{"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00043175198,0.0072128307,0.6833936,0.0032532637,0.0035157993,0.00025589782,0.012959646,0.05545326,0.23352389],"genre_scores_gemma":[0.013312302,0.009079257,0.5729789,0.0044734166,0.0030975402,0.0015239946,0.019635495,0.05112587,0.32477328],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99578,0.0013884935,0.00031575304,0.0008629438,0.0014694295,0.00018336234],"domain_scores_gemma":[0.99314535,0.0030373451,0.00031042582,0.001949936,0.0013521762,0.00020484129],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030072553,0.0023013481,0.0016252269,0.0030517553,0.00073373126,0.0044258228,0.0022946063,0.0016099917,0.20772573],"category_scores_gemma":[0.017685572,0.00096728496,0.0011703917,0.0025861298,0.0014186341,0.0032702503,0.0018504135,0.0032029718,0.28228486],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023069795,0.000017840512,0.00013499327,0.0006866412,0.000031017877,0.00007635685,0.0001221227,0.0009331589,0.0005403471,0.14542323,0.61595315,0.23605804],"study_design_scores_gemma":[0.000011564936,0.000010247941,0.00008951896,0.0001687821,0.000013175317,0.00013276836,0.000029436698,0.0009348136,0.0004180508,0.09816931,0.90000314,0.000019318353],"about_ca_topic_score_codex":0.0009789757,"about_ca_topic_score_gemma":0.0012045348,"teacher_disagreement_score":0.20772573,"about_ca_system_score_codex":0.0006177712,"about_ca_system_score_gemma":0.0022384354,"threshold_uncertainty_score":0.69491184},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011133367,0.0003789352,0.8955999,0.00053930684,0.0003894677,0.00049626146,0.008065662,0.03637066,0.04702638],"genre_scores_gemma":[0.17686251,0.0008475803,0.61947656,0.0008812847,0.00021137022,0.0008848712,0.04176397,0.008518859,0.15055314],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.999337,0.000051899326,0.0000402925,0.00021394095,0.00027933196,0.00007743907],"domain_scores_gemma":[0.99929917,0.00014109937,0.000026063373,0.0002632197,0.0002399387,0.00003044503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048785642,0.0008728219,0.00051738956,0.0017121296,0.0005130153,0.0019467581,0.001162142,0.000563671,0.03846046],"category_scores_gemma":[0.0031755872,0.000348173,0.0012041819,0.0014195477,0.00027149273,0.0021164245,0.0016125928,0.0012344786,0.021907398],"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":[0.00014120605,0.00011740763,0.001286268,0.00021586972,0.00005140648,0.0001772334,0.00009234257,0.0043382472,0.012400304,0.031124106,0.09539714,0.85465837],"study_design_scores_gemma":[0.00006730815,0.00017828857,0.0028039906,0.00014777626,0.00012457152,0.00094111904,0.00021457298,0.15635616,0.07496801,0.1330849,0.6310409,0.000072489245],"about_ca_topic_score_codex":0.002124502,"about_ca_topic_score_gemma":0.0029928316,"teacher_disagreement_score":0.03846046,"about_ca_system_score_codex":0.00058799115,"about_ca_system_score_gemma":0.00086428324,"threshold_uncertainty_score":0.12866306},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0076389057,0.0047747535,0.9377298,0.00072863314,0.0008237329,0.00016396976,0.0014742903,0.007398502,0.039267514],"genre_scores_gemma":[0.20028466,0.004993306,0.6662566,0.00070861954,0.0012548256,0.00041258585,0.008913992,0.0010203663,0.11615498],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99895525,0.00018430209,0.0000627751,0.00025176172,0.0004768644,0.000069121335],"domain_scores_gemma":[0.99878746,0.00042783775,0.00007539903,0.00025728386,0.00041050607,0.000041527903],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069972017,0.0011923397,0.0012239313,0.0012201786,0.00040829778,0.002018939,0.0012885451,0.0010454606,0.016586736],"category_scores_gemma":[0.0037711633,0.00041313903,0.0006384736,0.0018483802,0.00035319474,0.0017252162,0.000957204,0.0014923022,0.01816757],"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":[0.00006240769,0.00007269513,0.00034212662,0.00013993445,0.00004759423,0.00003515542,0.00001977483,0.01939593,0.0018095295,0.013215578,0.033796325,0.93106294],"study_design_scores_gemma":[0.000033350167,0.000161542,0.0010811645,0.00012907042,0.000061814666,0.0002692761,0.000070078124,0.78791124,0.010692709,0.08048027