{"meta":{"query_hash":"d2dce2612f16","filters":{"venue":"Statisctics and computing/Statistics and computing"},"cohort_total":14,"direct_labels_cover":0,"predictions_cover":14,"exported":14,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/d2dce2612f16","api":"https://metacan.xera.ac/api/v1/cohort?venue=Statisctics+and+computing%2FStatistics+and+computing"},"results":[{"id":"W4252485560","doi":"10.1007/978-1-4614-9020-3_1","title":"Introducing R","year":2013,"lang":"en","type":"book-chapter","venue":"Statisctics and computing/Statistics and computing","topic":"Data Analysis with R","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"clone (Java method); Programming language; Computer science; Software; Window (computing); Code (set theory); Statistical software; Statistical analysis; Software engineering; Computer graphics (images); Mathematics; Operating system; Statistics; Biology","score_opus":0.011258339251950881,"score_gpt":0.23467820354921362,"score_spread":0.22341986429726274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4252485560","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001429077,0.0012324895,0.961753,0.00027062785,0.0006174967,0.0002913915,0.00016048871,0.00018279067,0.03534882],"genre_scores_gemma":[0.0191096,0.0006917922,0.9460507,0.00072705717,0.0006698564,0.0000021491078,0.00022743928,0.00013596,0.03238544],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961247,0.00006520678,0.0010319224,0.0015004869,0.0005792312,0.0006984772],"domain_scores_gemma":[0.9966124,0.0008696775,0.00087767193,0.0009764629,0.0002914469,0.00037231477],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005042443,0.0007662112,0.000983391,0.0003458363,0.00069472124,0.0015926644,0.00084579206,0.0002452873,0.00006409719],"category_scores_gemma":[0.00008761522,0.00077667035,0.00008334391,0.00012787992,0.0002619803,0.000227741,0.0021909955,0.00083185267,0.00007121275],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013178825,0.000010613006,0.000034062257,0.00010844105,0.00013155633,0.000049276292,0.00037314926,0.00012976868,0.0000037540576,0.6530789,0.005837354,0.3402418],"study_design_scores_gemma":[0.00039236536,0.00017593431,0.0003003741,0.00033575794,0.00017108057,0.00014707574,0.000043609303,0.7915807,0.0000037824695,0.17691766,0.028864145,0.0010675208],"about_ca_topic_score_codex":0.00006276633,"about_ca_topic_score_gemma":0.000010323529,"teacher_disagreement_score":0.7914509,"about_ca_system_score_codex":0.000045137163,"about_ca_system_score_gemma":0.00012236505,"threshold_uncertainty_score":0.99946845},"labels":[],"label_agreement":null},{"id":"W4385486326","doi":"10.1007/978-3-031-33390-3_13","title":"Feature Engineering","year":2023,"lang":"en","type":"book-chapter","venue":"Statisctics and computing/Statistics and computing","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Feature engineering; Feature (linguistics); Computer science; Artificial intelligence; Logarithm; Data mining; Machine learning; Mathematics; Deep learning","score_opus":0.012205269216241557,"score_gpt":0.24356324849001937,"score_spread":0.23135797927377783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385486326","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00993752,0.013035169,0.9416732,0.0011659631,0.0034556207,0.0008609622,0.001943325,0.00058870274,0.027339494],"genre_scores_gemma":[0.09352043,0.007632566,0.56171477,0.0011487048,0.0039538993,0.0000074263894,0.0026859439,0.00077883474,0.3285574],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983175,0.000018198474,0.00033538623,0.00068633474,0.00021898776,0.00042358474],"domain_scores_gemma":[0.9989843,0.00023723731,0.00024292502,0.0002564819,0.00008513236,0.00019395548],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021609705,0.00046693854,0.00046501923,0.00010302573,0.00026298506,0.00014523762,0.0