{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":280,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":280,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"d7ed052de473","filters":{"topic":"Data Mining and Machine Learning Applications"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02683354521457981,"gpt":0.4465176621825136,"spread":0.4196841169679338,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001403989,0.00009144628,0.0001761903,0.0001332216,0.0005592072,0.0003975374,0.002188739,0.0001259773,0.00001182646],"category_scores_gemma":[0.0005682755,0.00007710826,0.0001114888,0.0002792868,0.00004431514,0.0002224176,0.0005903717,0.0005618266,0.00002947774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001511561,"about_ca_system_score_gemma":0.00002321199,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000615145,"about_ca_topic_score_gemma":0.00000933129,"domain_scores_codex":[0.9989833,0.0001993806,0.0001176542,0.0003712502,0.0001641057,0.0001642922],"domain_scores_gemma":[0.9972376,0.0001751537,0.000163395,0.00228931,0.00005396213,0.00008057408],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000002504584,0.00006099746,0.007355157,0.000005565767,0.0003047526,0.00000611312,0.0002742806,0.0002241853,0.001333523,0.2606017,0.001712788,0.7281185],"study_design_scores_gemma":[0.0001724448,0.00001877826,0.4301294,0.000004322633,0.0001567563,0.000006438401,0.000004407341,0.1487022,0.001280094,0.003377536,0.4159323,0.0002153502],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002531118,0.0001244114,0.9810972,0.002764844,0.0003102655,0.00004977244,0.000004276017,0.0001608927,0.01295728],"genre_scores_gemma":[0.2795486,0.000003308863,0.7194675,0.0002094708,0.00005307204,0.000009713109,0.000009866034,0.000003545073,0.0006949496],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7279031,"threshold_uncertainty_score":0.4301026,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.08228267693032645,"gpt":0.2974609950454966,"spread":0.2151783181151702,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004964884,0.0001493596,0.0003298922,0.0001105926,0.0003422734,0.00006875736,0.0002651623,0.00002204246,0.000004134055],"category_scores_gemma":[0.00002956002,0.0001355764,0.00002271684,0.00022604,0.00003768515,0.0001248543,0.0003763999,0.0004286308,9.765167e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001418789,"about_ca_system_score_gemma":0.00001091517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004565224,"about_ca_topic_score_gemma":2.660403e-7,"domain_scores_codex":[0.9988322,0.00008669219,0.0003243462,0.0003175739,0.0002741473,0.0001650717],"domain_scores_gemma":[0.9990427,0.000535675,0.0001185947,0.0001914677,0.00002764826,0.00008386882],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001961119,0.0001733409,0.0002053486,0.00009348807,0.00003136212,7.685975e-7,0.009185371,0.9759665,0.00001889824,0.01256047,0.000005398182,0.001757109],"study_design_scores_gemma":[0.0003546914,0.0002529511,0.0002609495,0.00004749384,0.00001733135,0.00001795026,0.000284897,0.985971,0.000005824015,0.01249599,0.0001517481,0.0001391188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2461611,0.0001101981,0.7532337,0.0001100951,0.00001196973,0.0001963968,0.00001013496,0.000131126,0.00003530441],"genre_scores_gemma":[0.8340712,0.000004097161,0.1658069,0.000003828233,0.000008912283,0.00005598409,0.00002290559,0.000009580514,0.00001653081],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5879101,"threshold_uncertainty_score":0.5528644,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Visualization; Computer science; Data science; Data visualization; Quarter (Canadian coin); World Wide Web; Data mining; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.06894903330201307,"gpt":0.3238826768715423,"spread":0.2549336435695292,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0009119696,0.0003024241,0.0003074522,0.0001492676,0.0003533144,0.0007177923,0.008151279,0.00009299805,0.000006927117],"category_scores_gemma":[0.0003092793,0.0002149006,0.00006399228,0.0003080253,0.0001056011,0.005196786,0.006173058,0.0003334678,0.0001440651],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008806303,"about_ca_system_score_gemma":0.0002459793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000774369,"about_ca_topic_score_gemma":0.0001229409,"domain_scores_codex":[0.9973902,0.00008227317,0.0007296292,0.0008627601,0.0004122223,0.0005229021],"domain_scores_gemma":[0.9932243,0.0002062028,0.0003976121,0.005798667,0.0000992709,0.0002739732],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002706078,0.0001268823,0.01155742,0.00005325337,0.00008884667,0.00001375894,0.0007510571,0.000006751555,0.0004436678,0.03578423,0.01535674,0.9357903],"study_design_scores_gemma":[0.0005658751,0.0001195721,0.0120541,0.0001224576,0.00002268621,0.0001472547,0.0001017005,0.01473919,0.0002697971,0.00002045749,0.9714659,0.0003709942],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.16278,0.000276833,0.7348547,0.02470722,0.003289149,0.001464748,0.000830796,0.002133542,0.06966295],"genre_scores_gemma":[0.9713989,0.00008631919,0.01895478,0.001853049,0.0007906464,0.00006908729,0.001895607,0.00005532784,0.004896269],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9561092,"threshold_uncertainty_score":0.9972151,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Encana (Canada)","funders":"","keywords":"Humanities; Sociology; Political science; Art","retraction":null,"screen_n_in":null,"score":{"opus":0.09912961771542043,"gpt":0.3519504096740539,"spread":0.2528207919586334,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00228416,0.0006203568,0.001401878,0.000302543,0.001854431,0.0005889182,0.01134455,0.0002102823,0.00004331668],"category_scores_gemma":[0.001771223,0.0005892092,0.0005033607,0.001269183,0.0009367483,0.00115332,0.006079595,0.002711039,0.00009705411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000274839,"about_ca_system_score_gemma":0.0005772242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003362763,"about_ca_topic_score_gemma":0.0003257678,"domain_scores_codex":[0.9931523,0.002630554,0.002081122,0.0004944874,0.001028664,0.0006129195],"domain_scores_gemma":[0.9874159,0.002028751,0.002687243,0.005053489,0.002224468,0.0005902076],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002723979,0.001348135,0.009572317,0.0007515592,0.004919466,0.00009795537,0.2319852,0.001097548,0.001341564,0.04162632,0.5310927,0.1758948],"study_design_scores_gemma":[0.003636682,0.002209939,0.02760841,0.003303088,0.001541432,0.000410226,0.06103455,0.00771597,0.0006224921,0.002070058,0.887939,0.001908124],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.08108847,0.396141,0.01562265,0.4842797,0.001682236,0.001361342,0.0003106919,0.0005609013,0.018953],"genre_scores_gemma":[0.926946,0.04274601,0.02594559,0.003486031,0.0002933251,0.00002331177,0.00008502243,0.00006616989,0.0004085821],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8458575,"threshold_uncertainty_score":0.9996559,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.07151672977805348,"gpt":0.3094294367601256,"spread":0.2379127069820721,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006409916,0.0002569297,0.0003787053,0.00007093241,0.0004188788,0.0003216759,0.0008759258,0.00007260099,0.000001506002],"category_scores_gemma":[0.0001634308,0.0001836904,0.00008496179,0.0002459109,0.0001162578,0.0002439601,0.0005753923,0.0002063692,0.00000269383],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001257282,"about_ca_system_score_gemma":0.00005773346,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002202161,"about_ca_topic_score_gemma":0.00001572024,"domain_scores_codex":[0.9980255,0.0001143044,0.0004711634,0.0008117149,0.0002618654,0.0003154447],"domain_scores_gemma":[0.998335,0.0005394503,0.0002130133,0.0006170462,0.00010889,0.0001865872],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007187495,0.0003268853,0.001332953,0.0001909324,0.000127675,0.0000128368,0.02710058,0.0108476,0.0001200015,0.0221119,0.001284874,0.9364719],"study_design_scores_gemma":[0.001030101,0.0006987593,0.003589516,0.00003423633,0.00006201176,0.00002834865,0.001061025,0.9882121,0.000007776018,0.004571322,0.0004909798,0.0002138009],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04937579,0.0003551134,0.9465964,0.002339348,0.0000940625,0.0006749309,0.00003916083,0.0001707183,0.0003544141],"genre_scores_gemma":[0.8033133,0.00002253363,0.1958374,0.0005320309,0.0001278137,0.00009483285,0.00001398584,0.00001574513,0.00004242125],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9773645,"threshold_uncertainty_score":0.7490675,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Innovation Cluster (Canada)","funders":"","keywords":"Humanities; Physics; Cluster (spacecraft); Computer science; Art; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.01845186821246702,"gpt":0.2422038322400252,"spread":0.2237519640275582,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00151453,0.0003204232,0.0006160185,0.0004992552,0.00035344,0.001083252,0.001429987,0.0001650218,0.00006849656],"category_scores_gemma":[0.000368911,0.0002813188,0.0003385495,0.001033428,0.00005574447,0.004023248,0.0002875419,0.0007395313,0.001255933],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002045521,"about_ca_system_score_gemma":0.0003653764,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005215477,"about_ca_topic_score_gemma":0.000002990481,"domain_scores_codex":[0.9960387,0.0003096105,0.002022973,0.0002255656,0.001017063,0.0003860444],"domain_scores_gemma":[0.9955427,0.0001259822,0.002422371,0.000612095,0.0007698865,0.0005269678],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004872796,0.0002724973,0.01339563,0.004139378,0.001490101,0.0001171123,0.2957827,0.03203478,0.0003915571,0.03435717,0.551167,0.06636482],"study_design_scores_gemma":[0.002736594,0.0008171453,0.006562016,0.0010515,0.0002421754,0.00109568,0.02280113,0.4692303,0.0001106287,0.000005602005,0.4946919,0.0006553713],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02369526,0.0001970791,0.91743,0.02502623,0.001549113,0.0005409043,0.0001660815,0.0002280967,0.03116716],"genre_scores_gemma":[0.9846135,0.00004314141,0.01112303,0.003287424,0.0006707362,0.00000886443,0.00005759436,0.00002005865,0.0001756097],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9609182,"threshold_uncertainty_score":0.9999639,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Encana (Canada)","funders":"","keywords":"Humanities; Psychology; Geography; Political