{"meta":{"query_hash":"591345dbeb0d","filters":{"venue":"Machine Learning"},"cohort_total":113,"direct_labels_cover":0,"predictions_cover":113,"exported":113,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/591345dbeb0d","api":"https://metacan.xera.ac/api/v1/cohort?venue=Machine+Learning"},"results":[{"id":"W138226303","doi":"10.1007/s10994-016-5557-9","title":"Fast learning of relational dependency networks","year":2016,"lang":"en","type":"article","venue":"Machine Learning","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"China Scholarship Council; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Bayesian network; Statistical relational learning; Computer science; Boosting (machine learning); Tuple; Artificial intelligence; Dependency (UML); Relational database; Benchmark (surveying); Machine learning; Bayesian probability; Data mining; Mathematics","score_opus":0.01565735542101996,"score_gpt":0.23234033158792922,"score_spread":0.21668297616690926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W138226303","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014284858,0.00021379859,0.9812053,0.00047258037,0.000108431144,0.000029867666,3.4522733e-7,0.00017698412,0.0035078225],"genre_scores_gemma":[0.97986084,0.000034579676,0.017842092,0.00003539545,0.000061860315,0.000002730028,0.0000023376967,0.000010360643,0.0021498145],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988617,0.00015959717,0.00023707733,0.00027261054,0.00023681077,0.00023222496],"domain_scores_gemma":[0.99929965,0.0002148703,0.00015072625,0.00019003557,0.0000781953,0.00006652249],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043069775,0.00011143127,0.00013949507,0.00007912709,0.00015661714,0.00003415403,0.00037032578,0.00007095615,0.000089190595],"category_scores_gemma":[0.00019276596,0.000080938735,0.00005824647,0.00020195424,0.00003324284,0.00028701016,0.0001855858,0.0003424713,0.000043425352],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009927832,0.000027042186,0.12927336,0.000008787054,0.000020562054,0.00000796111,0.00035966255,0.2365913,0.0026626422,0.14374289,0.000036418758,0.48725945],"study_design_scores_gemma":[0.00024611223,0.0000941628,0.0072323713,0.000073002884,0.000003728606,0.000014122097,0.000006105818,0.9883664,0.0001380065,0.0026111351,0.0010666536,0.00014814457],"about_ca_topic_score_codex":0.000032051736,"about_ca_topic_score_gemma":0.0000040498685,"teacher_disagreement_score":0.965576,"about_ca_system_score_codex":0.000019410969,"about_ca_system_score_gemma":0.000035514688,"threshold_uncertainty_score":0.3300586},"labels":[],"label_agreement":null},{"id":"W1499053674","doi":"10.1007/s10994-011-5259-2","title":"ILP turns 20","year":2011,"lang":"en","type":"article","venue":"Machine Learning","topic":"Logic, Reasoning, and Knowledge","field":"Computer Science","cited_by":128,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Biotechnology and Biological Sciences Research Council; Microsoft Research; University of Oxford; Imperial College London; University of New South Wales; Royal Academy of Engineering; Jawaharlal Nehru University","keywords":"Inductive logic programming; Analogy; Subject (documents); Implementation; Computer science; Artificial intelligence; Development (topology); Projection (relational algebra); Cognitive science; Machine learning; Epistemology; Psychology; Programming language; Mathematics; Algorithm; Library science","score_opus":0.02463525336756793,"score_gpt":0.22296309924810606,"score_spread":0.19832784588053815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1499053674","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03242247,0.001267568,0.31157708,0.0002773168,0.0007539078,0.00011198684,6.503285e-7,0.00093986496,0.65264916],"genre_scores_gemma":[0.9767629,0.000014153506,0.013666509,0.00016796486,0.00011195433,0.0000044488575,0.0000026097453,0.000011573413,0.009257906],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99905896,0.00010150482,0.00012631131,0.0002900965,0.00013264253,0.00029046016],"domain_scores_gemma":[0.9994503,0.000046721412,0.00007012935,0.00029754627,0.000037496386,0.00009775574],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028675975,0.00012551059,0.00013060069,0.00007109987,0.00016053887,0.00007586957,0.00064865605,0.000055961948,0.00030093698],"category_scores_gemma":[0.00011763819,0.00010222469,0.000067294655,0.00021525513,0.00003080445,0.00022923622,0.0002044829,0.00033438718,0.00056211726],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025979218,0.00032439278,0.33372068,0.00007055476,0.00008673107,0.00028552083,0.06400905,0.0002833721,0.0018750618,0.41224667,0.002977057,0.1840949],"study_design_scores_gemma":[0.0014129053,0.0007246406,0.087404035,0.000058851605,0.000029162316,0.00019156508,0.00016508825,0.28608954,0.002984132,0.023792254,0.5959365,0.001211382],"about_ca_topic_score_codex":0.00010873426,"about_ca_topic_score_gemma":0.0000542672,"teacher_disagreement_score":0.9443404,"about_ca_system_score_codex":0.000018423954,"about_ca_system_score_gemma":0.000022059581,"threshold_uncertainty_score":0.7225068},"labels":[],"label_agreement":null},{"id":"W1560635010","doi":"10.1023/a:1007653929870","title":"Stochastic Grammatical Inference of Text Database Structure","year":2000,"lang":"en","type":"article","venue":"Machine Learning","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Grammar induction; Computer science; Nesting (process); Markup language; Inference; Construct (python library); Semantics (computer science); Grammar; Artificial intelligence; Natural language processing; Theoretical computer science; Programming language; XML; Rule-based machine translation; Linguistics","score_opus":0.008191670648523592,"score_gpt":0.2716978941340115,"score_spread":0.2635062234854879,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1560635010","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04429649,0.00078398414,0.95384985,0.00021577255,0.000031585038,0.00008216453,0.0000056913323,0.00045247297,0.00028197607],"genre_scores_gemma":[0.73066545,0.000002634991,0.2690635,0.00005866955,0.00001820938,0.000001636101,0.000010928276,0.0000066658367,0.00017230921],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990522,0.000078069635,0.00019004823,0.0002425479,0.0002425468,0.00019457558],"domain_scores_gemma":[0.99933743,0.00013535752,0.00007761598,0.00035026367,0.00004222268,0.000057082798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001536593,0.00012217935,0.00015997444,0.00008007927,0.000086907006,0.0000736852,0.00070711726,0.00005212107,0.0004100142],"category_scores_gemma":[0.00033273062,0.00009858245,0.000029720357,0.00031170514,0.000049759663,0.00031421843,0.000189349,0.00043046928,0.000015776064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018961193,0.000049527796,0.0010963595,0.0001260178,0.000016118353,0.000033958626,0.0012606949,0.006314202,0.012079588,0.05179463,0.000065705026,0.9271442],"study_design_scores_gemma":[0.0002996453,0.00014845443,0.00040486545,0.00017411393,0.0000125494735,0.000059640268,0.0000089807845,0.9551142,0.006100874,0.03662026,0.0007124164,0.00034402835],"about_ca_topic_score_codex":0.000086682136,"about_ca_topic_score_gemma":0.000010966929,"teacher_disagreement_score":0.94879997,"about_ca_system_score_codex":0.0000133526055,"about_ca_system_score_gemma":0.000029656716,"threshold_uncertainty_score":0.44893682},"labels":[],"label_agreement":null},{"id":"W1560659665","doi":"10.1023/a:1013947519741","title":"Metric-Based Methods for Adaptive Model Selection and Regularization","year":2002,"lang":"en","type":"article","venue":"Machine Learning","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Regularization (linguistics); Artificial intelligence; Computer science; Machine learning; Labeled data; Training set; Exploit; Model selection; Supervised learning; Regression; Pattern recognition (psychology); Mathematics; Statistics; Artificial neural network","score_opus":0.029202128097776763,"score_gpt":0.29442337625596693,"score_spread":0.26522124815819015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1560659665","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014610405,0.0002398729,0.9980432,0.00059262186,0.00002900058,0.000113288814,5.210749e-7,0.00014033733,0.00069510116],"genre_scores_gemma":[0.39745298,0.0000067343067,0.6019513,0.00008767148,0.000012291867,0.000013359192,0.00000156108,0.000006248431,0.000467873],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992681,0.000089594934,0.0001178039,0.00028016025,0.00008436137,0.00015994237],"domain_scores_gemma":[0.99956125,0.0001274054,0.00008814826,0.0000960203,0.00007979244,0.000047355214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032062584,0.00009612305,0.0001086057,0.00015665143,0.00023864013,0.00013497197,0.00015704922,0.000048821206,0.00001052412],"category_scores_gemma":[0.00019688682,0.00008841565,0.000028727512,0.00052692153,0.000011080095,0.00027509726,0.000044117216,0.00012783283,0.0000017795415],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010462806,0.000037757804,0.00085291546,0.000047331887,0.000013138067,4.9267607e-7,0.0004322148,0.13464716,0.0011434379,0.11386098,0.000058239704,0.7488959],"study_design_scores_gemma":[0.00024168428,0.0001424236,0.00010784155,0.000008839416,0.0000075520006,0.0000037540306,0.000002833794,0.9866405,0.0011763299,0.010911893,0.00064551906,0.00011081651],"about_ca_topic_score_codex":0.000008028908,"about_ca_topic_score_gemma":0.0000024329406,"teacher_disagreement_score":0.8519933,"about_ca_system_score_codex":0.000021206853,"about_ca_system_score_gemma":0.000015755291,"threshold_uncertainty_score":0.36054853},"labels":[],"label_agreement":null},{"id":"W1589662877","doi":"10.5772/9149","title":"Fuzzy System with Positive and Negative Rules","year":2010,"lang":"en","type":"book-chapter","venue":"Machine Learning","topic":"Fuzzy Logic and Control Systems","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Fuzzy logic; Computer science; Artificial intelligence","score_opus":0.005503985490406825,"score_gpt":0.180494299935262,"score_spread":0.1749903144448552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1589662877","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018040792,0.0012015462,0.017294664,0.00026118732,0.00022010536,0.0003338182,0.000014805696,0.00035458457,0.9801389],"genre_scores_gemma":[0.7000329,0.000039312574,0.009026173,0.00020075141,0.00052410614,0.000031399435,0.00003483577,0.000096974814,0.29001355],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984265,0.00008494657,0.0002469669,0.00062955415,0.0003443633,0.00026764564],"domain_scores_gemma":[0.99881583,0.00022436888,0.00035009568,0.00036734404,0.00011342693,0.0001289467],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026822797,0.00040388704,0.0005454136,0.00013029107,0.00033386558,0.0002593864,0.00045604276,0.00027802328,0.00000640187],"category_scores_gemma":[0.000021621208,0.00029463274,0.00007639973,0.000032810705,0.0001125336,0.00016805148,0.00028397076,0.0011154383,0.00009485948],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025356238,0.0000039219726,0.00017983792,0.00008283565,0.00011627887,0.00019324299,0.00069404446,0.000048082748,0.000045467423,0.98175794,0.000015013428,0.016837962],"study_design_scores_gemma":[0.016636869,0.010099909,0.009874297,0.01581009,0.0012475888,0.010416435,0.0012800891,0.14459614,0.0002526873,0.3681614,0.40682563,0.014798843],"about_ca_topic_score_codex":0.00032895216,"about_ca_topic_score_gemma":0.000103014376,"teacher_disagreement_score":0.69985247,"about_ca_system_score_codex":0.000054313372,"about_ca_system_score_gemma":0.000054668435,"threshold_uncertainty_score":0.9999506},"labels":[],"label_agreement":null},{"id":"W1591760165","doi":"10.1023/a:1013943418833","title":"Model Selection for Small Sample Regression","year":2002,"lang":"en","type":"article","venue":"Machine Learning","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":125,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Overfitting; Estimator; Generalization; Model selection; Generalization error; Mathematics; Covariance matrix; Artificial intelligence; Selection (genetic algorithm); Linear regression; Applied mathematics; Regression; Sample size determination; Computer science; Statistics; Artificial neural network","score_opus":0.05444036630139729,"score_gpt":0.265644620019226,"score_spread":0.21120425371782872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1591760165","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008386652,0.00008692452,0.989285,0.0014134465,0.00003657787,0.00010301508,9.552846e-7,0.0002023816,0.00048503128],"genre_scores_gemma":[0.7670095,0.000019681891,0.23006321,0.00022698539,0.00008882468,0.000043142067,0.0000065733598,0.000009316187,0.0025327436],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994864,0.000019402569,0.000084881576,0.00020039872,0.000058412024,0.00015053371],"domain_scores_gemma":[0.99967325,0.00009375621,0.000049277707,0.0001213437,0.000025028938,0.0000373411],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000802494,0.00006622533,0.000062258725,0.00003053182,0.00030784128,0.000065993896,0.00019874306,0.00002656543,0.000016323265],"category_scores_gemma":[0.000034726556,0.000055162374,0.000037718735,0.00016899219,0.000005303495,0.000096033065,0.00005823122,0.00012620594,0.000010121929],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033864085,0.00006558645,0.0032836306,0.000011704974,0.000005596336,2.6856102e-7,0.0002758704,0.57876784,0.0034060685,0.034156922,0.0039783674,0.37604475],"study_design_scores_gemma":[0.00010754656,0.000032287076,0.00005169276,0.000005646386,0.0000017927051,0.0000025458567,8.7814107e-7,0.9702407,0.00018346263,0.0032444475,0.026060503,0.00006845943],"about_ca_topic_score_codex":0.000028437524,"about_ca_topic_score_gemma":0.000024264042,"teacher_disagreement_score":0.7592218,"about_ca_system_score_codex":0.000011649583,"about_ca_system_score_gemma":0.0000027878673,"threshold_uncertainty_score":0.23676974},"labels":[],"label_agreement":null},{"id":"W1851653583","doi":"10.1007/s10994-015-5535-7","title":"Learning to identify relevant studies for systematic reviews using random forest and external information","year":2015,"lang":"en","type":"article","venue":"Machine Learning","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Random forest; Computer science; Heuristics; Machine learning; Classifier (UML); Artificial intelligence; Cluster analysis; Systematic review; Class (philosophy); Recall; USable; Task (project management); Data mining; Information retrieval; Natural language processing; World Wide Web","score_opus":0.09096737967275106,"score_gpt":0.3815705795832492,"score_spread":0.2906031999104981,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1851653583","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014117168,0.0015692016,0.98222136,0.00023327649,0.00012615771,0.0014371225,0.0000011872712,0.00026104896,0.00003346516],"genre_scores_gemma":[0.5247203,0.00030686843,0.47351047,0.0003923212,0.00009509682,0.00056394667,0.000025052323,0.000024265779,0.00036166643],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984247,0.0002987865,0.0006055691,0.000221158,0.00024268626,0.00020711178],"domain_scores_gemma":[0.99857575,0.0003375062,0.00047188895,0.00028330734,0.00023366518,0.00009787907],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002732664,0.00015537621,0.0004358626,0.00019945853,0.00024989218,0.00034847078,0.00035432688,0.00003739154,4.7997275e-7],"category_scores_gemma":[0.0065354267,0.00012382567,0.00004760855,0.0002327659,0.000020591633,0.0013463374,0.00030405758,0.0001844383,0.000023496486],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007638857,0.00018823867,0.071897626,0.10947682,0.0005691663,0.00003425526,0.17429128,0.2071294,0.035417013,0.053001586,0.007588075,0.33964264],"study_design_scores_gemma":[0.0010086042,0.00021052791,0.0004560792,0.003750595,0.000030474872,0.00004902403,0.0005741933,0.978644,0.00024330315,0.0016505023,0.013111398,0.0002712948],"about_ca_topic_score_codex":0.000023846855,"about_ca_topic_score_gemma":0.000005902542,"teacher_disagreement_score":0.7715146,"about_ca_system_score_codex":0.00010061424,"about_ca_system_score_gemma":0.000021242522,"threshold_uncertainty_score":0.7823988},"labels":[],"label_agreement":null},{"id":"W1964505066","doi":"10.1007/s10994-008-5087-1","title":"Guest editor’s introduction: special issue on inductive transfer learning","year":2008,"lang":"en","type":"article","venue":"Machine Learning","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Acadia University","funders":"","keywords":"Inductive transfer; Computer science; Transfer of learning; Multi-task learning; Artificial intelligence; Generalization; Task (project management); Heuristics; Machine learning; Representation (politics); Similarity (geometry); Transfer of training; Instance-based learning; Sequence learning; Active learning (machine learning); Robot learning; Knowledge management; Mathematics","score_opus":0.008890312988525221,"score_gpt":0.2275228686149516,"score_spread":0.2186325556264264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964505066","genre_codex":"methods","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26122624,0.0007111621,0.3366117,0.0522076,0.15978605,0.0014912873,0.000010659454,0.008427576,0.17952774],"genre_scores_gemma":[0.40961996,0.000096906864,0.007966585,0.00050764676,0.54572207,0.000031474097,0.000057639158,0.000107381034,0.035890345],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968281,0.0005698353,0.00037071932,0.0009334915,0.00070567854,0.000592224],"domain_scores_gemma":[0.9989538,0.0001666913,0.00010816641,0.00046208085,0.00011604329,0.00019321387],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005688433,0.0003946241,0.0003928526,0.00030955224,0.0012788058,0.00016138614,0.0007242685,0.00015731534,0.00078797434],"category_scores_gemma":[0.00039641146,0.00037182347,0.00015900517,0.00070084905,0.000118190655,0.00051401893,0.00017840271,0.0024606325,0.0009611085],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002567587,0.00083259493,0.051782552,0.000084792286,0.00027144892,0.0007369092,0.029469365,0.2141461,0.0013189734,0.010758916,0.23987614,0.45046544],"study_design_scores_gemma":[0.00062123954,0.000646625,0.002408643,0.000019009984,0.00000841886,0.00015444454,0.00007551398,0.0448727,0.00046732952,0.000053476422,0.95021886,0.0004537583],"about_ca_topic_score_codex":0.00016176088,"about_ca_topic_score_gemma":0.00000848601,"teacher_disagreement_score":0.7103427,"about_ca_system_score_codex":0.00009025284,"about_ca_system_score_gemma":0.00006276917,"threshold_uncertainty_score":0.9998734},"labels":[],"label_agreement":null},{"id":"W1970842225","doi":"10.1007/s10994-013-5336-9","title":"Learning semantic representations of objects and their parts","year":2013,"lang":"en","type":"article","venue":"Machine Learning","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Agence Nationale de la Recherche; Compute Canada; Defense Advanced Research Projects Agency; Canadian Institute for Advanced Research","keywords":"Computer science; WordNet; Object (grammar); Embedding; Artificial intelligence; Image retrieval; Annotation; Set (abstract data type); Image (mathematics); Information retrieval; Automatic image annotation; Learning object; Cognitive neuroscience of visual object recognition; Machine learning; Pattern recognition (psychology)","score_opus":0.01081827026464842,"score_gpt":0.2673789469826173,"score_spread":0.2565606767179689,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970842225","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10852943,0.00059102225,0.886584,0.00036143357,0.00003349761,0.00017897593,2.4938916e-7,0.0003737063,0.0033476981],"genre_scores_gemma":[0.9822151,0.000111631445,0.01681304,0.000055884753,0.0000174252,0.00001182402,0.0000024660067,0.000009948215,0.00076264946],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991919,0.000120384575,0.0001743383,0.00023891896,0.00010110919,0.00017334755],"domain_scores_gemma":[0.99934125,0.00020260362,0.00012328984,0.00020794236,0.0000728877,0.00005204908],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018490838,0.00010484037,0.00015597839,0.000094517876,0.00016673314,0.00008761133,0.00020486579,0.000030445985,0.000027271253],"category_scores_gemma":[0.0002588005,0.0000846462,0.000036967875,0.00026064442,0.000045236873,0.0005619738,0.00024573947,0.00026247534,0.0000118357275],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000063963544,0.00006511856,0.16152543,0.00011177385,0.000046617013,0.000013965572,0.010143742,0.003172213,0.055724464,0.0056447526,0.00019591807,0.7633496],"study_design_scores_gemma":[0.0007475115,0.00093008083,0.06300277,0.00021436729,0.000016595013,0.00010639511,0.0012790787,0.669373,0.23218624,0.022357404,0.009065222,0.00072134705],"about_ca_topic_score_codex":0.00016648877,"about_ca_topic_score_gemma":0.000003968249,"teacher_disagreement_score":0.8736857,"about_ca_system_score_codex":0.0000067419883,"about_ca_system_score_gemma":0.000010364117,"threshold_uncertainty_score":0.3451772},"labels":[],"label_agreement":null},{"id":"W1973974006","doi":"10.1007/s10994-014-5435-2","title":"Asymptotic stability of equilibrium points of mean shift algorithm","year":2014,"lang":"en","type":"article","venue":"Machine Learning","topic":"Statistical Mechanics and Entropy","field":"Physics and Astronomy","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Lyapunov function; Mathematics; Equilibrium point; Stationary point; Cluster analysis; Stability theory; Function (biology); Algorithm; Mathematical optimization; Applied mathematics; Nonlinear system; Mathematical analysis; Statistics; Differential equation","score_opus":0.008805442501923695,"score_gpt":0.23631504181872012,"score_spread":0.22750959931679643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973974006","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40330008,0.00001373535,0.59205043,0.000062735984,0.000088292116,0.00006716898,0.000040144,0.00001714742,0.004360279],"genre_scores_gemma":[0.99270636,1.965876e-7,0.0071309204,0.000008544476,0.000073558454,0.000002043724,0.000029875615,0.000014374012,0.000034110155],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99911934,0.00012457202,0.00026123726,0.0001609438,0.000154835,0.0001790758],"domain_scores_gemma":[0.9993846,0.00019809765,0.00014143,0.00017063631,0.00004231354,0.000062940584],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00034329228,0.000101039324,0.00024979582,0.000029568782,0.00003100609,0.000009000805,0.00010956568,0.000020655178,0.0012090022],"category_scores_gemma":[0.00007217885,0.000090777336,0.00007875978,0.000080152735,0.00003646398,0.000033272197,0.000078810044,0.00015920609,0.0000122955535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003376445,0.00025271042,0.22294757,0.00010384808,0.000100198245,4.813185e-7,0.00071898533,0.00045117864,0.0047467593,0.527916,0.000022757777,0.24270573],"study_design_scores_gemma":[0.0008708973,0.0003597973,0.012923542,0.00004462561,0.00005092004,2.3804019e-7,0.00011759174,0.9130641,0.012504743,0.05905993,0.00078967295,0.00021394393],"about_ca_topic_score_codex":0.00039505007,"about_ca_topic_score_gemma":0.0000013518681,"teacher_disagreement_score":0.9126129,"about_ca_system_score_codex":0.0000065409563,"about_ca_system_score_gemma":0.000011584686,"threshold_uncertainty_score":0.999704},"labels":[],"label_agreement":null},{"id":"W1987756646","doi":"10.1007/s10994-009-5151-5","title":"A co-classification approach to learning from multilingual corpora","year":2009,"lang":"en","type":"article","venue":"Machine Learning","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Categorization; Artificial intelligence; Boosting (machine learning); Regularization (linguistics); Natural language processing; Benchmarking; Consistency (knowledge bases); Text categorization; Machine learning","score_opus":0.02645328759020278,"score_gpt":0.2968939080229041,"score_spread":0.27044062043270134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987756646","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0351734,0.0007605026,0.9562909,0.00081209897,0.000059695267,0.00019543343,9.956696e-7,0.002126655,0.004580319],"genre_scores_gemma":[0.6150366,0.0000026216787,0.3840418,0.00035213193,0.000071864226,0.000006828438,0.000041081148,0.00001139572,0.0004356901],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99827874,0.00020297694,0.0002491153,0.0006068752,0.00034725704,0.00031505126],"domain_scores_gemma":[0.9991418,0.000101607744,0.00018547536,0.00036233457,0.00008147995,0.00012726891],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048058154,0.00020539662,0.00021291022,0.000196269,0.0003094629,0.0003278538,0.0008676764,0.000114466086,0.000009719724],"category_scores_gemma":[0.0005149575,0.0001917604,0.00005686011,0.0004933618,0.00001932623,0.00034923558,0.00010434186,0.00087657385,0.000056111712],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003969925,0.0001871108,0.009763365,0.000016528546,0.000018063467,0.00003240375,0.006913859,0.004619214,0.10989055,0.016692149,0.00030091108,0.85152614],"study_design_scores_gemma":[0.00037311797,0.00026030556,0.0063269893,0.00005757127,0.00000918299,0.000021585638,0.000105791136,0.96355975,0.017109077,0.005114126,0.006532614,0.0005298763],"about_ca_topic_score_codex":0.00014228612,"about_ca_topic_score_gemma":0.000002045042,"teacher_disagreement_score":0.95894057,"about_ca_system_score_codex":0.000057278015,"about_ca_system_score_gemma":0.000033757922,"threshold_uncertainty_score":0.78197616},"labels":[],"label_agreement":null},{"id":"W1992860510","doi":"10.1007/s10994-014-5446-z","title":"Adaptive Euclidean maps for histograms: generalized Aitchison embeddings","year":2014,"lang":"en","type":"article","venue":"Machine Learning","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Japan Society for the Promotion of Science; Ministry of Education, Culture, Sports, Science and Technology; McGill University","keywords":"Mahalanobis distance; Simplex; Euclidean space; Metric (unit); Euclidean geometry; Euclidean distance; Artificial intelligence; Metric space; Histogram; Mathematics; Computer science; Simple (philosophy); Pattern recognition (psychology); Machine learning; Combinatorics; Discrete mathematics; Image (mathematics)","score_opus":0.015586888487415388,"score_gpt":0.2740671935572671,"score_spread":0.2584803050698517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992860510","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011065106,0.0003032599,0.9945037,0.000490647,0.00013846128,0.0002566654,0.000002175508,0.0009290408,0.0022695453],"genre_scores_gemma":[0.315504,0.000030938943,0.6809212,0.0008064762,0.0001761034,0.000054609995,0.0000223967,0.000040715586,0.0024435394],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985355,0.00013768206,0.0002550494,0.0004831246,0.0001992921,0.00038931947],"domain_scores_gemma":[0.99904037,0.00021703175,0.00018484471,0.00035571182,0.00010173675,0.000100334386],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006002615,0.00021134858,0.00027520471,0.00012899021,0.00031125077,0.00012947417,0.0006110884,0.00006972638,0.000012844697],"category_scores_gemma":[0.00045212585,0.00019531108,0.0001451232,0.00026958092,0.000037297777,0.0004457714,0.00022184936,0.00028908125,0.000019224906],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006882633,0.000046718007,0.0010425844,0.000032750202,0.000023927645,0.000005217001,0.0007653302,0.0007330624,0.004400758,0.09031999,0.0024800398,0.9000808],"study_design_scores_gemma":[0.0006677801,0.00061261764,0.00008327852,0.00003258987,0.000010761785,0.00001053823,0.000014128581,0.4119639,0.0075094113,0.028906275,0.5498383,0.00035036504],"about_ca_topic_score_codex":0.000077051365,"about_ca_topic_score_gemma":0.000007889842,"teacher_disagreement_score":0.89973044,"about_ca_system_score_codex":0.00006351158,"about_ca_system_score_gemma":0.00001579352,"threshold_uncertainty_score":0.79645544},"labels":[],"label_agreement":null},{"id":"W2000334459","doi":"10.1007/s10994-006-8366-8","title":"Learning decomposable markov networks in pseudo-independent domains with local evaluation","year":2006,"lang":"en","type":"article","venue":"Machine Learning","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Graphical model; Inference; Computer science; Domain (mathematical analysis); Focus (optics); Probabilistic logic; Approximate inference; Theoretical computer science; Markov chain; Artificial intelligence; Algorithm; Bayesian network; Computation; Machine learning; Mathematics","score_opus":0.008028931723578174,"score_gpt":0.23737798604925192,"score_spread":0.22934905432567373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000334459","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16646476,0.00020850191,0.8287129,0.000203679,0.000075435106,0.00013536918,1.198093e-7,0.00019650249,0.0040027807],"genre_scores_gemma":[0.976164,0.000010609617,0.023159537,0.0000707506,0.00007818806,0.000024485871,0.000022714063,0.000021468288,0.00044823452],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976349,0.00048339064,0.0003097328,0.000526969,0.0005556606,0.0004893438],"domain_scores_gemma":[0.9993082,0.000115362825,0.00014211205,0.00026120566,0.00009740218,0.00007565989],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015858937,0.00021446824,0.00021816655,0.00016669229,0.00027461306,0.000245865,0.00042278404,0.000102665035,0.000046053086],"category_scores_gemma":[0.00003626742,0.00019257942,0.00004336735,0.0005236162,0.000040234903,0.0003432882,0.00016111416,0.00089180627,0.000023748802],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022097778,0.000038167014,0.06297301,0.0000048703932,0.0000053566428,0.000024683422,0.00013105232,0.8728412,0.000055991706,0.0019881334,0.000017126862,0.061898302],"study_design_scores_gemma":[0.0007960631,0.00021445786,0.01486767,0.00006178293,0.000009343794,0.000042072967,0.000035355737,0.9822827,0.00003351818,0.0011110989,0.00029007805,0.00025587314],"about_ca_topic_score_codex":0.0011606358,"about_ca_topic_score_gemma":0.0011869135,"teacher_disagreement_score":0.80969924,"about_ca_system_score_codex":0.00015485073,"about_ca_system_score_gemma":0.000090004934,"threshold_uncertainty_score":0.7853161},"labels":[],"label_agreement":null},{"id":"W2006330826","doi":"10.1007/s10994-011-5254-7","title":"Model selection in reinforcement learning","year":2011,"lang":"en","type":"article","venue":"Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Mathematics; Estimator; Oracle; Bellman equation; Function (biology); Regularization (linguistics); Countable set; Sequence (biology); Combinatorics; Rate of convergence; Discrete mathematics; Mathematical optimization; Computer science; Artificial intelligence; Statistics","score_opus":0.03659510899503107,"score_gpt":0.24580997705280483,"score_spread":0.20921486805777376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006330826","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011630058,0.000032261352,0.95233506,0.00005427527,0.0000875936,0.00014456488,2.4758874e-8,0.0004751324,0.035241026],"genre_scores_gemma":[0.9450121,0.000022998864,0.04760224,0.00012001906,0.000026164897,0.000017012218,0.0000047837857,0.00002597894,0.007168737],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980894,0.00017286876,0.00041560244,0.0004235083,0.00037620112,0.00052242656],"domain_scores_gemma":[0.9993745,0.000050998355,0.00020816305,0.00021750944,0.000056722907,0.00009208832],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072162424,0.00022232444,0.00020933771,0.00035403066,0.00025698816,0.000104198385,0.0006113523,0.00009321766,0.00012050052],"category_scores_gemma":[0.00021140643,0.00023082737,0.00005644726,0.0006207123,0.000025038764,0.0006239088,0.00035339664,0.00097225,0.000120692195],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009690553,0.000014581834,0.04922677,0.000010969682,0.000008971184,0.000007598156,0.0026841678,0.93778723,0.00047906884,0.0067916154,0.000014693481,0.0029646424],"study_design_scores_gemma":[0.0003952052,0.00024998034,0.003296698,0.00002753902,0.0000043152136,0.000010029676,0.00003269272,0.9940863,0.00032765605,0.00024449057,0.0010667791,0.00025829588],"about_ca_topic_score_codex":0.00026800553,"about_ca_topic_score_gemma":0.000031890402,"teacher_disagreement_score":0.93338203,"about_ca_system_score_codex":0.00014025607,"about_ca_system_score_gemma":0.00005610281,"threshold_uncertainty_score":0.9412867},"labels":[],"label_agreement":null},{"id":"W2013023084","doi":"10.1007/s10994-013-5371-6","title":"Beam