{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":113,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":113,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"591345dbeb0d","filters":{"venue":"Machine Learning"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01522449661702889,"gpt":0.238178710034388,"spread":0.2229542134173591,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005718979,0.0002127086,0.0003100233,0.0001732478,0.0002757437,0.0001261138,0.0006088751,0.00007317591,0.000212707],"category_scores_gemma":[0.0003525464,0.0001871653,0.0001333517,0.0002886886,0.00004126017,0.0002556076,0.0001553769,0.0006799455,0.0000520027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003330615,"about_ca_system_score_gemma":0.00002776958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003731561,"about_ca_topic_score_gemma":0.000005473646,"domain_scores_codex":[0.9979191,0.0006108301,0.0003476078,0.0004052678,0.0003852202,0.0003319466],"domain_scores_gemma":[0.9987923,0.0004428513,0.0002692094,0.0003296864,0.00004644108,0.0001195191],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009806625,0.000218502,0.04797753,0.00001593306,0.00008582185,0.00004906955,0.01071478,0.04557895,0.02364017,0.2662945,0.00005855816,0.6052681],"study_design_scores_gemma":[0.002464702,0.0009755949,0.1984461,0.000152535,0.00004193813,0.00001947759,0.0009397705,0.7160631,0.002709239,0.03768295,0.03963972,0.0008648383],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2014566,0.0004796658,0.7847553,0.0005121039,0.0001309541,0.00008889902,6.754224e-7,0.0004015143,0.01217424],"genre_scores_gemma":[0.9865344,0.00003003881,0.01147111,0.0002925804,0.00007018614,0.000002879302,0.00001798414,0.00001551135,0.001565274],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7850778,"threshold_uncertainty_score":0.7632381,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02000205411217099,"gpt":0.2499751384948166,"spread":0.2299730843826456,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001539548,0.0002583931,0.0002932762,0.00023581,0.000352664,0.0003278158,0.0007223844,0.00009533234,0.0005621254],"category_scores_gemma":[0.0006591348,0.0002485089,0.000106816,0.0006559719,0.00002236813,0.0003302303,0.0002694195,0.001123123,0.002668973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005685072,"about_ca_system_score_gemma":0.00005007652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000243376,"about_ca_topic_score_gemma":0.0000300637,"domain_scores_codex":[0.9971267,0.0009331268,0.0002955096,0.0006362402,0.0005137307,0.0004946854],"domain_scores_gemma":[0.9984772,0.0006621158,0.0001687922,0.000450958,0.00008424926,0.0001567119],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006164592,0.00008401326,0.6871551,0.00002892876,0.00004622502,0.00003179953,0.003014915,0.2051803,0.002104581,0.006959332,0.000268149,0.09506497],"study_design_scores_gemma":[0.0008708292,0.0003396895,0.1246026,0.00004230001,0.000002864224,0.000006839505,0.00007947131,0.8281636,0.00008335344,0.00007532196,0.04536372,0.000369486],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6930301,0.0003770766,0.2049665,0.0009530357,0.001073706,0.0004907195,0.000002791169,0.001954698,0.09715143],"genre_scores_gemma":[0.9784343,0.00001451468,0.002863805,0.0007052377,0.00005524905,0.000006263053,0.00005006761,0.00003999462,0.01783051],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6229833,"threshold_uncertainty_score":0.9999967,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01302649663491802,"gpt":0.28260567903664,"spread":0.269579182401722,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001782363,0.0002148388,0.0002451608,0.0001878252,0.0004685462,0.0002113337,0.0004476219,0.00007874475,0.00005735251],"category_scores_gemma":[0.0007210961,0.0002010155,0.00008723621,0.0004230205,0.00001451331,0.0003948959,0.00007923493,0.0004847009,0.0000229029],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004266309,"about_ca_system_score_gemma":0.00003083852,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004168242,"about_ca_topic_score_gemma":0.00001999761,"domain_scores_codex":[0.9978321,0.0006021866,0.0002427748,0.0006886558,0.0001973759,0.000436896],"domain_scores_gemma":[0.9990399,0.0001152727,0.0001020812,0.0004515169,0.00008654518,0.0002046277],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004240217,0.0001103321,0.004663254,0.00004060822,0.00003135214,0.00000774934,0.002224323,0.03069295,0.01941396,0.2924618,0.0007739117,0.6495374],"study_design_scores_gemma":[0.0004521184,0.0005863546,0.0002234468,0.000007592253,0.0000114811,0.00004058112,0.0000155608,0.5805165,0.003174778,0.007521212,0.4070992,0.0003511086],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00396141,0.0001988884,0.9908195,0.002861885,0.0004851263,0.0002622867,0.000001210925,0.0003611529,0.001048609],"genre_scores_gemma":[0.2371298,0.000006271267,0.7592789,0.0004624994,0.0004438872,0.00003414929,0.00001619873,0.00003479401,0.002593518],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6491863,"threshold_uncertainty_score":0.8197173,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02690503830497755,"gpt":0.2926671986209821,"spread":0.2657621603160046,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001530406,0.00004809528,0.00003927925,0.00001272394,0.0003353549,0.00008745756,0.0002428215,0.00001384908,0.00001320907],"category_scores_gemma":[0.00008193417,0.00003183263,0.00002469709,0.0001752988,0.000009492688,0.00008032174,0.0000334382,0.000076629,0.00000816784],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004977682,"about_ca_system_score_gemma":0.000009825683,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000129724,"about_ca_topic_score_gemma":0.0000119568,"domain_scores_codex":[0.9995982,0.00003918491,0.00007046891,0.000125849,0.00005743258,0.0001088662],"domain_scores_gemma":[0.9995756,0.0001712824,0.00003939262,0.0001681365,0.00002602071,0.00001962202],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[7.163455e-7,0.00001101449,0.003944558,0.000003168104,0.000004952204,2.119056e-7,0.0001500622,0.1976917,0.0005299897,0.7503098,0.0007812814,0.04657253],"study_design_scores_gemma":[0.00006444207,0.0000127712,0.0004954191,0.000001468796,0.000001955688,0.000001495161,0.00000283161,0.7737195,0.0001717651,0.00266971,0.222815,0.00004364017],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001988689,0.0001858508,0.9950275,0.001831804,0.00008257948,0.0001264428,3.134595e-7,0.00007452285,0.0006822816],"genre_scores_gemma":[0.977432,0.00001893094,0.02077898,0.0004840173,0.00004645079,0.00005703879,0.000003515838,0.000005162176,0.001173967],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9754432,"threshold_uncertainty_score":0.2579313,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01257153537582592,"gpt":0.2570000966085654,"spread":0.2444285612327395,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002877924,0.0001029329,0.000201606,0.00009956268,0.00009007094,0.00004028133,0.0005906328,0.00003510354,0.00002417345],"category_scores_gemma":[0.00006904569,0.00008832983,0.00005645952,0.0002182876,0.00001942016,0.0002962335,0.0003119447,0.0001695971,0.000004779636],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008426187,"about_ca_system_score_gemma":0.00001472367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001433479,"about_ca_topic_score_gemma":0.000006045932,"domain_scores_codex":[0.9990502,0.0000799035,0.0002547769,0.0002183046,0.0002262018,0.0001705955],"domain_scores_gemma":[0.9993237,0.0000561207,0.0001733539,0.0003496883,0.00004867672,0.00004845458],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000361148,0.0001476012,0.0223073,0.00009879423,0.00002144139,0.00002945185,0.00217315,0.02789392,0.02091124,0.007085649,0.0004690984,0.9188262],"study_design_scores_gemma":[0.0004402649,0.0003240778,0.021916,0.0001310633,0.000006084716,0.00001740623,0.00003018395,0.9600604,0.004901212,0.000777822,0.0111894,0.0002060849],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07549964,0.0004412319,0.9213738,0.0003280406,0.0002323205,0.00006994044,0.000003568863,0.0001317409,0.001919711],"genre_scores_gemma":[0.9626423,0.00001524472,0.03705162,0.00006543299,0.00004169533,7.022889e-7,0.000008362369,0.000005963895,0.0001686986],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9321665,"threshold_uncertainty_score":0.3601986,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03555843756672505,"gpt":0.2470883916188504,"spread":0.2115299540521254,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003938468,0.0001559131,0.0001496432,0.000107549,0.0004376358,0.0002358764,0.0005869463,0.00005343849,0.00004724959],"category_scores_gemma":[0.0001144741,0.0001338279,0.00003206465,0.0001650836,0.00001445449,0.001060323,0.0004217863,0.0003336057,0.00003385874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002730786,"about_ca_system_score_gemma":0.00003851376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009437639,"about_ca_topic_score_gemma":0.0001124578,"domain_scores_codex":[0.9985829,0.0001065829,0.0002151714,0.0005529302,0.0002456186,0.0002967699],"domain_scores_gemma":[0.999032,0.000198396,0.0001438876,0.0004784648,0.00007970477,0.00006753036],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001723725,0.00004543965,0.02787056,0.00004503271,0.00007097876,0.000003785454,0.0008413686,0.7546744,0.001073619,0.02800208,0.00009737399,0.1872581],"study_design_scores_gemma":[0.0005311448,0.00008330824,0.00302763,0.0000340678,0.00001165143,0.00001508151,0.0000427985,0.9867896,0.00001072467,0.0010097,0.008264799,0.0001794394],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01512985,0.0001256628,0.9832813,0.00062011,0.0001360496,0.0001452741,8.061429e-7,0.0003179715,0.0002429923],"genre_scores_gemma":[0.725957,0.000002594358,0.2718276,0.0001518331,0.0001091587,0.00003197351,0.00008460276,0.00002163663,0.001813511],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7114537,"threshold_uncertainty_score":0.5457344,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2227258883317751,"gpt":0.4461106063891386,"spread":0.2233847180573635,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002022339,0.0002054051,0.0002370464,0.00009567495,