science; Art","retraction":null,"screen_n_in":null,"score":{"opus":0.03719362288462801,"gpt":0.2768442814581239,"spread":0.2396506585734959,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.00158906,0.001587831,0.00140392,0.000431864,0.002418791,0.004559071,0.004981643,0.0005143501,0.0003258028],"category_scores_gemma":[0.001033844,0.001780369,0.0006322344,0.002677005,0.0004273403,0.0022123,0.002451385,0.002613644,0.001902353],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003956227,"about_ca_system_score_gemma":0.0009975976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008520503,"about_ca_topic_score_gemma":0.0002364065,"domain_scores_codex":[0.9890667,0.0009949134,0.001758055,0.003813489,0.001572467,0.00279436],"domain_scores_gemma":[0.9929413,0.0004444085,0.001039224,0.002672455,0.0004607586,0.002441891],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00045869,0.003480966,0.1502834,0.00532097,0.001352717,0.002092561,0.06297754,0.001293702,0.0294661,0.03240186,0.1248734,0.5859981],"study_design_scores_gemma":[0.005479548,0.003551703,0.08341929,0.002294611,0.00103587,0.0005491412,0.004050834,0.2879266,0.01291129,0.0004184778,0.5908722,0.007490396],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7189571,0.01169758,0.04577837,0.1038996,0.007485527,0.01836555,0.001792875,0.0141624,0.07786093],"genre_scores_gemma":[0.9719878,0.0002625074,0.01860261,0.002358701,0.001357999,0.0006790566,0.0009185316,0.0002972966,0.00353544],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5785077,"threshold_uncertainty_score":0.9996874,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02271163559400273,"gpt":0.2855543445041292,"spread":0.2628427089101265,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00134909,0.0005012964,0.0005325216,0.0003215422,0.0005037902,0.001221237,0.005299824,0.0001975737,0.00004507295],"category_scores_gemma":[0.0001954422,0.0004474347,0.0001397617,0.0006348631,0.000120427,0.004581845,0.002283481,0.0006242485,0.002133807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001137526,"about_ca_system_score_gemma":0.0004070984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009214997,"about_ca_topic_score_gemma":0.00002492902,"domain_scores_codex":[0.9961873,0.0001195114,0.001067357,0.0009174208,0.0008877163,0.0008207335],"domain_scores_gemma":[0.9942585,0.0001962602,0.0006896759,0.004206238,0.0002674328,0.0003819269],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002540834,0.00104091,0.313236,0.001099609,0.0006595453,0.00007674031,0.01856814,0.001908667,0.003082735,0.1375157,0.134385,0.3881728],"study_design_scores_gemma":[0.001120869,0.0002499689,0.04242899,0.0001328085,0.00003936254,0.00030087,0.0003585931,0.08078551,0.0003924631,0.000025327,0.8733604,0.0008048686],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7381752,0.0004558828,0.0801412,0.00531724,0.004572631,0.003650953,0.0003197291,0.003303734,0.1640635],"genre_scores_gemma":[0.9456784,0.00005853599,0.0428059,0.001784134,0.0004954332,0.0001331901,0.001846393,0.00008338367,0.007114602],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7389753,"threshold_uncertainty_score":0.9998156,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Humanities; Computer science; Mathematics; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.0259836335049272,"gpt":0.2926541658426853,"spread":0.2666705323377581,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002019663,0.001128112,0.00106716,0.0004955542,0.002279698,0.002171254,0.004020843,0.000394526,0.0001801239],"category_scores_gemma":[0.0003599502,0.001048715,0.0003378682,0.002225715,0.0007416672,0.001248787,0.001695146,0.001395694,0.000612763],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003491724,"about_ca_system_score_gemma":0.000723228,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00708749,"about_ca_topic_score_gemma":0.001094882,"domain_scores_codex":[0.9921205,0.0007970891,0.001223584,0.002615254,0.001414359,0.001829206],"domain_scores_gemma":[0.9939899,0.0005295377,0.0006958108,0.003076992,0.0007172066,0.0009905271],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002404528,0.003952062,0.103892,0.0005645068,0.00418039,0.0004498334,0.06829102,0.0001642464,0.01929719,0.486323,0.1372397,0.1754056],"study_design_scores_gemma":[0.009817769,0.01009497,0.2738976,0.001127154,0.003271384,0.000798372,0.0283636,0.2784318,0.01872991,0.003796691,0.3607478,0.01092296],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3745037,0.002477271,0.480845,0.01085371,0.005660834,0.002620936,0.000501602,0.002828292,0.1197086],"genre_scores_gemma":[0.9624571,0.0002189467,0.02491251,0.0007222043,0.001650726,0.00006899912,0.0004124466,0.0001266905,0.009430331],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5879534,"threshold_uncertainty_score":0.9995244,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06215650915473732,"gpt":0.38296671872973,"spread":0.3208102095749927,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008924146,0.00008424652,0.0001140004,0.000146763,0.0008968969,0.0004609138,0.003873322,0.00001649454,0.000006335258],"category_scores_gemma":[0.0007881727,0.00007312029,0.000007577087,0.0004391329,0.0003482127,0.001805979,0.00676479,0.0005748888,6.192204e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006217371,"about_ca_system_score_gemma":0.0002764777,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006713141,"about_ca_topic_score_gemma":0.00001299792,"domain_scores_codex":[0.9979538,0.0001734247,0.0003193608,0.0005174773,0.0008839851,0.000151962],"domain_scores_gemma":[0.9978667,0.0003994529,0.0002925376,0.0008774177,0.0004766264,0.00008723242],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000139191,0.0002905854,0.1211595,0.00004576073,0.0001591431,0.00003437509,0.001055488,0.02448654,0.00001176737,0.1319131,0.016965,0.7037395],"study_design_scores_gemma":[0.000526598,0.0001269351,0.3749745,0.00004736848,0.00002758417,0.0002279159,0.0003417539,0.5184596,0.000002506291,0.005423941,0.09964333,0.0001979807],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4113922,0.0008113105,0.5416112,0.04206872,0.001509076,0.0003103064,0.001419653,0.00004947592,0.0008281379],"genre_scores_gemma":[0.9572606,0.001006194,0.04084146,0.0005735985,0.0001336066,0.000002506637,0.0001134147,0.000003088184,0.00006551505],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7035416,"threshold_uncertainty_score":0.8431827,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Mathematics; Artificial intelligence; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.01560721734585094,"gpt":0.2792210424184654,"spread":0.2636138250726145,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001057942,0.0006080431,0.0006020801,0.0001744075,0.001035308,0.0007853738,0.00175751,0.0002381319,0.0005134887],"category_scores_gemma":[0.0002668275,0.0006498252,0.0002451547,0.001550378,0.0001759516,0.0008414607,0.001447381,0.0009651214,0.001501405],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004543663,"about_ca_system_score_gemma":0.001004205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001758876,"about_ca_topic_score_gemma":0.0008875385,"domain_scores_codex":[0.9944834,0.0006471921,0.000925823,0.001871685,0.0008609911,0.001210941],"domain_scores_gemma":[0.99551,0.000322161,0.0004183143,0.002815713,0.0004539546,0.0004797872],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000445005,0.001394359,0.02448695,0.0005388556,0.0007995102,0.0002966474,0.004233322,0.0006221084,0.01825167,0.5155877,0.2824416,0.1513027],"study_design_scores_gemma":[0.001719899,0.0003043503,0.0209855,0.0001782618,0.0001969058,0.0002381363,0.00157339,0.05018298,0.006678239,0.001734346,0.914912,0.001295934],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04837226,0.00617403,0.8449901,0.02792944,0.004283086,0.001372071,0.001500487,0.001851368,0.06352714],"genre_scores_gemma":[0.9076305,0.0008013058,0.05328422,0.001992809,0.0005856767,0.0001321858,0.001815834,0.00009076631,0.03366673],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8592582,"threshold_uncertainty_score":0.9995953,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Encana (Canada)","funders":"","keywords":"Flood myth; Geography; Population; Vulnerability (computing); Social vulnerability; Socioeconomics; Asset (computer security); Demography; Psychology; Sociology","retraction":null,"screen_n_in":null,"score":{"opus":0.0102894994642588,"gpt":0.2402598692315065,"spread":0.2299703697672477,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000413806,0.0001686694,0.0001700614,0.0001908216,0.0009966225,0.0002454247,0.001674685,0.00003185738,0.0002858409],"category_scores_gemma":[0.00002856649,0.0001754271,0.0001051444,0.0005811349,0.0000385307,0.000333424,0.0008023435,0.0005888283,0.0001049935],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001344446,"about_ca_system_score_gemma":0.0001563439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002683023,"about_ca_topic_score_gemma":0.00005219944,"domain_scores_codex":[0.9981862,0.00013822,0.0002791379,0.0004876632,0.0004892105,0.000419614],"domain_scores_gemma":[0.9987749,0.00006117259,0.000156213,0.0007715848,0.00002971235,0.0002064382],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003291761,0.0006010892,0.01940005,0.00003170525,0.0001489173,0.0002766125,0.005999996,0.002745625,0.003549032,0.3207458,0.177449,0.4690193],"study_design_scores_gemma":[0.0007574436,0.0003571547,0.04361431,0.00002207564,0.00003182329,0.0004242586,0.0006785517,0.03899102,0.0002084338,0.002694075,0.9115613,0.0006595952],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4269827,0.0008922964,0.388128,0.05360205,0.005697134,0.001179815,0.0003170522,0.002432232,0.1207687],"genre_scores_gemma":[0.9841706,0.000004123685,0.01157861,0.001323369,0.0002315088,0.0000758774,0.00006542795,0.00002168288,0.002528857],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7341123,"threshold_uncertainty_score":0.7665315,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Computer science; Operating