search algorithms for multilabel learning","year":2013,"lang":"en","type":"article","venue":"Machine Learning","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":90,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Inference; Beam search; Computer science; Machine learning; Artificial intelligence; Probabilistic logic; Classifier (UML); Task (project management); Range (aeronautics); Algorithm; Search algorithm","score_opus":0.031059016798618035,"score_gpt":0.28921241142287696,"score_spread":0.2581533946242589,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013023084","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039460715,0.00026385646,0.95220774,0.0039168014,0.0001526392,0.0004657455,7.0607626e-7,0.0019241988,0.0016076122],"genre_scores_gemma":[0.8799031,0.00002405072,0.10918187,0.000109933266,0.000051002815,0.00016328624,0.000014766971,0.0000203198,0.010531713],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987253,0.000060504957,0.00020204856,0.00039780943,0.00022230898,0.0003920475],"domain_scores_gemma":[0.9991853,0.0002253539,0.00008975557,0.00031502347,0.000117394266,0.000067138506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036615905,0.00014506347,0.00014942823,0.00017296703,0.00044022218,0.00037148324,0.0007656517,0.000083667706,0.000101856014],"category_scores_gemma":[0.00031967578,0.00012957207,0.000068359375,0.0003135354,0.00004708021,0.00056961353,0.00033942104,0.00044856878,0.0003290929],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029000173,0.000051733765,0.016837971,0.000024703733,0.000020367277,0.0000013881217,0.00074068265,0.004272901,0.008324143,0.011920179,0.00091141846,0.9568916],"study_design_scores_gemma":[0.00048738113,0.0001861828,0.0051194467,0.000010289276,0.000003086764,0.0000039642655,0.00022140346,0.9297019,0.006100121,0.0013954606,0.056539353,0.0002314131],"about_ca_topic_score_codex":0.00013530823,"about_ca_topic_score_gemma":0.0000020858865,"teacher_disagreement_score":0.9566602,"about_ca_system_score_codex":0.000036759953,"about_ca_system_score_gemma":0.000021623964,"threshold_uncertainty_score":0.5283796},"labels":[],"label_agreement":null},{"id":"W2013029345","doi":"10.1007/s10994-009-5137-3","title":"Learning the set covering machine by bound minimization and margin-sparsity trade-off","year":2009,"lang":"en","type":"article","venue":"Machine Learning","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"VC dimension; Classifier (UML); Margin (machine learning); Computer science; Minification; Upper and lower bounds; Artificial intelligence; Machine learning; Dimension (graph theory); Algorithm; Structural risk minimization; Mathematics; Mathematical optimization; Support vector machine; Combinatorics","score_opus":0.007079538754920486,"score_gpt":0.22503493450158998,"score_spread":0.2179553957466695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013029345","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4131886,0.011196907,0.5320848,0.033369202,0.00067220186,0.0006574867,0.000017082313,0.0020942625,0.006719425],"genre_scores_gemma":[0.9917265,0.0003013705,0.0042169453,0.0008858913,0.0001502039,0.0000049277924,0.00006693775,0.000030052324,0.0026171482],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99740535,0.0005957794,0.00033671054,0.00066112453,0.00044870176,0.0005523144],"domain_scores_gemma":[0.9988936,0.00028095458,0.00024895213,0.00038390493,0.000028610331,0.00016396857],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0009551202,0.00035545553,0.00032520213,0.00012674202,0.0014237522,0.0006753601,0.0007075848,0.00010715163,0.00004568839],"category_scores_gemma":[0.00027302047,0.0002845261,0.000090866684,0.0004989722,0.0000740428,0.00047283355,0.00028307384,0.0013757766,0.00001874141],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004259044,0.000102846934,0.063769095,0.000039720944,0.00006361701,0.000048961796,0.0061198547,0.08036226,0.0015364846,0.0024165702,0.0022981593,0.84319985],"study_design_scores_gemma":[0.0005808953,0.00030907852,0.016105384,0.000028030581,0.000016681091,0.00008734086,0.00006344324,0.82618076,0.000098822886,0.00025498105,0.15592447,0.00035011713],"about_ca_topic_score_codex":0.0001932509,"about_ca_topic_score_gemma":0.000013760361,"teacher_disagreement_score":0.84284973,"about_ca_system_score_codex":0.000046972953,"about_ca_system_score_gemma":0.000027200284,"threshold_uncertainty_score":0.99996066},"labels":[],"label_agreement":null},{"id":"W2014398373","doi":"10.1007/s10994-006-0477-8","title":"Bidding agents for online auctions with hidden bids","year":2006,"lang":"en","type":"article","venue":"Machine Learning","topic":"Auction Theory and Applications","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Common value auction; Bidding; Valuation (finance); Computer science; Combinatorial auction; Artificial intelligence; Machine learning; Ex-ante; Econometrics; Mathematical optimization; Microeconomics; Economics; Mathematics","score_opus":0.078163754291518,"score_gpt":0.38805502070464504,"score_spread":0.30989126641312703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014398373","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5606782,0.000063580475,0.42874932,0.0026725247,0.00016425161,0.00030250062,0.00006053163,0.00023219135,0.007076926],"genre_scores_gemma":[0.9362422,0.0000015826223,0.013589116,0.00010407266,0.00033296712,0.00004367476,0.000087636436,0.000018978786,0.049579777],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99874663,0.000091198905,0.00030296127,0.0003258582,0.00034873132,0.00018463239],"domain_scores_gemma":[0.9989145,0.00047258884,0.00018418633,0.00024884014,0.0001289421,0.00005096156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007368358,0.000104659004,0.00014228911,0.00019312103,0.0006868014,0.0001325143,0.00026141678,0.000039130075,0.0006382599],"category_scores_gemma":[0.0003906069,0.00007479454,0.00007358244,0.00066383835,0.00006398577,0.00016514701,0.00004550635,0.00016408574,0.00014522907],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002339838,0.0006535295,0.17964733,0.000016733444,0.00008483805,0.000007663015,0.00076959067,0.22709446,0.0036788834,0.18329918,0.024512399,0.3800014],"study_design_scores_gemma":[0.00061719166,0.00011374529,0.030110056,0.00001161985,0.000026366559,0.000024706094,0.0005063548,0.05708013,0.00022097827,0.04622293,0.8648502,0.00021569927],"about_ca_topic_score_codex":0.00008279159,"about_ca_topic_score_gemma":0.00014212923,"teacher_disagreement_score":0.8403378,"about_ca_system_score_codex":0.000021937849,"about_ca_system_score_gemma":0.000019620913,"threshold_uncertainty_score":0.69884986},"labels":[],"label_agreement":null},{"id":"W2018288672","doi":"10.1007/s10994-006-9713-5","title":"Slow emergence of cooperation for win-stay lose-shift on trees","year":2006,"lang":"en","type":"article","venue":"Machine Learning","topic":"Evolutionary Game Theory and Cooperation","field":"Social Sciences","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Division of Emerging Frontiers; Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies; National Science Foundation","keywords":"Exponential growth; Graph; Bounded function; Exponential function; Convergence (economics); Computer science; Dilemma; Mathematics; Discrete mathematics; Theoretical computer science; Economics","score_opus":0.013706365712844998,"score_gpt":0.2847747342946952,"score_spread":0.2710683685818502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2018288672","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92998594,0.00027921656,0.023378093,0.0017573086,0.00026749383,0.00038379795,0.000013765632,0.00012622013,0.043808144],"genre_scores_gemma":[0.9901863,0.000017889206,0.00035734655,0.000050589548,0.0002912169,0.000016404358,0.00006667698,0.000008388649,0.0090052085],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99909604,0.0002627607,0.00017305858,0.0001421368,0.00017500127,0.0001510094],"domain_scores_gemma":[0.9996016,0.00014440044,0.00008076507,0.00006899498,0.000079612255,0.000024621257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065629213,0.00007261121,0.000096803895,0.00004847257,0.0006194572,0.000023193063,0.00009406604,0.000051324154,0.0003974381],"category_scores_gemma":[0.00024410491,0.00007004664,0.000046270627,0.00017338638,0.00008089199,0.00015720377,0.000009012146,0.00009210036,0.000018707868],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018094375,0.0001509883,0.021918936,0.00001600785,0.000012321463,7.918499e-7,0.0046146153,0.12467689,0.006912443,0.83147514,0.0013754894,0.008665463],"study_design_scores_gemma":[0.0040689274,0.0034029018,0.1297596,0.0002614718,0.00015641941,0.0000023745552,0.006941322,0.18874145,0.015104234,0.07870166,0.57107735,0.0017823247],"about_ca_topic_score_codex":0.0010084237,"about_ca_topic_score_gemma":0.003917013,"teacher_disagreement_score":0.75277346,"about_ca_system_score_codex":0.000022452421,"about_ca_system_score_gemma":0.000044731358,"threshold_uncertainty_score":0.47644266},"labels":[],"label_agreement":null},{"id":"W2023719154","doi":"10.1007/s10994-012-5308-5","title":"Learning directed relational models with recursive dependencies","year":2012,"lang":"en","type":"article","venue":"Machine Learning","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Statistical relational learning; Computer science; Markov blanket; Theoretical computer science; Graphical model; Probabilistic logic; Inductive logic programming; Predicate (mathematical logic); Bayesian network; Relational database; Artificial intelligence; Machine learning; Markov chain; Markov model; Data mining; Variable-order Markov model; Programming language","score_opus":0.027453026784250344,"score_gpt":0.234085874637636,"score_spread":0.20663284785338565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023719154","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04287689,0.0005268397,0.9461071,0.0003729875,0.0000988846,0.000060676623,4.6805397e-7,0.0006806249,0.009275518],"genre_scores_gemma":[0.88418216,0.000016951044,0.11409458,0.00007760086,0.00007836226,0.000009445665,0.000012012402,0.000016894648,0.0015119767],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851066,0.00022299957,0.00016896855,0.00029299306,0.00036924862,0.00043515075],"domain_scores_gemma":[0.9992618,0.00016034445,0.00012162539,0.00019383116,0.00011469251,0.00014768624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048365782,0.00017328879,0.00015729526,0.00010467913,0.0004067514,0.00010209402,0.00031368373,0.000073759,0.00003555972],"category_scores_gemma":[0.00012896498,0.00014470925,0.000040788178,0.00034255942,0.000034628138,0.0010883273,0.00014968317,0.0007152459,0.00006104939],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002958611,0.00007159221,0.10256226,0.000014728389,0.00005253147,0.000011818491,0.008016353,0.55801076,0.0002634343,0.30500317,0.000099506644,0.025864283],"study_design_scores_gemma":[0.00022423986,0.00013597003,0.004650531,0.000043940563,0.000010628235,0.00006187645,0.0000726592,0.9874516,0.00011500224,0.0051827617,0.001769602,0.0002811469],"about_ca_topic_score_codex":0.00009452044,"about_ca_topic_score_gemma":0.0000109766825,"teacher_disagreement_score":0.8413053,"about_ca_system_score_codex":0.00004261558,"about_ca_system_score_gemma":0.0000514526,"threshold_uncertainty_score":0.5901072},"labels":[],"label_agreement":null},{"id":"W2026798797","doi":"10.1007/s10994-005-0464-5","title":"Maximizing Agreements with One-Sided Error with Applications to Heuristic Learning","year":2005,"lang":"en","type":"article","venue":"Machine Learning","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Learnability; Constraint (computer-aided design); Heuristic; Class (philosophy); Mathematics; Discrete mathematics; Boolean function; Combinatorics; Artificial intelligence; Computer science; Mathematical optimization","score_opus":0.01560519044351934,"score_gpt":0.25798942077620063,"score_spread":0.24238423033268128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026798797","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025525805,0.00012748402,0.9625762,0.0032936756,0.000038228052,0.00045800305,0.0000011441855,0.00093116565,0.007048272],"genre_scores_gemma":[0.68844354,0.0000047271947,0.30490988,0.0005042717,0.0002152165,0.00012266092,0.000021807573,0.00005466045,0.0057232333],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99726653,0.00022931962,0.00033077455,0.00084862893,0.000646328,0.0006784065],"domain_scores_gemma":[0.99857104,0.00017920442,0.00023769183,0.00057827047,0.00012368087,0.00031014],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00050242036,0.00036530555,0.0003477186,0.00029901412,0.0008779164,0.00036091564,0.0008508762,0.000059882048,0.00010699694],"category_scores_gemma":[0.0001417119,0.00030107948,0.000057214373,0.0009723498,0.000044896457,0.0003788682,0.00033726552,0.001070679,0.00038050715],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006135165,0.00016966846,0.04162077,0.000043109852,0.00009635059,0.000036029232,0.0022103402,0.6456068,0.00045077846,0.0023183958,0.00008506109,0.3073013],"study_design_scores_gemma":[0.0016186165,0.001115092,0.0102275815,0.000240808,0.00005299078,0.00013117553,0.00016173992,0.8060467,0.00026237784,0.00008449118,0.17910478,0.0009536383],"about_ca_topic_score_codex":0.00021296676,"about_ca_topic_score_gemma":0.00012956654,"teacher_disagreement_score":0.66291773,"about_ca_system_score_codex":0.00009148821,"about_ca_system_score_gemma":0.00006644947,"threshold_uncertainty_score":0.99994415},"labels":[],"label_agreement":null},{"id":"W2026829590","doi":"10.1007/s10994-008-5091-5","title":"Effective short-term opponent exploitation in simplified poker","year":2008,"lang":"en","type":"article","venue":"Machine Learning","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; University of Alberta","keywords":"Nash equilibrium; Fictitious play; Computer science; Adversary; Best response; Bayesian game; Context (archaeology); Set (abstract data type); Convergence (economics); Game theory; Term (time); Mathematical economics; Repeated game; Artificial intelligence; Mathematical optimization; Mathematics; Computer security; Economics","score_opus":0.03764273235022859,"score_gpt":0.2966816643115067,"score_spread":0.25903893196127814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026829590","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7460401,0.00008807688,0.2517368,0.0002728005,0.00016492757,0.00019841909,2.344891e-7,0.00017517534,0.0013234513],"genre_scores_gemma":[0.99593925,0.000019882575,0.0035627917,0.00010978671,0.000054001022,0.000044963122,0.000003942466,0.000013339562,0.0002520212],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866104,0.0002141119,0.0002483529,0.0003585917,0.00023850698,0.00027941907],"domain_scores_gemma":[0.9993294,0.0002667987,0.000056318466,0.0002399781,0.000043848002,0.00006366716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033456547,0.00013750631,0.00016036292,0.00018188135,0.00018061681,0.00005653328,0.00038592058,0.000052863794,0.000030355519],"category_scores_gemma":[0.0002429973,0.00013397487,0.000051904983,0.00034402782,0.00004696053,0.00042607827,0.00018088745,0.0003305243,0.00012800751],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034746645,0.000144986,0.58572185,0.000015712292,0.000018166224,0.00029249192,0.020841593,0.04344433,0.011902393,0.0053315666,0.00008559016,0.33216658],"study_design_scores_gemma":[0.00019879753,0.00025544825,0.32069096,0.000052397296,0.0000040016935,0.000065153356,0.00022102278,0.6581988,0.016343785,0.0020017028,0.0015277497,0.00044019608],"about_ca_topic_score_codex":0.00017888962,"about_ca_topic_score_gemma":0.00007562769,"teacher_disagreement_score":0.61475444,"about_ca_system_score_codex":0.00008306299,"about_ca_system_score_gemma":0.000021302121,"threshold_uncertainty_score":0.5463337},"labels":[],"label_agreement":null},{"id":"W2031056773","doi":"10.1007/s10994-012-5316-5","title":"Quantum speed-up for unsupervised learning","year":2012,"lang":"en","type":"article","venue":"Machine Learning","topic":"Quantum Computing Algorithms and Architecture","field":"Computer Science","cited_by":213,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Cluster analysis; Unsupervised learning; Initialization; Graph; Speedup; Quantum; Quantum machine learning; Theoretical computer science; Quantization (signal processing); Algorithm; Artificial intelligence; Quantum algorithm","score_opus":0.016506940666037247,"score_gpt":0.25622023387617643,"score_spread":0.23971329321013918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2031056773","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2756375,0.0009996658,0.7194963,0.00086460944,0.0012613751,0.00020957128,0.0000014038399,0.0008387761,0.0006908047],"genre_scores_gemma":[0.96233195,0.000008294269,0.03527698,0.00023312072,0.0006591195,0.0000074490663,0.000016104133,0.000040197152,0.0014267678],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980759,0.00020858625,0.00025791366,0.00039536308,0.00026640802,0.0007958121],"domain_scores_gemma":[0.9989432,0.00035695152,0.00013195268,0.00030524548,0.000058558,0.00020405356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009488318,0.00024796702,0.0002599452,0.0001492463,0.0006705517,0.00018912325,0.00064355874,0.00007940943,0.000029171493],"category_scores_gemma":[0.00031701106,0.00021877607,0.00015973973,0.00034878153,0.000029584397,0.00031405236,0.00034185903,0.00067374384,0.00006895092],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004948697,0.00020830243,0.09246003,0.00017669704,0.00011223953,0.0000134563315,0.013904688,0.2212991,0.005262007,0.044499494,0.0009265791,0.6210879],"study_design_scores_gemma":[0.00049592904,0.00017181225,0.002745099,0.00002515938,0.000007965884,0.00003455772,0.000047355752,0.9136071,0.00027294716,0.00046178533,0.081840076,0.00029017538],"about_ca_topic_score_codex":0.00005126415,"about_ca_topic_score_gemma":0.000001567702,"teacher_disagreement_score":0.692308,"about_ca_system_score_codex":0.000027352251,"about_ca_system_score_gemma":0.000027256108,"threshold_uncertainty_score":0.89214295},"labels":[],"label_agreement":null},{"id":"W2032024758","doi":"10.1007/s10994-013-5421-0","title":"Tracking people over time in 19th century Canada for longitudinal analysis","year":2013,"lang":"en","type":"article","venue":"Machine Learning","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":36,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Waterloo; University of Guelph","funders":"Ontario Ministry of Research and Innovation; Research and Innovation Foundation","keywords":"Tracking (education); Late 19th century; Longitudinal data; Artificial intelligence; Computer science; Psychology; Data mining; Period (music); Art","score_opus":0.04624489143412698,"score_gpt":0.3420139273379866,"score_spread":0.2957690359038596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032024758","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9798911,0.00016074124,0.014231311,0.002454866,0.00019215788,0.00040874394,0.000058833815,0.0000412942,0.0025609056],"genre_scores_gemma":[0.9935564,0.0000046891023,0.00044448717,0.0003050841,0.00003867074,0.000010280273,0.0001176236,0.00000844991,0.005514347],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978137,0.00020658325,0.00046430784,0.0004415689,0.0007535646,0.0003202565],"domain_scores_gemma":[0.9984389,0.00087399624,0.00018037113,0.00034214812,0.00008274517,0.000081842496],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022162306,0.00012141717,0.00033537994,0.0003631206,0.00017290622,0.00034815786,0.00047123374,0.000030243293,0.0046446114],"category_scores_gemma":[0.0015959325,0.00009785692,0.00011637765,0.0012873982,0.00001427187,0.00038792545,0.00018682974,0.00017098815,0.00013464951],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017683387,0.000046343856,0.8881738,0.000012691732,0.00013640751,0.00000740321,0.0007724999,0.031050388,0.000038726354,0.00045263657,0.018180063,0.061111312],"study_design_scores_gemma":[0.000270056,0.00001981184,0.6950224,0.0000049249843,0.000053914286,4.3515456e-7,0.00048290123,0.21019818,0.0000045463894,0.00044050007,0.09335497,0.00014734015],"about_ca_topic_score_codex":0.6159591,"about_ca_topic_score_gemma":0.87547034,"teacher_disagreement_score":0.25951126,"about_ca_system_score_codex":0.0000889328,"about_ca_system_score_gemma":0.00005553258,"threshold_uncertainty_score":0.9962653},"labels":[],"label_agreement":null},{"id":"W2037905382","doi":"10.1007/s10994-006-0219-y","title":"Online calibrated forecasts: Memory efficiency versus universality for learning in games","year":2006,"lang":"en","type":"article","venue":"Machine Learning","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Army Research Office; Air Force Office of Scientific Research; Fonds Québécois de la Recherche sur la Nature et les Technologies; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Fictitious play; Regret; Repeated game; Computer science; Nash equilibrium; Best response; Universality (dynamical systems); Artificial intelligence; Mathematics; Mathematical optimization; Game theory; Mathematical economics; Machine learning","score_opus":0.08089650883186325,"score_gpt":0.4011498157716262,"score_spread":0.32025330693976295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037905382","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78996855,0.0005772659,0.20370324,0.0010154739,0.0004276768,0.0006337576,0.000046911915,0.00032871554,0.0032983818],"genre_scores_gemma":[0.98213756,0.000010683641,0.0043632654,0.00002465705,0.00021124752,0.000017108996,0.00014233589,0.000044879016,0.013048248],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959083,0.00066041946,0.00070927927,0.0007876571,0.0012043327,0.0007299988],"domain_scores_gemma":[0.9951629,0.0037872333,0.0002885261,0.00034423295,0.00030342993,0.000113660746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030030229,0.0002493677,0.0004391629,0.00069686456,0.00041187156,0.00020204825,0.00071068516,0.00012550276,0.00035923268],"category_scores_gemma":[0.008214424,0.0002109508,0.00014970184,0.0018979859,0.00017320727,0.00048234596,0.00026184795,0.00090102677,0.00005347026],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00059980416,0.00021459725,0.030579207,0.000012750575,0.000010726725,0.00005188862,0.0003369952,0.85403824,0.00036411482,0.000191316,0.00033247494,0.113267906],"study_design_scores_gemma":[0.0036869752,0.0004011752,0.013848882,0.000021148797,0.000006797649,0.0000044405865,0.0015913886,0.9368796,0.00034504713,0.0020766265,0.040835053,0.0003028924],"about_ca_topic_score_codex":0.0012942208,"about_ca_topic_score_gemma":0.0019389308,"teacher_disagreement_score":0.19933997,"about_ca_system_score_codex":0.00021876284,"about_ca_system_score_gemma":0.00013853931,"threshold_uncertainty_score":0.98340267},"labels":[],"label_agreement":null},{"id":"W2038227658","doi":"10.1007/s10994-005-0913-1","title":"Corpus-based Learning of Analogies and Semantic Relations","year":2005,"lang":"en","type":"article","venue":"Machine Learning","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":178,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Analogy; Noun; Artificial intelligence; Natural language processing; Part of speech; Computer science; Class (philosophy); Meaning (existential); Word (group theory); Set (abstract data type); Semantics (computer science); Mathematics; Linguistics; Psychology","score_opus":0.008477493126515724,"score_gpt":0.25691361684639447,"score_spread":0.24843612371987875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038227658","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061053816,0.007019996,0.9287503,0.0015315489,0.000023831926,0.00007143614,3.6949282e-7,0.000869533,0.00067922095],"genre_scores_gemma":[0.69759667,0.000014184792,0.30200347,0.00005650159,0.00001380569,0.0000019007418,0.0000028419454,0.0000065422832,0.00030412048],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99924105,0.00009141251,0.00016771466,0.00020346981,0.00015011377,0.00014625088],"domain_scores_gemma":[0.9994605,0.00015546463,0.00014714815,0.00015243767,0.000052157164,0.000032267413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003034842,0.00009643193,0.0001361934,0.00016454504,0.00017780937,0.00007133123,0.0002632401,0.000048369955,0.000014095255],"category_scores_gemma":[0.00036975165,0.00008625239,0.000030986208,0.00029612202,0.000046521935,0.00027862997,0.00015336953,0.0003850977,0.000005212095],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014286364,0.00005809075,0.27067694,0.00012295744,0.000026050733,0.000020199248,0.0017840153,0.05008628,0.016451221,0.040083252,0.00011894866,0.6205578],"study_design_scores_gemma":[0.0002136888,0.00011266482,0.0045261728,0.0000788052,0.000009263461,0.000014851882,0.000011846328,0.98000365,0.0071820556,0.0021372545,0.0055420334,0.00016773467],"about_ca_topic_score_codex":0.000064446736,"about_ca_topic_score_gemma":0.000016669814,"teacher_disagreement_score":0.92991734,"about_ca_system_score_codex":0.000018750843,"about_ca_system_score_gemma":0.000023891746,"threshold_uncertainty_score":0.35172704},"labels":[],"label_agreement":null},{"id":"W2040852548","doi":"10.1007/s10994-007-5043-5","title":"A notion of task relatedness yielding provable multiple-task learning guarantees","year":2008,"lang":"en","type":"article","venue":"Machine Learning","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":103,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Generalization; Multi-task learning; Computer science; Task (project management); Artificial intelligence; Similarity (geometry); Machine learning; Point (geometry); Domain (mathematical analysis); Variety (cybernetics); Theoretical computer science; Mathematics","score_opus":0.012613177219527812,"score_gpt":0.22340017247581537,"score_spread":0.21078699525628755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040852548","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5518563,0.0007758206,0.4411004,0.0004991053,0.00047864893,0.00025902092,0.0000017193628,0.0010774493,0.0039515826],"genre_scores_gemma":[0.977063,0.000081859675,0.018612266,0.000055113494,0.00013182056,0.000015237268,0.000023735185,0.000045725847,0.0039712694],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970704,0.0004870683,0.000581018,0.00069904263,0.0005698424,0.0005926701],"domain_scores_gemma":[0.9983854,0.0004102279,0.0004785217,0.0004520465,0.00015180193,0.0001219931],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00093424175,0.00034040486,0.00048270708,0.00035600236,0.00091958145,0.0000977481,0.0007863823,0.00016181634,0.000040007522],"category_scores_gemma":[0.001192423,0.00032046277,0.0001877897,0.000895884,0.00009808132,0.0005885282,0.00038637107,0.0015273286,0.00007131031],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007993837,0.00029037954,0.38225955,0.00022410456,0.00013550944,0.00025387172,0.013751765,0.46491513,0.030894877,0.002020499,0.00014942636,0.105024956],"study_design_scores_gemma":[0.0009857407,0.0003508611,0.009582072,0.0001634652,0.000015195236,0.00021565428,0.00009759334,0.9761927,0.0014427785,0.00009566322,0.010429401,0.00042884008],"about_ca_topic_score_codex":0.00085000205,"about_ca_topic_score_gemma":0.000013374956,"teacher_disagreement_score":0.5112776,"about_ca_system_score_codex":0.000050406077,"about_ca_system_score_gemma":0.000076794066,"threshold_uncertainty_score":0.9999247},"labels":[],"label_agreement":null},{"id":"W2065015368","doi":"10.1007/s10994-010-5179-6","title":"Polynomial regression under arbitrary product distributions","year":2010,"lang":"en","type":"article","venue":"Machine Learning","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Carnegie Mellon University; Fonds Québécois de la Recherche sur la Nature et les Technologies; National Science Foundation","keywords":"Mathematics; Product (mathematics); Polynomial; Degree (music); Discrete mathematics; Noise (video); Gaussian; Simple (philosophy); Distribution (mathematics); Combinatorics; Algorithm; Applied mathematics; Mathematical analysis; Computer science; Artificial intelligence","score_opus":0.0072890674834150656,"score_gpt":0.24878458362669115,"score_spread":0.24149551614327608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065015368","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44207108,0.0005948577,0.5106109,0.022477934,0.003998741,0.0003396248,0.000013112819,0.0025380794,0.017355675],"genre_scores_gemma":[0.960389,0.0000063292646,0.03523689,0.0002029106,0.00067393464,0.000009796407,0.00005440487,0.000022040358,0.003404668],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983602,0.00017239603,0.00022342923,0.00054674747,0.00028628472,0.00041090895],"domain_scores_gemma":[0.99897933,0.000101660225,0.00012969747,0.00058059406,0.000048260106,0.00016044076],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005017774,0.00021785172,0.00018818068,0.00012166743,0.00066493824,0.00024181981,0.0007227446,0.00007958899,0.00014475903],"category_scores_gemma":[0.000298946,0.00017505587,0.000099794925,0.00040581136,0.000063531275,0.0003388436,0.00035523006,0.0017471641,0.00013147823],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046365025,0.0005256082,0.11368561,0.00006384259,0.000094801566,0.00014048778,0.001395297,0.005352559,0.0818256,0.04997005,0.016329098,0.7305707],"study_design_scores_gemma":[0.00088690105,0.00016588956,0.04955398,0.000046666115,0.000016907485,0.0002562029,0.000020318597,0.5471185,0.0048376215,0.0013445355,0.39498758,0.0007649258],"about_ca_topic_score_codex":0.0002018588,"about_ca_topic_score_gemma":0.000028361063,"teacher_disagreement_score":0.72980577,"about_ca_system_score_codex":0.000019064246,"about_ca_system_score_gemma":0.00007214204,"threshold_uncertainty_score":0.75906557},"labels":[],"label_agreement":null},{"id":"W2069150044","doi":"10.1007/s10994-013-5362-7","title":"Modelling relational statistics with Bayes Nets","year":2013,"lang":"en","type":"article","venue":"Machine Learning","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Semantics (computer science); Bayes' theorem; Class (philosophy); Benchmark (surveying); Approximate Bayesian computation; Function (biology); Artificial intelligence; Theoretical computer science; Machine learning; Bayesian probability; Data mining; Inference; Programming language","score_opus":0.02059995532552589,"score_gpt":0.21840187201107317,"score_spread":0.19780191668554728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069150044","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0071508805,0.00008240418,0.98982584,0.0005995063,0.000042062613,0.000057979687,0.0000013221858,0.00019044397,0.002049565],"genre_scores_gemma":[0.57543266,0.000005190223,0.42373037,0.00012070504,0.000019747104,0.0000062801414,0.000009391008,0.0000078376315,0.00066784356],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991066,0.000058717458,0.00014212483,0.00024995007,0.0002282596,0.00021437764],"domain_scores_gemma":[0.99947006,0.000105016625,0.00006689646,0.00017413948,0.00010412865,0.0000797701],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013383313,0.00011182974,0.000097922675,0.000053799795,0.00019624463,0.00018991726,0.0002476859,0.000036503774,0.000105397274],"category_scores_gemma":[0.000023261522,0.00009063886,0.000015298341,0.00014412777,0.000022519338,0.0003793561,0.000077241006,0.0003085666,0.00017277487],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014708432,0.000009300993,0.003125506,0.0000040327036,0.0000067639467,0.0000037343502,0.00024979337,0.88967055,0.000025333647,0.08925141,0.00019372952,0.017458396],"study_design_scores_gemma":[0.000110615285,0.00006418794,0.000444516,0.000017872962,0.000002530338,0.0000118483695,0.0000057197803,0.98563546,0.000011637213,0.012461853,0.0010982432,0.00013550188],"about_ca_topic_score_codex":0.0003226472,"about_ca_topic_score_gemma":0.000006012023,"teacher_disagreement_score":0.56828177,"about_ca_system_score_codex":0.000014514174,"about_ca_system_score_gemma":0.000039375107,"threshold_uncertainty_score":0.36961454},"labels":[],"label_agreement":null},{"id":"W2073171642","doi":"10.1007/s10994-012-5289-4","title":"Learning