001665682,0.00046789338,0.0000046444793],"category_scores_gemma":[0.00013155774,0.00046967668,0.00006091475,0.00004056761,0.00021888451,0.0000015693124,0.0005818211,0.00050758646,0.000006392142],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004085829,0.000025011386,0.00025981315,0.0007712983,0.000593904,0.00021645901,0.00039055088,0.00034492702,0.000515927,0.25642008,0.04257757,0.6978436],"study_design_scores_gemma":[0.0020051901,0.0017543786,0.0031832897,0.0016229494,0.00048854854,0.0004994876,0.00031596495,0.18384542,0.0001325795,0.032437135,0.7703181,0.0033969914],"about_ca_topic_score_codex":0.0000051666334,"about_ca_topic_score_gemma":0.000006327385,"teacher_disagreement_score":0.7277405,"about_ca_system_score_codex":0.000008844573,"about_ca_system_score_gemma":0.000060096932,"threshold_uncertainty_score":0.99977547},"labels":[],"label_agreement":null},{"id":"W4385486382","doi":"10.1007/978-3-031-33390-3_12","title":"Support Vector Machines","year":2023,"lang":"en","type":"book-chapter","venue":"Statisctics and computing/Statistics and computing","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Hyperplane; Support vector machine; Mathematics; Real line; Separable space; Space (punctuation); Quadratic equation; Line (geometry); Kernel (algebra); Class (philosophy); Artificial intelligence; Combinatorics; Computer science","score_opus":0.017994683128614863,"score_gpt":0.26465094730332434,"score_spread":0.24665626417470948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385486382","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007011134,0.00019124131,0.9699002,0.0002895586,0.00045178173,0.00032062156,0.00026085923,0.0006299353,0.027885715],"genre_scores_gemma":[0.053296775,0.0014807018,0.8056377,0.0008314126,0.0007628397,0.000012905353,0.00026845429,0.00027944727,0.13742976],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997498,0.000027535534,0.00071754126,0.0009503675,0.0003483872,0.00045819336],"domain_scores_gemma":[0.99798024,0.0005504941,0.00054184726,0.0005231243,0.00016311594,0.00024118568],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003015983,0.00053057674,0.00057601585,0.00023714988,0.0007466553,0.00059675676,0.00048578638,0.00022846845,0.000022386039],"category_scores_gemma":[0.000027112508,0.0005547054,0.0000767111,0.00013171649,0.00018968855,0.00007777404,0.0011169981,0.0005798369,0.000038063754],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000141473,0.0000086283535,0.000021809781,0.000078310775,0.00004345274,0.000035279645,0.0001839961,0.000017489348,0.000004648055,0.7302947,0.002788967,0.2665213],"study_design_scores_gemma":[0.00032227964,0.00036491643,0.00085429393,0.00020408332,0.000090670095,0.00018981291,0.000026814869,0.53066826,0.00001259514,0.42124096,0.04497031,0.0010550038],"about_ca_topic_score_codex":0.000027688815,"about_ca_topic_score_gemma":0.0000095147325,"teacher_disagreement_score":0.53065073,"about_ca_system_score_codex":0.000026818727,"about_ca_system_score_gemma":0.000093688104,"threshold_uncertainty_score":0.9996905},"labels":[],"label_agreement":null},{"id":"W4385486392","doi":"10.1007/978-3-031-33390-3_11","title":"Boosting","year":2023,"lang":"en","type":"book-chapter","venue":"Statisctics and computing/Statistics and computing","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Boosting (machine learning); Gradient boosting; Multinomial logistic regression; Artificial intelligence; Computer science; Machine learning; AdaBoost; Random forest; Mathematics; Classifier (UML)","score_opus":0.034862397596778456,"score_gpt":0.2658821743200783,"score_spread":0.23101977672329987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385486392","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011706051,0.00070915115,0.9632402,0.00020625745,0.00079115963,0.00020529397,0.00013083783,0.00045716544,0.03414287],"genre_scores_gemma":[0.08974124,0.0016190881,0.8383316,0.00091177644,0.0007908524,0.0000031191905,0.00015570276,0.00029467314,0.068152],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99666107,0.0000500097,0.0008822267,0.0012052943,0.0004975571,0.000703853],"domain_scores_gemma":[0.9971252,0.0011678291,0.00060662883,0.0005351715,0.00022596322,0.0003391738],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005451122,0.00068584393,0.00075483444,0.00025554237,0.0008120132,0.0010098278,0.0006006699,0.0002969482,0.000007199894],"category_scores_gemma":[0.00008832846,0.0007338351,0.000072245144,0.00012227942,0.00022413972,0.00010775136,0.0015467636,0.00090843014,0.000036996917],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017933785,0.00000660789,0.000020380563,0.00013070062,0.000055979865,0.000096815354,0.0004530204,0.00016973753,0.0000031754778,0.7006793,0.0009598143,0.29742268],"study_design_scores_gemma":[0.00023268486,0.00014132503,0.00013837665,0.00050343346,0.000054846798,0.00009705179,0.000032463286,0.6431707,0.0000021758444,0.3524867,0.0024283233,0.0007119161],"about_ca_topic_score_codex":0.000028423809,"about_ca_topic_score_gemma":0.000007574866,"teacher_disagreement_score":0.64300096,"about_ca_system_score_codex":0.000028959264,"about_ca_system_score_gemma":0.00015061907,"threshold_uncertainty_score":0.99951124},"labels":[],"label_agreement":null},{"id":"W4385486397","doi":"10.1007/978-3-031-33390-3_7","title":"Nearest Neighbors","year":2023,"lang":"en","type":"book-chapter","venue":"Statisctics and computing/Statistics and computing","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"k-nearest neighbors algorithm; Computer science; Pattern recognition (psychology); Naive Bayes classifier; Artificial intelligence; Classifier (UML); Similarity (geometry); Data mining; Machine learning; Support vector machine","score_opus":0.025564252508237035,"score_gpt":0.25865924454697137,"score_spread":0.23309499203873432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385486397","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014378644,0.00069821224,0.9655215,0.0006881821,0.0008577871,0.00030428992,0.00015612942,0.000974073,0.030656021],"genre_scores_gemma":[0.1274056,0.0039232844,0.7139563,0.0009102091,0.0006346993,0.000008475196,0.00031460947,0.00035304631,0.1524938],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99718547,0.000031249336,0.00075078517,0.0010363907,0.00044751883,0.00054858637],"domain_scores_gemma":[0.99742216,0.00093563617,0.00062814774,0.00065213075,0.00015745954,0.00020449272],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003087306,0.0005771513,0.0006153883,0.00033249683,0.0006868925,0.0010282317,0.0007096131,0.00030007283,0.000012210281],"category_scores_gemma":[0.000086294574,0.0005932801,0.00006340119,0.00015507003,0.00033346142,0.00012446614,0.0016563156,0.0006746995,0.000048169048],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015289298,0.000007363566,0.000057828776,0.00007603842,0.00004649634,0.00004674835,0.00024447392,0.000027948827,0.0000021800245,0.69546187,0.002507172,0.30152035],"study_design_scores_gemma":[0.00041958454,0.00022790435,0.0012584289,0.0002973815,0.00006478435,0.000057995043,0.00011806329,0.35037977,0.0000070823285,0.61598295,0.030217733,0.00096832553],"about_ca_topic_score_codex":0.000017241435,"about_ca_topic_score_gemma":0.000008170062,"teacher_disagreement_score":0.35035184,"about_ca_system_score_codex":0.00003267646,"about_ca_system_score_gemma":0.00010394365,"threshold_uncertainty_score":0.99965185},"labels":[],"label_agreement":null},{"id":"W4385486431","doi":"10.1007/978-3-031-33390-3_2","title":"Statistical Learning: Concepts","year":2023,"lang":"en","type":"book-chapter","venue":"Statisctics and computing/Statistics and computing","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Machine