system; Malware; Humanities; Art","retraction":null,"screen_n_in":null,"score":{"opus":0.01519276380883068,"gpt":0.2467422087838022,"spread":0.2315494449749715,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.003532324,0.001416806,0.001448622,0.001141454,0.005271194,0.003062089,0.005804196,0.0003675869,0.0001698766],"category_scores_gemma":[0.0005274532,0.001448152,0.0007665246,0.002962518,0.0004035561,0.006830865,0.004322641,0.003715936,0.0006190521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001171539,"about_ca_system_score_gemma":0.001204676,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001784925,"about_ca_topic_score_gemma":0.00004177171,"domain_scores_codex":[0.9891366,0.0005470532,0.003884929,0.00107606,0.003157125,0.002198277],"domain_scores_gemma":[0.9913759,0.0007007416,0.003131624,0.003136923,0.0005191339,0.001135632],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005585459,0.00136328,0.01824817,0.00246247,0.001303421,0.0002747751,0.1101589,0.01020727,0.0007055113,0.1626766,0.1188856,0.5731554],"study_design_scores_gemma":[0.002655995,0.001307411,0.007906782,0.0002857325,0.0001612207,0.002504031,0.009678742,0.05093091,0.000535173,0.00007964835,0.9221483,0.001806046],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2972808,0.004532442,0.07202879,0.009853512,0.01263083,0.007502184,0.001775198,0.00511721,0.5892791],"genre_scores_gemma":[0.9492847,0.000828304,0.01342461,0.005889529,0.0008824298,0.000982768,0.002795858,0.0002330613,0.02567877],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8032627,"threshold_uncertainty_score":0.9998582,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01028718361609056,"gpt":0.2599549192476049,"spread":0.2496677356315143,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002443614,0.000164009,0.0001621155,0.0001056805,0.000358106,0.0002208386,0.001219869,0.00005753558,0.00001426833],"category_scores_gemma":[0.00006713745,0.0001563509,0.00005370174,0.000454698,0.0001314259,0.0003497774,0.0003963918,0.000210051,0.0005316482],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003694659,"about_ca_system_score_gemma":0.0000635484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002681905,"about_ca_topic_score_gemma":0.00004034265,"domain_scores_codex":[0.9985785,0.00008934287,0.0001987992,0.0005251162,0.0002485101,0.0003597165],"domain_scores_gemma":[0.998427,0.00007543642,0.00009634847,0.001169683,0.000073639,0.0001578797],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00004139264,0.000522288,0.08261064,0.00007487068,0.0001399078,0.00008466514,0.007306345,0.0001326431,0.0103646,0.1666251,0.0973008,0.6347967],"study_design_scores_gemma":[0.001142318,0.0007690543,0.4747405,0.0001019709,0.00005293464,0.00009919444,0.0001717611,0.0872961,0.00316442,0.001982243,0.4293255,0.001154017],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.692494,0.00007880964,0.288232,0.002917457,0.0004186512,0.0001939596,0.0000229086,0.000723308,0.01491889],"genre_scores_gemma":[0.9849442,0.000006193558,0.01369859,0.0003566888,0.0003212475,0.00002575941,0.00005596946,0.00001955513,0.0005718314],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6336427,"threshold_uncertainty_score":0.6833439,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2327382594396288,"gpt":0.4188529535437773,"spread":0.1861146941041485,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008757698,0.0002315817,0.0003018584,0.0003548781,0.0006079383,0.0001846775,0.003485897,0.00003620779,0.00002222813],"category_scores_gemma":[0.00003782579,0.000228165,0.00003693408,0.000899775,0.00005623521,0.0002858276,0.003307151,0.0002953749,0.00002526331],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000324985,"about_ca_system_score_gemma":0.0006991948,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002785866,"about_ca_topic_score_gemma":0.00005784826,"domain_scores_codex":[0.9974275,0.0001944283,0.0004991698,0.001109303,0.0004623753,0.0003071956],"domain_scores_gemma":[0.9954361,0.0002725238,0.0003054495,0.003683645,0.0002174478,0.00008486871],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002021687,0.003878421,0.02551982,0.0004242337,0.0003685356,0.000002579539,0.003538075,0.0005696347,0.00007440907,0.08171933,0.5337983,0.3500864],"study_design_scores_gemma":[0.0002904726,0.00005846291,0.0977651,0.00004207245,0.0001771883,0.000009950599,0.002796096,0.0003509834,0.000003003775,0.000309724,0.8978973,0.0002996321],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.2794673,0.07224927,0.1450629,0.2109671,0.247036,0.01521457,0.009283939,0.004311126,0.01640779],"genre_scores_gemma":[0.9303774,0.00006417992,0.02409093,0.001193559,0.00212679,0.004240121,0.003739489,0.00004596902,0.03412154],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6509101,"threshold_uncertainty_score":0.93043,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"WiLAN (Canada)","funders":"","keywords":"Physics; Humanities; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.02114901149478854,"gpt":0.2690219916404388,"spread":0.2478729801456503,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001060978,0.0008623331,0.001269535,0.001171819,0.00130797,0.001181827,0.003965694,0.0007271858,0.0002862517],"category_scores_gemma":[0.0005472803,0.0008950602,0.0006987186,0.007349287,0.0004250018,0.0006574523,0.002759136,0.002424625,0.0007075632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003332963,"about_ca_system_score_gemma":0.000516568,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004417114,"about_ca_topic_score_gemma":0.0003702302,"domain_scores_codex":[0.9936274,0.0003525085,0.001240486,0.002260027,0.001022473,0.001497075],"domain_scores_gemma":[0.9943388,0.0002869684,0.0007061834,0.003722241,0.0005577226,0.0003880729],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001287954,0.003224057,0.08104263,0.0004644894,0.01220176,0.004332311,0.005364614,0.01626964,0.04269297,0.0426096,0.03533508,0.7563341],"study_design_scores_gemma":[0.004527342,0.001656516,0.06034615,0.000623815,0.006547225,0.002141437,0.007661894,0.7517858,0.01988509,0.002265337,0.1371541,0.005405353],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1039109,0.00453493,0.8639317,0.01247868,0.001354337,0.0005647905,0.0003567786,0.003369407,0.009498486],"genre_scores_gemma":[0.8636454,0.0006572946,0.122704,0.0002935406,0.0002760064,0.0001043037,0.0003504489,0.00008807924,0.01188085],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7597346,"threshold_uncertainty_score":0.9999922,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01918793801461597,"gpt":0.2743457013183178,"spread":0.2551577633037018,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001293928,0.0006817238,0.0007048188,0.0002989241,0.001065468,0.001377466,0.001898798,0.0002720865,0.0005012266],"category_scores_gemma":[0.0005697571,0.0006940122,0.0002779768,0.001670278,0.0001718352,0.00115887,0.001501441,0.0009874537,0.002417359],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002207351,"about_ca_system_score_gemma":0.0007532769,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004460809,"about_ca_topic_score_gemma":0.0002182211,"domain_scores_codex":[0.9943095,0.00062192,0.0009870607,0.002031685,0.0009995652,0.001050294],"domain_scores_gemma":[0.9953769,0.0003761832,0.0004199927,0.002655397,0.000656485,0.0005150367],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000141299,0.006366788,0.01507775,0.001658045,0.002974669,0.0005657434,0.03170688,0.003116297,0.09808704,0.3884033,0.1800009,0.2719012],"study_design_scores_gemma":[0.00758046,0.002037026,0.1239557,0.001442622,0.001789357,0.0007810597,0.0067041,0.3177808,0.08224891,0.002955056,0.4460911,0.006633827],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1478027,0.003779974,0.6312146,0.02757982,0.004538811,0.002420689,0.0002921933,0.003161154,0.1792101],"genre_scores_gemma":[0.8950723,0.0001699784,0.04885414,0.0009129354,0.0008160999,0.000159371,0.0005592743,0.0001119082,0.05334392],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7472697,"threshold_uncertainty_score":0.9996592,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Innovation Cluster (Canada)","funders":"","keywords":"Pollution; Geography; Java; Environmental pollution; Environmental protection; Ecology; Computer science; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.01530618588813311,"gpt":0.2430882416775816,"spread":0.2277820557894485,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00087447,0.0007103074,0.0007457711,0.0004888406,0.0005811317,0.0008741369,0.003832221,0.0003359507,0.0000246453],"category_scores_gemma":[0.0002568679,0.0006270317,0.0002242852,0.0007522346,0.0001865976,0.002475395,0.002723821,0.001202918,0.000647931],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001384049,"about_ca_system_score_gemma":0.0005964329,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003703084,"about_ca_topic_score_gemma":0.00002005441,"domain_scores_codex":[0.9953558,0.0001711498,0.001045956,0.001401483,0.0009077148,0.001117872],"domain_scores_gemma":[0.9955796,0.0005214459,0.0005922972,0.002600331,0.0003133836,0.0003929234],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001137699,0.0006291004,0.01987656,0.0002945104,0.0002824455,0.0002155887,0.0041934,0.001548409,0.007355724,0.5713111,0.01551217,0.3786673],"study_design_scores_gemma":[0.003683808,0.001639373,0.07883927,0.0005443824,0.00006938555,0.001503138,0.001063162,0.2702484,0.003904642,0.001657788,0.6339664,0.002880332],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7523385,0.0002442571,0.2085061,0.006171017,0.003370131,0.002226891,0.00007943786,0.003964552,0.02309904],"genre_scores_gemma":[0.8805441,0.00005222036,0.1152401,0.001138201,0.0002768761,0.00007544584,0.0008835842,0.00005419813,0.001735264],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6184542,"threshold_uncertainty_score":0.9996181,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01770645243964184,"gpt":0.2625500304331479,"spread":0.2448435779935061,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001947223,0.00008096446,0.0001256684,0.0001488033,0.0002699706,0.00002944084,0.0004991323,0.00001647618,0.00003044084],"category_scores_gemma":[0.00001302042,0.00008584551,0.00004806235,0.0001997138,0.00002639344,0.0001046595,0.0001791112,0.0001707421,0.000008817576],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001079745,"about_ca_system_score_gemma":0.0001473137,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003532939,"about_ca_topic_score_gemma":0.00003838801,"domain_scores_codex":[0.999206,0.00008412913,0.0001929718,0.0002545833,0.0001284092,0.0001338868],"domain_scores_gemma":[0.9991447,0.0001046748,0.0001364218,0.0005585342,0.0000120354,0.00004357843],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002968375,0.0001902193,0.00512954,0.000005205262,0.00000912137,7.306164e-7,0.0001436238,0.9792396,0.0001640258,0.003977011,0.0008663302,0.01024488],"study_design_scores_gemma":[0.0009367828,0.0001523601,0.006416748,0.000006271605,0.000009884622,0.000003819741,0.00003993683,0.9819843,0.00001699051,0.0001793153,0.0101711,0.00008244098],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