graphical models for relational data via lattice search","year":2012,"lang":"en","type":"article","venue":"Machine Learning","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Statistical relational learning; Graphical model; Relational database; Computer science; Machine learning; Artificial intelligence; Relational calculus; Bayesian network; Relational model; Naive Bayes classifier; Theoretical computer science; Data mining; Support vector machine","score_opus":0.10801632996442037,"score_gpt":0.32518487109788347,"score_spread":0.2171685411334631,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073171642","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00800156,0.0004079077,0.9889213,0.00096424494,0.0001494467,0.00010450765,0.0000038511603,0.00027899345,0.0011681943],"genre_scores_gemma":[0.83715683,0.000013733435,0.16186367,0.00013666828,0.00018932208,0.000009236772,0.00010716923,0.00001852752,0.0005048654],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981881,0.00024400455,0.00022985257,0.00044622176,0.00036175942,0.0005300961],"domain_scores_gemma":[0.9987006,0.00044109966,0.00007231951,0.00051011564,0.000094390765,0.00018145083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018650361,0.00015200261,0.00015937326,0.0001136635,0.0004956863,0.0001298103,0.00093809195,0.000100065336,0.000021317972],"category_scores_gemma":[0.00023104211,0.00014595129,0.000054764885,0.0002964301,0.00003687216,0.0013976527,0.0006749034,0.00081504154,0.00004669587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030523588,0.0001283442,0.037678882,0.00005151398,0.000057179517,0.0000029934313,0.0022288272,0.3903852,0.00043695484,0.44555593,0.00022058777,0.12322307],"study_design_scores_gemma":[0.00021243632,0.000068637186,0.0009216222,0.000014761021,0.000010045713,0.000018789811,0.0000142783865,0.98727673,0.000018897337,0.0071007386,0.0041561117,0.00018694375],"about_ca_topic_score_codex":0.000062097526,"about_ca_topic_score_gemma":0.0000032380192,"teacher_disagreement_score":0.82915527,"about_ca_system_score_codex":0.000021102242,"about_ca_system_score_gemma":0.000045523964,"threshold_uncertainty_score":0.59517205},"labels":[],"label_agreement":null},{"id":"W2076167926","doi":"10.1007/s10994-008-5088-0","title":"Inductive transfer with context-sensitive neural networks","year":2008,"lang":"en","type":"article","venue":"Machine Learning","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Acadia University","funders":"","keywords":"Computer science; Inductive transfer; Machine learning; Task (project management); Multi-task learning; Artificial intelligence; Transfer of learning; Context (archaeology); Artificial neural network; Encoding (memory); Reduction (mathematics); Robot learning","score_opus":0.017420568659186616,"score_gpt":0.2137613535598668,"score_spread":0.1963407849006802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076167926","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14230521,0.000106042695,0.85315746,0.00053613447,0.000118284624,0.00011975942,3.5031775e-7,0.00031245637,0.0033443132],"genre_scores_gemma":[0.9934808,0.000011169864,0.0045177764,0.0009409776,0.00008826278,0.0000075411417,0.000007182613,0.0000234234,0.0009228415],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984986,0.00028032408,0.00017942759,0.00040635394,0.0002775768,0.00035772377],"domain_scores_gemma":[0.9993672,0.00015453735,0.000059084105,0.00019880515,0.00009542579,0.00012494635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020406969,0.00019942183,0.00021842596,0.000105871826,0.0005187348,0.000086993765,0.0002780282,0.00006238967,0.00003289368],"category_scores_gemma":[0.000045052508,0.00016596082,0.00006346264,0.00042969422,0.00011265182,0.000457904,0.000066276436,0.000754912,0.000026250069],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026659336,0.000121030425,0.060451485,0.000008976011,0.00015542662,0.0010909607,0.034599967,0.55458224,0.0005204579,0.02118206,0.00012830166,0.3268925],"study_design_scores_gemma":[0.0009070605,0.0002716848,0.017470418,0.000013749674,0.000006622525,0.00029067326,0.00036037568,0.9756056,0.00012435147,0.000019064648,0.00465089,0.00027951744],"about_ca_topic_score_codex":0.00012882102,"about_ca_topic_score_gemma":0.000047240064,"teacher_disagreement_score":0.8511756,"about_ca_system_score_codex":0.000031003165,"about_ca_system_score_gemma":0.00003263133,"threshold_uncertainty_score":0.6767686},"labels":[],"label_agreement":null},{"id":"W2082021920","doi":"10.1023/b:mach.0000033118.09057.80","title":"Subquadratic Approximation Algorithms for Clustering Problems in High Dimensional Spaces","year":2004,"lang":"en","type":"article","venue":"Machine Learning","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Cluster analysis; Dimension (graph theory); Clustering high-dimensional data; CURE data clustering algorithm; Mathematics; Quadratic equation; Correlation clustering; Computer science; Constrained clustering; Approximation algorithm; Data stream clustering; Algorithm; Data mining; Pattern recognition (psychology); Artificial intelligence; Combinatorics","score_opus":0.018086759246439765,"score_gpt":0.24490751639547292,"score_spread":0.22682075714903316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082021920","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020246634,0.00007095338,0.9773334,0.0014311636,0.00021205083,0.0003871707,0.0000021605538,0.00016593031,0.00015050125],"genre_scores_gemma":[0.65783876,0.000005513626,0.341316,0.00012704631,0.00008512108,0.000078084224,0.00011216604,0.000017018348,0.00042024365],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989007,0.000039589253,0.00021738844,0.00035110046,0.0002131894,0.00027800986],"domain_scores_gemma":[0.9995952,0.000049024027,0.000096784075,0.00019575006,0.000023998065,0.000039223705],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004997632,0.00013467009,0.00014884784,0.00017931635,0.00015229399,0.0002756951,0.00038025598,0.00003256934,0.00000616912],"category_scores_gemma":[0.000052925625,0.00012473976,0.000035552406,0.00031429747,0.000015190137,0.00081528636,0.00028328708,0.00015516671,0.000016944487],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000065297877,0.000114048584,0.0025746792,0.00015371137,0.000018232286,0.000012884609,0.0009861514,0.86274827,0.00035883873,0.021109942,0.000030958217,0.11188574],"study_design_scores_gemma":[0.0010682804,0.000102492675,0.0015144463,0.000060564427,0.0000037236803,0.0000039527154,0.000016655324,0.98909485,0.00009220606,0.00701273,0.0008572849,0.00017281565],"about_ca_topic_score_codex":0.00026692866,"about_ca_topic_score_gemma":0.00012266623,"teacher_disagreement_score":0.63759214,"about_ca_system_score_codex":0.000055313474,"about_ca_system_score_gemma":0.00001718881,"threshold_uncertainty_score":0.50867397},"labels":[],"label_agreement":null},{"id":"W2083002797","doi":"10.1007/s10994-013-5361-8","title":"Alignment based kernel learning with a continuous set of base kernels","year":2013,"lang":"en","type":"article","venue":"Machine Learning","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates; Alberta Innovates - Technology Futures","keywords":"Kernel (algebra); Tree kernel; Base (topology); A priori and a posteriori; Parameterized complexity; Computer science; Kernel embedding of distributions; Kernel method; Multiple kernel learning; Set (abstract data type); String kernel; Artificial intelligence; Variable kernel density estimation; Polynomial kernel; Machine learning; Computation; Discretization; Algorithm; Mathematics; Support vector machine; Discrete mathematics","score_opus":0.011064948118837077,"score_gpt":0.21890172120634782,"score_spread":0.20783677308751075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083002797","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6299575,0.00004852773,0.36457664,0.0006974291,0.000067305584,0.0002593293,0.0000016376182,0.00030246328,0.004089181],"genre_scores_gemma":[0.99060494,0.000003219856,0.007390132,0.00025515907,0.00004439718,0.000030282743,0.000021584468,0.000017057268,0.0016332475],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873024,0.00019806369,0.00023012809,0.00030061897,0.00029288963,0.00024804974],"domain_scores_gemma":[0.99925935,0.00011297759,0.00022276535,0.00020490064,0.00010854028,0.00009144869],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002805722,0.00015331946,0.00020355273,0.00013020364,0.0001693618,0.00013516143,0.00024425995,0.00004263516,0.0006723695],"category_scores_gemma":[0.00005728053,0.0001267262,0.00005994725,0.0002072309,0.000032714153,0.00035028675,0.00007832248,0.0003107214,0.00019508967],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011148191,0.00051014585,0.32359198,0.000318605,0.00026581925,0.00016249025,0.0067165927,0.12657396,0.0396538,0.002872428,0.0017320616,0.4974906],"study_design_scores_gemma":[0.0017108719,0.00080499955,0.011382108,0.00015963906,0.000023121724,0.000030634685,0.0002661453,0.9598665,0.014549429,0.0002746727,0.01052051,0.0004113375],"about_ca_topic_score_codex":0.0004347981,"about_ca_topic_score_gemma":0.0000112006555,"teacher_disagreement_score":0.83329254,"about_ca_system_score_codex":0.000025356974,"about_ca_system_score_gemma":0.000032910415,"threshold_uncertainty_score":0.7361975},"labels":[],"label_agreement":null},{"id":"W2086587356","doi":"10.1007/s10994-013-5364-5","title":"BoostingTree: parallel selection of weak learners in boosting, with application to ranking","year":2013,"lang":"en","type":"article","venue":"Machine Learning","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Magyarország Kormánya; Alberta Innovates; Nemzeti Kutatási és Technológiai Hivatal; Hungarian Scientific Research Fund","keywords":"Boosting (machine learning); Gradient boosting; Machine learning; Artificial intelligence; Ranking (information retrieval); Decision tree; Computer science; Mathematics; Feature selection; Pattern recognition (psychology); Random forest","score_opus":0.03175220600398684,"score_gpt":0.3621694942332327,"score_spread":0.3304172882292459,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086587356","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47570717,0.000056824905,0.51987964,0.0007598484,0.000026478085,0.00066846836,7.452016e-7,0.00008141148,0.0028194264],"genre_scores_gemma":[0.97724617,0.0000035791425,0.020248536,0.00003784252,0.000046954774,0.000096959884,0.0000052230184,0.000026243964,0.0022884782],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970195,0.0002859545,0.0005395414,0.0005356711,0.0012143161,0.0004049909],"domain_scores_gemma":[0.99810374,0.0008769504,0.00029629344,0.00027095753,0.00033872252,0.00011335123],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001953911,0.0001556107,0.0002964136,0.0006322474,0.00017951122,0.00012587172,0.00043479993,0.000060629278,0.0003649809],"category_scores_gemma":[0.0037771796,0.00011806615,0.000040559924,0.002018929,0.00006117595,0.00038898012,0.0001485913,0.0005214591,0.00027175696],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006188652,0.00002504332,0.36882448,0.000005854422,0.000005196535,0.0000011725945,0.00052877946,0.43513834,0.004137064,0.00004044869,0.000075520154,0.19115618],"study_design_scores_gemma":[0.0010498277,0.00034444244,0.17779292,0.000068378926,0.0000044042304,0.00001571268,0.0012440255,0.8088503,0.001067305,0.0015997038,0.007670211,0.00029277027],"about_ca_topic_score_codex":0.0017180096,"about_ca_topic_score_gemma":0.0008075886,"teacher_disagreement_score":0.501539,"about_ca_system_score_codex":0.00008541432,"about_ca_system_score_gemma":0.000047986236,"threshold_uncertainty_score":0.4814598},"labels":[],"label_agreement":null},{"id":"W2086959852","doi":"10.1007/s10994-009-5103-0","title":"NP-hardness of Euclidean sum-of-squares clustering","year":2009,"lang":"en","type":"article","venue":"Machine Learning","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":863,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Group for Research in Decision Analysis; HEC Montréal; Polytechnique Montréal","funders":"","keywords":"Cluster analysis; Mathematics; Euclidean distance; Explained sum of squares; Euclidean geometry; Combinatorics; Pattern recognition (psychology); Artificial intelligence; Computer science; Statistics","score_opus":0.012571535375825917,"score_gpt":0.2570000966085654,"score_spread":0.24442856123273946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086959852","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07549964,0.00044123194,0.9213738,0.0003280406,0.00023232054,0.00006994044,0.0000035688633,0.00013174093,0.0019197107],"genre_scores_gemma":[0.9626423,0.000015244719,0.037051618,0.000065432985,0.000041695333,7.022889e-7,0.000008362369,0.000005963895,0.00016869859],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990502,0.0000799035,0.00025477694,0.00021830465,0.00022620184,0.00017059552],"domain_scores_gemma":[0.9993237,0.000056120698,0.00017335388,0.0003496883,0.000048676724,0.000048454578],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028779235,0.00010293286,0.00020160596,0.00009956268,0.00009007094,0.000040281335,0.00059063284,0.000035103538,0.000024173449],"category_scores_gemma":[0.00006904569,0.000088329834,0.000056459518,0.00021828765,0.00001942016,0.00029623354,0.00031194466,0.00016959712,0.000004779636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000361148,0.00014760121,0.0223073,0.000098794226,0.000021441387,0.000029451849,0.0021731497,0.027893921,0.020911243,0.007085649,0.00046909836,0.9188262],"study_design_scores_gemma":[0.0004402649,0.00032407782,0.021916,0.00013106334,0.000006084716,0.000017406228,0.00003018395,0.9600604,0.0049012117,0.00077782205,0.011189399,0.00020608492],"about_ca_topic_score_codex":0.0001433479,"about_ca_topic_score_gemma":0.0000060459315,"teacher_disagreement_score":0.93216646,"about_ca_system_score_codex":0.000008426187,"about_ca_system_score_gemma":0.00001472367,"threshold_uncertainty_score":0.3601986},"labels":[],"label_agreement":null},{"id":"W2099367269","doi":"10.1023/b:mach.0000035516.74817.51","title":"Introduction: Lessons Learned from Data Mining Applications and Collaborative Problem Solving","year":2004,"lang":"en","type":"article","venue":"Machine Learning","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Ministrstvo za Izobraževanje, Znanost in Šport; Ministry of Education, Culture, Sports, Science and Technology","keywords":"Computer science; Data science; Data mining","score_opus":0.037539201725950364,"score_gpt":0.30025338922856964,"score_spread":0.26271418750261927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099367269","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023060231,0.00075656123,0.95604575,0.03923559,0.00006363491,0.00024738288,0.00011983337,0.00036387637,0.00086134963],"genre_scores_gemma":[0.047799215,0.00019149615,0.9499408,0.00014036917,0.0005897279,0.00009823155,0.00084153656,0.000022703829,0.0003759012],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99842334,0.00006180941,0.00022257288,0.00088583975,0.000175914,0.00023050178],"domain_scores_gemma":[0.9985419,0.00011806924,0.00014846587,0.0010192298,0.000075095726,0.00009725693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037013442,0.00015426576,0.00016673232,0.00007918526,0.00070874783,0.00045471409,0.00096996233,0.000048818496,0.000019514677],"category_scores_gemma":[0.000102973776,0.00015599553,0.000014582864,0.00067891466,0.00006860532,0.0008125189,0.0010231368,0.0002936498,0.000041980333],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034891718,0.000088474764,0.0006760365,0.000013118218,0.000053644348,0.0000043154155,0.0035807132,0.0037457168,0.0016338844,0.040025238,0.0013158985,0.94885945],"study_design_scores_gemma":[0.0008853387,0.00008307632,0.0013414364,0.000051491024,0.000040394672,0.000030557723,0.001040142,0.30015573,0.0003424087,0.0109295035,0.6845813,0.00051865814],"about_ca_topic_score_codex":0.00029452774,"about_ca_topic_score_gemma":0.000094333824,"teacher_disagreement_score":0.94834083,"about_ca_system_score_codex":0.000035529407,"about_ca_system_score_gemma":0.000098128905,"threshold_uncertainty_score":0.6361313},"labels":[],"label_agreement":null},{"id":"W2104094955","doi":"10.1007/s10994-009-5152-4","title":"A theory of learning from different domains","year":2009,"lang":"en","type":"article","venue":"Machine Learning","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":3486,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Advanced Research Projects Agency; Defense Advanced Research Projects Agency; University of Pennsylvania; National Science Foundation","keywords":"Classifier (UML); Computer science; Weighting; Discriminative model; Artificial intelligence; Bounding overwatch; Pattern recognition (psychology); Bayes error rate; Labeled data; Machine learning; Test data; Quadratic classifier; Divergence (linguistics); Algorithm; Bayes classifier; Support vector machine; Naive Bayes classifier","score_opus":0.015224496617028887,"score_gpt":0.23817871003438795,"score_spread":0.22295421341735908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104094955","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20145664,0.00047966582,0.7847553,0.0005121039,0.00013095407,0.00008889902,6.7542237e-7,0.00040151426,0.012174241],"genre_scores_gemma":[0.9865344,0.00003003881,0.01147111,0.0002925804,0.000070186135,0.0000028793015,0.000017984135,0.000015511347,0.0015652744],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99791914,0.0006108301,0.0003476078,0.00040526778,0.0003852202,0.00033194665],"domain_scores_gemma":[0.9987923,0.00044285128,0.00026920944,0.00032968642,0.00004644108,0.00011951906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005718979,0.00021270865,0.00031002334,0.00017324778,0.00027574372,0.00012611381,0.00060887507,0.00007317591,0.00021270697],"category_scores_gemma":[0.00035254637,0.00018716534,0.00013335171,0.00028868858,0.000041260166,0.00025560762,0.00015537688,0.00067994546,0.000052002702],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009806625,0.00021850198,0.047977526,0.000015933061,0.00008582185,0.000049069546,0.010714778,0.045578953,0.023640174,0.26629448,0.000058558162,0.6052681],"study_design_scores_gemma":[0.002464702,0.00097559486,0.19844611,0.00015253495,0.00004193813,0.00001947759,0.0009397705,0.71606314,0.002709239,0.037682947,0.039639715,0.0008648383],"about_ca_topic_score_codex":0.00003731561,"about_ca_topic_score_gemma":0.0000054736456,"teacher_disagreement_score":0.7850778,"about_ca_system_score_codex":0.000033306147,"about_ca_system_score_gemma":0.00002776958,"threshold_uncertainty_score":0.7632381},"labels":[],"label_agreement":null},{"id":"W2114563530","doi":"10.1023/a:1013916107446","title":"Bayesian Treed Models","year":2002,"lang":"en","type":"article","venue":"Machine Learning","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":184,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; University of Texas at Austin; University of Chicago; National Science Foundation","keywords":"Partition (number theory); Simple (philosophy); Computer science; Bayesian probability; Parametric statistics; Artificial neural network; Parametric model; Mathematics; Tree (set theory); Set (abstract data type); Algorithm; Artificial intelligence; Statistics","score_opus":0.11840723952739055,"score_gpt":0.3423309401831147,"score_spread":0.22392370065572417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114563530","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031928027,0.00009624543,0.8868608,0.00026750096,0.000044584227,0.000058867696,0.000002962528,0.00014996628,0.109326296],"genre_scores_gemma":[0.62267756,0.000010733239,0.37242204,0.00008846606,0.000050540624,0.000005444999,0.0000012588628,0.000021271328,0.0047226716],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999162,0.0001563325,0.00017692512,0.00015835343,0.00014386965,0.00020251311],"domain_scores_gemma":[0.9990478,0.0006519508,0.000056372683,0.00014676673,0.00002278004,0.00007433942],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00024804496,0.00010604885,0.00017454887,0.000040889037,0.00010974054,0.000030616808,0.00010071446,0.000044073397,0.0030527506],"category_scores_gemma":[0.0013135186,0.00008810879,0.000043538537,0.000102127364,0.000025165467,0.000048184138,0.000038201306,0.00026332826,0.00006754662],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007556207,0.0000944123,0.0019838153,0.000053755848,0.000022921939,0.000021150154,0.0010775907,0.00071533595,0.00019241084,0.74990106,0.001531503,0.2443985],"study_design_scores_gemma":[0.00013848556,0.00004263429,0.00006342103,0.000012624744,0.000009234104,0.0000042787333,0.000015936495,0.648652,0.000021673859,0.34946442,0.0014873492,0.0000878927],"about_ca_topic_score_codex":0.000034088367,"about_ca_topic_score_gemma":0.0000066630314,"teacher_disagreement_score":0.6479367,"about_ca_system_score_codex":0.000012797599,"about_ca_system_score_gemma":0.00000230166,"threshold_uncertainty_score":0.9978586},"labels":[],"label_agreement":null},{"id":"W2115650093","doi":"10.1007/s10994-006-8199-5","title":"Cost curves: An improved method for visualizing classifier performance","year":2006,"lang":"en","type":"article","venue":"Machine Learning","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":324,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; National Research Council Canada","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Classifier (UML); Computer science; Artificial intelligence; Pattern recognition (psychology); Software; Learning curve; Visualization; Machine learning; Receiver operating characteristic; Range (aeronautics); Data mining; Engineering","score_opus":0.03939313177323189,"score_gpt":0.3477566611305509,"score_spread":0.30836352935731903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115650093","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000841417,0.00016460837,0.99557394,0.00062385155,0.000102734004,0.00046679217,0.00000952183,0.0009886813,0.0012284508],"genre_scores_gemma":[0.13130726,0.000051719868,0.86546576,0.0009059614,0.0001494958,0.00027230792,0.0002855865,0.000039413044,0.0015224809],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984053,0.00018556179,0.00032520102,0.00052262034,0.00019105722,0.00037028678],"domain_scores_gemma":[0.99883515,0.00016167232,0.0002255595,0.00059190014,0.000120968274,0.00006475226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011569539,0.00018242428,0.00020426074,0.00012907994,0.0003365926,0.00019305662,0.00081994873,0.00007379762,0.00001374196],"category_scores_gemma":[0.00013748716,0.00017578172,0.00005827227,0.000328283,0.000026943255,0.0010164574,0.00015964304,0.00027642047,0.000010942827],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044698052,0.0002639799,0.016202424,0.0005075472,0.000027771974,0.0000034240686,0.00045009397,0.0016540772,0.101935945,0.053878985,0.0073655443,0.8176655],"study_design_scores_gemma":[0.0002663679,0.00014530831,0.002960971,0.0000510549,0.0000057669386,0.000008255183,0.0000087513135,0.88941175,0.0129841175,0.00037853452,0.09354976,0.00022936439],"about_ca_topic_score_codex":0.00013684198,"about_ca_topic_score_gemma":0.000024582992,"teacher_disagreement_score":0.88775766,"about_ca_system_score_codex":0.000066607914,"about_ca_system_score_gemma":0.000042532854,"threshold_uncertainty_score":0.716817},"labels":[],"label_agreement":null},{"id":"W2119296376","doi":"10.1007/s10994-006-6205-6","title":"Adaptive game AI with dynamic scripting","year":2006,"lang":"en","type":"article","venue":"Machine Learning","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":260,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; University of Alberta","keywords":"Computer science; Scripting language; CLARITY; Human–computer interaction; Computer game; Game design; Sequential game; Scalability; Artificial intelligence; Game design document; Adaptation (eye); Multimedia; Game theory; Game Developer; Programming language; Database","score_opus":0.010368082131558508,"score_gpt":0.24754596782144508,"score_spread":0.23717788568988657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119296376","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060481906,0.00021434945,0.93153447,0.0008903741,0.000114412134,0.00009133191,4.635639e-7,0.00044353164,0.006229147],"genre_scores_gemma":[0.96907437,0.0000016981406,0.02848195,0.00025063107,0.00006475137,0.0000073041447,0.0000029797682,0.000019563642,0.0020967766],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986787,0.00009801167,0.00020698756,0.00038735566,0.0002718607,0.00035708916],"domain_scores_gemma":[0.9993958,0.0000892896,0.000115411916,0.00027559305,0.00007649699,0.000047437403],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002392487,0.00016154756,0.00014922477,0.00011034481,0.00020885549,0.00021190847,0.0005059295,0.000041384967,0.000033261662],"category_scores_gemma":[0.000052614512,0.0001358463,0.00004191509,0.00038264066,0.00007000623,0.00044641702,0.00017804481,0.00041502272,0.00014198288],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000459942,0.0001152778,0.074227706,0.000017112156,0.000037905444,0.00021631068,0.0027855986,0.60673714,0.004028623,0.07598835,0.00024341655,0.23555657],"study_design_scores_gemma":[0.000065673754,0.00015300894,0.0027167695,0.000031074702,0.0000041692797,0.000028859027,0.00008351883,0.98800194,0.00096278643,0.0034857185,0.00425976,0.00020671343],"about_ca_topic_score_codex":0.00097381824,"about_ca_topic_score_gemma":0.00051278766,"teacher_disagreement_score":0.90859246,"about_ca_system_score_codex":0.000060337064,"about_ca_system_score_gemma":0.000034177556,"threshold_uncertainty_score":0.55396515},"labels":[],"label_agreement":null},{"id":"W2119785746","doi":"10.1007/s10994-009-5110-1","title":"Training parsers by inverse reinforcement learning","year":2009,"lang":"en","type":"article","venue":"Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Treebank; Parsing; Computer science; Generalization; Artificial intelligence; Set (abstract data type); Reinforcement learning; Function (biology); Machine learning; Training set; Inverse; Algorithm; Mathematics","score_opus":0.02311423201309188,"score_gpt":0.2528785846531024,"score_spread":0.22976435264001055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119785746","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0053719906,0.00014025996,0.95776445,0.0011481398,0.00026125895,0.00020554055,2.0077422e-7,0.0010942443,0.03401393],"genre_scores_gemma":[0.9683691,0.000065382985,0.015494074,0.0015293333,0.00008932386,0.000008185975,0.000053488497,0.000032920125,0.014358181],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969763,0.00026363137,0.00054705027,0.00062130915,0.0007161278,0.0008755513],"domain_scores_gemma":[0.99866337,0.00014646107,0.00036231475,0.00050234626,0.00006959905,0.0002559408],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008953355,0.0003839408,0.00036077978,0.00023496346,0.00066871895,0.00039596218,0.0010499478,0.0001285741,0.00014964138],"category_scores_gemma":[0.0004570929,0.00039516378,0.00014618738,0.00061835296,0.000051472995,0.0007917808,0.0002581384,0.0012406264,0.0002110276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008422765,0.000012736875,0.0020073855,0.0000075747525,0.000023590985,0.0000211593,0.0028737956,0.9460119,0.0014554831,0.002259953,0.0010955204,0.0442225],"study_design_scores_gemma":[0.0005922793,0.00054548593,0.0002844098,0.000038545113,0.000011440844,0.000017910532,0.00020421341,0.873429,0.00027419408,0.000092262635,0.12408241,0.0004278263],"about_ca_topic_score_codex":0.000047158337,"about_ca_topic_score_gemma":0.0000023433117,"teacher_disagreement_score":0.96299714,"about_ca_system_score_codex":0.0001395637,"about_ca_system_score_gemma":0.00006895386,"threshold_uncertainty_score":0.99985003},"labels":[],"label_agreement":null},{"id":"W2120199131","doi":"10.1023/a:1024068626366","title":"Inference for the Generalization Error","year":2003,"lang":"en","type":"article","venue":"Machine Learning","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":959,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université du Québec à Montréal; Health Canada; Center for Interuniversity Research and Analysis on Organizations","funders":"","keywords":"Estimator; Variance (accounting); Generalization; Statistical hypothesis testing; Null hypothesis; Statistics; Set (abstract data type); Generalization error; Mathematics; Computer science; Randomness; Econometrics; Artificial intelligence; Algorithm; Machine learning; Artificial neural network","score_opus":0.026905038304977553,"score_gpt":0.2926671986209821,"score_spread":0.2657621603160046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120199131","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019886892,0.0001858508,0.99502754,0.0018318043,0.00008257948,0.00012644281,3.134595e-7,0.00007452285,0.0006822816],"genre_scores_gemma":[0.97743195,0.000018930941,0.02077898,0.00048401728,0.000046450794,0.000057038786,0.0000035158375,0.0000051621764,0.001173967],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995982,0.00003918491,0.00007046891,0.00012584895,0.00005743258,0.00010886621],"domain_scores_gemma":[0.99957556,0.00017128237,0.00003939262,0.00016813645,0.000026020707,0.000019622019],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015304062,0.00004809528,0.000039279246,0.000012723939,0.00033535494,0.00008745756,0.00024282151,0.000013849081,0.000013209073],"category_scores_gemma":[0.00008193417,0.000031832627,0.000024697089,0.00017529885,0.000009492688,0.00008032174,0.000033438202,0.000076629,0.00000816784],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.1634554e-7,0.000011014491,0.0039445576,0.0000031681043,0.000004952204,2.1190557e-7,0.00015006222,0.19769171,0.00052998966,0.7503098,0.0007812814,0.046572533],"study_design_scores_gemma":[0.000064442065,0.000012771203,0.00049541914,0.0000014687963,0.000001955688,0.0000014951607,0.0000028316101,0.7737195,0.00017176506,0.0026697104,0.222815,0.00004364017],"about_ca_topic_score_codex":0.0000129724,"about_ca_topic_score_gemma":0.000011956797,"teacher_disagreement_score":0.97544324,"about_ca_system_score_codex":0.000004977682,"about_ca_system_score_gemma":0.000009825683,"threshold_uncertainty_score":0.2579313},"labels":[],"label_agreement":null},{"id":"W2129809168","doi":"10.1023/a:1013955821559","title":"Kernel Matching Pursuit","year":2002,"lang":"en","type":"article","venue":"Machine Learning","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":322,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Radial basis function; Basis (linear algebra); Basis function; Boosting (machine learning); Algorithm; Matching pursuit; Artificial intelligence; Computer science; Matching (statistics); Mathematics; Function (biology); Kernel (algebra); Pattern recognition (psychology); Artificial neural network; Statistics","score_opus":0.01448241195974086,"score_gpt":0.20520698678331692,"score_spread":0.19072457482357605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129809168","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.699387,0.0050320453,0.07119611,0.00037399665,0.0005436307,0.00018824155,0.0000026059645,0.0094271535,0.21384919],"genre_scores_gemma":[0.995937,0.000107115695,0.00233063,0.00008241007,0.00010709416,0.000003832472,0.0000036639303,0.000048271613,0.0013800184],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99940187,0.0000246585,0.000115402654,0.000120466226,0.00012236032,0.0002152575],"domain_scores_gemma":[0.99974823,0.000030020645,0.000019445706,0.00014727323,0.000011133881,0.00004391103],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007064576,0.00012785953,0.00012186535,0.0000703858,0.00009378001,0.00006361916,0.00013798452,0.000049223498,0.0004438719],"category_scores_gemma":[0.000017677592,0.00012985824,0.000046430665,0.00009762742,0.000012034777,0.000077351804,0.000043364318,0.00033676947,0.00018804445],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000073200595,0.000060752904,0.011457256,0.00006741398,0.00014764075,0.00020504792,0.0029868376,0.561471,0.08562649,0.0016757747,0.02689539,0.30939907],"study_design_scores_gemma":[0.00015581121,0.000027324788,0.00075327634,0.00005322379,0.000011190036,0.000038991886,0.000029178573,0.8969455,0.0050707813,0.00081271044,0.095815755,0.00028630754],"about_ca_topic_score_codex":0.00004182134,"about_ca_topic_score_gemma":0.0000060936013,"teacher_disagreement_score":0.33547446,"about_ca_system_score_codex":0.000022101034,"about_ca_system_score_gemma":6.797643e-7,"threshold_uncertainty_score":0.5295465},"labels":[],"label_agreement":null},{"id":"W2135194391","doi":"10.1023/a:1020281327116","title":"An