learning; Artificial intelligence; Computer science; Statistical learning; Bayes' theorem; Interpretation (philosophy); Variance (accounting); Naive Bayes classifier; Supervised learning; Unsupervised learning; Statistics; Mathematics; Bayesian probability; Artificial neural network; Support vector machine","score_opus":0.10250899665452803,"score_gpt":0.4155633201201151,"score_spread":0.31305432346558704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385486431","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013290785,0.00033599773,0.96467155,0.00006961573,0.0005593973,0.00047625732,0.0012979642,0.00033787743,0.032118455],"genre_scores_gemma":[0.009417924,0.00080718216,0.9111578,0.0001523398,0.00044619988,0.0000042651195,0.00029413056,0.00038061928,0.07733954],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9956103,0.00017819552,0.0013496452,0.0012896247,0.00066483265,0.00090741087],"domain_scores_gemma":[0.9869798,0.010981374,0.0008472834,0.0003834619,0.00027680516,0.0005313054],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008343753,0.0009561243,0.0014820381,0.00021103266,0.00086100627,0.00033053293,0.0002374157,0.00042440387,0.00008804355],"category_scores_gemma":[0.0013079721,0.0009731741,0.00008958358,0.000081550716,0.0007163296,0.000052131807,0.0007760911,0.0015824276,0.000026047694],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019427136,0.0000207391,0.000023376571,0.0004968438,0.00014431275,0.0002055409,0.00046804323,0.0000836235,0.000002762865,0.78110385,0.0021082726,0.2153232],"study_design_scores_gemma":[0.00061358407,0.00038311616,0.000100102756,0.0004943619,0.00030115288,0.000079733894,0.00017274672,0.1382968,0.0000014051145,0.8488599,0.009724691,0.0009724165],"about_ca_topic_score_codex":0.000013732699,"about_ca_topic_score_gemma":0.000009421668,"teacher_disagreement_score":0.21435077,"about_ca_system_score_codex":0.00004836718,"about_ca_system_score_gemma":0.000118592936,"threshold_uncertainty_score":0.99927187},"labels":[],"label_agreement":null},{"id":"W4385486542","doi":"10.1007/978-3-031-33390-3_4","title":"Logistic Regression","year":2023,"lang":"en","type":"book-chapter","venue":"Statisctics and computing/Statistics and computing","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Logistic regression; Statistics; Covariate; Mathematics; Logistic model tree; Econometrics; Computer science; Artificial intelligence","score_opus":0.1867757406559741,"score_gpt":0.4257310844756461,"score_spread":0.238955343819672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385486542","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000092236725,0.0004858872,0.9714871,0.000080474405,0.00066874345,0.00042073333,0.0009058809,0.0002607313,0.025598187],"genre_scores_gemma":[0.005311747,0.0009903903,0.92646384,0.00015231721,0.0004226751,0.0000029404298,0.00014882957,0.00029942018,0.06620785],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99643147,0.000097287586,0.0011411805,0.0010916995,0.00053236634,0.00070599944],"domain_scores_gemma":[0.99140996,0.006676469,0.0008573393,0.00045456563,0.00022645261,0.00037523525],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006736891,0.0008399514,0.0012441275,0.00020972404,0.00070860673,0.00024746524,0.00022454359,0.00037870862,0.000035098357],"category_scores_gemma":[0.0008598135,0.000769089,0.00008800284,0.00007390435,0.00046059155,0.000042162865,0.00077514135,0.0009788752,0.000014815948],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014784259,0.000016442622,0.0000075694643,0.0005516771,0.00008944549,0.0001679569,0.0002674232,0.000039043865,0.0000032815265,0.7613648,0.002199465,0.2352781],"study_design_scores_gemma":[0.00043127057,0.00020979287,0.000051414707,0.0010253688,0.0002519147,0.00006917016,0.00008069524,0.13210857,0.0000016786557,0.86156344,0.0034319276,0.0007747336],"about_ca_topic_score_codex":0.000010788753,"about_ca_topic_score_gemma":0.000008573063,"teacher_disagreement_score":0.23450337,"about_ca_system_score_codex":0.000040810784,"about_ca_system_score_gemma":0.00008169367,"threshold_uncertainty_score":0.999476},"labels":[],"label_agreement":null},{"id":"W4385486861","doi":"10.1007/978-3-031-33390-3_9","title":"Trees","year":2023,"lang":"en","type":"book-chapter","venue":"Statisctics