3379849,0.00002785001,0.6577637,0.001486168,0.0003806359,0.0002598337,0.0002388819,0.0002081519,0.001649948],"genre_scores_gemma":[0.9851376,0.000001307491,0.01430432,0.000212046,0.0000774425,0.0000348457,0.0001508298,0.00001033601,0.00007127567],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6471527,"threshold_uncertainty_score":0.3500678,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.00804468182461166,"gpt":0.204745272260683,"spread":0.1967005904360714,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009243593,0.00009370226,0.00008827355,0.0002368702,0.0007859842,0.0001573978,0.0006824258,0.0000250802,0.00003549005],"category_scores_gemma":[0.00004937978,0.00008268457,0.00003209384,0.0006801996,0.00004252365,0.001364671,0.0002305952,0.0002684715,0.00005170151],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003604378,"about_ca_system_score_gemma":0.00007506002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007554624,"about_ca_topic_score_gemma":0.000006208086,"domain_scores_codex":[0.9989651,0.0001681559,0.0002244103,0.0001310812,0.0003432247,0.0001680457],"domain_scores_gemma":[0.9992192,0.0001464764,0.0001551271,0.0003968514,0.00005084703,0.00003153861],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001018406,0.0001614414,0.03599397,0.00005568498,0.00002320296,0.000004843372,0.01289587,0.5377764,0.000005472774,0.02064707,0.005094424,0.3872398],"study_design_scores_gemma":[0.0007159997,0.0001403935,0.07128498,0.00002195591,0.000003659017,0.000007606267,0.0008938598,0.9045227,0.000007495185,0.0001516894,0.02216307,0.00008665774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2184986,0.000007291379,0.7674803,0.0006415246,0.0002819114,0.0005423058,0.00009164984,0.0002451778,0.01221129],"genre_scores_gemma":[0.9957067,0.000004286213,0.003546299,0.0002921605,0.00001447504,0.00008610482,0.0001730929,0.000003616502,0.0001732067],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7772082,"threshold_uncertainty_score":0.6045234,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Encana (Canada)","funders":"","keywords":"Physics; Forestry; Horticulture; Biology; Mathematics; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.02938817875815523,"gpt":0.2744174585292508,"spread":0.2450292797710955,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","open_science"],"category_scores_codex":[0.004337547,0.001650619,0.001697087,0.001414712,0.005737295,0.003041485,0.01379777,0.0004245797,0.0004639473],"category_scores_gemma":[0.0005588021,0.001853297,0.0005157891,0.003403658,0.0006824367,0.006417392,0.01199178,0.00470402,0.0009079329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007264662,"about_ca_system_score_gemma":0.002267136,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005835827,"about_ca_topic_score_gemma":0.0001684938,"domain_scores_codex":[0.986373,0.001266152,0.003406855,0.002704598,0.003446368,0.002803017],"domain_scores_gemma":[0.9863313,0.00062215,0.002434961,0.008565458,0.0006203354,0.00142581],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001097891,0.003784948,0.06718607,0.002529419,0.002477527,0.001338284,0.1109504,0.01770692,0.001505052,0.02744185,0.4296298,0.3343518],"study_design_scores_gemma":[0.004074429,0.001165274,0.08779285,0.0005660141,0.0004262931,0.002756122,0.01138269,0.2309936,0.000061537,0.00009242314,0.657622,0.003066776],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7667599,0.004448151,0.06554084,0.02631457,0.01005953,0.006191482,0.01389005,0.003532041,0.1032635],"genre_scores_gemma":[0.952764,0.0003181942,0.02292821,0.004269165,0.00165068,0.0005498876,0.01234429,0.0003113936,0.004864201],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3312851,"threshold_uncertainty_score":0.99987,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01131267473939492,"gpt":0.2406514456181341,"spread":0.2293387708787392,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009125232,0.000561978,0.0005975905,0.0005837124,0.0004561185,0.001104729,0.003320476,0.0002759153,0.00004957494],"category_scores_gemma":[0.0002195848,0.0005061444,0.0002546261,0.001016607,0.0001215903,0.003006803,0.001237709,0.001021875,0.001386461],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001497834,"about_ca_system_score_gemma":0.000228886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002046242,"about_ca_topic_score_gemma":0.00003669487,"domain_scores_codex":[0.9961227,0.0003389982,0.0009274848,0.0009498892,0.0007341313,0.0009267714],"domain_scores_gemma":[0.9961586,0.0003656464,0.0006852706,0.002171184,0.0002639033,0.0003553724],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008845836,0.0009070141,0.03666865,0.0003090488,0.000490326,0.0001187764,0.005784797,0.01474503,0.01347843,0.1253022,0.07217661,0.7299306],"study_design_scores_gemma":[0.002152789,0.001029924,0.08952087,0.0001444152,0.00007596903,0.0004206646,0.0003138062,0.3082815,0.003598999,0.001360169,0.5914944,0.001606518],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6031149,0.0003253878,0.3741719,0.007027376,0.001841646,0.001141426,0.00006479664,0.002069501,0.01024306],"genre_scores_gemma":[0.8902544,0.00008108031,0.1059564,0.00186234,0.0003751154,0.0000921806,0.0003350715,0.00004753127,0.0009957964],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7283241,"threshold_uncertainty_score":0.9999322,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"WiLAN (Canada)","funders":"","keywords":"Humanities; Computer science; Art","retraction":null,"screen_n_in":null,"score":{"opus":0.1591427698515661,"gpt":0.3472932904234806,"spread":0.1881505205719145,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":["metaepi_narrow","open_science","research_integrity"],"category_scores_codex":[0.01017271,0.002609659,0.003253266,0.001057437,0.005774629,0.005117493,0.00857503,0.001452178,0.0003003292],"category_scores_gemma":[0.009821425,0.002934407,0.001023492,0.006509247,0.001680933,0.003969411,0.01061425,0.004444998,0.0007469794],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001740677,"about_ca_system_score_gemma":0.009652642,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001214193,"about_ca_topic_score_gemma":0.002099856,"domain_scores_codex":[0.972943,0.007697633,0.003646021,0.008194434,0.004090583,0.003428295],"domain_scores_gemma":[0.9776466,0.00378298,0.003297249,0.009816832,0.003362777,0.002093518],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.008167186,0.01419171,0.2421068,0.004290016,0.004042224,0.01245002,0.02577318,0.0004677833,0.2152925,0.2222748,0.1482587,0.1026851],"study_design_scores_gemma":[0.01360937,0.002604606,0.5756713,0.003556638,0.003412187,0.002421968,0.01937691,0.1074705,0.04259845,0.02537006,0.1864226,0.01748546],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9504619,0.002381176,0.009666981,0.01838037,0.003394617,0.002895363,0.008999427,0.00163391,0.002186311],"genre_scores_gemma":[0.9604811,0.0005078258,0.01113511,0.001006768,0.001718917,0.0002207512,0.01762523,0.0004225049,0.006881761],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3335645,"threshold_uncertainty_score":0.9998441,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Cluster (spacecraft); Cluster analysis; Humanities; Computer science; Art; Operating system; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.0625656695631132,"gpt":0.3009743017603898,"spread":0.2384086321972765,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":["open_science"],"category_scores_codex":[0.005408099,0.001236806,0.001348057,0.0007536258,0.004670977,0.001941158,0.020083,0.0002899528,0.000385332],"category_scores_gemma":[0.0004173512,0.001359147,0.0003200295,0.002077482,0.0002753362,0.006078479,0.03572575,0.002879004,0.0003324856],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006249924,"about_ca_system_score_gemma":0.001220362,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007701244,"about_ca_topic_score_gemma":0.0005565685,"domain_scores_codex":[0.9892009,0.0008468668,0.002340479,0.002856971,0.002637739,0.002117006],"domain_scores_gemma":[0.9855598,0.0007223043,0.001853756,0.01058772,0.0002614431,0.001014988],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005321294,0.002021864,0.007533485,0.001479399,0.002378293,0.0007728213,0.03982143,0.02996456,0.001288324,0.004794285,0.3358021,0.5736113],"study_design_scores_gemma":[0.001271107,0.0003702203,0.002192762,0.0001591318,0.000280997,0.0007821116,0.00343011,0.3365381,0.00005190276,0.0000119771,0.6537356,0.001175886],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2381133,0.01433186,0.210191,0.06614495,0.03122626,0.011541,0.02890586,0.008656735,0.390889],"genre_scores_gemma":[0.8956428,0.0002677224,0.04182198,0.003714854,0.002167552,0.0002853215,0.02721008,0.0003195786,0.02857017],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6575294,"threshold_uncertainty_score":0.9994214,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.08785438586259763,"gpt":0.3523426165322655,"spread":0.2644882306696679,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001348836,0.0001049136,0.0001270133,0.0001286682,0.0003482934,0.0004926827,0.0005756801,0.00004482142,0.000001166969],"category_scores_gemma":[0.0005598589,0.00008161839,0.00001937812,0.0003597396,0.00009226314,0.001988717,0.0002885514,0.0001025814,0.000006531004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005721872,"about_ca_system_score_gemma":0.000121317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009636152,"about_ca_topic_score_gemma":0.000004356448,"domain_scores_codex":[0.9990108,0.00005697263,0.0004304181,0.000211686,0.0001481006,0.000142027],"domain_scores_gemma":[0.9982783,0.0005979587,0.0002203002,0.0007113726,0.0001591337,0.00003293333],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004975451,0.00005464034,0.0003394976,0.0007103482,0.00009521963,3.501549e-7,0.007537483,0.0005399381,0.009787137,0.09624207,0.0009300665,0.8837582],"study_design_scores_gemma":[0.0001756234,0.00003442798,0.0004018937,0.0001377115,0.00004438519,0.00002865811,0.0004675911,0.9925012,0.0003959682,0.001220511,0.004497693,0.00009433585],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002890456,0.00044898,0.9951063,0.0003577989,0.0001436814,0.0003976805,0.0002058409,0.0001529936,0.0002962423],"genre_scores_gemma":[0.2975594,0.00002596056,0.701919,0.00006438139,0.00002793317,0.00005256318,0.0003133638,0.000007630127,0.00002983445],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9919612,"threshold_uncertainty_score":0.4750951,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.008298942351034243,"gpt":0.