naive Bayes classifier; AdaBoost","score_opus":0.020313113410232196,"score_gpt":0.2843137575026259,"score_spread":0.2640006440923937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417142765","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":[0.27176064,0.14197548,0.38354003,0.04742687,0.02986229,0.0064523704,0.0037462122,0.0129424175,0.10229368],"genre_scores_gemma":[0.9683223,0.0056489846,0.005560091,0.0010106912,0.0038575223,0.00022349587,0.0010981052,0.0007650678,0.013513771],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9755079,0.002809536,0.005168378,0.006353687,0.0049439655,0.0052165217],"domain_scores_gemma":[0.98613524,0.002221413,0.002049428,0.0048479224,0.0011248525,0.0036211566],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"category_scores_codex":[0.005963367,0.0038789366,0.0032953606,0.003950606,0.0050454,0.010911006,0.008605481,0.0015354761,0.002075337],"category_scores_gemma":[0.0015064431,0.0038798552,0.002630463,0.0087316455,0.0011516882,0.006672786,0.0032053837,0.007969175,0.0053205355],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011946183,0.00383474,0.08784956,0.0045588217,0.007958642,0.008497029,0.023891775,0.013588286,0.006401529,0.08664068,0.048376337,0.707208],"study_design_scores_gemma":[0.0029100915,0.002403307,0.02401618,0.0035625973,0.0017639184,0.0056279427,0.0008552201,0.49106503,0.0009706197,0.0018696798,0.4596567,0.0052987337],"about_ca_topic_score_codex":0.002934599,"about_ca_topic_score_gemma":0.0004439066,"teacher_disagreement_score":0.70190924,"about_ca_system_score_codex":0.0014908918,"about_ca_system_score_gemma":0.0029805077,"threshold_uncertainty_score":0.99976075},"labels":[],"label_agreement":null},{"id":"W4417155087","doi":"10.33395/jmp.v14i2.15690","title":"Data Mining Untuk Memprediksi Penjualan","year":2025,"lang":"","type":"article","venue":"Jurnal Minfo Polgan","topic":"Data Mining and Machine Learning 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 Roads University","funders":"","keywords":"Naive Bayes classifier; Informatics engineering; Pattern recognition (psychology); Classifier (UML)","score_opus":0.03879283527059328,"score_gpt":0.33960855663128325,"score_spread":0.30081572136068996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417155087","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":[0.07204369,0.005171918,0.5691448,0.068249345,0.0107860565,0.0013258144,0.0030172297,0.0013045261,0.26895666],"genre_scores_gemma":[0.8969333,0.00024654792,0.053819083,0.0039274753,0.0010990854,0.000038314647,0.0008411193,0.00006203725,0.043033004],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9954783,0.0001909388,0.0010865845,0.0016131882,0.00065130764,0.0009796896],"domain_scores_gemma":[0.9928022,0.00054206885,0.0005168006,0.0055270214,0.00019825061,0.0004136533],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0015491005,0.0005348774,0.0005915456,0.0006005379,0.001020531,0.0015047429,0.008249659,0.0002496928,0.00014964488],"category_scores_gemma":[0.0008667793,0.0005630355,0.00013949905,0.0018727301,0.0002777429,0.0014710388,0.005330635,0.001030505,0.000509424],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003113344,0.00029235412,0.009147229,0.000126873,0.00030268612,0.000042944586,0.0022758378,0.000086226064,0.00032533536,0.028672392,0.268111,0.690586],"study_design_scores_gemma":[0.0009320565,0.00017500635,0.025273291,0.0005615328,0.0002725535,0.00010593406,0.0004922277,0.20017084,0.00017046412,0.0004351987,0.7706895,0.00072139216],"about_ca_topic_score_codex":0.0005007347,"about_ca_topic_score_gemma":0.00012575588,"teacher_disagreement_score":0.82488966,"about_ca_system_score_codex":0.00011511024,"about_ca_system_score_gemma":0.0012184321,"threshold_uncertainty_score":0.9996821},"labels":[],"label_agreement":null},{"id":"W6923500016","doi":"10.1371/journal.pone.0221361.t002","title":"Size and age of burbot, lake whitefish