{"meta":{"query_hash":"f36dcb0356dd","filters":{"venue":"Springer series in the data sciences"},"cohort_total":12,"direct_labels_cover":0,"predictions_cover":12,"exported":12,"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/f36dcb0356dd","api":"https://metacan.xera.ac/api/v1/cohort?venue=Springer+series+in+the+data+sciences"},"results":[{"id":"W2303810353","doi":"10.1007/978-3-319-25388-6","title":"Lectures on the Nearest Neighbor Method","year":2015,"lang":"en","type":"book","venue":"Springer series in the data sciences","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":224,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"k-nearest neighbors algorithm; Nearest neighbor search; Computer science; Artificial intelligence","score_opus":0.12361419541651521,"score_gpt":0.35329369356177265,"score_spread":0.22967949814525745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2303810353","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000027672659,0.0017812145,0.045678142,0.06748308,0.0022776194,0.0008098871,0.00042377776,0.00026701886,0.8812516],"genre_scores_gemma":[0.012403629,0.0020112076,0.3802884,0.03392128,0.0064870548,0.000423913,0.0042123324,0.00022379404,0.5600284],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.996571,0.00066095067,0.0002889086,0.0010156948,0.0011097805,0.00035368383],"domain_scores_gemma":[0.9940485,0.0011871564,0.00026929783,0.0043933904,0.000052364096,0.000049322807],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.008113025,0.00027712903,0.0002303598,0.00016607375,0.0005866836,0.0013939921,0.017715417,0.00011690776,0.000033045497],"category_scores_gemma":[0.0012819843,0.00013430223,0.000037361286,0.0006026211,0.00065034686,0.0010434226,0.0024245318,0.00081468595,0.00014741876],"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":[0.0000068717018,0.000018563052,0.00003446702,0.000013380537,0.00000850687,0.000008351412,0.0010322445,0.00016566526,0.0000039068846,0.71335304,0.26066965,0.024685318],"study_design_scores_gemma":[0.00004330619,0.0001083398,0.00042645686,0.000061565705,0.000007928331,0.000020195757,0.00011841006,0.009460178,0.000009278472,0.045115184,0.94441086,0.00021827684],"about_ca_topic_score_codex":0.00013738625,"about_ca_topic_score_gemma":0.00029183298,"teacher_disagreement_score":0.6837412,"about_ca_system_score_codex":0.000055513898,"about_ca_system_score_gemma":0.0007268412,"threshold_uncertainty_score":0.99964267},"labels":[],"label_agreement":null},{"id":"W2469324836","doi":"10.1007/978-3-319-25388-6_8","title":"The nearest neighbor regression function estimate","year":2015,"lang":"en","type":"book-chapter","venue":"Springer series in the data sciences","topic":"Statistical Methods and Inference","field":"Mathematics","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":"McGill University","funders":"","keywords":"Regression function; Mathematics; Function (biology); Combinatorics; k-nearest neighbors algorithm; Random variable; Regression analysis; Statistics; Computer science; Biology","score_opus":0.33760199115258516,"score_gpt":0.43815756954935414,"score_spread":0.10055557839676899,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2469324836","genre_codex":"other","genre_gemma":"methods","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":[0.00013721987,0.003271833,0.015874082,0.003421606,0.003653627,0.000869015,0.0009174359,0.00012949751,0.9717257],"genre_scores_gemma":[0.0067471983,0.004051138,0.6990249,0.00089888036,0.0027729047,0.00015856033,0.000415448,0.00024344353,0.28568754],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99796134,0.00012755988,0.00037260403,0.00048345127,0.0007634459,0.000291618],"domain_scores_gemma":[0.9959541,0.0020543167,0.00027030657,0.0015889588,0.000081431994,0.00005088059],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004766889,0.0002422899,0.00025612497,0.000052996897,0.0005869214,0.000408869,0.0027619575,0.0001177188,