{"meta":{"query_hash":"a7bdaead1c37","filters":{"venue":"Studies in classification, data analysis, and knowledge organization"},"cohort_total":27,"direct_labels_cover":0,"predictions_cover":27,"exported":27,"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/a7bdaead1c37","api":"https://metacan.xera.ac/api/v1/cohort?venue=Studies+in+classification%2C+data+analysis%2C+and+knowledge+organization"},"results":[{"id":"W129103391","doi":"10.1007/978-3-540-73560-1_51","title":"Locally Linear Regression and the Calibration Problem for Micro-Array Analysis","year":2007,"lang":"en","type":"book-chapter","venue":"Studies in classification, data analysis, and knowledge organization","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"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 and Génome Québec Innovation Centre; McGill University","funders":"","keywords":"Proper linear model; Linear regression; Segmented regression; Regression analysis; Calibration; Regression diagnostic; Bayesian multivariate linear regression; Regression; Bayesian linear regression; Statistics; Linear model; Data set; Mathematics; Tree (set theory); Bayesian probability; Computer science; Data mining; Bayesian inference","score_opus":0.05591057143890545,"score_gpt":0.35444303056904214,"score_spread":0.2985324591301367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W129103391","genre_codex":"methods","genre_gemma":"review","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":[0.0004860708,0.03982664,0.9465997,0.00064959604,0.00006858745,0.0016575009,0.00034284827,0.00007492453,0.010294135],"genre_scores_gemma":[0.21148363,0.37740853,0.04617242,0.00058333436,0.0020492624,0.0002270014,0.17724329,0.00039586614,0.18443668],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99764353,0.000108758424,0.0007992754,0.0011035894,0.0001668076,0.00017805895],"domain_scores_gemma":[0.9967464,0.0001396424,0.00057890784,0.001328024,0.0011550051,0.000052027768],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014171381,0.0003670011,0.00077262934,0.0007391613,0.0003266045,0.000079603255,0.0003943219,0.00039301178,0.000014422048],"category_scores_gemma":[0.0005797035,0.0002730462,0.00014723041,0.0012558671,0.00063697307,0.000028035436,0.00043150116,0.00015574021,0.0000014685581],"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":[0.002221067,0.0013338914,0.24026011,0.004318433,0.2365046,0.0000129092405,0.01302496,0.00030265836,0.12620592,0.094400175,0.2042027,0.07721257],"study_design_scores_gemma":[0.0071193874,0.0004245067,0.0141906105,0.00073349586,0.1773679,0.000019227891,0.0026161075,0.053821135,0.042375386,0.0099877035,0.68647575,0.0048687677],"about_ca_topic_score_codex":0.000032567805,"about_ca_topic_score_gemma":0.00554987,"teacher_disagreement_score":0.9004273,"about_ca_system_score_codex":0.00005322022,"about_ca_system_score_gemma":0.00010162058,"threshold_uncertainty_score":0.99997216},"labels":[],"label_agreement":null},{"id":"W149153453","doi":"10.1007/978-3-642-56181-8_37","title":"A Comparison of Alternative Methods for Detecting Reticulation Events in Phylogenetic Analysis","year":2002,"lang":"en","type":"book-chapter","venue":"Studies in classification, data analysis, and knowledge organization","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"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":"Phylogenetic tree; Reticulate; Reticulate evolution; Identification (biology); Phylogenetic network; Tree (set theory); Branching (polymer chemistry); Evolutionary biology; Biology; Pattern recognition (psychology); Algorithm; Computer science; Artificial intelligence; Mathematics; Paleontology; Combinatorics; Botany; Genetics","score_opus":0.14428885196283925,"score_gpt":0.42911589178184084,"score_spread":0.2848270398190016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W149153453","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22929601,0.1809326,0.57489455,0.00021189627,0.0009893014,0.00395173,0.0018715312,0.000027832355,0.007824563],"genre_scores_gemma":[0.9700758,0.017244611,0.007313646,0.0000049505343,0.0001234717,0.000026896121,0.0032084438,0.000038664984,0.0019635116],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978403,0.00013858314,0.00089934,0.00085980055,0.00010312818,0.00015886985],"domain_scores_gemma":[0.9976215,0.00016585973,0.0006843814,0.0007260864,0.0007709467,0.000031275275],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00069184846,0.00029044546,0.0009122535,0.00078156654,0.00011736425,0.0000098957,0.00029113994,0.00023634851,0.000008369595],"category_scores_gemma":[0.0007294734,0.0003015334,0.00011128566,0.001055028,0.00015130558,0.0000036941933,0.00037235647,0.00009405364,7.211172e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046585326,0.00023051529,0.9417945,0.00039231416,0.019269178,2.505806e-7,0.004403021,0.0015460462,0.014180565,0.0019299426,0.00016267,0.016044382],"study_design_scores_gemma":[0.0021760394,0.00043872517,0.7953998,0.0002823963,0.03349776,0.0000020780494,0.0025747404,0.13638344,0.011192619,0.0056133466,0.010498528,0.0019405521],"about_ca_topic_score_codex":0.000022087615,"about_ca_topic_score_gemma":0.0027354718,"teacher_disagreement_score":0.7407798,"about_ca_system_score_codex":0.000067426765,"about_ca_system_score_gemma":0.00004391245,"threshold_uncertainty_score":0.9999437},"labels":[],"label_agreement":null},{"id":"W1540530916","doi":"10.1007/978-3-642-01044-6_69","title":"Nonnegative Matrix Factorization for Binary Data to Extract Elementary Failure Maps from Wafer Test Images","year":2009,"lang":"en","type":"book-chapter","venue":"Studies in classification, data analysis, and knowledge organization","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Infineon Technologies (Canada)","funders":"","keywords":"Non-negative matrix factorization; Binary number; Logical matrix; Probabilistic logic; Wafer; Computer science; Matrix (chemical analysis); Superposition principle; Binary data; Matrix decomposition; Pattern recognition (psychology); Algorithm; Artificial intelligence; Mathematics; Engineering; Arithmetic; Materials science","score_opus":0.11265509268367462,"score_gpt":0.3503634868738844,"score_spread":0.23770839419020978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1540530916","genre_codex":"methods","genre_gemma":"dataset","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":[0.0015995486,0.034863345,0.79161197,0.0016292697,0.0063119796,0.009799698,0.13802795,0.0017256871,0.014430552],"genre_scores_gemma":[0.45811695,0.02581525,0.010241041,0.00007388401,0.005559356,0.00012332661,0.46490797,0.0005026315,0.03465957],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973311,0.000054005526,0.0009949072,0.001135395,0.00025503183,0.00022960249],"domain_scores_gemma":[0.99669117,0.0004613977,0.0003166874,0.0016625464,0.0007797803,0.00008839922],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00053541636,0.00049116096,0.00081490516,0.00088773423,0.00030174424,0.00014471897,0.0005957188,0.00040287903,0.0000877033],"category_scores_gemma":[0.0008189276,0.00048836984,0.000052822776,0.0011853946,0.000065505716,0.000670072,0.0003836784,0.00026502836,0.00005017098],"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":[0.00012576468,0.00042596328,0.02328695,0.0013436426,0.012482354,0.000011991949,0.006447724,0.0011480639,0.011808707,0.0030635474,0.8356167,0.104238555],"study_design_scores_gemma":[0.002057945,0.00028618803,0.027983524,0.0010877239,0.00878065,0.000004171436,0.0034590047,0.03397983,0.0009950817,0.002316324,0.91628766,0.0027618809],"about_ca_topic_score_codex":0.00006236236,"about_ca_topic_score_gemma":0.0024688917,"teacher_disagreement_score":0.78137094,"about_ca_system_score_codex":0.00033734582,"about_ca_system_score_gemma":0.000080309335,"threshold_uncertainty_score":0.9997568},"labels":[],"label_agreement":null},{"id":"W163807921","doi":"10.1007/978-3-319-00035-0_27","title":"A New Effective Method for