and northern pike collected from Great Slave Lake, Northwest Territories, Canada.","year":2019,"lang":"en","type":"dataset","venue":"Figshare","topic":"Data Mining and Machine Learning 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":"Pike; Fish <Actinopterygii>; Fishing; Esox; Shore","score_opus":0.013502084262150377,"score_gpt":0.21675405217765267,"score_spread":0.2032519679155023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6923500016","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":[0.00015580654,0.00020150101,0.00000530334,0.00009623055,0.00014654335,0.00026797788,0.9990109,0.000053669064,0.00006203361],"genre_scores_gemma":[0.00018384721,0.000019056106,0.00034808784,0.0001624621,0.00014336355,0.000096960255,0.9984957,0.000021004156,0.0005295445],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982909,0.000063332795,0.00030804754,0.000725798,0.00034109308,0.00027085643],"domain_scores_gemma":[0.99748707,0.00059492537,0.00033149237,0.0012630436,0.0001587515,0.00016474548],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00004007659,0.00033731048,0.0004807679,0.00007163673,0.00015347941,0.00024970458,0.0010683271,0.00021560953,0.0032648307],"category_scores_gemma":[0.0007348097,0.00033549723,0.000033437926,0.00033132444,0.000022452623,0.00014420768,0.00076853187,0.00042974332,0.000045797253],"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":[0.0000031065197,0.000015294823,0.00068054994,0.00015369925,0.000043744796,0.000044585257,0.00007365612,0.00000475868,6.133639e-7,4.946501e-7,0.9983726,0.00060687773],"study_design_scores_gemma":[0.00026580365,0.00004343092,0.034426965,0.00058966957,0.000030890707,0.0000146775865,0.0000055698297,0.000101637735,0.0000015428074,0.000005488919,0.96418715,0.00032717077],"about_ca_topic_score_codex":0.4364719,"about_ca_topic_score_gemma":0.9956156,"teacher_disagreement_score":0.55914366,"about_ca_system_score_codex":0.000036272068,"about_ca_system_score_gemma":0.00071851566,"threshold_uncertainty_score":0.9999097},"labels":[],"label_agreement":null},{"id":"W7006235579","doi":"","title":"Swords, Clunks and Widowmakers : The Tumultuous Life of the RCAF's Original 1 Canadian Air Division = Swords, clunks et widowmakers : la vie tumultueuse de la 1re Division Aérienne du Canada d'Origine de l'Aviation Royale Canadienne","year":2015,"lang":"fr","type":"book","venue":"Virtual Defense Library (Ministerio de Defensa)","topic":"Data Mining and Machine Learning 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":"Division (mathematics); White (mutation); Colonialism; Tower","score_opus":0.009062785864072354,"score_gpt":0.2194447450905774,"score_spread":0.21038195922650504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7006235579","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":[0.8535651,0.0025529421,0.014261332,0.05338763,0.0035784943,0.0030033675,0.0077020177,0.0006232627,0.061325856],"genre_scores_gemma":[0.9596069,0.00045931683,0.0044975453,0.010577913,0.0004727904,0.0001537725,0.0011297096,0.0002593771,0.02284267],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9905793,0.0032966158,0.0013465441,0.0016312664,0.0010662283,0.0020800268],"domain_scores_gemma":[0.9901892,0.0032005857,0.0011952885,0.0024947887,0.00028413144,0.0026360399],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0031190761,0.0013129595,0.0011421356,0.0004257002,0.0017109181,0.0010998205,0.0031806077,0.0010031589,0.00006259768],"category_scores_gemma":[0.0017360119,0.0010766753,0.00034608328,0.0011388185,0.0016174215,0.0011085372,0.0015596037,0.0026946447,0.000027648184],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005449575,0.0005029657,0.06635362,0.00060753536,0.0008588834,0.0017820236,0.030240944,0.021396369,0.00021003863,0.25711137,0.5633127,0.05707856],"study_design_scores_gemma":[0.0011790197,0.0004992893,0.03187173,0.00080255314,0.00030667736,0.0011143516,0.00074769015,0.023544556,0.000029918414,0.001067339,0.9376515,0.0011853508],"about_ca_topic_score_codex":0.7531945,"about_ca_topic_score_gemma":0.8159083,"teacher_disagreement_score":0.3743388,"about_ca_system_score_codex":0.0016709927,"about_ca_system_score_gemma":0.03480655,"threshold_uncertainty_score":0.9999622},"labels":[],"label_agreement":null},{"id":"W7033816477","doi":"","title":"Rules