,0.119060524,0.00004899152],"about_ca_topic_score_codex":0.0007748769,"about_ca_topic_score_gemma":0.00096013193,"teacher_disagreement_score":0.016586736,"about_ca_system_score_codex":0.00028811267,"about_ca_system_score_gemma":0.0006315338,"threshold_uncertainty_score":0.05548823},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047711646,0.004591346,0.7952481,0.0014731934,0.0019325024,0.00023578221,0.0014278953,0.0074251406,0.18289484],"genre_scores_gemma":[0.14238511,0.0036063306,0.5642023,0.003004943,0.0022172283,0.0005091664,0.0048069805,0.0035720335,0.27569583],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99912924,0.00021277605,0.000021585622,0.00025192782,0.0002876039,0.000096893775],"domain_scores_gemma":[0.9990613,0.00026523566,0.0000342074,0.0003393987,0.00022708067,0.00007273213],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010865906,0.00083828805,0.0012476512,0.0011105245,0.0008043572,0.0018077692,0.0015406301,0.0012787575,0.055794924],"category_scores_gemma":[0.0039638737,0.0004694403,0.0008577213,0.001236528,0.0005912289,0.0012670537,0.0012935861,0.001964336,0.03423324],"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":[0.00011786416,0.000104113016,0.0003537794,0.00018324895,0.00007872094,0.000035883004,0.000040238294,0.024876961,0.0019815685,0.14851195,0.19039153,0.6333242],"study_design_scores_gemma":[0.00007667602,0.00009659206,0.0006537407,0.00012380697,0.00008254081,0.00029513793,0.000030363735,0.23858476,0.0045466297,0.33666018,0.4188155,0.000034101904],"about_ca_topic_score_codex":0.0011099962,"about_ca_topic_score_gemma":0.00179208,"teacher_disagreement_score":0.055794924,"about_ca_system_score_codex":0.0005389618,"about_ca_system_score_gemma":0.00081937795,"threshold_uncertainty_score":0},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011876061,0.005913408,0.69220185,0.0009844238,0.0020378486,0.00070484617,0.0056541143,0.0058862707,0.2747411],"genre_scores_gemma":[0.12340546,0.0036421723,0.564432,0.0008485681,0.00063558447,0.0004613431,0.015910324,0.0014875516,0.289177],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99788564,0.00021370746,0.00009778121,0.0006222745,0.001029037,0.00015157006],"domain_scores_gemma":[0.99866354,0.00023670743,0.00006228151,0.00048238557,0.0004966872,0.000058372858],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096938614,0.0010727313,0.0014394938,0.0030329204,0.0015773614,0.0035066246,0.0022191934,0.0018915604,0.05380809],"category_scores_gemma":[0.005044371,0.00058481237,0.0011597052,0.002969342,0.0006596121,0.0034529425,0.0017426147,0.0012480904,0.041537687],"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":[0.00018341653,0.00013486073,0.0009779328,0.0002837245,0.00006939263,0.000100617224,0.000105918945,0.014557294,0.0028672833,0.066157155,0.11536281,0.79919964],"study_design_scores_gemma":[0.00007298932,0.00018207307,0.0015618632,0.00032072177,0.00011556571,0.0014547042,0.00054844155,0.22792342,0.014154529,0.18760413,0.56596357,0.000098007244],"about_ca_topic_score_codex":0.0040190793,"about_ca_topic_score_gemma":0.008667668,"teacher_disagreement_score":0.05380809,"about_ca_system_score_codex":0.0007702143,"about_ca_system_score_gemma":0.0012497582,"threshold_uncertainty_score":0.18000603},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010805395,0.032844204,0.88933265,0.0063668992,0.0020477932,0.00012350103,0.00051930605,0.0009385021,0.06674668],"genre_scores_gemma":[0.103559576,0.063810855,0.67890054,0.010515587,0.021117002,0.0020107501,0.0020799767,0.0015403839,0.1164653],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967969,0.0011686817,0.00027599398,0.00050483656,0.0011673952,0.000086225424],"domain_scores_gemma":[0.99566036,0.0027493485,0.00018127693,0.00069217157,0.0005817804,0.00013500307],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035659827,0.0017320119,0.0020483122,0.003201386,0.00095447205,0.0057967887,0.001911583,0.0017614865,0.011936846],"category_scores_gemma":[0.0077825394,0.0008347247,0.0010897835,0.003849131,0.0067026187,0.006828843,0.0034882145,0.0054115844,0.008718705],"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":[0.000004934073,0.00002304475,0.00009990603