Elimination of Systematic Error in Experimental High-Throughput Screening","year":2013,"lang":"en","type":"book-chapter","venue":"Studies in classification, data analysis, and knowledge organization","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":"McGill University; Université du Québec à Montréal","funders":"","keywords":"Throughput; Systematic error; Computer science; Reliability engineering; High-throughput screening; Computational biology; Biology; Statistics; Engineering; Mathematics; Bioinformatics; Telecommunications","score_opus":0.5789561825739972,"score_gpt":0.5719166883885102,"score_spread":0.007039494185486994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W163807921","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":[0.000040206472,0.0033126357,0.99123657,0.00010225443,0.00031158977,0.0032904064,0.00034401112,0.000039687115,0.0013226527],"genre_scores_gemma":[0.011377597,0.001353761,0.9779702,0.000012681291,0.00029317648,0.00026939702,0.0009491975,0.000113416434,0.0076606013],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99519676,0.0007978174,0.0024067601,0.0010565912,0.00033301362,0.00020907639],"domain_scores_gemma":[0.9700811,0.025766976,0.0016417911,0.0012144557,0.0012227057,0.000072989846],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0043719555,0.0004382953,0.0024776321,0.0008386019,0.00011137119,0.000044116703,0.0004800739,0.00041685105,0.000114932336],"category_scores_gemma":[0.05903345,0.00039634766,0.000111558664,0.0010566924,0.00021452698,0.00022244023,0.00043900154,0.00023221067,0.000008649955],"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":[0.000068010944,0.00030018057,0.00065893977,0.021613907,0.004723,0.0000010782403,0.004382858,0.000007718523,0.0001914588,0.9541776,0.003963697,0.009911538],"study_design_scores_gemma":[0.0039917687,0.00033838526,0.0062249997,0.013539287,0.019020693,0.0000029908235,0.0039880574,0.02784423,0.001355371,0.9219104,0.0003321405,0.0014516612],"about_ca_topic_score_codex":0.00008041212,"about_ca_topic_score_gemma":0.0006036155,"teacher_disagreement_score":0.054661494,"about_ca_system_score_codex":0.00028156547,"about_ca_system_score_gemma":0.00011730479,"threshold_uncertainty_score":0.99984884},"labels":[],"label_agreement":null},{"id":"W164202556","doi":"10.1007/978-3-319-00035-0_46","title":"Non-symmetrical Correspondence Analysis of Abbreviated Hard Laddering Interviews","year":2013,"lang":"en","type":"book-chapter","venue":"Studies in classification, data analysis, and knowledge organization","topic":"Cognitive and psychological constructs research","field":"Psychology","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":"Brock University","funders":"","keywords":"Laddering; Pairwise comparison; Matrix (chemical analysis); Presentation (obstetrics); Mathematics; Computer science; Psychology; Statistics; Materials science; Marketing; Medicine","score_opus":0.31937673253780074,"score_gpt":0.45672809831495403,"score_spread":0.1373513657771533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W164202556","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":[0.023244206,0.11559317,0.053784505,0.0007189717,0.0022285627,0.0033453356,0.004611319,0.00025435243,0.7962196],"genre_scores_gemma":[0.76926243,0.05101068,0.00035512308,0.00008500438,0.00021956598,0.000054178636,0.012874664,0.000085747066,0.16605261],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99646974,0.00027169724,0.0012857781,0.0013655332,0.00032201922,0.0002852348],"domain_scores_gemma":[0.9946925,0.0007895684,0.00068373996,0.001623863,0.002102072,0.00010827128],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010862001,0.00041085455,0.0015888381,0.0037453934,0.00015159798,0.0000637481,0.0008077406,0.00040770238,0.007550505],"category_scores_gemma":[0.0012120445,0.0003604771,0.00017209462,0.00836745,0.00067041063,0.00017711979,0.00074073527,0.00045032537,0.00038715624],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012759228,0.0006343007,0.6039646,0.0006221746,0.078421205,0.000022852992,0.008831702,0.0000027718374,0.00020204608,0.05177376,0.047169086,0.2082279],"study_design_scores_gemma":[0.0005570713,0.00009168745,0.9417781,0.0002460326,0.018242216,0.000002852042,0.0015622623,0.0018693374,0.000010184559,0.0004930238,0.03446038,0.00068681693],"about_ca_topic_score_codex":0.0001205954,"about_ca_topic_score_gemma":0.0015379854,"teacher_disagreement_score":0.74601823,"about_ca_system_score_codex":0.00010722679,"about_ca_system_score_gemma":0.00008273262,"threshold_uncertainty_score":0.9998847},"labels":[],"label_agreement":null},{"id":"W183542246","doi":"10.1007/978-3-642-56181-8_40","title":"A Family of Average Consensus Methods for Weighted Trees","year":2002,"lang":"en","type":"book-chapter","venue":"Studies in classification, data analysis, and knowledge organization","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"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":"Phylogenetic tree; Mathematics; Relation (database); Tree (set theory); Statistics; Computer science; Combinatorics; Data mining; Biology","score_opus":0.10837558942394292,"score_gpt":0.37322222758296675,"score_spread":0.2648466381590238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W183542246","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018098557,0.61521155,0.25252947,0.00084251683,0.0020106733,0.004114827,0.009987063,0.000059192957,0.09714614],"genre_scores_gemma":[0.3899733,0.42735815,0.054921202,0.00011461849,0.0009573134,0.00008072697,0.018448556,0.00024132496,0.10790479],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99833286,0.00007366724,0.00063091476,0.000749127,0.00007200479,0.00014144997],"domain_scores_gemma":[0.9975458,0.0001499752,0.00040962055,0.000888095,0.0009707498,0.000035802197],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00044713684,0.00028889874,0.0006597406,0.00028608926,0.0001427312,0.000014451758,0.00028342422,0.00025176673,0.000011726384],"category_scores_gemma":[0.00045070655,0.0002787777,0.00008021871,0.00033207893,0.00033778613,0.0000016314827,0.00038699774,0.000068603,0.0000017765268],"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":[0.00039509416,0.001226326,0.101847835,0.0036799088,0.088811524,0.000004752702,0.009647846,0.00012215714,0.358771,0.13658668,0.11968614,0.17922074],"study_design_scores_gemma":[0.0027155601,0.00045726745,0.065651804,0.00026566972,0.013381322,0.0000056794843,0.0011683697,0.008377065,0.0061358945,0.012365492,0.88722473,0.0022511203],"about_ca_topic_score_codex":0.000010461542,"about_ca_topic_score_gemma":0.0004789557,"teacher_disagreement_score":0.7675386,"about_ca_system_score_codex":0.000028434846,"about_ca_system_score_gemma":0.000080217585,"threshold_uncertainty_score":0.99996644},"labels":[],"label_agreement":null},{"id":"W2162677492","doi":"10.1007/978-3-642-10745-0_53","title":"Identification of Specific Genomic Regions Responsible for the Invasivity of Neisseria Meningitidis","year":2010,"lang":"en","type":"book-chapter","venue":"Studies in classification, data analysis, and knowledge organization","topic":"Bacterial Infections and Vaccines","field":"Immunology and Microbiology","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Neisseria meningitidis; Identification (biology); Biology; Neisseria; Computational