and regulations of the mayor and aldermen for the government of the Halifax Police Department.","year":2014,"lang":"en","type":"article","venue":"QSpace (Queen's University Library)","topic":"Data Mining and Machine Learning 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":"Government (linguistics); State government; Legislation; Work (physics)","score_opus":0.005097148977275696,"score_gpt":0.18248906430698345,"score_spread":0.17739191532970774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7033816477","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":[0.45408526,0.000033269906,0.08620527,0.45119348,0.00012579496,0.0010257378,0.00045434746,0.000116222174,0.0067606266],"genre_scores_gemma":[0.97781116,0.0000283875,0.011689601,0.0002027345,0.000014182481,0.0000022942443,0.0000041453754,0.000005560292,0.01024196],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994596,0.00008492864,0.00006341517,0.00015231715,0.00014950421,0.000090229405],"domain_scores_gemma":[0.99897444,0.00031559737,0.00012601071,0.00053861056,0.000013644175,0.000031679847],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006996159,0.000065739805,0.00007589867,0.000016641223,0.0003256671,0.000034912206,0.0006541215,0.000024696552,0.0000024988556],"category_scores_gemma":[0.000023354478,0.00003937004,0.00003993289,0.00015563318,0.00016089603,0.0002735928,0.0006531928,0.000060217964,3.1499303e-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":[0.00002752168,0.000092481736,0.05546693,0.00006325495,0.000095958865,1.3992245e-7,0.0034831879,0.00034368125,0.00009108498,0.7966431,0.1324172,0.0112754535],"study_design_scores_gemma":[0.0005298246,0.000065917135,0.46736073,0.000047712605,0.00008689398,8.44031e-7,0.000732718,0.005133922,0.0018277763,0.0025116056,0.5215618,0.00014024484],"about_ca_topic_score_codex":0.0010323973,"about_ca_topic_score_gemma":0.000026510414,"teacher_disagreement_score":0.7941315,"about_ca_system_score_codex":0.000009782101,"about_ca_system_score_gemma":0.000031922373,"threshold_uncertainty_score":0.2504801},"labels":[],"label_agreement":null},{"id":"W7115067809","doi":"10.46576/device.v6i2.7432","title":"PENGELOMPOKAN DATA KELUHAN PASIEN PADA LAYANAN RUMAH SAKIT BERDASARKAN KATEGORI MASALAH MENGGUNAKAN METODE CLUSTERING","year":2025,"lang":"","type":"article","venue":"DEVICE JOURNAL OF INFORMATION SYSTEM COMPUTER SCIENCE AND INFORMATION TECHNOLOGY","topic":"Data Mining and Machine Learning 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":"Cluster analysis; Cluster (spacecraft); Statistical analysis; Variance components; Statistical hypothesis testing","score_opus":0.013315561709251376,"score_gpt":0.26801261521997893,"score_spread":0.2546970535107276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115067809","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004516739,0.000263397,0.97922695,0.008215357,0.0031618853,0.0006371079,0.00008302947,0.0003129335,0.003582607],"genre_scores_gemma":[0.8594892,0.0002093839,0.13764325,0.0022691702,0.00020798492,0.000022520446,0.00012405452,0.000011061774,0.000023375207],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9931421,0.00016836773,0.0037092303,0.00051431486,0.0016109312,0.0008550512],"domain_scores_gemma":[0.9895423,0.00016850304,0.003927932,0.0024904925,0.0035193393,0.00035145032],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.007806003,0.00053521653,0.00088563416,0.0060769455,0.0016232249,0.0037361686,0.007821985,0.00038392123,0.000005304641],"category_scores_gemma":