and computing/Statistics and computing","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Decision tree; Mathematics; Rectangle; Combinatorics; Boosting (machine learning); Artificial intelligence; Computer science; Discrete mathematics; Theoretical computer science","score_opus":0.02492851284539378,"score_gpt":0.26491244602047254,"score_spread":0.23998393317507877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385486861","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006393295,0.00047405928,0.97376966,0.00028823622,0.00053300796,0.00023561245,0.0006136127,0.00035876612,0.023663128],"genre_scores_gemma":[0.005892499,0.0012892201,0.9227986,0.00039588843,0.00052348536,0.0000045917377,0.00038271103,0.00016872147,0.068544276],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973259,0.000026904736,0.0006873847,0.0010590747,0.00039061377,0.00051012996],"domain_scores_gemma":[0.99756765,0.0009165742,0.00048699664,0.0006238688,0.00014042632,0.00026450993],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003477581,0.0005361688,0.0005982905,0.00021814308,0.00073811173,0.00091122754,0.00062436913,0.00019393225,0.000007506433],"category_scores_gemma":[0.00004230448,0.00056121923,0.00005669983,0.00012703142,0.00021896895,0.00009885351,0.0015154246,0.0005505089,0.000041169653],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.981859e-7,0.000007871007,0.0000109401035,0.000049442828,0.000046698326,0.000037070276,0.0002833433,0.000027749564,0.0000012948378,0.5985931,0.002836582,0.3981052],"study_design_scores_gemma":[0.00029625033,0.00014634385,0.00058900786,0.0002906395,0.000070178125,0.00008319545,0.000051854768,0.7181413,0.0000016124033,0.2495574,0.030035742,0.00073645817],"about_ca_topic_score_codex":0.000029904497,"about_ca_topic_score_gemma":0.000015078887,"teacher_disagreement_score":0.71811354,"about_ca_system_score_codex":0.000020986447,"about_ca_system_score_gemma":0.000095998126,"threshold_uncertainty_score":0.9996839},"labels":[],"label_agreement":null},{"id":"W4385489604","doi":"10.1007/978-3-031-33390-3_1","title":"Prologue","year":2023,"lang":"en","type":"book-chapter","venue":"Statisctics and computing/Statistics and computing","topic":"Economic Theory and Institutions","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Prologue; Computer science; Mathematics; Art; Literature","score_opus":0.037259756813683674,"score_gpt":0.22741942998119397,"score_spread":0.19015967316751028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385489604","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002650787,0.0038174742,0.4071855,0.0004206249,0.0027641463,0.0007394776,0.005650466,0.00035316552,0.57641834],"genre_scores_gemma":[0.4633685,0.006681335,0.10568781,0.0017207202,0.002174756,0.000013569102,0.0014509367,0.00066021056,0.41824213],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99746275,0.000014904813,0.0011188271,0.00087932724,0.00005174663,0.0004724169],"domain_scores_gemma":[0.99810773,0.00047777686,0.00084128027,0.0003274787,0.000051170413,0.00019455148],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00057005044,0.00047652773,0.0008726309,0.0002856321,0.00066257647,0.00029179256,0.00020720108,0.0002914438,0.000099335455],"category_scores_gemma":[0.000086067965,0.00059122767,0.00008180154,0.000054749373,0.0003832811,0.00007072955,0.00043858273,0.0006074688,0.00025469027],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