biology; Genome; Genetics; Virology; Gene; Bacteria","score_opus":0.10461134056263498,"score_gpt":0.33865356558354226,"score_spread":0.23404222502090727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162677492","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40614223,0.33425784,0.17303272,0.0068482608,0.022796066,0.0140231075,0.027651707,0.0005408608,0.014707226],"genre_scores_gemma":[0.90888363,0.051890083,0.00019531781,0.0000037497657,0.00018140543,0.000036268997,0.008588862,0.0000526815,0.030168006],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983544,0.00008789148,0.00091688836,0.00050301134,0.000021619158,0.00011620184],"domain_scores_gemma":[0.99603677,0.00063923746,0.00092441007,0.0012317159,0.0011569379,0.000010946587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008503975,0.00021223174,0.0006054975,0.00053589296,0.00035704,0.000020887712,0.00039091613,0.00033331712,0.00011737061],"category_scores_gemma":[0.0006693687,0.00017264184,0.00007676787,0.00065314927,0.00054615724,0.00012929617,0.0002582435,0.00019157887,0.000012249392],"study_design_candidate":"bench_or_experimental","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":[0.00009259718,0.00014502139,0.007725787,0.00026833988,0.004169038,4.3096936e-8,0.0018446383,0.0000025718762,0.83949924,0.13904049,0.0054346933,0.0017775497],"study_design_scores_gemma":[0.002589202,0.00022065855,0.32755855,0.00043427025,0.017641835,0.000021962403,0.0029773668,0.00020611068,0.12448769,0.025203176,0.49723116,0.0014280077],"about_ca_topic_score_codex":0.00005016324,"about_ca_topic_score_gemma":0.0032001478,"teacher_disagreement_score":0.71501154,"about_ca_system_score_codex":0.00004650021,"about_ca_system_score_gemma":0.0001606152,"threshold_uncertainty_score":0.704013},"labels":[],"label_agreement":null},{"id":"W2284845990","doi":"10.1007/978-3-642-10745-0_56","title":"Virtual High Throughput Screening Using Machine Learning Methods","year":2010,"lang":"en","type":"book-chapter","venue":"Studies in classification, data analysis, and knowledge organization","topic":"Cell Image Analysis Techniques","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":"Université du Québec à Montréal","funders":"","keywords":"Throughput; Computer science; High-throughput screening; Machine learning; Virtual screening; Artificial intelligence; Biology; Operating system; Bioinformatics; Drug discovery","score_opus":0.0901693015071354,"score_gpt":0.402010894764952,"score_spread":0.3118415932578166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2284845990","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":[0.0013686036,0.018907974,0.9725773,0.00007649543,0.00015086184,0.00035371745,0.00014370285,0.00010200682,0.006319391],"genre_scores_gemma":[0.22178303,0.17996782,0.332897,0.0001699502,0.002436478,0.000029580497,0.114005975,0.0005719729,0.1481382],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974613,0.0002038073,0.0007043106,0.0012560682,0.00017085775,0.00020360749],"domain_scores_gemma":[0.99691546,0.00008773741,0.000558519,0.0014577016,0.00092149404,0.000059075108],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011539353,0.00042664632,0.0007417083,0.00060012145,0.00039091724,0.00007977485,0.00050668395,0.00052449113,0.00007654199],"category_scores_gemma":[0.0012207458,0.00043508384,0.00009251374,0.00078934786,0.00041598818,0.00003294331,0.0012578769,0.00047567373,0.000004469777],"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":[0.00011541411,0.0005091772,0.15799402,0.000676048,0.037300527,0.000019505318,0.0033217755,0.00034990787,0.6540904,0.022672484,0.007290372,0.11566035],"study_design_scores_gemma":[0.0016477682,0.00032504633,0.008964598,0.00048055706,0.030816663,0.000040530922,0.0014464317,0.059559863,0.09170348,0.002943155,0.7975279,0.0045439685],"about_ca_topic_score_codex":0.0001280667,"about_ca_topic_score_gemma":0.0036618712,"teacher_disagreement_score":0.79023755,"about_ca_system_score_codex":0.000060105096,"about_ca_system_score_gemma":0.000110179484,"threshold_uncertainty_score":0.9998101},"labels":[],"label_agreement":null},{"id":"W3087978613","doi":"10.1007/978-981-15-3311-2_13","title":"From Joint Graphical Display to Bi-Modal Clustering: [1] A Giant Leap in Quantification Theory","year":2020,"lang":"en","type":"book-chapter","venue":"Studies in classification, data analysis, and knowledge organization","topic":"Sensory Analysis and Statistical Methods","field":"Agricultural and Biological Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Cluster analysis; Set (abstract data type); Graphical model; Multidimensional scaling; Scaling; Graphical display; Cluster (spacecraft); Theoretical computer science; Artificial intelligence; Mathematics; Machine learning; Computer graphics (images); Geometry","score_opus":0.19749490679735485,"score_gpt":0.3631668787169121,"score_spread":0.16567197191955726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3087978613","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09647633,0.054950636,0.6825985,0.05902088,0.0044900444,0.009194337,0.033037722,0.001296907,0.05893467],"genre_scores_gemma":[0.9524088,0.009285001,0.0041384534,0.00034929987,0.000989083,0.00003597158,0.026067154,0.000022265258,0.0067039737],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9966443,0.00040005412,0.0010296468,0.0014358237,0.00027031451,0.00021982501],"domain_scores_gemma":[0.99769735,0.0009556436,0.000332818,0.0004581996,0.00040240417,0.00015357471],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010504618,0.0003835786,0.0009904465,0.00027585038,0.00023928915,0.00011359594,0.0004880616,0.0002909942,0.00025226086],"category_scores_gemma":[0.0021402084,0.00020431662,0.00009232649,0.0022450692,0.00025671002,0.00013797404,0.0005097531,0.00031548252,0.000056943878],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028224793,0.0007078297,0.043130524,0.00032005762,0.0052293134,0.000039813458,0.0077153784,0.00007296908,0.03345604,0.70632774,0.0051735947,0.19754447],"study_design_scores_gemma":[0.00052035565,0.00020378367,0.8240698,0.0004987958,0.0049467646,0.0000028404622,0.004547254,0.035174374,0.00016052971,0.089594826,0.03829267,0.0019879814],"about_ca_topic_score_codex":0.00019858514,"about_ca_topic_score_gemma":0.018754084,"teacher_disagreement_score":0.8559325,"about_ca_system_score_codex":0.000103291095,"about_ca_system_score_gemma":0.000028867451,"threshold_uncertainty_score":0.9991511},"labels":[],"label_agreement":null},{"id":"W3132725877","doi":"10.1007/978-3-030-60104-1_3","title":"A Fast Electric Vehicle Planner Using Clustering","year":2021,"lang":"en","type":"book-chapter","venue":"Studies in classification, data analysis, and knowledge organization","topic":"Vehicle Routing Optimization Methods","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Cluster analysis; Computation; Speedup; Computer science; Shortest path problem; Planner; Range (aeronautics); Electric vehicle; Graph; Path (computing); Mathematical optimization; Real-time computing; Algorithm; Engineering; Mathematics; Artificial intelligence; Parallel computing; Theoretical computer science; Computer network","score_opus":0.11164230897041949,"score_gpt":0.3458162574810454,"score_spread":0.2341739485106259,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3132725877","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001587552,0.04660318,0.9128782,0.0000993182,0.0011540035,0.00061006687,0.00039853822,0.0006885365,0.035980612],"genre_scores_gemma":[0.42365626,0.259024,0.12458237,0.0001607922,0.0038285584,0.000059747046,0.04245683,0.0017827222,0.14444873],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979726,0.00009067452,0.0007434265,0.00075955386,0.00019220832,0.00024149969],"domain_scores_gemma":[0.9979041,0.00016219019,0.00021293429,0.0009898542,0.0006666244,0.00006429701],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00053061853,0.00038400464,0.0007241463,0.0008971704,0.00023260663,0.0001062484,0.0003287167,0.00029691358,0.00007721992],"category_scores_gemma":[0.00043360822,0.00043613912,0.000046080597,0.0021686465,0.00009228397,0.00025597043,0.0004042078,0.00031108747,0.000013587456],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000497152,0.00051215815,0.15252264,0.008762105,0.04361825,0.00010183617,0.0258961,0.55083805,0.014001618,0.053575467,0.020864008,0.12925807],"study_design_scores_gemma":[0.00022289187,0.0000059123813,0.002926225,0.00021384264,0.0018862433,0.000006796494,0.00029604926,0.9888818,0.00007249711,0.000111318746,0.0048124753,0.00056389737],"about_ca_topic_score_codex":0.000010068229,"about_ca_topic_score_gemma":0.0006243611,"teacher_disagreement_score":0.7882958,"about_ca_system_score_codex":0.00037288104,"about_ca_system_score_gemma":0.000109829154,"threshold_uncertainty_score":0.999809},"labels":[],"label_agreement":null},{"id":"W3174761163","doi":"10.1007/978-3-030-75190-6_17","title":"The