[0.00050988153,0.0004923881,0.00010032071,0.006876796,0.0006841347,0.04766516,0.0049681296,0.0010843017,0.00013551724],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028745368,0.000033250035,0.0005415034,0.0008644572,0.00013496524,0.0000040684604,0.005167791,0.0021583498,0.000027487182,0.06903508,0.004955948,0.91704834],"study_design_scores_gemma":[0.0012647003,0.00035597265,0.001800367,0.0011264425,0.00008763475,0.00084574893,0.004784566,0.793748,0.00023990139,0.00016932821,0.19511376,0.0004635771],"about_ca_topic_score_codex":0.000092147886,"about_ca_topic_score_gemma":0.000010124977,"teacher_disagreement_score":0.9165848,"about_ca_system_score_codex":0.0005415631,"about_ca_system_score_gemma":0.002041534,"threshold_uncertainty_score":0.99975276},"labels":[],"label_agreement":null},{"id":"W7115071877","doi":"10.46576/device.v6i2.7277","title":"PENGCLUSTERAN JENIS USAHA UKM BERDASARKAN PROGRAM BANTUAN DI KOTA BINJAI MENGGUNAKAN ALGORITMA K-MEANS","year":2025,"lang":"","type":"article","venue":"DEVICE JOURNAL OF INFORMATION SYSTEM COMPUTER SCIENCE AND INFORMATION TECHNOLOGY","topic":"Data Mining and Machine Learning 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":"Cluster (spacecraft); Research Object; Cluster development","score_opus":0.006302317644186224,"score_gpt":0.2580249890898697,"score_spread":0.2517226714456835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115071877","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01402949,0.00019917933,0.96891403,0.008677005,0.0026331812,0.0011338333,0.000039403683,0.0004971518,0.0038766947],"genre_scores_gemma":[0.85736805,0.00020805001,0.13988507,0.0022287583,0.00015360945,0.00007809683,0.000037087568,0.000010538445,0.00003073562],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9931616,0.00015365527,0.003726785,0.0004132282,0.0016490552,0.0008956835],"domain_scores_gemma":[0.9894842,0.00015242735,0.0036164133,0.0013202027,0.0050435765,0.00038316328],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.00545474,0.000555053,0.00087437336,0.0069996356,0.0018066871,0.0042154402,0.0042914483,0.0004394904,0.0000058901674],"category_scores_gemma":[0.00044719272,0.00050211884,0.00016849127,0.008718262,0.00095673586,0.034472834,0.0017068875,0.0011378144,0.00015912206],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019598254,0.00007436578,0.00052916806,0.000509277,0.00007803443,0.0000024393992,0.00517082,0.0012162912,0.000013120358,0.07539839,0.0019300036,0.9150585],"study_design_scores_gemma":[0.0014571516,0.00090638065,0.00320808,0.0010310468,0.00007277676,0.0009306157,0.0036507118,0.7779281,0.0002629488,0.00010905931,0.2099892,0.0004539309],"about_ca_topic_score_codex":0.00004133507,"about_ca_topic_score_gemma":0.0000029404325,"teacher_disagreement_score":0.91460454,"about_ca_system_score_codex":0.0005463262,"about_ca_system_score_gemma":0.0019738895,"threshold_uncertainty_score":0.99974304},"labels":[],"label_agreement":null},{"id":"W7126173975","doi":"10.18280/isi.301225","title":"Predicting Tourist Visits Using LSTM for Smart Eco-Tourism Management in Banyuanyar Village, Indonesia: A Comparative Analysis with ARIMA and Prophet","year":2025,"lang":"","type":"article","venue":"Ingénierie des systèmes d information","topic":"Data Mining and Machine Learning 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":"Kementerian Pendidikan, Kebudayaan, Riset, dan Teknologi","keywords":"Tourism; Autoregressive integrated moving average; Key (lock); Time series; Field (mathematics)","score_opus":0.014593925509433224,"score_gpt":0.27385140564626137,"score_spread":0.25925748013682814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7126173975","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":[0.3885181,0.00015158762,0.60525113,0.00012809112,0.00011388212,0.0013903414,0.000064900094,0.00010322852,0.0042787176],"genre_scores_gemma":[0.9323038,0.00003697032,0.06679204,0.00014374002,0.000035299785,0.0003662341,0.00020539627,0.000010958796,0.00010556108],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99703115,0.0001748678,0.0012261977,0.00060410594,0.0003690707,0.0005946051],"domain_scores_gemma":[0.9977223,0.00021487265,0.000864742,0.0006835013,0.0003900093,0.00012453167],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001167467,0.0004464,0.00072505267,0.0018320493,0.0010245498,0.0014711975,0.0005868893,0.00017066687,0.000003791695],"category_scores_gemma":[0.0000786272,0.00044028825,0.00011182126,0.0038791962,0.00020008654,0.0033822535,0.00046545104,0.0003453944,0.0000058683204],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007562119,0.00053798605,0.28111893,0.005791589,0.005730196,0.000035285604,0.07330548,0.17259054,0.000061388266,0.04594927,0.0007457817,0.41337734],"study_design_scores_gemma":[0.0014617662,0.00019019266,0.12047057,0.0007598255,0.0007780258,0.000018797306,0.0026868489,0.87132365,0.000067263136,0.00060094194,0.0012201307,0.00042198846],"about_ca_topic_score_codex":0.00063100026,"about_ca_topic_score_gemma":0.0002314788,"teacher_disagreement_score":0.6987331,"about_ca_system_score_codex":0.00044399893,"about_ca_system_score_gemma":0.00022709262,"threshold_uncertainty_score":0.9998049},"labels":[],"label_agreement":null},{"id":"W7131363961","doi":"10.62951/switch.v2i5.226","title":"Clustering Menggunakan Algoritma K-Means untuk Mengelompokan Data Perjudian Berdasarkan Wilayah di Kota Binjai (Studi Kasus : Pengadilan Negeri Binjai)","year":2024,"lang":"","type":"article","venue":"Switch Jurnal Sains dan Teknologi Informasi","topic":"Data Mining and Machine Learning 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":"Cluster analysis; Centroid; Group (periodic table); Center (category theory); Pattern recognition (psychology)","score_opus":0.03849528211345137,"score_gpt":0.30288759636451695,"score_spread":0.2643923142510656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7131363961","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":[0.18123484,0.022520801,0.6066361,0.051628396,0.024010362,0.007073234,0.0049418993,0.012151512,0.08980284],"genre_scores_gemma":[0.9703047,0.004016399,0.017066658,0.0010704712,0.0022019583,0.0002082517,0.0025349879,0.00029005858,0.0023064602],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98754585,0.00057837117,0.0029438678,0.0035483274,0.0018757879,0.0035077953],"domain_scores_gemma":[0.9888356,0.00081932184,0.001018534,0.0074060387,0.00041902481,0.0015014814],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","open_science"],"category_scores_codex":[0.003989885,0.0020079613,0.0016491546,0.0015507241,0.0031861074,0.005257573,0.012186058,0.00088097353,0.00007510087],"category_scores_gemma":[0.0008803834,0.0019067511,0.0005567121,0.0040729516,0.0008944624,0.0060686753,0.011297101,0.0052651432,0.0008110324],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011796286,0.0005644223,0.006169772,0.00071613054,0.0014372594,0.00081774744,0.017087627,0.0029866346,0.0005690312,0.015993804,0.01610656,0.93743306],"study_design_scores_gemma":[0.0010221583,0.0009146486,0.007435798,0.0007566153,0.0003149655,0.00096417015,0.0021145032,0.5030585,0.000111270405,0.00012253971,0.48142037,0.0017644677],"about_ca_topic_score_codex":0.00066104723,"about_ca_topic_score_gemma":0.0011806464,"teacher_disagreement_score":0.9356686,"about_ca_system_score_codex":0.001008914,"about_ca_system_score_gemma":0.002349961,"threshold_uncertainty_score":0.999967},"labels":[],"label_agreement":null},{"id":"W7154487029","doi":"10.66341/fusion.v2i1.261","title":"Pengelompokkan Pendonor Darah Berdasarkan Golongan Darah Di PMI Kabupaten Langkat Menggunakan Metode Clustering K-Means","year":2025,"lang":"","type":"article","venue":"Fusion Journal of Research in Engineering Technology and Applied Sciences","topic":"Data Mining and Machine Learning 