2282417158129216,"spread":0.2199427734618874,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006213395,0.0003576224,0.0003902511,0.0002233353,0.0004321226,0.0006253722,0.001861375,0.0001343378,0.00007079338],"category_scores_gemma":[0.00007282718,0.0003503007,0.000162394,0.0004892498,0.0000507998,0.0009141463,0.0006260695,0.0005230967,0.0005443997],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008569627,"about_ca_system_score_gemma":0.0001029115,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004979754,"about_ca_topic_score_gemma":0.00007643903,"domain_scores_codex":[0.9970781,0.0001910761,0.0004695206,0.001029706,0.0005925278,0.0006390279],"domain_scores_gemma":[0.9974865,0.0001595,0.0002795631,0.001729237,0.00008433766,0.0002608336],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002354713,0.001502049,0.03501928,0.000403992,0.0008179339,0.0001182541,0.03082645,0.002914977,0.3971234,0.1082442,0.06523673,0.3575573],"study_design_scores_gemma":[0.004505561,0.0007458708,0.01897524,0.0002915623,0.0001625779,0.0001890388,0.0005096255,0.2755171,0.02041305,0.0007041211,0.675747,0.002239203],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8852957,0.0002894281,0.08830358,0.002010799,0.002383539,0.0007903964,0.00004506839,0.001459792,0.01942163],"genre_scores_gemma":[0.959419,0.0000154629,0.02826699,0.000313238,0.0002725758,0.00007182039,0.0001192343,0.00005736916,0.01146429],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6105103,"threshold_uncertainty_score":0.9998949,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1587099163189113,"gpt":0.4184433805244925,"spread":0.2597334642055813,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.005437537,0.0000466541,0.00007181338,0.00007749826,0.0006531748,0.00019077,0.006811029,0.000006427897,9.094417e-7],"category_scores_gemma":[0.0002481609,0.00003166404,0.00001561054,0.0004069728,0.000124786,0.001169181,0.004738214,0.0001519996,1.228969e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004509349,"about_ca_system_score_gemma":0.0004375661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008446779,"about_ca_topic_score_gemma":0.00009750311,"domain_scores_codex":[0.9986792,0.00005722163,0.0003373527,0.0002216526,0.000551376,0.0001531715],"domain_scores_gemma":[0.9983656,0.0004034879,0.0004634533,0.0005894055,0.0001508237,0.00002719598],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005286548,0.0000577935,0.0875012,0.000005766734,0.00005301959,0.000002298302,0.00273861,0.3332849,0.001046423,0.008322365,0.00412231,0.5628124],"study_design_scores_gemma":[0.0002261974,0.00002035419,0.002915621,0.00001851694,0.000006030866,0.00006067427,0.0002938879,0.9936585,0.0000215718,0.001205119,0.001537457,0.00003600461],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3272002,0.0001666721,0.6692792,0.002389184,0.0005712623,0.0001320723,0.0002229721,0.000003904691,0.00003456642],"genre_scores_gemma":[0.8734964,0.00001578701,0.1262579,0.0001063956,0.00008711303,0.00000270139,0.000026086,0.00000228974,0.000005389245],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6603736,"threshold_uncertainty_score":0.9985626,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Inflation (cosmology); Econometrics; Economics; Kernel (algebra); Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.04628639768748586,"gpt":0.3249820525022005,"spread":0.2786956548147146,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002049118,0.00006633245,0.0001446539,0.0001581523,0.00006060297,0.00003530346,0.0004072899,0.00008992454,0.000009254561],"category_scores_gemma":[0.0004445076,0.00005524391,0.00002871505,0.0000137074,0.0001900873,0.0002349738,0.0001684539,0.0002258259,0.0000110044],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001618166,"about_ca_system_score_gemma":0.00006747014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001101742,"about_ca_topic_score_gemma":2.056366e-7,"domain_scores_codex":[0.9993613,0.0001158653,0.0002327286,0.0001466202,0.00006348808,0.00007997697],"domain_scores_gemma":[0.9990758,0.0004323605,0.0002512913,0.00006204045,0.0001102417,0.00006821175],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0001900193,0.00003466208,0.03139654,0.0000088891,0.0001999295,0.00006774841,0.006788895,0.00009243636,0.0008553393,0.8655436,0.003368297,0.09145362],"study_design_scores_gemma":[0.003289625,0.001598339,0.5842683,0.00004511768,0.00009019868,0.003364359,0.0003447983,0.03035864,0.0008597329,0.3412129,0.03410079,0.0004672622],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9194305,0.000472945,0.04634056,0.03324431,0.0003223938,0.00002017583,0.000003160881,0.00001956673,0.000146402],"genre_scores_gemma":[0.9902083,0.0003860163,0.007675177,0.001524298,0.0001847184,0.000001331143,0.000002765645,0.000002847929,0.00001458153],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5528717,"threshold_uncertainty_score":0.2252781,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01044480708709052,"gpt":0.3118742563805611,"spread":0.3014294492934706,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001617306,0.0001107816,0.0002224737,0.0003730634,0.0002865613,0.00006969218,0.0004421363,0.00001674987,0.00001800601],"category_scores_gemma":[0.0001627365,0.0001071344,0.00005991978,0.0005947022,0.00001956786,0.0002727036,0.0003370338,0.0005324146,2.039147e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001329818,"about_ca_system_score_gemma":0.00008152122,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009703213,"about_ca_topic_score_gemma":0.00001292157,"domain_scores_codex":[0.9983194,0.0002955532,0.0005290528,0.000199152,0.0004878383,0.0001689503],"domain_scores_gemma":[0.9985276,0.0001351558,0.0006697956,0.0002312956,0.0003579487,0.00007818209],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004637676,0.0003674884,0.07170662,0.0001925911,0.0001586432,0.00003485785,0.1491067,0.6967592,0.002147959,0.002552344,0.0002187999,0.07670835],"study_design_scores_gemma":[0.00221843,0.0008857756,0.04258458,0.0002361965,0.0001736027,0.0001344365,0.1294922,0.8076007,0.001192359,0.000002055933,0.01515806,0.0003215621],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9438657,0.0002896692,0.05472149,0.00002616292,0.0006892205,0.0001191918,0.00003801133,0.00007322631,0.0001773923],"genre_scores_gemma":[0.9555175,0.00001064792,0.04398324,0.00001977313,0.0003843707,0.000005513316,0.00002283173,0.00001280848,0.00004325304],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1108415,"threshold_uncertainty_score":0.4368814,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01884103927955952,"gpt":0.2671880761038298,"spread":0.2483470368242703,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007377247,0.0001426408,0.0002776693,0.0004448935,0.0002389658,0.0002328221,0.001250634,0.0001320101,0.00001799374],"category_scores_gemma":[0.0004505131,0.0001271143,0.00003627362,0.0007928766,0.00008052473,0.00183352,0.0007137556,0.0004566775,0.00001863197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003438267,"about_ca_system_score_gemma":0.0002620869,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001411007,"about_ca_topic_score_gemma":0.00001534874,"domain_scores_codex":[0.9985499,0.00004843874,0.0006900597,0.0002017897,0.0002772331,0.0002325978],"domain_scores_gemma":[0.9979438,0.00008515934,0.0006138469,0.0008827566,0.0003659356,0.000108564],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000009912426,0.0001188607,0.003995636,0.00004848867,0.0001850001,0.00003852107,0.002409745,0.0002069687,0.0003901892,0.03443526,0.03585555,0.9223059],"study_design_scores_gemma":[0.00161555,0.0003925767,0.002229708,0.0001280838,0.00008067096,0.002221858,0.00579928,0.05432357,0.001362151,0.001892519,0.9295455,0.0004085354],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3315718,0.003457622,0.595001,0.05873748,0.0018354,0.0004993316,0.0002024121,0.000808057,0.007886906],"genre_scores_gemma":[0.719581,0.001180593,0.2774718,0.0009119582,0.0002180189,0.00002180304,0.000274368,0.00001573082,0.0003247546],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9218974,"threshold_uncertainty_score":0.5183569,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Innovation Cluster (Canada)","funders":"","keywords":"Mathematics; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.01577133992137836,"gpt":0.2579603977869958,"spread":0.2421890578656175,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002345659,0.001205382,0.001142962,0.0009239375,0.004823093,0.002573246,0.004768643,0.0001966001,0.0001361368],"category_scores_gemma":[0.0004747546,0.001268672,0.0005096088,0.001943056,0.0003013457,0.007169361,0.005700401,0.002576554,0.0004925881],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001033948,"about_ca_system_score_gemma":0.0008849746,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001177425,"about_ca_topic_score_gemma":0.00003949659,"domain_scores_codex":[0.9905243,0.000521337,0.003142292,0.001017007,0.002883533,0.00191156],"domain_scores_gemma":[0.9923449,0.0004361732,0.002060385,0.003256115,0.0003644442,0.001538043],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001302665,0.003082022,0.1014457,0.003868398,0.001259383,0.0001753812,0.07648049,0.1087339,0.00006754396,0.03947318,0.4879447,0.1761666],"study_design_scores_gemma":[0.001999774,0.0006824106,0.01853864,0.0002471819,0.0001680304,0.0001950726,0.002519268,0.2053186,0.00001935996,0.00002535886,0.7690256,0.001260691],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1893422,0.002920626,0.4689834,0.02087579,0.02214336,0.01803003,0.08660465,0.007116234,0.1839837],"genre_scores_gemma":[0.875972,0.0003182107,0.02178935,0.01751067,0.0008565838,0.001455235,0.07466628,0.0003472374,0.007084472],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6866297,"threshold_uncertainty_score":0.9997246,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Innovation Cluster (Canada)","funders":"","keywords":"Mathematics; Selection (genetic algorithm); Artificial