Impact of the COVID-19 Pandemic on the Economies of European Countries in the Period January–September 2020 Based on Economic Indicators","year":2021,"lang":"en","type":"book-chapter","venue":"Studies in classification, data analysis, and knowledge organization","topic":"COVID-19 Pandemic Impacts","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Pandemic; Coronavirus disease 2019 (COVID-19); Limiting; Economic indicator; Geography; Period (music); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Development economics; Economic impact analysis; Economy; Economics; Disease; Medicine; Macroeconomics; Infectious disease (medical specialty)","score_opus":0.1176783749140545,"score_gpt":0.3409317114051785,"score_spread":0.22325333649112397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174761163","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21944,0.09294524,0.0023673952,0.055639293,0.0035649822,0.009088084,0.029555853,0.000189545,0.5872096],"genre_scores_gemma":[0.9759151,0.019337859,0.0000041047824,0.00045087075,0.00013793539,0.000015324054,0.0007394806,0.000045542336,0.0033537948],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.997267,0.0003267775,0.0013727976,0.0007246792,0.00009623781,0.00021248905],"domain_scores_gemma":[0.99373084,0.0022646186,0.0016748077,0.0021568213,0.00012588926,0.000047016336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036305222,0.0003604371,0.0008283837,0.00057951873,0.0004895579,0.0001166319,0.001323791,0.00016219434,0.00022858904],"category_scores_gemma":[0.0031260708,0.00020815487,0.00018321726,0.0010011336,0.0009492978,0.00012806286,0.00038675085,0.00038576254,0.000054650936],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030468565,0.00006901775,0.86853915,0.00011226029,0.0013544303,8.3290007e-7,0.0050520217,0.001148948,8.972982e-7,0.10318628,0.020332426,0.0001732906],"study_design_scores_gemma":[0.0010019366,0.00010331045,0.7476545,0.0002085866,0.0007622914,0.0000039814886,0.0029408103,0.006481159,0.0000062773297,0.005618018,0.23453398,0.0006851784],"about_ca_topic_score_codex":0.00021602146,"about_ca_topic_score_gemma":0.006314029,"teacher_disagreement_score":0.7564751,"about_ca_system_score_codex":0.0009432898,"about_ca_system_score_gemma":0.0006556801,"threshold_uncertainty_score":0.84883094},"labels":[],"label_agreement":null},{"id":"W4389449482","doi":"10.1007/978-3-031-09034-9_12","title":"PcTVI: Parallel MDP Solver Using a Decomposition into Independent Chains","year":2023,"lang":"en","type":"book-chapter","venue":"Studies in classification, data analysis, and knowledge organization","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Speedup; Dependency (UML); Probabilistic logic; Markov decision process; Markov chain; Solver; Domain (mathematical analysis); Decomposition; Parallel computing; Mathematical optimization; Algorithm; Markov process; Mathematics; Artificial intelligence; Machine learning","score_opus":0.2049655389049641,"score_gpt":0.39508244309424584,"score_spread":0.19011690418928173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389449482","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010118319,0.002834676,0.99280304,0.0003242102,0.00054135325,0.00023228819,0.00006579124,0.0002080364,0.0028894194],"genre_scores_gemma":[0.63737774,0.12505645,0.105838,0.00039293125,0.0022443838,0.00008113834,0.020488815,0.00045513193,0.10806542],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971807,0.00009347,0.00078332436,0.0013450162,0.0003460691,0.00025141222],"domain_scores_gemma":[0.99678963,0.00013754767,0.00043688956,0.0015761211,0.000967125,0.00009269138],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00073741184,0.00039681792,0.0006559293,0.0010214619,0.0004631021,0.00023357269,0.0010782551,0.00031834628,0.0000143672805],"category_scores_gemma":[0.00020545705,0.00040482654,0.00006088173,0.0017246845,0.00020543698,0.00060116337,0.0014012135,0.00030914776,0.00007398969],"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":[0.000010196042,0.00019189242,0.008331041,0.00046311706,0.0037061076,0.0000140870925,0.010820025,0.00075469445,0.00025133346,0.9528865,0.0051283357,0.017442627],"study_design_scores_gemma":[0.00053536665,0.00004505379,0.0088900635,0.000564075,0.0022826802,0.000010714236,0.00047257502,0.923246,0.000022830205,0.059031587,0.0035478969,0.0013511549],"about_ca_topic_score_codex":0.00008786112,"about_ca_topic_score_gemma":0.002988908,"teacher_disagreement_score":0.9224913,"about_ca_system_score_codex":0.00029195074,"about_ca_system_score_gemma":0.0002802591,"threshold_uncertainty_score":0.9998404},"labels":[],"label_agreement":null},{"id":"W4389449640","doi":"10.1007/978-3-031-09034-9_41","title":"New Metrics for Classifying Phylogenetic Trees Using K-means and the Symmetric Difference Metric","year":2023,"lang":"en","type":"book-chapter","venue":"Studies in classification, data analysis, and knowledge organization","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Compute Canada; Université de Sherbrooke","keywords":"Cluster analysis; Mathematics; Metric (unit); Silhouette; Phylogenetic tree; Partition (number theory); Metric space; Tree (set theory); Embedding; Euclidean distance; Artificial intelligence; Combinatorics; Pattern recognition (psychology); Computer science; Discrete mathematics; Biology","score_opus":0.13224942923258398,"score_gpt":0.3409427669056752,"score_spread":0.20869333767309123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389449640","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014456274,0.6873576,0.28115684,0.0009774349,0.0020003214,0.0039988714,0.0025512953,0.00007374007,0.0074276035],"genre_scores_gemma":[0.5472477,0.39701384,0.005137245,0.00006327668,0.0010382336,0.000044740646,0.0037963656,0.00018576613,0.04547281],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9979378,0.00007638421,0.00060130475,0.0009944813,0.00016182079,0.00022818221],"domain_scores_gemma":[0.99756,0.00045745773,0.0003995235,0.00090067287,0.00061644026,0.000065868204],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00067855115,0.00038162933,0.0007138553,0.0010075833,0.00042137667,0.00008139256,0.0004441375,0.000260209,0.0000024589544],"category_scores_gemma":[0.0018019311,0.00030288813,0.00008471385,0.0021955604,0.00039671938,0.000003784897,0.0008698984,0.000121910285,0.0000018602187],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039257493,0.0003050674,0.38414145,0.0024097448,0.05517584,0.0000045413353,0.006544597,0.0007322704,0.017081374,0.2581348,0.015415684,0.25966206],"study_design_scores_gemma":[0.013034017,0.0006724985,0.590171,0.0006287489,0.06138775,0.000030925927,0.0040967194,0.10979476,0.0011626289,0.054422937,0.15849991,0.0060980995],"about_ca_topic_score_codex":0.000045898647,"about_ca_topic_score_gemma":0.0022202116,"teacher_disagreement_score":0.53279144,"about_ca_system_score_codex":0.000057049907,"about_ca_system_score_gemma":0.00017309505,"threshold_uncertainty_score":0.9999423},"labels":[],"label_agreement":null},{"id":"W4389449694","doi":"10.1007/978-3-031-09034-9_2","title":"Model Based Clustering of Functional Data with Mild Outliers","year":2023,"lang":"en","type":"book-chapter","venue":"Studies in classification, data analysis, and knowledge organization","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University","funders":"","keywords":"Outlier; Cluster analysis; Computer science; Multivariate statistics; Data mining; Functional data analysis; CURE data clustering algorithm; Pattern recognition (psychology); Artificial intelligence; Correlation clustering; Machine