0.0003589314,0.0002753486,0.0007855791,0.00004541466,0.0000134662],"category_scores_gemma":[0.0009736035,0.0001905029,0.00003319782,0.0004320681,0.00002063014,0.001680084,0.0005567123,0.0004593974,0.00002853004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003988345,"about_ca_system_score_gemma":0.00003585907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001572107,"about_ca_topic_score_gemma":6.304853e-7,"domain_scores_codex":[0.9976035,0.0008404233,0.000309073,0.0005851585,0.0003968904,0.000264973],"domain_scores_gemma":[0.9989898,0.0002381279,0.0001759291,0.0004236317,0.00006096451,0.0001115301],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003345795,0.00008482142,0.01283607,0.00001784265,0.00001384492,0.000009724229,0.01068433,0.2386116,0.0005024699,0.0001394863,0.00003356554,0.7370328],"study_design_scores_gemma":[0.0001929182,0.002742896,0.00179676,0.00003048672,0.0000104596,0.00001237748,0.0000859712,0.9939082,0.000591326,0.0003786011,0.00004915857,0.0002008493],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3462314,0.000007882085,0.6515204,0.0004135149,0.00002401126,0.0001759307,0.00000100388,0.0009903993,0.0006354444],"genre_scores_gemma":[0.4618991,3.203216e-7,0.5378457,0.000148994,0.00003325177,0.00001757212,0.00001417836,0.00001573779,0.00002516716],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7552966,"threshold_uncertainty_score":0.7768481,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03939313177323189,"gpt":0.3477566611305509,"spread":0.308363529357319,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001156954,0.0001824243,0.0002042607,0.0001290799,0.0003365926,0.0001930566,0.0008199487,0.00007379762,0.00001374196],"category_scores_gemma":[0.0001374872,0.0001757817,0.00005827227,0.000328283,0.00002694325,0.001016457,0.000159643,0.0002764205,0.00001094283],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006660791,"about_ca_system_score_gemma":0.00004253285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000136842,"about_ca_topic_score_gemma":0.00002458299,"domain_scores_codex":[0.9984053,0.0001855618,0.000325201,0.0005226203,0.0001910572,0.0003702868],"domain_scores_gemma":[0.9988351,0.0001616723,0.0002255595,0.0005919001,0.0001209683,0.00006475226],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004469805,0.0002639799,0.01620242,0.0005075472,0.00002777197,0.000003424069,0.000450094,0.001654077,0.1019359,0.05387899,0.007365544,0.8176655],"study_design_scores_gemma":[0.0002663679,0.0001453083,0.002960971,0.0000510549,0.000005766939,0.000008255183,0.000008751314,0.8894117,0.01298412,0.0003785345,0.09354976,0.0002293644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000841417,0.0001646084,0.9955739,0.0006238515,0.000102734,0.0004667922,0.00000952183,0.0009886813,0.001228451],"genre_scores_gemma":[0.1313073,0.00005171987,0.8654658,0.0009059614,0.0001494958,0.0002723079,0.0002855865,0.00003941304,0.001522481],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8877577,"threshold_uncertainty_score":0.716817,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01448241195974086,"gpt":0.2052069867833169,"spread":0.190724574823576,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007064576,0.0001278595,0.0001218653,0.0000703858,0.00009378001,0.00006361916,0.0001379845,0.0000492235,0.0004438719],"category_scores_gemma":[0.00001767759,0.0001298582,0.00004643066,0.00009762742,0.00001203478,0.0000773518,0.00004336432,0.0003367695,0.0001880444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002210103,"about_ca_system_score_gemma":6.797643e-7,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004182134,"about_ca_topic_score_gemma":0.000006093601,"domain_scores_codex":[0.9994019,0.0000246585,0.0001154027,0.0001204662,0.0001223603,0.0002152575],"domain_scores_gemma":[0.9997482,0.00003002064,0.00001944571,0.0001472732,0.00001113388,0.00004391103],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007320059,0.0000607529,0.01145726,0.00006741398,0.0001476407,0.0002050479,0.002986838,0.561471,0.08562649,0.001675775,0.02689539,0.3093991],"study_design_scores_gemma":[0.0001558112,0.00002732479,0.0007532763,0.00005322379,0.00001119004,0.00003899189,0.00002917857,0.8969455,0.005070781,0.0008127104,0.09581576,0.0002863075],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.699387,0.005032045,0.07119611,0.0003739966,0.0005436307,0.0001882416,0.000002605964,0.009427154,0.2138492],"genre_scores_gemma":[0.995937,0.0001071157,0.00233063,0.00008241007,0.0001070942,0.000003832472,0.00000366393,0.00004827161,0.001380018],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3354745,"threshold_uncertainty_score":0.5295465,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.007893058798280584,"gpt":0.2351205030355744,"spread":0.2272274442372938,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001594122,0.0001366829,0.000138481,0.00013024,0.001227841,0.0002133822,0.001556248,0.00002933665,0.0000339925],"category_scores_gemma":[0.0002161822,0.000117784,0.00004187259,0.0008189601,0.00004274244,0.000287173,0.001078749,0.001330353,0.00002558936],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001804565,"about_ca_system_score_gemma":0.00003920694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007687417,"about_ca_topic_score_gemma":0.00004413929,"domain_scores_codex":[0.9977947,0.000683082,0.0002989678,0.000421414,0.0003990731,0.0004028009],"domain_scores_gemma":[0.9989344,0.000276936,0.0002117651,0.000503498,0.00003239681,0.00004094506],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003796087,0.0001318572,0.2537819,0.00002802194,0.00002185796,0.00006463336,0.003214826,0.1116962,0.005872093,0.157999,0.001389754,0.4657619],"study_design_scores_gemma":[0.0001943378,0.00009053003,0.008757674,0.00000590597,9.981333e-7,0.00002240645,0.0001248601,0.60501,0.0001643542,0.001644659,0.3838211,0.0001631786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01687898,0.002367247,0.9346989,0.0142694,0.0005359176,0.0009831137,0.000005267758,0.003266586,0.02699455],"genre_scores_gemma":[0.9791753,0.00007677604,0.01763399,0.0002723296,0.00002787327,0.0002595936,0.00002543767,0.000021608,0.002507115],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9622963,"threshold_uncertainty_score":0.9443681,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01036808213155851,"gpt":0.2475459678214451,"spread":0.2371778856898866,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002392487,0.0001615476,0.0001492248,0.0001103448,0.0002088555,0.0002119085,0.0005059295,0.00004138497,0.00003326166],"category_scores_gemma":[0.00005261451,0.0001358463,0.00004191509,0.0003826407,0.00007000623,0.000446417,0.0001780448,0.0004150227,0.0001419829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006033706,"about_ca_system_score_gemma":0.00003417756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009738182,"about_ca_topic_score_gemma":0.0005127877,"domain_scores_codex":[0.9986787,0.00009801167,0.0002069876,0.0003873557,0.0002718607,0.0003570892],"domain_scores_gemma":[0.9993958,0.0000892896,0.0001154119,0.000275593,0.00007649699,0.0000474374],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000459942,0.0001152778,0.07422771,0.00001711216,0.00003790544,0.0002163107,0.002785599,0.6067371,0.004028623,0.07598835,0.0002434166,0.2355566],"study_design_scores_gemma":[0.00006567375,0.0001530089,0.002716769,0.0000310747,0.00000416928,0.00002885903,0.00008351883,0.9880019,0.0009627864,0.003485719,0.00425976,0.0002067134],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06048191,0.0002143494,0.9315345,0.0008903741,0.0001144121,0.00009133191,4.635639e-7,0.0004435316,0.006229147],"genre_scores_gemma":[0.9690744,0.000001698141,0.02848195,0.0002506311,0.00006475137,0.000007304145,0.000002979768,0.00001956364,0.002096777],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9085925,"threshold_uncertainty_score":0.5539652,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01650694066603725,"gpt":0.2562202338761764,"spread":0.2397132932101392,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009488318,0.000247967,0.0002599452,0.0001492463,0.0006705517,0.0001891233,0.0006435587,0.00007940943,0.00002917149],"category_scores_gemma":[0.0003170111,0.0002187761,0.0001597397,0.0003487815,0.0000295844,0.0003140524,0.000341859,0.0006737438,0.00006895092],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002735225,"about_ca_system_score_gemma":0.00002725611,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005126415,"about_ca_topic_score_gemma":0.000001567702,"domain_scores_codex":[0.9980759,0.0002085863,0.0002579137,0.0003953631,0.000266408,0.0007958121],"domain_scores_gemma":[0.9989432,0.0003569515,0.0001319527,0.0003052455,0.000058558,0.0002040536],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004948697,0.0002083024,0.09246003,0.000176697,0.0001122395,0.00001345633,0.01390469,0.2212991,0.005262007,0.04449949,0.0009265791,0.6210879],"study_design_scores_gemma":[0.000495929,0.0001718123,0.002745099,0.00002515938,0.000007965884,0.00003455772,0.00004735575,0.9136071,0.0002729472,0.0004617853,0.08184008,0.0002901754],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2756375,0.0009996658,0.7194963,0.0008646094,0.001261375,0.0002095713,0.00000140384,0.0008387761,0.0006908047],"genre_scores_gemma":[0.962332,0.000008294269,0.03527698,0.0002331207,0.0006591195,0.000007449066,0.00001610413,0.00004019715,0.001426768],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.692308,"threshold_uncertainty_score":0.892143,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.3261500829909371,"gpt":0.5301317871582475,"spread":0.2039817041673104,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.0294816,0.0003374951,0.001193928,0.0003195181,0.0008953791,0.0003015135,0.0005430632,0.0002990678,0.002164664],"category_scores_gemma":[0.01801433,0.0003975561,0.0002407721,0.0002833462,0.00009900813,0.001202313,0.0002935998,0.002102671,0.001725644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002055575,"about_ca_system_score_gemma":0.000160717,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007965756,"about_ca_topic_score_gemma":0.0006428837,"domain_scores_codex":[0.9914742,0.0008406122,0.005841505,0.0009142478,0.0002648264,0.0