0.00016238866],"category_scores_gemma":[0.0036979925,0.00010766065,0.000029159519,0.00010451161,0.001447143,0.00034821502,0.001014989,0.0004112696,0.0000581113],"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":[0.000024797762,0.0000057723655,0.000015353438,0.000023744376,0.000006076097,0.0000059305034,0.0001002124,9.184042e-7,0.0000021634546,0.95842266,0.015012124,0.02638025],"study_design_scores_gemma":[0.000038221326,0.000095509466,0.00009173977,0.0001970193,0.000026782169,0.0000086483205,0.00014237642,0.00046152686,0.0000026804837,0.7550211,0.24377781,0.00013658435],"about_ca_topic_score_codex":0.00003225435,"about_ca_topic_score_gemma":0.000215687,"teacher_disagreement_score":0.68603814,"about_ca_system_score_codex":0.000026776472,"about_ca_system_score_gemma":0.00015440809,"threshold_uncertainty_score":0.5332059},"labels":[],"label_agreement":null},{"id":"W2470346259","doi":"10.1007/978-3-319-25388-6_1","title":"Order statistics and nearest neighbors","year":2015,"lang":"en","type":"book-chapter","venue":"Springer series in the data sciences","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Order statistic; Statistics; Probability and statistics; Order (exchange); Mathematics; Statistical physics; Physics; Economics","score_opus":0.10905930463665656,"score_gpt":0.326035775456214,"score_spread":0.21697647081955743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2470346259","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":[0.000004214041,0.002427039,0.7990783,0.0015771287,0.0007157051,0.00020688937,0.0004007839,0.000040787345,0.19554919],"genre_scores_gemma":[0.0001435342,0.00089016126,0.973368,0.00054108835,0.00016686314,0.0000050734216,0.000051258685,0.000016946726,0.024817077],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979028,0.00008593533,0.00026796607,0.0008204888,0.00061797915,0.00030481632],"domain_scores_gemma":[0.997674,0.00021019514,0.0001503821,0.0018041478,0.00008077018,0.00008053199],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0028190466,0.00025576103,0.00026825813,0.00012819789,0.00022882751,0.0006959179,0.005554659,0.00011783397,0.000025673271],"category_scores_gemma":[0.00018752324,0.00016579333,0.000013864813,0.00019154507,0.001030997,0.0011685957,0.0025885715,0.00034546523,0.000016690241],"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":[0.0000018586628,0.0000038948538,0.000011919015,0.000012750168,0.0000045477555,0.00002704095,0.00041997136,0.000002383596,7.1093194e-7,0.94759184,0.0074623264,0.04446078],"study_design_scores_gemma":[0.00006337017,0.00008046217,0.00006173795,0.00005385424,0.000010757705,0.000050477905,0.000031332915,0.003364042,0.0000014496421,0.6048405,0.391164,0.00027799094],"about_ca_topic_score_codex":0.00006291814,"about_ca_topic_score_gemma":0.00026508974,"teacher_disagreement_score":0.38370168,"about_ca_system_score_codex":0.000016621963,"about_ca_system_score_gemma":0.00031514472,"threshold_uncertainty_score":0.9998258},"labels":[],"label_agreement":null},{"id":"W2475598160","doi":"10.1007/978-3-319-25388-6_15","title":"Regression: the noiseless case","year":2015,"lang":"en","type":"book-chapter","venue":"Springer series in the data sciences","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":"McGill University","funders":"","keywords":"Lebesgue measure; Mathematics; Measure (data warehouse); Combinatorics; Function (biology); Monte Carlo method; Lebesgue integration; Discrete mathematics; Statistical physics; Physics; Statistics; Computer