learning","score_opus":0.24569123234731524,"score_gpt":0.36175186103108525,"score_spread":0.11606062868377001,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389449694","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":[0.0000016015905,0.0012814308,0.9922797,0.00027278627,0.00018601038,0.00018617543,0.0004835788,0.00008093536,0.0052277655],"genre_scores_gemma":[0.031763025,0.018972622,0.82544327,0.00017769297,0.00046918425,0.000028193575,0.033598594,0.0002459153,0.08930153],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974398,0.0000761541,0.0006415103,0.0013414738,0.00032785317,0.00017319771],"domain_scores_gemma":[0.9952469,0.00022241591,0.0004531123,0.0031624013,0.0008534057,0.00006177086],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010473046,0.0003190917,0.00067253294,0.0008218217,0.00019556186,0.00007184557,0.0014806368,0.00018731167,0.000008902075],"category_scores_gemma":[0.00027794065,0.0002799185,0.00003308734,0.0015913127,0.00026281513,0.0005286716,0.0017295873,0.00020266516,0.000006968673],"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":[0.000063826206,0.0003109808,0.0089727165,0.0018253094,0.009053992,0.000009915544,0.004788445,0.00708527,0.0001116522,0.87344426,0.03556982,0.058763824],"study_design_scores_gemma":[0.00027610525,0.00001513076,0.0015934157,0.0001688792,0.001138381,9.4308535e-7,0.000050729257,0.98805666,0.0000051066795,0.007095604,0.001265369,0.00033367032],"about_ca_topic_score_codex":0.00001270735,"about_ca_topic_score_gemma":0.0021570688,"teacher_disagreement_score":0.9809714,"about_ca_system_score_codex":0.00008051838,"about_ca_system_score_gemma":0.00038611775,"threshold_uncertainty_score":0.9999653},"labels":[],"label_agreement":null},{"id":"W4389449699","doi":"10.1007/978-3-031-09034-9_10","title":"Using Clustering and Machine Learning Methods to Provide Intelligent Grocery Shopping Recommendations","year":2023,"lang":"en","type":"book-chapter","venue":"Studies in classification, data analysis, and knowledge organization","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke; McGill University; Mila - Quebec Artificial Intelligence Institute; Université du Québec à Montréal","funders":"","keywords":"Computer science; Recommender system; Naive Bayes classifier; Machine learning; Cluster analysis; Popularity; Random forest; Decision tree; Grocery shopping; Artificial intelligence; Grocery store; Tree (set theory); Support vector machine; Marketing; Business; Mathematics","score_opus":0.3711693618150535,"score_gpt":0.44725872421160895,"score_spread":0.07608936239655545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389449699","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":[0.000007244562,0.0035710884,0.9922395,0.0008259735,0.0003725875,0.00037530178,0.000034764285,0.0002493679,0.0023242102],"genre_scores_gemma":[0.020791719,0.10580509,0.8073844,0.0002346923,0.0007027877,0.00009934129,0.0047530844,0.0003202506,0.05990867],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997431,0.00022287417,0.0008531424,0.0011331135,0.00015284547,0.00020702172],"domain_scores_gemma":[0.997604,0.0003649669,0.00042252897,0.0009821748,0.0005379234,0.000088394074],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001781058,0.0003361061,0.00067021395,0.00139616,0.00050200964,0.00028184976,0.0006345307,0.0001670646,0.000007678065],"category_scores_gemma":[0.0007202792,0.00033715187,0.000037848797,0.0017856694,0.000076241515,0.0005088435,0.0025307774,0.0002884335,0.000007580776],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000081281305,0.00011359382,0.036929063,0.0017200649,0.0055600195,0.00000894117,0.02327028,0.00027525588,0.00041050944,0.2209494,0.006693843,0.7040609],"study_design_scores_gemma":[0.00025653097,0.00007220212,0.0029255424,0.0015004281,0.0017237032,0.00002480681,0.0017019201,0.7016984,0.00014328083,0.0064803204,0.281918,0.0015548506],"about_ca_topic_score_codex":0.0000951486,"about_ca_topic_score_gemma":0.0030485871,"teacher_disagreement_score":0.70250607,"about_ca_system_score_codex":0.00022981399,"about_ca_system_score_gemma":0.00008844187,"threshold_uncertainty_score":0.99990803},"labels":[],"label_agreement":null},{"id":"W4402728835","doi":"10.1007/978-3-031-55917-4_2","title":"Statistical Profiling of Hybrid CNN-SVM Effectiveness","year":2024,"lang":"en","type":"book-chapter","venue":"Studies in classification, data analysis, and knowledge organization","topic":"Neural Networks and Applications","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 du Québec à Trois-Rivières","funders":"","keywords":"Profiling (computer programming); Support vector machine; Computer science; Artificial intelligence; Pattern recognition (psychology); Machine learning; Operating system","score_opus":0.09016797561016919,"score_gpt":0.361576834046765,"score_spread":0.2714088584365958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402728835","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022644851,0.014914892,0.9646396,0.00029857105,0.0005354502,0.00072060444,0.00084074086,0.00017183123,0.01765188],"genre_scores_gemma":[0.90708756,0.03726397,0.017224576,0.00003500757,0.00059691956,0.00008202342,0.012858467,0.00013930212,0.024712186],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99787575,0.00006706764,0.00064496446,0.0010544095,0.00020374377,0.00015406865],"domain_scores_gemma":[0.99720645,0.00048810692,0.00027730144,0.001298627,0.0006768572,0.000052650477],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005684991,0.0002736515,0.0006278554,0.00048464764,0.00015975884,0.000094189796,0.0007597592,0.00009319761,0.000014218161],"category_scores_gemma":[0.00019424927,0.00024979503,0.000042240685,0.0013921409,0.0002835004,0.00024446548,0.0009887494,0.00022309895,0.000035693483],"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":[0.0000021300204,0.000048105543,0.0027473308,0.00052713533,0.00091040425,0.0000037057835,0.00019516576,0.000024683673,0.000080916354,0.989366,0.0016095458,0.0044849007],"study_design_scores_gemma":[0.0011627327,0.0001990099,0.04792907,0.0025634104,0.0125315925,0.00003823056,0.00039153843,0.3828809,0.002516312,0.46414924,0.0823662,0.0032717679],"about_ca_topic_score_codex":0.0000094195875,"about_ca_topic_score_gemma":0.00013709589,"teacher_disagreement_score":0.947415,"about_ca_system_score_codex":0.0000946428,"about_ca_system_score_gemma":0.00012985106,"threshold_uncertainty_score":0.9999954},"labels":[],"label_agreement":null},{"id":"W4409589658","doi":"10.1007/978-3-031-85870-3_1","title":"A Comparison of Multivariate Mixed Models and Generalized Estimation Equations Models for Discrimination in Multivariate Longitudinal Data","year":2025,"lang":"en","type":"book-chapter","venue":"Studies in classification, data analysis, and knowledge organization","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 Manitoba; University of Calgary","funders":"","keywords":"Multivariate statistics; Longitudinal data; Multivariate analysis; Statistics; Estimation; Mathematics; Generalized estimating equation; Econometrics; Applied mathematics; Computer science; Data