Introduction to MCMC for Machine Learning","year":2003,"lang":"en","type":"article","venue":"Machine Learning","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2418,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Markov chain Monte Carlo; Monte Carlo method; Probabilistic logic; Artificial intelligence; Machine learning; Bayesian probability; Mathematics; Statistics","score_opus":0.01302649663491802,"score_gpt":0.28260567903664,"score_spread":0.269579182401722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135194391","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039614104,0.00019888839,0.99081945,0.0028618847,0.0004851263,0.00026228666,0.0000012109247,0.0003611529,0.0010486089],"genre_scores_gemma":[0.2371298,0.0000062712675,0.7592789,0.00046249942,0.00044388717,0.000034149285,0.000016198726,0.000034794015,0.0025935178],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978321,0.0006021866,0.00024277478,0.00068865577,0.00019737592,0.00043689596],"domain_scores_gemma":[0.99903995,0.00011527274,0.000102081176,0.00045151688,0.00008654518,0.00020462772],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017823628,0.00021483876,0.0002451608,0.0001878252,0.0004685462,0.0002113337,0.00044762195,0.00007874475,0.000057352514],"category_scores_gemma":[0.0007210961,0.00020101549,0.00008723621,0.00042302054,0.000014513309,0.0003948959,0.00007923493,0.0004847009,0.000022902897],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042402167,0.00011033206,0.0046632537,0.000040608218,0.00003135214,0.00000774934,0.0022243226,0.030692954,0.019413956,0.29246175,0.00077391166,0.6495374],"study_design_scores_gemma":[0.00045211843,0.00058635464,0.00022344677,0.000007592253,0.0000114811,0.000040581115,0.000015560801,0.5805165,0.0031747778,0.0075212116,0.40709925,0.00035110864],"about_ca_topic_score_codex":0.000041682415,"about_ca_topic_score_gemma":0.000019997608,"teacher_disagreement_score":0.6491863,"about_ca_system_score_codex":0.000042663087,"about_ca_system_score_gemma":0.000030838517,"threshold_uncertainty_score":0.81971735},"labels":[],"label_agreement":null},{"id":"W2137027418","doi":"10.1007/s10994-012-5307-6","title":"Learning compact Markov logic networks with decision trees","year":2012,"lang":"en","type":"article","venue":"Machine Learning","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Computer science; Markov chain; Graphical model; Bayesian network; Horn clause; Decision tree; Inductive logic programming; Set (abstract data type); Probabilistic logic; Class (philosophy); Machine learning; Inference; Theoretical computer science; Logic programming","score_opus":0.017743112740989813,"score_gpt":0.25844724040643563,"score_spread":0.24070412766544583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137027418","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04961438,0.00085546274,0.944623,0.00029008745,0.00015971725,0.00006081942,1.4912531e-7,0.00043628435,0.003960105],"genre_scores_gemma":[0.9468732,0.000038647024,0.052100167,0.0001969194,0.00015471845,0.000002846662,0.000006641545,0.00002156163,0.00060531276],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99827325,0.00025339398,0.00021132137,0.00033829908,0.00031109297,0.00061262836],"domain_scores_gemma":[0.99900544,0.00028927636,0.00013348309,0.0003036338,0.00005232242,0.00021584358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007815713,0.00022985224,0.00023944136,0.00010577645,0.00041558733,0.00023727352,0.00052362634,0.000086180386,0.000062894585],"category_scores_gemma":[0.00010685469,0.00017081923,0.000061057806,0.00039664615,0.00003858388,0.0005303113,0.00017423752,0.0008546045,0.00006782187],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003421945,0.000052968837,0.2187593,0.0000051236425,0.00001881941,0.000011744075,0.00061441335,0.5593005,0.00007402664,0.004894469,0.00013585985,0.2160986],"study_design_scores_gemma":[0.00029218697,0.00027464028,0.026528861,0.000065823646,0.0000091408765,0.00006129926,0.000032317344,0.96918637,0.000021162336,0.00033774323,0.0029108408,0.00027964276],"about_ca_topic_score_codex":0.00008725728,"about_ca_topic_score_gemma":0.000020931804,"teacher_disagreement_score":0.8972588,"about_ca_system_score_codex":0.000035716876,"about_ca_system_score_gemma":0.000026770154,"threshold_uncertainty_score":0.6965806},"labels":[],"label_agreement":null},{"id":"W2143379662","doi":"10.1007/s10994-009-5154-2","title":"Particle swarm optimizer for variable weighting in clustering high-dimensional data","year":2009,"lang":"en","type":"article","venue":"Machine Learning","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":72,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Cluster analysis; k-medians clustering; Weighting; Particle swarm optimization; Correlation clustering; Variable (mathematics); Mathematical optimization; Algorithm; CURE data clustering algorithm; Mathematics; Computer science; Fuzzy clustering; Jaccard index; Data mining; Artificial intelligence","score_opus":0.027126925669503376,"score_gpt":0.2695101599614228,"score_spread":0.24238323429191944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143379662","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.118040256,0.00014591668,0.87857723,0.002227861,0.00020295058,0.00016846538,0.000005065508,0.0001847221,0.00044750006],"genre_scores_gemma":[0.6640264,0.000004147784,0.33498052,0.0005806595,0.00006143701,0.0000064737296,0.00006882834,0.000007362855,0.00026416444],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891573,0.000066876106,0.00020399704,0.00037960347,0.00014409106,0.0002896756],"domain_scores_gemma":[0.99937975,0.00013475667,0.000066032495,0.00033714136,0.000027790025,0.000054527718],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005941018,0.00009891893,0.00013201823,0.00005808723,0.0001800429,0.000114634895,0.00047045643,0.000042235308,0.000036856236],"category_scores_gemma":[0.00015262581,0.00009037043,0.00001950044,0.00020323072,0.0000062246486,0.00062118744,0.00033822298,0.00018514668,0.000021458432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000101118654,0.00020681872,0.0029888712,0.00003446729,0.000015186992,0.000027346558,0.0005738155,0.7732374,0.023357775,0.004551042,0.0011801642,0.19372599],"study_design_scores_gemma":[0.00073185214,0.00006628075,0.0005035342,0.00006031079,0.0000030757274,0.0000057736734,0.000007834375,0.9929172,0.0017340411,0.0012985894,0.0025454392,0.00012610952],"about_ca_topic_score_codex":0.00009349763,"about_ca_topic_score_gemma":0.000011816078,"teacher_disagreement_score":0.5459861,"about_ca_system_score_codex":0.000018003002,"about_ca_system_score_gemma":0.000020122341,"threshold_uncertainty_score":0.3685199},"labels":[],"label_agreement":null},{"id":"W2151161180","doi":"10.1007/s10994-010-5229-0","title":"Informing sequential clinical decision-making through reinforcement learning: an empirical study","year":2010,"lang":"en","type":"article","venue":"Machine Learning","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":204,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institute of Mental Health; National Institute on Drug Abuse; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Reinforcement learning; Computer science; Imputation (statistics); Artificial intelligence; Machine learning; Missing data; Context (archaeology); Set (abstract data type)","score_opus":0.3261500829909371,"score_gpt":0.5301317871582475,"score_spread":0.20398170416731037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151161180","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94945276,0.00013156552,0.036442526,0.0027056132,0.0017278077,0.0008067017,0.000006892569,0.00026007544,0.008466089],"genre_scores_gemma":[0.9850942,0.000020808042,0.009237816,0.0036401819,0.0011314596,0.00005509686,0.000049070295,0.00007169625,0.0006996936],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9914742,0.00084061216,0.005841505,0.0009142478,0.0002648264,0.00066460844],"domain_scores_gemma":[0.99398637,0.0023276769,0.0026150807,0.00070245645,0.00009229985,0.00027611392],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.029481597,0.00033749512,0.0011939276,0.00031951815,0.0008953791,0.00030151347,0.0005430632,0.00029906785,0.002164664],"category_scores_gemma":[0.018014334,0.00039755608,0.00024077213,0.00028334616,0.00009900813,0.0012023129,0.00029359976,0.002102671,0.0017256436],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059065056,0.00024008434,0.96224463,0.000036056234,0.00008201962,0.000008492538,0.007228307,0.02063522,0.0000023103378,0.0039068037,0.0007671051,0.0047899266],"study_design_scores_gemma":[0.0030421119,0.0016111395,0.15779017,0.00009783343,0.000032499964,0.000035848858,0.0051640035,0.3998917,0.0000015323459,0.005785256,0.4255085,0.0010394027],"about_ca_topic_score_codex":0.0007965756,"about_ca_topic_score_gemma":0.0006428837,"teacher_disagreement_score":0.80445445,"about_ca_system_score_codex":0.00020555752,"about_ca_system_score_gemma":0.000160717,"threshold_uncertainty_score":0.99984765},"labels":[],"label_agreement":null},{"id":"W2153039919","doi":"10.1007/s10994-012-5280-0","title":"Temporal-difference search in computer Go","year":2012,"lang":"en","type":"article","venue":"Machine Learning","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Monte Carlo tree search; Temporal difference learning; Computer science; Search algorithm; Monte Carlo method; Bootstrapping (finance); Tree (set theory); Artificial intelligence; Reinforcement learning; Markov decision process; Beam search; Markov chain Monte Carlo; Search problem; Machine learning; Algorithm; Markov process; Mathematics; Statistics; Bayesian probability","score_opus":0.044164561907309385,"score_gpt":0.309821783679691,"score_spread":0.2656572217723816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153039919","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36098897,0.00021928681,0.6365866,0.00053884985,0.00029733017,0.000085347616,2.5077696e-7,0.0001777458,0.0011055847],"genre_scores_gemma":[0.9600753,0.0000073199117,0.03881128,0.00019761172,0.0001755306,0.0000058463297,0.0000024484634,0.000011338019,0.0007133055],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99842966,0.00024534672,0.00024308042,0.0002762816,0.00026989548,0.00053576595],"domain_scores_gemma":[0.9992937,0.00018774909,0.000053232838,0.00031100368,0.000033642173,0.00012067407],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007587237,0.00013708972,0.00016014578,0.00016209402,0.000115019524,0.00012326131,0.00069156784,0.000057220695,0.000071179835],"category_scores_gemma":[0.00007378367,0.00012450635,0.00004128942,0.00043260006,0.00004708205,0.00043499022,0.0004668406,0.0004993384,0.0005071312],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026155362,0.000056968674,0.7552085,0.000006857801,0.0000030289427,0.000008824315,0.0035513598,0.0057315226,0.00032016844,0.004641677,0.00004427469,0.23042423],"study_design_scores_gemma":[0.00006787829,0.000063642634,0.09152698,0.000026544054,9.837954e-7,0.0000135203745,0.000036465717,0.9015283,0.0016696675,0.0005128399,0.0043401346,0.00021307568],"about_ca_topic_score_codex":0.00051287835,"about_ca_topic_score_gemma":0.0000757967,"teacher_disagreement_score":0.8957968,"about_ca_system_score_codex":0.00005078119,"about_ca_system_score_gemma":0.000022940223,"threshold_uncertainty_score":0.6518315},"labels":[],"label_agreement":null},{"id":"W2159863202","doi":"10.1007/s10994-005-0928-7","title":"Combining Statistical Language Models via the Latent Maximum Entropy Principle","year":2005,"lang":"en","type":"article","venue":"Machine Learning","topic":"Topic Modeling","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; Canada Research Chairs","keywords":"Computer science; Principle of maximum entropy; Perplexity; Language model; Artificial intelligence; Probabilistic latent semantic analysis; Probabilistic logic; Smoothing; Natural language processing; Inference; Statistical model; Entropy (arrow of time); Natural language","score_opus":0.015687245931904955,"score_gpt":0.26299922893494887,"score_spread":0.2473119830030439,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159863202","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056095265,0.00024533714,0.9397546,0.0020841106,0.00011251451,0.000105863735,0.0000011705264,0.00025649136,0.0013446409],"genre_scores_gemma":[0.8941785,0.0000052065493,0.10462624,0.0004627486,0.00011828413,0.000008327413,0.0000066170937,0.000014690418,0.00057938724],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985775,0.00016631062,0.00023814171,0.00033104024,0.00032135812,0.00036566006],"domain_scores_gemma":[0.9992224,0.00014814334,0.0000801576,0.0004399618,0.000024965468,0.00008438594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004868242,0.00014146659,0.00014550202,0.000047481823,0.00027719562,0.00016251706,0.0006633482,0.00003990721,0.00007536501],"category_scores_gemma":[0.00006241328,0.000103110186,0.00004560754,0.00011950195,0.000027209126,0.00026453388,0.00044079204,0.0004790771,0.00009269647],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005801075,0.000040077597,0.0024656977,0.000008754802,0.000018437284,0.000032187763,0.0046147476,0.6607096,0.00068180537,0.16754708,0.000038818336,0.16383697],"study_design_scores_gemma":[0.00027031347,0.000031661955,0.0003770668,0.000008222753,0.000005176218,0.00002390172,0.000024378633,0.9901963,0.00011179589,0.0038605055,0.0049619153,0.00012879903],"about_ca_topic_score_codex":0.00015709337,"about_ca_topic_score_gemma":0.000027287873,"teacher_disagreement_score":0.8380832,"about_ca_system_score_codex":0.00005357061,"about_ca_system_score_gemma":0.000022657325,"threshold_uncertainty_score":0.42047113},"labels":[],"label_agreement":null},{"id":"W2214733097","doi":"10.1023/b:mach.0000019803.57720.7b","title":"Classification Using Φ-Machines and Constructive Function Approximation","year":2004,"lang":"en","type":"article","venue":"Machine Learning","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Cleveland Clinic Foundation; Cleveland Clinic; National Science Foundation","keywords":"Clef; Computer science; Support vector machine; Artificial intelligence; Decision tree; Machine learning; Classifier (UML); Constructive; Artificial neural network; Linear classifier","score_opus":0.020357497995076457,"score_gpt":0.251239282618204,"score_spread":0.23088178462312753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2214733097","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24940486,0.00009799771,0.7491644,0.0005976845,0.00006333849,0.00009756439,3.9036217e-7,0.0001368902,0.00043684384],"genre_scores_gemma":[0.96255046,0.0000102829235,0.037248544,0.00008464052,0.00005889893,0.000008827626,0.0000081028165,0.000006177874,0.000024078061],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99940217,0.000038780585,0.00011890333,0.00023664082,0.000094292904,0.00010920208],"domain_scores_gemma":[0.99967074,0.000028698443,0.00009695968,0.00013030272,0.000034691246,0.000038617396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011069371,0.00008255944,0.000073607014,0.00005773988,0.00032349088,0.00011665731,0.00010387608,0.000032083713,0.0000025502914],"category_scores_gemma":[0.00001666458,0.000075559896,0.00001881455,0.0002481618,0.000034870034,0.00036331185,0.00006390832,0.00015172905,0.0000051870124],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009332332,0.000046371075,0.020327754,0.00002038936,0.000018855997,0.000001537375,0.0005889194,0.07754128,0.04678054,0.61163497,0.000010839203,0.24301924],"study_design_scores_gemma":[0.00025153763,0.00003330855,0.013496056,0.000011512483,0.0000073837728,0.000031091102,0.000024180094,0.9674306,0.0002318713,0.017888922,0.00049087906,0.00010266837],"about_ca_topic_score_codex":0.00006601623,"about_ca_topic_score_gemma":0.0000075091175,"teacher_disagreement_score":0.8898893,"about_ca_system_score_codex":0.00002938462,"about_ca_system_score_gemma":0.000014261601,"threshold_uncertainty_score":0.3081243},"labels":[],"label_agreement":null},{"id":"W2284548247","doi":"10.1007/s10994-021-06019-1","title":"Bayesian optimization with safety constraints: safe and automatic parameter tuning in robotics","year":2021,"lang":"en","type":"preprint","venue":"Machine Learning","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":80,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Eidgenössische Technische Hochschule Zürich; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Bayesian optimization; Overshoot (microwave communication); Computer science; Robotics; Process (computing); Context (archaeology); Gaussian process; Robot; Bayesian probability; Set (abstract data type); Artificial intelligence; Probabilistic logic; Optimization problem; Mathematical optimization; Machine learning; Algorithm; Gaussian; Mathematics","score_opus":0.008947761347103697,"score_gpt":0.22550247125578554,"score_spread":0.21655470990868184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2284548247","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020865947,0.00035876915,0.99459845,0.0010854708,0.00010551206,0.00021600994,0.0000020563175,0.00017914404,0.0013679869],"genre_scores_gemma":[0.52125263,0.00008228571,0.47844693,0.000099908866,0.000014632206,0.000009862333,0.000035347013,0.000018378241,0.00004003826],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99781114,0.0002573118,0.00047642793,0.0007939684,0.0002845722,0.00037660796],"domain_scores_gemma":[0.9987909,0.000202442,0.00033383627,0.00046479193,0.00008861218,0.00011942629],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004079912,0.00036478616,0.0005074999,0.00023416909,0.0001691854,0.0008843661,0.0005254286,0.00021193312,0.00008795017],"category_scores_gemma":[0.00022870644,0.00032792543,0.00004793345,0.0004171217,0.00011773479,0.00034531977,0.00096201786,0.0012490752,0.0000016031059],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000048052834,0.000029195175,0.017200947,0.00035387214,0.000030162531,0.0001321478,0.0012703902,0.9150462,0.0000036378844,0.0015023799,0.0000011676865,0.0644251],"study_design_scores_gemma":[0.0003745403,0.00006392915,0.0031140593,0.0011290001,0.00001954274,0.0001088283,0.00010552836,0.9940725,0.0000057740685,0.0005836401,0.000019722038,0.00040294608],"about_ca_topic_score_codex":0.00008779319,"about_ca_topic_score_gemma":0.00008107511,"teacher_disagreement_score":0.519166,"about_ca_system_score_codex":0.00007756336,"about_ca_system_score_gemma":0.00028064472,"threshold_uncertainty_score":0.99991727},"labels":[],"label_agreement":null},{"id":"W2501500329","doi":"10.1007/s10994-016-5585-5","title":"Improving probabilistic inference in graphical models with determinism and cycles","year":2016,"lang":"en","type":"article","venue":"Machine Learning","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Graphical model; Belief propagation; Factor graph; Message passing; Computer science; Approximate inference; Inference; Theoretical computer science; Leverage (statistics); Local consistency; Artificial intelligence; Machine learning; Algorithm; Mathematics; Mathematical optimization; Probabilistic logic; Constraint satisfaction","score_opus":0.016583001162358054,"score_gpt":0.23959821481261537,"score_spread":0.2230152136502573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2501500329","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2805975,0.00006168164,0.7185951,0.00040815535,0.000015146684,0.000057256675,3.808294e-7,0.00010906218,0.00015574484],"genre_scores_gemma":[0.97418565,0.000020329653,0.025656123,0.000060271534,0.000011552161,0.000014734157,3.4199104e-7,0.000009638503,0.000041370655],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99886745,0.00009864787,0.00017607755,0.0004204226,0.00015625522,0.00028114798],"domain_scores_gemma":[0.99932027,0.00026850984,0.00006577579,0.00022128918,0.000034042765,0.00009011781],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029187216,0.00014501368,0.00015738535,0.00011783784,0.00009442199,0.00011938086,0.00030413445,0.000056428536,0.0000024414323],"category_scores_gemma":[0.00016887853,0.00008974049,0.000016793969,0.00018492981,0.000083173145,0.00046242576,0.00019890415,0.00024201022,0.0000028184036],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029148889,0.000052673633,0.08187241,0.000054669195,0.0000080819245,0.00006647416,0.0011591353,0.01443205,0.0031979238,0.15176338,7.32503e-7,0.7473633],"study_design_scores_gemma":[0.0003688388,0.00015532193,0.004687975,0.00013047825,0.0000027007297,0.000021015832,0.0000061116602,0.957545,0.00006759081,0.036817197,0.0000088729275,0.0001889371],"about_ca_topic_score_codex":0.00014050308,"about_ca_topic_score_gemma":0.00013547397,"teacher_disagreement_score":0.9431129,"about_ca_system_score_codex":0.000016917968,"about_ca_system_score_gemma":0.00004714571,"threshold_uncertainty_score":0.3659511},"labels":[],"label_agreement":null},{"id":"W2581879608","doi":"10.1007/s10994-016-5619-z","title":"Efficient parameter learning of Bayesian network classifiers","year":2017,"lang":"en","type":"article","venue":"Machine Learning","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Air Force Office of Scientific Research; Australian Research Council; Asian Office of Aerospace Research and Development","keywords":"Discriminative model; Artificial intelligence; Machine learning; Computer science; Pattern recognition (psychology); Bayesian network; Generative model; Bayesian probability; Generative grammar; Mathematics","score_opus":0.023678123723986304,"score_gpt":0.2688267466209545,"score_spread":0.2451486228969682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2581879608","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058171056,0.0001642226,0.9338402,0.0005169275,0.00029675796,0.00006476542,3.1416786e-7,0.00017794878,0.0067677624],"genre_scores_gemma":[0.9632102,0.000010476427,0.03583412,0.00007132355,0.00009218294,0.0000046621144,0.0000018391132,0.000016434215,0.00075874326],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983598,0.00020048251,0.00029122588,0.0004147691,0.00029109253,0.00044265747],"domain_scores_gemma":[0.9985256,0.00016497032,0.00039639403,0.00072059064,0.00006969879,0.00012270757],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079517957,0.00018127714,0.0002714144,0.00006894515,0.0009422855,0.00034245546,0.0011724716,0.00009315616,0.000028513577],"category_scores_gemma":[0.00050045695,0.00016639676,0.00011218853,0.00012409643,0.00010926408,0.00013396524,0.00046955983,0.0006754032,0.000026785772],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012311693,0.000033899,0.061302178,0.000022700939,0.000029441639,0.000016510548,0.00064064155,0.8060865,0.00041534269,0.02168654,0.00008081683,0.109673135],"study_design_scores_gemma":[0.00020879894,0.00011491063,0.0056862333,0.00006878063,0.000008151313,0.0000071262025,0.000013857916,0.9908013,0.0001320059,0.0013198177,0.0014463766,0.00019268085],"about_ca_topic_score_codex":0.00014197825,"about_ca_topic_score_gemma":0.000007473984,"teacher_disagreement_score":0.9050392,"about_ca_system_score_codex":0.000021694545,"about_ca_system_score_gemma":0.00004372522,"threshold_uncertainty_score":0.7247394},"labels":[],"label_agreement":null},{"id":"W2585472988","doi":"10.1007/s10994-016-5617-1","title":"Memory-adaptive high utility sequential pattern mining over data streams","year":2017,"lang":"en","type":"article","venue":"Machine Learning","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Clickstream; Data stream mining; Data stream; Data mining; Tree (set theory); Web server; The Internet","score_opus":0.05879960194168286,"score_gpt":0.31258075664599344,"score_spread":0.25378115470431056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2585472988","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17181568,0.000068535905,0.8233526,0.0010740163,0.00042391568,0.00014775725,0.00024093932,0.00029119587,0.0025853855],"genre_scores_gemma":[0.9496348,0.0000050690533,0.049225114,0.00009558949,0.00015555818,0.000009547011,0.00026916974,0.00001556256,0.0005895962],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99836445,0.00008489569,0.0002065011,0.00075858907,0.00027686433,0.00030871708],"domain_scores_gemma":[0.9966361,0.00007907169,0.0002699666,0.0028763765,0.000036500358,0.00010197656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005686749,0.00017220703,0.00018741068,0.000044009463,0.0011207137,0.00080897566,0.0034980061,0.000053664233,0.00011613506],"category_scores_gemma":[0.00015905227,0.00016344167,0.00003695088,0.000075317796,0.00008578411,0.0012117344,0.0033052822,0.00032481522,0.00006062937],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024409449,0.000038764323,0.015387149,0.0000049856208,0.000024690602,0.000035097506,0.0002845095,0.00007648231,0.00004786681,0.00040960804,0.0006509818,0.9830374],"study_design_scores_gemma":[0.00035116944,0.000045919987,0.061783914,0.000022980214,0.000013905507,0.000016527281,0.000036643116,0.92782676,0.00010311121,0.00015382808,0.009432988,0.00021223293],"about_ca_topic_score_codex":0.004129658,"about_ca_topic_score_gemma":0.00027129008,"teacher_disagreement_score":0.9828252,"about_ca_system_score_codex":0.000020576581,"about_ca_system_score_gemma":0.00004405221,"threshold_uncertainty_score":0.8619737},"labels":[],"label_agreement":null},{"id":"W2604867865","doi":"10.1007/s10994-017-5683-z","title":"Efficient benchmarking of algorithm configurators via model-based surrogates","year":2017,"lang":"en","type":"article","venue":"Machine Learning","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Deutsche Forschungsgemeinschaft","keywords":"Benchmarking; Computer science; Surrogate model; Range (aeronautics); Algorithm; Set (abstract data type); Configurator; Hyperparameter; Mathematical optimization; Machine learning; Artificial intelligence; Mathematics; Engineering","score_opus":0.013987542445136907,"score_gpt":0.2622762930874399,"score_spread":0.24828875064230296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2604867865","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02380304,0.00007116527,0.97153425,0.0006062008,0.00019640845,0.00009690036,0.0000060910897,0.00018242488,0.0035034872],"genre_scores_gemma":[0.9123327,0.000003834147,0.08738801,0.000041290194,0.000048365182,0.000006747804,0.00003988406,0.0000151843615,0.00012398769],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984225,0.00015991664,0.0003113005,0.00045565542,0.0003610006,0.00028962785],"domain_scores_gemma":[0.9980095,0.00014080042,0.00057567225,0.0010625181,0.00011258385,0.00009894643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087905984,0.00018838508,0.0002460587,0.00015117561,0.00082046574,0.0002732738,0.0012242185,0.000072119255,0.000023437518],"category_scores_gemma":[0.00033586973,0.00017471696,0.000091750975,0.00012619195,0.00010274594,0.00016600726,0.00027170812,0.00037937853,0.000020234444],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006069941,0.00006474873,0.025225258,0.00003167851,0.000013517537,0.000004390442,0.00025589406,0.5704937,0.0019982238,0.0029589667,0.00001662835,0.39893094],"study_design_scores_gemma":[0.00037339426,0.00006995167,0.012488086,0.000038700382,0.000008352923,0.0000029297632,0.0000051068755,0.9844541,0.0012620593,0.00012980944,0.000982986,0.0001844997],"about_ca_topic_score_codex":0.0003406058,"about_ca_topic_score_gemma":0.000015986381,"teacher_disagreement_score":0.88852966,"about_ca_system_score_codex":0.000028768405,"about_ca_system_score_gemma":0.00006879822,"threshold_uncertainty_score":0.71247506},"labels":[],"label_agreement":null},{"id":"W2611665460","doi":"10.1007/s10994-009-5134-6","title":"Pointwise exact bootstrap distributions of ROC curves","year":2009,"lang":"en","type":"article","venue":"Machine Learning","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Pointwise; Mathematics; Receiver operating characteristic; Confidence interval; Statistics; Mathematical analysis","score_opus":0.0197606494335381,"score_gpt":0.28621812602858154,"score_spread":0.26645747659504343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2611665460","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025973942,0.00052164186,0.989415,0.004129078,0.000035559176,0.00010635482,0.000020039994,0.0005758374,0.002599092],"genre_scores_gemma":[0.97252506,0.00013174118,0.026692059,0.00027597413,0.000017124337,0.000005245288,0.00010288421,0.0000046822493,0.00024524273],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9990762,0.00008768715,0.00023571885,0.00023306442,0.00018951806,0.00017782516],"domain_scores_gemma":[0.9991902,0.00005476247,0.00016307874,0.00047523197,0.00006542274,0.000051270752],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028628373,0.00010036303,0.00014525674,0.00008301488,0.00010407344,0.00004223949,0.00062462036,0.000035085952,0.00003520184],"category_scores_gemma":[0.00023277928,0.00009574633,0.000053559816,0.00036296397,0.000030828258,0.0003678806,0.0000873879,0.00022277037,0.000015997975],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021449248,0.00061572145,0.036593016,0.00018885049,0.000044910495,0.000027598195,0.00069908553,0.0004898657,0.08691147,0.40582833,0.019121744,0.44945797],"study_design_scores_gemma":[0.0010330477,0.0010871928,0.49844006,0.0007516033,0.000039990628,0.00009963142,0.00003139974,0.1986175,0.115267836,0.02552366,0.1579346,0.0011734683],"about_ca_topic_score_codex":0.000019769115,"about_ca_topic_score_gemma":0.0000021771987,"teacher_disagreement_score":0.96992767,"about_ca_system_score_codex":0.000026153359,"about_ca_system_score_gemma":0.000026992313,"threshold_uncertainty_score":0.3904422},"labels":[],"label_agreement":null},{"id":"W2735649811","doi":"10.1007/s10994-017-5657-1","title":"Generalized exploration in policy search","year":2017,"lang":"en","type":"article","venue":"Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Seventh Framework Programme; Technische Universität Darmstadt","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Entropy (arrow of time); Policy learning; Machine learning; Mathematical optimization; Mathematics","score_opus":0.05004398310810728,"score_gpt":0.33199694268441793,"score_spread":0.28195295957631067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2735649811","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033805106,0.00003210797,0.9499956,0.0053218263,0.00015694907,0.00012128982,1.273012e-7,0.00016531452,0.010401704],"genre_scores_gemma":[0.97775114,0.000038540587,0.017607665,0.0001528087,0.00013360548,0.000008388068,0.000006124803,0.000014098485,0.004287634],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987234,0.00017347687,0.00020218542,0.0002707607,0.00030098407,0.00032923443],"domain_scores_gemma":[0.9990062,0.00004563515,0.00014152988,0.00070436357,0.000039257462,0.000063004445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064282265,0.000116331226,0.00014000414,0.0002491295,0.00055592484,0.0006979775,0.0011297861,0.00005046502,0.000022222079],"category_scores_gemma":[0.0005954194,0.00011517728,0.00003848538,0.00017802078,0.000037829366,0.0011267762,0.00058455067,0.00039733818,0.00011525934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038084327,0.0000073215037,0.04780951,0.0000067268065,0.0000039390825,0.000014678674,0.001040809,0.906871,0.00039191305,0.026926177,0.000021313414,0.016902769],"study_design_scores_gemma":[0.00050457456,0.00005081924,0.017376885,0.000016567856,8.7023307e-7,0.0000031611191,0.000013643594,0.9765167,0.00027144438,0.00034418964,0.004770864,0.00013023968],"about_ca_topic_score_codex":0.0013324973,"about_ca_topic_score_gemma":0.00005964848,"teacher_disagreement_score":0.943946,"about_ca_system_score_codex":0.00007797277,"about_ca_system_score_gemma":0.00006998652,"threshold_uncertainty_score":0.6730613},"labels":[],"label_agreement":null},{"id":"W2751686959","doi":"10.1007/s10994-018-5719-z","title":"Reservoir of diverse adaptive learners and stacking fast