,0.00030478352,0.000019937215,0.00003234741,0.00015817225,0.0012942823,0.00020414813,0.88508224,0.029059248,0.08371688],"study_design_scores_gemma":[0.0000032456696,0.000010481667,0.00009493228,0.00008463857,0.000007231195,0.0000999292,0.00002904721,0.0042111427,0.00013325908,0.91411287,0.081204765,0.000008447393],"about_ca_topic_score_codex":0.0008123,"about_ca_topic_score_gemma":0.00055706844,"teacher_disagreement_score":0.011936846,"about_ca_system_score_codex":0.0016742877,"about_ca_system_score_gemma":0.0020537896,"threshold_uncertainty_score":0.039932728},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063665733,0.011304352,0.37716994,0.008972376,0.0019548684,0.00021851236,0.0057905763,0.0044998867,0.5837229],"genre_scores_gemma":[0.05383102,0.009883529,0.080783315,0.0021771318,0.0011534641,0.00033694794,0.0068456368,0.0016141857,0.8433748],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99918693,0.0003061132,0.000029815457,0.00015795587,0.00027783657,0.000041370113],"domain_scores_gemma":[0.99856853,0.0008269755,0.00008234627,0.00021938994,0.00024924468,0.00005344217],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001689873,0.00089097983,0.00061060453,0.0011928628,0.00041868215,0.0017193787,0.0013370374,0.0008571812,0.09487865],"category_scores_gemma":[0.00781088,0.00041196158,0.0006987073,0.002006202,0.00041652427,0.0014388779,0.0011240286,0.0018478243,0.07434159],"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":[0.00006573483,0.00006470275,0.0023980187,0.00026398178,0.000073568706,0.00021601332,0.00015300213,0.0019840503,0.00044860042,0.10736379,0.34635365,0.5406149],"study_design_scores_gemma":[0.000022549444,0.00006307097,0.0035819022,0.00029207682,0.00006657188,0.0014670476,0.00016318382,0.011879398,0.0011432746,0.11374566,0.86752963,0.00004564536],"about_ca_topic_score_codex":0.0016054475,"about_ca_topic_score_gemma":0.002659941,"teacher_disagreement_score":0.09487865,"about_ca_system_score_codex":0.00053368625,"about_ca_system_score_gemma":0.0008880736,"threshold_uncertainty_score":0.3174007},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0078455,0.002962476,0.4987082,0.0021054815,0.0016458357,0.0004722878,0.021901578,0.014602552,0.44975612],"genre_scores_gemma":[0.083214045,0.0036169267,0.35699558,0.0021461097,0.000784254,0.0006398713,0.044325598,0.006307551,0.50197005],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993299,0.0000726621,0.000029896037,0.00020449296,0.00028349238,0.0000794972],"domain_scores_gemma":[0.9991731,0.00019782492,0.00003595784,0.00029604175,0.00023297204,0.00006404264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039282796,0.0006955042,0.00066901976,0.0015693092,0.0010834953,0.002548423,0.0012730138,0.0009600953,0.117700726],"category_scores_gemma":[0.0024398933,0.00047156794,0.00085768127,0.0021702803,0.0005359662,0.002824315,0.0014302323,0.0017474066,0.086149864],"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":[0.00009506943,0.00007046348,0.00043557477,0.00027825375,0.000034128712,0.00008329147,0.00014250517,0.0042574,0.003088072,0.24547878,0.3077825,0.43825403],"study_design_scores_gemma":[0.00002184387,0.000028268068,0.000248028,0.00008623746,0.000026213644,0.00020939013,0.00006202832,0.012857526,0.0028308267,0.24684508,0.73676765,0.000016953816],"about_ca_topic_score_codex":0.0012105872,"about_ca_topic_score_gemma":0.0024295985,"teacher_disagreement_score":0.117700726,"about_ca_system_score_codex":0.00055255607,"about_ca_system_score_gemma":0.00089529186,"threshold_uncertainty_score":0},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022039968,0.00092792156,0.06552557,0.002373783,0.0014779445,0.0005637479,0.05610467,0.050143145,0.82067925],"genre_scores_gemma":[0.025558926,0.0017126269,0.075088665,0.0026537364,0.0007915377,0.0008668,0.11052214,0.046726767,0.73607886],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99943393,0.00011596089,0.000032202708,0.00013260082,0.00020130823,0.00008397804],"domain_scores_gemma":[0.9993304,0.000217803,0.000022134844,0.00013889602,0.00020864012,0.00008215438],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056674174,0.0011861597,0.0006373634,0.0014480678,0.00092328