mining; Engineering","score_opus":0.5617459231948173,"score_gpt":0.5386650628968298,"score_spread":0.023080860297987504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409589658","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":[0.000053327472,0.0020713462,0.99304986,0.00013004488,0.00011621239,0.0009797311,0.0027741091,0.000032416006,0.0007929359],"genre_scores_gemma":[0.2332616,0.004957928,0.73088527,0.000006309779,0.0000641898,0.00008917005,0.026696427,0.000075898795,0.003963227],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99656314,0.0002022884,0.0015740996,0.0012191641,0.00023566795,0.000205663],"domain_scores_gemma":[0.99372804,0.00273728,0.0009053262,0.00140127,0.0011731233,0.000054975837],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014082612,0.00040358843,0.0013601466,0.00087912986,0.00022840149,0.00004940253,0.00046339593,0.00027509715,0.0000049567375],"category_scores_gemma":[0.0058918097,0.00039452635,0.00004073585,0.000760757,0.0002604353,0.00076645013,0.0008048074,0.00020149378,3.0682742e-7],"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":[0.00003698289,0.0002257219,0.000328283,0.0010804922,0.0008586182,2.5977275e-7,0.0027033014,0.0036065176,0.000028152426,0.97431165,0.00032034126,0.016499687],"study_design_scores_gemma":[0.0005355085,0.0000124911785,0.00037828166,0.00026640613,0.0019767242,1.3931178e-7,0.00021780308,0.5999457,0.000006723279,0.39640376,0.000049678245,0.00020675448],"about_ca_topic_score_codex":0.00010717291,"about_ca_topic_score_gemma":0.0055952286,"teacher_disagreement_score":0.5963392,"about_ca_system_score_codex":0.00016086725,"about_ca_system_score_gemma":0.00015909648,"threshold_uncertainty_score":0.9998507},"labels":[],"label_agreement":null},{"id":"W4409589724","doi":"10.1007/978-3-031-85870-3_2","title":"A Multivariate Functional Data Clustering Method Using Parsimonious Cluster Weighted Models","year":2025,"lang":"en","type":"book-chapter","venue":"Studies in classification, data analysis, and knowledge organization","topic":"Bayesian Methods and Mixture Models","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 Alberta; MacEwan University","funders":"","keywords":"Multivariate statistics; Cluster analysis; Cluster (spacecraft); Computer science; Data mining; Statistics; Artificial intelligence; Mathematics","score_opus":0.23402062003701513,"score_gpt":0.4014019355760586,"score_spread":0.16738131553904345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409589724","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":[8.78704e-7,0.006060737,0.98350406,0.00032009702,0.00063163514,0.00037101336,0.00045042436,0.000112765876,0.008548406],"genre_scores_gemma":[0.0019266764,0.010212811,0.94921666,0.0001626569,0.00040966942,0.000011526689,0.008782639,0.00007478039,0.02920258],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956095,0.00037689615,0.0010494818,0.0023184053,0.00033734165,0.0003083467],"domain_scores_gemma":[0.9935202,0.00052405504,0.0005837509,0.0041555683,0.0011225631,0.000093840885],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0020122402,0.000547651,0.0010358028,0.0011992088,0.00049617887,0.00025121772,0.0021131835,0.00040362668,0.000018214],"category_scores_gemma":[0.0003991408,0.0005245975,0.00006627733,0.001978297,0.00016970279,0.0013343664,0.0056699887,0.0003961826,0.000006285655],"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":[0.000039365324,0.00026559675,0.0009786524,0.00092269114,0.01024535,0.000012721651,0.0046652537,0.0011850455,0.00010223711,0.8037777,0.018936228,0.15886915],"study_design_scores_gemma":[0.00036454786,0.0000064958463,0.00025319296,0.00021072569,0.0020409015,0.0000057704833,0.00003892414,0.94869626,0.0000047517924,0.041339554,0.0065483563,0.00049052323],"about_ca_topic_score_codex":0.00008537967,"about_ca_topic_score_gemma":0.001394296,"teacher_disagreement_score":0.9475112,"about_ca_system_score_codex":0.00025909414,"about_ca_system_score_gemma":0.00046185357,"threshold_uncertainty_score":0.9997206},"labels":[],"label_agreement":null},{"id":"W4409589738","doi":"10.1007/978-3-031-85870-3_12","title":"Machine Learning-Based Classification and Prediction to Assess Corrosion Degradation in Mining Pipelines","year":2025,"lang":"en","type":"book-chapter","venue":"Studies in classification, data analysis, and knowledge organization","topic":"Non-Destructive Testing Techniques","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Corrosion; Degradation (telecommunications); Pipeline transport; Computer science; Mining engineering; Engineering; Environmental science; Materials science; Metallurgy; Environmental engineering","score_opus":0.10917706673818618,"score_gpt":0.3369107185685346,"score_spread":0.22773365183034844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409589738","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010464028,0.01814344,0.9257553,0.00063512,0.0012789344,0.002904079,0.0015019114,0.002539866,0.036777318],"genre_scores_gemma":[0.8352674,0.035824757,0.07986333,0.000049632807,0.00034786062,0.0001659054,0.04041788,0.00029458854,0.007768618],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977495,0.00010624968,0.0008625165,0.0008941816,0.00020326098,0.00018426041],"domain_scores_gemma":[0.99786705,0.00038175462,0.00026256093,0.0007068138,0.00072163896,0.000060183163],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00076439715,0.0004158335,0.00063115475,0.0019410187,0.00020031362,0.00008607344,0.0002782008,0.00031598881,0.000010887964],"category_scores_gemma":[0.0016097812,0.00046176132,0.000025751548,0.0019143919,0.00014334844,0.0003058803,0.00024563423,0.0003548352,0.000003587119],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030182366,0.00009825353,0.9515477,0.0014057198,0.0005250488,0.0000025199402,0.0014264862,0.0007816564,0.0021755877,0.025302973,0.0038040932,0.012899775],"study_design_scores_gemma":[0.00079367077,0.00008521545,0.37677944,0.001991718,0.0022279709,0.00000364533,0.00060138426,0.6043771,0.0002152857,0.005430691,0.0062846686,0.0012091814],"about_ca_topic_score_codex":0.000034940676,"about_ca_topic_score_gemma":0.003166799,"teacher_disagreement_score":0.84589195,"about_ca_system_score_codex":0.00046000766,"about_ca_system_score_gemma":0.00010360617,"threshold_uncertainty_score":0.9997834},"labels":[],"label_agreement":null},{"id":"W4409589740","doi":"10.1007/978-3-031-85870-3_4","title":"Predicting Soil Bacterial and Fungal Communities at Different Taxonomic Levels Using Machine Learning","year":2025,"lang":"en","type":"book-chapter","venue":"Studies in classification, data analysis, and knowledge organization","topic":"Genomics and Phylogenetic Studies","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":"Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Biology","score_opus":0.09552162689760141,"score_gpt":0.3075578810994994,"score_spread":0.21203625420189798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409589740","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9379636,0.05279674,0.0013618917,0.000076562734,0.00054268824,0.00043414565,0.0019578228,0.000018842888,0.004847706],"genre_scores_gemma":[0.9299156,0.050738472,0.00018487951,0.000011840094,0.00029872355,0.000006336755,0.0069363303,0.000038025257,0.011869797],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986395,0.00009821904,0.00046950753,0.0005667298,0.00007235857,0.0001536565],"domain_scores_gemma":[0.9986885,0.00008031388,0.0003001208,0.0005930126,0.00030116554,0.000036870955],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00023313401,0.00032636028,0.0005341807,0.00024131304,0.0005167341,0.000059663853,0.00022888626,0.00021036262,0.00001840628],"category_scores_gemma":[0.00018094762,0.00032148673,0.000039379633,0.00014675579,0.00029530245,0.0000047070716,0.0017561082,0.00015687864,8.579417e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004331304,0.000048926733,0.96665984,0.00037455038,0.0054138056,6.7499184e-7,0.0017340694,0.000052339758,0.022287535,0.0013133638,0.0005131906,0.0015583887],"study_design_scores_gemma":[0.0048481547,0.0004875556,0.65734226,0.0012955558,0.023412181,0.000045181445,0.008730507,0.06305741,0.007347409,0.0009403677,0.22768007,0.00481333],"about_ca_topic_score_codex":0.00010342067,"about_ca_topic_score_gemma":0.014719748,"teacher_disagreement_score":0.30931756,"about_ca_system_score_codex":0.00009096772,"about_ca_system_score_gemma":0.000068053894,"threshold_uncertainty_score":0.9999237},"labels":[],"label_agreement":null},{"id":"W4409589766","doi":"10.1007/978-3-031-85870-3_10","title":"A New Metric to Classify B Cell Lineage Tree","year":2025,"lang":"en","type":"book-chapter","venue":"Studies in classification, data analysis, and knowledge organization","topic":"Chronic Lymphocytic Leukemia Research","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":"Université