hoeffding drift detection methods for evolving data streams","year":2018,"lang":"en","type":"article","venue":"Machine Learning","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":71,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Trillium Foundation; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; University of Ottawa","keywords":"Concept drift; Data stream mining; Data stream; Change detection; Streaming data; False alarm; Intrusion detection system; Resource (disambiguation); Ranging","score_opus":0.06608287604619553,"score_gpt":0.3737000284153294,"score_spread":0.3076171523691339,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2751686959","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03170109,0.00013986482,0.9669339,0.00006580421,0.00012375631,0.00020617685,0.00002840604,0.00034052477,0.00046046305],"genre_scores_gemma":[0.5076516,0.000009904032,0.49219382,0.000009875712,0.00005298742,0.0000039915335,0.000025730122,0.00001303439,0.000039021576],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982004,0.00034727674,0.000271299,0.00067862985,0.00018533535,0.00031705102],"domain_scores_gemma":[0.99797946,0.00060537877,0.000299526,0.0008947076,0.00014836215,0.00007254805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020204661,0.0001857689,0.00025476894,0.00023768238,0.00039992845,0.00017712502,0.0012042028,0.00007742607,0.000009942703],"category_scores_gemma":[0.0015247278,0.00018462092,0.000037618047,0.00036606443,0.00013678467,0.0012483175,0.0018917472,0.0002922092,0.0000013467996],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034084074,0.000012988559,0.0077497847,0.000032692187,0.00004093384,0.0000017654286,0.0016582423,0.00019785283,0.0059076054,0.0005123583,0.0000907046,0.983761],"study_design_scores_gemma":[0.00028294028,0.0005974805,0.0012204235,0.00011088643,0.000024194504,0.0000069622015,0.00055507605,0.98147523,0.012396789,0.00051536993,0.0026102473,0.00020438778],"about_ca_topic_score_codex":0.000861444,"about_ca_topic_score_gemma":0.00026468557,"teacher_disagreement_score":0.9835566,"about_ca_system_score_codex":0.00003663198,"about_ca_system_score_gemma":0.000031671465,"threshold_uncertainty_score":0.7528623},"labels":[],"label_agreement":null},{"id":"W2897984390","doi":"10.1007/s10994-019-05833-y","title":"Combining Bayesian optimization and Lipschitz optimization","year":2019,"lang":"en","type":"preprint","venue":"Machine Learning","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Canadian Institute for Advanced Research","keywords":"Lipschitz continuity; Bayesian optimization; Heuristics; Regret; Mathematical optimization; Computer science; Bayesian probability; Constant (computer programming); Optimization problem; Function (biology); Algorithm; Mathematics; Artificial intelligence; Machine learning","score_opus":0.05627383965606547,"score_gpt":0.3841076774584195,"score_spread":0.32783383780235403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2897984390","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015203854,0.0008416001,0.99286467,0.00071481825,0.0006703257,0.0005665836,0.000019671246,0.00018840074,0.0026135352],"genre_scores_gemma":[0.6659848,0.0005854549,0.32079318,0.0001563053,0.0004233613,0.000057268797,0.0005836512,0.00018198248,0.011234011],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9944639,0.00090996677,0.00087182986,0.0013454778,0.0019120212,0.00049675576],"domain_scores_gemma":[0.9962934,0.0014231125,0.0007406874,0.0008620419,0.00047793746,0.00020276823],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0032875924,0.00042200836,0.0007110097,0.0008745902,0.00046614886,0.0011939545,0.0009172485,0.0003993274,0.0010351839],"category_scores_gemma":[0.0059672836,0.00037101735,0.00013402312,0.00068035757,0.00012614578,0.00042701335,0.0023928867,0.0020998153,0.00008652739],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026859547,0.000019414127,0.010160468,0.000030031384,0.000022026274,0.000008326792,0.00041268746,0.9703333,0.0000046205496,0.000026942675,0.00008636732,0.01886895],"study_design_scores_gemma":[0.0005467594,0.000089719375,0.00040418413,0.00009771563,0.000016118845,0.000012541116,0.00017802787,0.9948166,0.000014916299,0.0014746932,0.0019663812,0.00038232937],"about_ca_topic_score_codex":0.0000856247,"about_ca_topic_score_gemma":0.000012019328,"teacher_disagreement_score":0.6720715,"about_ca_system_score_codex":0.00010774473,"about_ca_system_score_gemma":0.00015552064,"threshold_uncertainty_score":0.999878},"labels":[],"label_agreement":null},{"id":"W2901999103","doi":"10.1007/s10994-018-05774-y","title":"Arbitrage of forecasting experts","year":2018,"lang":"en","type":"article","venue":"Machine Learning","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"European Regional Development Fund; Fundação para a Ciência e a Tecnologia; Electronic Components and Systems for European Leadership","keywords":"Computer science; Set (abstract data type); Task (project management); Machine learning; Arbitrage; Component (thermodynamics); Data mining; Artificial intelligence; Series (stratigraphy); Econometrics; Mathematics; Finance","score_opus":0.020222925291654262,"score_gpt":0.22770358929800594,"score_spread":0.20748066400635168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901999103","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32320017,0.00027958275,0.63735807,0.00025941108,0.00019671071,0.00006203264,6.4580377e-7,0.00021365368,0.03842972],"genre_scores_gemma":[0.96452266,0.0000022645886,0.034639798,0.0000636837,0.0001365892,0.000001429759,0.0000016939784,0.000009479445,0.00062239496],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906784,0.000052974057,0.0002376425,0.0002355021,0.0001734002,0.00023266088],"domain_scores_gemma":[0.99938816,0.000063746746,0.00017293896,0.00024493798,0.000079895064,0.000050343053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033155375,0.0001006009,0.00017405914,0.00009621732,0.00021764277,0.00006347626,0.00038677125,0.00003023206,0.00013941889],"category_scores_gemma":[0.00016101691,0.00008665504,0.0000845584,0.00038982485,0.000055333603,0.0002299669,0.0002550141,0.00013214514,0.000013283788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027117312,0.00009426518,0.061374262,0.00006335884,0.00012937454,0.000051483523,0.014947521,0.0047342335,0.017943224,0.031130137,0.00038804676,0.86911696],"study_design_scores_gemma":[0.000123555,0.00017661575,0.00067346,0.000028468748,0.000005711364,0.0000212216,0.000059394322,0.9851007,0.0032441143,0.00032620443,0.010116683,0.00012386165],"about_ca_topic_score_codex":0.00016949559,"about_ca_topic_score_gemma":0.000039467966,"teacher_disagreement_score":0.98036647,"about_ca_system_score_codex":0.000009766773,"about_ca_system_score_gemma":0.000014280462,"threshold_uncertainty_score":0.353369},"labels":[],"label_agreement":null},{"id":"W2947014533","doi":"10.1007/s10994-020-05910-7","title":"Evaluating time series forecasting models: an empirical study on performance estimation methods","year":2020,"lang":"en","type":"article","venue":"Machine Learning","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":386,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Fundação para a Ciência e a Tecnologia; Canada Research Chairs","keywords":"Series (stratigraphy); Computer science; Time series; Independent and identically distributed random variables; Dependency (UML); Machine learning; Data mining; Pipeline (software); Sample (material); Estimation; Artificial intelligence; Statistics; Mathematics; Random variable; Engineering","score_opus":0.22272588833177512,"score_gpt":0.44611060638913863,"score_spread":0.2233847180573635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947014533","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34623137,0.000007882085,0.65152043,0.00041351488,0.000024011262,0.0001759307,0.0000010038799,0.0009903993,0.00063544436],"genre_scores_gemma":[0.46189907,3.2032162e-7,0.53784573,0.00014899398,0.00003325177,0.000017572123,0.00001417836,0.000015737785,0.00002516716],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976035,0.0008404233,0.00030907302,0.0005851585,0.00039689042,0.00026497297],"domain_scores_gemma":[0.9989898,0.00023812786,0.00017592906,0.0004236317,0.00006096451,0.00011153007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020223386,0.00020540507,0.0002370464,0.00009567495,0.0003589314,0.00027534858,0.00078557915,0.000045414658,0.000013466199],"category_scores_gemma":[0.00097360346,0.00019050286,0.000033197815,0.00043206813,0.000020630137,0.0016800844,0.00055671233,0.00045939736,0.000028530045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033457945,0.00008482142,0.012836073,0.000017842654,0.000013844916,0.000009724229,0.010684327,0.23861156,0.0005024699,0.00013948628,0.00003356554,0.73703283],"study_design_scores_gemma":[0.00019291823,0.002742896,0.0017967597,0.000030486717,0.000010459599,0.000012377476,0.0000859712,0.99390817,0.00059132604,0.00037860114,0.000049158567,0.00020084927],"about_ca_topic_score_codex":0.000015721067,"about_ca_topic_score_gemma":6.304853e-7,"teacher_disagreement_score":0.75529665,"about_ca_system_score_codex":0.00003988345,"about_ca_system_score_gemma":0.000035859066,"threshold_uncertainty_score":0.7768481},"labels":[],"label_agreement":null},{"id":"W2984353870","doi":"10.1007/s10994-019-05855-6","title":"A survey on semi-supervised learning","year":2019,"lang":"en","type":"article","venue":"Machine Learning","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":2562,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Universiteit Leiden","keywords":"Artificial intelligence; Machine learning; Computer science; Supervised learning; Unsupervised learning; Scope (computer science); Semi-supervised learning; Artificial neural network; Field (mathematics); Data science; Mathematics","score_opus":0.02000205411217099,"score_gpt":0.24997513849481656,"score_spread":0.22997308438264558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2984353870","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69303006,0.00037707665,0.20496647,0.0009530357,0.001073706,0.00049071945,0.0000027911694,0.0019546982,0.09715143],"genre_scores_gemma":[0.9784343,0.000014514681,0.0028638053,0.0007052377,0.000055249053,0.000006263053,0.000050067614,0.000039994622,0.017830513],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971267,0.0009331268,0.00029550956,0.0006362402,0.0005137307,0.0004946854],"domain_scores_gemma":[0.99847716,0.0006621158,0.00016879216,0.00045095803,0.00008424926,0.00015671186],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015395482,0.00025839306,0.0002932762,0.00023580996,0.00035266398,0.00032781583,0.00072238443,0.00009533234,0.00056212535],"category_scores_gemma":[0.0006591348,0.00024850894,0.000106816035,0.00065597193,0.000022368127,0.0003302303,0.00026941948,0.0011231232,0.0026689728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006164592,0.000084013256,0.6871551,0.000028928758,0.00004622502,0.000031799533,0.003014915,0.20518029,0.0021045813,0.006959332,0.00026814902,0.09506497],"study_design_scores_gemma":[0.00087082916,0.00033968955,0.124602556,0.000042300013,0.000002864224,0.000006839505,0.000079471305,0.82816356,0.00008335344,0.000075321965,0.045363724,0.00036948596],"about_ca_topic_score_codex":0.000243376,"about_ca_topic_score_gemma":0.000030063702,"teacher_disagreement_score":0.6229833,"about_ca_system_score_codex":0.000056850724,"about_ca_system_score_gemma":0.00005007652,"threshold_uncertainty_score":0.9999967},"labels":[],"label_agreement":null},{"id":"W3003871186","doi":"10.1007/s10994-021-06092-6","title":"Improving sequential latent variable models with autoregressive flows","year":2021,"lang":"en","type":"article","venue":"Machine Learning","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Autoregressive model; STAR model; Latent variable; Computer science; Generalization; Benchmark (surveying); Decorrelation; Series (stratigraphy); Sequence (biology); Nonlinear autoregressive exogenous model; Autocorrelation; Latent variable model; Time series; Algorithm; Mathematics; Artificial intelligence; Machine learning; Autoregressive integrated moving average; Econometrics; Statistics","score_opus":0.012232198424941554,"score_gpt":0.201964833962153,"score_spread":0.18973263553721145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3003871186","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014690705,0.00038368933,0.98028654,0.00020365264,0.00011021674,0.000043813012,0.0000013762681,0.00020498909,0.00407501],"genre_scores_gemma":[0.73223335,0.0000063740204,0.26414827,0.00009927599,0.000106437765,0.0000063680964,0.00002237155,0.000022368158,0.00335516],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862236,0.00010230144,0.00019912093,0.00045738247,0.00027327865,0.00034558066],"domain_scores_gemma":[0.999245,0.00003676865,0.00015481989,0.00033337262,0.00014140065,0.00008867682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002446955,0.00016041796,0.00022101394,0.000060413568,0.00037048338,0.00039550342,0.0003177776,0.000045973335,0.00014140556],"category_scores_gemma":[0.00004751261,0.00012785046,0.00007411677,0.00039576492,0.00001649642,0.000570683,0.00042329845,0.00031745867,0.000012031262],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009026981,0.000027555712,0.0017983525,0.000022625605,0.000085325024,0.00022376423,0.00071411795,0.93018836,0.004161837,0.02146558,0.000015095719,0.041288346],"study_design_scores_gemma":[0.00024584946,0.000058379628,0.000069512455,0.00003521809,0.000025824906,0.00008123965,0.000029993736,0.99651086,0.0005620526,0.0004850009,0.0017123747,0.00018368675],"about_ca_topic_score_codex":0.00043682553,"about_ca_topic_score_gemma":0.00008402468,"teacher_disagreement_score":0.71754265,"about_ca_system_score_codex":0.000040848947,"about_ca_system_score_gemma":0.000115692106,"threshold_uncertainty_score":0.521359},"labels":[],"label_agreement":null},{"id":"W3088086419","doi":"10.1007/s10994-020-05902-7","title":"Fast greedy $$\\mathcal {C}$$-bound minimization with guarantees","year":2020,"lang":"en","type":"article","venue":"Machine Learning","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; Agence Nationale de la Recherche","keywords":"Algorithm; Upper and lower bounds; Boosting (machine learning); Combinatorics; Machine learning; Mathematics; Artificial intelligence; Computer science; Mathematical analysis","score_opus":0.010887755744747697,"score_gpt":0.21806746839543142,"score_spread":0.20717971265068372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088086419","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04530884,0.0002219477,0.93957174,0.009612639,0.0001317848,0.00013283847,0.0000017789903,0.0009741961,0.0040442157],"genre_scores_gemma":[0.94826585,0.000009702069,0.04918131,0.0011782275,0.0002960795,0.000007799868,0.000025610698,0.00003666487,0.0009987303],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99829966,0.00019292752,0.00022633922,0.000538905,0.00039640508,0.00034578762],"domain_scores_gemma":[0.9992928,0.00008089402,0.00014300265,0.0002504456,0.0000611263,0.00017174668],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018645854,0.00023624825,0.0002439091,0.000083455554,0.00035553038,0.00034219195,0.0006287265,0.000057789464,0.000093512775],"category_scores_gemma":[0.00015155114,0.00018958857,0.000061980354,0.0005987673,0.00004805531,0.00035841603,0.00022659,0.00059654564,0.00013729703],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016649732,0.00017735806,0.15618692,0.00019189267,0.00015994071,0.00043792094,0.01764915,0.3522128,0.0015774778,0.019788433,0.0010688868,0.45038274],"study_design_scores_gemma":[0.0006226169,0.00043625935,0.0030401598,0.000027180646,0.000009550289,0.00005315154,0.000061254956,0.97433376,0.000111775196,0.00006919225,0.020950725,0.00028435315],"about_ca_topic_score_codex":0.00011594221,"about_ca_topic_score_gemma":0.000013754258,"teacher_disagreement_score":0.902957,"about_ca_system_score_codex":0.00001660476,"about_ca_system_score_gemma":0.000042120268,"threshold_uncertainty_score":0.7731197},"labels":[],"label_agreement":null},{"id":"W3093752029","doi":"10.1007/s10994-022-06300-x","title":"Early anomaly detection in time series: a hierarchical approach for predicting critical health episodes","year":2023,"lang":"en","type":"article","venue":"Machine Learning","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Leverage (statistics); Computer science; Anomaly detection; Key (lock); Machine learning; Artificial intelligence; Data mining; Time series; Series (stratigraphy); Event (particle physics); Computer security","score_opus":0.014507948139910411,"score_gpt":0.2850247771733264,"score_spread":0.270516829033416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093752029","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05737827,0.000025996034,0.9387802,0.0017996884,0.000030345469,0.0003464387,0.000003819785,0.0013137117,0.00032155446],"genre_scores_gemma":[0.89148706,0.00000830816,0.10739201,0.000098714794,0.00007559325,0.00033659063,0.000014306579,0.00001949832,0.0005679406],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986002,0.0001424875,0.0002859561,0.00042174303,0.00016972655,0.00037988467],"domain_scores_gemma":[0.9993667,0.00022285763,0.00006959333,0.00021260498,0.00003346403,0.00009480425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088762975,0.0001181901,0.00017729752,0.00025617488,0.00046204735,0.00014568186,0.00033777647,0.0000733837,0.000004626888],"category_scores_gemma":[0.0002478633,0.00012197031,0.00006842593,0.0009196476,0.0000423028,0.0002880165,0.00017546973,0.0003818049,0.000020316344],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001856261,0.00053240574,0.11512301,0.00058238703,0.00005362944,0.000019237199,0.007098157,0.014680381,0.011715796,0.075211324,0.0004708263,0.7743272],"study_design_scores_gemma":[0.0001831957,0.00041767134,0.015687753,0.000016823255,0.0000017527881,0.000019624453,0.000030824373,0.97836995,0.0005104045,0.0024136477,0.0022104986,0.00013788012],"about_ca_topic_score_codex":0.00019987668,"about_ca_topic_score_gemma":0.0000164928,"teacher_disagreement_score":0.96368957,"about_ca_system_score_codex":0.00006147243,"about_ca_system_score_gemma":0.000032658878,"threshold_uncertainty_score":0.4973805},"labels":[],"label_agreement":null},{"id":"W3094116343","doi":"10.1007/s10994-023-06337-6","title":"The role of mutual information in variational classifiers","year":2023,"lang":"en","type":"article","venue":"Machine Learning","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"H2020 Marie Skłodowska-Curie Actions; Universidad de Buenos Aires; Consejo Nacional de Investigaciones Científicas y Técnicas","keywords":"Information bottleneck method; Mutual information; Overfitting; Artificial intelligence; Regularization (linguistics); Computer science; Mathematics; Generalization; Kullback–Leibler divergence; Early stopping; MNIST database; Entropy (arrow of time); Inference; Algorithm; Machine learning; Artificial neural network","score_opus":0.00828382254537237,"score_gpt":0.22553121530298656,"score_spread":0.21724739275761418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094116343","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13407181,0.00032367473,0.76965004,0.006768359,0.00091589097,0.0004585554,0.0000042994793,0.0010724857,0.08673488],"genre_scores_gemma":[0.996949,0.00001448187,0.0024533505,0.00007499794,0.000017128319,0.0000074480577,0.000018216628,0.0000036346335,0.0004617007],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99913996,0.00012806132,0.00022656751,0.000084820706,0.000258746,0.00016183902],"domain_scores_gemma":[0.99938303,0.00030971275,0.00012534423,0.000116997944,0.000038077884,0.000026811966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008419888,0.000056289104,0.00006596396,0.00017739733,0.00019281506,0.000104465355,0.0002944443,0.000029809096,0.000014286956],"category_scores_gemma":[0.00040872802,0.00004535992,0.00002763378,0.0006881428,0.000022356704,0.00047944227,0.00011176143,0.0002213308,0.00013721891],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001627904,0.000010467391,0.049521387,0.000006768201,0.0000116051115,0.0000018025805,0.009096131,0.21540037,0.00042863458,0.31231022,0.00013505312,0.4130613],"study_design_scores_gemma":[0.00018040412,0.00001858236,0.039260045,0.0000046665955,5.5974795e-7,0.0000011191642,0.0005209335,0.8607024,0.000026583604,0.0022538395,0.09698454,0.000046332716],"about_ca_topic_score_codex":0.000046460056,"about_ca_topic_score_gemma":0.000015318554,"teacher_disagreement_score":0.86287725,"about_ca_system_score_codex":0.000022571016,"about_ca_system_score_gemma":0.000042891337,"threshold_uncertainty_score":0.18497239},"labels":[],"label_agreement":null},{"id":"W3098081048","doi":"10.1007/s10994-021-05989-6","title":"A framework for the fine-grained evaluation of the instantaneous expected value of soccer possessions","year":2021,"lang":"en","type":"preprint","venue":"Machine Learning","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Agència de Gestió d'Ajuts Universitaris i de Recerca; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Possession (linguistics); Interpretation (philosophy); Computer science; Set (abstract data type); Value (mathematics); Series (stratigraphy); Artificial intelligence; Machine learning; Geology","score_opus":0.06513801801211416,"score_gpt":0.3054878476148347,"score_spread":0.24034982960272055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3098081048","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94994044,0.009872192,0.03469287,0.0015014284,0.001176099,0.0008664672,0.00026656772,0.000020061761,0.0016638446],"genre_scores_gemma":[0.9975876,0.0002971372,0.0013867896,0.000070077986,0.00012585644,0.0000692236,0.000093728886,0.000031727606,0.0003378374],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855345,0.000056904977,0.0007455676,0.00032539276,0.00014612144,0.00017253685],"domain_scores_gemma":[0.99743795,0.00033713036,0.0013255733,0.0006350771,0.00024067011,0.000023568815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015318784,0.00017872,0.00048942823,0.00010749838,0.00022992295,0.00005789307,0.00042161494,0.00020356305,0.00075474667],"category_scores_gemma":[0.0015777443,0.00012625373,0.00037322528,0.00027286954,0.00006633137,0.000030751864,0.00033351462,0.00070770684,0.0000015416886],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037955368,0.000107108084,0.12317588,0.00026143776,0.00039919632,9.51243e-7,0.0040301923,0.7847167,0.00003615539,0.08274338,0.00008716937,0.004403867],"study_design_scores_gemma":[0.0003267666,0.00003241673,0.046369508,0.00027879965,0.00013681118,0.0000024501658,0.00027963627,0.9246941,0.000068329726,0.02514761,0.0024805074,0.00018305151],"about_ca_topic_score_codex":0.0007863208,"about_ca_topic_score_gemma":0.00015321893,"teacher_disagreement_score":0.13997741,"about_ca_system_score_codex":0.000070370195,"about_ca_system_score_gemma":0.0001489588,"threshold_uncertainty_score":0.8263947},"labels":[],"label_agreement":null},{"id":"W3131097734","doi":"10.1007/s10994-022-06265-x","title":"SVRG meets AdaGrad: painless variance reduction","year":2022,"lang":"en","type":"article","venue":"Machine Learning","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; SAIT Polytechnic; Université de Montréal; Simon Fraser University","funders":"Agence Nationale de la Recherche","keywords":"Minification; Mathematics; Variance reduction; Constant (computer programming); Reduction (mathematics); Heuristic; Variance (accounting); Robustness (evolution); Regular polygon; Algorithm; Mathematical optimization; Computer science; Applied mathematics; Statistics; Geometry","score_opus":0.009090252797299359,"score_gpt":0.20340088466178724,"score_spread":0.19431063186448788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3131097734","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8132125,0.0064851404,0.117187075,0.0016307646,0.0031442174,0.0005875329,0.000017591368,0.012751306,0.04498383],"genre_scores_gemma":[0.99714386,0.000035117817,0.001964679,0.00004205178,0.00011772497,0.000024604555,0.000022035438,0.000042044423,0.0006078955],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992785,0.000109071094,0.000118184274,0.00015612626,0.00015588033,0.00018222822],"domain_scores_gemma":[0.9997405,0.00002102111,0.000032303462,0.0001625507,0.000012629995,0.00003101759],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018669736,0.00011191344,0.000115727744,0.00008188779,0.00029033856,0.000026302907,0.00012935407,0.000025468416,0.00019973716],"category_scores_gemma":[0.000016556833,0.00012839258,0.000041557472,0.00018764022,0.000011683155,0.000056803612,0.000087322514,0.00046689212,0.000008631636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012997085,0.000020931038,0.00066385284,0.000012944051,0.00003775393,0.000039486604,0.00051841623,0.9111771,0.043982826,0.0011525227,0.0048388885,0.03754228],"study_design_scores_gemma":[0.00015969267,0.00006432836,0.0003625844,0.000017823277,0.000013166014,0.00011421374,0.0001237956,0.6171791,0.008511717,0.0005033537,0.37268996,0.00026024223],"about_ca_topic_score_codex":0.00008559206,"about_ca_topic_score_gemma":0.0000023131918,"teacher_disagreement_score":0.36785108,"about_ca_system_score_codex":0.0000653028,"about_ca_system_score_gemma":0.000005639982,"threshold_uncertainty_score":0.52356976},"labels":[],"label_agreement":null},{"id":"W3134713499","doi":"10.1007/s10994-021-05947-2","title":"Incremental learning of iterated dependencies","year":2021,"lang":"en","type":"article","venue":"Machine Learning","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Atomic Energy of Canada Limited; Universiteit van Amsterdam; University of Cambridge; Institut national de recherche en informatique et en automatique (INRIA); University of Pennsylvania","keywords":"Link grammar; Dependency (UML); Iterated function; Categorial grammar; Grammar induction; Rule-based machine translation; Combinatory categorial grammar; Computer science; Dependency theory (database theory); Mathematics; Learnability; Theoretical computer science; L-attributed grammar; Tree-adjoining grammar; Artificial intelligence; Context-free grammar; Mildly context-sensitive grammar formalism; Functional dependency; Generative grammar; Emergent grammar; Attribute grammar","score_opus":0.00914247867839503,"score_gpt":0.2367233856628351,"score_spread":0.22758090698444006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134713499","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5472466,0.0019121697,0.4306198,0.0010722133,0.0005046932,0.000110419605,0.0000025704803,0.0008700276,0.017661544],"genre_scores_gemma":[0.970624,0.000032313383,0.02509099,0.00011222842,0.0000744415,0.0000037164266,0.00003065496,0.00002055567,0.0040110713],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99790716,0.0005255599,0.00034431773,0.000444229,0.0004331284,0.00034557751],"domain_scores_gemma":[0.9990581,0.0001721405,0.00020590315,0.0003070546,0.00016251196,0.00009427403],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058760913,0.00019618479,0.0002889305,0.00014271236,0.00032438687,0.00016652663,0.00048655792,0.00006797566,0.00027816088],"category_scores_gemma":[0.0005509226,0.00019201606,0.00011421494,0.0007021855,0.000036656107,0.0003029121,0.00054035994,0.00081317953,0.000050707404],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028238203,0.0003005016,0.45079693,0.0001900456,0.00020928672,0.00062203046,0.0064996537,0.09875194,0.09747313,0.020281991,0.00022007096,0.32462618],"study_design_scores_gemma":[0.0007426324,0.00021234596,0.009998688,0.000076961805,0.000013939454,0.00018232416,0.00022041277,0.94522625,0.022895249,0.00023102053,0.019834373,0.00036582726],"about_ca_topic_score_codex":0.0002132953,"about_ca_topic_score_gemma":0.000015596865,"teacher_disagreement_score":0.8464743,"about_ca_system_score_codex":0.000029682178,"about_ca_system_score_gemma":0.00008552711,"threshold_uncertainty_score":0.78301877},"labels":[],"label_agreement":null},{"id":"W3135908355","doi":"10.1007/s10994-022-06188-7","title":"STUDD: a student–teacher method for unsupervised concept drift detection","year":2022,"lang":"en","type":"article","venue":"Machine Learning","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Fundação para a Ciência e a Tecnologia","keywords":"Concept drift; Computer science; Unsupervised learning; Context (archaeology); Data stream mining; Artificial intelligence; Data stream; Machine learning; Set (abstract data type); Task (project management); State (computer science); Algorithm; Engineering","score_opus":0.016396987087168403,"score_gpt":0.31820220685964856,"score_spread":0.30180521977248015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135908355","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011017773,0.00012266201,0.9862059,0.00041194097,0.00022862502,0.00041843424,0.000019114728,0.001033173,0.00054242875],"genre_scores_gemma":[0.64115494,0.0000017327687,0.35629737,0.00028390606,0.00007421859,0.00041842597,0.000046086217,0.000033687862,0.0016896297],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99791765,0.0006217664,0.00023356211,0.00053807977,0.0003805377,0.0003084236],"domain_scores_gemma":[0.9990208,0.00024399805,0.00013677301,0.00049797987,0.000041592768,0.000058867667],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013888787,0.00017057807,0.00021156104,0.0001653576,0.000690171,0.00016436311,0.0012300201,0.00003588365,0.000115024086],"category_scores_gemma":[0.00016775087,0.00017960687,0.00009231448,0.0003873542,0.000017467804,0.0002591246,0.0012562539,0.0005098768,0.000004814703],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042624273,0.00030628685,0.009698974,0.000018788518,0.00011884656,0.00002384555,0.014012495,0.006243857,0.009222832,0.0050803386,0.0022941858,0.95293695],"study_design_scores_gemma":[0.0012609318,0.0013401025,0.0019514159,0.0000087588805,0.00003273455,0.00004606399,0.0007971368,0.7819194,0.004665144,0.0010826514,0.20642939,0.00046625343],"about_ca_topic_score_codex":0.00023683706,"about_ca_topic_score_gemma":0.000026909327,"teacher_disagreement_score":0.95247066,"about_ca_system_score_codex":0.00010398835,"about_ca_system_score_gemma":0.000029529401,"threshold_uncertainty_score":0.73241556},"labels":[],"label_agreement":null},{"id":"W3160953847","doi":"10.1007/s10994-021-06012-8","title":"RB-CCR: Radial-Based Combined Cleaning and Resampling algorithm for imbalanced data classification","year":2021,"lang":"en","type":"preprint","venue":"Machine Learning","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"Infrastruktura PL-Grid; Narodowe Centrum Nauki","keywords":"Resampling; Oversampling; Benchmark (surveying); Computer science; Artificial intelligence; Prior probability; Binary classification; Binary number; Pattern recognition (psychology); Class (philosophy); Data mining; Machine learning; Algorithm; Mathematics; Support vector machine; Bayesian probability","score_opus":0.06623426337024325,"score_gpt":0.321198295922057,"score_spread":0.25496403255181377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160953847","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006767655,0.0005301067,0.99401,0.0017444789,0.0005365028,0.0008405674,0.000248834,0.0012752349,0.0001375394],"genre_scores_gemma":[0.12172508,0.00016289967,0.86359704,0.0003294038,0.00021757545,0.00023549893,0.013537561,0.00007757984,0.000117385396],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99595976,0.0004015044,0.0007119604,0.0020028024,0.0004309624,0.00049300224],"domain_scores_gemma":[0.9949072,0.00068599737,0.00081472745,0.0031691012,0.0002780066,0.00014499108],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0019247824,0.00046550823,0.0006231827,0.00030583478,0.00050080306,0.0012486214,0.002837503,0.00036799238,0.000008349968],"category_scores_gemma":[0.0010764452,0.000526445,0.000102642254,0.00036205733,0.000092882416,0.00062310114,0.0034173545,0.001298059,0.0000032382927],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039557497,0.0001510266,0.003696268,0.0005159887,0.000120209435,0.000015761449,0.00053775683,0.0031076125,0.0057440265,0.0054882853,0.0012451065,0.9793384],"study_design_scores_gemma":[0.00077084854,0.00007567042,0.0023889395,0.0002684832,0.000035703637,0.0000061810515,0.00004929564,0.9829503,0.0010985129,0.0007696512,0.011045638,0.00054075255],"about_ca_topic_score_codex":0.000107891334,"about_ca_topic_score_gemma":0.000017499322,"teacher_disagreement_score":0.9798427,"about_ca_system_score_codex":0.00015238998,"about_ca_system_score_gemma":0.000325844,"threshold_uncertainty_score":0.99978817},"labels":[],"label_agreement":null},{"id":"W3169315049","doi":"10.1007/s10994-021-06080-w","title":"On