intelligence; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.02388675878536045,"gpt":0.2667803418528745,"spread":0.242893583067514,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.00256533,0.001411569,0.001314098,0.001155412,0.001874379,0.003078805,0.005603668,0.0006790703,0.00004708399],"category_scores_gemma":[0.0001783035,0.001488929,0.0006057249,0.00333853,0.0003004575,0.003763482,0.004531779,0.002135949,0.004192312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004006644,"about_ca_system_score_gemma":0.0006245742,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004516948,"about_ca_topic_score_gemma":0.0002459474,"domain_scores_codex":[0.9911612,0.0004657468,0.002496597,0.00179121,0.001672684,0.002412534],"domain_scores_gemma":[0.9927149,0.0006395573,0.001321557,0.003899744,0.0004044736,0.001019793],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006390349,0.0004722404,0.001587925,0.002172929,0.00110818,0.0002286507,0.05600732,0.01375909,0.0008452216,0.01015575,0.1750734,0.7385254],"study_design_scores_gemma":[0.001288187,0.0003268408,0.007881485,0.0005505361,0.0001521754,0.0002846694,0.001598393,0.5545014,0.0007756934,0.0001126062,0.4308906,0.001637428],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07123455,0.001335984,0.8296853,0.009306259,0.01006237,0.005286873,0.0009698978,0.01242141,0.05969742],"genre_scores_gemma":[0.7901796,0.0008593542,0.164465,0.003615782,0.002741651,0.001013574,0.003736904,0.0005706968,0.03281746],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7368879,"threshold_uncertainty_score":0.9998634,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Confusion matrix; Naive Bayes classifier; Computer science; Nave; Confusion; Quarter (Canadian coin); Database; Data mining; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.02775443352960149,"gpt":0.2931667686138043,"spread":0.2654123350842028,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.001595676,0.0004130839,0.0004349413,0.000201988,0.001629923,0.0007832923,0.005786199,0.00008693196,0.00006532745],"category_scores_gemma":[0.0002259254,0.0004062621,0.0001095069,0.001396506,0.0001076033,0.003117456,0.006114161,0.0008256412,0.0001068674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003200878,"about_ca_system_score_gemma":0.0005437853,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004042972,"about_ca_topic_score_gemma":0.00002987526,"domain_scores_codex":[0.9959282,0.0002280141,0.0009333743,0.0008256899,0.001289649,0.0007950701],"domain_scores_gemma":[0.9960549,0.0001251829,0.0006607012,0.002667373,0.0001747977,0.0003170085],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008505046,0.0005576554,0.0138138,0.00009604845,0.0005013511,0.00008030202,0.01267993,0.004731708,0.00005464249,0.03036548,0.2924111,0.6446229],"study_design_scores_gemma":[0.00177845,0.0007387043,0.01052285,0.00005014307,0.00009795139,0.0008718956,0.003742288,0.2610879,0.00004524199,0.0006289935,0.719427,0.001008626],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3263688,0.002100798,0.4731484,0.02340294,0.008889087,0.004770548,0.00885342,0.00519153,0.1472744],"genre_scores_gemma":[0.8153626,0.00005325488,0.1783903,0.002354068,0.0005899197,0.0004543462,0.001879725,0.00004457283,0.0008712125],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6436143,"threshold_uncertainty_score":0.9998389,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"WiLAN (Canada)","funders":"","keywords":"Physics; Humanities; Art","retraction":null,"screen_n_in":null,"score":{"opus":0.02035937868703847,"gpt":0.2628968829321344,"spread":0.242537504245096,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002698709,0.001250343,0.001262847,0.0009510665,0.004247003,0.001257862,0.005871825,0.0003645572,0.0002265055],"category_scores_gemma":[0.0004200223,0.001320356,0.0006919625,0.002464687,0.000410292,0.002086,0.005513326,0.003690514,0.000256927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00161144,"about_ca_system_score_gemma":0.001475548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004659332,"about_ca_topic_score_gemma":0.00007592375,"domain_scores_codex":[0.9905084,0.0008879346,0.002362214,0.001887289,0.00193153,0.002422679],"domain_scores_gemma":[0.9930553,0.0005090447,0.001926786,0.003253707,0.0004406897,0.0008144844],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006982659,0.003145227,0.04915863,0.00177899,0.002289598,0.00139027,0.01672995,0.003072572,0.01369665,0.09127197,0.05005188,0.766716],"study_design_scores_gemma":[0.002274197,0.002174919,0.0112796,0.0001374494,0.000205581,0.001222158,0.00603603,0.01335493,0.00101798,0.0001017876,0.960615,0.001580323],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7569111,0.007963276,0.08761898,0.03084028,0.01672591,0.01212566,0.005787487,0.008050892,0.0739764],"genre_scores_gemma":[0.8835586,0.001093038,0.03099174,0.003038797,0.001268193,0.001214928,0.002274781,0.0003545492,0.07620541],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9105632,"threshold_uncertainty_score":0.9997789,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0734760502229931,"gpt":0.3092667859674979,"spread":0.2357907357445048,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001346608,0.0001206131,0.0002347667,0.00003748141,0.0001416381,0.00007318572,0.0008140708,0.0000438531,5.994123e-8],"category_scores_gemma":[0.0002178171,0.00009127832,0.00002005337,0.000163562,0.00002154602,0.0001659215,0.000667572,0.0001586415,3.823765e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005891259,"about_ca_system_score_gemma":0.00002535388,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001637767,"about_ca_topic_score_gemma":0.00000243484,"domain_scores_codex":[0.9987426,0.00003330271,0.0004043029,0.000498543,0.0001647339,0.0001565302],"domain_scores_gemma":[0.9972259,0.0004849543,0.0001150849,0.002022113,0.000106207,0.00004577879],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000351773,0.0001355862,0.000004827097,0.0002356783,0.00002233671,0.000005512255,0.0004488494,0.9713496,0.00118346,0.02460397,0.000005578046,0.002001109],"study_design_scores_gemma":[0.0001387198,0.0000576269,7.997457e-7,0.0001281705,0.00003356336,0.0001303949,0.0001220775,0.9923247,0.0002159619,0.006692278,0.00005986777,0.00009591304],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01328835,0.00009752649,0.9857507,0.0001331431,0.00001976509,0.0005778378,0.00005216181,0.00007162845,0.000008899254],"genre_scores_gemma":[0.7217212,0.00001207435,0.2781121,0.000004153873,0.000008317909,0.00009117425,0.00003485306,0.00001081666,0.000005368332],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7084328,"threshold_uncertainty_score":0.3722222,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Encana (Canada)","funders":"","keywords":"Humanities; Physics; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.04673726730096101,"gpt":0.3109930361373792,"spread":0.2642557688364182,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002261979,0.0008328568,0.0008335776,0.0003897899,0.00128851,0.001538004,0.007499065,0.0004472903,0.0003906704],"category_scores_gemma":[0.002744668,0.0008291246,0.0001881665,0.001550871,0.0007543983,0.002042831,0.004234625,0.001664945,0.003200032],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001830692,"about_ca_system_score_gemma":0.001132649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002153675,"about_ca_topic_score_gemma":0.0002907247,"domain_scores_codex":[0.9930544,0.0004004874,0.001432616,0.002008715,0.001563913,0.001539906],"domain_scores_gemma":[0.9910502,0.001162318,0.001063784,0.005141403,0.0005404965,0.00104177],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006004035,0.0005394766,0.01711486,0.00009924789,0.0003179559,0.0001168151,0.02139598,0.000004875661,0.000631808,0.003559079,0.0958516,0.8603082],"study_design_scores_gemma":[0.001908255,0.0009316702,0.06358675,0.0005756912,0.0002510944,0.0004119016,0.0007954749,0.06975164,0.0003153274,0.0001435719,0.8600037,0.001324902],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6084287,0.004448269,0.2221777,0.03110428,0.03876067,0.00367505,0.00228959,0.003301219,0.08581453],"genre_scores_gemma":[0.6679344,0.0005701876,0.29929,0.002141084,0.01781028,0.000185349,0.002370393,0.0003219605,0.009376355],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8589833,"threshold_uncertainty_score":0.9994985,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"WOMAC; Osteoarthritis; Medicine; Reliability (semiconductor); Physical therapy; Alternative medicine; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.01089959529404551,"gpt":0.2035786696402266,"spread":0.1926790743461811,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001641004,0.0002027963,0.000229602,0.00005802321,0.0002015843,0.0002730602,0.0006613138,0.00008761796,0.0003107089],"category_scores_gemma":[0.00004022983,0.0002053626,0.00005000328,0.0002829768,0.0001124924,0.0008053458,0.0009845862,0.0003762993,0.0001770176],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006527119,"about_ca_system_score_gemma":0.00009918594,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005880226,"about_ca_topic_score_gemma":0.01802622,"domain_scores_codex":[0.9983937,0.0001139059,0.0002248911,0.0007779215,0.0001855554,0.0003040971],"domain_scores_gemma":[0.9988761,0.0000821112,0.00008086828,0.0005897455,0.00008098316,0.0002901981],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005085391,0.00005827279,0.2220635,0.00002142892,0.00001704296,0.00005599871,0.007325199,0.00002450535,0.0001030611,0.001090307,0.002577627,0.7666122],"study_design_scores_gemma":[0.002134176,0.0009660519,0.1202565,0.00004021135,0.00001744273,0.00006571937,0.000390192,0.002512743,0.0001062037,0.0002333285,0.8727522,0.0005251564],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6840357,0.00008621901,0.2662457,0.02066325,0.0002436808,0.000592854,0.00006469138,0.000870416,0.02719745],"genre_scores_gemma":[0.9814887,0.00001045551,0.00937718,0.001953157,0.00005045094,0.000008460675,0.00002678768,0.00001353087,0.007071254],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8701746,"threshold_uncertainty_score":0.9998922,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Backpropagation; Climate change; Artificial neural network; MATLAB; Computer science; Activation function; Environmental science; Artificial