de Sherbrooke","funders":"","keywords":"Tree (set theory); Lineage (genetic); Metric (unit); Mathematics; Computer science; Combinatorics; Biology; Engineering; Genetics; Operations management","score_opus":0.10949832859698225,"score_gpt":0.3967340030190539,"score_spread":0.28723567442207165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409589766","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":[0.00023222725,0.08879624,0.09071363,0.0034072,0.0011904592,0.003811441,0.0010168044,0.00041098954,0.810421],"genre_scores_gemma":[0.019528948,0.050470203,0.00391779,0.00017681837,0.00084363995,0.000021650832,0.011016887,0.000116301926,0.91390777],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965364,0.000071606366,0.0010207363,0.0014968601,0.0005291743,0.0003452344],"domain_scores_gemma":[0.9950742,0.0004919247,0.0003001195,0.0023364837,0.0015141234,0.0002831641],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00068451394,0.0004923388,0.0013143613,0.0032744354,0.00020161431,0.00007792946,0.0006158037,0.0004548649,0.0003230414],"category_scores_gemma":[0.0025144457,0.00045784382,0.00010051729,0.005746497,0.0002033302,0.00014593721,0.0012240745,0.00044518273,0.00021400682],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00017463566,0.00043117494,0.013067696,0.0036361434,0.010451919,0.00006865609,0.0037654042,0.000011664614,0.0001742499,0.031292766,0.87401056,0.06291512],"study_design_scores_gemma":[0.009238291,0.00022614225,0.01433043,0.001404103,0.02096016,0.000020466703,0.0010084086,0.01366776,0.0004164636,0.0006823517,0.93662554,0.0014198598],"about_ca_topic_score_codex":0.00021855008,"about_ca_topic_score_gemma":0.005777258,"teacher_disagreement_score":0.10348676,"about_ca_system_score_codex":0.005866557,"about_ca_system_score_gemma":0.007073031,"threshold_uncertainty_score":0.99978733},"labels":[],"label_agreement":null},{"id":"W4409589849","doi":"10.1007/978-3-031-85870-3_7","title":"Towards Topologically Diverse Probabilistic Planning Benchmarks: Synthetic Domain Generation for Markov Decision Processes","year":2025,"lang":"en","type":"book-chapter","venue":"Studies in classification, data analysis, and knowledge organization","topic":"AI-based Problem Solving and Planning","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 du Québec à Montréal","funders":"","keywords":"Probabilistic logic; Markov chain; Computer science; Domain (mathematical analysis); Markov decision process; Artificial intelligence; Markov model; Markov process; Machine learning; Mathematics; Statistics","score_opus":0.11060220816994146,"score_gpt":0.35399534880204786,"score_spread":0.2433931406321064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409589849","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":[0.000098490025,0.010170141,0.9794088,0.0004410132,0.00045053405,0.0006767258,0.00030379355,0.000110614536,0.008339868],"genre_scores_gemma":[0.24024011,0.042176906,0.59388036,0.00043437714,0.001974361,0.00045064732,0.068740144,0.00020479763,0.051898316],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972109,0.00009896674,0.00078463915,0.0014053478,0.0002581533,0.00024195183],"domain_scores_gemma":[0.99579024,0.0009783756,0.00046028013,0.0011972768,0.0015110133,0.000062823725],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012164547,0.00038833704,0.0006629812,0.0007479044,0.00066508655,0.00024209537,0.0010064372,0.00030471283,0.000029289919],"category_scores_gemma":[0.003524355,0.00034971215,0.000052791955,0.0014325167,0.00020289469,0.0004121254,0.0008540456,0.00019817571,0.0000040457453],"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":[0.0000807936,0.00035991851,0.018231498,0.0044167675,0.003990427,0.000018687999,0.012738406,0.0011290851,0.00007273601,0.7323567,0.0848663,0.14173867],"study_design_scores_gemma":[0.0024831758,0.00049552263,0.009719544,0.0065203784,0.009417342,0.000021565238,0.0024001936,0.5272398,0.000089984096,0.2825201,0.15470457,0.0043878523],"about_ca_topic_score_codex":0.000011353106,"about_ca_topic_score_gemma":0.00059206213,"teacher_disagreement_score":0.5261107,"about_ca_system_score_codex":0.00021450831,"about_ca_system_score_gemma":0.00056690664,"threshold_uncertainty_score":0.9998955},"labels":[],"label_agreement":null},{"id":"W44614705","doi":"10.1007/978-3-642-59789-3_24","title":"Estimating Trees From Incomplete Distance Matrices: A Comparison of Two Methods","year":2000,"lang":"en","type":"book-chapter","venue":"Studies in classification, data analysis, and knowledge organization","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Path (computing); Distance matrices in phylogeny; Algorithm; Mathematics; Tree (set theory); Combinatorics; Computer science; Topology (electrical circuits)","score_opus":0.17093780995420788,"score_gpt":0.45570590503897723,"score_spread":0.28476809508476936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W44614705","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":[0.00002203099,0.009795281,0.9816335,0.000079880236,0.00020660936,0.00015941498,0.00073592016,0.000085891224,0.007281514],"genre_scores_gemma":[0.09074197,0.035532754,0.81637895,0.000101246296,0.0006657182,0.00001617289,0.042886723,0.00015362613,0.013522839],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968378,0.00020322212,0.0013532332,0.0011209667,0.0003098483,0.00017491738],"domain_scores_gemma":[0.9956508,0.00053890754,0.0010643022,0.0019439133,0.0007330839,0.000068963505],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007162126,0.00037108533,0.0011348813,0.0008112105,0.0002493154,0.00017115909,0.001486184,0.0001485973,0.00008292391],"category_scores_gemma":[0.0005150516,0.00036364608,0.000060618524,0.0023492977,0.00030733144,0.0005974586,0.0009664741,0.00018993493,0.000020431824],"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":[0.000010607321,0.00041185273,0.061788004,0.00053939223,0.004948125,0.0000032607174,0.012957416,0.0007217086,0.000087281915,0.75636786,0.008026379,0.1541381],"study_design_scores_gemma":[0.00038766966,0.000020077916,0.003875439,0.00038153742,0.0021065057,6.9643545e-7,0.00029382843,0.93853325,0.000034548586,0.021453263,0.03232191,0.0005912768],"about_ca_topic_score_codex":0.00009641857,"about_ca_topic_score_gemma":0.0029285776,"teacher_disagreement_score":0.93781155,"about_ca_system_score_codex":0.00011065722,"about_ca_system_score_gemma":0.00014347036,"threshold_uncertainty_score":0.99988157},"labels":[],"label_agreement":null},{"id":"W5960048","doi":"10.1007/978-3-642-24466-7_10","title":"Reduced Versus Complete Space Configurations in Total Information Analysis","year":2012,"lang":"en","type":"book-chapter","venue":"Studies in classification, data analysis, and knowledge organization","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"GRASP; Dimension (graph theory); Point (geometry); Space (punctuation); Dimensionality reduction; Computer science; Key (lock); Reduction (mathematics); Information space; Data mining; Algorithm; Theoretical computer science; Mathematics; Artificial intelligence; Pure mathematics; Geometry","score_opus":0.13295365760318625,"score_gpt":0.3403312368409699,"score_spread":0.20737757923778363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W5960048","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025552805,0.018972602,0.7811196,0.0037434432,0.003262919,0.0025322542,0.0027164428,0.00068623066,0.18441124],"genre_scores_gemma":[0.8721422,0.03440936,0.007587027,0.00010487782,0.00046026293,0.000077376346,0.07047306,0.00007091111,0.014674958],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99763685,0.0001151118,0.0009539219,0.0007281355,0.00031333082,0.00025264817],"domain_scores_gemma":[0.99667233,0.0002613816,0.00059840526,0.0014062775,0.0009708534,0.00009073004],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00060788833,0.00034895822,0.00074436114,0.0024563554,0.00028149222,0.0002112497,0.00064209994,0.00027171854,0.00011343998],"category_scores_gemma":[0.0004751393,0.00035408293,0.00008141452,0.004137472,0.00016745883,0.0021640393,0.00061170635,0.0002645457,0.00015330929],"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":[0.000107273976,0.00057901494,0.034094527,0.0006967817,0.021579936,0.0000067701935,0.034113463,0.00076385704,0.0007758111,0.81570464,0.025794458,0.06578345],"study_design_scores_gemma":[0.005778521,0.00018472118,0.4250054,0.0008275971,0.030979281,0.000012579588,0.006076311,0.32698232,0.00029698116,0.008262098,0.19054595,0.0050482345],"about_ca_topic_score_codex":0.00006382557,"about_ca_topic_score_gemma":0.002358689,"teacher_disagreement_score":0.8695869,"about_ca_system_score_codex":0.00023531335,"about_ca_system_score_gemma":0.00015420358,"threshold_uncertainty_score":0.9998911},"labels":[],"label_agreement":null},{"id":"W65262223","doi":"10.1007/3-540-34416-0_26","title":"Comparison