006646084],"domain_scores_gemma":[0.9939864,0.002327677,0.002615081,0.0007024565,0.00009229985,0.0002761139],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005906506,0.0002400843,0.9622446,0.00003605623,0.00008201962,0.000008492538,0.007228307,0.02063522,0.000002310338,0.003906804,0.0007671051,0.004789927],"study_design_scores_gemma":[0.003042112,0.00161114,0.1577902,0.00009783343,0.00003249996,0.00003584886,0.005164003,0.3998917,0.000001532346,0.005785256,0.4255085,0.001039403],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9494528,0.0001315655,0.03644253,0.002705613,0.001727808,0.0008067017,0.000006892569,0.0002600754,0.008466089],"genre_scores_gemma":[0.9850942,0.00002080804,0.009237816,0.003640182,0.00113146,0.00005509686,0.0000490703,0.00007169625,0.0006996936],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8044544,"threshold_uncertainty_score":0.9998477,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1184072395273905,"gpt":0.3423309401831147,"spread":0.2239237006557242,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000248045,0.0001060489,0.0001745489,0.00004088904,0.0001097405,0.00003061681,0.0001007145,0.0000440734,0.003052751],"category_scores_gemma":[0.001313519,0.00008810879,0.00004353854,0.0001021274,0.00002516547,0.00004818414,0.00003820131,0.0002633283,0.00006754662],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000127976,"about_ca_system_score_gemma":0.00000230166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003408837,"about_ca_topic_score_gemma":0.000006663031,"domain_scores_codex":[0.999162,0.0001563325,0.0001769251,0.0001583534,0.0001438696,0.0002025131],"domain_scores_gemma":[0.9990478,0.0006519508,0.00005637268,0.0001467667,0.00002278004,0.00007433942],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007556207,0.0000944123,0.001983815,0.00005375585,0.00002292194,0.00002115015,0.001077591,0.0007153359,0.0001924108,0.7499011,0.001531503,0.2443985],"study_design_scores_gemma":[0.0001384856,0.00004263429,0.00006342103,0.00001262474,0.000009234104,0.000004278733,0.0000159365,0.648652,0.00002167386,0.3494644,0.001487349,0.0000878927],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003192803,0.00009624543,0.8868608,0.000267501,0.00004458423,0.0000588677,0.000002962528,0.0001499663,0.1093263],"genre_scores_gemma":[0.6226776,0.00001073324,0.372422,0.00008846606,0.00005054062,0.000005444999,0.000001258863,0.00002127133,0.004722672],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6479367,"threshold_uncertainty_score":0.9978586,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.008477493126515724,"gpt":0.2569136168463945,"spread":0.2484361237198787,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003034842,0.00009643193,0.0001361934,0.000164545,0.0001778094,0.00007133123,0.0002632401,0.00004836996,0.00001409526],"category_scores_gemma":[0.0003697517,0.00008625239,0.00003098621,0.000296122,0.00004652193,0.00027863,0.0001533695,0.0003850977,0.000005212095],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001875084,"about_ca_system_score_gemma":0.00002389175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006444674,"about_ca_topic_score_gemma":0.00001666981,"domain_scores_codex":[0.9992411,0.00009141251,0.0001677147,0.0002034698,0.0001501138,0.0001462509],"domain_scores_gemma":[0.9994605,0.0001554646,0.0001471482,0.0001524377,0.00005215716,0.00003226741],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001428636,0.00005809075,0.2706769,0.0001229574,0.00002605073,0.00002019925,0.001784015,0.05008628,0.01645122,0.04008325,0.0001189487,0.6205578],"study_design_scores_gemma":[0.0002136888,0.0001126648,0.004526173,0.0000788052,0.000009263461,0.00001485188,0.00001184633,0.9800037,0.007182056,0.002137254,0.005542033,0.0001677347],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06105382,0.007019996,0.9287503,0.001531549,0.00002383193,0.00007143614,3.694928e-7,0.000869533,0.0006792209],"genre_scores_gemma":[0.6975967,0.00001418479,0.3020035,0.00005650159,0.00001380569,0.000001900742,0.000002841945,0.000006542283,0.0003041205],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9299173,"threshold_uncertainty_score":0.351727,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02463525336756793,"gpt":0.2229630992481061,"spread":0.1983278458805381,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002867598,0.0001255106,0.0001306007,0.00007109987,0.0001605389,0.00007586957,0.000648656,0.00005596195,0.000300937],"category_scores_gemma":[0.0001176382,0.0001022247,0.00006729466,0.0002152551,0.00003080445,0.0002292362,0.0002044829,0.0003343872,0.0005621173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001842395,"about_ca_system_score_gemma":0.00002205958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001087343,"about_ca_topic_score_gemma":0.0000542672,"domain_scores_codex":[0.999059,0.0001015048,0.0001263113,0.0002900965,0.0001326425,0.0002904602],"domain_scores_gemma":[0.9994503,0.00004672141,0.00007012935,0.0002975463,0.00003749639,0.00009775574],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002597922,0.0003243928,0.3337207,0.00007055476,0.00008673107,0.0002855208,0.06400905,0.0002833721,0.001875062,0.4122467,0.002977057,0.1840949],"study_design_scores_gemma":[0.001412905,0.0007246406,0.08740404,0.0000588516,0.00002916232,0.0001915651,0.0001650882,0.2860895,0.002984132,0.02379225,0.5959365,0.001211382],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.03242247,0.001267568,0.3115771,0.0002773168,0.0007539078,0.0001119868,6.503285e-7,0.000939865,0.6526492],"genre_scores_gemma":[0.9767629,0.00001415351,0.01366651,0.0001679649,0.0001119543,0.000004448857,0.000002609745,0.00001157341,0.009257906],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9443404,"threshold_uncertainty_score":0.7225068,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05444036630139729,"gpt":0.265644620019226,"spread":0.2112042537178287,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000802494,0.00006622533,0.00006225872,0.00003053182,0.0003078413,0.0000659939,0.0001987431,0.00002656543,0.00001632327],"category_scores_gemma":[0.00003472656,0.00005516237,0.00003771874,0.0001689922,0.000005303495,0.00009603307,0.00005823122,0.0001262059,0.00001012193],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001164958,"about_ca_system_score_gemma":0.000002787867,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002843752,"about_ca_topic_score_gemma":0.00002426404,"domain_scores_codex":[0.9994864,0.00001940257,0.00008488158,0.0002003987,0.00005841202,0.0001505337],"domain_scores_gemma":[0.9996732,0.00009375621,0.00004927771,0.0001213437,0.00002502894,0.0000373411],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003386408,0.00006558645,0.003283631,0.00001170497,0.000005596336,2.68561e-7,0.0002758704,0.5787678,0.003406069,0.03415692,0.003978367,0.3760448],"study_design_scores_gemma":[0.0001075466,0.00003228708,0.00005169276,0.000005646386,0.000001792705,0.000002545857,8.781411e-7,0.9702407,0.0001834626,0.003244448,0.0260605,0.00006845943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008386652,0.00008692452,0.989285,0.001413447,0.00003657787,0.0001030151,9.552846e-7,0.0002023816,0.0004850313],"genre_scores_gemma":[0.7670095,0.00001968189,0.2300632,0.0002269854,0.00008882468,0.00004314207,0.00000657336,0.000009316187,0.002532744],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7592218,"threshold_uncertainty_score":0.2367697,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01261317721952781,"gpt":0.2234001724758154,"spread":0.2107869952562876,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009342417,0.0003404049,0.0004827071,0.0003560024,0.0009195814,0.0000977481,0.0007863823,0.0001618163,0.00004000752],"category_scores_gemma":[0.001192423,0.0003204628,0.0001877897,0.000895884,0.00009808132,0.0005885282,0.0003863711,0.001527329,0.00007131031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005040608,"about_ca_system_score_gemma":0.00007679407,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000850002,"about_ca_topic_score_gemma":0.00001337496,"domain_scores_codex":[0.9970704,0.0004870683,0.000581018,0.0006990426,0.0005698424,0.0005926701],"domain_scores_gemma":[0.9983854,0.0004102279,0.0004785217,0.0004520465,0.0001518019,0.0001219931],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007993837,0.0002903795,0.3822595,0.0002241046,0.0001355094,0.0002538717,0.01375176,0.4649151,0.03089488,0.002020499,0.0001494264,0.105025],"study_design_scores_gemma":[0.0009857407,0.0003508611,0.009582072,0.0001634652,0.00001519524,0.0002156543,0.00009759334,0.9761927,0.001442779,0.00009566322,0.0104294,0.0004288401],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5518563,0.0007758206,0.4411004,0.0004991053,0.0004786489,0.0002590209,0.000001719363,0.001077449,0.003951583],"genre_scores_gemma":[0.977063,0.00008185967,0.01861227,0.00005511349,0.0001318206,0.00001523727,0.00002373519,0.00004572585,0.003971269],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5112776,"threshold_uncertainty_score":0.9999247,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.09096737967275106,"gpt":0.3815705795832492,"spread":0.2906031999104981,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002732664,0.0001553762,0.0004358626,0.0001994585,0.0002498922,0.0003484708,0.0003543269,0.00003739154,4.799728e-7],"category_scores_gemma":[0.006535427,0.0001238257,0.00004760855,0.0002327659,0.00002059163,0.001346337,0.0003040576,0.0001844383,0.00002349649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001006142,"about_ca_system_score_gemma":0.00002124252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002384685,"about_ca_topic_score_gemma":0.000005902542,"domain_scores_codex":[0.9984247,0.0002987865,0.0006055691,0.000221158,0.0002426863,0.0002071118],"domain_scores_gemma":[0.9985757,0.0003375062,0.000471889,0.0002833073,0.0002336652,0.00009787907],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007638857,0.0001882387,0.07189763,0.1094768,0.0005691663,0.00003425526,0.1742913,0.2071294,0.03541701,0.05300159,0.007588075,0.3396426],"study_design_scores_gemma":[0.001008604,0.0002105279,0.0004560792,0.003750595,0.00003047487,0.00004902403,0.0005741933,0.978644,0.0002433031,0.001650502