707,0.003352671,0.0012989005,0.0008531295,0.60247236],"category_scores_gemma":[0.0037098094,0.00060769095,0.00067693,0.0011363968,0.00041128666,0.0032620477,0.0023104313,0.0014740512,0.4454255],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017134578,0.00007103578,0.00019804404,0.00037064054,0.000009245971,0.000060401344,0.000057321493,0.00032523557,0.00074487366,0.024858715,0.8394972,0.13363586],"study_design_scores_gemma":[0.000047863217,0.000013709458,0.00010039906,0.00007109853,0.000005853866,0.000081573045,0.00003401161,0.0006134969,0.00067382766,0.012814989,0.985532,0.000011174969],"about_ca_topic_score_codex":0.0026215545,"about_ca_topic_score_gemma":0.0033107246,"teacher_disagreement_score":0.60247236,"about_ca_system_score_codex":0.00083547796,"about_ca_system_score_gemma":0.001219475,"threshold_uncertainty_score":0},"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":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0066094934,0.01819362,0.66314566,0.002377307,0.002635745,0.00011141347,0.0011836338,0.0025589736,0.30318412],"genre_scores_gemma":[0.18522874,0.019065551,0.2273573,0.0013002469,0.0013784749,0.00031912854,0.002794788,0.00071540626,0.5618404],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99977964,0.000029744167,0.000010618099,0.000058798447,0.000103832994,0.000017373031],"domain_scores_gemma":[0.9997769,0.00006536149,0.000014038164,0.000050290775,0.000083011124,0.000010284321],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027361105,0.00065379526,0.0005068755,0.00062654965,0.0003145273,0.0014743578,0.0009222092,0.0010116844,0.027682083],"category_scores_gemma":[0.0013300279,0.0002931022,0.00029954806,0.0008008624,0.0004233866,0.001430955,0.00070606644,0.0010500231,0.0123584345],"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":[0.000039912095,0.00003453557,0.0003162027,0.00026930377,0.00005321874,0.00007107152,0.00003700966,0.061835054,0.0032159796,0.15510641,0.06662439,0.7123969],"study_design_scores_gemma":[0.000016355581,0.000053758056,0.0006491442,0.00021125839,0.000058651134,0.00026671521,0.000046750236,0.42783505,0.007026293,0.25706238,0.30673617,0.000037487636],"about_ca_topic_score_codex":0.0018159697,"about_ca_topic_score_gemma":0.0025706138,"teacher_disagreement_score":0.027682083,"about_ca_system_score_codex":0.0004815368,"about_ca_system_score_gemma":0.000482152,"threshold_uncertainty_score":0.09260583},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00076865865,0.012817278,0.92244947,0.008024749,0.0010387274,0.000049148613,0.00013668639,0.0008192467,0.053896084],"genre_scores_gemma":[0.06021962,0.022225944,0.7520203,0.0056197112,0.008903953,0.00046615483,0.00061056326,0.001426087,0.14850767],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99719477,0.0012980386,0.00016293486,0.00030628705,0.0009821367,0.00005575816],"domain_scores_gemma":[0.98797905,0.009517098,0.00011932744,0.00123038,0.0010234489,0.00013066966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047818804,0.0014438597,0.0012496766,0.0014866564,0.00082216505,0.003731823,0.0019360156,0.0020056008,0.016281096],"category_scores_gemma":[0.016464114,0.000952311,0.00066498865,0.0017480953,0.005122779,0.0059600463,0.0027370045,0.0051940084,0.0132174045],"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":[0.000012724611,0.00005739757,0.00022811134,0.0003669448,0.000031590156,0.00013152037,0.00031330675,0.0056335926,0.00046161388,0.64482164,0.07873678,0.26920474],"study_design_scores_gemma":[0.0000044338362,0.000013022862,0.00012989924,0.000070329595,0.000006262642,0.0001580645,0.000055958226,0.0120371925,0.00026120423,0.90233636,0.08491402,0.000013323174],"about_ca_topic_score_codex":0.0013288194,"about_ca_topic_score_gemma":0.0013785758,"teacher_disagreement_score":0.016281096,"about_ca_system_score_codex":0.0011901963,"about_ca_system_score_gemma":0.001304698,"threshold_uncertainty_score":0.05446571},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002224691,0.0020168356,0.88507384,0.00042650462,0.0007087463,0.00026087,0.006874861,0.018794328,0.083619356],"genre_scores_gemma":[0.032567274,0.0018402699,0.8057572,0.0008518379,0.00047563817,0.00051321305,0.02264339,0.0063