of Two Methods for Detecting and Correcting Systematic Error in High-throughput Screening Data","year":2006,"lang":"en","type":"book-chapter","venue":"Studies in classification, data analysis, and knowledge organization","topic":"Computational Drug Discovery Methods","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":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Throughput; Selection (genetic algorithm); Systematic error; High-throughput screening; Process (computing); Drug discovery; Data mining; Machine learning; Bioinformatics; Statistics; Mathematics; Biology","score_opus":0.29446445114873876,"score_gpt":0.5011863299425744,"score_spread":0.20672187879383563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W65262223","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":[0.00023270851,0.012655564,0.98549485,0.00006587626,0.00030592532,0.00068094314,0.00014736135,0.000045743247,0.00037100064],"genre_scores_gemma":[0.19947043,0.0009756677,0.79413354,0.000011726144,0.00017922929,0.00003100707,0.004134496,0.00006955045,0.0009943603],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99581486,0.00058566546,0.0016935894,0.0014499333,0.00024432494,0.00021164087],"domain_scores_gemma":[0.991371,0.0043626535,0.0013873187,0.001951854,0.0008870076,0.00004021307],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004854914,0.00036467856,0.0015295501,0.0011020803,0.00027361038,0.00014498056,0.0013246824,0.00015333683,0.0000016358665],"category_scores_gemma":[0.0043577473,0.00037177265,0.000040199826,0.0018714879,0.00019813604,0.0007983188,0.002461759,0.0002396232,6.9979086e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000548053,0.0007348779,0.24106975,0.053314637,0.010365735,0.0000055751334,0.028641077,0.025175998,0.00028106096,0.27860087,0.002285462,0.35947016],"study_design_scores_gemma":[0.00044082024,0.000020519123,0.007276496,0.0020453942,0.0015034865,0.000003697549,0.0007386891,0.9812908,0.00005023115,0.0060805297,0.0001474499,0.0004018819],"about_ca_topic_score_codex":0.00015977543,"about_ca_topic_score_gemma":0.0036190713,"teacher_disagreement_score":0.9561148,"about_ca_system_score_codex":0.00015163606,"about_ca_system_score_gemma":0.00015859921,"threshold_uncertainty_score":0.9998734},"labels":[],"label_agreement":null},{"id":"W73449135","doi":"10.1007/978-3-319-01264-3_7","title":"Structural Representation of Categorical Data and Cluster Analysis Through Filters","year":2013,"lang":"en","type":"book-chapter","venue":"Studies in classification, data analysis, and knowledge organization","topic":"Sensory Analysis and Statistical Methods","field":"Agricultural and Biological Sciences","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Categorical variable; Dimensionality reduction; Dimension (graph theory); Representation (politics); Data reduction; Multidimensional scaling; Mathematics; Simple (philosophy); Reduction (mathematics); Space (punctuation); Cluster (spacecraft); Algorithm; Scaling; Data analysis; Computer science; Data mining; Statistics; Artificial intelligence; Pure mathematics","score_opus":0.2617969241649431,"score_gpt":0.3981748959171858,"score_spread":0.1363779717522427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W73449135","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35045022,0.14180854,0.27786836,0.02019933,0.0036610365,0.0101477,0.06421097,0.0009546162,0.13069923],"genre_scores_gemma":[0.87205553,0.029300407,0.0059475927,0.00008826253,0.0004198802,0.0000092224755,0.0774576,0.000012250758,0.014709252],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9970672,0.000275473,0.0009445167,0.0012700929,0.0002692512,0.00017347648],"domain_scores_gemma":[0.996706,0.0011044664,0.00058892264,0.0008179707,0.00071068853,0.00007192313],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000568084,0.00031522417,0.0011269848,0.00021454031,0.00024657496,0.00009121584,0.0006142154,0.00023710322,0.00052744936],"category_scores_gemma":[0.0012143055,0.00015823764,0.000079267156,0.0026265134,0.00047235604,0.0004219675,0.0009122728,0.00017519896,0.000007654152],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009990547,0.00030390144,0.5359498,0.0006254252,0.05131573,0.000009258148,0.006010867,0.000099168254,0.0018056164,0.16120373,0.026491294,0.2160853],"study_design_scores_gemma":[0.00042589506,0.00010184922,0.8017047,0.00007726774,0.042347144,0.0000052392975,0.0030315404,0.1121164,0.000049974307,0.02319254,0.015691478,0.0012559784],"about_ca_topic_score_codex":0.0004354316,"about_ca_topic_score_gemma":0.0069557857,"teacher_disagreement_score":0.5216053,"about_ca_system_score_codex":0.000044607204,"about_ca_system_score_gemma":0.000018043082,"threshold_uncertainty_score":0.6452744},"labels":[],"label_agreement":null},{"id":"W978183862","doi":"10.1007/978-3-662-44983-7_27","title":"Effect of Hundreds Sequenced Genomes on the Classification of Human Papillomaviruses","year":2015,"lang":"en","type":"book-chapter","venue":"Studies in classification, data analysis, and knowledge organization","topic":"Cervical Cancer and HPV Research","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Phylogenetic tree; Genome; Similarity (geometry); Monophyly; Biology; Computational biology; Identification (biology); Tree (set theory); Gene; Genetics; Evolutionary biology; Clade; Artificial intelligence; Computer science; Mathematics; Combinatorics","score_opus":0.2811387688556453,"score_gpt":0.46097352536653535,"score_spread":0.17983475651089004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W978183862","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043241892,0.13763627,0.0009333624,0.003026987,0.0007032654,0.0066836714,0.002691858,0.0002338556,0.80484885],"genre_scores_gemma":[0.9617726,0.02006033,0.000019506526,0.0000172858,0.00020006507,0.00002277327,0.0045878226,0.000051701878,0.013267866],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9976245,0.00020608673,0.0008405148,0.0006459687,0.00052820874,0.00015472705],"domain_scores_gemma":[0.9951003,0.0005958545,0.0005343477,0.0015120346,0.0021807607,0.000076677854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016345752,0.0002929865,0.0010634692,0.00073280785,0.00016760734,0.000018222863,0.0004100885,0.00023131887,0.00041434317],"category_scores_gemma":[0.0013638927,0.00020171708,0.00008421689,0.0012866146,0.0008594682,0.00008743833,0.0003019886,0.00029576154,0.00001696715],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010462669,0.0009318256,0.29877308,0.010453315,0.019169537,0.00000874645,0.008631327,0.000009310466,0.013679794,0.47578445,0.03388718,0.13762514],"study_design_scores_gemma":[0.0058095492,0.0040809037,0.8653099,0.0017391988,0.031280212,0.000009193822,0.00316951,0.0020048465,0.008197112,0.010171831,0.06648246,0.0017453085],"about_ca_topic_score_codex":0.00004749745,"about_ca_topic_score_gemma":0.0008433455,"teacher_disagreement_score":0.91853076,"about_ca_system_score_codex":0.00028784815,"about_ca_system_score_gemma":0.00028723793,"threshold_uncertainty_score":0.8225784},"labels":[],"label_agreement":null}]}