science","score_opus":0.4681110534256192,"score_gpt":0.4534592882772717,"score_spread":0.014651765148347484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2475598160","genre_codex":"other","genre_gemma":"methods","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":[0.00020757031,0.0018742668,0.0022904673,0.0030812912,0.001319212,0.00060978514,0.0012720354,0.000056921457,0.98928845],"genre_scores_gemma":[0.013676704,0.0018512505,0.70351845,0.0017367152,0.0029593345,0.00013735853,0.00016872314,0.00019143548,0.27576005],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979856,0.00016639692,0.000365411,0.000506602,0.0007093473,0.00026664644],"domain_scores_gemma":[0.99553365,0.002082925,0.00023285646,0.0020235062,0.000074897216,0.000052192332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005400422,0.0002515518,0.00031596568,0.000057117824,0.00038882077,0.00023752036,0.0036617394,0.00011635573,0.00035260053],"category_scores_gemma":[0.0025109588,0.00010707598,0.00003184086,0.00011605124,0.001835898,0.00025695033,0.001399863,0.00048405374,0.00003726411],"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":[0.0000060018365,0.0000072732523,0.000004884404,0.000031612846,0.0000061347496,0.0003188253,0.0004976102,2.486275e-7,4.7201084e-7,0.96994734,0.01915293,0.010026679],"study_design_scores_gemma":[0.000038413065,0.000048263137,0.00000476978,0.00018842738,0.00003069943,0.00056043547,0.0008077568,0.00010110468,0.0000029349271,0.78784275,0.21020389,0.00017055345],"about_ca_topic_score_codex":0.000060866438,"about_ca_topic_score_gemma":0.00035644654,"teacher_disagreement_score":0.7135284,"about_ca_system_score_codex":0.000020614641,"about_ca_system_score_gemma":0.00016082959,"threshold_uncertainty_score":0.68044835},"labels":[],"label_agreement":null},{"id":"W2486128631","doi":"10.1007/978-3-319-25388-6_2","title":"The nearest neighbor distance","year":2015,"lang":"en","type":"book-chapter","venue":"Springer series in the data sciences","topic":"Computational Geometry and Mesh Generation","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":"McGill University","funders":"","keywords":"Equidistant; k-nearest neighbors algorithm; Combinatorics; Physics; Mathematics; Condensed matter physics; Geometry; Computer science; Artificial intelligence","score_opus":0.10875444591649007,"score_gpt":0.30749797614937235,"score_spread":0.19874353023288227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2486128631","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008339887,0.021351552,0.10410892,0.026249567,0.0072707688,0.0009897611,0.00040784525,0.0001956698,0.83934253],"genre_scores_gemma":[0.074884705,0.0082713645,0.106662914,0.004569303,0.0061276564,0.00016755892,0.0012249075,0.0001219905,0.7979696],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99786496,0.00006219675,0.00027779903,0.000627508,0.00090707495,0.00026043778],"domain_scores_gemma":[0.99755144,0.0003465863,0.00017607395,0.0017919219,0.00009011578,0.000043854205],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0027931407,0.00018926863,0.0001410673,0.000084671636,0.00072784605,0.0011584653,0.008502606,0.000061009323,0.000012705344],"category_scores_gemma":[0.00018354585,0.00010552274,0.000029875153,0.00031143537,0.0007267539,0.0013973231,0.0017670972,0.0002527347,0.00006462055],"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":[0.0000036020804,0.00000435655,0.000008435041,0.0000038491085,0.0000041785693,0.0000074021127,0.00019208476,0.00030702873,0.0000010503417,0.96800053,0.011789671,0.019677788],"study_design_scores_gemma":[0.00003649711,0.000043160988,0.00010194135,0.000027228822,0.0000034573368,0.000016883925,0.000043227188,0.0059701926,0.000003532629,0.13807918,0.855523,0.00015171425],"about_ca_topic_score_codex":0.000017187658,"about_ca_topic_score_gemma":0.0005029725,"teacher_disagreement_score":0.8437333,"about_ca_system_score_codex":0.00003490205,"about_ca_system_score_gemma":0.00035884933,"threshold_uncertainty_score":0.9998784},"labels":[],"label_agreement":null},{"id":"W2493818561","doi":"10.1007/978-3-319-25388-6_16","title":"The choice of a nearest neighbor estimate","year":2015,"lang":"en","type":"book-chapter","venue":"Springer series in the data sciences","topic":"Machine Learning and Algorithms","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":"McGill