,0.0131114,0.0002712948],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01411717,0.001569202,0.9822214,0.0002332765,0.0001261577,0.001437122,0.000001187271,0.000261049,0.00003346516],"genre_scores_gemma":[0.5247203,0.0003068684,0.4735105,0.0003923212,0.00009509682,0.0005639467,0.00002505232,0.00002426578,0.0003616664],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7715146,"threshold_uncertainty_score":0.7823988,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04416456190730939,"gpt":0.309821783679691,"spread":0.2656572217723816,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007587237,0.0001370897,0.0001601458,0.000162094,0.0001150195,0.0001232613,0.0006915678,0.0000572207,0.00007117983],"category_scores_gemma":[0.00007378367,0.0001245063,0.00004128942,0.0004326001,0.00004708205,0.0004349902,0.0004668406,0.0004993384,0.0005071312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005078119,"about_ca_system_score_gemma":0.00002294022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005128784,"about_ca_topic_score_gemma":0.0000757967,"domain_scores_codex":[0.9984297,0.0002453467,0.0002430804,0.0002762816,0.0002698955,0.000535766],"domain_scores_gemma":[0.9992937,0.0001877491,0.00005323284,0.0003110037,0.00003364217,0.0001206741],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002615536,0.00005696867,0.7552085,0.000006857801,0.000003028943,0.000008824315,0.00355136,0.005731523,0.0003201684,0.004641677,0.00004427469,0.2304242],"study_design_scores_gemma":[0.00006787829,0.00006364263,0.09152698,0.00002654405,9.837954e-7,0.00001352037,0.00003646572,0.9015283,0.001669668,0.0005128399,0.004340135,0.0002130757],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.360989,0.0002192868,0.6365866,0.0005388499,0.0002973302,0.00008534762,2.50777e-7,0.0001777458,0.001105585],"genre_scores_gemma":[0.9600753,0.000007319912,0.03881128,0.0001976117,0.0001755306,0.00000584633,0.000002448463,0.00001133802,0.0007133055],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8957968,"threshold_uncertainty_score":0.6518315,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03105901679861803,"gpt":0.289212411422877,"spread":0.2581533946242589,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000366159,0.0001450635,0.0001494282,0.000172967,0.0004402222,0.0003714832,0.0007656517,0.00008366771,0.000101856],"category_scores_gemma":[0.0003196758,0.0001295721,0.00006835938,0.0003135354,0.00004708021,0.0005696135,0.000339421,0.0004485688,0.0003290929],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003675995,"about_ca_system_score_gemma":0.00002162396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001353082,"about_ca_topic_score_gemma":0.000002085887,"domain_scores_codex":[0.9987253,0.00006050496,0.0002020486,0.0003978094,0.000222309,0.0003920475],"domain_scores_gemma":[0.9991853,0.0002253539,0.00008975557,0.0003150235,0.0001173943,0.00006713851],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002900017,0.00005173376,0.01683797,0.00002470373,0.00002036728,0.000001388122,0.0007406826,0.004272901,0.008324143,0.01192018,0.0009114185,0.9568916],"study_design_scores_gemma":[0.0004873811,0.0001861828,0.005119447,0.00001028928,0.000003086764,0.000003964265,0.0002214035,0.9297019,0.006100121,0.001395461,0.05653935,0.0002314131],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03946071,0.0002638565,0.9522077,0.003916801,0.0001526392,0.0004657455,7.060763e-7,0.001924199,0.001607612],"genre_scores_gemma":[0.8799031,0.00002405072,0.1091819,0.0001099333,0.00005100281,0.0001632862,0.00001476697,0.0000203198,0.01053171],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9566602,"threshold_uncertainty_score":0.5283796,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.008947761347103697,"gpt":0.2255024712557855,"spread":0.2165547099086818,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004079912,0.0003647862,0.0005074999,0.0002341691,0.0001691854,0.0008843661,0.0005254286,0.0002119331,0.00008795017],"category_scores_gemma":[0.0002287064,0.0003279254,0.00004793345,0.0004171217,0.0001177348,0.0003453198,0.0009620179,0.001249075,0.000001603106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007756336,"about_ca_system_score_gemma":0.0002806447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008779319,"about_ca_topic_score_gemma":0.00008107511,"domain_scores_codex":[0.9978111,0.0002573118,0.0004764279,0.0007939684,0.0002845722,0.000376608],"domain_scores_gemma":[0.9987909,0.000202442,0.0003338363,0.0004647919,0.00008861218,0.0001194263],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004805283,0.00002919517,0.01720095,0.0003538721,0.00003016253,0.0001321478,0.00127039,0.9150462,0.000003637884,0.00150238,0.000001167686,0.0644251],"study_design_scores_gemma":[0.0003745403,0.00006392915,0.003114059,0.001129,0.00001954274,0.0001088283,0.0001055284,0.9940725,0.000005774069,0.0005836401,0.00001972204,0.0004029461],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002086595,0.0003587691,0.9945984,0.001085471,0.0001055121,0.0002160099,0.000002056317,0.000179144,0.001367987],"genre_scores_gemma":[0.5212526,0.00008228571,0.4784469,0.00009990887,0.00001463221,0.000009862333,0.00003534701,0.00001837824,0.00004003826],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.519166,"threshold_uncertainty_score":0.9999173,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02712692566950338,"gpt":0.2695101599614228,"spread":0.2423832342919194,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005941018,0.00009891893,0.0001320182,0.00005808723,0.0001800429,0.0001146349,0.0004704564,0.00004223531,0.00003685624],"category_scores_gemma":[0.0001526258,0.00009037043,0.00001950044,0.0002032307,0.000006224649,0.0006211874,0.000338223,0.0001851467,0.00002145843],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000018003,"about_ca_system_score_gemma":0.00002012234,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009349763,"about_ca_topic_score_gemma":0.00001181608,"domain_scores_codex":[0.9989157,0.00006687611,0.000203997,0.0003796035,0.0001440911,0.0002896756],"domain_scores_gemma":[0.9993798,0.0001347567,0.00006603249,0.0003371414,0.00002779003,0.00005452772],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001011187,0.0002068187,0.002988871,0.00003446729,0.00001518699,0.00002734656,0.0005738155,0.7732374,0.02335778,0.004551042,0.001180164,0.193726],"study_design_scores_gemma":[0.0007318521,0.00006628075,0.0005035342,0.00006031079,0.000003075727,0.000005773673,0.000007834375,0.9929172,0.001734041,0.001298589,0.002545439,0.0001261095],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1180403,0.0001459167,0.8785772,0.002227861,0.0002029506,0.0001684654,0.000005065508,0.0001847221,0.0004475001],"genre_scores_gemma":[0.6640264,0.000004147784,0.3349805,0.0005806595,0.00006143701,0.00000647373,0.00006882834,0.000007362855,0.0002641644],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5459861,"threshold_uncertainty_score":0.3685199,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06608287604619553,"gpt":0.3737000284153294,"spread":0.3076171523691339,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002020466,0.0001857689,0.0002547689,0.0002376824,0.0003999285,0.000177125,0.001204203,0.00007742607,0.000009942703],"category_scores_gemma":[0.001524728,0.0001846209,0.00003761805,0.0003660644,0.0001367847,0.001248318,0.001891747,0.0002922092,0.0000013468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003663198,"about_ca_system_score_gemma":0.00003167146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000861444,"about_ca_topic_score_gemma":0.0002646856,"domain_scores_codex":[0.9982004,0.0003472767,0.000271299,0.0006786298,0.0001853353,0.000317051],"domain_scores_gemma":[0.9979795,0.0006053788,0.000299526,0.0008947076,0.0001483621,0.00007254805],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003408407,0.00001298856,0.007749785,0.00003269219,0.00004093384,0.000001765429,0.001658242,0.0001978528,0.005907605,0.0005123583,0.0000907046,0.983761],"study_design_scores_gemma":[0.0002829403,0.0005974805,0.001220423,0.0001108864,0.0000241945,0.000006962201,0.0005550761,0.9814752,0.01239679,0.0005153699,0.002610247,0.0002043878],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03170109,0.0001398648,0.9669339,0.00006580421,0.0001237563,0.0002061768,0.00002840604,0.0003405248,0.0004604631],"genre_scores_gemma":[0.5076516,0.000009904032,0.4921938,0.000009875712,0.00005298742,0.000003991534,0.00002573012,0.00001303439,0.00003902158],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9835566,"threshold_uncertainty_score":0.7528623,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02311423201309188,"gpt":0.2528785846531024,"spread":0.2297643526400105,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008953355,0.0003839408,0.0003607798,0.0002349635,0.0006687189,0.0003959622,0.001049948,0.0001285741,0.0001496414],"category_scores_gemma":[0.0004570929,0.0003951638,0.0001461874,0.000618353,0.00005147299,0.0007917808,0.0002581384,0.001240626,0.0002110276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001395637,"about_ca_system_score_gemma":0.00006895386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004715834,"about_ca_topic_score_gemma":0.000002343312,"domain_scores_codex":[0.9969763,0.0002636314,0.0005470503,0.0006213092,0.0007161278,0.0008755513],"domain_scores_gemma":[0.9986634,0.0001464611,0.0003623147,0.0005023463,0.00006959905,0.0002559408],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008422765,0.00001273687,0.002007385,0.000007574753,0.00002359098,0.0000211593,0.002873796,0.9460119,0.001455483,0.002259953,0.00109552,0.0442225],"study_design_scores_gemma":[0.0005922793,0.0005454859,0.0002844098,0.00003854511,0.00001144084,0.00001791053,0.0002042134,0.873429,0.0002741941,0.00009226264,0.1240824,0.0004278263],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005371991,0.00014026,0.9577644,0.00114814,0.0002612589,0.0002055405,2.007742e-7,0.001094244,0.03401393],"genre_scores_gemma":[0.9683691,0.00006538298,0.01549407,0.001529333,0.00008932386,0.000008185975,0.0000534885,0.00003292012,0.01435818],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9629971,"threshold_uncertainty_score":0.99985,