000065064423,0.0000131934685,0.00028716147,0.00014514933,0.00014190536,0.00003282769,0.000410595,0.00014392645,3.0145722e-7,0.97436917,0.0015940111,0.022855276],"study_design_scores_gemma":[0.00040662728,0.00014204925,0.00069719955,0.00016167732,0.000044375134,0.000046223868,0.00006007325,0.061076023,5.0890105e-7,0.8665894,0.070084184,0.0006916544],"about_ca_topic_score_codex":0.000034991892,"about_ca_topic_score_gemma":0.000017085036,"teacher_disagreement_score":0.46071774,"about_ca_system_score_codex":0.000040372543,"about_ca_system_score_gemma":0.000046745707,"threshold_uncertainty_score":0.99965394},"labels":[],"label_agreement":null},{"id":"W4385489627","doi":"10.1007/978-3-031-33390-3_14","title":"Neural Networks","year":2023,"lang":"en","type":"book-chapter","venue":"Statisctics and computing/Statistics and computing","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Initialization; Backpropagation; Artificial neural network; Normalization (sociology); Regularization (linguistics); Gradient descent; Stochastic gradient descent; Computer science; Artificial intelligence; Feedforward neural network; Nonlinear system; Dropout (neural networks); Feed forward; Algorithm; Mathematics; Pattern recognition (psychology); Machine learning","score_opus":0.02097023155890035,"score_gpt":0.25225664645191254,"score_spread":0.2312864148930122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385489627","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012397833,0.00082896726,0.9866088,0.00038353208,0.0008764549,0.00033414282,0.00010862529,0.00036739165,0.0103681],"genre_scores_gemma":[0.31555745,0.0049747643,0.5645449,0.0030721612,0.0033856463,0.000016034484,0.0006006178,0.00063755,0.10721085],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971266,0.000038869464,0.0007520165,0.0010739622,0.00035549368,0.0006530964],"domain_scores_gemma":[0.9973712,0.0010660335,0.00054829067,0.0005607014,0.00014139249,0.0003123837],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027529485,0.00060877984,0.0006462328,0.00015873059,0.0008498857,0.00086071366,0.0005853162,0.00023814595,0.0000064673786],"category_scores_gemma":[0.000019062705,0.0006241549,0.00007773731,0.00015329821,0.00021846444,0.000086696054,0.0014701072,0.0008403582,0.000012274095],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016114575,0.000007173799,0.000021227077,0.00004637123,0.000043761367,0.000060620874,0.00010478956,0.0033426005,6.964463e-7,0.6920589,0.002684439,0.3016278],"study_design_scores_gemma":[0.00021848826,0.00010847723,0.00027733235,0.00013815699,0.000050914314,0.00008038136,0.000012157053,0.85378796,3.3070256e-7,0.1385861,0.0061489,0.00059079344],"about_ca_topic_score_codex":0.000015329942,"about_ca_topic_score_gemma":0.000009877569,"teacher_disagreement_score":0.8504454,"about_ca_system_score_codex":0.000019173713,"about_ca_system_score_gemma":0.00004480788,"threshold_uncertainty_score":0.999621},"labels":[],"label_agreement":null},{"id":"W4385489676","doi":"10.1007/978-3-031-33390-3_3","title":"Statistical Learning: Practical Aspects","year":2023,"lang":"en","type":"book-chapter","venue":"Statisctics and computing/Statistics and computing","topic":"Voice and Speech Disorders","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Variance (accounting); Bayes' theorem; Computer science; Scaling; Artificial intelligence; Algorithm; Machine learning; Variable (mathematics); Statistical learning; Mathematics; Statistics; Data mining; Bayesian