University","funders":"","keywords":"Minimax; Mathematics; k-nearest neighbors algorithm; Nonparametric statistics; Class (philosophy); Universality (dynamical systems); Convergence (economics); Nonparametric regression; Property (philosophy); Function (biology); Applied mathematics; Econometrics; Statistics; Computer science; Mathematical economics; Artificial intelligence; Economics; Physics","score_opus":0.09872209417537257,"score_gpt":0.34689705553420336,"score_spread":0.24817496135883077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2493818561","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002960774,0.013131223,0.01052247,0.020698803,0.0053464854,0.00096704543,0.000452412,0.00030865177,0.9482768],"genre_scores_gemma":[0.060115907,0.005730501,0.30604535,0.0024706475,0.0054145236,0.00014686411,0.00048977294,0.0002920633,0.61929435],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99765813,0.000091085654,0.0003534287,0.00063877704,0.00091946824,0.00033912793],"domain_scores_gemma":[0.99635774,0.00056649424,0.0003308368,0.002619896,0.000074407966,0.00005063262],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0036306453,0.00023571553,0.00025126684,0.0000996953,0.0004931518,0.0006644377,0.013358506,0.000076409066,0.000015846837],"category_scores_gemma":[0.00051697897,0.00012245582,0.000041903757,0.000249398,0.0013305325,0.00089248846,0.0031812196,0.0004767413,0.000038960465],"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":[0.0000058438336,0.000013328832,0.00023051555,0.000029589371,0.000016543443,0.00001905295,0.0007427518,0.00032119045,0.0000028780016,0.93384784,0.006175131,0.05859535],"study_design_scores_gemma":[0.00009093647,0.00015352588,0.0005311204,0.00014707916,0.00001161017,0.000029819885,0.00007038063,0.029964354,0.0000058351848,0.049555834,0.91915846,0.00028101887],"about_ca_topic_score_codex":0.00032115137,"about_ca_topic_score_gemma":0.00044392934,"teacher_disagreement_score":0.91298336,"about_ca_system_score_codex":0.000016471597,"about_ca_system_score_gemma":0.00028071154,"threshold_uncertainty_score":0.9919797},"labels":[],"label_agreement":null},{"id":"W2897222754","doi":"10.1007/978-3-319-94153-0_10","title":"Multiple Change-Point Problems","year":2018,"lang":"en","type":"book-chapter","venue":"Springer series in the data sciences","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":"University of Ottawa","funders":"","keywords":"Mathematics; Sequence (biology); Distribution (mathematics); Point (geometry); Random sequence; Combinatorics; Distribution function; Mathematical analysis; Physics; Geometry; Chemistry; Thermodynamics","score_opus":0.3918705169175193,"score_gpt":0.3972969669493789,"score_spread":0.005426450031859598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2897222754","genre_codex":"other","genre_gemma":"methods","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":[0.00037600787,0.0012144978,0.011853538,0.0027832591,0.0025535878,0.00234042,0.003037451,0.00018587925,0.9756554],"genre_scores_gemma":[0.0027121014,0.0012300753,0.9332593,0.0010877489,0.0020483793,0.0001917385,0.00017158852,0.00010898659,0.05919006],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979517,0.00008014581,0.00040443108,0.0006543555,0.0005682064,0.00034116334],"domain_scores_gemma":[0.996773,0.0013175942,0.0002337253,0.0015732904,0.00005711843,0.00004524658],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0033478418,0.00026942653,0.00034577856,0.000101317106,0.00022691938,0.00019785443,0.003230946,0.00013132644,0.0010262815],"category_scores_gemma":[0.0022715663,0.00016141933,0.000035792225,0.00010163258,0.0017169453,0.00042939137,0.0012775193,0.00031932647,0.000120904835],"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":[0.000006594072,0.000018558407,0.000050589617,0.00012426263,0.000010309837,0.000008584202,0.0015819219,6.7395916e-8,0.000005299626,0.98456234,0.0056874817,0.007943997],"study_design_scores_gemma":[0.00005251396,0.00013656901,0.00006520832,0.00036287485,0.000020485095,0.00001228462,0.00021158224,0.00025108378,0.000013783942,0.8424082,0.15622304,0.0002423723],"about_ca_topic_score_codex":0.00006970606,"about_ca_topic_score_gemma":0.0005788351,"teacher_disagreement_score":0.9214058,"about_ca_system_score_codex":0.000019702578,"about_ca_system_score_gemma":0.000061861014,"threshold_uncertainty_score":0.99988693},"labels":[],"label_agreement":null},{"id":"W2897353815","doi":"10.1007/978-3-319-94153-0_5","title":"One-Sample