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.1495274344458986,"gpt":0.3026147751511101,"spread":0.1530873407052114,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001386701,0.0002148388,0.0002371595,0.0002385513,0.0005575525,0.000343239,0.002092936,0.00007623041,0.00004850201],"category_scores_gemma":[0.0004478138,0.000190929,0.00002858073,0.001013791,0.00007659347,0.00114823,0.00142516,0.0007737989,0.0001629912],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001427068,"about_ca_system_score_gemma":0.00006486328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008095434,"about_ca_topic_score_gemma":0.0000300351,"domain_scores_codex":[0.9976045,0.0002813513,0.0002697555,0.0008801569,0.0004787494,0.0004854983],"domain_scores_gemma":[0.9978097,0.0002592376,0.0002104322,0.001568868,0.00005287277,0.00009887269],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000155178,0.0001982669,0.6480634,0.0003277371,0.000286116,0.0003494786,0.008970428,0.02483997,0.01700132,0.1544479,0.03238554,0.1129746],"study_design_scores_gemma":[0.0004310152,0.0001328173,0.009986797,0.00006458494,0.00000898988,0.00001749442,0.0002283989,0.927022,0.0005316269,0.004402128,0.05677562,0.0003985611],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002529686,0.00003647565,0.9873849,0.002016819,0.00008950529,0.0001716698,0.00001143223,0.003953662,0.003805894],"genre_scores_gemma":[0.9279655,0.00004551175,0.06925254,0.0001535701,0.00006118517,0.00002137979,0.0006673097,0.00003868547,0.001794316],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9254358,"threshold_uncertainty_score":0.778586,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0163969870871684,"gpt":0.3182022068596486,"spread":0.3018052197724801,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001388879,0.0001705781,0.000211561,0.0001653576,0.000690171,0.0001643631,0.00123002,0.00003588365,0.0001150241],"category_scores_gemma":[0.0001677509,0.0001796069,0.00009231448,0.0003873542,0.0000174678,0.0002591246,0.001256254,0.0005098768,0.000004814703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001039884,"about_ca_system_score_gemma":0.0000295294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002368371,"about_ca_topic_score_gemma":0.00002690933,"domain_scores_codex":[0.9979177,0.0006217664,0.0002335621,0.0005380798,0.0003805377,0.0003084236],"domain_scores_gemma":[0.9990208,0.000243998,0.000136773,0.0004979799,0.00004159277,0.00005886767],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004262427,0.0003062868,0.009698974,0.00001878852,0.0001188466,0.00002384555,0.0140125,0.006243857,0.009222832,0.005080339,0.002294186,0.9529369],"study_design_scores_gemma":[0.001260932,0.001340103,0.001951416,0.000008758881,0.00003273455,0.00004606399,0.0007971368,0.7819194,0.004665144,0.001082651,0.2064294,0.0004662534],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01101777,0.000122662,0.9862059,0.000411941,0.000228625,0.0004184342,0.00001911473,0.001033173,0.0005424288],"genre_scores_gemma":[0.6411549,0.000001732769,0.3562974,0.0002839061,0.00007421859,0.000418426,0.00004608622,0.00003368786,0.00168963],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9524707,"threshold_uncertainty_score":0.7324156,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02022292529165426,"gpt":0.2277035892980059,"spread":0.2074806640063517,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003315537,0.0001006009,0.0001740591,0.00009621732,0.0002176428,0.00006347626,0.0003867713,0.00003023206,0.0001394189],"category_scores_gemma":[0.0001610169,0.00008665504,0.0000845584,0.0003898249,0.0000553336,0.0002299669,0.0002550141,0.0001321451,0.00001328379],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009766773,"about_ca_system_score_gemma":0.00001428046,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001694956,"about_ca_topic_score_gemma":0.00003946797,"domain_scores_codex":[0.9990678,0.00005297406,0.0002376425,0.0002355021,0.0001734002,0.0002326609],"domain_scores_gemma":[0.9993882,0.00006374675,0.000172939,0.000244938,0.00007989506,0.00005034305],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002711731,0.00009426518,0.06137426,0.00006335884,0.0001293745,0.00005148352,0.01494752,0.004734233,0.01794322,0.03113014,0.0003880468,0.869117],"study_design_scores_gemma":[0.000123555,0.0001766158,0.00067346,0.00002846875,0.000005711364,0.0000212216,0.00005939432,0.9851007,0.003244114,0.0003262044,0.01011668,0.0001238617],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3232002,0.0002795827,0.6373581,0.0002594111,0.0001967107,0.00006203264,6.458038e-7,0.0002136537,0.03842972],"genre_scores_gemma":[0.9645227,0.000002264589,0.0346398,0.0000636837,0.0001365892,0.000001429759,0.000001693978,0.000009479445,0.000622395],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9803665,"threshold_uncertainty_score":0.353369,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01742056865918662,"gpt":0.2137613535598668,"spread":0.1963407849006802,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002040697,0.0001994218,0.000218426,0.0001058718,0.0005187348,0.00008699376,0.0002780282,0.00006238967,0.00003289368],"category_scores_gemma":[0.00004505251,0.0001659608,0.00006346264,0.0004296942,0.0001126518,0.000457904,0.00006627644,0.000754912,0.00002625007],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003100316,"about_ca_system_score_gemma":0.00003263133,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000128821,"about_ca_topic_score_gemma":0.00004724006,"domain_scores_codex":[0.9984986,0.0002803241,0.0001794276,0.0004063539,0.0002775768,0.0003577238],"domain_scores_gemma":[0.9993672,0.0001545374,0.0000590841,0.0001988052,0.00009542579,0.0001249464],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002665934,0.0001210304,0.06045149,0.000008976011,0.0001554266,0.001090961,0.03459997,0.5545822,0.0005204579,0.02118206,0.0001283017,0.3268925],"study_design_scores_gemma":[0.0009070605,0.0002716848,0.01747042,0.00001374967,0.000006622525,0.0002906733,0.0003603757,0.9756056,0.0001243515,0.00001906465,0.00465089,0.0002795174],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1423052,0.0001060427,0.8531575,0.0005361345,0.0001182846,0.0001197594,3.503177e-7,0.0003124564,0.003344313],"genre_scores_gemma":[0.9934808,0.00001116986,0.004517776,0.0009409776,0.00008826278,0.000007541142,0.000007182613,0.0000234234,0.0009228415],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8511756,"threshold_uncertainty_score":0.6767686,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01398754244513691,"gpt":0.2622762930874399,"spread":0.248288750642303,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008790598,0.0001883851,0.0002460587,0.0001511756,0.0008204657,0.0002732738,0.001224219,0.00007211926,0.00002343752],"category_scores_gemma":[0.0003358697,0.000174717,0.00009175098,0.000126192,0.0001027459,0.0001660073,0.0002717081,0.0003793785,0.00002023444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002876841,"about_ca_system_score_gemma":0.00006879822,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003406058,"about_ca_topic_score_gemma":0.00001598638,"domain_scores_codex":[0.9984225,0.0001599166,0.0003113005,0.0004556554,0.0003610006,0.0002896278],"domain_scores_gemma":[0.9980095,0.0001408004,0.0005756723,0.001062518,0.0001125839,0.00009894643],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006069941,0.00006474873,0.02522526,0.00003167851,0.00001351754,0.000004390442,0.0002558941,0.5704937,0.001998224,0.002958967,0.00001662835,0.3989309],"study_design_scores_gemma":[0.0003733943,0.00006995167,0.01248809,0.00003870038,0.000008352923,0.000002929763,0.000005106876,0.9844541,0.001262059,0.0001298094,0.0009829859,0.0001844997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02380304,0.00007116527,0.9715343,0.0006062008,0.0001964085,0.00009690036,0.00000609109,0.0001824249,0.003503487],"genre_scores_gemma":[0.9123327,0.000003834147,0.08738801,0.00004129019,0.00004836518,0.000006747804,0.00003988406,0.00001518436,0.0001239877],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8885297,"threshold_uncertainty_score":0.7124751,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02920212809777676,"gpt":0.2944233762559669,"spread":0.2652212481581901,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003206258,0.00009612305,0.0001086057,0.0001566514,0.0002386401,0.000134972,0.0001570492,0.00004882121,0.00001052412],"category_scores_gemma":[0.0001968868,0.00008841565,0.00002872751,0.0005269215,0.00001108009,0.0002750973,0.00004411722,0.0001278328,0.000001779542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002120685,"about_ca_system_score_gemma":0.00001575529,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008028908,"about_ca_topic_score_gemma":0.000002432941,"domain_scores_codex":[0.9992681,0.00008959493,0.0001178039,0.0002801603,0.00008436137,0.0001599424],"domain_scores_gemma":[0.9995613,0.0001274054,0.00008814826,0.0000960203,0.00007979244,0.00004735521],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001046281,0.0000377578,0.0008529155,0.00004733189,0.00001313807,4.926761e-7,0.0004322148,0.1346472,0.001143438,0.113861,0.0000582397,0.7488959],"study_design_scores_gemma":[0.0002416843,0.0001424236,0.0001078416,0.000008839416,0.000007552001,0.000003754031,0.000002833794,0.9866405,0.00117633,0.01091189,0.0006455191,0.0001108165],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001461041,0.0002398729,0.9980432,0.0005926219,0.00002900058,0.0001132888,5.210749e-7,0.0001403373,0.0006951012],"genre_scores_gemma":[0.397453,0.000006734307,0.6019513,0.00008767148,0.00001229187,0.00001335919,0.00000156108,0.000006248431,0.000467873],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8519933,"threshold_uncertainty_score":0.3605485,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03753920172595036,"gpt":0.3002533892285696,"spread":0.2627141875026193,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003701344,0.0001542658,0.0001667323,0.00007918526,0.0007087478,0.0004547141,0.0009699623,0.0000488185,0.00001951468],"category_scores_gemma":[0.0001029738,0.0001559955,0.00001458286,0.0006789147,0.00006860532,0.0008125189,0.001023137,0.0002936498,0.00004198033],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