intelligence; Ecology","retraction":null,"screen_n_in":null,"score":{"opus":0.110632491951251,"gpt":0.3272579264995295,"spread":0.2166254345482784,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001047637,0.0000859736,0.0001102361,0.0001069521,0.0003192974,0.00007632335,0.001268936,0.00001436593,0.00005351428],"category_scores_gemma":[0.00003888271,0.00007775406,0.00003533902,0.0008297048,0.00002316009,0.0002064849,0.0004615462,0.0002412977,0.00001122747],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003988247,"about_ca_system_score_gemma":0.00001318602,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002069321,"about_ca_topic_score_gemma":0.00003581413,"domain_scores_codex":[0.9986619,0.0002203166,0.0003408538,0.0003057273,0.0002637962,0.0002073476],"domain_scores_gemma":[0.9990475,0.0001297079,0.0001823347,0.0005710442,0.00004953586,0.00001992702],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009108264,0.0005978365,0.01739274,0.00001068505,0.00000914605,0.00001731463,0.02479491,0.8515606,0.000113232,0.02012734,0.00009108242,0.08527604],"study_design_scores_gemma":[0.00004871185,0.0001481385,0.002934928,0.0000163715,0.000005694106,0.00003269116,0.004123001,0.9910706,0.00003105103,0.0006272537,0.0008728358,0.00008869455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8811334,0.00008053078,0.1145335,0.001011848,0.0008005282,0.0007445151,0.00001561728,0.00006829671,0.001611762],"genre_scores_gemma":[0.998713,0.00001328205,0.0007976572,0.0001660809,0.00009429211,0.0001670305,0.00001777942,0.000006534766,0.00002436283],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1395101,"threshold_uncertainty_score":0.3170718,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01302203122856045,"gpt":0.2415866640379005,"spread":0.2285646328093401,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009791913,0.0008165993,0.0008696677,0.0006316655,0.0006598417,0.0006834919,0.003303793,0.0004028396,0.00003709858],"category_scores_gemma":[0.0003400732,0.0007174274,0.0003833699,0.001052287,0.0002156113,0.001922769,0.002164597,0.001172605,0.0005819403],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002388603,"about_ca_system_score_gemma":0.000537631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001543233,"about_ca_topic_score_gemma":0.00007158123,"domain_scores_codex":[0.9948419,0.0002706652,0.00112424,0.001469019,0.001021695,0.001272455],"domain_scores_gemma":[0.9954001,0.0006449327,0.0005724526,0.002459636,0.0004417951,0.0004810788],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001816576,0.0009875507,0.04793943,0.0003585816,0.0007625367,0.0001763417,0.007488765,0.005084455,0.006342753,0.4571607,0.0356006,0.4379167],"study_design_scores_gemma":[0.003845213,0.001677669,0.1525774,0.0004196728,0.0001545515,0.0009055256,0.001821888,0.3450032,0.004288444,0.002065283,0.4839385,0.003302662],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8625479,0.000293819,0.1026086,0.005731015,0.001812246,0.001675169,0.0001211663,0.002828647,0.02238142],"genre_scores_gemma":[0.8936601,0.0000632554,0.1028608,0.001417195,0.0002359121,0.000103535,0.0006390892,0.00006361874,0.0009564926],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4550954,"threshold_uncertainty_score":0.9995277,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Encana (Canada)","funders":"","keywords":"Physics; Humanities; Art","retraction":null,"screen_n_in":null,"score":{"opus":0.02349902128384234,"gpt":0.2522067122383979,"spread":0.2287076909545555,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.001710148,0.001928681,0.001995254,0.0005861245,0.003151869,0.002748176,0.007091848,0.0009410363,0.0002817217],"category_scores_gemma":[0.00200236,0.002067486,0.001060826,0.003359164,0.001035139,0.001731949,0.003282796,0.005099225,0.001051347],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004374783,"about_ca_system_score_gemma":0.001501894,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00183878,"about_ca_topic_score_gemma":0.0005480969,"domain_scores_codex":[0.9878916,0.001558994,0.002404866,0.003216015,0.002120967,0.00280752],"domain_scores_gemma":[0.989579,0.001460003,0.001428939,0.003651006,0.0006247644,0.003256272],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006644194,0.002147566,0.01814295,0.0009449814,0.002357929,0.01008312,0.07831351,0.001862246,0.01294407,0.05897288,0.1313184,0.6822479],"study_design_scores_gemma":[0.005113774,0.001931862,0.01549277,0.0009622205,0.001168641,0.00515073,0.00508539,0.07775905,0.004776142,0.0005814161,0.8769454,0.005032654],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8218462,0.005813188,0.04679833,0.07907503,0.009836501,0.003947622,0.002666598,0.004028403,0.02598805],"genre_scores_gemma":[0.9571298,0.0008726367,0.02756512,0.004331336,0.006125366,0.0001278953,0.001562819,0.0004209692,0.001864098],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7456269,"threshold_uncertainty_score":0.9997265,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02575381225775621,"gpt":0.2888518961292369,"spread":0.2630980838714807,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006132476,0.0001633666,0.0001870576,0.001416095,0.0001298858,0.0009890813,0.0002888968,0.00005822576,0.000005140212],"category_scores_gemma":[0.00002537628,0.0001576031,0.00004317141,0.001639917,0.00002743708,0.003427787,0.000238218,0.0001766486,0.00002289392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003394261,"about_ca_system_score_gemma":0.00002949902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008102743,"about_ca_topic_score_gemma":0.00002237331,"domain_scores_codex":[0.9986055,0.00009010983,0.0005291724,0.0002631037,0.0002624647,0.0002496718],"domain_scores_gemma":[0.99934,0.00008971326,0.0001313054,0.0003478971,0.00003291143,0.00005820393],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002181419,0.0001962557,0.1510648,0.0008150203,0.0004809097,0.00003200231,0.03114076,0.166743,0.00003752328,0.06677871,0.00008679291,0.5826024],"study_design_scores_gemma":[0.0002668268,0.0000287327,0.0855487,0.0001532373,0.00003261747,0.000004345395,0.0003057835,0.9123613,0.000009135919,0.0003379938,0.0007990355,0.0001523395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3276103,0.00005905026,0.6702976,0.0003530456,0.0001345572,0.0003391438,0.00001672683,0.0001832879,0.001006267],"genre_scores_gemma":[0.9927053,0.00001025383,0.006811574,0.0001735048,0.0000109577,0.00005674591,0.0002066645,0.000007241975,0.00001777457],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7456182,"threshold_uncertainty_score":0.9537734,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04878470491938541,"gpt":0.3033176084357681,"spread":0.2545329035163827,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000298565,0.0001296836,0.0001824309,0.00005556847,0.0002239567,0.0004260836,0.0007721245,0.00003003288,0.00003256623],"category_scores_gemma":[0.00009662997,0.00009511915,0.00008672602,0.0003745573,0.00005569007,0.0008787996,0.0002431271,0.0003629625,0.00001351608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003265495,"about_ca_system_score_gemma":0.001161782,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004858295,"about_ca_topic_score_gemma":0.00001381539,"domain_scores_codex":[0.9990186,0.0001320335,0.0002389317,0.0001610883,0.0002506261,0.000198734],"domain_scores_gemma":[0.998782,0.0001182726,0.0002328565,0.0004724118,0.000289307,0.0001051932],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001522067,0.00006828068,0.000382371,0.00001707942,0.00007473755,0.00006284064,0.002805731,0.0005815873,0.01422123,0.3454418,0.001298176,0.635031],"study_design_scores_gemma":[0.001734683,0.001345995,0.05058625,0.001200646,0.0002346439,0.002215196,0.002647032,0.02313248,0.789368,0.1015067,0.0241503,0.001878077],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1099631,0.00008502596,0.8772996,0.009469394,0.0003492668,0.00006099172,0.000007694105,0.00003735275,0.002727567],"genre_scores_gemma":[0.9839584,0.00008199067,0.01356507,0.0004901926,0.0009127,0.000001798049,0.000004305251,0.00001095475,0.0009746383],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8739952,"threshold_uncertainty_score":0.4108734,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Encana (Canada)","funders":"","keywords":"Artificial neural network; Statistic; Statistics; Preprocessor; Computer science; Data pre-processing; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.05899427922816992,"gpt":0.3209810170725358,"spread":0.2619867378443659,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007278448,0.0001902748,0.0003505913,0.0003226238,0.0008875888,0.0005056398,0.002795651,0.00006431207,0.00001574271],"category_scores_gemma":[0.0003492963,0.0001299835,0.0001181445,0.0008469642,0.0002013086,0.0006826993,0.0002492779,0.0008351586,0.0000932694],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001263571,"about_ca_system_score_gemma":0.001159944,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001647484,"about_ca_topic_score_gemma":0.00005328993,"domain_scores_codex":[0.9969318,0.0008262474,0.0007530748,0.0002830888,0.0005528181,0.000652953],"domain_scores_gemma":[0.9969687,0.0002272003,0.0008309321,0.00103201,0.0003412714,0.0005998831],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000166544,0.0003256743,0.01109911,0.00004296019,0.00015902,0.00002433438,0.01870876,0.00002883062,0.0002080578,0.19642,0.01359004,0.7593766],"study_design_scores_gemma":[0.003497056,0.004179554,0.2721227,0.0003218833,0.00006982351,0.005992705,0.003356529,0.01998368,0.0004024274,0.01024709,0.6786563,0.001170246],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2174478,0.0002737738,0.6595948,0.1199314,0.0006839124,0.0002050623,0.000005046335,0.0001542189,0.001703886],"genre_scores_gemma":[0.9738705,0.00003232925,0.02222402,0.002839882,0.0007990203,0.000005644675,0.000003778991,0.00002205727,0.00020283],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7582064,"threshold_uncertainty_score":0.6826705,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.08062731783390474,"gpt":0.4160534329598738,"spread":0.3354261151259691,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["bibliometrics"],"consensus_categories":["bibliometrics"],"category_scores_codex":[0.002228094,0.000144638,0.0003178107,0.08363015,0.0003774522,0.0004313013,0.001690338,0.00006354843,0.0001378698],"category_scores_gemma":[0.0005437424,0.0001373112,0.0001033968,0.2923509,0.0001501498,0.0004534794,0.0009648721,0.0003512678,0.0003774711],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002877914,"about_ca_system_score_gemma":0.00008562044,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006197063,"about_ca_topic_score_gemma":0.0002791345,"domain_scores_codex":[0.9970675,0.0002239061,0.0003729119,0.0007650633,0.001026418,0.0005442526],"domain_scores_gemma":[0.9976673,0.0006077015,0.0001176499,0.001013491,0.000220413,0.0003734823],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00002656549,0.0002024954,0.07646281,0.0000318391,0.0003559796,0.00009878806,0.005450935,0.0009316184,0.006298211,0.009988447,0.1967826,0.7033697],"study_design_scores_gemma":[0.0001617942,0.000159513,0.9489035,0.00002614767,0.0000444064,0.00000624864,0.0001917908,0.01763643,0.0004917209,0.001025253,0.03115248,0.0002007346],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.939799,0.001215113,0.03249826,0.01874567,0.000245126,0.0001954733,0.0004901339,0.0003631529,0.006448125],"genre_scores_gemma":[0.9813684,0.0002763073,0.01345381,0.0001148103,0.0001007416,0.00003207076,0.00007543881,0.00001152676,0.004566844],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8724406,"threshold_uncertainty_score":0.9368147,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Agricultural