and Two-Sample Problems","year":2018,"lang":"en","type":"book-chapter","venue":"Springer series in the data sciences","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 Ottawa","funders":"","keywords":"Nonparametric statistics; Wilcoxon signed-rank test; Statistic; Test statistic; Parametric statistics; Sign test; Mathematics; Statistics; Asymptotic distribution; Rank (graph theory); Order statistic; Sample (material); Statistical hypothesis testing; Estimator; Combinatorics; Mann–Whitney U test","score_opus":0.34904205384062376,"score_gpt":0.4346756887338155,"score_spread":0.08563363489319176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2897353815","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":[0.00016981496,0.0008845795,0.8425188,0.0008530397,0.00059402286,0.001114292,0.0061494224,0.000097538024,0.14761849],"genre_scores_gemma":[0.0001678046,0.00043739777,0.9932173,0.00013488105,0.00021184009,0.000017965449,0.00007590324,0.00002852915,0.0057084113],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99807835,0.00006208237,0.00036357093,0.0007063537,0.00046294942,0.0003267116],"domain_scores_gemma":[0.9952136,0.0032905515,0.00019551894,0.0012033978,0.000042951975,0.000053957396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024700605,0.00024111698,0.00036578818,0.000079670885,0.00029445946,0.00017646528,0.0017030591,0.00008863653,0.00025380164],"category_scores_gemma":[0.0026032727,0.00016508576,0.000023711536,0.000069375244,0.0018550721,0.0004868419,0.0011753037,0.0002689815,0.000009646967],"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":[0.000006517938,0.000011835896,0.0000066430243,0.00008884469,0.000009965475,0.0000015515953,0.0005885598,0.0000020583343,0.0000059659155,0.99101144,0.00032861799,0.007937972],"study_design_scores_gemma":[0.00006578791,0.00009235664,0.0000042872616,0.00016296645,0.00002771494,0.0000048971874,0.00011926519,0.00026679083,0.0000064535993,0.8757341,0.123307675,0.00020769327],"about_ca_topic_score_codex":0.00011108617,"about_ca_topic_score_gemma":0.00084772176,"teacher_disagreement_score":0.15069847,"about_ca_system_score_codex":0.000014989467,"about_ca_system_score_gemma":0.000058967646,"threshold_uncertainty_score":0.68350905},"labels":[],"label_agreement":null},{"id":"W4247735967","doi":"10.1007/978-3-319-94153-0_9","title":"Efficiency","year":2018,"lang":"en","type":"book-chapter","venue":"Springer series in the data sciences","topic":"Statistical Methods in Clinical Trials","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 Ottawa","funders":"","keywords":"Mathematics; Sign test; Statistics; Test statistic; Wilcoxon signed-rank test; Statistic; Null hypothesis; Statistical hypothesis testing; Asymptotic distribution; Alternative hypothesis; Mann–Whitney U test","score_opus":0.725581839700009,"score_gpt":0.5610421790588936,"score_spread":0.16453966064111536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247735967","genre_codex":"other","genre_gemma":"methods","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":[0.00010117773,0.0002876982,0.0050368807,0.0011278649,0.0028242504,0.00073473656,0.0010937748,0.00009399205,0.9886996],"genre_scores_gemma":[0.00020770122,0.00039598215,0.91864896,0.00051942404,0.0016417557,0.000019835887,0.00001940581,0.000059702645,0.078487255],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99642646,0.0002882264,0.0008917352,0.0009