003552941,"about_ca_system_score_gemma":0.0000981289,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002945277,"about_ca_topic_score_gemma":0.00009433382,"domain_scores_codex":[0.9984233,0.00006180941,0.0002225729,0.0008858397,0.000175914,0.0002305018],"domain_scores_gemma":[0.9985419,0.0001180692,0.0001484659,0.00101923,0.00007509573,0.00009725693],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003489172,0.00008847476,0.0006760365,0.00001311822,0.00005364435,0.000004315415,0.003580713,0.003745717,0.001633884,0.04002524,0.001315898,0.9488595],"study_design_scores_gemma":[0.0008853387,0.00008307632,0.001341436,0.00005149102,0.00004039467,0.00003055772,0.001040142,0.3001557,0.0003424087,0.0109295,0.6845813,0.0005186581],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002306023,0.0007565612,0.9560457,0.03923559,0.00006363491,0.0002473829,0.0001198334,0.0003638764,0.0008613496],"genre_scores_gemma":[0.04779921,0.0001914961,0.9499408,0.0001403692,0.0005897279,0.00009823155,0.0008415366,0.00002270383,0.0003759012],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9483408,"threshold_uncertainty_score":0.6361313,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03659510899503107,"gpt":0.2458099770528048,"spread":0.2092148680577738,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007216242,0.0002223244,0.0002093377,0.0003540307,0.0002569882,0.0001041984,0.0006113523,0.00009321766,0.0001205005],"category_scores_gemma":[0.0002114064,0.0002308274,0.00005644726,0.0006207123,0.00002503876,0.0006239088,0.0003533966,0.00097225,0.0001206922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001402561,"about_ca_system_score_gemma":0.00005610281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002680055,"about_ca_topic_score_gemma":0.0000318904,"domain_scores_codex":[0.9980894,0.0001728688,0.0004156024,0.0004235083,0.0003762011,0.0005224266],"domain_scores_gemma":[0.9993745,0.00005099835,0.0002081631,0.0002175094,0.00005672291,0.00009208832],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009690553,0.00001458183,0.04922677,0.00001096968,0.000008971184,0.000007598156,0.002684168,0.9377872,0.0004790688,0.006791615,0.00001469348,0.002964642],"study_design_scores_gemma":[0.0003952052,0.0002499803,0.003296698,0.00002753902,0.000004315214,0.00001002968,0.00003269272,0.9940863,0.000327656,0.0002444906,0.001066779,0.0002582959],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01163006,0.00003226135,0.9523351,0.00005427527,0.0000875936,0.0001445649,2.475887e-8,0.0004751324,0.03524103],"genre_scores_gemma":[0.9450121,0.00002299886,0.04760224,0.0001200191,0.0000261649,0.00001701222,0.000004783786,0.00002597894,0.007168737],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.933382,"threshold_uncertainty_score":0.9412867,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.008191670648523592,"gpt":0.2716978941340115,"spread":0.2635062234854879,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001536593,0.0001221794,0.0001599744,0.00008007927,0.00008690701,0.0000736852,0.0007071173,0.00005212107,0.0004100142],"category_scores_gemma":[0.0003327306,0.00009858245,0.00002972036,0.0003117051,0.00004975966,0.0003142184,0.000189349,0.0004304693,0.00001577606],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001335261,"about_ca_system_score_gemma":0.00002965672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008668214,"about_ca_topic_score_gemma":0.00001096693,"domain_scores_codex":[0.9990522,0.00007806964,0.0001900482,0.0002425479,0.0002425468,0.0001945756],"domain_scores_gemma":[0.9993374,0.0001353575,0.00007761598,0.0003502637,0.00004222268,0.0000570828],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001896119,0.0000495278,0.001096359,0.0001260178,0.00001611835,0.00003395863,0.001260695,0.006314202,0.01207959,0.05179463,0.00006570503,0.9271442],"study_design_scores_gemma":[0.0002996453,0.0001484544,0.0004048655,0.0001741139,0.00001254947,0.00005964027,0.000008980785,0.9551142,0.006100874,0.03662026,0.0007124164,0.0003440283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04429649,0.0007839841,0.9538499,0.0002157726,0.00003158504,0.00008216453,0.000005691332,0.000452473,0.0002819761],"genre_scores_gemma":[0.7306654,0.000002634991,0.2690635,0.00005866955,0.00001820938,0.000001636101,0.00001092828,0.000006665837,0.0001723092],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9488,"threshold_uncertainty_score":0.4489368,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02645328759020278,"gpt":0.2968939080229041,"spread":0.2704406204327013,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004805815,0.0002053966,0.0002129102,0.000196269,0.0003094629,0.0003278538,0.0008676764,0.0001144661,0.000009719724],"category_scores_gemma":[0.0005149575,0.0001917604,0.00005686011,0.0004933618,0.00001932623,0.0003492356,0.0001043419,0.0008765738,0.00005611171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005727802,"about_ca_system_score_gemma":0.00003375792,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001422861,"about_ca_topic_score_gemma":0.000002045042,"domain_scores_codex":[0.9982787,0.0002029769,0.0002491153,0.0006068752,0.000347257,0.0003150513],"domain_scores_gemma":[0.9991418,0.0001016077,0.0001854754,0.0003623346,0.00008147995,0.0001272689],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003969925,0.0001871108,0.009763365,0.00001652855,0.00001806347,0.00003240375,0.006913859,0.004619214,0.1098906,0.01669215,0.0003009111,0.8515261],"study_design_scores_gemma":[0.000373118,0.0002603056,0.006326989,0.00005757127,0.00000918299,0.00002158564,0.0001057911,0.9635597,0.01710908,0.005114126,0.006532614,0.0005298763],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0351734,0.0007605026,0.9562909,0.000812099,0.00005969527,0.0001954334,9.956696e-7,0.002126655,0.004580319],"genre_scores_gemma":[0.6150366,0.000002621679,0.3840418,0.0003521319,0.00007186423,0.000006828438,0.00004108115,0.00001139572,0.0004356901],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9589406,"threshold_uncertainty_score":0.7819762,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03764273235022859,"gpt":0.2966816643115067,"spread":0.2590389319612781,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003345655,0.0001375063,0.0001603629,0.0001818813,0.0001806168,0.00005653328,0.0003859206,0.00005286379,0.00003035552],"category_scores_gemma":[0.0002429973,0.0001339749,0.00005190498,0.0003440278,0.00004696053,0.0004260783,0.0001808875,0.0003305243,0.0001280075],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008306299,"about_ca_system_score_gemma":0.00002130212,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001788896,"about_ca_topic_score_gemma":0.00007562769,"domain_scores_codex":[0.998661,0.0002141119,0.0002483529,0.0003585917,0.000238507,0.0002794191],"domain_scores_gemma":[0.9993294,0.0002667987,0.00005631847,0.0002399781,0.000043848,0.00006366716],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003474664,0.000144986,0.5857219,0.00001571229,0.00001816622,0.0002924919,0.02084159,0.04344433,0.01190239,0.005331567,0.00008559016,0.3321666],"study_design_scores_gemma":[0.0001987975,0.0002554482,0.320691,0.0000523973,0.000004001693,0.00006515336,0.0002210228,0.6581988,0.01634379,0.002001703,0.00152775,0.0004401961],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7460401,0.00008807688,0.2517368,0.0002728005,0.0001649276,0.0001984191,2.344891e-7,0.0001751753,0.001323451],"genre_scores_gemma":[0.9959393,0.00001988257,0.003562792,0.0001097867,0.00005400102,0.00004496312,0.000003942466,0.00001333956,0.0002520212],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6147544,"threshold_uncertainty_score":0.5463337,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.008890312988525221,"gpt":0.2275228686149516,"spread":0.2186325556264264,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005688433,0.0003946241,0.0003928526,0.0003095522,0.001278806,0.0001613861,0.0007242685,0.0001573153,0.0007879743],"category_scores_gemma":[0.0003964115,0.0003718235,0.0001590052,0.0007008491,0.0001181907,0.0005140189,0.0001784027,0.002460632,0.0009611085],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009025284,"about_ca_system_score_gemma":0.00006276917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001617609,"about_ca_topic_score_gemma":0.00000848601,"domain_scores_codex":[0.9968281,0.0005698353,0.0003707193,0.0009334915,0.0007056785,0.000592224],"domain_scores_gemma":[0.9989538,0.0001666913,0.0001081664,0.0004620808,0.0001160433,0.0001932139],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002567587,0.0008325949,0.05178255,0.00008479229,0.0002714489,0.0007369092,0.02946937,0.2141461,0.001318973,0.01075892,0.2398761,0.4504654],"study_design_scores_gemma":[0.0006212395,0.000646625,0.002408643,0.00001900998,0.00000841886,0.0001544445,0.00007551398,0.0448727,0.0004673295,0.00005347642,0.9502189,0.0004537583],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"editorial","genre_scores_codex":[0.2612262,0.0007111621,0.3366117,0.0522076,0.159786,0.001491287,0.00001065945,0.008427576,0.1795277],"genre_scores_gemma":[0.40962,0.00009690686,0.007966585,0.0005076468,0.5457221,0.0000314741,0.00005763916,0.000107381,0.03589034],"genre_candidate":"editorial","genre_consensus":null,"teacher_disagreement_score":0.7103427,"threshold_uncertainty_score":0.9998734,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04624489143412698,"gpt":0.3420139273379866,"spread":0.2957690359038596,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002216231,0.0001214172,0.0003353799,0.0003631206,0.0001729062,0.0003481579,0.0004712337,0.00003024329,0.004644611],"category_scores_gemma":[0.001595933,0.00009785692,0.0001163776,0.001287398,0.00001427187,0.0003879255,0.0001868297,0.0001709881,0.0001346495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000889328,"about_ca_system_score_gemma":0.00005553258,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.6159591,"about_ca_topic_score_gemma":0.8754703,"domain_scores_codex":[0.9978137,0.0002065833,0.0004643078,0.0004415689,0.0007535646,0.0003202565],"domain_scores_gemma":[0.9984389,0.0008739962,0.0001803711,0.0003421481,0.00008274517,0.0000818425],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