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":"Cluster analysis; Cluster (spacecraft)","score_opus":0.032425217049756164,"score_gpt":0.3440130041183888,"score_spread":0.31158778706863266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7154487029","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":[0.6481262,0.0051022433,0.30823526,0.031282548,0.0011225996,0.0008071852,0.000018653696,0.0003143133,0.0049910094],"genre_scores_gemma":[0.96363586,0.0006932155,0.035289906,0.000029592353,0.000104414976,0.00004109865,0.0000021483108,0.000015987247,0.00018776965],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959841,0.00019730085,0.0009235583,0.0008733439,0.0009147039,0.0011069934],"domain_scores_gemma":[0.9977056,0.0007789658,0.00031411814,0.0007209873,0.00023855829,0.00024181556],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.008154787,0.00035180998,0.00063538476,0.005854907,0.0010731537,0.00051403063,0.0035826003,0.000305945,0.000013526652],"category_scores_gemma":[0.00059808395,0.00031522682,0.00007940434,0.0071917246,0.0012731405,0.00047760564,0.0023020573,0.002905244,0.000010700357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023055892,0.00092432863,0.02006278,0.0009961241,0.00027685027,0.00041191874,0.004453271,0.10511598,0.0672332,0.2941777,0.001620009,0.5044973],"study_design_scores_gemma":[0.0033180318,0.0021084654,0.018811325,0.004242392,0.00008853404,0.00085052854,0.00499671,0.8972785,0.013816916,0.015704613,0.037514664,0.0012693362],"about_ca_topic_score_codex":0.000044135846,"about_ca_topic_score_gemma":0.000031717216,"teacher_disagreement_score":0.7921625,"about_ca_system_score_codex":0.00013421703,"about_ca_system_score_gemma":0.000497311,"threshold_uncertainty_score":0.99992996},"labels":[],"label_agreement":null},{"id":"W893501441","doi":"","title":"Data Mining: Implementasi Regresi Linear Untuk Prediksi Nilai Ujian","year":2013,"lang":"id","type":"article","venue":"","topic":"Data Mining and Machine Learning 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":"Linear regression; Statistics; Data mining; Proper linear model; Computer science; Linear model; Mathematics; Bayesian multivariate linear regression","score_opus":0.06588370321750264,"score_gpt":0.33650543921071807,"score_spread":0.27062173599321543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W893501441","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03387741,0.0012055007,0.6493244,0.09524588,0.0036129057,0.0041192505,0.0035104689,0.0033091668,0.20579498],"genre_scores_gemma":[0.22570284,0.00023979817,0.59089917,0.0048120823,0.0016270946,0.00030008683,0.006879415,0.00016451348,0.16937503],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99552333,0.00023044331,0.00080814393,0.0018272455,0.0006165885,0.0009942333],"domain_scores_gemma":[0.99214864,0.00033675885,0.00036923826,0.0064202514,0.00021250619,0.0005125992],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009338943,0.0004803195,0.0004258799,0.00019673127,0.0006264176,0.001149976,0.0066999868,0.00017305925,0.002518711],"category_scores_gemma":[0.00033471067,0.00044227214,0.00008631907,0.0007956246,0.00018377909,0.001971885,0.0052051865,0.00054769614,0.008384874],"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":[0.0000032562045,0.00021728383,0.0030520987,0.000039413277,0.00009283639,0.0000068683967,0.0008065172,0.000011019994,0.00020412236,0.006041152,0.84990644,0.13961896],"study_design_scores_gemma":[0.00054803176,0.00021566892,0.006682927,0.000056277586,0.00006625272,0.000041078638,0.0004909594,0.18161704,0.00016176386,0.00018326321,0.80936223,0.0005744948],"about_ca_topic_score_codex":0.0022962037,"about_ca_topic_score_gemma":0.0002566802,"teacher_disagreement_score":0.19182542,"about_ca_system_score_codex":0.00005690319,"about_ca_system_score_gemma":0.00035827557,"threshold_uncertainty_score":0.99988693},"labels":[],"label_agreement":null}]}