567118,0.0010338454,0.00040300033],"domain_scores_gemma":[0.97548753,0.021163277,0.0004254175,0.002805509,0.00006166255,0.000056585628],"candidate_categories":["metaresearch","sts","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015524263,0.00031443103,0.0006086499,0.00012578856,0.00026433446,0.00021925037,0.006811036,0.00024168234,0.0022967423],"category_scores_gemma":[0.045055877,0.00018868386,0.0000743328,0.00017216631,0.004171193,0.0002783535,0.0019415596,0.0005251279,0.00030815185],"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":[0.000014705133,0.000024331972,0.000007229842,0.000055358378,0.000012360368,0.00001695122,0.0002189238,1.2979446e-7,0.0000015749428,0.9803754,0.016035786,0.0032372633],"study_design_scores_gemma":[0.00007236881,0.00014741873,0.000010837425,0.00019596017,0.000043870532,0.000010749089,0.00010163628,0.000028859053,0.000011887797,0.87416995,0.12497645,0.00023002346],"about_ca_topic_score_codex":0.000007931659,"about_ca_topic_score_gemma":0.0000624395,"teacher_disagreement_score":0.91361207,"about_ca_system_score_codex":0.000025222665,"about_ca_system_score_gemma":0.00014770239,"threshold_uncertainty_score":0.99861526},"labels":[],"label_agreement":null},{"id":"W4312378116","doi":"10.1007/978-3-031-06784-6_4","title":"Multivariate Methods","year":2022,"lang":"en","type":"book-chapter","venue":"Springer series in the data sciences","topic":"Advanced Statistical Methods and Models","field":"Mathematics","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 Ottawa","funders":"","keywords":"Univariate; Multivariate statistics; Principal component analysis; Statistics; Multivariate analysis; Canonical correlation; Multidimensional scaling; Mathematics; Scaling; Econometrics","score_opus":0.43072274135038807,"score_gpt":0.5229505243334631,"score_spread":0.09222778298307505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312378116","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000029047083,0.000556927,0.4488394,0.0006950903,0.00086650264,0.00045884555,0.0012639331,0.000059329934,0.54725707],"genre_scores_gemma":[0.00001648437,0.0002589817,0.96494526,0.0001588861,0.00009581508,0.000026696092,0.00004704847,0.000029337312,0.034421515],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975921,0.00034021976,0.00042882416,0.0007510032,0.000568686,0.0003191462],"domain_scores_gemma":[0.99483013,0.0032033331,0.00024721836,0.0016568096,0.000022561953,0.000039927687],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007139467,0.00026823994,0.0004126285,0.00011047137,0.00040567465,0.00009898467,0.0034706863,0.000086443775,0.0010517777],"category_scores_gemma":[0.002131823,0.00017421755,0.000049402006,0.000111028225,0.00082432607,0.0004945106,0.002244257,0.0005985046,0.000008662281],"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":[0.000008724244,0.0000113869355,4.7558072e-7,0.00003401549,0.000011170498,0.000018574234,0.00036770952,0.000008911627,0.0000109819375,0.9717927,0.00055800466,0.027177338],"study_design_scores_gemma":[0.000036768284,0.000039728653,0.0000020453715,0.000029954223,0.000023641178,0.000010250142,0.00013728836,0.00031181407,0.000005974324,0.64265347,0.35658774,0.00016130692],"about_ca_topic_score_codex":0.00003767494,"about_ca_topic_score_gemma":0.00005374928,"teacher_disagreement_score":0.51610583,"about_ca_system_score_codex":0.000035592733,"about_ca_system_score_gemma":0.00008909162,"threshold_uncertainty_score":0.9998614},"labels":[],"label_agreement":null},{"id":"W4312384497","doi":"10.1007/978-3-031-06784-6_13","title":"Bayesian Computation Methods","year":2022,"lang":"en","type":"book-chapter","venue":"Springer series in the data sciences","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Prior probability; Conjugate prior; Bayesian probability; Computer science; Markov chain; Posterior probability; Mathematics; Computation; Markov chain Monte Carlo; Algorithm; Artificial