probability","score_opus":0.03189300187760231,"score_gpt":0.318637779957082,"score_spread":0.2867447780794797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385489676","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025608304,0.0012744693,0.7314981,0.002052072,0.0011804824,0.0013348009,0.0007549517,0.0007452805,0.258599],"genre_scores_gemma":[0.22004719,0.0060724905,0.48275504,0.0022383532,0.002155913,0.000007384758,0.0027259325,0.0010725587,0.28292513],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966742,0.00006311583,0.00087662623,0.0009936448,0.00067694596,0.0007154776],"domain_scores_gemma":[0.99634117,0.002090276,0.00048774263,0.0003015801,0.00024456717,0.00053466874],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00042840332,0.0006934593,0.0011172884,0.00026135735,0.0005928104,0.00029615776,0.00009383178,0.0003953997,0.00010678306],"category_scores_gemma":[0.0005237364,0.0007024265,0.00008660384,0.000089637826,0.00044653346,0.00004249022,0.00044405003,0.0017626465,0.00008238055],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006625087,0.000059188358,0.00058356073,0.0007050387,0.00036282794,0.0015248647,0.00046885587,0.000038278697,0.0000059495783,0.86895555,0.007249762,0.11997985],"study_design_scores_gemma":[0.00520101,0.004236575,0.011807052,0.002674406,0.0028537733,0.0027770929,0.0016038028,0.37643567,0.000007782678,0.47253245,0.116642684,0.0032277282],"about_ca_topic_score_codex":0.000029263976,"about_ca_topic_score_gemma":0.000015613676,"teacher_disagreement_score":0.39642313,"about_ca_system_score_codex":0.000044457083,"about_ca_system_score_gemma":0.0003170601,"threshold_uncertainty_score":0.9995427},"labels":[],"label_agreement":null},{"id":"W4385489859","doi":"10.1007/978-3-031-33390-3_10","title":"Random Forests","year":2023,"lang":"en","type":"book-chapter","venue":"Statisctics and computing/Statistics and computing","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Random forest; Sample (material); Mathematics; Statistics; Tree (set theory); Bootstrap aggregating; Artificial intelligence; Machine learning; Computer science; Combinatorics","score_opus":0.09674985517006617,"score_gpt":0.38691000279231075,"score_spread":0.29016014762224457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385489859","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014968902,0.000420556,0.9725197,0.000071436574,0.0006065919,0.0005436101,0.0009560912,0.0002439494,0.024488382],"genre_scores_gemma":[0.0064785886,0.00073390297,0.934991,0.00015094357,0.00046603088,0.000004348235,0.00014348586,0.00033335199,0.05669833],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964479,0.000092859824,0.0011811234,0.0010251058,0.00052014546,0.00073282444],"domain_scores_gemma":[0.99036765,0.0078402115,0.00076661917,0.00041886378,0.00022541861,0.00038124758],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000770305,0.00081685645,0.0013466486,0.00020793288,0.00066559756,0.00027429842,0.00022067959,0.0003431367,0.00003133702],"category_scores_gemma":[0.0007082761,0.0007983036,0.000105707346,0.000071110066,0.00039413304,0.000046424706,0.00067122246,0.00088593835,0.000012971038],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029553546,0.000015873282,0.000018799541,0.00049499644,0.00014026118,0.00013395077,0.0003398273,0.000088443696,0.0000014608745,0.7834142,0.0019337928,0.21338885],"study_design_scores_gemma":[0.0010201456,0.00018223468,0.0000932091,0.0005773483,0.0002665427,0.00006346618,0.000059473,0.16453092,0.0000012704999,0.8290375,0.0034096497,0.0007582576],"about_ca_topic_score_codex":0.000011663435,"about_ca_topic_score_gemma":0.000032528482,"teacher_disagreement_score":0.21263058,"about_ca_system_score_codex":0.00003331096,"about_ca_system_score_gemma":0.000082199556,"threshold_uncertainty_score":0.9994468},"labels":[],"label_agreement":null},{"id":"W58877873","doi":"10.1007/978-1-4614-9020-3_4","title":"Importing, Exporting and Producing Data","year":2013,"lang":"en","type":"book-chapter","venue":"Statisctics and computing/Statistics and