001768339,0.00004634386,0.8881738,0.00001269173,0.0001364075,0.00000740321,0.0007724999,0.03105039,0.00003872635,0.0004526366,0.01818006,0.06111131],"study_design_scores_gemma":[0.000270056,0.00001981184,0.6950224,0.000004924984,0.00005391429,4.351546e-7,0.0004829012,0.2101982,0.000004546389,0.0004405001,0.09335497,0.0001473401],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9798911,0.0001607412,0.01423131,0.002454866,0.0001921579,0.0004087439,0.00005883382,0.0000412942,0.002560906],"genre_scores_gemma":[0.9935564,0.000004689102,0.0004444872,0.0003050841,0.00003867074,0.00001028027,0.0001176236,0.00000844991,0.005514347],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2595113,"threshold_uncertainty_score":0.9962653,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05879960194168286,"gpt":0.3125807566459934,"spread":0.2537811547043106,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005686749,0.000172207,0.0001874107,0.00004400946,0.001120714,0.0008089757,0.003498006,0.00005366423,0.0001161351],"category_scores_gemma":[0.0001590523,0.0001634417,0.00003695088,0.0000753178,0.00008578411,0.001211734,0.003305282,0.0003248152,0.00006062937],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002057658,"about_ca_system_score_gemma":0.00004405221,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004129658,"about_ca_topic_score_gemma":0.0002712901,"domain_scores_codex":[0.9983644,0.00008489569,0.0002065011,0.0007585891,0.0002768643,0.0003087171],"domain_scores_gemma":[0.9966361,0.00007907169,0.0002699666,0.002876377,0.00003650036,0.0001019766],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002440945,0.00003876432,0.01538715,0.000004985621,0.0000246906,0.00003509751,0.0002845095,0.00007648231,0.00004786681,0.000409608,0.0006509818,0.9830374],"study_design_scores_gemma":[0.0003511694,0.00004591999,0.06178391,0.00002298021,0.00001390551,0.00001652728,0.00003664312,0.9278268,0.0001031112,0.0001538281,0.009432988,0.0002122329],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1718157,0.0000685359,0.8233526,0.001074016,0.0004239157,0.0001477573,0.0002409393,0.0002911959,0.002585385],"genre_scores_gemma":[0.9496348,0.000005069053,0.04922511,0.00009558949,0.0001555582,0.000009547011,0.0002691697,0.00001556256,0.0005895962],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9828252,"threshold_uncertainty_score":0.8619737,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0236781237239863,"gpt":0.2688267466209545,"spread":0.2451486228969682,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007951796,0.0001812771,0.0002714144,0.00006894515,0.0009422855,0.0003424555,0.001172472,0.00009315616,0.00002851358],"category_scores_gemma":[0.000500457,0.0001663968,0.0001121885,0.0001240964,0.0001092641,0.0001339652,0.0004695598,0.0006754032,0.00002678577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002169454,"about_ca_system_score_gemma":0.00004372522,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001419782,"about_ca_topic_score_gemma":0.000007473984,"domain_scores_codex":[0.9983598,0.0002004825,0.0002912259,0.0004147691,0.0002910925,0.0004426575],"domain_scores_gemma":[0.9985256,0.0001649703,0.000396394,0.0007205906,0.00006969879,0.0001227076],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001231169,0.000033899,0.06130218,0.00002270094,0.00002944164,0.00001651055,0.0006406415,0.8060865,0.0004153427,0.02168654,0.00008081683,0.1096731],"study_design_scores_gemma":[0.0002087989,0.0001149106,0.005686233,0.00006878063,0.000008151313,0.000007126202,0.00001385792,0.9908013,0.0001320059,0.001319818,0.001446377,0.0001926808],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05817106,0.0001642226,0.9338402,0.0005169275,0.000296758,0.00006476542,3.141679e-7,0.0001779488,0.006767762],"genre_scores_gemma":[0.9632102,0.00001047643,0.03583412,0.00007132355,0.00009218294,0.000004662114,0.000001839113,0.00001643421,0.0007587433],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9050392,"threshold_uncertainty_score":0.7247394,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1080163299644204,"gpt":0.3251848710978835,"spread":0.2171685411334631,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001865036,0.0001520026,0.0001593733,0.0001136635,0.0004956863,0.0001298103,0.000938092,0.0001000653,0.00002131797],"category_scores_gemma":[0.0002310421,0.0001459513,0.00005476489,0.0002964301,0.00003687216,0.001397653,0.0006749034,0.0008150415,0.00004669587],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002110224,"about_ca_system_score_gemma":0.00004552396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006209753,"about_ca_topic_score_gemma":0.000003238019,"domain_scores_codex":[0.9981881,0.0002440046,0.0002298526,0.0004462218,0.0003617594,0.0005300961],"domain_scores_gemma":[0.9987006,0.0004410997,0.00007231951,0.0005101156,0.00009439077,0.0001814508],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003052359,0.0001283442,0.03767888,0.00005151398,0.00005717952,0.000002993431,0.002228827,0.3903852,0.0004369548,0.4455559,0.0002205878,0.1232231],"study_design_scores_gemma":[0.0002124363,0.00006863719,0.0009216222,0.00001476102,0.00001004571,0.00001878981,0.00001427839,0.9872767,0.00001889734,0.007100739,0.004156112,0.0001869438],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00800156,0.0004079077,0.9889213,0.0009642449,0.0001494467,0.0001045076,0.00000385116,0.0002789935,0.001168194],"genre_scores_gemma":[0.8371568,0.00001373343,0.1618637,0.0001366683,0.0001893221,0.000009236772,0.0001071692,0.00001852752,0.0005048654],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8291553,"threshold_uncertainty_score":0.595172,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Machine learning; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.0385424843247923,"gpt":0.3639158091002024,"spread":0.3253733247754101,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006608437,0.0001098201,0.0002252641,0.000476814,0.00009858361,0.0001301749,0.0005084097,0.00005464385,0.00001774563],"category_scores_gemma":[0.00007636415,0.00009833213,0.0001277267,0.001575593,0.00003018467,0.0003798237,0.00009610483,0.0001965219,0.000005518411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008525913,"about_ca_system_score_gemma":0.00006897278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005158606,"about_ca_topic_score_gemma":0.000002404414,"domain_scores_codex":[0.9987916,0.00007597259,0.0003221052,0.0004027307,0.0002345013,0.0001730865],"domain_scores_gemma":[0.9990535,0.0002341208,0.0001255892,0.0004541644,0.00009603596,0.00003652575],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002011132,0.0001420359,0.3650208,0.0003686534,0.0007687629,0.000002430708,0.000970721,0.007109936,0.04656546,0.1615127,0.001520892,0.4159975],"study_design_scores_gemma":[0.00006167423,0.00007099031,0.1288364,0.00001801263,0.00007347651,8.269856e-7,0.000006957651,0.8422994,0.001633587,0.0001761679,0.02672972,0.00009273946],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01192235,0.00009733842,0.9847929,0.001092578,0.00009992925,0.0001656775,0.00001717364,0.0005798422,0.001232197],"genre_scores_gemma":[0.8673596,0.00003926843,0.1319536,0.00005645655,0.00002256784,0.00008065172,0.000181885,0.000009805745,0.0002961593],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8554372,"threshold_uncertainty_score":0.4009868,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02059995532552589,"gpt":0.2184018720110732,"spread":0.1978019166855473,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001338331,0.0001118297,0.00009792268,0.00005379979,0.0001962446,0.0001899173,0.0002476859,0.00003650377,0.0001053973],"category_scores_gemma":[0.00002326152,0.00009063886,0.00001529834,0.0001441278,0.00002251934,0.0003793561,0.00007724101,0.0003085666,0.0001727749],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001451417,"about_ca_system_score_gemma":0.00003937511,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003226472,"about_ca_topic_score_gemma":0.000006012023,"domain_scores_codex":[0.9991066,0.00005871746,0.0001421248,0.0002499501,0.0002282596,0.0002143776],"domain_scores_gemma":[0.9994701,0.0001050166,0.00006689646,0.0001741395,0.0001041287,0.0000797701],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001470843,0.000009300993,0.003125506,0.000004032704,0.000006763947,0.00000373435,0.0002497934,0.8896706,0.00002533365,0.08925141,0.0001937295,0.0174584],"study_design_scores_gemma":[0.0001106153,0.00006418794,0.000444516,0.00001787296,0.000002530338,0.00001184837,0.00000571978,0.9856355,0.00001163721,0.01246185,0.001098243,0.0001355019],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007150881,0.00008240418,0.9898258,0.0005995063,0.00004206261,0.00005797969,0.000001322186,0.000190444,0.002049565],"genre_scores_gemma":[0.5754327,0.000005190223,0.4237304,0.000120705,0.0000197471,0.000006280141,0.000009391008,0.000007837632,0.0006678436],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5682818,"threshold_uncertainty_score":0.3696145,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.007289067483415066,"gpt":0.2487845836266911,"spread":0.2414955161432761,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005017774,0.0002178517,0.0001881807,0.0001216674,0.0006649382,0.0002418198,0.0007227446,0.00007958899,0.000144759],"category_scores_gemma":[0.000298946,0.0001750559,0.00009979492,0.0004058114,0.00006353128,0.0003388436,0.0003552301,0.001747164,0.0001314782],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001906425,"about_ca_system_score_gemma":0.00007214204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002018588,"about_ca_topic_score_gemma":0.00002836106,"domain_scores_codex":[0.9983602,0.000172396,0.0002234292,0.0005467475,0.0002862847,0.0004109089],"domain_scores_gemma":[0.9989793,0.0001016602,0.0001296975,0.0005805941,0.00004826011,0.0001604408],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004636502,0.0005256082,0.1136856,0.00006384259,0.00009480157,0.0001404878,0.001395297,0.005352559,0.0818256,0.04997005,0.0163291,0.7305707],"study_design_scores_gemma":[0.000886901,0.0001658896,0.04955398,0.00004666611,0.00001690748,0.0002562029,0.0000203186,0.5471185,0.004837621,0.001344535,0.3949876,0.0007649258],