intelligence; Machine learning","score_opus":0.09987620520094698,"score_gpt":0.371740452115156,"score_spread":0.271864246914209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312384497","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":[4.319291e-7,0.00086207327,0.712255,0.0019294411,0.00094866264,0.00020804873,0.000052739677,0.000060633716,0.28368297],"genre_scores_gemma":[0.00011572399,0.00034776347,0.9872476,0.0007845632,0.00014055661,0.000017525734,0.000064424705,0.00001857168,0.011263304],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99659914,0.0005298783,0.00044309048,0.0012311486,0.0008132054,0.00038356212],"domain_scores_gemma":[0.99678266,0.0005015222,0.00028916326,0.0023399792,0.00003118872,0.000055472152],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.008529336,0.0003233423,0.00036657078,0.00030167607,0.0006094042,0.000599784,0.010994155,0.0001178077,0.00016129095],"category_scores_gemma":[0.000102487924,0.0002329077,0.00007344908,0.00039492146,0.00058560073,0.0018607691,0.004284241,0.0006480821,0.000012624976],"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":[0.0000019781667,0.0000073866413,0.000001937054,0.000012341113,0.000007728782,0.000022246064,0.0005716377,0.000037288522,0.0000047865274,0.8192963,0.0014127223,0.17862366],"study_design_scores_gemma":[0.00005202406,0.00008375073,0.000016105883,0.000033366956,0.000012721225,0.00006838511,0.00004113932,0.015646784,0.000011412004,0.55858,0.4251316,0.00032270324],"about_ca_topic_score_codex":0.00005038725,"about_ca_topic_score_gemma":0.000053858723,"teacher_disagreement_score":0.42371887,"about_ca_system_score_codex":0.00004913205,"about_ca_system_score_gemma":0.0002439328,"threshold_uncertainty_score":0.9943568},"labels":[],"label_agreement":null},{"id":"W4312572234","doi":"10.1007/978-3-031-06784-6_10","title":"Symbolic Data Analysis","year":2022,"lang":"en","type":"book-chapter","venue":"Springer series in the data sciences","topic":"Time Series Analysis and Forecasting","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 Ottawa","funders":"","keywords":"Big data; Computer science; The Internet; Data science; Government (linguistics); World Wide Web; Internet privacy; Data mining; Linguistics","score_opus":0.12003324126704333,"score_gpt":0.2965796579336715,"score_spread":0.17654641666662818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312572234","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008910915,0.0065315478,0.013314085,0.006647109,0.0015473545,0.0005586538,0.0033954773,0.0002648293,0.96765184],"genre_scores_gemma":[0.06926728,0.019873828,0.33105698,0.0072381436,0.0040114727,0.00017303383,0.028396675,0.00037016327,0.5396124],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99529946,0.00011270498,0.00062123744,0.0020671375,0.001387995,0.00051147095],"domain_scores_gemma":[0.9890009,0.00023371747,0.00045928007,0.010208435,0.00003520422,0.00006244102],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.0050626,0.00037181997,0.00061700644,0.0007260223,0.00094994716,0.0012050543,0.038615342,0.000089267276,0.0010794984],"category_scores_gemma":[0.0001369187,0.0002637137,0.00014435883,0.00194521,0.00075116416,0.0037358864,0.023556547,0.0005748321,0.000048098675],"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":[0.000003997464,0.000021649856,0.00025529688,0.000016608674,0.00039663093,0.000077908655,0.0007614421,0.0005929766,0.0000013874252,0.97567475,0.0038263884,0.018370965],"study_design_scores_gemma":[0.000044379063,0.00006417342,0.00026668733,0.000023979492,0.00040186054,0.00003242073,0.00029282726,0.049918946,9.20267e-7,0.011778189,0.9366716,0.0005040068],"about_ca_topic_score_codex":0.00043317178,"about_ca_topic_score_gemma":0.0016509471,"teacher_disagreement_score":0.9638966,"about_ca_system_score_codex":0.000041268715,"about_ca_system_score_gemma":0.00021311619,"threshold_uncertainty_score":0.9999815},"labels":[],"label_agreement":null}]}