computing","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science","score_opus":0.12447099437256504,"score_gpt":0.36667361289072165,"score_spread":0.2422026185181566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W58877873","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006368903,0.0019517804,0.95760036,0.0001356488,0.00055447215,0.00089675275,0.0010642926,0.00019157756,0.031236246],"genre_scores_gemma":[0.025831603,0.00059627724,0.96416426,0.0001930793,0.0005470192,0.0000027466942,0.00020279094,0.00019744562,0.008264769],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9953117,0.000098240045,0.0017607989,0.001597147,0.00049047766,0.0007416584],"domain_scores_gemma":[0.9925093,0.00416325,0.0017420802,0.0009120903,0.00026789654,0.0004053656],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014641333,0.00083550083,0.0012740128,0.00016159222,0.0007528146,0.00065788947,0.00039143077,0.0002967586,0.00010759289],"category_scores_gemma":[0.0020004914,0.0008040202,0.00004083753,0.000059181933,0.00046146655,0.00010167304,0.0021902616,0.0009894093,0.0000055877313],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000047260773,0.000016776208,0.0002611869,0.0007158879,0.00010475984,0.00004738375,0.0006284792,0.0000015878129,0.000007316057,0.6102278,0.0024516308,0.38553244],"study_design_scores_gemma":[0.00043582713,0.00021583258,0.0009082509,0.0011628014,0.00035504746,0.00019054535,0.00022754811,0.22600316,0.0000037523682,0.7661672,0.0032681262,0.0010618863],"about_ca_topic_score_codex":0.00007382182,"about_ca_topic_score_gemma":0.000012101166,"teacher_disagreement_score":0.38447055,"about_ca_system_score_codex":0.00002460326,"about_ca_system_score_gemma":0.000115752126,"threshold_uncertainty_score":0.9994411},"labels":[],"label_agreement":null},{"id":"W982522955","doi":"10.1007/978-1-4614-9020-3_8","title":"Programming in R","year":2013,"lang":"en","type":"book-chapter","venue":"Statisctics and computing/Statistics and computing","topic":"Data Analysis with R","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Programming language; Computer science; Programming paradigm; Order (exchange); Programming domain; C programming language; Object-oriented programming; Inductive programming; Artificial intelligence; Software","score_opus":0.01385810052166029,"score_gpt":0.24519402531812265,"score_spread":0.23133592479646237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W982522955","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003569327,0.0012342201,0.97505844,0.00016104695,0.0003575903,0.00044549195,0.000092098264,0.00014081874,0.022153366],"genre_scores_gemma":[0.04505215,0.0005251796,0.93892425,0.00039943287,0.000242345,0.000004481535,0.00017807727,0.00011555354,0.0145585425],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99645925,0.00006236446,0.001041907,0.0012292631,0.00049613393,0.0007111087],"domain_scores_gemma":[0.9974537,0.0007153373,0.00070504396,0.0006653416,0.00017492914,0.0002856339],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00050277327,0.0006644272,0.000901841,0.00043082453,0.00036741493,0.0012739368,0.00071453565,0.00023963107,0.000025143236],"category_scores_gemma":[0.000060410235,0.00068641885,0.00006466689,0.00016883497,0.00022063946,0.00020490504,0.0016260437,0.0008038849,0.000030517676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012340992,0.000015598911,0.00014765351,0.00010441195,0.000055166467,0.00008708463,0.0003976401,0.00005926005,9.394652e-7,0.54277897,0.0007297952,0.45562223],"study_design_scores_gemma":[0.0005977418,0.000201681,0.0011505103,0.0005814822,0.00009451387,0.00011407232,0.00007197584,0.816619,0.0000014796909,0.15111873,0.028316885,0.0011319313],"about_ca_topic_score_codex":0.0001048313,"about_ca_topic_score_gemma":0.0000452781,"teacher_disagreement_score":0.81655973,"about_ca_system_score_codex":0.00004949653,"about_ca_system_score_gemma":0.000113858645,"threshold_uncertainty_score":0.99976283},"labels":[],"label_agreement":null}]}