science; Environmental science","retraction":null,"screen_n_in":null,"score":{"opus":0.01193546187938579,"gpt":0.2459626361589483,"spread":0.2340271742795625,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001279899,0.0008564241,0.0007983258,0.0006289628,0.000962977,0.001826795,0.003946396,0.0003750723,0.0002190192],"category_scores_gemma":[0.0001958444,0.0006394074,0.0004137776,0.001028036,0.0003483626,0.005067439,0.001889356,0.0009600262,0.003822695],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002702944,"about_ca_system_score_gemma":0.0005621955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001078968,"about_ca_topic_score_gemma":0.00001800225,"domain_scores_codex":[0.9943191,0.0002780618,0.001751877,0.0009967005,0.00120723,0.001446961],"domain_scores_gemma":[0.9945596,0.0005826251,0.001195687,0.002367519,0.0004180908,0.0008764407],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005684885,0.0003501138,0.003115156,0.0002007356,0.0003753469,0.00004649808,0.008586854,0.000303144,0.000786837,0.02987431,0.2668313,0.6894729],"study_design_scores_gemma":[0.002471144,0.001103072,0.01881391,0.001068795,0.0001165597,0.0006864434,0.0002205229,0.08319094,0.001153568,0.0005684135,0.8889939,0.001612788],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07064717,0.0005042814,0.877187,0.01447474,0.005529209,0.0009799735,0.0005409757,0.001461532,0.02867515],"genre_scores_gemma":[0.9133435,0.0007758603,0.06153701,0.004135757,0.004513,0.0001966792,0.000380854,0.0001681823,0.01494912],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8426964,"threshold_uncertainty_score":0.9996057,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.009700565042861733,"gpt":0.254515882193227,"spread":0.2448153171503652,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001014489,0.00009751869,0.000170819,0.000285075,0.0001367648,0.00008409814,0.0003338846,0.00009147186,0.000001711124],"category_scores_gemma":[0.0001284391,0.0000791753,0.00001862877,0.0005847149,0.0001906705,0.001088075,0.0001416833,0.0003987956,0.000006870476],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002146272,"about_ca_system_score_gemma":0.00002077605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001808844,"about_ca_topic_score_gemma":6.60901e-7,"domain_scores_codex":[0.9989511,0.00003098776,0.0005388682,0.00009444982,0.0001192519,0.0002652934],"domain_scores_gemma":[0.9991578,0.00009610022,0.0003485545,0.0002389753,0.00006347434,0.00009512918],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001165193,0.00003285984,0.0008802625,0.000006397266,0.000002433403,0.000003243246,0.0002673394,0.000761457,0.00005166084,0.6727513,0.00001689077,0.3252145],"study_design_scores_gemma":[0.0009226454,0.0004362047,0.004478357,0.00004147194,0.00004365897,0.0236446,0.0009886217,0.432291,0.001649571,0.532801,0.002185174,0.0005177099],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5877054,0.00002930772,0.4105832,0.00120439,0.00007243754,0.0001263252,9.331769e-7,0.00005985788,0.0002181666],"genre_scores_gemma":[0.9628945,0.000002833369,0.03679925,0.0001311235,0.0001389809,0.00002415788,0.00000503196,0.000003783502,3.40531e-7],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4315295,"threshold_uncertainty_score":0.3228675,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Innovation Cluster (Canada)","funders":"","keywords":"Cluster analysis; Physics; Cluster (spacecraft); Computer science; Database; Operating system; Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02035813353643767,"gpt":0.2701337795502442,"spread":0.2497756460138065,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00153203,0.0008890951,0.0008584815,0.0005927544,0.001780813,0.001307875,0.00384766,0.0005403965,0.0002080302],"category_scores_gemma":[0.0005943319,0.000883737,0.0004038916,0.001652708,0.0009889344,0.001109101,0.002203263,0.001446473,0.003134023],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002554707,"about_ca_system_score_gemma":0.0003161146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003583497,"about_ca_topic_score_gemma":0.0005580344,"domain_scores_codex":[0.9939865,0.0004631071,0.001165204,0.001692853,0.0008283782,0.00186394],"domain_scores_gemma":[0.9949895,0.0002805483,0.0006933043,0.003025109,0.0004767884,0.0005347711],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002850904,0.00161054,0.09450794,0.0006863243,0.001948967,0.0003827619,0.02801066,0.0007930802,0.009747543,0.04575113,0.0781996,0.7380764],"study_design_scores_gemma":[0.001775035,0.001858421,0.05722477,0.000241314,0.0003371012,0.000452996,0.001490686,0.09810124,0.002115628,0.0001754288,0.8343564,0.001871023],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4922497,0.002613385,0.3529021,0.01439088,0.007306668,0.002877168,0.0002043372,0.006297117,0.1211586],"genre_scores_gemma":[0.9420469,0.000179352,0.02625848,0.00167519,0.001115526,0.0001425053,0.0002109898,0.0000996697,0.02827144],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7561567,"threshold_uncertainty_score":0.9997289,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Encana (Canada)","funders":"","keywords":"Humanities; Mathematics; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.03308089082681665,"gpt":0.2794984714068098,"spread":0.2464175805799931,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011762,0.0009815464,0.001036008,0.0003646388,0.001402332,0.001213263,0.004093191,0.0004703689,0.0001836281],"category_scores_gemma":[0.001344095,0.0009802853,0.0004940922,0.001529041,0.0005703533,0.0009448366,0.002755458,0.002504206,0.001719515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003483094,"about_ca_system_score_gemma":0.000408154,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004109281,"about_ca_topic_score_gemma":0.0002016751,"domain_scores_codex":[0.9932755,0.0009152338,0.001240224,0.002022971,0.0009400661,0.001606063],"domain_scores_gemma":[0.995075,0.0006911169,0.0008347393,0.002018308,0.0002063885,0.001174435],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0009734409,0.003070978,0.07938369,0.00133612,0.002592453,0.004645856,0.07107438,0.01488987,0.03563107,0.02715937,0.2534802,0.5057626],"study_design_scores_gemma":[0.00312299,0.001805457,0.01529734,0.0004413967,0.0005449164,0.0006650792,0.007202758,0.3247567,0.002036742,0.0003223355,0.641148,0.002656325],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3558939,0.003453146,0.4951329,0.1027283,0.003373259,0.002340605,0.001833104,0.003792153,0.03145268],"genre_scores_gemma":[0.956295,0.0007049638,0.03322989,0.005140725,0.0013731,0.0001008475,0.0006990316,0.0001844306,0.002272007],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6004012,"threshold_uncertainty_score":0.9998977,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"WiLAN (Canada)","funders":"","keywords":"Forestry; Physics; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.02933751243510622,"gpt":0.2741286099144958,"spread":0.2447910974793896,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","research_integrity"],"category_scores_codex":[0.006540051,0.003200375,0.002805751,0.002177126,0.002536575,0.005217674,0.01137144,0.001496782,0.00004936021],"category_scores_gemma":[0.001158058,0.003251993,0.001163313,0.005399103,0.002134009,0.007500037,0.006736953,0.003982913,0.001646122],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001239077,"about_ca_system_score_gemma":0.003144254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007191614,"about_ca_topic_score_gemma":0.00139751,"domain_scores_codex":[0.9803622,0.0009232211,0.004714669,0.003418804,0.004958244,0.005622895],"domain_scores_gemma":[0.9805896,0.000482652,0.003072335,0.008874497,0.001902028,0.005078848],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007066891,0.00292255,0.1857542,0.002290573,0.001920698,0.0005264982,0.07107134,0.001259174,0.0003449636,0.06011261,0.01679403,0.6562966],"study_design_scores_gemma":[0.00571912,0.002712159,0.07331508,0.0008833862,0.0006317825,0.0005556182,0.007163142,0.03690385,0.0002914743,0.0002657571,0.8676006,0.003957988],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5738158,0.007389177,0.02030117,0.02219509,0.02378817,0.02142642,0.001489907,0.01452799,0.3150663],"genre_scores_gemma":[0.9268402,0.001156474,0.01535332,0.00223829,0.002590869,0.002404847,0.01813836,0.0007051979,0.03057246],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8508066,"threshold_uncertainty_score":0.9997995,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Character (mathematics); Cluster analysis; Psychology; Mathematics; Computer science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.03155691135943124,"gpt":0.3489949930942264,"spread":0.3174380817347952,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002143745,0.0001060268,0.0001996819,0.0009260086,0.0001466321,0.0002560519,0.001213166,0.00001499034,0.000001650681],"category_scores_gemma":[0.00003568827,0.00008778464,0.0000460728,0.0003744627,0.00006357997,0.0008383129,0.001012245,0.0001200281,0.000002360703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007917049,"about_ca_system_score_gemma":0.00005781919,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002371655,"about_ca_topic_score_gemma":0.000005756386,"domain_scores_codex":[0.9983633,0.00003302129,0.000852151,0.0001450861,0.0004568354,0.0001496665],"domain_scores_gemma":[0.9982805,0.0001263234,0.0009820033,0.0002977415,0.0002451974,0.0000682614],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005504331,0.001192742,0.02986418,0.0001449609,0.0004855162,0.0001970288,0.03611622,0.8428419,0.0007480392,0.009854663,0.00008326165,0.07841644],"study_design_scores_gemma":[0.0007113083,0.0002240172,0.01646336,0.0001193642,0.00002623812,0.0001057585,0.008776855,0.9732245,0.000130055,0.00004927838,0.00006997032,0.00009931751],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8380609,0.000002387992,0.1610537,0.00009312142,0.0003628936,0.000183897,0.000006510991,0.0000121248,0.0002245222],"genre_scores_gemma":[0.9307885,0.0000256168,0.06906584,0.0000744961,0.00001961016,0.000004729116,0.00000174609,0.000004308883,0.00001518723],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1303826,"threshold_uncertainty_score":0.3579754,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}