the benefits of representation regularization in invariance based domain generalization","year":2022,"lang":"en","type":"article","venue":"Machine Learning","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research; Mila - Quebec Artificial Intelligence Institute; Vector Institute; Western University; Université Laval","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Mitacs; Canadian Institute for Advanced Research","keywords":"Regularization (linguistics); Invariant (physics); Computer science; Generalization error; Artificial intelligence; Representation (politics); Generalization; Machine learning; Feature learning; Robustness (evolution); Algorithm; Mathematics; Unsupervised learning","score_opus":0.021319547624807592,"score_gpt":0.24230291248694885,"score_spread":0.22098336486214126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3169315049","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12523627,0.00007076799,0.86784583,0.0035978858,0.00013940084,0.00023269797,0.0000015694699,0.0000865542,0.0027890215],"genre_scores_gemma":[0.9896374,0.0000031035183,0.0088507,0.00084063516,0.000014729631,0.000041735544,0.00005185059,0.000011338276,0.00054854044],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805444,0.0008965424,0.00024968936,0.00025604383,0.00041078147,0.00013251534],"domain_scores_gemma":[0.9991592,0.00027077578,0.0002374675,0.0002742243,0.000037777143,0.000020540234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010561494,0.00008364351,0.00010118097,0.00020244549,0.00034900598,0.0000571128,0.0003733576,0.00002152049,0.00013889515],"category_scores_gemma":[0.00032381673,0.00007581317,0.000033882523,0.0011005137,0.000017014983,0.00015980029,0.00013411038,0.00027771314,0.0000039299243],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012568294,0.000023693598,0.00471676,0.0000026900275,0.000001849165,0.000001249844,0.00097628555,0.6889799,0.0005977808,0.30059895,0.000024797877,0.0040634503],"study_design_scores_gemma":[0.0004554857,0.000083700645,0.010546044,0.000013154965,0.0000013796572,0.0000018531977,0.00011740612,0.97981304,0.00039927923,0.0068881037,0.0015939341,0.00008659095],"about_ca_topic_score_codex":0.00006140406,"about_ca_topic_score_gemma":0.000014970506,"teacher_disagreement_score":0.8644011,"about_ca_system_score_codex":0.00006198621,"about_ca_system_score_gemma":0.000035998244,"threshold_uncertainty_score":0.30915716},"labels":[],"label_agreement":null},{"id":"W3182947351","doi":"10.1007/s10994-021-05980-1","title":"Triply stochastic gradient method for large-scale nonlinear similar unlabeled classification","year":2021,"lang":"en","type":"article","venue":"Machine Learning","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Priority Academic Program Development of Jiangsu Higher Education Institutions; Government of Jiangsu Province; Six Talent Peaks Project in Jiangsu Province; National Natural Science Foundation of China","keywords":"Scalability; Classifier (UML); Computer science; Artificial intelligence; Generalization; Machine learning; Kernel (algebra); Stochastic gradient descent; Benchmark (surveying); Data point; Nonlinear system; Scale (ratio); Linear classifier; Algorithm; Mathematics; Artificial neural network","score_opus":0.024356367146481445,"score_gpt":0.3079578563482156,"score_spread":0.28360148920173417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3182947351","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017207799,0.00037016824,0.9895494,0.006588617,0.00034681335,0.0002890391,0.00003532015,0.00046372743,0.0006361252],"genre_scores_gemma":[0.15939605,0.000030439702,0.8339679,0.0008141656,0.00029558584,0.00013354412,0.0013375324,0.000060264025,0.003964481],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971566,0.0005810369,0.0004578716,0.0009221923,0.00036730754,0.0005149725],"domain_scores_gemma":[0.99785346,0.0005692575,0.0002940671,0.0008349519,0.0002822647,0.00016597692],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015761071,0.00026105918,0.00033707827,0.00017345084,0.0006090223,0.00028828645,0.00063228287,0.00012295166,0.000051946863],"category_scores_gemma":[0.0013424793,0.00025837208,0.00016208529,0.0007241412,0.00001766507,0.0003290605,0.0002458759,0.00055682374,0.00006181988],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021427177,0.0016494818,0.011998376,0.0004187297,0.0002788752,0.00004935765,0.007543456,0.09687438,0.046444427,0.19708796,0.0037811573,0.63365954],"study_design_scores_gemma":[0.0009780715,0.00010597069,0.0025636242,0.00002122874,0.000030103349,0.000023214985,0.00013748612,0.8654332,0.0003861267,0.00060693384,0.12945557,0.0002584526],"about_ca_topic_score_codex":0.000027002046,"about_ca_topic_score_gemma":0.00006664413,"teacher_disagreement_score":0.76855886,"about_ca_system_score_codex":0.000080593185,"about_ca_system_score_gemma":0.00013553242,"threshold_uncertainty_score":0.9999868},"labels":[],"label_agreement":null},{"id":"W3184701629","doi":"10.1007/s10994-021-06029-z","title":"Multimodal deep learning for cetacean distribution modeling of fin whales (Balaenoptera physalus) in the western Mediterranean Sea","year":2021,"lang":"en","type":"article","venue":"Machine Learning","topic":"Marine animal studies overview","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Ocean Frontier Institute; Agence Nationale de la Recherche; ISblue","keywords":"Balaenoptera; Whale; Artificial intelligence; Deep learning; Species distribution; Range (aeronautics); Metric (unit); Task (project management); Machine learning; Computer science; Transfer of learning; Habitat; Geography; Cetacea; Mediterranean climate; Ecology; Engineering; Biology","score_opus":0.022617051752978477,"score_gpt":0.261314677143047,"score_spread":0.23869762539006853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3184701629","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97878414,0.00068407366,0.018159216,0.0007280909,0.000055247772,0.0002718122,0.000009697571,0.000042254094,0.0012654454],"genre_scores_gemma":[0.99866986,0.00012718306,0.0006044401,0.00012837436,0.000065486376,0.00002754405,0.00021215962,0.000021388314,0.0001435342],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837595,0.00029817034,0.00032418643,0.00034287496,0.00032842046,0.00033041224],"domain_scores_gemma":[0.99942636,0.00021938492,0.0001309675,0.00016439604,0.00002046201,0.000038403807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069591554,0.00017914994,0.00026611626,0.000017922017,0.00025105214,0.0000415189,0.00024680112,0.000051335952,0.00020613549],"category_scores_gemma":[0.00038160718,0.00014557033,0.00010871342,0.00023748714,0.00005537579,0.00015226708,0.00036665247,0.0004110256,0.000017926293],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031264404,0.00006896335,0.5677828,0.000069718546,0.000015344609,0.000011136522,0.0026839762,0.3865025,0.0003049117,0.000015255055,0.000022916325,0.042491198],"study_design_scores_gemma":[0.0005198398,0.00010018241,0.09294584,0.00004523102,0.000022843775,0.0000081833205,0.00057010865,0.8955418,0.000082005456,0.000039252736,0.009963834,0.00016092423],"about_ca_topic_score_codex":0.0025255098,"about_ca_topic_score_gemma":0.005820063,"teacher_disagreement_score":0.5090392,"about_ca_system_score_codex":0.000089880705,"about_ca_system_score_gemma":0.000006674816,"threshold_uncertainty_score":0.59361863},"labels":[],"label_agreement":null},{"id":"W3196229027","doi":"10.1007/s10994-021-06041-3","title":"Guest editorial: special issue on reinforcement learning for real life","year":2021,"lang":"en","type":"editorial","venue":"Machine Learning","topic":"Modular Robots and Swarm Intelligence","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Reinforcement; Cognitive science; Artificial intelligence; Psychology; Social psychology","score_opus":0.009127397020637387,"score_gpt":0.25391970605673,"score_spread":0.2447923090360926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196229027","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000013043485,0.00032072948,0.005978378,0.000037411726,0.97566855,0.00038968667,0.000023909774,0.00057676394,0.016991556],"genre_scores_gemma":[0.00031200878,0.0015702059,0.00017408651,0.000017167311,0.9785279,0.00009926708,0.0028369352,0.00031167676,0.016150758],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964635,0.00013654366,0.0007457723,0.0007079855,0.001194619,0.00075161236],"domain_scores_gemma":[0.9979504,0.0008529956,0.0002261161,0.00042471744,0.00029661314,0.00024918423],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0007283025,0.0007181149,0.00087495835,0.00021185292,0.00039739962,0.00029935336,0.0004513118,0.0011182319,0.0008525541],"category_scores_gemma":[0.0032057983,0.00075847434,0.00031990634,0.00018898363,0.000032582957,0.00009875867,0.0001401178,0.0034967388,0.0002384462],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045499553,0.000010307028,0.000007409829,0.00022612036,0.0000914971,0.000011849837,0.000198178,0.4211336,0.000022858725,0.000023086966,0.5761771,0.0020524568],"study_design_scores_gemma":[0.00046776,0.00038004896,0.0000011859463,0.0002693752,0.00007146336,5.760021e-7,0.000047919995,0.05194094,0.00016840544,0.0000060172424,0.94592315,0.0007231834],"about_ca_topic_score_codex":0.0002597211,"about_ca_topic_score_gemma":0.00007334531,"teacher_disagreement_score":0.369746,"about_ca_system_score_codex":0.00029700616,"about_ca_system_score_gemma":0.00016365632,"threshold_uncertainty_score":0.9994866},"labels":[],"label_agreement":null},{"id":"W3208335533","doi":"10.1007/s10994-023-06340-x","title":"A moment-matching metric for latent variable generative models","year":2023,"lang":"en","type":"preprint","venue":"Machine Learning","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Canadian Statistical Sciences Institute; University of Toronto","keywords":"Latent variable; Metric (unit); Regularization (linguistics); Gaussian; Matrix norm; Computer science; Latent variable model; Mathematics; Applied mathematics; Moment (physics); Generative grammar; Norm (philosophy); Artificial intelligence; Algorithm; Mathematical optimization","score_opus":0.060794617866384765,"score_gpt":0.30770584740672646,"score_spread":0.2469112295403417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208335533","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017269565,0.0010995961,0.99363476,0.0012001175,0.001081965,0.00075081724,0.00003677974,0.0007447531,0.0012785244],"genre_scores_gemma":[0.0098286,0.0001374835,0.9815159,0.00026610633,0.00032026507,0.00036310925,0.00010232763,0.00009382892,0.0073723653],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99680036,0.0004505894,0.0005001751,0.0012159575,0.00040900163,0.00062392856],"domain_scores_gemma":[0.9981181,0.00042318652,0.00037499226,0.00076859054,0.00015597808,0.00015913315],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0022047143,0.00047254557,0.0006625759,0.0005502958,0.0004678814,0.00056539406,0.0012832775,0.00031098354,0.000008124952],"category_scores_gemma":[0.00014432504,0.00043553798,0.0002857544,0.00062288396,0.000018798042,0.0002777175,0.0024030826,0.0013089908,0.000013650957],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000071953095,0.00003118577,0.000021711136,0.00016832029,0.00013466577,0.0000101854885,0.0013542571,0.7356918,0.00020646305,0.23222834,0.00030806495,0.029837847],"study_design_scores_gemma":[0.00020035073,0.000042212836,0.000006921255,0.00007301832,0.000028298591,0.000003038877,0.0000032858065,0.61692166,0.00007986311,0.3809542,0.0013933969,0.00029371493],"about_ca_topic_score_codex":0.00056968146,"about_ca_topic_score_gemma":0.000010334564,"teacher_disagreement_score":0.14872587,"about_ca_system_score_codex":0.0001501376,"about_ca_system_score_gemma":0.00016710523,"threshold_uncertainty_score":0.9998096},"labels":[],"label_agreement":null},{"id":"W4200566067","doi":"10.1007/s10994-021-06069-5","title":"A taxonomy of weight learning methods for statistical relational learning","year":2021,"lang":"en","type":"article","venue":"Machine Learning","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Defense Advanced Research Projects Agency; Institut de Valorisation des Données; Canada First Research Excellence Fund; National Science Foundation","keywords":"Statistical relational learning; Probabilistic logic; Artificial intelligence; Computer science; Machine learning; Metric (unit); Set (abstract data type); Theoretical computer science; Data mining; Relational database","score_opus":0.05351484882150161,"score_gpt":0.33730451084438556,"score_spread":0.28378966202288397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200566067","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010687512,0.00056159205,0.9950024,0.0003551521,0.00014208727,0.00010323686,0.0000020354855,0.00017852783,0.0025862043],"genre_scores_gemma":[0.28198934,0.00001831656,0.7160245,0.000050376377,0.00006002837,0.000032765594,0.000046935173,0.000016905118,0.0017607893],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99772906,0.000814264,0.00040866065,0.00049048377,0.00022016438,0.00033737379],"domain_scores_gemma":[0.9976747,0.0015308049,0.0002196805,0.00020261097,0.00026357322,0.00010861818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001308123,0.00017486089,0.00031511378,0.00010383371,0.00036398636,0.0001009026,0.0002928838,0.00009880634,0.00013500512],"category_scores_gemma":[0.0019960704,0.00017917964,0.00011085268,0.0003411219,0.000048409485,0.00022445632,0.00024339902,0.0008454904,0.000014502107],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024689301,0.00006624655,0.019395528,0.00008843496,0.00007265066,0.000015693773,0.0007008288,0.13102977,0.0048633222,0.3084778,0.00009038478,0.53517467],"study_design_scores_gemma":[0.00035470398,0.00014206379,0.00079489785,0.00004103576,0.000017005867,0.000025393689,0.000038981216,0.9103584,0.0012870652,0.00452981,0.08221039,0.0002002312],"about_ca_topic_score_codex":0.000025497251,"about_ca_topic_score_gemma":0.0000026793762,"teacher_disagreement_score":0.77932864,"about_ca_system_score_codex":0.00003371902,"about_ca_system_score_gemma":0.0001835132,"threshold_uncertainty_score":0.7306734},"labels":[],"label_agreement":null},{"id":"W4225277467","doi":"10.1007/s10994-022-06171-2","title":"Arbitrary conditional inference in variational autoencoders via fast prior network training","year":2022,"lang":"en","type":"article","venue":"Machine Learning","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Inference; Computer science; Artificial intelligence; Conditional probability distribution; Machine learning; Approximate inference; Pattern recognition (psychology); Mathematics; Statistics","score_opus":0.015102373214212433,"score_gpt":0.23249925987396183,"score_spread":0.2173968866597494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225277467","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017225542,0.00011150895,0.99440277,0.0011207183,0.00030169464,0.000110143985,0.0000060609077,0.00010805005,0.002116482],"genre_scores_gemma":[0.90975606,0.0000026630942,0.08891719,0.00076047296,0.00020881108,0.00004799942,0.00007720053,0.000011769217,0.00021786323],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980714,0.00050113455,0.00027166202,0.00039556727,0.00038529772,0.00037496633],"domain_scores_gemma":[0.9991441,0.0004671989,0.0001375005,0.0001566707,0.000029116374,0.0000654263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076199445,0.00015206696,0.00018922905,0.00012551525,0.0007506012,0.000109969966,0.0004914668,0.000030669547,0.0006588404],"category_scores_gemma":[0.0001336597,0.00016739192,0.000065173146,0.0005874003,0.00003261171,0.00039728847,0.0004044057,0.00065381813,0.000011681732],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000076195884,0.000028974708,0.0058698244,0.0000018720742,0.000014681252,0.000022742093,0.0013349927,0.96087015,0.00009648382,0.011808168,0.000104884384,0.019839607],"study_design_scores_gemma":[0.0003355341,0.00006907348,0.020246528,0.0000069096914,0.00000318993,0.000013239898,0.00007005249,0.9650587,0.0000050297162,0.008650196,0.005355738,0.00018581272],"about_ca_topic_score_codex":0.00010093677,"about_ca_topic_score_gemma":0.00004209761,"teacher_disagreement_score":0.9080335,"about_ca_system_score_codex":0.000088830326,"about_ca_system_score_gemma":0.00016203182,"threshold_uncertainty_score":0.72138405},"labels":[],"label_agreement":null},{"id":"W4229516452","doi":"10.4018/978-1-60960-818-7.ch804","title":"Pattern Discovery as Event Association","year":2011,"lang":"en","type":"book-chapter","venue":"Machine Learning","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Pattern Discovery Technologies (Canada); University of Waterloo","funders":"","keywords":"Event (particle physics); Association (psychology); Task (project management); Binary number; Mathematics; Computer science; Artificial intelligence; Algorithm; Combinatorics; Discrete mathematics; Arithmetic; Psychology; Physics","score_opus":0.012529066127516131,"score_gpt":0.2193140326999921,"score_spread":0.20678496657247597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229516452","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000144093765,0.0002599073,0.33652982,0.0004915396,0.00073005253,0.00014267922,0.000013957882,0.00026055946,0.6615571],"genre_scores_gemma":[0.005673633,0.0001774801,0.0006224104,0.00038465083,0.00028018063,0.0000051699894,0.000230852,0.00004055862,0.99258506],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998474,0.000040873696,0.00025342195,0.000500502,0.0004675197,0.00026368944],"domain_scores_gemma":[0.99896073,0.000053440526,0.0004315214,0.00046716054,0.00003356448,0.000053553613],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004285406,0.00027250475,0.00025176624,0.00015596296,0.0001388023,0.0004394505,0.00088620966,0.00014098354,0.0004415338],"category_scores_gemma":[0.000043480435,0.00026204466,0.00014644284,0.000035288016,0.000009777906,0.00078662595,0.0009398203,0.00059409946,0.0014933748],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032167657,0.000029958579,0.0029825415,0.00005315784,0.0002397533,0.0001262827,0.0003433008,0.000078156816,0.0000029962907,0.22750868,0.005990798,0.76264113],"study_design_scores_gemma":[0.00020568435,0.00010664798,0.0004717639,0.00011120554,0.000045273504,0.0000037797652,0.0000017315257,0.011463156,0.000006221677,0.0191623,0.9679385,0.00048373998],"about_ca_topic_score_codex":0.00018933055,"about_ca_topic_score_gemma":0.000028519451,"teacher_disagreement_score":0.9619477,"about_ca_system_score_codex":0.00012941842,"about_ca_system_score_gemma":0.000022861168,"threshold_uncertainty_score":0.9999832},"labels":[],"label_agreement":null},{"id":"W4230976265","doi":"10.4018/978-1-60960-818-7.ch710","title":"Ethology-Based Approximate Adaptive Learning","year":2011,"lang":"en","type":"book-chapter","venue":"Machine Learning","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Ethology; Artificial intelligence; Computer science; Animal learning; Machine learning; Adaptive learning; Adaptive behavior; Psychology; Biology; Cognitive psychology; Ecology","score_opus":0.025530463959230084,"score_gpt":0.2349662953763786,"score_spread":0.2094358314171485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230976265","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001598804,0.0009942495,0.48472965,0.0002874117,0.00047789796,0.00023089473,0.0000048161583,0.001575521,0.5116836],"genre_scores_gemma":[0.020982374,0.000118587646,0.10071999,0.0006436309,0.0005958809,0.000040336025,0.00018492056,0.0003431783,0.8763711],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995838,0.00045105527,0.00065717596,0.0015305231,0.0006633809,0.000859898],"domain_scores_gemma":[0.99732673,0.00036244126,0.00090481807,0.00094956846,0.00017614834,0.00028031677],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0012408709,0.0009903085,0.0009827996,0.0006390244,0.0007576053,0.00023691088,0.0016713514,0.00071074435,0.00094474206],"category_scores_gemma":[0.00023000507,0.0009600965,0.00046795586,0.00015764678,0.000193475,0.00024361411,0.00084761984,0.0055437405,0.00095592596],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011105287,0.00010069851,0.0015402867,0.00023584635,0.0003529677,0.00092388043,0.0023108851,0.042559355,0.0000604353,0.49113563,0.00069444487,0.45997453],"study_design_scores_gemma":[0.0007248621,0.0007949797,0.00008883651,0.00029601995,0.000072869545,0.0000954782,0.000008338259,0.6045947,0.00003664458,0.013487917,0.37844983,0.0013495467],"about_ca_topic_score_codex":0.00014178653,"about_ca_topic_score_gemma":0.000011301383,"teacher_disagreement_score":0.5620353,"about_ca_system_score_codex":0.00010426299,"about_ca_system_score_gemma":0.00017184847,"threshold_uncertainty_score":0.9999685},"labels":[],"label_agreement":null},{"id":"W4233822191","doi":"10.4018/978-1-60960-818-7.ch702","title":"Granular Computing and Human-Centricity in Computational Intelligence","year":2011,"lang":"en","type":"book-chapter","venue":"Machine Learning","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Granular computing; Computer science; Fuzzy logic; Facet (psychology); Fuzzy set; Cluster analysis; Set (abstract data type); Computational intelligence; Suite; Rough set; Theoretical computer science; Artificial intelligence; Data mining; Data science","score_opus":0.03026399410605888,"score_gpt":0.2575815101774934,"score_spread":0.22731751607143455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233822191","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005444435,0.0017389957,0.74045223,0.00016928658,0.00019126337,0.0002439944,0.0000033388203,0.00022874516,0.2564277],"genre_scores_gemma":[0.951218,0.0001316733,0.037803013,0.00031016715,0.00013100865,0.0000019238685,0.00006498999,0.00005008893,0.01028914],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983813,0.000064373184,0.00040759039,0.00059270824,0.0002696714,0.00028436733],"domain_scores_gemma":[0.9992559,0.00013555268,0.0002497151,0.00022802882,0.000047852573,0.00008296245],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00042606494,0.00030254023,0.00037268025,0.00027903763,0.0002543109,0.00013828922,0.0005496743,0.00016982759,0.000075517906],"category_scores_gemma":[0.00002476228,0.00029378157,0.000072807474,0.00008207872,0.00008229335,0.00012659065,0.0006168076,0.0009106257,0.000042740354],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036036884,0.000025566802,0.007744261,0.000048464502,0.000012927773,0.0001486811,0.00090554584,0.019510565,7.845439e-7,0.84404624,0.000023847413,0.1275295],"study_design_scores_gemma":[0.00032409205,0.00019268533,0.008164953,0.0002693608,0.000014872881,0.00008012152,0.000006140695,0.6105785,0.0000020026202,0.35892177,0.020668214,0.0007773219],"about_ca_topic_score_codex":0.00021000655,"about_ca_topic_score_gemma":0.000034599554,"teacher_disagreement_score":0.9506736,"about_ca_system_score_codex":0.000046492216,"about_ca_system_score_gemma":0.00002486344,"threshold_uncertainty_score":0.9999514},"labels":[],"label_agreement":null},{"id":"W4240001947","doi":"10.4018/978-1-60960-818-7.ch420","title":"A Case Study on Scaffolding Adaptive Feedback within Virtual Learning Environments","year":2011,"lang":"en","type":"book-chapter","venue":"Machine Learning","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Process (computing); Representation (politics); Virtual Laboratory; Knowledge representation and reasoning; Human–computer interaction; Domain (mathematical analysis); Domain knowledge; Artificial intelligence; Multimedia","score_opus":0.04625016421813858,"score_gpt":0.2410604903703685,"score_spread":0.19481032615222993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240001947","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051265016,0.00095945643,0.3526115,0.000062588275,0.00422179,0.003350405,0.000012537404,0.0023295998,0.5851871],"genre_scores_gemma":[0.5226366,0.000011561156,0.00062863494,0.00003908323,0.0003060406,0.000021993455,0.000007341621,0.00016051644,0.4761882],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9946795,0.0005760304,0.0010071923,0.0018369865,0.0011017497,0.00079850544],"domain_scores_gemma":[0.9970908,0.00034621457,0.001279222,0.0009118819,0.00007746149,0.00029440207],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015212739,0.0011720596,0.0010322457,0.0006461783,0.0012518809,0.00039098162,0.0011169261,0.00043679457,0.00024988776],"category_scores_gemma":[0.00013301577,0.0011407436,0.00036888802,0.00012485003,0.00008814713,0.0004289875,0.0010723732,0.003774687,0.0014053751],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020720383,0.00052997883,0.0044822088,0.00006834612,0.0015092568,0.04337184,0.060598116,0.11244767,0.00022585859,0.69659716,0.00007396946,0.079888366],"study_design_scores_gemma":[0.005771235,0.035485994,0.0005077434,0.004951409,0.00078715244,0.013856204,0.016689906,0.15840897,0.0005080109,0.0028531284,0.7489788,0.01120145],"about_ca_topic_score_codex":0.0005441986,"about_ca_topic_score_gemma":0.00003655314,"teacher_disagreement_score":0.7489048,"about_ca_system_score_codex":0.0003942969,"about_ca_system_score_gemma":0.00007693499,"threshold_uncertainty_score":0.9993721},"labels":[],"label_agreement":null},{"id":"W4240420143","doi":"10.4018/978-1-60960-818-7.ch708","title":"A Cognitive Computational Knowledge Representation Theory","year":2011,"lang":"en","type":"book-chapter","venue":"Machine Learning","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Representation (politics); Computer science; Cognition; Knowledge representation and reasoning; Cognitive science; Field (mathematics); Cognitive model; Computational model; Artificial intelligence; Psychology; Mathematics","score_opus":0.04657129650791966,"score_gpt":0.2844310450365971,"score_spread":0.23785974852867744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240420143","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000013313827,0.00094941206,0.49813944,0.000018618577,0.00035389807,0.0001547555,0.0000032605096,0.00025671968,0.50011057],"genre_scores_gemma":[0.057223093,0.000030994746,0.0025220416,0.000066030436,0.00037835917,0.000013419983,0.000097236305,0.000075528886,0.9395933],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99793786,0.0002596083,0.00043158702,0.0007279214,0.0003523936,0.00029062663],"domain_scores_gemma":[0.9982012,0.0006295694,0.00047952434,0.0002688565,0.00032414816,0.00009670602],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00069487887,0.00039498668,0.0004040097,0.00031654455,0.00036377102,0.00016830859,0.0005107885,0.00021630866,0.00052004494],"category_scores_gemma":[0.00017205642,0.0003914952,0.0002219386,0.00007394862,0.000063252584,0.0002493888,0.0003866631,0.0010567673,0.0013464014],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015477153,0.000015499925,0.00019032601,0.000031711814,0.00011963321,0.000042349817,0.0027641316,0.0013031748,0.0000034512236,0.93079007,0.00008096606,0.064643234],"study_design_scores_gemma":[0.0006512539,0.00037206043,0.00046811014,0.0015106099,0.00010288486,0.00013107543,0.0000944657,0.047811,0.00005532662,0.25926134,0.6882049,0.0013369735],"about_ca_topic_score_codex":0.00004515485,"about_ca_topic_score_gemma":0.000005888523,"teacher_disagreement_score":0.68812394,"about_ca_system_score_codex":0.00008310265,"about_ca_system_score_gemma":0.000095983814,"threshold_uncertainty_score":0.9998537},"labels":[],"label_agreement":null},{"id":"W4244216214","doi":"10.4018/978-1-60960-818-7.ch109","title":"Adaptive Algorithms for Intelligent Geometric Computing","year":2011,"lang":"en","type":"book-chapter","venue":"Machine Learning","topic":"Computer Graphics and Visualization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Visualization; Computation; Focus (optics); Terrain; Biometrics; Data mining; Algorithm; Artificial intelligence","score_opus":0.06151726145225705,"score_gpt":0.29956108285762567,"score_spread":0.23804382140536862,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244216214","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.926107e-7,0.0012952543,0.9560345,0.00003354402,0.0003962042,0.00043279846,0.000007967354,0.00078021793,0.041018527],"genre_scores_gemma":[0.05918969,0.001726676,0.66660374,0.0010388799,0.0015279851,0.000078981335,0.00037055273,0.0004970054,0.2689665],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980386,0.000040760304,0.000500983,0.00075966667,0.0003157345,0.00034426735],"domain_scores_gemma":[0.998384,0.00026039002,0.0005056185,0.0004431014,0.00029008405,0.00011682171],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00058111537,0.0004291401,0.00047292473,0.0011026775,0.00027872474,0.00020538636,0.001094306,0.00025016503,0.000057416684],"category_scores_gemma":[0.000045599918,0.0004349994,0.0003102395,0.00026326932,0.000043693635,0.00013358862,0.00085931324,0.00063109613,0.00002695541],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030221006,0.000013557303,0.000029380994,0.000031202006,0.00005286253,0.0000055995424,0.00035100736,0.00006110818,3.137041e-7,0.69888777,0.000280572,0.30028364],"study_design_scores_gemma":[0.0001433425,0.0005288136,0.000014462946,0.00015435612,0.000023223965,0.0000133005115,0.0000027417998,0.66354334,0.000073102456,0.077026054,0.25792453,0.0005527179],"about_ca_topic_score_codex":0.000043925702,"about_ca_topic_score_gemma":0.0000032941205,"teacher_disagreement_score":0.66348225,"about_ca_system_score_codex":0.00006640737,"about_ca_system_score_gemma":0.000051372746,"threshold_uncertainty_score":0.99981016},"labels":[],"label_agreement":null},{"id":"W4247922211","doi":"10.4018/978-1-60960-818-7.ch609","title":"Forecasting Supply Chain Demand Using Machine Learning Algorithms","year":2011,"lang":"en","type":"book-chapter","venue":"Machine Learning","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"HEC Montréal","funders":"","keywords":"Supply chain; Ranking (information retrieval); Computer science; Demand forecasting; Quality (philosophy); Support vector machine; Supply and demand; Machine learning; Competition (biology); Noise (video); Artificial intelligence; Supply chain management; Distortion (music); Demand management; Operations research; Algorithm; Engineering; Marketing; Business; Economics; Microeconomics","score_opus":0.1585308921770113,"score_gpt":0.3428885349061645,"score_spread":0.1843576427291532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247922211","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038827735,0.0049046096,0.22808653,0.00055449444,0.00073597336,0.0017115382,0.0002423558,0.0019867108,0.757895],"genre_scores_gemma":[0.12236051,0.00027804312,0.076206036,0.00019507641,0.0010282655,0.000052170864,0.00040857354,0.00053317443,0.79893816],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9941201,0.00027076906,0.0016485142,0.0015651735,0.001570061,0.00082534296],"domain_scores_gemma":[0.99520415,0.0011722032,0.0018988216,0.00096938264,0.00044055184,0.00031489812],"candidate_categories":["metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004765304,0.00090554974,0.0011740617,0.00097217277,0.0014956539,0.00049125403,0.0014448721,0.0006327452,0.0040584626],"category_scores_gemma":[0.0021612297,0.00078206614,0.00055947,0.00037400375,0.0002605,0.00026210133,0.001075605,0.0029393542,0.00034955656],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015088652,0.000121551086,0.024767088,0.0001436857,0.00034037002,0.00037510507,0.0026352247,0.02260477,0.00057289016,0.06624868,0.0023927733,0.87964696],"study_design_scores_gemma":[0.00023897887,0.0001823472,0.000031600448,0.00028146544,0.00008362689,0.00021800847,0.000024834828,0.57664025,0.00007764788,0.044714,0.37676346,0.0007437942],"about_ca_topic_score_codex":0.0009040375,"about_ca_topic_score_gemma":0.00019733228,"teacher_disagreement_score":0.8789032,"about_ca_system_score_codex":0.00015729213,"about_ca_system_score_gemma":0.00010880922,"threshold_uncertainty_score":0.99980426},"labels":[],"label_agreement":null},{"id":"W4280576960","doi":"10.1007/s10994-022-06172-1","title":"MAGMA: inference and prediction using multi-task Gaussian processes with common mean","year":2022,"lang":"en","type":"article","venue":"Machine Learning","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Army Research Laboratory; Army Research Office; Engineering and Physical Sciences Research Council; CHIST-ERA; Agence Nationale de la Recherche","keywords":"Gaussian process; Computer science; Task (project management); Inference; Computation; Process (computing); Gaussian; Machine learning; Data mining; Artificial intelligence; Algorithm","score_opus":0.016205121222673265,"score_gpt":0.24954763735420707,"score_spread":0.2333425161315338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280576960","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18572912,0.00059575855,0.8118972,0.00047821578,0.00009480599,0.00020320644,0.000011779809,0.00037801237,0.00061189407],"genre_scores_gemma":[0.9710103,0.000025790825,0.028595356,0.00012291415,0.000026123063,0.000027161783,0.0000124779735,0.000018843206,0.00016100905],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998488,0.00014013369,0.00021179407,0.0004966969,0.00034709636,0.0003162892],"domain_scores_gemma":[0.9993068,0.00008415734,0.00018553948,0.00025470334,0.000063330604,0.0001054593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025802432,0.00020097136,0.000197286,0.000148594,0.0010160764,0.00029979562,0.00049593486,0.000031779913,0.00003796536],"category_scores_gemma":[0.000066447916,0.00017184492,0.000018816218,0.0007323174,0.00006105073,0.00058395235,0.0005710917,0.0005250393,0.0000023659386],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000071162445,0.00028017908,0.88922274,0.00063644594,0.000059718306,0.00015605526,0.010286181,0.040616654,0.0016001863,0.0070961122,0.000020346442,0.04995423],"study_design_scores_gemma":[0.0008841723,0.00065888476,0.02761789,0.00011332813,0.000026128726,0.00040093795,0.00038669314,0.96607155,0.00022148904,0.0007527741,0.0024298031,0.00043635102],"about_ca_topic_score_codex":0.00028449149,"about_ca_topic_score_gemma":0.00023625341,"teacher_disagreement_score":0.9254549,"about_ca_system_score_codex":0.00005335706,"about_ca_system_score_gemma":0.00018636571,"threshold_uncertainty_score":0.78149414},"labels":[],"label_agreement":null},{"id":"W4286632124","doi":"10.1007/s10994-022-06191-y","title":"Improving fairness generalization through a sample-robust optimization method","year":2022,"lang":"en","type":"article","venue":"Machine Learning","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; École de Technologie Supérieure","funders":"Canada Research Chairs; Centre International de Mathématiques et Informatique de Toulouse; Agence Nationale de la Recherche","keywords":"Computer science; Robustness (evolution); Machine learning; Scalability; Artificial intelligence; Generalization; Fairness measure; Heuristic; Metric (unit); Set (abstract data type); Generalization error; Artificial neural network; Throughput; Mathematics","score_opus":0.04930835796936283,"score_gpt":0.36396374213362154,"score_spread":0.3146553841642587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286632124","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025266455,0.00014106822,0.97820723,0.005898884,0.00037014228,0.00019271663,0.0000112023845,0.00022596485,0.012426174],"genre_scores_gemma":[0.70195806,0.00016540842,0.2905459,0.00243998,0.0007364126,0.000059373207,0.00027451836,0.00007187079,0.003748477],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997317,0.0014049171,0.00018539307,0.00023578176,0.00053966517,0.00031721656],"domain_scores_gemma":[0.9991289,0.00037295616,0.0001878856,0.00009690522,0.00014445232,0.0000689505],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0024960828,0.00010236391,0.00014369744,0.00006496764,0.004227643,0.0002536459,0.00022632598,0.00007992243,0.0012603534],"category_scores_gemma":[0.0025759116,0.0001170135,0.00006652403,0.00052749406,0.000062877,0.00046523625,0.00016677754,0.0005484383,0.000002216869],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000069049156,0.000021075519,0.0021621287,0.00000685319,0.000009655364,0.0000017425548,0.0315007,0.91117316,0.00006748178,0.049083296,0.000083205516,0.0058837985],"study_design_scores_gemma":[0.0003926461,0.00010168988,0.00010380905,0.000006503498,0.000031598007,0.0000016156075,0.013923737,0.879012,0.000022404156,0.008235883,0.09783359,0.00033453008],"about_ca_topic_score_codex":0.05063549,"about_ca_topic_score_gemma":0.0015730937,"teacher_disagreement_score":0.6994314,"about_ca_system_score_codex":0.00021575268,"about_ca_system_score_gemma":0.0001739304,"threshold_uncertainty_score":0.9996526},"labels":[],"label_agreement":null},{"id":"W4297691576","doi":"10.1007/s10994-022-06212-w","title":"Speeding up neural network robustness verification via algorithm configuration and an optimised mixed integer linear programming solver portfolio","year":2022,"lang":"en","type":"article","venue":"Machine Learning","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Robustness (evolution); Artificial neural network; Solver; Algorithm; Linear programming; Integer programming; Scalability; Machine learning; Artificial intelligence; Programming language; Database","score_opus":0.01773640680379212,"score_gpt":0.26762500283110385,"score_spread":0.24988859602731173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297691576","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019813288,0.00017680154,0.9768093,0.0004154862,0.0014768089,0.00040891167,0.0000013235953,0.00067966344,0.00021841502],"genre_scores_gemma":[0.7390056,0.000007797985,0.25937155,0.0001584713,0.0006536735,0.00007717532,0.00020341601,0.00006914875,0.00045315514],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964378,0.0007983021,0.00053022045,0.0009301168,0.0006396333,0.00066395185],"domain_scores_gemma":[0.9985351,0.0001668696,0.0004817272,0.0004890618,0.00012862471,0.00019863053],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0017349228,0.0003731235,0.00037260927,0.00023894524,0.0018262044,0.00041378316,0.0008156601,0.00010161362,0.00017839714],"category_scores_gemma":[0.00016968831,0.00041111113,0.00009155775,0.0008835448,0.00007733674,0.0012417417,0.0008246914,0.0014998866,0.000004708365],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028004422,0.00003145326,0.0019436873,0.000009915747,0.000019735518,0.000022441374,0.0007772754,0.74651766,0.00019512491,0.0006944568,0.000041856867,0.24971841],"study_design_scores_gemma":[0.00078909745,0.00026520062,0.0007259107,0.000013690885,0.000027688882,0.000096330536,0.00031559326,0.9913703,0.000058710044,0.000106918764,0.0057713757,0.00045914235],"about_ca_topic_score_codex":0.00019559194,"about_ca_topic_score_gemma":0.0000070163424,"teacher_disagreement_score":0.7191923,"about_ca_system_score_codex":0.000144422,"about_ca_system_score_gemma":0.00006178239,"threshold_uncertainty_score":0.99983406},"labels":[],"label_agreement":null},{"id":"W4313421115","doi":"10.1007/s10994-022-06282-w","title":"Automated imbalanced classification via layered learning","year":2022,"lang":"en","type":"article","venue":"Machine Learning","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; University of Ottawa; Dalhousie University","funders":"Canada Research Chairs","keywords":"Overfitting; Artificial intelligence; Computer science; Machine learning; Decision boundary; Cluster analysis; Resampling; Benchmark (surveying); Class (philosophy); Binary classification; Data mining; Oversampling; Pattern recognition (psychology); Support vector machine; Artificial neural network","score_opus":0.016691511570374844,"score_gpt":0.2665123368446004,"score_spread":0.24982082527422556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313421115","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009930589,0.00012321069,0.9730046,0.0017282062,0.00027488562,0.00029988374,0.000007740566,0.010606279,0.004024646],"genre_scores_gemma":[0.9669545,0.000013022086,0.030677391,0.000274288,0.000037672806,0.00019305304,0.00028137237,0.000034393754,0.0015342585],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99733204,0.00071378896,0.00038187453,0.000636253,0.0005373704,0.00039866279],"domain_scores_gemma":[0.99864763,0.00012603874,0.00038487779,0.00067705964,0.000080253805,0.00008411343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009349755,0.0002051699,0.00021973324,0.0002729133,0.0011489181,0.00017983821,0.0012954049,0.000056372242,0.00019060777],"category_scores_gemma":[0.00021344634,0.00022940552,0.00007065932,0.0010140262,0.000034854747,0.0004761965,0.00079548196,0.0010066384,0.00009646784],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000082844505,0.00044651818,0.09495447,0.000070718226,0.000103609345,0.000076505894,0.0035365035,0.10885536,0.44034752,0.05093165,0.009484034,0.29111025],"study_design_scores_gemma":[0.00028510852,0.00013288984,0.015030418,0.000004700892,0.000003425651,0.000038694452,0.000063897605,0.90038586,0.0014009076,0.0003263898,0.082074136,0.00025358298],"about_ca_topic_score_codex":0.00006474913,"about_ca_topic_score_gemma":0.0000028168379,"teacher_disagreement_score":0.957024,"about_ca_system_score_codex":0.00023708762,"about_ca_system_score_gemma":0.00005948366,"threshold_uncertainty_score":0.9354885},"labels":[],"label_agreement":null},{"id":"W4313421210","doi":"10.1007/s10994-022-06268-8","title":"The class imbalance problem in deep learning","year":2022,"lang":"en","type":"article","venue":"Machine Learning","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":270,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; National Research Council Canada; University of Alberta","funders":"","keywords":"Artificial intelligence; Deep learning; Computer science; Machine learning; Class (philosophy); Context (archaeology)","score_opus":0.007893058798280584,"score_gpt":0.2351205030355744,"score_spread":0.22722744423729382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313421210","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016878983,0.0023672471,0.93469894,0.014269397,0.0005359176,0.0009831137,0.000005267758,0.0032665855,0.02699455],"genre_scores_gemma":[0.97917527,0.000076776036,0.017633988,0.00027232958,0.000027873273,0.00025959357,0.00002543767,0.000021608002,0.0025071148],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977947,0.000683082,0.00029896785,0.00042141398,0.00039907306,0.0004028009],"domain_scores_gemma":[0.99893445,0.00027693596,0.00021176513,0.000503498,0.00003239681,0.000040945062],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001594122,0.00013668288,0.00013848103,0.00013023999,0.0012278405,0.00021338221,0.0015562477,0.00002933665,0.000033992503],"category_scores_gemma":[0.00021618223,0.00011778397,0.00004187259,0.0008189601,0.00004274244,0.000287173,0.0010787491,0.0013303531,0.000025589365],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003796087,0.00013185722,0.25378188,0.00002802194,0.000021857964,0.000064633365,0.0032148256,0.11169622,0.0058720927,0.15799898,0.0013897537,0.46576193],"study_design_scores_gemma":[0.00019433776,0.00009053003,0.008757674,0.0000059059703,9.981333e-7,0.00002240645,0.00012486012,0.60501,0.00016435425,0.001644659,0.38382113,0.00016317861],"about_ca_topic_score_codex":0.000076874174,"about_ca_topic_score_gemma":0.000044139288,"teacher_disagreement_score":0.9622963,"about_ca_system_score_codex":0.00018045653,"about_ca_system_score_gemma":0.00003920694,"threshold_uncertainty_score":0.9443681},"labels":[],"label_agreement":null},{"id":"W4321016149","doi":"10.1007/s10994-023-06305-0","title":"Diverse and consistent multi-view networks for semi-supervised regression","year":2023,"lang":"en","type":"article","venue":"Machine Learning","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto; University of New Brunswick","funders":"Institute for Infocomm Research; Agency for Science, Technology and Research","keywords":"DICOM; Computer science; Consistency (knowledge bases); Probabilistic logic; Artificial intelligence; Machine learning; Graphical model; Data mining; Regression; Mathematics","score_opus":0.04672530729582696,"score_gpt":0.29844873456331644,"score_spread":0.2517234272674895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321016149","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02200254,0.0012194195,0.9716623,0.0028931277,0.00039598046,0.00038050418,0.000008172188,0.0011561625,0.00028181376],"genre_scores_gemma":[0.95884115,0.0006973069,0.035926864,0.00039259368,0.00013585643,0.000069756825,0.0003844895,0.000034660643,0.0035173448],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986619,0.00019928087,0.00020597501,0.00047576573,0.00015676527,0.00030034865],"domain_scores_gemma":[0.9990568,0.00030712248,0.0001196333,0.0003556397,0.00005101773,0.00010976546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075689144,0.00016286156,0.00019295746,0.00012762076,0.00051143364,0.00017787129,0.00033684098,0.00007357347,0.000012237316],"category_scores_gemma":[0.00038609153,0.00013449443,0.00006190749,0.00038899097,0.00003442406,0.00022211277,0.00039244743,0.00029545827,0.00003826501],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002615571,0.000057698868,0.07696668,0.00015288599,0.000033630335,0.000018724137,0.0009518779,0.023479534,0.00071179436,0.004810042,0.002599133,0.89019185],"study_design_scores_gemma":[0.0006557015,0.000060453953,0.019230654,0.00006174268,0.00000995136,0.000007509839,0.00007655073,0.9267289,0.000010384869,0.000048243335,0.05295243,0.00015744807],"about_ca_topic_score_codex":0.000063382395,"about_ca_topic_score_gemma":0.000021913,"teacher_disagreement_score":0.93683857,"about_ca_system_score_codex":0.000017793564,"about_ca_system_score_gemma":0.000016008373,"threshold_uncertainty_score":0.5484524},"labels":[],"label_agreement":null},{"id":"W4364381349","doi":"10.1007/s10994-023-06326-9","title":"Understanding CNN fragility when learning with imbalanced data","year":2023,"lang":"en","type":"article","venue":"Machine Learning","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"Office of Naval Research","keywords":"Convolutional neural network; Class (philosophy); Artificial intelligence; Computer science; Feature (linguistics); Focus (optics); Pattern recognition (psychology); Set (abstract data type); Machine learning; Image (mathematics)","score_opus":0.14952743444589864,"score_gpt":0.30261477515111007,"score_spread":0.15308734070521143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4364381349","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025296859,0.000036475645,0.98738486,0.0020168193,0.00008950529,0.00017166979,0.000011432226,0.0039536622,0.0038058937],"genre_scores_gemma":[0.9279655,0.000045511748,0.06925254,0.00015357012,0.00006118517,0.000021379787,0.0006673097,0.000038685474,0.0017943165],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976045,0.00028135133,0.0002697555,0.0008801569,0.00047874937,0.00048549825],"domain_scores_gemma":[0.9978097,0.0002592376,0.00021043222,0.0015688682,0.00005287277,0.00009887269],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013867014,0.00021483879,0.00023715949,0.00023855126,0.0005575525,0.00034323902,0.002092936,0.00007623041,0.000048502006],"category_scores_gemma":[0.00044781383,0.00019092903,0.000028580731,0.0010137912,0.000076593475,0.0011482297,0.0014251599,0.0007737989,0.0001629912],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015517803,0.00019826695,0.6480634,0.0003277371,0.00028611603,0.00034947862,0.008970428,0.024839967,0.017001318,0.15444791,0.032385536,0.11297463],"study_design_scores_gemma":[0.00043101516,0.00013281727,0.009986797,0.00006458494,0.00000898988,0.000017494418,0.00022839895,0.927022,0.00053162687,0.004402128,0.05677562,0.00039856107],"about_ca_topic_score_codex":0.00008095434,"about_ca_topic_score_gemma":0.000030035104,"teacher_disagreement_score":0.92543584,"about_ca_system_score_codex":0.00014270683,"about_ca_system_score_gemma":0.00006486328,"threshold_uncertainty_score":0.778586},"labels":[],"label_agreement":null},{"id":"W4376636921","doi":"10.1007/s10994-023-06332-x","title":"Federated learning with superquantile aggregation for heterogeneous data","year":2023,"lang":"en","type":"article","venue":"Machine Learning","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institute for Advanced Research; Agence Nationale de la Recherche; National Science Foundation","keywords":"Computer science; Artificial intelligence; Machine learning","score_opus":0.05211959121355498,"score_gpt":0.29835848739190035,"score_spread":0.24623889617834538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376636921","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11102267,0.00020144253,0.8730082,0.008954454,0.00019441529,0.000373254,0.000033010958,0.006027972,0.00018457069],"genre_scores_gemma":[0.8753595,0.00005968304,0.12263058,0.000076836455,0.000054271713,0.00004460791,0.0013258704,0.000050202307,0.0003984797],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980134,0.00013517746,0.00022111548,0.00082766445,0.00030296223,0.0004997158],"domain_scores_gemma":[0.9959737,0.00038436017,0.00013614201,0.0033746278,0.00007684566,0.0000542961],"candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00084845617,0.00019958572,0.00020470555,0.00022372551,0.00068687217,0.00045633694,0.011604865,0.000096092335,0.000013634592],"category_scores_gemma":[0.014741298,0.00017721162,0.000030453382,0.00097130705,0.000048823807,0.0008052365,0.03599026,0.00047904623,0.00008551334],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014343708,0.00010447933,0.0695785,0.00024418786,0.00027001635,0.00033561524,0.00046754393,0.07486783,0.0060232016,0.0010079687,0.06530562,0.7816516],"study_design_scores_gemma":[0.00039898232,0.00020940753,0.00028038258,0.00004404278,0.00000756834,0.00003976725,0.000028942744,0.9714201,0.0016538233,0.0016672843,0.024016697,0.0002329846],"about_ca_topic_score_codex":0.00008871883,"about_ca_topic_score_gemma":0.000070152215,"teacher_disagreement_score":0.89655226,"about_ca_system_score_codex":0.000036422396,"about_ca_system_score_gemma":0.00004645877,"threshold_uncertainty_score":0.9937428},"labels":[],"label_agreement":null},{"id":"W4386126338","doi":"10.1007/s10994-023-06368-z","title":"Cautious policy programming: exploiting KL regularization for monotonic policy improvement in reinforcement learning","year":2023,"lang":"en","type":"article","venue":"Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Japan Society for the Promotion of Science","keywords":"Reinforcement learning; Monotonic function; Computer science; Mathematical optimization; Regularization (linguistics); Bellman equation; Entropy (arrow of time); Maximization; Upper and lower bounds; Exploit; Artificial intelligence; Mathematics","score_opus":0.017741848969039416,"score_gpt":0.2845911047478464,"score_spread":0.26684925577880697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386126338","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0110484725,0.00004146834,0.9820335,0.0023141736,0.00018918801,0.0012707292,4.9940707e-7,0.0014688879,0.0016330769],"genre_scores_gemma":[0.97342724,0.000081385086,0.013475663,0.00026140906,0.00034145504,0.0004352007,0.0001714327,0.0000896411,0.011716554],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99629915,0.00018813222,0.00083687104,0.0007455106,0.00064096734,0.0012893492],"domain_scores_gemma":[0.99840784,0.00025492333,0.0005125187,0.00052582665,0.00013415693,0.00016474414],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016207938,0.00038847976,0.00037628587,0.001513009,0.0007072092,0.00048120605,0.00082759955,0.00014846823,0.000007689317],"category_scores_gemma":[0.0020856345,0.00042440154,0.00013539505,0.0029763384,0.00004557974,0.0005990695,0.00076985604,0.0007320837,0.00006062848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012706826,0.000016148872,0.004871021,0.0000923164,0.000025271258,0.000009722112,0.002248586,0.89706147,0.0012234851,0.024919651,0.000020754394,0.06949887],"study_design_scores_gemma":[0.0011907064,0.0006953932,0.00095463457,0.00009464132,0.000008343748,0.0000058344567,0.0002380562,0.9772773,0.00057432905,0.0006633642,0.017874127,0.0004233024],"about_ca_topic_score_codex":0.0007558073,"about_ca_topic_score_gemma":0.000025527042,"teacher_disagreement_score":0.96855783,"about_ca_system_score_codex":0.00070828036,"about_ca_system_score_gemma":0.0003482175,"threshold_uncertainty_score":0.99982077},"labels":[],"label_agreement":null},{"id":"W4386838733","doi":"10.1007/s10994-023-06391-0","title":"A general framework for the practical disintegration of PAC-Bayesian bounds","year":2023,"lang":"en","type":"article","venue":"Machine Learning","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Agence Nationale de la Recherche; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Generalization; Computer science; Bayesian probability; Artificial neural network; Artificial intelligence; Generalization error; Bayesian network; Machine learning; Algorithm; Mathematics","score_opus":0.022321818771002738,"score_gpt":0.33163513537195954,"score_spread":0.3093133166009568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386838733","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005282594,0.00008473445,0.9792858,0.014181693,0.00038558163,0.00015732231,0.0000024416572,0.0003288664,0.00029100297],"genre_scores_gemma":[0.7476931,0.000023360793,0.24939007,0.00023960501,0.00040227157,0.000029223202,0.00002603063,0.00002491351,0.0021714282],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986961,0.00019472209,0.00023137963,0.00028904068,0.00028828747,0.0003004801],"domain_scores_gemma":[0.9979653,0.0013931592,0.00016483903,0.0003582306,0.00006238577,0.000056118537],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010074669,0.00013621434,0.00016969055,0.0001037861,0.0004496594,0.00019905657,0.00043173024,0.000072486575,0.00002431538],"category_scores_gemma":[0.001682953,0.00009042491,0.00012434737,0.0006522961,0.00004904868,0.00017280233,0.0001620762,0.0005748645,0.000021728547],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037647096,0.00006900111,0.01318367,0.00005744406,0.000085302,0.000015436144,0.0038842962,0.04050262,0.00045173062,0.61366814,0.0018496296,0.32619506],"study_design_scores_gemma":[0.00016629462,0.00014663114,0.0033159575,0.000021957556,0.000011607347,0.000011363496,0.00007657203,0.958629,0.00009878999,0.014502614,0.02290826,0.00011095128],"about_ca_topic_score_codex":0.0001514714,"about_ca_topic_score_gemma":0.000013666377,"teacher_disagreement_score":0.9181264,"about_ca_system_score_codex":0.000016066175,"about_ca_system_score_gemma":0.000051730203,"threshold_uncertainty_score":0.36874208},"labels":[],"label_agreement":null},{"id":"W4388488218","doi":"10.1007/s10994-023-06413-x","title":"GVFs in the real world: making predictions online for water treatment","year":2023,"lang":"en","type":"article","venue":"Machine Learning","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research; University of Alberta","funders":"Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Observability; Computer science; Hyperparameter; Reinforcement learning; Predictability; Artificial intelligence; Machine learning; Online learning; Artificial neural network; Software deployment; Online and offline; Data mining; Mathematics; Statistics","score_opus":0.04528288908384457,"score_gpt":0.3443340184857532,"score_spread":0.2990511294019086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388488218","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4675306,0.000087492626,0.47537845,0.033640534,0.00079619914,0.0022859382,0.00023246618,0.008571021,0.011477291],"genre_scores_gemma":[0.9458976,0.00003087991,0.050573457,0.0002304769,0.00014649276,0.00023892564,0.00044475833,0.000022269947,0.0024151413],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898285,0.00011471842,0.00017271654,0.00028180014,0.0001375502,0.00031035847],"domain_scores_gemma":[0.9993082,0.0002196825,0.000039050363,0.00039946593,0.000014161129,0.000019387031],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005061733,0.00011718154,0.000116180214,0.00030307277,0.00021747945,0.00012799398,0.0006080284,0.00002626428,0.00000796268],"category_scores_gemma":[0.00004982693,0.00006971222,0.0000514102,0.00053972483,0.000017005681,0.00021737641,0.00022386135,0.00015893676,0.000021070717],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006763389,0.00073743897,0.15376078,0.00007224898,0.000118963166,0.00028678228,0.03325463,0.02585104,0.0023246743,0.046199247,0.012089098,0.7252375],"study_design_scores_gemma":[0.00053559424,0.00045155277,0.018315166,0.00006799349,0.000015543868,0.000012425019,0.00016522665,0.77405816,0.00062437454,0.0022841562,0.20325623,0.00021357414],"about_ca_topic_score_codex":0.00030792868,"about_ca_topic_score_gemma":0.0007662933,"teacher_disagreement_score":0.7482071,"about_ca_system_score_codex":0.000065438806,"about_ca_system_score_gemma":0.0000134542815,"threshold_uncertainty_score":0.2842782},"labels":[],"label_agreement":null},{"id":"W4389074848","doi":"10.1007/s10994-023-06460-4","title":"Multi-agent reinforcement learning for fast-timescale demand response of residential loads","year":2023,"lang":"en","type":"article","venue":"Machine Learning","topic":"Smart Grid Energy Management","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Group for Research in Decision Analysis; Université de Montréal; Polytechnique Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Natural Sciences and Engineering Research Council of Canada; Samsung; Institut de Valorisation des Données; Microsoft Research","keywords":"Reinforcement learning; Computer science; Demand response; Renewable energy; Distributed computing; Power (physics); Artificial intelligence; Engineering; Electrical engineering; Electricity","score_opus":0.01256083026442792,"score_gpt":0.24168967895844878,"score_spread":0.22912884869402086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389074848","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6075171,0.0002676276,0.3884405,0.0001571841,0.00080652075,0.00049889705,0.00000362073,0.0014260482,0.00088248047],"genre_scores_gemma":[0.9829456,0.00007661959,0.0021292858,0.000016082706,0.00013379495,0.0000937915,0.00009296183,0.00009784589,0.014414022],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837303,0.00015058092,0.0004409916,0.0002665637,0.0002989005,0.0004699039],"domain_scores_gemma":[0.9992807,0.00025447118,0.00009385261,0.00024056279,0.000044792163,0.00008561288],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012133769,0.00023220392,0.00028345754,0.00038862517,0.00019164999,0.000040947845,0.00020542875,0.00007877451,0.00013725933],"category_scores_gemma":[0.0003869203,0.00025236944,0.00014337561,0.00041175014,0.000029696797,0.00010108213,0.0001878374,0.00028480185,0.0001058407],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020161239,0.00001023163,0.0041576023,0.00015835045,0.00011010813,0.000011844626,0.00061046483,0.96694547,0.024855325,0.000024876015,0.0017042215,0.001209868],"study_design_scores_gemma":[0.0011849427,0.00016289236,0.013125025,0.000056359193,0.000040572148,0.0000016612905,0.00016820093,0.93442655,0.0077627357,0.000005450216,0.042823996,0.00024163598],"about_ca_topic_score_codex":0.000058252073,"about_ca_topic_score_gemma":0.000020898335,"teacher_disagreement_score":0.3863112,"about_ca_system_score_codex":0.00009503617,"about_ca_system_score_gemma":0.000013121608,"threshold_uncertainty_score":0.99999285},"labels":[],"label_agreement":null},{"id":"W4389914665","doi":"10.1007/s10994-023-06410-0","title":"Heterogeneous multi-task feature learning with mixed $$\\ell _{2,1}$$ regularization","year":2023,"lang":"en","type":"article","venue":"Machine Learning","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Regularization (linguistics); Multi-task learning; Artificial intelligence; Computer science; Pattern recognition (psychology); Task (project management); Machine learning; Feature (linguistics); Feature learning; Mathematics; Engineering","score_opus":0.01001073199106917,"score_gpt":0.21192493207020055,"score_spread":0.20191420007913138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389914665","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.767717,0.0012209143,0.20863697,0.0002791415,0.0004185641,0.00045459444,0.000005591369,0.018335663,0.0029315678],"genre_scores_gemma":[0.9919884,0.00009162866,0.0040237363,0.000028023835,0.00008813204,0.000013307581,0.0001653679,0.00012269868,0.0034786912],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99897736,0.00009331572,0.00013464542,0.00025984476,0.00018763382,0.0003471674],"domain_scores_gemma":[0.999589,0.000047494417,0.000052045525,0.00020084249,0.00004534645,0.00006526287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013211812,0.00023514709,0.0002063623,0.00019483444,0.00022345662,0.00008155008,0.00013040005,0.00012488628,0.000018806573],"category_scores_gemma":[0.00005245339,0.00021650038,0.000056236822,0.00048625265,0.000027784232,0.000083517065,0.000061563216,0.00062607735,0.000075638156],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000132971,0.000007389858,0.0046548517,0.000022773378,0.000050483544,0.000100633275,0.00028858663,0.9637915,0.02207803,0.000015959835,0.0006038348,0.008372674],"study_design_scores_gemma":[0.00033947598,0.00009573809,0.002067372,0.0000925482,0.000023589067,0.000054379296,0.00004649257,0.9485891,0.019460306,0.000034011755,0.028880445,0.00031654353],"about_ca_topic_score_codex":0.000022787757,"about_ca_topic_score_gemma":0.000030893872,"teacher_disagreement_score":0.22427142,"about_ca_system_score_codex":0.000035219156,"about_ca_system_score_gemma":0.0000067580963,"threshold_uncertainty_score":0.8828629},"labels":[],"label_agreement":null},{"id":"W4390906071","doi":"10.1007/s10994-023-06414-w","title":"Understanding imbalanced data: XAI & interpretable ML framework","year":2024,"lang":"en","type":"article","venue":"Machine Learning","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Class (philosophy); Deep learning; Focus (optics); Key (lock); Outlier; Set (abstract data type); Data mining","score_opus":0.13825777887594604,"score_gpt":0.34134489256745015,"score_spread":0.20308711369150412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390906071","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012048605,0.0007508159,0.98861897,0.0021495542,0.00059775496,0.000116666146,0.000023943203,0.0027396309,0.004882169],"genre_scores_gemma":[0.7488422,0.00011034758,0.24874432,0.00031201108,0.00013204264,0.000015349011,0.00024377866,0.00003440879,0.0015655779],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981203,0.00013696177,0.00027430075,0.00080330746,0.00030338022,0.0003617276],"domain_scores_gemma":[0.9978846,0.00036529676,0.00008102619,0.001566554,0.00002491175,0.000077666446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082355534,0.00019066769,0.00019319839,0.00021231074,0.00023278703,0.000984968,0.0019915842,0.00010400311,0.00010836559],"category_scores_gemma":[0.0004777203,0.00017882432,0.000044515516,0.0007616716,0.00004892865,0.0014871377,0.0012353543,0.00085869286,0.0002820563],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011997179,0.000048312853,0.00474761,0.00018780034,0.00010072462,0.00005380204,0.0021209035,0.00077160954,0.005558932,0.9098765,0.030439511,0.046082254],"study_design_scores_gemma":[0.000062707266,0.000027714656,0.0001446939,0.0002786042,0.000008681578,0.000026989921,0.000028506012,0.6696479,0.00027210845,0.031692836,0.29753992,0.00026939905],"about_ca_topic_score_codex":0.0000364906,"about_ca_topic_score_gemma":0.000014545294,"teacher_disagreement_score":0.8781837,"about_ca_system_score_codex":0.00019607985,"about_ca_system_score_gemma":0.0000627634,"threshold_uncertainty_score":0.9498069},"labels":[],"label_agreement":null},{"id":"W4391127911","doi":"10.1007/s10994-023-06497-5","title":"Empirical analysis of performance assessment for imbalanced classification","year":2024,"lang":"en","type":"article","venue":"Machine Learning","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Machine learning; Computer