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4420711,0.0005948577,0.5106109,0.02247793,0.003998741,0.0003396248,0.00001311282,0.002538079,0.01735567],"genre_scores_gemma":[0.960389,0.000006329265,0.03523689,0.0002029106,0.0006739346,0.000009796407,0.00005440487,0.00002204036,0.003404668],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7298058,"threshold_uncertainty_score":0.7590656,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.078163754291518,"gpt":0.388055020704645,"spread":0.309891266413127,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007368358,0.000104659,0.0001422891,0.000193121,0.0006868014,0.0001325143,0.0002614168,0.00003913007,0.0006382599],"category_scores_gemma":[0.0003906069,0.00007479454,0.00007358244,0.0006638383,0.00006398577,0.000165147,0.00004550635,0.0001640857,0.0001452291],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002193785,"about_ca_system_score_gemma":0.00001962091,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008279159,"about_ca_topic_score_gemma":0.0001421292,"domain_scores_codex":[0.9987466,0.0000911989,0.0003029613,0.0003258582,0.0003487313,0.0001846324],"domain_scores_gemma":[0.9989145,0.0004725888,0.0001841863,0.0002488401,0.0001289421,0.00005096156],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002339838,0.0006535295,0.1796473,0.00001673344,0.00008483805,0.000007663015,0.0007695907,0.2270945,0.003678883,0.1832992,0.0245124,0.3800014],"study_design_scores_gemma":[0.0006171917,0.0001137453,0.03011006,0.00001161985,0.00002636656,0.00002470609,0.0005063548,0.05708013,0.0002209783,0.04622293,0.8648502,0.0002156993],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5606782,0.00006358048,0.4287493,0.002672525,0.0001642516,0.0003025006,0.00006053163,0.0002321913,0.007076926],"genre_scores_gemma":[0.9362422,0.000001582622,0.01358912,0.0001040727,0.0003329671,0.00004367476,0.00008763644,0.00001897879,0.04957978],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8403378,"threshold_uncertainty_score":0.6988499,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01774311274098981,"gpt":0.2584472404064356,"spread":0.2407041276654458,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007815713,0.0002298522,0.0002394414,0.0001057765,0.0004155873,0.0002372735,0.0005236263,0.00008618039,0.00006289459],"category_scores_gemma":[0.0001068547,0.0001708192,0.00006105781,0.0003966462,0.00003858388,0.0005303113,0.0001742375,0.0008546045,0.00006782187],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003571688,"about_ca_system_score_gemma":0.00002677015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008725728,"about_ca_topic_score_gemma":0.0000209318,"domain_scores_codex":[0.9982733,0.000253394,0.0002113214,0.0003382991,0.000311093,0.0006126284],"domain_scores_gemma":[0.9990054,0.0002892764,0.0001334831,0.0003036338,0.00005232242,0.0002158436],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003421945,0.00005296884,0.2187593,0.000005123642,0.00001881941,0.00001174407,0.0006144134,0.5593005,0.00007402664,0.004894469,0.0001358599,0.2160986],"study_design_scores_gemma":[0.000292187,0.0002746403,0.02652886,0.00006582365,0.000009140877,0.00006129926,0.00003231734,0.9691864,0.00002116234,0.0003377432,0.002910841,0.0002796428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04961438,0.0008554627,0.944623,0.0002900875,0.0001597173,0.00006081942,1.491253e-7,0.0004362843,0.003960105],"genre_scores_gemma":[0.9468732,0.00003864702,0.05210017,0.0001969194,0.0001547185,0.000002846662,0.000006641545,0.00002156163,0.0006053128],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8972588,"threshold_uncertainty_score":0.6965806,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01568724593190495,"gpt":0.2629992289349489,"spread":0.2473119830030439,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004868242,0.0001414666,0.000145502,0.00004748182,0.0002771956,0.0001625171,0.0006633482,0.00003990721,0.00007536501],"category_scores_gemma":[0.00006241328,0.0001031102,0.00004560754,0.000119502,0.00002720913,0.0002645339,0.000440792,0.0004790771,0.00009269647],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005357061,"about_ca_system_score_gemma":0.00002265732,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001570934,"about_ca_topic_score_gemma":0.00002728787,"domain_scores_codex":[0.9985775,0.0001663106,0.0002381417,0.0003310402,0.0003213581,0.0003656601],"domain_scores_gemma":[0.9992224,0.0001481433,0.0000801576,0.0004399618,0.00002496547,0.00008438594],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005801075,0.0000400776,0.002465698,0.000008754802,0.00001843728,0.00003218776,0.004614748,0.6607096,0.0006818054,0.1675471,0.00003881834,0.163837],"study_design_scores_gemma":[0.0002703135,0.00003166196,0.0003770668,0.000008222753,0.000005176218,0.00002390172,0.00002437863,0.9901963,0.0001117959,0.003860506,0.004961915,0.000128799],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05609526,0.0002453371,0.9397546,0.002084111,0.0001125145,0.0001058637,0.000001170526,0.0002564914,0.001344641],"genre_scores_gemma":[0.8941785,0.000005206549,0.1046262,0.0004627486,0.0001182841,0.000008327413,0.000006617094,0.00001469042,0.0005793872],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8380832,"threshold_uncertainty_score":0.4204711,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.08089650883186325,"gpt":0.4011498157716262,"spread":0.3202533069397629,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003003023,0.0002493677,0.0004391629,0.0006968646,0.0004118716,0.0002020482,0.0007106852,0.0001255028,0.0003592327],"category_scores_gemma":[0.008214424,0.0002109508,0.0001497018,0.001897986,0.0001732073,0.000482346,0.0002618479,0.0009010268,0.00005347026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002187628,"about_ca_system_score_gemma":0.0001385393,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001294221,"about_ca_topic_score_gemma":0.001938931,"domain_scores_codex":[0.9959083,0.0006604195,0.0007092793,0.0007876571,0.001204333,0.0007299988],"domain_scores_gemma":[0.9951629,0.003787233,0.0002885261,0.0003442329,0.0003034299,0.0001136607],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005998042,0.0002145973,0.03057921,0.00001275057,0.00001072673,0.00005188862,0.0003369952,0.8540382,0.0003641148,0.000191316,0.0003324749,0.1132679],"study_design_scores_gemma":[0.003686975,0.0004011752,0.01384888,0.0000211488,0.000006797649,0.000004440587,0.001591389,0.9368796,0.0003450471,0.002076627,0.04083505,0.0003028924],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7899686,0.0005772659,0.2037032,0.001015474,0.0004276768,0.0006337576,0.00004691191,0.0003287155,0.003298382],"genre_scores_gemma":[0.9821376,0.00001068364,0.004363265,0.00002465705,0.0002112475,0.000017109,0.0001423359,0.00004487902,0.01304825],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.19934,"threshold_uncertainty_score":0.9834027,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02131954762480759,"gpt":0.2423029124869489,"spread":0.2209833648621413,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001056149,0.00008364351,0.000101181,0.0002024455,0.000349006,0.0000571128,0.0003733576,0.00002152049,0.0001388951],"category_scores_gemma":[0.0003238167,0.00007581317,0.00003388252,0.001100514,0.00001701498,0.0001598003,0.0001341104,0.0002777131,0.000003929924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006198621,"about_ca_system_score_gemma":0.00003599824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006140406,"about_ca_topic_score_gemma":0.00001497051,"domain_scores_codex":[0.9980544,0.0008965424,0.0002496894,0.0002560438,0.0004107815,0.0001325153],"domain_scores_gemma":[0.9991592,0.0002707758,0.0002374675,0.0002742243,0.00003777714,0.00002054023],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001256829,0.0000236936,0.00471676,0.000002690027,0.000001849165,0.000001249844,0.0009762855,0.6889799,0.0005977808,0.3005989,0.00002479788,0.00406345],"study_design_scores_gemma":[0.0004554857,0.00008370064,0.01054604,0.00001315497,0.000001379657,0.000001853198,0.0001174061,0.979813,0.0003992792,0.006888104,0.001593934,0.00008659095],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1252363,0.00007076799,0.8678458,0.003597886,0.0001394008,0.000232698,0.00000156947,0.0000865542,0.002789021],"genre_scores_gemma":[0.9896374,0.000003103518,0.0088507,0.0008406352,0.00001472963,0.00004173554,0.00005185059,0.00001133828,0.0005485404],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8644011,"threshold_uncertainty_score":0.3091572,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01658300116235805,"gpt":0.2395982148126154,"spread":0.2230152136502573,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002918722,0.0001450137,0.0001573854,0.0001178378,0.00009442199,0.0001193809,0.0003041344,0.00005642854,0.000002441432],"category_scores_gemma":[0.0001688785,0.00008974049,0.00001679397,0.0001849298,0.00008317314,0.0004624258,0.0001989041,0.0002420102,0.000002818404],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001691797,"about_ca_system_score_gemma":0.00004714571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001405031,"about_ca_topic_score_gemma":0.000135474,"domain_scores_codex":[0.9988675,0.00009864787,0.0001760775,0.0004204226,0.0001562552,0.000281148],"domain_scores_gemma":[0.9993203,0.0002685098,0.00006577579,0.0002212892,0.00003404277,0.00009011781],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002914889,0.00005267363,0.08187241,0.0000546692,0.000008081925,0.00006647416,0.001159135,0.01443205,0.003197924,0.1517634,7.32503e-7,0.7473633],"study_design_scores_gemma":[0.0003688388,0.0001553219,0.004687975,0.0001304782,0.00000270073,0.00002101583,0.00000611166,0.957545,0.00006759081,0.0368172,0.000008872928,0.0001889371],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2805975,0.00006168164,0.7185951,0.0004081553,0.00001514668,0.00005725668,3.808294e-7,0.0001090622,0.0001557448],"genre_scores_gemma":[0.9741856,0.00002032965,0.02565612,0.00006027153,0.00001155216,0.00001473416,3.41991e-7,0.000009638503,0.00004137065],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9431129,"threshold_uncertainty_score":0.3659511,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}