110334,0.12904009],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99853766,0.00030007347,0.000060559163,0.0004018875,0.00058074977,0.00011901476],"domain_scores_gemma":[0.9985379,0.0005854672,0.000065368644,0.00039308323,0.00034738705,0.000070885304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014798202,0.0012760892,0.0010575777,0.0018823112,0.0008375407,0.002253399,0.0020479418,0.001134965,0.073400505],"category_scores_gemma":[0.0041306084,0.0008110506,0.0015336681,0.0019782307,0.00040311535,0.001973023,0.0013083117,0.0016877635,0.07146852],"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":[0.00011219891,0.00013072361,0.00065222895,0.00041147743,0.00014454503,0.00010031887,0.000056954344,0.02147305,0.0031451306,0.05717362,0.29683363,0.6197662],"study_design_scores_gemma":[0.00006204169,0.0000743261,0.0007889297,0.0002312185,0.00011581124,0.00057974306,0.000058563983,0.1755658,0.009497753,0.1792925,0.63365906,0.00007435559],"about_ca_topic_score_codex":0.001314498,"about_ca_topic_score_gemma":0.00437299,"teacher_disagreement_score":0.073400505,"about_ca_system_score_codex":0.0003439257,"about_ca_system_score_gemma":0.0008967081,"threshold_uncertainty_score":0.24554914},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005361721,0.0016061725,0.7240561,0.0018278062,0.0008978879,0.0007820584,0.03190093,0.044380054,0.18918721],"genre_scores_gemma":[0.017223261,0.004713329,0.7817066,0.0011571503,0.000482776,0.0007717786,0.04105434,0.03543881,0.11745204],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981724,0.00029888432,0.00023446548,0.00031742427,0.00088807725,0.00008884466],"domain_scores_gemma":[0.9917869,0.003169649,0.0002146951,0.0032791044,0.0013755099,0.0001741955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002974075,0.0013913806,0.00115617,0.0037401845,0.0009293593,0.005543447,0.0020541444,0.000915349,0.06374364],"category_scores_gemma":[0.014102425,0.0010649419,0.0011588709,0.007077789,0.00089376915,0.005170308,0.0037097635,0.0025316963,0.09317264],"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":[0.00008336236,0.00006530332,0.0014167628,0.0013001027,0.000033074553,0.0003497821,0.0010943809,0.0010699852,0.009397834,0.03683526,0.16651917,0.7818351],"study_design_scores_gemma":[0.0000165197,0.000024668328,0.0015190978,0.00034275165,0.000035865858,0.0006532225,0.000376023,0.0018079279,0.016784849,0.035623413,0.9427614,0.000054288517],"about_ca_topic_score_codex":0.002028138,"about_ca_topic_score_gemma":0.0023161166,"teacher_disagreement_score":0.06374364,"about_ca_system_score_codex":0.00073408335,"about_ca_system_score_gemma":0.002746892,"threshold_uncertainty_score":0.21324378},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003419749,0.001578828,0.90130454,0.0012511845,0.00055515015,0.00012844297,0.0042447974,0.029737806,0.06085732],"genre_scores_gemma":[0.010684094,0.002180889,0.87330216,0.0015688562,0.00062863895,0.0010463501,0.006640485,0.029412465,0.07453606],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99600726,0.0017811909,0.00041062848,0.00069653924,0.0009580019,0.00014636797],"domain_scores_gemma":[0.99324,0.0040592933,0.00029220793,0.0014753002,0.0008001822,0.0001330172],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032315566,0.0019230555,0.0019305879,0.0019472657,0.0006704515,0.004374498,0.0019668804,0.0011767094,0.10919865],"category_scores_gemma":[0.013677032,0.0013119845,0.0016359251,0.0021456983,0.001298473,0.0026100955,0.001739858,0.003534074,0.14880434],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044424276,0.00003159516,0.00019285452,0.00094439625,0.000080381236,0.000103794315,0.00015738053,0.0046690544,0.0008948308,0.2769138,0.4414925,0.27447513],"study_design_scores_gemma":[0.000038959202,0.000022751243,0.00014727173,0.00032505894,0.000048097914,0.00030423937,0.00004883127,0.013244711,0.0018658838,0.30737185,0.67654264,0.00003975641],"about_ca_topic_score_codex":0.0009087429,"about_ca_topic_score_gemma":0.0012457963,"teacher_disagreement_score":0.10919865,"about_ca_system_score_codex":0.0005753277,"about_ca_system_score_gemma":0.0015911366,"threshold_uncertainty_score":0.3653059},"labels":[],"label_agreement":null}]}