science","score_opus":0.0385424843247923,"score_gpt":0.3639158091002024,"score_spread":0.3253733247754101,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391127911","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011922346,0.00009733842,0.9847929,0.001092578,0.00009992925,0.00016567751,0.000017173643,0.00057984225,0.0012321967],"genre_scores_gemma":[0.8673596,0.00003926843,0.13195364,0.000056456545,0.000022567843,0.00008065172,0.00018188504,0.000009805745,0.0002961593],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987916,0.00007597259,0.0003221052,0.00040273066,0.00023450129,0.00017308648],"domain_scores_gemma":[0.99905354,0.00023412077,0.00012558923,0.00045416437,0.00009603596,0.00003652575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006608437,0.00010982012,0.00022526411,0.000476814,0.00009858361,0.0001301749,0.0005084097,0.000054643853,0.000017745631],"category_scores_gemma":[0.00007636415,0.00009833213,0.00012772673,0.001575593,0.000030184667,0.00037982367,0.00009610483,0.00019652191,0.000005518411],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002011132,0.00014203586,0.36502075,0.00036865342,0.0007687629,0.0000024307085,0.00097072095,0.0071099363,0.046565462,0.1615127,0.0015208917,0.41599753],"study_design_scores_gemma":[0.000061674225,0.00007099031,0.12883644,0.00001801263,0.00007347651,8.2698557e-7,0.0000069576513,0.8422994,0.0016335867,0.0001761679,0.026729718,0.00009273946],"about_ca_topic_score_codex":0.000005158606,"about_ca_topic_score_gemma":0.0000024044139,"teacher_disagreement_score":0.8554372,"about_ca_system_score_codex":0.000085259126,"about_ca_system_score_gemma":0.00006897278,"threshold_uncertainty_score":0.4009868},"labels":[],"label_agreement":null},{"id":"W4392094980","doi":"10.1007/s10994-024-06514-1","title":"Correction to: Multi-agent reinforcement learning for fast-timescale demand response of residential loads","year":2024,"lang":"en","type":"article","venue":"Machine Learning","topic":"Smart Grid Energy Management","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Group for Research in Decision Analysis; Université de Montréal; Polytechnique Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Reinforcement learning; Computer science; Reinforcement; Demand response; Artificial intelligence; Engineering; Structural engineering; Electrical engineering","score_opus":0.00856574228745731,"score_gpt":0.2416009840240008,"score_spread":0.2330352417365435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392094980","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13430054,0.00054462417,0.8592755,0.00010849796,0.003624133,0.00037688515,0.0000016213125,0.0007922527,0.0009759217],"genre_scores_gemma":[0.97270375,0.00003561652,0.002014404,0.000019395138,0.00021511328,0.00009239851,0.000036476267,0.00008724032,0.02479561],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865127,0.000116850184,0.0003765972,0.00028478005,0.00024067608,0.00032984602],"domain_scores_gemma":[0.99938023,0.00028072542,0.000041665833,0.00017014162,0.00003915005,0.00008807988],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008762412,0.00021169746,0.00021886834,0.00037544777,0.00013529063,0.00008616098,0.00013064368,0.000057467663,0.00014798314],"category_scores_gemma":[0.00037707726,0.00022614823,0.0001287674,0.00032230146,0.000015586,0.00011607237,0.00011080001,0.00033380892,0.00007227862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021626221,0.000009535532,0.0008812382,0.00019079109,0.00010972877,0.000009224848,0.00094129966,0.9675601,0.018946912,0.000028155475,0.0058520245,0.0052547096],"study_design_scores_gemma":[0.00039874224,0.00024084497,0.0024497486,0.00018797042,0.000049023394,0.0000041980334,0.00011690237,0.8943477,0.010987769,0.0000024044357,0.0910089,0.0002057628],"about_ca_topic_score_codex":0.0001110438,"about_ca_topic_score_gemma":0.00004812237,"teacher_disagreement_score":0.8572611,"about_ca_system_score_codex":0.00018105471,"about_ca_system_score_gemma":0.0000170798,"threshold_uncertainty_score":0.92220575},"labels":[],"label_agreement":null},{"id":"W4400073212","doi":"10.1007/s10994-024-06541-y","title":"Secure and fast asynchronous Vertical Federated Learning via cascaded hybrid optimization","year":2024,"lang":"en","type":"article","venue":"Machine Learning","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Asynchronous communication; Asynchronous learning; Distributed computing; Artificial intelligence; Computer network; Mathematics; Synchronous learning; Cooperative learning; Mathematics education","score_opus":0.009790899163707976,"score_gpt":0.24336011641232386,"score_spread":0.23356921724861587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400073212","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027656639,0.0014428988,0.95882565,0.008115598,0.0002477365,0.00011539609,0.0000022778493,0.0030804446,0.0005133527],"genre_scores_gemma":[0.8968452,0.000098936056,0.10272428,0.00007732574,0.000056572713,0.0000096250515,0.0000567336,0.000034694833,0.00009660825],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981726,0.00020065812,0.00024047257,0.00070360163,0.00026972283,0.00041299345],"domain_scores_gemma":[0.99858636,0.00022273656,0.000040239993,0.0010196546,0.000042292573,0.00008874113],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00043007632,0.00022763321,0.00020430342,0.00020465262,0.0004566825,0.00093997485,0.0030528472,0.00012141998,0.000058149926],"category_scores_gemma":[0.005778667,0.00021702186,0.000040499406,0.00052289636,0.00007987715,0.0007091703,0.01646706,0.0012182113,0.000051663355],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003534792,0.00009086725,0.008252413,0.00034841415,0.00022696766,0.0012854675,0.0011074163,0.3237054,0.006137897,0.0027435648,0.01026017,0.6458061],"study_design_scores_gemma":[0.0001783029,0.000117628355,0.00012406916,0.000075829455,0.000011549695,0.0002639241,0.000019915002,0.9927298,0.00130835,0.001955556,0.002967639,0.00024747846],"about_ca_topic_score_codex":0.00007854933,"about_ca_topic_score_gemma":0.000007730054,"teacher_disagreement_score":0.8691886,"about_ca_system_score_codex":0.00009444711,"about_ca_system_score_gemma":0.00004622154,"threshold_uncertainty_score":0.99148756},"labels":[],"label_agreement":null},{"id":"W4407200740","doi":"10.1007/s10994-024-06659-z","title":"Robust query performance prediction for dense retrievers via adaptive disturbance generation","year":2025,"lang":"en","type":"article","venue":"Machine Learning","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Toronto Metropolitan University","funders":"","keywords":"Disturbance (geology); Computer science; Artificial intelligence; Control theory (sociology); Pattern recognition (psychology); Biology; Control (management)","score_opus":0.02459554223764634,"score_gpt":0.2541639193749147,"score_spread":0.22956837713726838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407200740","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007208,0.0005049274,0.9904185,0.00024741705,0.0002818778,0.0003003437,0.0000043585055,0.0004732916,0.0005613058],"genre_scores_gemma":[0.824052,0.00015206251,0.17231064,0.00027180588,0.00012761734,0.00005645553,0.000026993575,0.000012554711,0.002989924],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989788,0.00006067678,0.00021151963,0.00038360254,0.00014572278,0.00021971192],"domain_scores_gemma":[0.9993785,0.00009037515,0.000108855565,0.0002494773,0.00013819893,0.000034611327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033335443,0.00014213158,0.00014386362,0.0001204569,0.00039630022,0.00009710026,0.0002796412,0.00006921197,0.0000037157677],"category_scores_gemma":[0.00020979387,0.00013792216,0.00005989461,0.00047709027,0.000030499328,0.00087965484,0.00011458423,0.00026219798,0.0000029322027],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021186212,0.00006940781,0.021098232,0.000109522596,0.000057662426,0.0000066242324,0.0004745922,0.038250525,0.012394739,0.010954479,0.0027019503,0.9136704],"study_design_scores_gemma":[0.000280468,0.00025479269,0.0034390746,0.000046145466,0.000009572662,0.0000039446363,0.000006614224,0.94939417,0.031836424,0.00068290695,0.013907886,0.00013800139],"about_ca_topic_score_codex":0.000014835583,"about_ca_topic_score_gemma":0.0000050368317,"teacher_disagreement_score":0.9135324,"about_ca_system_score_codex":0.000113256174,"about_ca_system_score_gemma":0.000040458825,"threshold_uncertainty_score":0.56243026},"labels":[],"label_agreement":null},{"id":"W4407241185","doi":"10.1007/s10994-024-06670-4","title":"Schema-tune: noise-driven bias mitigation in transformer-based language models","year":2025,"lang":"en","type":"article","venue":"Machine Learning","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Schema (genetic algorithms); Transformer; Artificial intelligence; Natural language processing; Machine learning; Speech recognition; Engineering; Electrical engineering","score_opus":0.018024811983866115,"score_gpt":0.2643060661716281,"score_spread":0.24628125418776198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407241185","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24282257,0.00019794599,0.7503588,0.0016815979,0.0000766687,0.000112060494,5.174868e-7,0.0001858971,0.0045638992],"genre_scores_gemma":[0.9564562,0.0000040321775,0.042594258,0.0004117207,0.000020335478,0.000015800388,0.0000096019285,0.000008965818,0.000479084],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99886906,0.00011779323,0.00024520437,0.00033680207,0.00018705818,0.00024406996],"domain_scores_gemma":[0.9995098,0.00009373982,0.000051393818,0.00027968836,0.000025412315,0.000039954048],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033831617,0.00012670526,0.00016020208,0.0002659285,0.000097082666,0.00008641922,0.00040162695,0.00006697741,0.000014613873],"category_scores_gemma":[0.00007076745,0.00012823884,0.00006003261,0.00049312407,0.000014962932,0.0003222564,0.000050446397,0.00035819176,0.000010622276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000064300725,0.000033775683,0.017340343,0.00005522046,0.0000074150303,0.000016528047,0.0019657568,0.8790865,0.0050738263,0.01358184,0.000011063401,0.08282131],"study_design_scores_gemma":[0.00055924803,0.00001667363,0.00073137047,0.00009451806,0.0000034438856,9.3763146e-7,0.000051831386,0.9940367,0.0032065834,0.00086837966,0.0003089859,0.00012132668],"about_ca_topic_score_codex":0.0003598315,"about_ca_topic_score_gemma":0.00016896208,"teacher_disagreement_score":0.71363366,"about_ca_system_score_codex":0.00006409177,"about_ca_system_score_gemma":0.00008142052,"threshold_uncertainty_score":0.52294284},"labels":[],"label_agreement":null},{"id":"W4407939460","doi":"10.1007/s10994-025-06752-x","title":"A contrastive neural disentanglement approach for query performance prediction","year":2025,"lang":"en","type":"article","venue":"Machine Learning","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Waterloo; Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Artificial neural network; Natural language processing","score_opus":0.009212424396369148,"score_gpt":0.238969669819153,"score_spread":0.22975724542278383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407939460","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023082847,0.00013388407,0.97321653,0.00096999353,0.0001290741,0.00036548908,0.0000046498353,0.00017457282,0.0019229446],"genre_scores_gemma":[0.9863322,0.000013185786,0.011907886,0.00028048785,0.00007446788,0.000211176,0.00003962232,0.000004776071,0.0011362011],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993432,0.000029298173,0.00013263588,0.0002444224,0.000077312696,0.0001731054],"domain_scores_gemma":[0.99968666,0.00006273632,0.000048910293,0.000141718,0.000030011854,0.000029958635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012302489,0.00008305866,0.0000876677,0.000044839177,0.00030845738,0.00008444076,0.00022613507,0.000020962809,0.000002485029],"category_scores_gemma":[0.000012456503,0.000072382005,0.000043874956,0.00022368577,0.0000157083,0.00017021765,0.00009846125,0.00013987531,0.000001091605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006360696,0.00022712123,0.12793462,0.0001306407,0.00007210446,0.0000011375259,0.00041614362,0.32168934,0.0012982739,0.07705842,0.003474563,0.46763402],"study_design_scores_gemma":[0.0002944123,0.000059141807,0.009140026,0.000010000325,0.0000075549146,0.0000015197295,0.000012515616,0.98052675,0.00013272493,0.00015792498,0.0095968405,0.000060569353],"about_ca_topic_score_codex":0.000009254561,"about_ca_topic_score_gemma":0.0000015029376,"teacher_disagreement_score":0.9632493,"about_ca_system_score_codex":0.00002598946,"about_ca_system_score_gemma":0.0000140103375,"threshold_uncertainty_score":0.29516524},"labels":[],"label_agreement":null},{"id":"W4408558613","doi":"10.1007/s10994-024-06664-2","title":"Gender disentangled representation learning in neural rankers","year":2025,"lang":"en","type":"article","venue":"Machine Learning","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Toronto Metropolitan University; University of Waterloo; University of Toronto","funders":"","keywords":"Representation (politics); Artificial neural network; Computer science; Artificial intelligence; Machine learning; Political science","score_opus":0.026069682320608932,"score_gpt":0.2943342839074334,"score_spread":0.26826460158682447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408558613","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.984724,0.00006228025,0.0011554324,0.0012344392,0.0004551016,0.00018685595,7.8176805e-7,0.00020485767,0.011976279],"genre_scores_gemma":[0.9933405,0.000023230637,0.00003239378,0.0006853452,0.000033990513,0.000013040801,0.000015683978,0.000015837968,0.0058399756],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985215,0.0004076129,0.00022311845,0.00041573832,0.00017984565,0.00025217875],"domain_scores_gemma":[0.9994618,0.00029254743,0.00008045591,0.000117537,0.000012884909,0.00003475646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019296342,0.00012812958,0.00014549428,0.00024560245,0.000247266,0.00008316745,0.00011969179,0.000045332887,0.00007835241],"category_scores_gemma":[0.0011096558,0.00012298684,0.00006553223,0.0006995558,0.000034825505,0.00017654969,0.0000909915,0.0005675159,0.000019468807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016455268,0.00005265763,0.4874659,0.000031348725,0.00000572136,0.00006905791,0.00037794324,0.16030852,0.30881134,0.001911716,0.00008548328,0.04071578],"study_design_scores_gemma":[0.00091945607,0.000045152487,0.08362998,0.00001842776,0.000008810972,0.000008847327,0.00013006745,0.9084277,0.0038769562,0.00050256704,0.0022789887,0.00015301385],"about_ca_topic_score_codex":0.00012167528,"about_ca_topic_score_gemma":0.000041839205,"teacher_disagreement_score":0.7481192,"about_ca_system_score_codex":0.0000573778,"about_ca_system_score_gemma":0.000015559903,"threshold_uncertainty_score":0.50152576},"labels":[],"label_agreement":null},{"id":"W4409740531","doi":"10.1007/s10994-025-06767-4","title":"Developing safe and responsible large language model: can we balance bias reduction and language understanding?","year":2025,"lang":"en","type":"article","venue":"Machine Learning","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Vector Institute","funders":"","keywords":"Reduction (mathematics); Balance (ability); Computer science; Cognitive psychology; Linguistics; Psychology; Mathematics; Philosophy","score_opus":0.024262651807243713,"score_gpt":0.30208355966579215,"score_spread":0.2778209078585484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409740531","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07788008,0.013009659,0.9022833,0.0054093236,0.000069361005,0.00012467678,0.0000032574135,0.0006882701,0.00053206994],"genre_scores_gemma":[0.79213977,0.00014047151,0.20588769,0.0002716343,0.000018106024,0.0000054594343,0.000006088601,0.000011480458,0.0015192992],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988884,0.00013083663,0.00016142674,0.00040091274,0.00014376082,0.00027467118],"domain_scores_gemma":[0.9995331,0.00011031987,0.00008593172,0.00019713189,0.000025779837,0.000047744943],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005942171,0.00015827743,0.00017287573,0.00028232986,0.00035070113,0.00024356018,0.00024053587,0.00008066875,0.000002869463],"category_scores_gemma":[0.0002842525,0.00014650516,0.000019780382,0.00048678476,0.000040977207,0.00028311677,0.0004085837,0.00038368392,6.447812e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000105985586,0.000038227812,0.014776524,0.00060094433,0.000067501394,0.00013738265,0.036674213,0.00039870178,0.035079416,0.79568857,0.00036546425,0.11606708],"study_design_scores_gemma":[0.0009806409,0.00007545627,0.0003637202,0.0010009856,0.0000262302,0.00011020832,0.0031810636,0.88937306,0.018746277,0.08475613,0.00075978215,0.00062645326],"about_ca_topic_score_codex":0.00014801047,"about_ca_topic_score_gemma":0.00010483348,"teacher_disagreement_score":0.88897437,"about_ca_system_score_codex":0.00013019596,"about_ca_system_score_gemma":0.00010618287,"threshold_uncertainty_score":0.5974307},"labels":[],"label_agreement":null},{"id":"W4409880954","doi":"10.1007/s10994-025-06777-2","title":"Prioritizing the essential: A robust evaluation framework for novelty detection","year":2025,"lang":"en","type":"article","venue":"Machine Learning","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Novelty; Novelty detection; Computer science; Artificial intelligence; Machine learning; Psychology","score_opus":0.025304891856278728,"score_gpt":0.32635983173837857,"score_spread":0.30105493988209986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409880954","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039421245,0.00015626721,0.9923199,0.0015342812,0.00036362195,0.00043605355,0.0000021826359,0.0005641669,0.0006814091],"genre_scores_gemma":[0.6299542,0.000004973301,0.3695362,0.00017934534,0.00007217137,0.00012560663,0.000010763259,0.0000089489085,0.00010776688],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988842,0.00018046278,0.00017807505,0.00032864732,0.00023117154,0.00019744108],"domain_scores_gemma":[0.9987692,0.00051256974,0.00011386075,0.00046441835,0.00012134618,0.000018595527],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016135138,0.0001098843,0.000104762206,0.0001190614,0.0004953674,0.00031578165,0.00064272695,0.00007338471,0.0000041267576],"category_scores_gemma":[0.0017510569,0.00008964839,0.000057645746,0.0004619907,0.000024638324,0.000263165,0.00030612122,0.000339408,0.0000033457397],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013125513,0.000028195964,0.0011803476,0.000034787598,0.00003275501,7.861565e-7,0.0005800901,0.0022752176,0.004670242,0.07915508,0.00026551107,0.91176385],"study_design_scores_gemma":[0.0001885528,0.000055663466,0.0014569672,0.000090596164,0.00002974607,0.000005199048,0.00003153791,0.9526073,0.00423351,0.032341518,0.008846926,0.000112483984],"about_ca_topic_score_codex":0.00009320044,"about_ca_topic_score_gemma":0.000051149385,"teacher_disagreement_score":0.9503321,"about_ca_system_score_codex":0.000077540164,"about_ca_system_score_gemma":0.00005703301,"threshold_uncertainty_score":0.38100153},"labels":[],"label_agreement":null},{"id":"W4409921902","doi":"10.1007/s10994-025-06766-5","title":"Imbalanced regression pipeline recommendation","year":2025,"lang":"en","type":"article","venue":"Machine Learning","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"Fundação de Amparo à Ciência e Tecnologia do Estado de Pernambuco; Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Pipeline (software); Regression; Computer science; Artificial intelligence; Machine learning; Regression analysis; Statistics; Mathematics","score_opus":0.011448653263013342,"score_gpt":0.28772038332406075,"score_spread":0.2762717300610474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409921902","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016250262,0.00028268562,0.9454324,0.014513139,0.0004161572,0.00009760314,0.0000015029714,0.0006614194,0.03697007],"genre_scores_gemma":[0.9600199,0.00009600853,0.024578478,0.0008892648,0.00007898203,0.000017405742,0.0003249298,0.00001189085,0.013983126],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998705,0.00027362676,0.00025502744,0.00041813587,0.00013743623,0.00021075476],"domain_scores_gemma":[0.9991719,0.0001419046,0.00015135462,0.0004256195,0.00006111763,0.00004808444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062014465,0.00014255031,0.00015138465,0.00021470046,0.00034019043,0.00016985665,0.0005004138,0.00006478665,0.00008249613],"category_scores_gemma":[0.00048411908,0.0001212864,0.000046377023,0.0005946498,0.00001588344,0.00033948894,0.00026599225,0.00043556772,0.00008482773],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014499475,0.00004145648,0.02564126,0.000017131331,0.000009553194,0.0000017978932,0.00011721931,0.00067484,0.0017732325,0.018944694,0.0061494755,0.94661486],"study_design_scores_gemma":[0.00034189995,0.00002416881,0.011475686,0.000044028653,0.000004910955,0.0000025508853,0.000008597541,0.6163336,0.00036550258,0.0006188532,0.3706671,0.0001131045],"about_ca_topic_score_codex":0.000076955264,"about_ca_topic_score_gemma":0.000014215722,"teacher_disagreement_score":0.9583949,"about_ca_system_score_codex":0.00004623597,"about_ca_system_score_gemma":0.000036918183,"threshold_uncertainty_score":0.4945916},"labels":[],"label_agreement":null},{"id":"W4413681322","doi":"10.1007/s10994-025-06858-2","title":"Cluster weighted models for functional data","year":2025,"lang":"en","type":"article","venue":"Machine Learning","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster (spacecraft); Computer science; Data mining; Artificial intelligence; Programming language","score_opus":0.04294268084520292,"score_gpt":0.30349957117040394,"score_spread":0.260556890325201,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413681322","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007104886,0.00038932468,0.987549,0.0035344888,0.0004071737,0.00015820992,0.000007527909,0.00016863519,0.0077145663],"genre_scores_gemma":[0.043013554,0.000009465713,0.94621456,0.0017893106,0.00011360999,0.000022147575,0.00009662359,0.000010986105,0.008729733],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890184,0.00012819053,0.00016366347,0.00047313428,0.00012070012,0.00021248712],"domain_scores_gemma":[0.99893737,0.00024769982,0.000048939728,0.0006692668,0.00005522738,0.000041516305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007454389,0.000113637616,0.00014252131,0.00010878488,0.00023325543,0.00012541427,0.00085631845,0.000059461905,0.0000125461665],"category_scores_gemma":[0.00008569294,0.000097614386,0.000048518807,0.00023526726,0.000014480424,0.0004757016,0.0006883919,0.00021486632,0.000005034952],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028468174,0.000031314605,0.000232303,0.00003419262,0.000043272103,0.0000013989239,0.00011709468,0.0057890154,0.00013057371,0.587388,0.0113401245,0.39486426],"study_design_scores_gemma":[0.00036821573,0.000015894635,0.00006126173,0.000012832466,0.000009034032,0.0000025384497,0.0000011169794,0.8125688,0.000037338406,0.12994634,0.056890566,0.00008610082],"about_ca_topic_score_codex":0.000018601155,"about_ca_topic_score_gemma":0.00000815887,"teacher_disagreement_score":0.80677974,"about_ca_system_score_codex":0.000016671846,"about_ca_system_score_gemma":0.000059736583,"threshold_uncertainty_score":0.3980599},"labels":[],"label_agreement":null},{"id":"W4413681754","doi":"10.1007/s10994-025-06863-5","title":"Source-free domain adaptation requires penalized diversity","year":2025,"lang":"en","type":"article","venue":"Machine Learning","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; University of Calgary; Concordia University; Cybernet Systems Corporation (Canada)","funders":"Mitacs","keywords":"Adaptation (eye); Diversity (politics); Computer science; Domain adaptation; Mathematics; Artificial intelligence; Biology; Classifier (UML); Neuroscience","score_opus":0.016075978593558173,"score_gpt":0.24294979446534526,"score_spread":0.2268738158717871,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413681754","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021905528,0.00027029542,0.94857776,0.0025641392,0.0002527269,0.00012054532,6.1193333e-7,0.000560357,0.025748024],"genre_scores_gemma":[0.91789657,0.000018351198,0.06569711,0.0010214441,0.00004602775,0.000007862236,0.000013391681,0.000012715799,0.015286536],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982712,0.00039227,0.00024735057,0.00041493747,0.0003671505,0.0003070663],"domain_scores_gemma":[0.99899244,0.00023828704,0.00015110639,0.00046145316,0.00007389212,0.00008284467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006524303,0.00016757057,0.00019472082,0.000270861,0.0010963544,0.00024555458,0.0010604066,0.0000689782,0.000098640376],"category_scores_gemma":[0.0005398889,0.00017016778,0.00010110819,0.0006333717,0.00005059049,0.00044885764,0.0015816344,0.0003987221,0.000071274124],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019415704,0.0001559637,0.11886709,0.00010345138,0.0001868427,0.000061563725,0.03255752,0.13583083,0.0024296243,0.36255124,0.0027749082,0.3442868],"study_design_scores_gemma":[0.0020312648,0.00007722041,0.021139568,0.000059168153,0.000016810267,0.0000076286906,0.00086880947,0.76295674,0.00006437119,0.016939942,0.19551697,0.00032149325],"about_ca_topic_score_codex":0.00035386492,"about_ca_topic_score_gemma":0.000078132616,"teacher_disagreement_score":0.895991,"about_ca_system_score_codex":0.0000717691,"about_ca_system_score_gemma":0.000056003966,"threshold_uncertainty_score":0.8432383},"labels":[],"label_agreement":null},{"id":"W4416408141","doi":"10.1007/s10994-025-06909-8","title":"MetaML: a multi-label meta-learning approach for pipeline recommendation","year":2025,"lang":"en","type":"article","venue":"Machine Learning","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Pipeline (software); Preprocessor; Computational complexity theory; Pipeline transport; Sequence (biology); Code (set theory); Bayesian probability; Source code","score_opus":0.07266868996257791,"score_gpt":0.33080450384217086,"score_spread":0.25813581387959295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416408141","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013100296,0.0008814244,0.986982,0.0041511958,0.00019960833,0.000417564,0.000007138065,0.0007792556,0.006450842],"genre_scores_gemma":[0.1346643,0.00007291636,0.8380377,0.00080186443,0.00009740574,0.0002783648,0.0012839107,0.00004391369,0.02471959],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99730265,0.00067147444,0.00051810313,0.00086655054,0.00021032644,0.00043090124],"domain_scores_gemma":[0.99842787,0.00045716084,0.00033752312,0.0005144343,0.00017194223,0.000091049966],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0022504157,0.00032107576,0.0004903365,0.0004069797,0.0006910565,0.00037248663,0.00080654235,0.00012418175,0.00005783068],"category_scores_gemma":[0.0015423732,0.00028198943,0.00021918361,0.0008396214,0.000031149226,0.0005353925,0.00035512188,0.000827545,0.00002986919],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060626553,0.0004530047,0.0045396816,0.00017015933,0.0007799713,0.000001362609,0.0005243914,0.029864991,0.0017847061,0.031331483,0.0028853086,0.9276043],"study_design_scores_gemma":[0.0010073333,0.000065541244,0.0002846127,0.0000074423137,0.00027221395,0.0000031066338,0.000026651325,0.79227316,0.00015244326,0.00013672681,0.2055537,0.0002170732],"about_ca_topic_score_codex":0.00012863518,"about_ca_topic_score_gemma":0.00001616411,"teacher_disagreement_score":0.92738724,"about_ca_system_score_codex":0.00006277131,"about_ca_system_score_gemma":0.00006251733,"threshold_uncertainty_score":0.9999632},"labels":[],"label_agreement":null},{"id":"W68132019","doi":"10.1007/s10994-013-5363-6","title":"A semantic matching energy function for learning with multi-relational data","year":2013,"lang":"en","type":"article","venue":"Machine Learning","topic":"Topic Modeling","field":"Computer Science","cited_by":687,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Agence Nationale de la Recherche; Compute Canada; Defense Advanced Research Projects Agency; Canadian Institute for Advanced Research","keywords":"Computer science; WordNet; Artificial intelligence; Statistical relational learning; Natural language processing; Sentence; Relational database; Relation (database); Semantic matching; Semantics (computer science); Parsing; Word (group theory); Context (archaeology); Information retrieval; Matching (statistics); Data mining","score_opus":0.03555843756672505,"score_gpt":0.24708839161885043,"score_spread":0.21152995405212538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W68132019","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015129849,0.00012566276,0.98328125,0.00062011,0.00013604961,0.00014527411,8.061429e-7,0.00031797148,0.0002429923],"genre_scores_gemma":[0.72595704,0.000002594358,0.27182764,0.00015183305,0.00010915866,0.00003197351,0.00008460276,0.00002163663,0.0018135112],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985829,0.00010658294,0.00021517137,0.00055293017,0.00024561858,0.00029676993],"domain_scores_gemma":[0.999032,0.00019839601,0.00014388758,0.00047846476,0.00007970477,0.00006753036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039384677,0.00015591308,0.00014964321,0.000107549,0.0004376358,0.00023587637,0.00058694626,0.000053438493,0.00004724959],"category_scores_gemma":[0.00011447412,0.00013382791,0.000032064647,0.00016508358,0.000014454492,0.001060323,0.00042178627,0.00033360574,0.00003385874],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017237253,0.00004543965,0.027870558,0.00004503271,0.00007097876,0.0000037854543,0.0008413686,0.75467443,0.0010736194,0.028002076,0.00009737399,0.18725812],"study_design_scores_gemma":[0.00053114485,0.00008330824,0.00302763,0.0000340678,0.0000116514275,0.000015081513,0.000042798496,0.98678964,0.000010724669,0.0010097002,0.008264799,0.0001794394],"about_ca_topic_score_codex":0.0009437639,"about_ca_topic_score_gemma":0.00011245781,"teacher_disagreement_score":0.7114537,"about_ca_system_score_codex":0.00002730786,"about_ca_system_score_gemma":0.000038513765,"threshold_uncertainty_score":0.5457344},"labels":[],"label_agreement":null},{"id":"W7117323897","doi":"10.1007/s10994-025-06943-6","title":"Extended UCB Policies for Multi-armed Bandit Problems","year":2025,"lang":"en","type":"article","venue":"Machine Learning","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Novelis (Canada)","funders":"","keywords":"Regret; Process (computing); Markov decision process; Simplicity; Order (exchange); Reinforcement learning; Extension (predicate logic)","score_opus":0.15270853510586288,"score_gpt":0.48696366916655853,"score_spread":0.3342551340606956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117323897","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00972465,0.000982565,0.9819115,0.0029642277,0.0004466046,0.0009338223,0.000029900211,0.00023368638,0.002773053],"genre_scores_gemma":[0.79479253,0.000053373853,0.03199154,0.00044374398,0.00022375573,0.00029944215,0.000042040694,0.000053706437,0.17209986],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969368,0.00028029212,0.0005786738,0.00063935656,0.00093982805,0.0006250275],"domain_scores_gemma":[0.99679434,0.0020398027,0.00017917145,0.000470259,0.00040061952,0.00011579905],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0025741989,0.00020845344,0.0003847441,0.0006982075,0.0006478426,0.00035252256,0.0008694151,0.00009539142,0.00035375817],"category_scores_gemma":[0.01145622,0.00015516493,0.00017047267,0.001243871,0.00017418108,0.00026264976,0.0003560881,0.00047483874,0.00013966214],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003365572,0.0004255272,0.0610071,0.00013722005,0.00017193968,0.000022958318,0.003197398,0.12581636,0.00570742,0.0038569276,0.012290519,0.7870301],"study_design_scores_gemma":[0.002055271,0.00016150002,0.01831249,0.000042445936,0.00001160622,0.000004483434,0.0005348827,0.5994303,0.0012688861,0.017223885,0.36069855,0.00025563748],"about_ca_topic_score_codex":0.0001419023,"about_ca_topic_score_gemma":0.00016043104,"teacher_disagreement_score":0.94991994,"about_ca_system_score_codex":0.00008663331,"about_ca_system_score_gemma":0.000105695544,"threshold_uncertainty_score":0.9968707},"labels":[],"label_agreement":null}]}